Search | arXiv e-print repository

<!DOCTYPE html> <html lang="en"> <head> <meta charset="utf-8"/> <meta name="viewport" content="width=device-width, initial-scale=1"/>  <link rel="apple-touch-icon" sizes="180x180" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/apple-touch-icon.png"> <link rel="icon" type="image/png" sizes="32x32" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon-32x32.png"> <link rel="icon" type="image/png" sizes="16x16" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon-16x16.png"> <link rel="manifest" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/site.webmanifest"> <link rel="mask-icon" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/safari-pinned-tab.svg" color="#b31b1b"> <link rel="shortcut icon" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon.ico"> <meta name="msapplication-TileColor" content="#b31b1b"> <meta name="msapplication-config" content="images/icons/browserconfig.xml"> <meta name="theme-color" content="#b31b1b">  <title>Search | arXiv e-print repository</title> <script defer src="https://static.arxiv.org/static/base/1.0.0a5/fontawesome-free-5.11.2-web/js/all.js"></script> <link rel="stylesheet" href="https://static.arxiv.org/static/base/1.0.0a5/css/arxivstyle.css" /> <script type="text/x-mathjax-config"> MathJax.Hub.Config({ messageStyle: "none", extensions: ["tex2jax.js"], jax: ["input/TeX", "output/HTML-CSS"], tex2jax: { inlineMath: [ ['$','$'], ["\$","\$"] ], displayMath: [ ['$$','$$'], ["\\[","\\]"] ], processEscapes: true, ignoreClass: '.*', processClass: 'mathjax.*' }, TeX: { extensions: ["AMSmath.js", "AMSsymbols.js", "noErrors.js"], noErrors: { inlineDelimiters: ["$","$"], multiLine: false, style: { "font-size": "normal", "border": "" } } }, "HTML-CSS": { availableFonts: ["TeX"] } }); </script> <script src='//static.arxiv.org/MathJax-2.7.3/MathJax.js'></script> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/notification.js"></script> <link rel="stylesheet" href="https://static.arxiv.org/static/search/0.5.6/css/bulma-tooltip.min.css" /> <link rel="stylesheet" href="https://static.arxiv.org/static/search/0.5.6/css/search.css" /> <script src="https://code.jquery.com/jquery-3.2.1.slim.min.js" integrity="sha256-k2WSCIexGzOj3Euiig+TlR8gA0EmPjuc79OEeY5L45g=" crossorigin="anonymous"></script> <script src="https://static.arxiv.org/static/search/0.5.6/js/fieldset.js"></script> <style> radio#cf-customfield_11400 { display: none; } </style> </head> <body> <header><a href="#main-container" class="is-sr-only">Skip to main content</a>  <div class="attribution level is-marginless" role="banner"> <div class="level-left"> <a class="level-item" href="https://cornell.edu/"><img src="https://static.arxiv.org/static/base/1.0.0a5/images/cornell-reduced-white-SMALL.svg" alt="Cornell University" width="200" aria-label="logo" /></a> </div> <div class="level-right is-marginless"><p class="sponsors level-item is-marginless"><span id="support-ack-url">We gratefully acknowledge support from<br /> the Simons Foundation, <a href="https://info.arxiv.org/about/ourmembers.html">member institutions</a>, and all contributors. <a href="https://info.arxiv.org/about/donate.html">Donate</a></span></p></div> </div>  <div class="identity level is-marginless"> <div class="level-left"> <div class="level-item"> <a class="arxiv" href="https://arxiv.org/" aria-label="arxiv-logo"> <img src="https://static.arxiv.org/static/base/1.0.0a5/images/arxiv-logo-one-color-white.svg" aria-label="logo" alt="arxiv logo" width="85" style="width:85px;"/> </a> </div> </div> <div class="search-block level-right"> <form class="level-item mini-search" method="GET" action="https://arxiv.org/search"> <div class="field has-addons"> <div class="control"> <input class="input is-small" type="text" name="query" placeholder="Search..." aria-label="Search term or terms" /> <p class="help"><a href="https://info.arxiv.org/help">Help</a> | <a href="https://arxiv.org/search/advanced">Advanced Search</a></p> </div> <div class="control"> <div class="select is-small"> <select name="searchtype" aria-label="Field to search"> <option value="all" selected="selected">All fields</option> <option value="title">Title</option> <option value="author">Author</option> <option value="abstract">Abstract</option> <option value="comments">Comments</option> <option value="journal_ref">Journal reference</option> <option value="acm_class">ACM classification</option> <option value="msc_class">MSC classification</option> <option value="report_num">Report number</option> <option value="paper_id">arXiv identifier</option> <option value="doi">DOI</option> <option value="orcid">ORCID</option> <option value="author_id">arXiv author ID</option> <option value="help">Help pages</option> <option value="full_text">Full text</option> </select> </div> </div> <input type="hidden" name="source" value="header"> <button class="button is-small is-cul-darker">Search</button> </div> </form> </div> </div>  <div class="container"> <div class="user-tools is-size-7 has-text-right has-text-weight-bold" role="navigation" aria-label="User menu"> <a href="https://arxiv.org/login">Login</a> </div> </div> </header> <main class="container" id="main-container"> <div class="level is-marginless"> <div class="level-left"> <h1 class="title is-clearfix"> Showing 1–50 of 110 results for author: <span class="mathjax">Huo, Y</span> </h1> </div> <div class="level-right is-hidden-mobile">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> <div class="content"> <form method="GET" action="/search/eess" aria-role="search"> Searching in archive <strong>eess</strong>. <a href="/search/?searchtype=author&query=Huo%2C+Y">Search in all archives.</a> <div class="field has-addons-tablet"> <div class="control is-expanded"> <label for="query" class="hidden-label">Search term or terms</label> <input class="input is-medium" id="query" name="query" placeholder="Search term..." type="text" value="Huo, Y"> </div> <div class="select control is-medium"> <label class="is-hidden" for="searchtype">Field</label> <select class="is-medium" id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> </div> <div class="control"> <button class="button is-link is-medium">Search</button> </div> </div> <div class="field"> <div class="control is-size-7"> <label class="radio"> <input checked id="abstracts-0" name="abstracts" type="radio" value="show"> Show abstracts </label> <label class="radio"> <input id="abstracts-1" name="abstracts" type="radio" value="hide"> Hide abstracts </label> </div> </div> <div class="is-clearfix" style="height: 2.5em"> <div class="is-pulled-right"> <a href="/search/advanced?terms-0-term=Huo%2C+Y&terms-0-field=author&size=50&order=-announced_date_first">Advanced Search</a> </div> </div> <input type="hidden" name="order" value="-announced_date_first"> <input type="hidden" name="size" value="50"> </form> <div class="level breathe-horizontal"> <div class="level-left"> <form method="GET" action="/search/"> <div style="display: none;"> <select id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> <input id="query" name="query" type="text" value="Huo, Y"> <ul id="abstracts"><li><input checked id="abstracts-0" name="abstracts" type="radio" value="show"> <label for="abstracts-0">Show abstracts</label></li><li><input id="abstracts-1" name="abstracts" type="radio" value="hide"> <label for="abstracts-1">Hide abstracts</label></li></ul> </div> <div class="box field is-grouped is-grouped-multiline level-item"> <div class="control"> <span class="select is-small"> <select id="size" name="size"><option value="25">25</option><option selected value="50">50</option><option value="100">100</option><option value="200">200</option></select> </span> <label for="size">results per page</label>. </div> <div class="control"> <label for="order">Sort results by</label> <span class="select is-small"> <select id="order" name="order"><option selected value="-announced_date_first">Announcement date (newest first)</option><option value="announced_date_first">Announcement date (oldest first)</option><option value="-submitted_date">Submission date (newest first)</option><option value="submitted_date">Submission date (oldest first)</option><option value="">Relevance</option></select> </span> </div> <div class="control"> <button class="button is-small is-link">Go</button> </div> </div> </form> </div> </div> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Huo%2C+Y&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Huo%2C+Y&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Huo%2C+Y&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Huo%2C+Y&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> </ul> </nav> <ol class="breathe-horizontal" start="1"> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.04199">arXiv:2502.04199</a> <span> [<a href="https://arxiv.org/pdf/2502.04199">pdf</a>, <a href="https://arxiv.org/format/2502.04199">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Expanding Training Data for Endoscopic Phenotyping of Eosinophilic Esophagitis </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Xiong%2C+J">Juming Xiong</a>, <a href="/search/eess?searchtype=author&query=Xiong%2C+H">Hou Xiong</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Q">Quan Liu</a>, <a href="/search/eess?searchtype=author&query=Deng%2C+R">Ruining Deng</a>, <a href="/search/eess?searchtype=author&query=Tyree%2C+R+N">Regina N Tyree</a>, <a href="/search/eess?searchtype=author&query=Hiremath%2C+G">Girish Hiremath</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yuankai Huo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2502.04199v1-abstract-short" style="display: inline;"> Eosinophilic esophagitis (EoE) is a chronic esophageal disorder marked by eosinophil-dominated inflammation. Diagnosing EoE usually involves endoscopic inspection of the esophageal mucosa and obtaining esophageal biopsies for histologic confirmation. Recent advances have seen AI-assisted endoscopic imaging, guided by the EREFS system, emerge as a potential alternative to reduce reliance on invasiv… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.04199v1-abstract-full').style.display = 'inline'; document.getElementById('2502.04199v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.04199v1-abstract-full" style="display: none;"> Eosinophilic esophagitis (EoE) is a chronic esophageal disorder marked by eosinophil-dominated inflammation. Diagnosing EoE usually involves endoscopic inspection of the esophageal mucosa and obtaining esophageal biopsies for histologic confirmation. Recent advances have seen AI-assisted endoscopic imaging, guided by the EREFS system, emerge as a potential alternative to reduce reliance on invasive histological assessments. Despite these advancements, significant challenges persist due to the limited availability of data for training AI models - a common issue even in the development of AI for more prevalent diseases. This study seeks to improve the performance of deep learning-based EoE phenotype classification by augmenting our training data with a diverse set of images from online platforms, public datasets, and electronic textbooks increasing our dataset from 435 to 7050 images. We utilized the Data-efficient Image Transformer for image classification and incorporated attention map visualizations to boost interpretability. The findings show that our expanded dataset and model enhancements improved diagnostic accuracy, robustness, and comprehensive analysis, enhancing patient outcomes. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.04199v1-abstract-full').style.display = 'none'; document.getElementById('2502.04199v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.01832">arXiv:2502.01832</a> <span> [<a href="https://arxiv.org/pdf/2502.01832">pdf</a>, <a href="https://arxiv.org/format/2502.01832">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Medical Physics">physics.med-ph</span> </div> </div> <p class="title is-5 mathjax"> Sparse Measurement Medical CT Reconstruction using Multi-Fused Block Matching Denoising Priors </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Hossain%2C+M">Maliha Hossain</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yuankai Huo</a>, <a href="/search/eess?searchtype=author&query=Yan%2C+X">Xinqiang Yan</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+X">Xiao Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2502.01832v1-abstract-short" style="display: inline;"> A major challenge for medical X-ray CT imaging is reducing the number of X-ray projections to lower radiation dosage and reduce scan times without compromising image quality. However these under-determined inverse imaging problems rely on the formulation of an expressive prior model to constrain the solution space while remaining computationally tractable. Traditional analytical reconstruction met… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.01832v1-abstract-full').style.display = 'inline'; document.getElementById('2502.01832v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.01832v1-abstract-full" style="display: none;"> A major challenge for medical X-ray CT imaging is reducing the number of X-ray projections to lower radiation dosage and reduce scan times without compromising image quality. However these under-determined inverse imaging problems rely on the formulation of an expressive prior model to constrain the solution space while remaining computationally tractable. Traditional analytical reconstruction methods like Filtered Back Projection (FBP) often fail with sparse measurements, producing artifacts due to their reliance on the Shannon-Nyquist Sampling Theorem. Consensus Equilibrium, which is a generalization of Plug and Play, is a recent advancement in Model-Based Iterative Reconstruction (MBIR), has facilitated the use of multiple denoisers are prior models in an optimization free framework to capture complex, non-linear prior information. However, 3D prior modelling in a Plug and Play approach for volumetric image reconstruction requires long processing time due to high computing requirement. Instead of directly using a 3D prior, this work proposes a BM3D Multi Slice Fusion (BM3D-MSF) prior that uses multiple 2D image denoisers fused to act as a fully 3D prior model in Plug and Play reconstruction approach. Our approach does not require training and are thus able to circumvent ethical issues related with patient training data and are readily deployable in varying noise and measurement sparsity levels. In addition, reconstruction with the BM3D-MSF prior achieves similar reconstruction image quality as fully 3D image priors, but with significantly reduced computational complexity. We test our method on clinical CT data and demonstrate that our approach improves reconstructed image quality. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.01832v1-abstract-full').style.display = 'none'; document.getElementById('2502.01832v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 3 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.15368">arXiv:2501.15368</a> <span> [<a href="https://arxiv.org/pdf/2501.15368">pdf</a>, <a href="https://arxiv.org/format/2501.15368">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> </div> </div> <p class="title is-5 mathjax"> Baichuan-Omni-1.5 Technical Report </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Li%2C+Y">Yadong Li</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+J">Jun Liu</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+T">Tao Zhang</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+T">Tao Zhang</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+S">Song Chen</a>, <a href="/search/eess?searchtype=author&query=Li%2C+T">Tianpeng Li</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Z">Zehuan Li</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+L">Lijun Liu</a>, <a href="/search/eess?searchtype=author&query=Ming%2C+L">Lingfeng Ming</a>, <a href="/search/eess?searchtype=author&query=Dong%2C+G">Guosheng Dong</a>, <a href="/search/eess?searchtype=author&query=Pan%2C+D">Da Pan</a>, <a href="/search/eess?searchtype=author&query=Li%2C+C">Chong Li</a>, <a href="/search/eess?searchtype=author&query=Fang%2C+Y">Yuanbo Fang</a>, <a href="/search/eess?searchtype=author&query=Kuang%2C+D">Dongdong Kuang</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+M">Mingrui Wang</a>, <a href="/search/eess?searchtype=author&query=Zhu%2C+C">Chenglin Zhu</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+Y">Youwei Zhang</a>, <a href="/search/eess?searchtype=author&query=Guo%2C+H">Hongyu Guo</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+F">Fengyu Zhang</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+Y">Yuran Wang</a>, <a href="/search/eess?searchtype=author&query=Ding%2C+B">Bowen Ding</a>, <a href="/search/eess?searchtype=author&query=Song%2C+W">Wei Song</a>, <a href="/search/eess?searchtype=author&query=Li%2C+X">Xu Li</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yuqi Huo</a>, <a href="/search/eess?searchtype=author&query=Liang%2C+Z">Zheng Liang</a> , et al. (68 additional authors not shown) </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.15368v1-abstract-short" style="display: inline;"> We introduce Baichuan-Omni-1.5, an omni-modal model that not only has omni-modal understanding capabilities but also provides end-to-end audio generation capabilities. To achieve fluent and high-quality interaction across modalities without compromising the capabilities of any modality, we prioritized optimizing three key aspects. First, we establish a comprehensive data cleaning and synthesis pip… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.15368v1-abstract-full').style.display = 'inline'; document.getElementById('2501.15368v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.15368v1-abstract-full" style="display: none;"> We introduce Baichuan-Omni-1.5, an omni-modal model that not only has omni-modal understanding capabilities but also provides end-to-end audio generation capabilities. To achieve fluent and high-quality interaction across modalities without compromising the capabilities of any modality, we prioritized optimizing three key aspects. First, we establish a comprehensive data cleaning and synthesis pipeline for multimodal data, obtaining about 500B high-quality data (text, audio, and vision). Second, an audio-tokenizer (Baichuan-Audio-Tokenizer) has been designed to capture both semantic and acoustic information from audio, enabling seamless integration and enhanced compatibility with MLLM. Lastly, we designed a multi-stage training strategy that progressively integrates multimodal alignment and multitask fine-tuning, ensuring effective synergy across all modalities. Baichuan-Omni-1.5 leads contemporary models (including GPT4o-mini and MiniCPM-o 2.6) in terms of comprehensive omni-modal capabilities. Notably, it achieves results comparable to leading models such as Qwen2-VL-72B across various multimodal medical benchmarks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.15368v1-abstract-full').style.display = 'none'; document.getElementById('2501.15368v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.13352">arXiv:2501.13352</a> <span> [<a href="https://arxiv.org/pdf/2501.13352">pdf</a>, <a href="https://arxiv.org/format/2501.13352">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Polyhedra Encoding Transformers: Enhancing Diffusion MRI Analysis Beyond Voxel and Volumetric Embedding </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Yao%2C+T">Tianyuan Yao</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Z">Zhiyuan Li</a>, <a href="/search/eess?searchtype=author&query=Kanakaraj%2C+P">Praitayini Kanakaraj</a>, <a href="/search/eess?searchtype=author&query=Archer%2C+D+B">Derek B. Archer</a>, <a href="/search/eess?searchtype=author&query=Schilling%2C+K">Kurt Schilling</a>, <a href="/search/eess?searchtype=author&query=Beason-Held%2C+L">Lori Beason-Held</a>, <a href="/search/eess?searchtype=author&query=Resnick%2C+S">Susan Resnick</a>, <a href="/search/eess?searchtype=author&query=Landman%2C+B+A">Bennett A. Landman</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yuankai Huo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.13352v1-abstract-short" style="display: inline;"> Diffusion-weighted Magnetic Resonance Imaging (dMRI) is an essential tool in neuroimaging. It is arguably the sole noninvasive technique for examining the microstructural properties and structural connectivity of the brain. Recent years have seen the emergence of machine learning and data-driven approaches that enhance the speed, accuracy, and consistency of dMRI data analysis. However, traditiona… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.13352v1-abstract-full').style.display = 'inline'; document.getElementById('2501.13352v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.13352v1-abstract-full" style="display: none;"> Diffusion-weighted Magnetic Resonance Imaging (dMRI) is an essential tool in neuroimaging. It is arguably the sole noninvasive technique for examining the microstructural properties and structural connectivity of the brain. Recent years have seen the emergence of machine learning and data-driven approaches that enhance the speed, accuracy, and consistency of dMRI data analysis. However, traditional deep learning models often fell short, as they typically utilize pixel-level or volumetric patch-level embeddings similar to those used in structural MRI, and do not account for the unique distribution of various gradient encodings. In this paper, we propose a novel method called Polyhedra Encoding Transformer (PE-Transformer) for dMRI, designed specifically to handle spherical signals. Our approach involves projecting an icosahedral polygon onto a unit sphere to resample signals from predetermined directions. These resampled signals are then transformed into embeddings, which are processed by a transformer encoder that incorporates orientational information reflective of the icosahedral structure. Through experimental validation with various gradient encoding protocols, our method demonstrates superior accuracy in estimating multi-compartment models and Fiber Orientation Distributions (FOD), outperforming both conventional CNN architectures and standard transformers. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.13352v1-abstract-full').style.display = 'none'; document.getElementById('2501.13352v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.06151">arXiv:2501.06151</a> <span> [<a href="https://arxiv.org/pdf/2501.06151">pdf</a>, <a href="https://arxiv.org/format/2501.06151">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> PySpatial: A High-Speed Whole Slide Image Pathomics Toolkit </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Yang%2C+Y">Yuechen Yang</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+Y">Yu Wang</a>, <a href="/search/eess?searchtype=author&query=Yao%2C+T">Tianyuan Yao</a>, <a href="/search/eess?searchtype=author&query=Deng%2C+R">Ruining Deng</a>, <a href="/search/eess?searchtype=author&query=Yin%2C+M">Mengmeng Yin</a>, <a href="/search/eess?searchtype=author&query=Zhao%2C+S">Shilin Zhao</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+H">Haichun Yang</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yuankai Huo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.06151v1-abstract-short" style="display: inline;"> Whole Slide Image (WSI) analysis plays a crucial role in modern digital pathology, enabling large-scale feature extraction from tissue samples. However, traditional feature extraction pipelines based on tools like CellProfiler often involve lengthy workflows, requiring WSI segmentation into patches, feature extraction at the patch level, and subsequent mapping back to the original WSI. To address… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.06151v1-abstract-full').style.display = 'inline'; document.getElementById('2501.06151v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.06151v1-abstract-full" style="display: none;"> Whole Slide Image (WSI) analysis plays a crucial role in modern digital pathology, enabling large-scale feature extraction from tissue samples. However, traditional feature extraction pipelines based on tools like CellProfiler often involve lengthy workflows, requiring WSI segmentation into patches, feature extraction at the patch level, and subsequent mapping back to the original WSI. To address these challenges, we present PySpatial, a high-speed pathomics toolkit specifically designed for WSI-level analysis. PySpatial streamlines the conventional pipeline by directly operating on computational regions of interest, reducing redundant processing steps. Utilizing rtree-based spatial indexing and matrix-based computation, PySpatial efficiently maps and processes computational regions, significantly accelerating feature extraction while maintaining high accuracy. Our experiments on two datasets-Perivascular Epithelioid Cell (PEC) and data from the Kidney Precision Medicine Project (KPMP)-demonstrate substantial performance improvements. For smaller and sparse objects in PEC datasets, PySpatial achieves nearly a 10-fold speedup compared to standard CellProfiler pipelines. For larger objects, such as glomeruli and arteries in KPMP datasets, PySpatial achieves a 2-fold speedup. These results highlight PySpatial's potential to handle large-scale WSI analysis with enhanced efficiency and accuracy, paving the way for broader applications in digital pathology. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.06151v1-abstract-full').style.display = 'none'; document.getElementById('2501.06151v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.16085">arXiv:2412.16085</a> <span> [<a href="https://arxiv.org/pdf/2412.16085">pdf</a>, <a href="https://arxiv.org/format/2412.16085">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Efficient MedSAMs: Segment Anything in Medical Images on Laptop </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Ma%2C+J">Jun Ma</a>, <a href="/search/eess?searchtype=author&query=Li%2C+F">Feifei Li</a>, <a href="/search/eess?searchtype=author&query=Kim%2C+S">Sumin Kim</a>, <a href="/search/eess?searchtype=author&query=Asakereh%2C+R">Reza Asakereh</a>, <a href="/search/eess?searchtype=author&query=Le%2C+B">Bao-Hiep Le</a>, <a href="/search/eess?searchtype=author&query=Nguyen-Vu%2C+D">Dang-Khoa Nguyen-Vu</a>, <a href="/search/eess?searchtype=author&query=Pfefferle%2C+A">Alexander Pfefferle</a>, <a href="/search/eess?searchtype=author&query=Wei%2C+M">Muxin Wei</a>, <a href="/search/eess?searchtype=author&query=Gao%2C+R">Ruochen Gao</a>, <a href="/search/eess?searchtype=author&query=Lyu%2C+D">Donghang Lyu</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+S">Songxiao Yang</a>, <a href="/search/eess?searchtype=author&query=Purucker%2C+L">Lennart Purucker</a>, <a href="/search/eess?searchtype=author&query=Marinov%2C+Z">Zdravko Marinov</a>, <a href="/search/eess?searchtype=author&query=Staring%2C+M">Marius Staring</a>, <a href="/search/eess?searchtype=author&query=Lu%2C+H">Haisheng Lu</a>, <a href="/search/eess?searchtype=author&query=Dao%2C+T+T">Thuy Thanh Dao</a>, <a href="/search/eess?searchtype=author&query=Ye%2C+X">Xincheng Ye</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Z">Zhi Li</a>, <a href="/search/eess?searchtype=author&query=Brugnara%2C+G">Gianluca Brugnara</a>, <a href="/search/eess?searchtype=author&query=Vollmuth%2C+P">Philipp Vollmuth</a>, <a href="/search/eess?searchtype=author&query=Foltyn-Dumitru%2C+M">Martha Foltyn-Dumitru</a>, <a href="/search/eess?searchtype=author&query=Cho%2C+J">Jaeyoung Cho</a>, <a href="/search/eess?searchtype=author&query=Mahmutoglu%2C+M+A">Mustafa Ahmed Mahmutoglu</a>, <a href="/search/eess?searchtype=author&query=Bendszus%2C+M">Martin Bendszus</a>, <a href="/search/eess?searchtype=author&query=Pfl%C3%BCger%2C+I">Irada Pfl眉ger</a> , et al. (57 additional authors not shown) </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2412.16085v1-abstract-short" style="display: inline;"> Promptable segmentation foundation models have emerged as a transformative approach to addressing the diverse needs in medical images, but most existing models require expensive computing, posing a big barrier to their adoption in clinical practice. In this work, we organized the first international competition dedicated to promptable medical image segmentation, featuring a large-scale dataset spa… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.16085v1-abstract-full').style.display = 'inline'; document.getElementById('2412.16085v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.16085v1-abstract-full" style="display: none;"> Promptable segmentation foundation models have emerged as a transformative approach to addressing the diverse needs in medical images, but most existing models require expensive computing, posing a big barrier to their adoption in clinical practice. In this work, we organized the first international competition dedicated to promptable medical image segmentation, featuring a large-scale dataset spanning nine common imaging modalities from over 20 different institutions. The top teams developed lightweight segmentation foundation models and implemented an efficient inference pipeline that substantially reduced computational requirements while maintaining state-of-the-art segmentation accuracy. Moreover, the post-challenge phase advanced the algorithms through the design of performance booster and reproducibility tasks, resulting in improved algorithms and validated reproducibility of the winning solution. Furthermore, the best-performing algorithms have been incorporated into the open-source software with a user-friendly interface to facilitate clinical adoption. The data and code are publicly available to foster the further development of medical image segmentation foundation models and pave the way for impactful real-world applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.16085v1-abstract-full').style.display = 'none'; document.getElementById('2412.16085v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">CVPR 2024 MedSAM on Laptop Competition Summary: https://www.codabench.org/competitions/1847/</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.16961">arXiv:2411.16961</a> <span> [<a href="https://arxiv.org/pdf/2411.16961">pdf</a>, <a href="https://arxiv.org/format/2411.16961">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Glo-In-One-v2: Holistic Identification of Glomerular Cells, Tissues, and Lesions in Human and Mouse Histopathology </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Yu%2C+L">Lining Yu</a>, <a href="/search/eess?searchtype=author&query=Yin%2C+M">Mengmeng Yin</a>, <a href="/search/eess?searchtype=author&query=Deng%2C+R">Ruining Deng</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Q">Quan Liu</a>, <a href="/search/eess?searchtype=author&query=Yao%2C+T">Tianyuan Yao</a>, <a href="/search/eess?searchtype=author&query=Cui%2C+C">Can Cui</a>, <a href="/search/eess?searchtype=author&query=Guo%2C+J">Junlin Guo</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+Y">Yu Wang</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+Y">Yaohong Wang</a>, <a href="/search/eess?searchtype=author&query=Zhao%2C+S">Shilin Zhao</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+H">Haichun Yang</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yuankai Huo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.16961v1-abstract-short" style="display: inline;"> Segmenting glomerular intraglomerular tissue and lesions traditionally depends on detailed morphological evaluations by expert nephropathologists, a labor-intensive process susceptible to interobserver variability. Our group previously developed the Glo-In-One toolkit for integrated detection and segmentation of glomeruli. In this study, we leverage the Glo-In-One toolkit to version 2 with fine-gr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.16961v1-abstract-full').style.display = 'inline'; document.getElementById('2411.16961v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.16961v1-abstract-full" style="display: none;"> Segmenting glomerular intraglomerular tissue and lesions traditionally depends on detailed morphological evaluations by expert nephropathologists, a labor-intensive process susceptible to interobserver variability. Our group previously developed the Glo-In-One toolkit for integrated detection and segmentation of glomeruli. In this study, we leverage the Glo-In-One toolkit to version 2 with fine-grained segmentation capabilities, curating 14 distinct labels for tissue regions, cells, and lesions across a dataset of 23,529 annotated glomeruli across human and mouse histopathology data. To our knowledge, this dataset is among the largest of its kind to date.In this study, we present a single dynamic head deep learning architecture designed to segment 14 classes within partially labeled images of human and mouse pathology data. Our model was trained using a training set derived from 368 annotated kidney whole-slide images (WSIs) to identify 5 key intraglomerular tissues covering Bowman's capsule, glomerular tuft, mesangium, mesangial cells, and podocytes. Additionally, the network segments 9 glomerular lesion classes including adhesion, capsular drop, global sclerosis, hyalinosis, mesangial lysis, microaneurysm, nodular sclerosis, mesangial expansion, and segmental sclerosis. The glomerulus segmentation model achieved a decent performance compared with baselines, and achieved a 76.5 % average Dice Similarity Coefficient (DSC). Additional, transfer learning from rodent to human for glomerular lesion segmentation model has enhanced the average segmentation accuracy across different types of lesions by more than 3 %, as measured by Dice scores. The Glo-In-One-v2 model and trained weight have been made publicly available at https: //github.com/hrlblab/Glo-In-One_v2. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.16961v1-abstract-full').style.display = 'none'; document.getElementById('2411.16961v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.15942">arXiv:2411.15942</a> <span> [<a href="https://arxiv.org/pdf/2411.15942">pdf</a>, <a href="https://arxiv.org/format/2411.15942">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Cross-organ Deployment of EOS Detection AI without Retraining: Feasibility and Limitation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Wu%2C+Y">Yifei Wu</a>, <a href="/search/eess?searchtype=author&query=Xiong%2C+J">Juming Xiong</a>, <a href="/search/eess?searchtype=author&query=Yao%2C+T">Tianyuan Yao</a>, <a href="/search/eess?searchtype=author&query=Deng%2C+R">Ruining Deng</a>, <a href="/search/eess?searchtype=author&query=Guo%2C+J">Junlin Guo</a>, <a href="/search/eess?searchtype=author&query=Yue%2C+J">Jialin Yue</a>, <a href="/search/eess?searchtype=author&query=Chowdhury%2C+N">Naweed Chowdhury</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yuankai Huo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.15942v1-abstract-short" style="display: inline;"> Chronic rhinosinusitis (CRS) is characterized by persistent inflammation in the paranasal sinuses, leading to typical symptoms of nasal congestion, facial pressure, olfactory dysfunction, and discolored nasal drainage, which can significantly impact quality-of-life. Eosinophils (Eos), a crucial component in the mucosal immune response, have been linked to disease severity in CRS. The diagnosis of… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.15942v1-abstract-full').style.display = 'inline'; document.getElementById('2411.15942v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.15942v1-abstract-full" style="display: none;"> Chronic rhinosinusitis (CRS) is characterized by persistent inflammation in the paranasal sinuses, leading to typical symptoms of nasal congestion, facial pressure, olfactory dysfunction, and discolored nasal drainage, which can significantly impact quality-of-life. Eosinophils (Eos), a crucial component in the mucosal immune response, have been linked to disease severity in CRS. The diagnosis of eosinophilic CRS typically uses a threshold of 10-20 eos per high-power field (HPF). However, manually counting Eos in histological samples is laborious and time-intensive, making the use of AI-driven methods for automated evaluations highly desirable. Interestingly, eosinophils are predominantly located in the gastrointestinal (GI) tract, which has prompted the release of numerous deep learning models trained on GI data. This study leverages a CircleSnake model initially trained on upper-GI data to segment Eos cells in whole slide images (WSIs) of nasal tissues. It aims to determine the extent to which Eos segmentation models developed for the GI tract can be adapted to nasal applications without retraining. The experimental results show promising accuracy in some WSIs, although, unsurprisingly, the performance varies across cases. This paper details these performance outcomes, delves into the reasons for such variations, and aims to provide insights that could guide future development of deep learning models for eosinophilic CRS. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.15942v1-abstract-full').style.display = 'none'; document.getElementById('2411.15942v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">8 pages, 5 figures. Accepted by SPIE Medical Imaging 2025 on October 28, 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.00078">arXiv:2411.00078</a> <span> [<a href="https://arxiv.org/pdf/2411.00078">pdf</a>, <a href="https://arxiv.org/format/2411.00078">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> How Good Are We? Evaluating Cell AI Foundation Models in Kidney Pathology with Human-in-the-Loop Enrichment </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Guo%2C+J">Junlin Guo</a>, <a href="/search/eess?searchtype=author&query=Lu%2C+S">Siqi Lu</a>, <a href="/search/eess?searchtype=author&query=Cui%2C+C">Can Cui</a>, <a href="/search/eess?searchtype=author&query=Deng%2C+R">Ruining Deng</a>, <a href="/search/eess?searchtype=author&query=Yao%2C+T">Tianyuan Yao</a>, <a href="/search/eess?searchtype=author&query=Tao%2C+Z">Zhewen Tao</a>, <a href="/search/eess?searchtype=author&query=Lin%2C+Y">Yizhe Lin</a>, <a href="/search/eess?searchtype=author&query=Lionts%2C+M">Marilyn Lionts</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Q">Quan Liu</a>, <a href="/search/eess?searchtype=author&query=Xiong%2C+J">Juming Xiong</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+Y">Yu Wang</a>, <a href="/search/eess?searchtype=author&query=Zhao%2C+S">Shilin Zhao</a>, <a href="/search/eess?searchtype=author&query=Chang%2C+C">Catie Chang</a>, <a href="/search/eess?searchtype=author&query=Wilkes%2C+M">Mitchell Wilkes</a>, <a href="/search/eess?searchtype=author&query=Yin%2C+M">Mengmeng Yin</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+H">Haichun Yang</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yuankai Huo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.00078v1-abstract-short" style="display: inline;"> Training AI foundation models has emerged as a promising large-scale learning approach for addressing real-world healthcare challenges, including digital pathology. While many of these models have been developed for tasks like disease diagnosis and tissue quantification using extensive and diverse training datasets, their readiness for deployment on some arguably simplest tasks, such as nuclei seg… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00078v1-abstract-full').style.display = 'inline'; document.getElementById('2411.00078v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.00078v1-abstract-full" style="display: none;"> Training AI foundation models has emerged as a promising large-scale learning approach for addressing real-world healthcare challenges, including digital pathology. While many of these models have been developed for tasks like disease diagnosis and tissue quantification using extensive and diverse training datasets, their readiness for deployment on some arguably simplest tasks, such as nuclei segmentation within a single organ (e.g., the kidney), remains uncertain. This paper seeks to answer this key question, "How good are we?", by thoroughly evaluating the performance of recent cell foundation models on a curated multi-center, multi-disease, and multi-species external testing dataset. Additionally, we tackle a more challenging question, "How can we improve?", by developing and assessing human-in-the-loop data enrichment strategies aimed at enhancing model performance while minimizing the reliance on pixel-level human annotation. To address the first question, we curated a multicenter, multidisease, and multispecies dataset consisting of 2,542 kidney whole slide images (WSIs). Three state-of-the-art (SOTA) cell foundation models-Cellpose, StarDist, and CellViT-were selected for evaluation. To tackle the second question, we explored data enrichment algorithms by distilling predictions from the different foundation models with a human-in-the-loop framework, aiming to further enhance foundation model performance with minimal human efforts. Our experimental results showed that all three foundation models improved over their baselines with model fine-tuning with enriched data. Interestingly, the baseline model with the highest F1 score does not yield the best segmentation outcomes after fine-tuning. This study establishes a benchmark for the development and deployment of cell vision foundation models tailored for real-world data applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00078v1-abstract-full').style.display = 'none'; document.getElementById('2411.00078v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 31 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.14453">arXiv:2408.14453</a> <span> [<a href="https://arxiv.org/pdf/2408.14453">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Reconstructing physiological signals from fMRI across the adult lifespan </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Wang%2C+S">Shiyu Wang</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+Z">Ziyuan Xu</a>, <a href="/search/eess?searchtype=author&query=Lochard%2C+L+M">Laurent M. Lochard</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Y">Yamin Li</a>, <a href="/search/eess?searchtype=author&query=Fan%2C+J">Jiawen Fan</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+J+E">Jingyuan E. Chen</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yuankai Huo</a>, <a href="/search/eess?searchtype=author&query=Mather%2C+M">Mara Mather</a>, <a href="/search/eess?searchtype=author&query=Bayrak%2C+R+G">Roza G. Bayrak</a>, <a href="/search/eess?searchtype=author&query=Chang%2C+C">Catie Chang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.14453v2-abstract-short" style="display: inline;"> Interactions between the brain and body are of fundamental importance for human behavior and health. Functional magnetic resonance imaging (fMRI) captures whole-brain activity noninvasively, and modeling how fMRI signals interact with physiological dynamics of the body can provide new insight into brain function and offer potential biomarkers of disease. However, physiological recordings are not a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.14453v2-abstract-full').style.display = 'inline'; document.getElementById('2408.14453v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.14453v2-abstract-full" style="display: none;"> Interactions between the brain and body are of fundamental importance for human behavior and health. Functional magnetic resonance imaging (fMRI) captures whole-brain activity noninvasively, and modeling how fMRI signals interact with physiological dynamics of the body can provide new insight into brain function and offer potential biomarkers of disease. However, physiological recordings are not always possible to acquire since they require extra equipment and setup, and even when they are, the recorded physiological signals may contain substantial artifacts. To overcome this limitation, machine learning models have been proposed to directly extract features of respiratory and cardiac activity from resting-state fMRI signals. To date, such work has been carried out only in healthy young adults and in a pediatric population, leaving open questions about the efficacy of these approaches on older adults. Here, we propose a novel framework that leverages Transformer-based architectures for reconstructing two key physiological signals - low-frequency respiratory volume (RV) and heart rate (HR) fluctuations - from fMRI data, and test these models on a dataset of individuals aged 36-89 years old. Our framework outperforms previously proposed approaches (attaining median correlations between predicted and measured signals of r ~ .698 for RV and r ~ .618 for HR), indicating the potential of leveraging attention mechanisms to model fMRI-physiological signal relationships. We also evaluate several model training and fine-tuning strategies, and find that incorporating young-adult data during training improves the performance when predicting physiological signals in the aging cohort. Overall, our approach successfully infers key physiological variables directly from fMRI data from individuals across a wide range of the adult lifespan. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.14453v2-abstract-full').style.display = 'none'; document.getElementById('2408.14453v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 26 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.09278">arXiv:2408.09278</a> <span> [<a href="https://arxiv.org/pdf/2408.09278">pdf</a>, <a href="https://arxiv.org/format/2408.09278">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Cross-Species Data Integration for Enhanced Layer Segmentation in Kidney Pathology </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zhu%2C+J">Junchao Zhu</a>, <a href="/search/eess?searchtype=author&query=Yin%2C+M">Mengmeng Yin</a>, <a href="/search/eess?searchtype=author&query=Deng%2C+R">Ruining Deng</a>, <a href="/search/eess?searchtype=author&query=Long%2C+Y">Yitian Long</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+Y">Yu Wang</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+Y">Yaohong Wang</a>, <a href="/search/eess?searchtype=author&query=Zhao%2C+S">Shilin Zhao</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+H">Haichun Yang</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yuankai Huo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.09278v1-abstract-short" style="display: inline;"> Accurate delineation of the boundaries between the renal cortex and medulla is crucial for subsequent functional structural analysis and disease diagnosis. Training high-quality deep-learning models for layer segmentation relies on the availability of large amounts of annotated data. However, due to the patient's privacy of medical data and scarce clinical cases, constructing pathological datasets… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.09278v1-abstract-full').style.display = 'inline'; document.getElementById('2408.09278v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.09278v1-abstract-full" style="display: none;"> Accurate delineation of the boundaries between the renal cortex and medulla is crucial for subsequent functional structural analysis and disease diagnosis. Training high-quality deep-learning models for layer segmentation relies on the availability of large amounts of annotated data. However, due to the patient's privacy of medical data and scarce clinical cases, constructing pathological datasets from clinical sources is relatively difficult and expensive. Moreover, using external natural image datasets introduces noise during the domain generalization process. Cross-species homologous data, such as mouse kidney data, which exhibits high structural and feature similarity to human kidneys, has the potential to enhance model performance on human datasets. In this study, we incorporated the collected private Periodic Acid-Schiff (PAS) stained mouse kidney dataset into the human kidney dataset for joint training. The results showed that after introducing cross-species homologous data, the semantic segmentation models based on CNN and Transformer architectures achieved an average increase of 1.77% and 1.24% in mIoU, and 1.76% and 0.89% in Dice score for the human renal cortex and medulla datasets, respectively. This approach is also capable of enhancing the model's generalization ability. This indicates that cross-species homologous data, as a low-noise trainable data source, can help improve model performance under conditions of limited clinical samples. Code is available at https://github.com/hrlblab/layer_segmentation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.09278v1-abstract-full').style.display = 'none'; document.getElementById('2408.09278v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.06381">arXiv:2408.06381</a> <span> [<a href="https://arxiv.org/pdf/2408.06381">pdf</a>, <a href="https://arxiv.org/format/2408.06381">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Assessment of Cell Nuclei AI Foundation Models in Kidney Pathology </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Guo%2C+J">Junlin Guo</a>, <a href="/search/eess?searchtype=author&query=Lu%2C+S">Siqi Lu</a>, <a href="/search/eess?searchtype=author&query=Cui%2C+C">Can Cui</a>, <a href="/search/eess?searchtype=author&query=Deng%2C+R">Ruining Deng</a>, <a href="/search/eess?searchtype=author&query=Yao%2C+T">Tianyuan Yao</a>, <a href="/search/eess?searchtype=author&query=Tao%2C+Z">Zhewen Tao</a>, <a href="/search/eess?searchtype=author&query=Lin%2C+Y">Yizhe Lin</a>, <a href="/search/eess?searchtype=author&query=Lionts%2C+M">Marilyn Lionts</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Q">Quan Liu</a>, <a href="/search/eess?searchtype=author&query=Xiong%2C+J">Juming Xiong</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+Y">Yu Wang</a>, <a href="/search/eess?searchtype=author&query=Zhao%2C+S">Shilin Zhao</a>, <a href="/search/eess?searchtype=author&query=Chang%2C+C">Catie Chang</a>, <a href="/search/eess?searchtype=author&query=Wilkes%2C+M">Mitchell Wilkes</a>, <a href="/search/eess?searchtype=author&query=Yin%2C+M">Mengmeng Yin</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+H">Haichun Yang</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yuankai Huo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.06381v2-abstract-short" style="display: inline;"> Cell nuclei instance segmentation is a crucial task in digital kidney pathology. Traditional automatic segmentation methods often lack generalizability when applied to unseen datasets. Recently, the success of foundation models (FMs) has provided a more generalizable solution, potentially enabling the segmentation of any cell type. In this study, we perform a large-scale evaluation of three widely… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.06381v2-abstract-full').style.display = 'inline'; document.getElementById('2408.06381v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.06381v2-abstract-full" style="display: none;"> Cell nuclei instance segmentation is a crucial task in digital kidney pathology. Traditional automatic segmentation methods often lack generalizability when applied to unseen datasets. Recently, the success of foundation models (FMs) has provided a more generalizable solution, potentially enabling the segmentation of any cell type. In this study, we perform a large-scale evaluation of three widely used state-of-the-art (SOTA) cell nuclei foundation models (Cellpose, StarDist, and CellViT). Specifically, we created a highly diverse evaluation dataset consisting of 2,542 kidney whole slide images (WSIs) collected from both human and rodent sources, encompassing various tissue types, sizes, and staining methods. To our knowledge, this is the largest-scale evaluation of its kind to date. Our quantitative analysis of the prediction distribution reveals a persistent performance gap in kidney pathology. Among the evaluated models, CellViT demonstrated superior performance in segmenting nuclei in kidney pathology. However, none of the foundation models are perfect; a performance gap remains in general nuclei segmentation for kidney pathology. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.06381v2-abstract-full').style.display = 'none'; document.getElementById('2408.06381v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 9 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.18390">arXiv:2407.18390</a> <span> [<a href="https://arxiv.org/pdf/2407.18390">pdf</a>, <a href="https://arxiv.org/format/2407.18390">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> GLAM: Glomeruli Segmentation for Human Pathological Lesions using Adapted Mouse Model </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Yu%2C+L">Lining Yu</a>, <a href="/search/eess?searchtype=author&query=Yin%2C+M">Mengmeng Yin</a>, <a href="/search/eess?searchtype=author&query=Deng%2C+R">Ruining Deng</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Q">Quan Liu</a>, <a href="/search/eess?searchtype=author&query=Yao%2C+T">Tianyuan Yao</a>, <a href="/search/eess?searchtype=author&query=Cui%2C+C">Can Cui</a>, <a href="/search/eess?searchtype=author&query=Long%2C+Y">Yitian Long</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+Y">Yu Wang</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+Y">Yaohong Wang</a>, <a href="/search/eess?searchtype=author&query=Zhao%2C+S">Shilin Zhao</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+H">Haichun Yang</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yuankai Huo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.18390v2-abstract-short" style="display: inline;"> Moving from animal models to human applications in preclinical research encompasses a broad spectrum of disciplines in medical science. A fundamental element in the development of new drugs, treatments, diagnostic methods, and in deepening our understanding of disease processes is the accurate measurement of kidney tissues. Past studies have demonstrated the viability of translating glomeruli segm… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.18390v2-abstract-full').style.display = 'inline'; document.getElementById('2407.18390v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.18390v2-abstract-full" style="display: none;"> Moving from animal models to human applications in preclinical research encompasses a broad spectrum of disciplines in medical science. A fundamental element in the development of new drugs, treatments, diagnostic methods, and in deepening our understanding of disease processes is the accurate measurement of kidney tissues. Past studies have demonstrated the viability of translating glomeruli segmentation techniques from mouse models to human applications. Yet, these investigations tend to neglect the complexities involved in segmenting pathological glomeruli affected by different lesions. Such lesions present a wider range of morphological variations compared to healthy glomerular tissue, which are arguably more valuable than normal glomeruli in clinical practice. Furthermore, data on lesions from animal models can be more readily scaled up from disease models and whole kidney biopsies. This brings up a question: ``\textit{Can a pathological segmentation model trained on mouse models be effectively applied to human patients?}" To answer this question, we introduced GLAM, a deep learning study for fine-grained segmentation of human kidney lesions using a mouse model, addressing mouse-to-human transfer learning, by evaluating different learning strategies for segmenting human pathological lesions using zero-shot transfer learning and hybrid learning by leveraging mouse samples. From the results, the hybrid learning model achieved superior performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.18390v2-abstract-full').style.display = 'none'; document.getElementById('2407.18390v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 25 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.14429">arXiv:2407.14429</a> <span> [<a href="https://arxiv.org/pdf/2407.14429">pdf</a>, <a href="https://arxiv.org/format/2407.14429">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Dataset Distillation in Medical Imaging: A Feasibility Study </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Li%2C+M">Muyang Li</a>, <a href="/search/eess?searchtype=author&query=Cui%2C+C">Can Cui</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Q">Quan Liu</a>, <a href="/search/eess?searchtype=author&query=Deng%2C+R">Ruining Deng</a>, <a href="/search/eess?searchtype=author&query=Yao%2C+T">Tianyuan Yao</a>, <a href="/search/eess?searchtype=author&query=Lionts%2C+M">Marilyn Lionts</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yuankai Huo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.14429v2-abstract-short" style="display: inline;"> Data sharing in the medical image analysis field has potential yet remains underappreciated. The aim is often to share datasets efficiently with other sites to train models effectively. One possible solution is to avoid transferring the entire dataset while still achieving similar model performance. Recent progress in data distillation within computer science offers promising prospects for sharing… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.14429v2-abstract-full').style.display = 'inline'; document.getElementById('2407.14429v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.14429v2-abstract-full" style="display: none;"> Data sharing in the medical image analysis field has potential yet remains underappreciated. The aim is often to share datasets efficiently with other sites to train models effectively. One possible solution is to avoid transferring the entire dataset while still achieving similar model performance. Recent progress in data distillation within computer science offers promising prospects for sharing medical data efficiently without significantly compromising model effectiveness. However, it remains uncertain whether these methods would be applicable to medical imaging, since medical and natural images are distinct fields. Moreover, it is intriguing to consider what level of performance could be achieved with these methods. To answer these questions, we conduct investigations on a variety of leading data distillation methods, in different contexts of medical imaging. We evaluate the feasibility of these methods with extensive experiments in two aspects: 1) Assess the impact of data distillation across multiple datasets characterized by minor or great variations. 2) Explore the indicator to predict the distillation performance. Our extensive experiments across multiple medical datasets reveal that data distillation can significantly reduce dataset size while maintaining comparable model performance to that achieved with the full dataset, suggesting that a small, representative sample of images can serve as a reliable indicator of distillation success. This study demonstrates that data distillation is a viable method for efficient and secure medical data sharing, with the potential to facilitate enhanced collaborative research and clinical applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.14429v2-abstract-full').style.display = 'none'; document.getElementById('2407.14429v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 19 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.06116">arXiv:2407.06116</a> <span> [<a href="https://arxiv.org/pdf/2407.06116">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Data-driven Nucleus Subclassification on Colon H&E using Style-transferred Digital Pathology </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Remedios%2C+L+W">Lucas W. Remedios</a>, <a href="/search/eess?searchtype=author&query=Bao%2C+S">Shunxing Bao</a>, <a href="/search/eess?searchtype=author&query=Remedios%2C+S+W">Samuel W. Remedios</a>, <a href="/search/eess?searchtype=author&query=Lee%2C+H+H">Ho Hin Lee</a>, <a href="/search/eess?searchtype=author&query=Cai%2C+L+Y">Leon Y. Cai</a>, <a href="/search/eess?searchtype=author&query=Li%2C+T">Thomas Li</a>, <a href="/search/eess?searchtype=author&query=Deng%2C+R">Ruining Deng</a>, <a href="/search/eess?searchtype=author&query=Newlin%2C+N+R">Nancy R. Newlin</a>, <a href="/search/eess?searchtype=author&query=Saunders%2C+A+M">Adam M. Saunders</a>, <a href="/search/eess?searchtype=author&query=Cui%2C+C">Can Cui</a>, <a href="/search/eess?searchtype=author&query=Li%2C+J">Jia Li</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Q">Qi Liu</a>, <a href="/search/eess?searchtype=author&query=Lau%2C+K+S">Ken S. Lau</a>, <a href="/search/eess?searchtype=author&query=Roland%2C+J+T">Joseph T. Roland</a>, <a href="/search/eess?searchtype=author&query=Washington%2C+M+K">Mary K Washington</a>, <a href="/search/eess?searchtype=author&query=Coburn%2C+L+A">Lori A. Coburn</a>, <a href="/search/eess?searchtype=author&query=Wilson%2C+K+T">Keith T. Wilson</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yuankai Huo</a>, <a href="/search/eess?searchtype=author&query=Landman%2C+B+A">Bennett A. Landman</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.06116v1-abstract-short" style="display: inline;"> Understanding the way cells communicate, co-locate, and interrelate is essential to furthering our understanding of how the body functions. H&E is widely available, however, cell subtyping often requires expert knowledge and the use of specialized stains. To reduce the annotation burden, AI has been proposed for the classification of cells on H&E. For example, the recent Colon Nucleus Identificati… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.06116v1-abstract-full').style.display = 'inline'; document.getElementById('2407.06116v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.06116v1-abstract-full" style="display: none;"> Understanding the way cells communicate, co-locate, and interrelate is essential to furthering our understanding of how the body functions. H&E is widely available, however, cell subtyping often requires expert knowledge and the use of specialized stains. To reduce the annotation burden, AI has been proposed for the classification of cells on H&E. For example, the recent Colon Nucleus Identification and Classification (CoNIC) Challenge focused on labeling 6 cell types on H&E of the colon. However, the CoNIC Challenge was unable to classify epithelial subtypes (progenitor, enteroendocrine, goblet), lymphocyte subtypes (B, helper T, cytotoxic T), and connective subtypes (fibroblasts). We use inter-modality learning to label previously un-labelable cell types on H&E. We take advantage of multiplexed immunofluorescence (MxIF) histology to label 14 cell subclasses. We performed style transfer on the same MxIF tissues to synthesize realistic virtual H&E which we paired with the MxIF-derived cell subclassification labels. We evaluated the efficacy of using a supervised learning scheme where the input was realistic-quality virtual H&E and the labels were MxIF-derived cell subclasses. We assessed our model on private virtual H&E and public real H&E. On virtual H&E, we were able to classify helper T cells and epithelial progenitors with positive predictive values of $0.34 \pm 0.15$ (prevalence $0.03 \pm 0.01$) and $0.47 \pm 0.1$ (prevalence $0.07 \pm 0.02$) respectively, when using ground truth centroid information. On real H&E we could classify helper T cells and epithelial progenitors with upper bound positive predictive values of $0.43 \pm 0.03$ (parent class prevalence 0.21) and $0.94 \pm 0.02$ (parent class prevalence 0.49) when using ground truth centroid information. This is the first work to provide cell type classification for helper T and epithelial progenitor nuclei on H&E. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.06116v1-abstract-full').style.display = 'none'; document.getElementById('2407.06116v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">arXiv admin note: text overlap with arXiv:2401.05602</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.03307">arXiv:2407.03307</a> <span> [<a href="https://arxiv.org/pdf/2407.03307">pdf</a>, <a href="https://arxiv.org/format/2407.03307">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> HoloHisto: End-to-end Gigapixel WSI Segmentation with 4K Resolution Sequential Tokenization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Tang%2C+Y">Yucheng Tang</a>, <a href="/search/eess?searchtype=author&query=He%2C+Y">Yufan He</a>, <a href="/search/eess?searchtype=author&query=Nath%2C+V">Vishwesh Nath</a>, <a href="/search/eess?searchtype=author&query=Guo%2C+P">Pengfeig Guo</a>, <a href="/search/eess?searchtype=author&query=Deng%2C+R">Ruining Deng</a>, <a href="/search/eess?searchtype=author&query=Yao%2C+T">Tianyuan Yao</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Q">Quan Liu</a>, <a href="/search/eess?searchtype=author&query=Cui%2C+C">Can Cui</a>, <a href="/search/eess?searchtype=author&query=Yin%2C+M">Mengmeng Yin</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+Z">Ziyue Xu</a>, <a href="/search/eess?searchtype=author&query=Roth%2C+H">Holger Roth</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+D">Daguang Xu</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+H">Haichun Yang</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yuankai Huo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.03307v1-abstract-short" style="display: inline;"> In digital pathology, the traditional method for deep learning-based image segmentation typically involves a two-stage process: initially segmenting high-resolution whole slide images (WSI) into smaller patches (e.g., 256x256, 512x512, 1024x1024) and subsequently reconstructing them to their original scale. This method often struggles to capture the complex details and vast scope of WSIs. In this… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.03307v1-abstract-full').style.display = 'inline'; document.getElementById('2407.03307v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.03307v1-abstract-full" style="display: none;"> In digital pathology, the traditional method for deep learning-based image segmentation typically involves a two-stage process: initially segmenting high-resolution whole slide images (WSI) into smaller patches (e.g., 256x256, 512x512, 1024x1024) and subsequently reconstructing them to their original scale. This method often struggles to capture the complex details and vast scope of WSIs. In this paper, we propose the holistic histopathology (HoloHisto) segmentation method to achieve end-to-end segmentation on gigapixel WSIs, whose maximum resolution is above 80,000$\times$70,000 pixels. HoloHisto fundamentally shifts the paradigm of WSI segmentation to an end-to-end learning fashion with 1) a large (4K) resolution base patch for elevated visual information inclusion and efficient processing, and 2) a novel sequential tokenization mechanism to properly model the contextual relationships and efficiently model the rich information from the 4K input. To our best knowledge, HoloHisto presents the first holistic approach for gigapixel resolution WSI segmentation, supporting direct I/O of complete WSI and their corresponding gigapixel masks. Under the HoloHisto platform, we unveil a random 4K sampler that transcends ultra-high resolution, delivering 31 and 10 times more pixels than standard 2D and 3D patches, respectively, for advancing computational capabilities. To facilitate efficient 4K resolution dense prediction, we leverage sequential tokenization, utilizing a pre-trained image tokenizer to group image features into a discrete token grid. To assess the performance, our team curated a new kidney pathology image segmentation (KPIs) dataset with WSI-level glomeruli segmentation from whole mouse kidneys. From the results, HoloHisto-4K delivers remarkable performance gains over previous state-of-the-art models. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.03307v1-abstract-full').style.display = 'none'; document.getElementById('2407.03307v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 3 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.00596">arXiv:2407.00596</a> <span> [<a href="https://arxiv.org/pdf/2407.00596">pdf</a>, <a href="https://arxiv.org/format/2407.00596">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> HATs: Hierarchical Adaptive Taxonomy Segmentation for Panoramic Pathology Image Analysis </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Deng%2C+R">Ruining Deng</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Q">Quan Liu</a>, <a href="/search/eess?searchtype=author&query=Cui%2C+C">Can Cui</a>, <a href="/search/eess?searchtype=author&query=Yao%2C+T">Tianyuan Yao</a>, <a href="/search/eess?searchtype=author&query=Xiong%2C+J">Juming Xiong</a>, <a href="/search/eess?searchtype=author&query=Bao%2C+S">Shunxing Bao</a>, <a href="/search/eess?searchtype=author&query=Li%2C+H">Hao Li</a>, <a href="/search/eess?searchtype=author&query=Yin%2C+M">Mengmeng Yin</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+Y">Yu Wang</a>, <a href="/search/eess?searchtype=author&query=Zhao%2C+S">Shilin Zhao</a>, <a href="/search/eess?searchtype=author&query=Tang%2C+Y">Yucheng Tang</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+H">Haichun Yang</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yuankai Huo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.00596v1-abstract-short" style="display: inline;"> Panoramic image segmentation in computational pathology presents a remarkable challenge due to the morphologically complex and variably scaled anatomy. For instance, the intricate organization in kidney pathology spans multiple layers, from regions like the cortex and medulla to functional units such as glomeruli, tubules, and vessels, down to various cell types. In this paper, we propose a novel… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.00596v1-abstract-full').style.display = 'inline'; document.getElementById('2407.00596v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.00596v1-abstract-full" style="display: none;"> Panoramic image segmentation in computational pathology presents a remarkable challenge due to the morphologically complex and variably scaled anatomy. For instance, the intricate organization in kidney pathology spans multiple layers, from regions like the cortex and medulla to functional units such as glomeruli, tubules, and vessels, down to various cell types. In this paper, we propose a novel Hierarchical Adaptive Taxonomy Segmentation (HATs) method, which is designed to thoroughly segment panoramic views of kidney structures by leveraging detailed anatomical insights. Our approach entails (1) the innovative HATs technique which translates spatial relationships among 15 distinct object classes into a versatile "plug-and-play" loss function that spans across regions, functional units, and cells, (2) the incorporation of anatomical hierarchies and scale considerations into a unified simple matrix representation for all panoramic entities, (3) the adoption of the latest AI foundation model (EfficientSAM) as a feature extraction tool to boost the model's adaptability, yet eliminating the need for manual prompt generation in conventional segment anything model (SAM). Experimental findings demonstrate that the HATs method offers an efficient and effective strategy for integrating clinical insights and imaging precedents into a unified segmentation model across more than 15 categories. The official implementation is publicly available at https://github.com/hrlblab/HATs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.00596v1-abstract-full').style.display = 'none'; document.getElementById('2407.00596v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">arXiv admin note: text overlap with arXiv:2402.19286</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.12254">arXiv:2406.12254</a> <span> [<a href="https://arxiv.org/pdf/2406.12254">pdf</a>, <a href="https://arxiv.org/format/2406.12254">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Enhancing Single-Slice Segmentation with 3D-to-2D Unpaired Scan Distillation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Yu%2C+X">Xin Yu</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+Q">Qi Yang</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+H">Han Liu</a>, <a href="/search/eess?searchtype=author&query=Lee%2C+H+H">Ho Hin Lee</a>, <a href="/search/eess?searchtype=author&query=Tang%2C+Y">Yucheng Tang</a>, <a href="/search/eess?searchtype=author&query=Remedios%2C+L+W">Lucas W. Remedios</a>, <a href="/search/eess?searchtype=author&query=Kim%2C+M+E">Michael E. Kim</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+R">Rendong Zhang</a>, <a href="/search/eess?searchtype=author&query=Bao%2C+S">Shunxing Bao</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yuankai Huo</a>, <a href="/search/eess?searchtype=author&query=Moore%2C+A+Z">Ann Zenobia Moore</a>, <a href="/search/eess?searchtype=author&query=Ferrucci%2C+L">Luigi Ferrucci</a>, <a href="/search/eess?searchtype=author&query=Landman%2C+B+A">Bennett A. Landman</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.12254v2-abstract-short" style="display: inline;"> 2D single-slice abdominal computed tomography (CT) enables the assessment of body habitus and organ health with low radiation exposure. However, single-slice data necessitates the use of 2D networks for segmentation, but these networks often struggle to capture contextual information effectively. Consequently, even when trained on identical datasets, 3D networks typically achieve superior segmenta… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.12254v2-abstract-full').style.display = 'inline'; document.getElementById('2406.12254v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.12254v2-abstract-full" style="display: none;"> 2D single-slice abdominal computed tomography (CT) enables the assessment of body habitus and organ health with low radiation exposure. However, single-slice data necessitates the use of 2D networks for segmentation, but these networks often struggle to capture contextual information effectively. Consequently, even when trained on identical datasets, 3D networks typically achieve superior segmentation results. In this work, we propose a novel 3D-to-2D distillation framework, leveraging pre-trained 3D models to enhance 2D single-slice segmentation. Specifically, we extract the prediction distribution centroid from the 3D representations, to guide the 2D student by learning intra- and inter-class correlation. Unlike traditional knowledge distillation methods that require the same data input, our approach employs unpaired 3D CT scans with any contrast to guide the 2D student model. Experiments conducted on 707 subjects from the single-slice Baltimore Longitudinal Study of Aging (BLSA) dataset demonstrate that state-of-the-art 2D multi-organ segmentation methods can benefit from the 3D teacher model, achieving enhanced performance in single-slice multi-organ segmentation. Notably, our approach demonstrates considerable efficacy in low-data regimes, outperforming the model trained with all available training subjects even when utilizing only 200 training subjects. Thus, this work underscores the potential to alleviate manual annotation burdens. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.12254v2-abstract-full').style.display = 'none'; document.getElementById('2406.12254v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 12 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 18 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.02430">arXiv:2406.02430</a> <span> [<a href="https://arxiv.org/pdf/2406.02430">pdf</a>, <a href="https://arxiv.org/format/2406.02430">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> </div> </div> <p class="title is-5 mathjax"> Seed-TTS: A Family of High-Quality Versatile Speech Generation Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Anastassiou%2C+P">Philip Anastassiou</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+J">Jiawei Chen</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+J">Jitong Chen</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+Y">Yuanzhe Chen</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+Z">Zhuo Chen</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+Z">Ziyi Chen</a>, <a href="/search/eess?searchtype=author&query=Cong%2C+J">Jian Cong</a>, <a href="/search/eess?searchtype=author&query=Deng%2C+L">Lelai Deng</a>, <a href="/search/eess?searchtype=author&query=Ding%2C+C">Chuang Ding</a>, <a href="/search/eess?searchtype=author&query=Gao%2C+L">Lu Gao</a>, <a href="/search/eess?searchtype=author&query=Gong%2C+M">Mingqing Gong</a>, <a href="/search/eess?searchtype=author&query=Huang%2C+P">Peisong Huang</a>, <a href="/search/eess?searchtype=author&query=Huang%2C+Q">Qingqing Huang</a>, <a href="/search/eess?searchtype=author&query=Huang%2C+Z">Zhiying Huang</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yuanyuan Huo</a>, <a href="/search/eess?searchtype=author&query=Jia%2C+D">Dongya Jia</a>, <a href="/search/eess?searchtype=author&query=Li%2C+C">Chumin Li</a>, <a href="/search/eess?searchtype=author&query=Li%2C+F">Feiya Li</a>, <a href="/search/eess?searchtype=author&query=Li%2C+H">Hui Li</a>, <a href="/search/eess?searchtype=author&query=Li%2C+J">Jiaxin Li</a>, <a href="/search/eess?searchtype=author&query=Li%2C+X">Xiaoyang Li</a>, <a href="/search/eess?searchtype=author&query=Li%2C+X">Xingxing Li</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+L">Lin Liu</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+S">Shouda Liu</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+S">Sichao Liu</a> , et al. (21 additional authors not shown) </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.02430v1-abstract-short" style="display: inline;"> We introduce Seed-TTS, a family of large-scale autoregressive text-to-speech (TTS) models capable of generating speech that is virtually indistinguishable from human speech. Seed-TTS serves as a foundation model for speech generation and excels in speech in-context learning, achieving performance in speaker similarity and naturalness that matches ground truth human speech in both objective and sub… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.02430v1-abstract-full').style.display = 'inline'; document.getElementById('2406.02430v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.02430v1-abstract-full" style="display: none;"> We introduce Seed-TTS, a family of large-scale autoregressive text-to-speech (TTS) models capable of generating speech that is virtually indistinguishable from human speech. Seed-TTS serves as a foundation model for speech generation and excels in speech in-context learning, achieving performance in speaker similarity and naturalness that matches ground truth human speech in both objective and subjective evaluations. With fine-tuning, we achieve even higher subjective scores across these metrics. Seed-TTS offers superior controllability over various speech attributes such as emotion and is capable of generating highly expressive and diverse speech for speakers in the wild. Furthermore, we propose a self-distillation method for speech factorization, as well as a reinforcement learning approach to enhance model robustness, speaker similarity, and controllability. We additionally present a non-autoregressive (NAR) variant of the Seed-TTS model, named $\text{Seed-TTS}_\text{DiT}$, which utilizes a fully diffusion-based architecture. Unlike previous NAR-based TTS systems, $\text{Seed-TTS}_\text{DiT}$ does not depend on pre-estimated phoneme durations and performs speech generation through end-to-end processing. We demonstrate that this variant achieves comparable performance to the language model-based variant and showcase its effectiveness in speech editing. We encourage readers to listen to demos at \url{https://bytedancespeech.github.io/seedtts_tech_report}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.02430v1-abstract-full').style.display = 'none'; document.getElementById('2406.02430v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.11945">arXiv:2403.11945</a> <span> [<a href="https://arxiv.org/pdf/2403.11945">pdf</a>, <a href="https://arxiv.org/format/2403.11945">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Optimization and Control">math.OC</span> </div> </div> <p class="title is-5 mathjax"> Kernel Modelling of Fading Memory Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yongkang Huo</a>, <a href="/search/eess?searchtype=author&query=Chaffey%2C+T">Thomas Chaffey</a>, <a href="/search/eess?searchtype=author&query=Sepulchre%2C+R">Rodolphe Sepulchre</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2403.11945v1-abstract-short" style="display: inline;"> The paper introduces a kernel-based framework to model and identify time-invariant systems with the fading memory property. The key departure from the previous literature is to bypass the state-space representation of the model. Instead, a kernel representation is used to directly model the memory functional that maps past inputs to the present output. We explore the versatility of this approach t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.11945v1-abstract-full').style.display = 'inline'; document.getElementById('2403.11945v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.11945v1-abstract-full" style="display: none;"> The paper introduces a kernel-based framework to model and identify time-invariant systems with the fading memory property. The key departure from the previous literature is to bypass the state-space representation of the model. Instead, a kernel representation is used to directly model the memory functional that maps past inputs to the present output. We explore the versatility of this approach to encode important system properties in the hyperparameters of the kernel. The approach is illustrated on the Hodgkin and Huxley model of neuronal excitability. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.11945v1-abstract-full').style.display = 'none'; document.getElementById('2403.11945v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.11626">arXiv:2403.11626</a> <span> [<a href="https://arxiv.org/pdf/2403.11626">pdf</a>, <a href="https://arxiv.org/format/2403.11626">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Graphics">cs.GR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multimedia">cs.MM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> </div> </div> <p class="title is-5 mathjax"> QEAN: Quaternion-Enhanced Attention Network for Visual Dance Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zhou%2C+Z">Zhizhen Zhou</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yejing Huo</a>, <a href="/search/eess?searchtype=author&query=Huang%2C+G">Guoheng Huang</a>, <a href="/search/eess?searchtype=author&query=Zeng%2C+A">An Zeng</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+X">Xuhang Chen</a>, <a href="/search/eess?searchtype=author&query=Huang%2C+L">Lian Huang</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Z">Zinuo Li</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2403.11626v1-abstract-short" style="display: inline;"> The study of music-generated dance is a novel and challenging Image generation task. It aims to input a piece of music and seed motions, then generate natural dance movements for the subsequent music. Transformer-based methods face challenges in time series prediction tasks related to human movements and music due to their struggle in capturing the nonlinear relationship and temporal aspects. This… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.11626v1-abstract-full').style.display = 'inline'; document.getElementById('2403.11626v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.11626v1-abstract-full" style="display: none;"> The study of music-generated dance is a novel and challenging Image generation task. It aims to input a piece of music and seed motions, then generate natural dance movements for the subsequent music. Transformer-based methods face challenges in time series prediction tasks related to human movements and music due to their struggle in capturing the nonlinear relationship and temporal aspects. This can lead to issues like joint deformation, role deviation, floating, and inconsistencies in dance movements generated in response to the music. In this paper, we propose a Quaternion-Enhanced Attention Network (QEAN) for visual dance synthesis from a quaternion perspective, which consists of a Spin Position Embedding (SPE) module and a Quaternion Rotary Attention (QRA) module. First, SPE embeds position information into self-attention in a rotational manner, leading to better learning of features of movement sequences and audio sequences, and improved understanding of the connection between music and dance. Second, QRA represents and fuses 3D motion features and audio features in the form of a series of quaternions, enabling the model to better learn the temporal coordination of music and dance under the complex temporal cycle conditions of dance generation. Finally, we conducted experiments on the dataset AIST++, and the results show that our approach achieves better and more robust performance in generating accurate, high-quality dance movements. Our source code and dataset can be available from https://github.com/MarasyZZ/QEAN and https://google.github.io/aistplusplus_dataset respectively. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.11626v1-abstract-full').style.display = 'none'; document.getElementById('2403.11626v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by The Visual Computer Journal</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.06640">arXiv:2403.06640</a> <span> [<a href="https://arxiv.org/pdf/2403.06640">pdf</a>, <a href="https://arxiv.org/format/2403.06640">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Optimization and Control">math.OC</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/LCSYS.2024.3408065">10.1109/LCSYS.2024.3408065 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Passive iFIR Filters for Data-Driven Control </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Wang%2C+Z">Zixing Wang</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yongkang Huo</a>, <a href="/search/eess?searchtype=author&query=Forni%2C+F">Fulvio Forni</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2403.06640v2-abstract-short" style="display: inline;"> We consider the design of a new class of passive iFIR controllers given by the parallel action of an integrator and a finite impulse response filter. iFIRs are more expressive than PID controllers but retain their features and simplicity. The paper provides a model-free data-driven design for passive iFIR controllers based on virtual reference feedback tuning. Passivity is enforced through constra… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.06640v2-abstract-full').style.display = 'inline'; document.getElementById('2403.06640v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.06640v2-abstract-full" style="display: none;"> We consider the design of a new class of passive iFIR controllers given by the parallel action of an integrator and a finite impulse response filter. iFIRs are more expressive than PID controllers but retain their features and simplicity. The paper provides a model-free data-driven design for passive iFIR controllers based on virtual reference feedback tuning. Passivity is enforced through constrained optimization (three different formulations are discussed). The proposed design does not rely on large datasets or accurate plant models. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.06640v2-abstract-full').style.display = 'none'; document.getElementById('2403.06640v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 29 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 11 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">6 pages, 7 figures, Accepted by IEEE Control Systems Letters (L-CSS) with the option to present it to 2024 Conference on Decision and Control (CDC 2024)</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> IEEE Control Systems Letters, vol. 8, pp. 1289-1294, 2024 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.19286">arXiv:2402.19286</a> <span> [<a href="https://arxiv.org/pdf/2402.19286">pdf</a>, <a href="https://arxiv.org/format/2402.19286">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> PrPSeg: Universal Proposition Learning for Panoramic Renal Pathology Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Deng%2C+R">Ruining Deng</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Q">Quan Liu</a>, <a href="/search/eess?searchtype=author&query=Cui%2C+C">Can Cui</a>, <a href="/search/eess?searchtype=author&query=Yao%2C+T">Tianyuan Yao</a>, <a href="/search/eess?searchtype=author&query=Yue%2C+J">Jialin Yue</a>, <a href="/search/eess?searchtype=author&query=Xiong%2C+J">Juming Xiong</a>, <a href="/search/eess?searchtype=author&query=Yu%2C+L">Lining Yu</a>, <a href="/search/eess?searchtype=author&query=Wu%2C+Y">Yifei Wu</a>, <a href="/search/eess?searchtype=author&query=Yin%2C+M">Mengmeng Yin</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+Y">Yu Wang</a>, <a href="/search/eess?searchtype=author&query=Zhao%2C+S">Shilin Zhao</a>, <a href="/search/eess?searchtype=author&query=Tang%2C+Y">Yucheng Tang</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+H">Haichun Yang</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yuankai Huo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2402.19286v2-abstract-short" style="display: inline;"> Understanding the anatomy of renal pathology is crucial for advancing disease diagnostics, treatment evaluation, and clinical research. The complex kidney system comprises various components across multiple levels, including regions (cortex, medulla), functional units (glomeruli, tubules), and cells (podocytes, mesangial cells in glomerulus). Prior studies have predominantly overlooked the intrica… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.19286v2-abstract-full').style.display = 'inline'; document.getElementById('2402.19286v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.19286v2-abstract-full" style="display: none;"> Understanding the anatomy of renal pathology is crucial for advancing disease diagnostics, treatment evaluation, and clinical research. The complex kidney system comprises various components across multiple levels, including regions (cortex, medulla), functional units (glomeruli, tubules), and cells (podocytes, mesangial cells in glomerulus). Prior studies have predominantly overlooked the intricate spatial interrelations among objects from clinical knowledge. In this research, we introduce a novel universal proposition learning approach, called panoramic renal pathology segmentation (PrPSeg), designed to segment comprehensively panoramic structures within kidney by integrating extensive knowledge of kidney anatomy. In this paper, we propose (1) the design of a comprehensive universal proposition matrix for renal pathology, facilitating the incorporation of classification and spatial relationships into the segmentation process; (2) a token-based dynamic head single network architecture, with the improvement of the partial label image segmentation and capability for future data enlargement; and (3) an anatomy loss function, quantifying the inter-object relationships across the kidney. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.19286v2-abstract-full').style.display = 'none'; document.getElementById('2402.19286v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 29 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">IEEE / CVF Computer Vision and Pattern Recognition Conference 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.00028">arXiv:2402.00028</a> <span> [<a href="https://arxiv.org/pdf/2402.00028">pdf</a>, <a href="https://arxiv.org/format/2402.00028">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Graphics">cs.GR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> Neural Rendering and Its Hardware Acceleration: A Review </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Yan%2C+X">Xinkai Yan</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+J">Jieting Xu</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yuchi Huo</a>, <a href="/search/eess?searchtype=author&query=Bao%2C+H">Hujun Bao</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2402.00028v1-abstract-short" style="display: inline;"> Neural rendering is a new image and video generation method based on deep learning. It combines the deep learning model with the physical knowledge of computer graphics, to obtain a controllable and realistic scene model, and realize the control of scene attributes such as lighting, camera parameters, posture and so on. On the one hand, neural rendering can not only make full use of the advantages… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.00028v1-abstract-full').style.display = 'inline'; document.getElementById('2402.00028v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.00028v1-abstract-full" style="display: none;"> Neural rendering is a new image and video generation method based on deep learning. It combines the deep learning model with the physical knowledge of computer graphics, to obtain a controllable and realistic scene model, and realize the control of scene attributes such as lighting, camera parameters, posture and so on. On the one hand, neural rendering can not only make full use of the advantages of deep learning to accelerate the traditional forward rendering process, but also provide new solutions for specific tasks such as inverse rendering and 3D reconstruction. On the other hand, the design of innovative hardware structures that adapt to the neural rendering pipeline breaks through the parallel computing and power consumption bottleneck of existing graphics processors, which is expected to provide important support for future key areas such as virtual and augmented reality, film and television creation and digital entertainment, artificial intelligence and the metaverse. In this paper, we review the technical connotation, main challenges, and research progress of neural rendering. On this basis, we analyze the common requirements of neural rendering pipeline for hardware acceleration and the characteristics of the current hardware acceleration architecture, and then discuss the design challenges of neural rendering processor architecture. Finally, the future development trend of neural rendering processor architecture is prospected. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.00028v1-abstract-full').style.display = 'none'; document.getElementById('2402.00028v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2401.06798">arXiv:2401.06798</a> <span> [<a href="https://arxiv.org/pdf/2401.06798">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Neurons and Cognition">q-bio.NC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> Evaluation of Mean Shift, ComBat, and CycleGAN for Harmonizing Brain Connectivity Matrices Across Sites </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Xu%2C+H">Hanliang Xu</a>, <a href="/search/eess?searchtype=author&query=Newlin%2C+N+R">Nancy R. Newlin</a>, <a href="/search/eess?searchtype=author&query=Kim%2C+M+E">Michael E. Kim</a>, <a href="/search/eess?searchtype=author&query=Gao%2C+C">Chenyu Gao</a>, <a href="/search/eess?searchtype=author&query=Kanakaraj%2C+P">Praitayini Kanakaraj</a>, <a href="/search/eess?searchtype=author&query=Krishnan%2C+A+R">Aravind R. Krishnan</a>, <a href="/search/eess?searchtype=author&query=Remedios%2C+L+W">Lucas W. Remedios</a>, <a href="/search/eess?searchtype=author&query=Khairi%2C+N+M">Nazirah Mohd Khairi</a>, <a href="/search/eess?searchtype=author&query=Pechman%2C+K">Kimberly Pechman</a>, <a href="/search/eess?searchtype=author&query=Archer%2C+D">Derek Archer</a>, <a href="/search/eess?searchtype=author&query=Hohman%2C+T+J">Timothy J. Hohman</a>, <a href="/search/eess?searchtype=author&query=Jefferson%2C+A+L">Angela L. Jefferson</a>, <a href="/search/eess?searchtype=author&query=Team%2C+T+B+S">The BIOCARD Study Team</a>, <a href="/search/eess?searchtype=author&query=Isgum%2C+I">Ivana Isgum</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yuankai Huo</a>, <a href="/search/eess?searchtype=author&query=Moyer%2C+D">Daniel Moyer</a>, <a href="/search/eess?searchtype=author&query=Schilling%2C+K+G">Kurt G. Schilling</a>, <a href="/search/eess?searchtype=author&query=Landman%2C+B+A">Bennett A. Landman</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2401.06798v2-abstract-short" style="display: inline;"> Connectivity matrices derived from diffusion MRI (dMRI) provide an interpretable and generalizable way of understanding the human brain connectome. However, dMRI suffers from inter-site and between-scanner variation, which impedes analysis across datasets to improve robustness and reproducibility of results. To evaluate different harmonization approaches on connectivity matrices, we compared graph… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.06798v2-abstract-full').style.display = 'inline'; document.getElementById('2401.06798v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.06798v2-abstract-full" style="display: none;"> Connectivity matrices derived from diffusion MRI (dMRI) provide an interpretable and generalizable way of understanding the human brain connectome. However, dMRI suffers from inter-site and between-scanner variation, which impedes analysis across datasets to improve robustness and reproducibility of results. To evaluate different harmonization approaches on connectivity matrices, we compared graph measures derived from these matrices before and after applying three harmonization techniques: mean shift, ComBat, and CycleGAN. The sample comprises 168 age-matched, sex-matched normal subjects from two studies: the Vanderbilt Memory and Aging Project (VMAP) and the Biomarkers of Cognitive Decline Among Normal Individuals (BIOCARD). First, we plotted the graph measures and used coefficient of variation (CoV) and the Mann-Whitney U test to evaluate different methods' effectiveness in removing site effects on the matrices and the derived graph measures. ComBat effectively eliminated site effects for global efficiency and modularity and outperformed the other two methods. However, all methods exhibited poor performance when harmonizing average betweenness centrality. Second, we tested whether our harmonization methods preserved correlations between age and graph measures. All methods except for CycleGAN in one direction improved correlations between age and global efficiency and between age and modularity from insignificant to significant with p-values less than 0.05. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.06798v2-abstract-full').style.display = 'none'; document.getElementById('2401.06798v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 8 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">11 pages, 5 figures, to be published in SPIE Medical Imaging 2024: Image Processing</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2401.03060">arXiv:2401.03060</a> <span> [<a href="https://arxiv.org/pdf/2401.03060">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1117/1.JMI.11.6.064004">10.1117/1.JMI.11.6.064004 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Super-resolution multi-contrast unbiased eye atlases with deep probabilistic refinement </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Lee%2C+H+H">Ho Hin Lee</a>, <a href="/search/eess?searchtype=author&query=Saunders%2C+A+M">Adam M. Saunders</a>, <a href="/search/eess?searchtype=author&query=Kim%2C+M+E">Michael E. Kim</a>, <a href="/search/eess?searchtype=author&query=Remedios%2C+S+W">Samuel W. Remedios</a>, <a href="/search/eess?searchtype=author&query=Remedios%2C+L+W">Lucas W. Remedios</a>, <a href="/search/eess?searchtype=author&query=Tang%2C+Y">Yucheng Tang</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+Q">Qi Yang</a>, <a href="/search/eess?searchtype=author&query=Yu%2C+X">Xin Yu</a>, <a href="/search/eess?searchtype=author&query=Bao%2C+S">Shunxing Bao</a>, <a href="/search/eess?searchtype=author&query=Cho%2C+C">Chloe Cho</a>, <a href="/search/eess?searchtype=author&query=Mawn%2C+L+A">Louise A. Mawn</a>, <a href="/search/eess?searchtype=author&query=Rex%2C+T+S">Tonia S. Rex</a>, <a href="/search/eess?searchtype=author&query=Schey%2C+K+L">Kevin L. Schey</a>, <a href="/search/eess?searchtype=author&query=Dewey%2C+B+E">Blake E. Dewey</a>, <a href="/search/eess?searchtype=author&query=Spraggins%2C+J+M">Jeffrey M. Spraggins</a>, <a href="/search/eess?searchtype=author&query=Prince%2C+J+L">Jerry L. Prince</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yuankai Huo</a>, <a href="/search/eess?searchtype=author&query=Landman%2C+B+A">Bennett A. Landman</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2401.03060v3-abstract-short" style="display: inline;"> Purpose: Eye morphology varies significantly across the population, especially for the orbit and optic nerve. These variations limit the feasibility and robustness of generalizing population-wise features of eye organs to an unbiased spatial reference. Approach: To tackle these limitations, we propose a process for creating high-resolution unbiased eye atlases. First, to restore spatial details… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.03060v3-abstract-full').style.display = 'inline'; document.getElementById('2401.03060v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.03060v3-abstract-full" style="display: none;"> Purpose: Eye morphology varies significantly across the population, especially for the orbit and optic nerve. These variations limit the feasibility and robustness of generalizing population-wise features of eye organs to an unbiased spatial reference. Approach: To tackle these limitations, we propose a process for creating high-resolution unbiased eye atlases. First, to restore spatial details from scans with a low through-plane resolution compared to a high in-plane resolution, we apply a deep learning-based super-resolution algorithm. Then, we generate an initial unbiased reference with an iterative metric-based registration using a small portion of subject scans. We register the remaining scans to this template and refine the template using an unsupervised deep probabilistic approach that generates a more expansive deformation field to enhance the organ boundary alignment. We demonstrate this framework using magnetic resonance images across four different tissue contrasts, generating four atlases in separate spatial alignments. Results: For each tissue contrast, we find a significant improvement using the Wilcoxon signed-rank test in the average Dice score across four labeled regions compared to a standard registration framework consisting of rigid, affine, and deformable transformations. These results highlight the effective alignment of eye organs and boundaries using our proposed process. Conclusions: By combining super-resolution preprocessing and deep probabilistic models, we address the challenge of generating an eye atlas to serve as a standardized reference across a largely variable population. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.03060v3-abstract-full').style.display = 'none'; document.getElementById('2401.03060v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 5 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Published in SPIE Journal of Medical Imaging (https://doi.org/10.1117/1.JMI.11.6.064004). 27 pages, 6 figures</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> J. Med. Imag. 11(6), 064004 (2024) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2311.03500">arXiv:2311.03500</a> <span> [<a href="https://arxiv.org/pdf/2311.03500">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Neurons and Cognition">q-bio.NC</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1117/12.3006525">10.1117/12.3006525 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Predicting Age from White Matter Diffusivity with Residual Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Gao%2C+C">Chenyu Gao</a>, <a href="/search/eess?searchtype=author&query=Kim%2C+M+E">Michael E. Kim</a>, <a href="/search/eess?searchtype=author&query=Lee%2C+H+H">Ho Hin Lee</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+Q">Qi Yang</a>, <a href="/search/eess?searchtype=author&query=Khairi%2C+N+M">Nazirah Mohd Khairi</a>, <a href="/search/eess?searchtype=author&query=Kanakaraj%2C+P">Praitayini Kanakaraj</a>, <a href="/search/eess?searchtype=author&query=Newlin%2C+N+R">Nancy R. Newlin</a>, <a href="/search/eess?searchtype=author&query=Archer%2C+D+B">Derek B. Archer</a>, <a href="/search/eess?searchtype=author&query=Jefferson%2C+A+L">Angela L. Jefferson</a>, <a href="/search/eess?searchtype=author&query=Taylor%2C+W+D">Warren D. Taylor</a>, <a href="/search/eess?searchtype=author&query=Boyd%2C+B+D">Brian D. Boyd</a>, <a href="/search/eess?searchtype=author&query=Beason-Held%2C+L+L">Lori L. Beason-Held</a>, <a href="/search/eess?searchtype=author&query=Resnick%2C+S+M">Susan M. Resnick</a>, <a href="/search/eess?searchtype=author&query=Team%2C+T+B+S">The BIOCARD Study Team</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yuankai Huo</a>, <a href="/search/eess?searchtype=author&query=Van+Schaik%2C+K+D">Katherine D. Van Schaik</a>, <a href="/search/eess?searchtype=author&query=Schilling%2C+K+G">Kurt G. Schilling</a>, <a href="/search/eess?searchtype=author&query=Moyer%2C+D">Daniel Moyer</a>, <a href="/search/eess?searchtype=author&query=I%C5%A1gum%2C+I">Ivana I拧gum</a>, <a href="/search/eess?searchtype=author&query=Landman%2C+B+A">Bennett A. Landman</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2311.03500v2-abstract-short" style="display: inline;"> Imaging findings inconsistent with those expected at specific chronological age ranges may serve as early indicators of neurological disorders and increased mortality risk. Estimation of chronological age, and deviations from expected results, from structural MRI data has become an important task for developing biomarkers that are sensitive to such deviations. Complementary to structural analysis,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.03500v2-abstract-full').style.display = 'inline'; document.getElementById('2311.03500v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2311.03500v2-abstract-full" style="display: none;"> Imaging findings inconsistent with those expected at specific chronological age ranges may serve as early indicators of neurological disorders and increased mortality risk. Estimation of chronological age, and deviations from expected results, from structural MRI data has become an important task for developing biomarkers that are sensitive to such deviations. Complementary to structural analysis, diffusion tensor imaging (DTI) has proven effective in identifying age-related microstructural changes within the brain white matter, thereby presenting itself as a promising additional modality for brain age prediction. Although early studies have sought to harness DTI's advantages for age estimation, there is no evidence that the success of this prediction is owed to the unique microstructural and diffusivity features that DTI provides, rather than the macrostructural features that are also available in DTI data. Therefore, we seek to develop white-matter-specific age estimation to capture deviations from normal white matter aging. Specifically, we deliberately disregard the macrostructural information when predicting age from DTI scalar images, using two distinct methods. The first method relies on extracting only microstructural features from regions of interest. The second applies 3D residual neural networks (ResNets) to learn features directly from the images, which are non-linearly registered and warped to a template to minimize macrostructural variations. When tested on unseen data, the first method yields mean absolute error (MAE) of 6.11 years for cognitively normal participants and MAE of 6.62 years for cognitively impaired participants, while the second method achieves MAE of 4.69 years for cognitively normal participants and MAE of 4.96 years for cognitively impaired participants. We find that the ResNet model captures subtler, non-macrostructural features for brain age prediction. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.03500v2-abstract-full').style.display = 'none'; document.getElementById('2311.03500v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 6 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">SPIE Medical Imaging: Image Processing. San Diego, CA. February 2024 (accepted as poster presentation)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2309.09392">arXiv:2309.09392</a> <span> [<a href="https://arxiv.org/pdf/2309.09392">pdf</a>, <a href="https://arxiv.org/format/2309.09392">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Deep conditional generative models for longitudinal single-slice abdominal computed tomography harmonization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Yu%2C+X">Xin Yu</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+Q">Qi Yang</a>, <a href="/search/eess?searchtype=author&query=Tang%2C+Y">Yucheng Tang</a>, <a href="/search/eess?searchtype=author&query=Gao%2C+R">Riqiang Gao</a>, <a href="/search/eess?searchtype=author&query=Bao%2C+S">Shunxing Bao</a>, <a href="/search/eess?searchtype=author&query=Cai%2C+L+Y">Leon Y. Cai</a>, <a href="/search/eess?searchtype=author&query=Lee%2C+H+H">Ho Hin Lee</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yuankai Huo</a>, <a href="/search/eess?searchtype=author&query=Moore%2C+A+Z">Ann Zenobia Moore</a>, <a href="/search/eess?searchtype=author&query=Ferrucci%2C+L">Luigi Ferrucci</a>, <a href="/search/eess?searchtype=author&query=Landman%2C+B+A">Bennett A. Landman</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2309.09392v1-abstract-short" style="display: inline;"> Two-dimensional single-slice abdominal computed tomography (CT) provides a detailed tissue map with high resolution allowing quantitative characterization of relationships between health conditions and aging. However, longitudinal analysis of body composition changes using these scans is difficult due to positional variation between slices acquired in different years, which leading to different or… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.09392v1-abstract-full').style.display = 'inline'; document.getElementById('2309.09392v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2309.09392v1-abstract-full" style="display: none;"> Two-dimensional single-slice abdominal computed tomography (CT) provides a detailed tissue map with high resolution allowing quantitative characterization of relationships between health conditions and aging. However, longitudinal analysis of body composition changes using these scans is difficult due to positional variation between slices acquired in different years, which leading to different organs/tissues captured. To address this issue, we propose C-SliceGen, which takes an arbitrary axial slice in the abdominal region as a condition and generates a pre-defined vertebral level slice by estimating structural changes in the latent space. Our experiments on 2608 volumetric CT data from two in-house datasets and 50 subjects from the 2015 Multi-Atlas Abdomen Labeling Challenge dataset (BTCV) Challenge demonstrate that our model can generate high-quality images that are realistic and similar. We further evaluate our method's capability to harmonize longitudinal positional variation on 1033 subjects from the Baltimore Longitudinal Study of Aging (BLSA) dataset, which contains longitudinal single abdominal slices, and confirmed that our method can harmonize the slice positional variance in terms of visceral fat area. This approach provides a promising direction for mapping slices from different vertebral levels to a target slice and reducing positional variance for single-slice longitudinal analysis. The source code is available at: https://github.com/MASILab/C-SliceGen. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.09392v1-abstract-full').style.display = 'none'; document.getElementById('2309.09392v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 September, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2309.07136">arXiv:2309.07136</a> <span> [<a href="https://arxiv.org/pdf/2309.07136">pdf</a>, <a href="https://arxiv.org/format/2309.07136">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Applications">stat.AP</span> </div> </div> <p class="title is-5 mathjax"> Masked Transformer for Electrocardiogram Classification </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zhou%2C+Y">Ya Zhou</a>, <a href="/search/eess?searchtype=author&query=Diao%2C+X">Xiaolin Diao</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yanni Huo</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Y">Yang Liu</a>, <a href="/search/eess?searchtype=author&query=Fan%2C+X">Xiaohan Fan</a>, <a href="/search/eess?searchtype=author&query=Zhao%2C+W">Wei Zhao</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2309.07136v3-abstract-short" style="display: inline;"> Electrocardiogram (ECG) is one of the most important diagnostic tools in clinical applications. With the advent of advanced algorithms, various deep learning models have been adopted for ECG tasks. However, the potential of Transformer for ECG data has not been fully realized, despite their widespread success in computer vision and natural language processing. In this work, we present Masked Trans… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.07136v3-abstract-full').style.display = 'inline'; document.getElementById('2309.07136v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2309.07136v3-abstract-full" style="display: none;"> Electrocardiogram (ECG) is one of the most important diagnostic tools in clinical applications. With the advent of advanced algorithms, various deep learning models have been adopted for ECG tasks. However, the potential of Transformer for ECG data has not been fully realized, despite their widespread success in computer vision and natural language processing. In this work, we present Masked Transformer for ECG classification (MTECG), a simple yet effective method which significantly outperforms recent state-of-the-art algorithms in ECG classification. Our approach adapts the image-based masked autoencoders to self-supervised representation learning from ECG time series. We utilize a lightweight Transformer for the encoder and a 1-layer Transformer for the decoder. The ECG signal is split into a sequence of non-overlapping segments along the time dimension, and learnable positional embeddings are added to preserve the sequential information. We construct the Fuwai dataset comprising 220,251 ECG recordings with a broad range of diagnoses, annotated by medical experts, to explore the potential of Transformer. A strong pre-training and fine-tuning recipe is proposed from the empirical study. The experiments demonstrate that the proposed method increases the macro F1 scores by 3.4%-27.5% on the Fuwai dataset, 9.9%-32.0% on the PTB-XL dataset, and 9.4%-39.1% on a multicenter dataset, compared to the alternative methods. We hope that this study could direct future research on the application of Transformer to more ECG tasks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.07136v3-abstract-full').style.display = 'none'; document.getElementById('2309.07136v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 31 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">more experimental results; more implementation details; different abstracts</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2309.04071">arXiv:2309.04071</a> <span> [<a href="https://arxiv.org/pdf/2309.04071">pdf</a>, <a href="https://arxiv.org/format/2309.04071">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1117/12.3009084">10.1117/12.3009084 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Enhancing Hierarchical Transformers for Whole Brain Segmentation with Intracranial Measurements Integration </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Yu%2C+X">Xin Yu</a>, <a href="/search/eess?searchtype=author&query=Tang%2C+Y">Yucheng Tang</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+Q">Qi Yang</a>, <a href="/search/eess?searchtype=author&query=Lee%2C+H+H">Ho Hin Lee</a>, <a href="/search/eess?searchtype=author&query=Bao%2C+S">Shunxing Bao</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yuankai Huo</a>, <a href="/search/eess?searchtype=author&query=Landman%2C+B+A">Bennett A. Landman</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2309.04071v2-abstract-short" style="display: inline;"> Whole brain segmentation with magnetic resonance imaging (MRI) enables the non-invasive measurement of brain regions, including total intracranial volume (TICV) and posterior fossa volume (PFV). Enhancing the existing whole brain segmentation methodology to incorporate intracranial measurements offers a heightened level of comprehensiveness in the analysis of brain structures. Despite its potentia… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.04071v2-abstract-full').style.display = 'inline'; document.getElementById('2309.04071v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2309.04071v2-abstract-full" style="display: none;"> Whole brain segmentation with magnetic resonance imaging (MRI) enables the non-invasive measurement of brain regions, including total intracranial volume (TICV) and posterior fossa volume (PFV). Enhancing the existing whole brain segmentation methodology to incorporate intracranial measurements offers a heightened level of comprehensiveness in the analysis of brain structures. Despite its potential, the task of generalizing deep learning techniques for intracranial measurements faces data availability constraints due to limited manually annotated atlases encompassing whole brain and TICV/PFV labels. In this paper, we enhancing the hierarchical transformer UNesT for whole brain segmentation to achieve segmenting whole brain with 133 classes and TICV/PFV simultaneously. To address the problem of data scarcity, the model is first pretrained on 4859 T1-weighted (T1w) 3D volumes sourced from 8 different sites. These volumes are processed through a multi-atlas segmentation pipeline for label generation, while TICV/PFV labels are unavailable. Subsequently, the model is finetuned with 45 T1w 3D volumes from Open Access Series Imaging Studies (OASIS) where both 133 whole brain classes and TICV/PFV labels are available. We evaluate our method with Dice similarity coefficients(DSC). We show that our model is able to conduct precise TICV/PFV estimation while maintaining the 132 brain regions performance at a comparable level. Code and trained model are available at: https://github.com/MASILab/UNesT/tree/main/wholebrainSeg. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.04071v2-abstract-full').style.display = 'none'; document.getElementById('2309.04071v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 7 September, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2309.02563">arXiv:2309.02563</a> <span> [<a href="https://arxiv.org/pdf/2309.02563">pdf</a>, <a href="https://arxiv.org/format/2309.02563">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Evaluation Kidney Layer Segmentation on Whole Slide Imaging using Convolutional Neural Networks and Transformers </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Liu%2C+M">Muhao Liu</a>, <a href="/search/eess?searchtype=author&query=Qi%2C+C">Chenyang Qi</a>, <a href="/search/eess?searchtype=author&query=Bao%2C+S">Shunxing Bao</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Q">Quan Liu</a>, <a href="/search/eess?searchtype=author&query=Deng%2C+R">Ruining Deng</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+Y">Yu Wang</a>, <a href="/search/eess?searchtype=author&query=Zhao%2C+S">Shilin Zhao</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+H">Haichun Yang</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yuankai Huo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2309.02563v1-abstract-short" style="display: inline;"> The segmentation of kidney layer structures, including cortex, outer stripe, inner stripe, and inner medulla within human kidney whole slide images (WSI) plays an essential role in automated image analysis in renal pathology. However, the current manual segmentation process proves labor-intensive and infeasible for handling the extensive digital pathology images encountered at a large scale. In re… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.02563v1-abstract-full').style.display = 'inline'; document.getElementById('2309.02563v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2309.02563v1-abstract-full" style="display: none;"> The segmentation of kidney layer structures, including cortex, outer stripe, inner stripe, and inner medulla within human kidney whole slide images (WSI) plays an essential role in automated image analysis in renal pathology. However, the current manual segmentation process proves labor-intensive and infeasible for handling the extensive digital pathology images encountered at a large scale. In response, the realm of digital renal pathology has seen the emergence of deep learning-based methodologies. However, very few, if any, deep learning based approaches have been applied to kidney layer structure segmentation. Addressing this gap, this paper assesses the feasibility of performing deep learning based approaches on kidney layer structure segmetnation. This study employs the representative convolutional neural network (CNN) and Transformer segmentation approaches, including Swin-Unet, Medical-Transformer, TransUNet, U-Net, PSPNet, and DeepLabv3+. We quantitatively evaluated six prevalent deep learning models on renal cortex layer segmentation using mice kidney WSIs. The empirical results stemming from our approach exhibit compelling advancements, as evidenced by a decent Mean Intersection over Union (mIoU) index. The results demonstrate that Transformer models generally outperform CNN-based models. By enabling a quantitative evaluation of renal cortical structures, deep learning approaches are promising to empower these medical professionals to make more informed kidney layer segmentation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.02563v1-abstract-full').style.display = 'none'; document.getElementById('2309.02563v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 September, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2308.08974">arXiv:2308.08974</a> <span> [<a href="https://arxiv.org/pdf/2308.08974">pdf</a>, <a href="https://arxiv.org/format/2308.08974">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Eosinophils Instance Object Segmentation on Whole Slide Imaging Using Multi-label Circle Representation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Liu%2C+Y">Yilin Liu</a>, <a href="/search/eess?searchtype=author&query=Deng%2C+R">Ruining Deng</a>, <a href="/search/eess?searchtype=author&query=Xiong%2C+J">Juming Xiong</a>, <a href="/search/eess?searchtype=author&query=Tyree%2C+R+N">Regina N Tyree</a>, <a href="/search/eess?searchtype=author&query=Correa%2C+H">Hernan Correa</a>, <a href="/search/eess?searchtype=author&query=Hiremath%2C+G">Girish Hiremath</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+Y">Yaohong Wang</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yuankai Huo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2308.08974v1-abstract-short" style="display: inline;"> Eosinophilic esophagitis (EoE) is a chronic and relapsing disease characterized by esophageal inflammation. Symptoms of EoE include difficulty swallowing, food impaction, and chest pain which significantly impact the quality of life, resulting in nutritional impairments, social limitations, and psychological distress. The diagnosis of EoE is typically performed with a threshold (15 to 20) of eosin… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.08974v1-abstract-full').style.display = 'inline'; document.getElementById('2308.08974v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.08974v1-abstract-full" style="display: none;"> Eosinophilic esophagitis (EoE) is a chronic and relapsing disease characterized by esophageal inflammation. Symptoms of EoE include difficulty swallowing, food impaction, and chest pain which significantly impact the quality of life, resulting in nutritional impairments, social limitations, and psychological distress. The diagnosis of EoE is typically performed with a threshold (15 to 20) of eosinophils (Eos) per high-power field (HPF). Since the current counting process of Eos is a resource-intensive process for human pathologists, automatic methods are desired. Circle representation has been shown as a more precise, yet less complicated, representation for automatic instance cell segmentation such as CircleSnake approach. However, the CircleSnake was designed as a single-label model, which is not able to deal with multi-label scenarios. In this paper, we propose the multi-label CircleSnake model for instance segmentation on Eos. It extends the original CircleSnake model from a single-label design to a multi-label model, allowing segmentation of multiple object types. Experimental results illustrate the CircleSnake model's superiority over the traditional Mask R-CNN model and DeepSnake model in terms of average precision (AP) in identifying and segmenting eosinophils, thereby enabling enhanced characterization of EoE. This automated approach holds promise for streamlining the assessment process and improving diagnostic accuracy in EoE analysis. The source code has been made publicly available at https://github.com/yilinliu610730/EoE. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.08974v1-abstract-full').style.display = 'none'; document.getElementById('2308.08974v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2308.06333">arXiv:2308.06333</a> <span> [<a href="https://arxiv.org/pdf/2308.06333">pdf</a>, <a href="https://arxiv.org/format/2308.06333">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Deep Learning-Based Open Source Toolkit for Eosinophil Detection in Pediatric Eosinophilic Esophagitis </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Xiong%2C+J">Juming Xiong</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Y">Yilin Liu</a>, <a href="/search/eess?searchtype=author&query=Deng%2C+R">Ruining Deng</a>, <a href="/search/eess?searchtype=author&query=Tyree%2C+R+N">Regina N Tyree</a>, <a href="/search/eess?searchtype=author&query=Correa%2C+H">Hernan Correa</a>, <a href="/search/eess?searchtype=author&query=Hiremath%2C+G">Girish Hiremath</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+Y">Yaohong Wang</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yuankai Huo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2308.06333v1-abstract-short" style="display: inline;"> Eosinophilic Esophagitis (EoE) is a chronic, immune/antigen-mediated esophageal disease, characterized by symptoms related to esophageal dysfunction and histological evidence of eosinophil-dominant inflammation. Owing to the intricate microscopic representation of EoE in imaging, current methodologies which depend on manual identification are not only labor-intensive but also prone to inaccuracies… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.06333v1-abstract-full').style.display = 'inline'; document.getElementById('2308.06333v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.06333v1-abstract-full" style="display: none;"> Eosinophilic Esophagitis (EoE) is a chronic, immune/antigen-mediated esophageal disease, characterized by symptoms related to esophageal dysfunction and histological evidence of eosinophil-dominant inflammation. Owing to the intricate microscopic representation of EoE in imaging, current methodologies which depend on manual identification are not only labor-intensive but also prone to inaccuracies. In this study, we develop an open-source toolkit, named Open-EoE, to perform end-to-end whole slide image (WSI) level eosinophil (Eos) detection using one line of command via Docker. Specifically, the toolkit supports three state-of-the-art deep learning-based object detection models. Furthermore, Open-EoE further optimizes the performance by implementing an ensemble learning strategy, and enhancing the precision and reliability of our results. The experimental results demonstrated that the Open-EoE toolkit can efficiently detect Eos on a testing set with 289 WSIs. At the widely accepted threshold of >= 15 Eos per high power field (HPF) for diagnosing EoE, the Open-EoE achieved an accuracy of 91%, showing decent consistency with pathologist evaluations. This suggests a promising avenue for integrating machine learning methodologies into the diagnostic process for EoE. The docker and source code has been made publicly available at https://github.com/hrlblab/Open-EoE. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.06333v1-abstract-full').style.display = 'none'; document.getElementById('2308.06333v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2308.06288">arXiv:2308.06288</a> <span> [<a href="https://arxiv.org/pdf/2308.06288">pdf</a>, <a href="https://arxiv.org/format/2308.06288">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Quantitative Methods">q-bio.QM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> Spatial Pathomics Toolkit for Quantitative Analysis of Podocyte Nuclei with Histology and Spatial Transcriptomics Data in Renal Pathology </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Chen%2C+J">Jiayuan Chen</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+Y">Yu Wang</a>, <a href="/search/eess?searchtype=author&query=Deng%2C+R">Ruining Deng</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Q">Quan Liu</a>, <a href="/search/eess?searchtype=author&query=Cui%2C+C">Can Cui</a>, <a href="/search/eess?searchtype=author&query=Yao%2C+T">Tianyuan Yao</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Y">Yilin Liu</a>, <a href="/search/eess?searchtype=author&query=Zhong%2C+J">Jianyong Zhong</a>, <a href="/search/eess?searchtype=author&query=Fogo%2C+A+B">Agnes B. Fogo</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+H">Haichun Yang</a>, <a href="/search/eess?searchtype=author&query=Zhao%2C+S">Shilin Zhao</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yuankai Huo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2308.06288v1-abstract-short" style="display: inline;"> Podocytes, specialized epithelial cells that envelop the glomerular capillaries, play a pivotal role in maintaining renal health. The current description and quantification of features on pathology slides are limited, prompting the need for innovative solutions to comprehensively assess diverse phenotypic attributes within Whole Slide Images (WSIs). In particular, understanding the morphological c… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.06288v1-abstract-full').style.display = 'inline'; document.getElementById('2308.06288v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.06288v1-abstract-full" style="display: none;"> Podocytes, specialized epithelial cells that envelop the glomerular capillaries, play a pivotal role in maintaining renal health. The current description and quantification of features on pathology slides are limited, prompting the need for innovative solutions to comprehensively assess diverse phenotypic attributes within Whole Slide Images (WSIs). In particular, understanding the morphological characteristics of podocytes, terminally differentiated glomerular epithelial cells, is crucial for studying glomerular injury. This paper introduces the Spatial Pathomics Toolkit (SPT) and applies it to podocyte pathomics. The SPT consists of three main components: (1) instance object segmentation, enabling precise identification of podocyte nuclei; (2) pathomics feature generation, extracting a comprehensive array of quantitative features from the identified nuclei; and (3) robust statistical analyses, facilitating a comprehensive exploration of spatial relationships between morphological and spatial transcriptomics features.The SPT successfully extracted and analyzed morphological and textural features from podocyte nuclei, revealing a multitude of podocyte morphomic features through statistical analysis. Additionally, we demonstrated the SPT's ability to unravel spatial information inherent to podocyte distribution, shedding light on spatial patterns associated with glomerular injury. By disseminating the SPT, our goal is to provide the research community with a powerful and user-friendly resource that advances cellular spatial pathomics in renal pathology. The implementation and its complete source code of the toolkit are made openly accessible at https://github.com/hrlblab/spatial_pathomics. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.06288v1-abstract-full').style.display = 'none'; document.getElementById('2308.06288v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2308.05785">arXiv:2308.05785</a> <span> [<a href="https://arxiv.org/pdf/2308.05785">pdf</a>, <a href="https://arxiv.org/format/2308.05785">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Leverage Weakly Annotation to Pixel-wise Annotation via Zero-shot Segment Anything Model for Molecular-empowered Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Li%2C+X">Xueyuan Li</a>, <a href="/search/eess?searchtype=author&query=Deng%2C+R">Ruining Deng</a>, <a href="/search/eess?searchtype=author&query=Tang%2C+Y">Yucheng Tang</a>, <a href="/search/eess?searchtype=author&query=Bao%2C+S">Shunxing Bao</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+H">Haichun Yang</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yuankai Huo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2308.05785v1-abstract-short" style="display: inline;"> Precise identification of multiple cell classes in high-resolution Giga-pixel whole slide imaging (WSI) is critical for various clinical scenarios. Building an AI model for this purpose typically requires pixel-level annotations, which are often unscalable and must be done by skilled domain experts (e.g., pathologists). However, these annotations can be prone to errors, especially when distinguish… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.05785v1-abstract-full').style.display = 'inline'; document.getElementById('2308.05785v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.05785v1-abstract-full" style="display: none;"> Precise identification of multiple cell classes in high-resolution Giga-pixel whole slide imaging (WSI) is critical for various clinical scenarios. Building an AI model for this purpose typically requires pixel-level annotations, which are often unscalable and must be done by skilled domain experts (e.g., pathologists). However, these annotations can be prone to errors, especially when distinguishing between intricate cell types (e.g., podocytes and mesangial cells) using only visual inspection. Interestingly, a recent study showed that lay annotators, when using extra immunofluorescence (IF) images for reference (referred to as molecular-empowered learning), can sometimes outperform domain experts in labeling. Despite this, the resource-intensive task of manual delineation remains a necessity during the annotation process. In this paper, we explore the potential of bypassing pixel-level delineation by employing the recent segment anything model (SAM) on weak box annotation in a zero-shot learning approach. Specifically, we harness SAM's ability to produce pixel-level annotations from box annotations and utilize these SAM-generated labels to train a segmentation model. Our findings show that the proposed SAM-assisted molecular-empowered learning (SAM-L) can diminish the labeling efforts for lay annotators by only requiring weak box annotations. This is achieved without compromising annotation accuracy or the performance of the deep learning-based segmentation. This research represents a significant advancement in democratizing the annotation process for training pathological image segmentation, relying solely on non-expert annotators. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.05785v1-abstract-full').style.display = 'none'; document.getElementById('2308.05785v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2308.05784">arXiv:2308.05784</a> <span> [<a href="https://arxiv.org/pdf/2308.05784">pdf</a>, <a href="https://arxiv.org/format/2308.05784">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> High-performance Data Management for Whole Slide Image Analysis in Digital Pathology </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Leng%2C+H">Haoju Leng</a>, <a href="/search/eess?searchtype=author&query=Deng%2C+R">Ruining Deng</a>, <a href="/search/eess?searchtype=author&query=Bao%2C+S">Shunxing Bao</a>, <a href="/search/eess?searchtype=author&query=Fang%2C+D">Dazheng Fang</a>, <a href="/search/eess?searchtype=author&query=Millis%2C+B+A">Bryan A. Millis</a>, <a href="/search/eess?searchtype=author&query=Tang%2C+Y">Yucheng Tang</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+H">Haichun Yang</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+X">Xiao Wang</a>, <a href="/search/eess?searchtype=author&query=Peng%2C+Y">Yifan Peng</a>, <a href="/search/eess?searchtype=author&query=Wan%2C+L">Lipeng Wan</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yuankai Huo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2308.05784v2-abstract-short" style="display: inline;"> When dealing with giga-pixel digital pathology in whole-slide imaging, a notable proportion of data records holds relevance during each analysis operation. For instance, when deploying an image analysis algorithm on whole-slide images (WSI), the computational bottleneck often lies in the input-output (I/O) system. This is particularly notable as patch-level processing introduces a considerable I/O… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.05784v2-abstract-full').style.display = 'inline'; document.getElementById('2308.05784v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.05784v2-abstract-full" style="display: none;"> When dealing with giga-pixel digital pathology in whole-slide imaging, a notable proportion of data records holds relevance during each analysis operation. For instance, when deploying an image analysis algorithm on whole-slide images (WSI), the computational bottleneck often lies in the input-output (I/O) system. This is particularly notable as patch-level processing introduces a considerable I/O load onto the computer system. However, this data management process could be further paralleled, given the typical independence of patch-level image processes across different patches. This paper details our endeavors in tackling this data access challenge by implementing the Adaptable IO System version 2 (ADIOS2). Our focus has been constructing and releasing a digital pathology-centric pipeline using ADIOS2, which facilitates streamlined data management across WSIs. Additionally, we've developed strategies aimed at curtailing data retrieval times. The performance evaluation encompasses two key scenarios: (1) a pure CPU-based image analysis scenario ("CPU scenario"), and (2) a GPU-based deep learning framework scenario ("GPU scenario"). Our findings reveal noteworthy outcomes. Under the CPU scenario, ADIOS2 showcases an impressive two-fold speed-up compared to the brute-force approach. In the GPU scenario, its performance stands on par with the cutting-edge GPU I/O acceleration framework, NVIDIA Magnum IO GPU Direct Storage (GDS). From what we know, this appears to be among the initial instances, if any, of utilizing ADIOS2 within the field of digital pathology. The source code has been made publicly available at https://github.com/hrlblab/adios. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.05784v2-abstract-full').style.display = 'none'; document.getElementById('2308.05784v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 10 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2308.05782">arXiv:2308.05782</a> <span> [<a href="https://arxiv.org/pdf/2308.05782">pdf</a>, <a href="https://arxiv.org/format/2308.05782">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Multi-scale Multi-site Renal Microvascular Structures Segmentation for Whole Slide Imaging in Renal Pathology </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Hu%2C+F">Franklin Hu</a>, <a href="/search/eess?searchtype=author&query=Deng%2C+R">Ruining Deng</a>, <a href="/search/eess?searchtype=author&query=Bao%2C+S">Shunxing Bao</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+H">Haichun Yang</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yuankai Huo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2308.05782v1-abstract-short" style="display: inline;"> Segmentation of microvascular structures, such as arterioles, venules, and capillaries, from human kidney whole slide images (WSI) has become a focal point in renal pathology. Current manual segmentation techniques are time-consuming and not feasible for large-scale digital pathology images. While deep learning-based methods offer a solution for automatic segmentation, most suffer from a limitatio… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.05782v1-abstract-full').style.display = 'inline'; document.getElementById('2308.05782v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.05782v1-abstract-full" style="display: none;"> Segmentation of microvascular structures, such as arterioles, venules, and capillaries, from human kidney whole slide images (WSI) has become a focal point in renal pathology. Current manual segmentation techniques are time-consuming and not feasible for large-scale digital pathology images. While deep learning-based methods offer a solution for automatic segmentation, most suffer from a limitation: they are designed for and restricted to training on single-site, single-scale data. In this paper, we present Omni-Seg, a novel single dynamic network method that capitalizes on multi-site, multi-scale training data. Unique to our approach, we utilize partially labeled images, where only one tissue type is labeled per training image, to segment microvascular structures. We train a singular deep network using images from two datasets, HuBMAP and NEPTUNE, across different magnifications (40x, 20x, 10x, and 5x). Experimental results indicate that Omni-Seg outperforms in terms of both the Dice Similarity Coefficient (DSC) and Intersection over Union (IoU). Our proposed method provides renal pathologists with a powerful computational tool for the quantitative analysis of renal microvascular structures. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.05782v1-abstract-full').style.display = 'none'; document.getElementById('2308.05782v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2307.11862">arXiv:2307.11862</a> <span> [<a href="https://arxiv.org/pdf/2307.11862">pdf</a>, <a href="https://arxiv.org/format/2307.11862">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> Digital Modeling on Large Kernel Metamaterial Neural Network </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Liu%2C+Q">Quan Liu</a>, <a href="/search/eess?searchtype=author&query=Zheng%2C+H">Hanyu Zheng</a>, <a href="/search/eess?searchtype=author&query=Swartz%2C+B+T">Brandon T. Swartz</a>, <a href="/search/eess?searchtype=author&query=Lee%2C+H+h">Ho hin Lee</a>, <a href="/search/eess?searchtype=author&query=Asad%2C+Z">Zuhayr Asad</a>, <a href="/search/eess?searchtype=author&query=Kravchenko%2C+I">Ivan Kravchenko</a>, <a href="/search/eess?searchtype=author&query=Valentine%2C+J+G">Jason G. Valentine</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yuankai Huo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2307.11862v1-abstract-short" style="display: inline;"> Deep neural networks (DNNs) utilized recently are physically deployed with computational units (e.g., CPUs and GPUs). Such a design might lead to a heavy computational burden, significant latency, and intensive power consumption, which are critical limitations in applications such as the Internet of Things (IoT), edge computing, and the usage of drones. Recent advances in optical computational uni… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.11862v1-abstract-full').style.display = 'inline'; document.getElementById('2307.11862v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2307.11862v1-abstract-full" style="display: none;"> Deep neural networks (DNNs) utilized recently are physically deployed with computational units (e.g., CPUs and GPUs). Such a design might lead to a heavy computational burden, significant latency, and intensive power consumption, which are critical limitations in applications such as the Internet of Things (IoT), edge computing, and the usage of drones. Recent advances in optical computational units (e.g., metamaterial) have shed light on energy-free and light-speed neural networks. However, the digital design of the metamaterial neural network (MNN) is fundamentally limited by its physical limitations, such as precision, noise, and bandwidth during fabrication. Moreover, the unique advantages of MNN's (e.g., light-speed computation) are not fully explored via standard 3x3 convolution kernels. In this paper, we propose a novel large kernel metamaterial neural network (LMNN) that maximizes the digital capacity of the state-of-the-art (SOTA) MNN with model re-parametrization and network compression, while also considering the optical limitation explicitly. The new digital learning scheme can maximize the learning capacity of MNN while modeling the physical restrictions of meta-optic. With the proposed LMNN, the computation cost of the convolutional front-end can be offloaded into fabricated optical hardware. The experimental results on two publicly available datasets demonstrate that the optimized hybrid design improved classification accuracy while reducing computational latency. The development of the proposed LMNN is a promising step towards the ultimate goal of energy-free and light-speed AI. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.11862v1-abstract-full').style.display = 'none'; document.getElementById('2307.11862v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2306.01853">arXiv:2306.01853</a> <span> [<a href="https://arxiv.org/pdf/2306.01853">pdf</a>, <a href="https://arxiv.org/format/2306.01853">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Multi-Contrast Computed Tomography Atlas of Healthy Pancreas </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zhou%2C+Y">Yinchi Zhou</a>, <a href="/search/eess?searchtype=author&query=Lee%2C+H+H">Ho Hin Lee</a>, <a href="/search/eess?searchtype=author&query=Tang%2C+Y">Yucheng Tang</a>, <a href="/search/eess?searchtype=author&query=Yu%2C+X">Xin Yu</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+Q">Qi Yang</a>, <a href="/search/eess?searchtype=author&query=Bao%2C+S">Shunxing Bao</a>, <a href="/search/eess?searchtype=author&query=Spraggins%2C+J+M">Jeffrey M. Spraggins</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yuankai Huo</a>, <a href="/search/eess?searchtype=author&query=Landman%2C+B+A">Bennett A. Landman</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2306.01853v1-abstract-short" style="display: inline;"> With the substantial diversity in population demographics, such as differences in age and body composition, the volumetric morphology of pancreas varies greatly, resulting in distinctive variations in shape and appearance. Such variations increase the difficulty at generalizing population-wide pancreas features. A volumetric spatial reference is needed to adapt the morphological variability for or… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.01853v1-abstract-full').style.display = 'inline'; document.getElementById('2306.01853v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2306.01853v1-abstract-full" style="display: none;"> With the substantial diversity in population demographics, such as differences in age and body composition, the volumetric morphology of pancreas varies greatly, resulting in distinctive variations in shape and appearance. Such variations increase the difficulty at generalizing population-wide pancreas features. A volumetric spatial reference is needed to adapt the morphological variability for organ-specific analysis. Here, we proposed a high-resolution computed tomography (CT) atlas framework specifically optimized for the pancreas organ across multi-contrast CT. We introduce a deep learning-based pre-processing technique to extract the abdominal region of interests (ROIs) and leverage a hierarchical registration pipeline to align the pancreas anatomy across populations. Briefly, DEEDs affine and non-rigid registration are performed to transfer patient abdominal volumes to a fixed high-resolution atlas template. To generate and evaluate the pancreas atlas template, multi-contrast modality CT scans of 443 subjects (without reported history of pancreatic disease, age: 15-50 years old) are processed. Comparing with different registration state-of-the-art tools, the combination of DEEDs affine and non-rigid registration achieves the best performance for the pancreas label transfer across all contrast phases. We further perform external evaluation with another research cohort of 100 de-identified portal venous scans with 13 organs labeled, having the best label transfer performance of 0.504 Dice score in unsupervised setting. The qualitative representation (e.g., average mapping) of each phase creates a clear boundary of pancreas and its distinctive contrast appearance. The deformation surface renderings across scales (e.g., small to large volume) further illustrate the generalizability of the proposed atlas template. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.01853v1-abstract-full').style.display = 'none'; document.getElementById('2306.01853v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 2 June, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2306.00047">arXiv:2306.00047</a> <span> [<a href="https://arxiv.org/pdf/2306.00047">pdf</a>, <a href="https://arxiv.org/format/2306.00047">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Democratizing Pathological Image Segmentation with Lay Annotators via Molecular-empowered Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Deng%2C+R">Ruining Deng</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Y">Yanwei Li</a>, <a href="/search/eess?searchtype=author&query=Li%2C+P">Peize Li</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+J">Jiacheng Wang</a>, <a href="/search/eess?searchtype=author&query=Remedios%2C+L+W">Lucas W. Remedios</a>, <a href="/search/eess?searchtype=author&query=Agzamkhodjaev%2C+S">Saydolimkhon Agzamkhodjaev</a>, <a href="/search/eess?searchtype=author&query=Asad%2C+Z">Zuhayr Asad</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Q">Quan Liu</a>, <a href="/search/eess?searchtype=author&query=Cui%2C+C">Can Cui</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+Y">Yaohong Wang</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+Y">Yihan Wang</a>, <a href="/search/eess?searchtype=author&query=Tang%2C+Y">Yucheng Tang</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+H">Haichun Yang</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yuankai Huo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2306.00047v2-abstract-short" style="display: inline;"> Multi-class cell segmentation in high-resolution Giga-pixel whole slide images (WSI) is critical for various clinical applications. Training such an AI model typically requires labor-intensive pixel-wise manual annotation from experienced domain experts (e.g., pathologists). Moreover, such annotation is error-prone when differentiating fine-grained cell types (e.g., podocyte and mesangial cells) v… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.00047v2-abstract-full').style.display = 'inline'; document.getElementById('2306.00047v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2306.00047v2-abstract-full" style="display: none;"> Multi-class cell segmentation in high-resolution Giga-pixel whole slide images (WSI) is critical for various clinical applications. Training such an AI model typically requires labor-intensive pixel-wise manual annotation from experienced domain experts (e.g., pathologists). Moreover, such annotation is error-prone when differentiating fine-grained cell types (e.g., podocyte and mesangial cells) via the naked human eye. In this study, we assess the feasibility of democratizing pathological AI deployment by only using lay annotators (annotators without medical domain knowledge). The contribution of this paper is threefold: (1) We proposed a molecular-empowered learning scheme for multi-class cell segmentation using partial labels from lay annotators; (2) The proposed method integrated Giga-pixel level molecular-morphology cross-modality registration, molecular-informed annotation, and molecular-oriented segmentation model, so as to achieve significantly superior performance via 3 lay annotators as compared with 2 experienced pathologists; (3) A deep corrective learning (learning with imperfect label) method is proposed to further improve the segmentation performance using partially annotated noisy data. From the experimental results, our learning method achieved F1 = 0.8496 using molecular-informed annotations from lay annotators, which is better than conventional morphology-based annotations (F1 = 0.7015) from experienced pathologists. Our method democratizes the development of a pathological segmentation deep model to the lay annotator level, which consequently scales up the learning process similar to a non-medical computer vision task. The official implementation and cell annotations are publicly available at https://github.com/hrlblab/MolecularEL. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.00047v2-abstract-full').style.display = 'none'; document.getElementById('2306.00047v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 31 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2305.14566">arXiv:2305.14566</a> <span> [<a href="https://arxiv.org/pdf/2305.14566">pdf</a>, <a href="https://arxiv.org/format/2305.14566">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1117/12.2653651">10.1117/12.2653651 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> An Accelerated Pipeline for Multi-label Renal Pathology Image Segmentation at the Whole Slide Image Level </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Leng%2C+H">Haoju Leng</a>, <a href="/search/eess?searchtype=author&query=Deng%2C+R">Ruining Deng</a>, <a href="/search/eess?searchtype=author&query=Asad%2C+Z">Zuhayr Asad</a>, <a href="/search/eess?searchtype=author&query=Womick%2C+R+M">R. Michael Womick</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+H">Haichun Yang</a>, <a href="/search/eess?searchtype=author&query=Wan%2C+L">Lipeng Wan</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yuankai Huo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2305.14566v1-abstract-short" style="display: inline;"> Deep-learning techniques have been used widely to alleviate the labour-intensive and time-consuming manual annotation required for pixel-level tissue characterization. Our previous study introduced an efficient single dynamic network - Omni-Seg - that achieved multi-class multi-scale pathological segmentation with less computational complexity. However, the patch-wise segmentation paradigm still a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.14566v1-abstract-full').style.display = 'inline'; document.getElementById('2305.14566v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.14566v1-abstract-full" style="display: none;"> Deep-learning techniques have been used widely to alleviate the labour-intensive and time-consuming manual annotation required for pixel-level tissue characterization. Our previous study introduced an efficient single dynamic network - Omni-Seg - that achieved multi-class multi-scale pathological segmentation with less computational complexity. However, the patch-wise segmentation paradigm still applies to Omni-Seg, and the pipeline is time-consuming when providing segmentation for Whole Slide Images (WSIs). In this paper, we propose an enhanced version of the Omni-Seg pipeline in order to reduce the repetitive computing processes and utilize a GPU to accelerate the model's prediction for both better model performance and faster speed. Our proposed method's innovative contribution is two-fold: (1) a Docker is released for an end-to-end slide-wise multi-tissue segmentation for WSIs; and (2) the pipeline is deployed on a GPU to accelerate the prediction, achieving better segmentation quality in less time. The proposed accelerated implementation reduced the average processing time (at the testing stage) on a standard needle biopsy WSI from 2.3 hours to 22 minutes, using 35 WSIs from the Kidney Tissue Atlas (KPMP) Datasets. The source code and the Docker have been made publicly available at https://github.com/ddrrnn123/Omni-Seg. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.14566v1-abstract-full').style.display = 'none'; document.getElementById('2305.14566v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 23 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2305.11968">arXiv:2305.11968</a> <span> [<a href="https://arxiv.org/pdf/2305.11968">pdf</a>, <a href="https://arxiv.org/format/2305.11968">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1117/12.2654542">10.1117/12.2654542 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> An End-to-end Pipeline for 3D Slide-wise Multi-stain Renal Pathology Registration </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Li%2C+P">Peize Li</a>, <a href="/search/eess?searchtype=author&query=Deng%2C+R">Ruining Deng</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yuankai Huo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2305.11968v1-abstract-short" style="display: inline;"> Tissue examination and quantification in a 3D context on serial section whole slide images (WSIs) were laborintensive and time-consuming tasks. Our previous study proposed a novel registration-based method (Map3D) to automatically align WSIs to the same physical space, reducing the human efforts of screening serial sections from WSIs. However, the registration performance of our Map3D method was o… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.11968v1-abstract-full').style.display = 'inline'; document.getElementById('2305.11968v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.11968v1-abstract-full" style="display: none;"> Tissue examination and quantification in a 3D context on serial section whole slide images (WSIs) were laborintensive and time-consuming tasks. Our previous study proposed a novel registration-based method (Map3D) to automatically align WSIs to the same physical space, reducing the human efforts of screening serial sections from WSIs. However, the registration performance of our Map3D method was only evaluated on single-stain WSIs with large-scale kidney tissue samples. In this paper, we provide a Docker for an end-to-end 3D slide-wise registration pipeline on needle biopsy serial sections in a multi-stain paradigm. The contribution of this study is three-fold: (1) We release a containerized Docker for an end-to-end multi-stain WSI registration. (2) We prove that the Map3D pipeline is capable of sectional registration from multi-stain WSI. (3) We verify that the Map3D pipeline can also be applied to needle biopsy tissue samples. The source code and the Docker have been made publicly available at https://github.com/hrlblab/Map3D. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.11968v1-abstract-full').style.display = 'none'; document.getElementById('2305.11968v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">6 pages, 4 figures</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Proceedings Volume Medical Imaging 2023: Digital and Computational Pathology, 124710F (2023) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2305.10666">arXiv:2305.10666</a> <span> [<a href="https://arxiv.org/pdf/2305.10666">pdf</a>, <a href="https://arxiv.org/format/2305.10666">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/ICASSP48485.2024.10447144">10.1109/ICASSP48485.2024.10447144 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> A unified front-end framework for English text-to-speech synthesis </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Ying%2C+Z">Zelin Ying</a>, <a href="/search/eess?searchtype=author&query=Li%2C+C">Chen Li</a>, <a href="/search/eess?searchtype=author&query=Dong%2C+Y">Yu Dong</a>, <a href="/search/eess?searchtype=author&query=Kong%2C+Q">Qiuqiang Kong</a>, <a href="/search/eess?searchtype=author&query=Tian%2C+Q">Qiao Tian</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yuanyuan Huo</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+Y">Yuxuan Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2305.10666v3-abstract-short" style="display: inline;"> The front-end is a critical component of English text-to-speech (TTS) systems, responsible for extracting linguistic features that are essential for a text-to-speech model to synthesize speech, such as prosodies and phonemes. The English TTS front-end typically consists of a text normalization (TN) module, a prosody word prosody phrase (PWPP) module, and a grapheme-to-phoneme (G2P) module. However… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.10666v3-abstract-full').style.display = 'inline'; document.getElementById('2305.10666v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.10666v3-abstract-full" style="display: none;"> The front-end is a critical component of English text-to-speech (TTS) systems, responsible for extracting linguistic features that are essential for a text-to-speech model to synthesize speech, such as prosodies and phonemes. The English TTS front-end typically consists of a text normalization (TN) module, a prosody word prosody phrase (PWPP) module, and a grapheme-to-phoneme (G2P) module. However, current research on the English TTS front-end focuses solely on individual modules, neglecting the interdependence between them and resulting in sub-optimal performance for each module. Therefore, this paper proposes a unified front-end framework that captures the dependencies among the English TTS front-end modules. Extensive experiments have demonstrated that the proposed method achieves state-of-the-art (SOTA) performance in all modules. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.10666v3-abstract-full').style.display = 'none'; document.getElementById('2305.10666v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 17 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted in ICASSP 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2304.12149">arXiv:2304.12149</a> <span> [<a href="https://arxiv.org/pdf/2304.12149">pdf</a>, <a href="https://arxiv.org/format/2304.12149">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> Exploring shared memory architectures for end-to-end gigapixel deep learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Remedios%2C+L+W">Lucas W. Remedios</a>, <a href="/search/eess?searchtype=author&query=Cai%2C+L+Y">Leon Y. Cai</a>, <a href="/search/eess?searchtype=author&query=Remedios%2C+S+W">Samuel W. Remedios</a>, <a href="/search/eess?searchtype=author&query=Ramadass%2C+K">Karthik Ramadass</a>, <a href="/search/eess?searchtype=author&query=Krishnan%2C+A">Aravind Krishnan</a>, <a href="/search/eess?searchtype=author&query=Deng%2C+R">Ruining Deng</a>, <a href="/search/eess?searchtype=author&query=Cui%2C+C">Can Cui</a>, <a href="/search/eess?searchtype=author&query=Bao%2C+S">Shunxing Bao</a>, <a href="/search/eess?searchtype=author&query=Coburn%2C+L+A">Lori A. Coburn</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yuankai Huo</a>, <a href="/search/eess?searchtype=author&query=Landman%2C+B+A">Bennett A. Landman</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2304.12149v1-abstract-short" style="display: inline;"> Deep learning has made great strides in medical imaging, enabled by hardware advances in GPUs. One major constraint for the development of new models has been the saturation of GPU memory resources during training. This is especially true in computational pathology, where images regularly contain more than 1 billion pixels. These pathological images are traditionally divided into small patches to… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2304.12149v1-abstract-full').style.display = 'inline'; document.getElementById('2304.12149v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2304.12149v1-abstract-full" style="display: none;"> Deep learning has made great strides in medical imaging, enabled by hardware advances in GPUs. One major constraint for the development of new models has been the saturation of GPU memory resources during training. This is especially true in computational pathology, where images regularly contain more than 1 billion pixels. These pathological images are traditionally divided into small patches to enable deep learning due to hardware limitations. In this work, we explore whether the shared GPU/CPU memory architecture on the M1 Ultra systems-on-a-chip (SoCs) recently released by Apple, Inc. may provide a solution. These affordable systems (less than \$5000) provide access to 128 GB of unified memory (Mac Studio with M1 Ultra SoC). As a proof of concept for gigapixel deep learning, we identified tissue from background on gigapixel areas from whole slide images (WSIs). The model was a modified U-Net (4492 parameters) leveraging large kernels and high stride. The M1 Ultra SoC was able to train the model directly on gigapixel images (16000$\times$64000 pixels, 1.024 billion pixels) with a batch size of 1 using over 100 GB of unified memory for the process at an average speed of 1 minute and 21 seconds per batch with Tensorflow 2/Keras. As expected, the model converged with a high Dice score of 0.989 $\pm$ 0.005. Training up until this point took 111 hours and 24 minutes over 4940 steps. Other high RAM GPUs like the NVIDIA A100 (largest commercially accessible at 80 GB, $\sim$\$15000) are not yet widely available (in preview for select regions on Amazon Web Services at \$40.96/hour as a group of 8). This study is a promising step towards WSI-wise end-to-end deep learning with prevalent network architectures. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2304.12149v1-abstract-full').style.display = 'none'; document.getElementById('2304.12149v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 April, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2304.04155">arXiv:2304.04155</a> <span> [<a href="https://arxiv.org/pdf/2304.04155">pdf</a>, <a href="https://arxiv.org/format/2304.04155">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Segment Anything Model (SAM) for Digital Pathology: Assess Zero-shot Segmentation on Whole Slide Imaging </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Deng%2C+R">Ruining Deng</a>, <a href="/search/eess?searchtype=author&query=Cui%2C+C">Can Cui</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Q">Quan Liu</a>, <a href="/search/eess?searchtype=author&query=Yao%2C+T">Tianyuan Yao</a>, <a href="/search/eess?searchtype=author&query=Remedios%2C+L+W">Lucas W. Remedios</a>, <a href="/search/eess?searchtype=author&query=Bao%2C+S">Shunxing Bao</a>, <a href="/search/eess?searchtype=author&query=Landman%2C+B+A">Bennett A. Landman</a>, <a href="/search/eess?searchtype=author&query=Wheless%2C+L+E">Lee E. Wheless</a>, <a href="/search/eess?searchtype=author&query=Coburn%2C+L+A">Lori A. Coburn</a>, <a href="/search/eess?searchtype=author&query=Wilson%2C+K+T">Keith T. Wilson</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+Y">Yaohong Wang</a>, <a href="/search/eess?searchtype=author&query=Zhao%2C+S">Shilin Zhao</a>, <a href="/search/eess?searchtype=author&query=Fogo%2C+A+B">Agnes B. Fogo</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+H">Haichun Yang</a>, <a href="/search/eess?searchtype=author&query=Tang%2C+Y">Yucheng Tang</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yuankai Huo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2304.04155v1-abstract-short" style="display: inline;"> The segment anything model (SAM) was released as a foundation model for image segmentation. The promptable segmentation model was trained by over 1 billion masks on 11M licensed and privacy-respecting images. The model supports zero-shot image segmentation with various segmentation prompts (e.g., points, boxes, masks). It makes the SAM attractive for medical image analysis, especially for digital… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2304.04155v1-abstract-full').style.display = 'inline'; document.getElementById('2304.04155v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2304.04155v1-abstract-full" style="display: none;"> The segment anything model (SAM) was released as a foundation model for image segmentation. The promptable segmentation model was trained by over 1 billion masks on 11M licensed and privacy-respecting images. The model supports zero-shot image segmentation with various segmentation prompts (e.g., points, boxes, masks). It makes the SAM attractive for medical image analysis, especially for digital pathology where the training data are rare. In this study, we evaluate the zero-shot segmentation performance of SAM model on representative segmentation tasks on whole slide imaging (WSI), including (1) tumor segmentation, (2) non-tumor tissue segmentation, (3) cell nuclei segmentation. Core Results: The results suggest that the zero-shot SAM model achieves remarkable segmentation performance for large connected objects. However, it does not consistently achieve satisfying performance for dense instance object segmentation, even with 20 prompts (clicks/boxes) on each image. We also summarized the identified limitations for digital pathology: (1) image resolution, (2) multiple scales, (3) prompt selection, and (4) model fine-tuning. In the future, the few-shot fine-tuning with images from downstream pathological segmentation tasks might help the model to achieve better performance in dense object segmentation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2304.04155v1-abstract-full').style.display = 'none'; document.getElementById('2304.04155v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 April, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2304.03760">arXiv:2304.03760</a> <span> [<a href="https://arxiv.org/pdf/2304.03760">pdf</a>, <a href="https://arxiv.org/format/2304.03760">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Zero-shot CT Field-of-view Completion with Unconditional Generative Diffusion Prior </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Xu%2C+K">Kaiwen Xu</a>, <a href="/search/eess?searchtype=author&query=Krishnan%2C+A+R">Aravind R. Krishnan</a>, <a href="/search/eess?searchtype=author&query=Li%2C+T+Z">Thomas Z. Li</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yuankai Huo</a>, <a href="/search/eess?searchtype=author&query=Sandler%2C+K+L">Kim L. Sandler</a>, <a href="/search/eess?searchtype=author&query=Maldonado%2C+F">Fabien Maldonado</a>, <a href="/search/eess?searchtype=author&query=Landman%2C+B+A">Bennett A. Landman</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2304.03760v1-abstract-short" style="display: inline;"> Anatomically consistent field-of-view (FOV) completion to recover truncated body sections has important applications in quantitative analyses of computed tomography (CT) with limited FOV. Existing solution based on conditional generative models relies on the fidelity of synthetic truncation patterns at training phase, which poses limitations for the generalizability of the method to potential unkn… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2304.03760v1-abstract-full').style.display = 'inline'; document.getElementById('2304.03760v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2304.03760v1-abstract-full" style="display: none;"> Anatomically consistent field-of-view (FOV) completion to recover truncated body sections has important applications in quantitative analyses of computed tomography (CT) with limited FOV. Existing solution based on conditional generative models relies on the fidelity of synthetic truncation patterns at training phase, which poses limitations for the generalizability of the method to potential unknown types of truncation. In this study, we evaluate a zero-shot method based on a pretrained unconditional generative diffusion prior, where truncation pattern with arbitrary forms can be specified at inference phase. In evaluation on simulated chest CT slices with synthetic FOV truncation, the method is capable of recovering anatomically consistent body sections and subcutaneous adipose tissue measurement error caused by FOV truncation. However, the correction accuracy is inferior to the conditionally trained counterpart. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2304.03760v1-abstract-full').style.display = 'none'; document.getElementById('2304.03760v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 April, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Submitted to MIDL 2023, short paper track</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2304.00216">arXiv:2304.00216</a> <span> [<a href="https://arxiv.org/pdf/2304.00216">pdf</a>, <a href="https://arxiv.org/format/2304.00216">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Cross-scale Multi-instance Learning for Pathological Image Diagnosis </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Deng%2C+R">Ruining Deng</a>, <a href="/search/eess?searchtype=author&query=Cui%2C+C">Can Cui</a>, <a href="/search/eess?searchtype=author&query=Remedios%2C+L+W">Lucas W. Remedios</a>, <a href="/search/eess?searchtype=author&query=Bao%2C+S">Shunxing Bao</a>, <a href="/search/eess?searchtype=author&query=Womick%2C+R+M">R. Michael Womick</a>, <a href="/search/eess?searchtype=author&query=Chiron%2C+S">Sophie Chiron</a>, <a href="/search/eess?searchtype=author&query=Li%2C+J">Jia Li</a>, <a href="/search/eess?searchtype=author&query=Roland%2C+J+T">Joseph T. Roland</a>, <a href="/search/eess?searchtype=author&query=Lau%2C+K+S">Ken S. Lau</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Q">Qi Liu</a>, <a href="/search/eess?searchtype=author&query=Wilson%2C+K+T">Keith T. Wilson</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+Y">Yaohong Wang</a>, <a href="/search/eess?searchtype=author&query=Coburn%2C+L+A">Lori A. Coburn</a>, <a href="/search/eess?searchtype=author&query=Landman%2C+B+A">Bennett A. Landman</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yuankai Huo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2304.00216v3-abstract-short" style="display: inline;"> Analyzing high resolution whole slide images (WSIs) with regard to information across multiple scales poses a significant challenge in digital pathology. Multi-instance learning (MIL) is a common solution for working with high resolution images by classifying bags of objects (i.e. sets of smaller image patches). However, such processing is typically performed at a single scale (e.g., 20x magnifica… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2304.00216v3-abstract-full').style.display = 'inline'; document.getElementById('2304.00216v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2304.00216v3-abstract-full" style="display: none;"> Analyzing high resolution whole slide images (WSIs) with regard to information across multiple scales poses a significant challenge in digital pathology. Multi-instance learning (MIL) is a common solution for working with high resolution images by classifying bags of objects (i.e. sets of smaller image patches). However, such processing is typically performed at a single scale (e.g., 20x magnification) of WSIs, disregarding the vital inter-scale information that is key to diagnoses by human pathologists. In this study, we propose a novel cross-scale MIL algorithm to explicitly aggregate inter-scale relationships into a single MIL network for pathological image diagnosis. The contribution of this paper is three-fold: (1) A novel cross-scale MIL (CS-MIL) algorithm that integrates the multi-scale information and the inter-scale relationships is proposed; (2) A toy dataset with scale-specific morphological features is created and released to examine and visualize differential cross-scale attention; (3) Superior performance on both in-house and public datasets is demonstrated by our simple cross-scale MIL strategy. The official implementation is publicly available at https://github.com/hrlblab/CS-MIL. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2304.00216v3-abstract-full').style.display = 'none'; document.getElementById('2304.00216v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 31 March, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2303.05785">arXiv:2303.05785</a> <span> [<a href="https://arxiv.org/pdf/2303.05785">pdf</a>, <a href="https://arxiv.org/format/2303.05785">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Scaling Up 3D Kernels with Bayesian Frequency Re-parameterization for Medical Image Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Lee%2C+H+H">Ho Hin Lee</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Q">Quan Liu</a>, <a href="/search/eess?searchtype=author&query=Bao%2C+S">Shunxing Bao</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+Q">Qi Yang</a>, <a href="/search/eess?searchtype=author&query=Yu%2C+X">Xin Yu</a>, <a href="/search/eess?searchtype=author&query=Cai%2C+L+Y">Leon Y. Cai</a>, <a href="/search/eess?searchtype=author&query=Li%2C+T">Thomas Li</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yuankai Huo</a>, <a href="/search/eess?searchtype=author&query=Koutsoukos%2C+X">Xenofon Koutsoukos</a>, <a href="/search/eess?searchtype=author&query=Landman%2C+B+A">Bennett A. Landman</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2303.05785v2-abstract-short" style="display: inline;"> With the inspiration of vision transformers, the concept of depth-wise convolution revisits to provide a large Effective Receptive Field (ERF) using Large Kernel (LK) sizes for medical image segmentation. However, the segmentation performance might be saturated and even degraded as the kernel sizes scaled up (e.g., $21\times 21\times 21$) in a Convolutional Neural Network (CNN). We hypothesize tha… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.05785v2-abstract-full').style.display = 'inline'; document.getElementById('2303.05785v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2303.05785v2-abstract-full" style="display: none;"> With the inspiration of vision transformers, the concept of depth-wise convolution revisits to provide a large Effective Receptive Field (ERF) using Large Kernel (LK) sizes for medical image segmentation. However, the segmentation performance might be saturated and even degraded as the kernel sizes scaled up (e.g., $21\times 21\times 21$) in a Convolutional Neural Network (CNN). We hypothesize that convolution with LK sizes is limited to maintain an optimal convergence for locality learning. While Structural Re-parameterization (SR) enhances the local convergence with small kernels in parallel, optimal small kernel branches may hinder the computational efficiency for training. In this work, we propose RepUX-Net, a pure CNN architecture with a simple large kernel block design, which competes favorably with current network state-of-the-art (SOTA) (e.g., 3D UX-Net, SwinUNETR) using 6 challenging public datasets. We derive an equivalency between kernel re-parameterization and the branch-wise variation in kernel convergence. Inspired by the spatial frequency in the human visual system, we extend to vary the kernel convergence into element-wise setting and model the spatial frequency as a Bayesian prior to re-parameterize convolutional weights during training. Specifically, a reciprocal function is leveraged to estimate a frequency-weighted value, which rescales the corresponding kernel element for stochastic gradient descent. From the experimental results, RepUX-Net consistently outperforms 3D SOTA benchmarks with internal validation (FLARE: 0.929 to 0.944), external validation (MSD: 0.901 to 0.932, KiTS: 0.815 to 0.847, LiTS: 0.933 to 0.949, TCIA: 0.736 to 0.779) and transfer learning (AMOS: 0.880 to 0.911) scenarios in Dice Score. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.05785v2-abstract-full').style.display = 'none'; document.getElementById('2303.05785v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 June, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 10 March, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted to MICCAI 2023 (top 13.6%), both codes and pretrained models are available at: https://github.com/MASILab/RepUX-Net</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2301.01703">arXiv:2301.01703</a> <span> [<a href="https://arxiv.org/pdf/2301.01703">pdf</a>, <a href="https://arxiv.org/format/2301.01703">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Technology Trends for Massive MIMO towards 6G </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yiming Huo</a>, <a href="/search/eess?searchtype=author&query=Lin%2C+X">Xingqin Lin</a>, <a href="/search/eess?searchtype=author&query=Di%2C+B">Boya Di</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+H">Hongliang Zhang</a>, <a href="/search/eess?searchtype=author&query=Hernando%2C+F+J+L">Francisco Javier Lorca Hernando</a>, <a href="/search/eess?searchtype=author&query=Tan%2C+A+S">Ahmet Serdar Tan</a>, <a href="/search/eess?searchtype=author&query=Mumtaz%2C+S">Shahid Mumtaz</a>, <a href="/search/eess?searchtype=author&query=Demir%2C+%C3%96+T">脰zlem Tu臒fe Demir</a>, <a href="/search/eess?searchtype=author&query=Chen-Hu%2C+K">Kun Chen-Hu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2301.01703v2-abstract-short" style="display: inline;"> At the dawn of the next-generation wireless systems and networks, massive multiple-input multiple-output (MIMO) has been envisioned as one of the enabling technologies. With the continued success of being applied in the 5G and beyond, the massive MIMO technology has demonstrated its advantageousness, integrability, and extendibility. Moreover, several evolutionary features and revolutionizing tren… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.01703v2-abstract-full').style.display = 'inline'; document.getElementById('2301.01703v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2301.01703v2-abstract-full" style="display: none;"> At the dawn of the next-generation wireless systems and networks, massive multiple-input multiple-output (MIMO) has been envisioned as one of the enabling technologies. With the continued success of being applied in the 5G and beyond, the massive MIMO technology has demonstrated its advantageousness, integrability, and extendibility. Moreover, several evolutionary features and revolutionizing trends for massive MIMO have gradually emerged in recent years, which are expected to reshape the future 6G wireless systems and networks. Specifically, the functions and performance of future massive MIMO systems will be enabled and enhanced via combining other innovative technologies, architectures, and strategies such as intelligent omni-surfaces (IOSs)/intelligent reflecting surfaces (IRSs), artificial intelligence (AI), THz communications, cell free architecture. Also, more diverse vertical applications based on massive MIMO will emerge and prosper, such as wireless localization and sensing, vehicular communications, non-terrestrial communications, remote sensing, inter-planetary communications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.01703v2-abstract-full').style.display = 'none'; document.getElementById('2301.01703v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 January, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 4 January, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">7 pages, 5 figures. This work has been submitted to the IEEE for possible publication</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2212.00059">arXiv:2212.00059</a> <span> [<a href="https://arxiv.org/pdf/2212.00059">pdf</a>, <a href="https://arxiv.org/format/2212.00059">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Single Slice Thigh CT Muscle Group Segmentation with Domain Adaptation and Self-Training </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Yang%2C+Q">Qi Yang</a>, <a href="/search/eess?searchtype=author&query=Yu%2C+X">Xin Yu</a>, <a href="/search/eess?searchtype=author&query=Lee%2C+H+H">Ho Hin Lee</a>, <a href="/search/eess?searchtype=author&query=Cai%2C+L+Y">Leon Y. Cai</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+K">Kaiwen Xu</a>, <a href="/search/eess?searchtype=author&query=Bao%2C+S">Shunxing Bao</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yuankai Huo</a>, <a href="/search/eess?searchtype=author&query=Moore%2C+A+Z">Ann Zenobia Moore</a>, <a href="/search/eess?searchtype=author&query=Makrogiannis%2C+S">Sokratis Makrogiannis</a>, <a href="/search/eess?searchtype=author&query=Ferrucci%2C+L">Luigi Ferrucci</a>, <a href="/search/eess?searchtype=author&query=Landman%2C+B+A">Bennett A. Landman</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2212.00059v1-abstract-short" style="display: inline;"> Objective: Thigh muscle group segmentation is important for assessment of muscle anatomy, metabolic disease and aging. Many efforts have been put into quantifying muscle tissues with magnetic resonance (MR) imaging including manual annotation of individual muscles. However, leveraging publicly available annotations in MR images to achieve muscle group segmentation on single slice computed tomograp… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2212.00059v1-abstract-full').style.display = 'inline'; document.getElementById('2212.00059v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2212.00059v1-abstract-full" style="display: none;"> Objective: Thigh muscle group segmentation is important for assessment of muscle anatomy, metabolic disease and aging. Many efforts have been put into quantifying muscle tissues with magnetic resonance (MR) imaging including manual annotation of individual muscles. However, leveraging publicly available annotations in MR images to achieve muscle group segmentation on single slice computed tomography (CT) thigh images is challenging. Method: We propose an unsupervised domain adaptation pipeline with self-training to transfer labels from 3D MR to single CT slice. First, we transform the image appearance from MR to CT with CycleGAN and feed the synthesized CT images to a segmenter simultaneously. Single CT slices are divided into hard and easy cohorts based on the entropy of pseudo labels inferenced by the segmenter. After refining easy cohort pseudo labels based on anatomical assumption, self-training with easy and hard splits is applied to fine tune the segmenter. Results: On 152 withheld single CT thigh images, the proposed pipeline achieved a mean Dice of 0.888(0.041) across all muscle groups including sartorius, hamstrings, quadriceps femoris and gracilis. muscles Conclusion: To our best knowledge, this is the first pipeline to achieve thigh imaging domain adaptation from MR to CT. The proposed pipeline is effective and robust in extracting muscle groups on 2D single slice CT thigh images.The container is available for public use at https://github.com/MASILab/DA_CT_muscle_seg <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2212.00059v1-abstract-full').style.display = 'none'; document.getElementById('2212.00059v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 November, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2022. </p> </li> </ol> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Huo%2C+Y&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Huo%2C+Y&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Huo%2C+Y&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Huo%2C+Y&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> </ul> </nav> <div class="is-hidden-tablet">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> </main> <footer> <div class="columns is-desktop" role="navigation" aria-label="Secondary">  <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/about">About</a></li> <li><a href="https://info.arxiv.org/help">Help</a></li> </ul> </div> <div class="column"> <ul class="nav-spaced"> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>contact arXiv</title><desc>Click here to contact arXiv</desc><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg> <a href="https://info.arxiv.org/help/contact.html"> Contact</a> </li> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>subscribe to arXiv mailings</title><desc>Click here to subscribe</desc><path d="M476 3.2L12.5 270.6c-18.1 10.4-15.8 35.6 2.2 43.2L121 358.4l287.3-253.2c5.5-4.9 13.3 2.6 8.6 8.3L176 407v80.5c0 23.6 28.5 32.9 42.5 15.8L282 426l124.6 52.2c14.2 6 30.4-2.9 33-18.2l72-432C515 7.8 493.3-6.8 476 3.2z"/></svg> <a href="https://info.arxiv.org/help/subscribe"> Subscribe</a> </li> </ul> </div> </div> </div>   <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/license/index.html">Copyright</a></li> <li><a href="https://info.arxiv.org/help/policies/privacy_policy.html">Privacy Policy</a></li> </ul> </div> <div class="column sorry-app-links"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/web_accessibility.html">Web Accessibility Assistance</a></li> <li> <p class="help"> <a class="a11y-main-link" href="https://status.arxiv.org" target="_blank">arXiv Operational Status <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 256 512" class="icon filter-dark_grey" role="presentation"><path d="M224.3 273l-136 136c-9.4 9.4-24.6 9.4-33.9 0l-22.6-22.6c-9.4-9.4-9.4-24.6 0-33.9l96.4-96.4-96.4-96.4c-9.4-9.4-9.4-24.6 0-33.9L54.3 103c9.4-9.4 24.6-9.4 33.9 0l136 136c9.5 9.4 9.5 24.6.1 34z"/></svg></a><br> Get status notifications via <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/email/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg>email</a> or <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/slack/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512" class="icon filter-black" role="presentation"><path d="M94.12 315.1c0 25.9-21.16 47.06-47.06 47.06S0 341 0 315.1c0-25.9 21.16-47.06 47.06-47.06h47.06v47.06zm23.72 0c0-25.9 21.16-47.06 47.06-47.06s47.06 21.16 47.06 47.06v117.84c0 25.9-21.16 47.06-47.06 47.06s-47.06-21.16-47.06-47.06V315.1zm47.06-188.98c-25.9 0-47.06-21.16-47.06-47.06S139 32 164.9 32s47.06 21.16 47.06 47.06v47.06H164.9zm0 23.72c25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06H47.06C21.16 243.96 0 222.8 0 196.9s21.16-47.06 47.06-47.06H164.9zm188.98 47.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06h-47.06V196.9zm-23.72 0c0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06V79.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06V196.9zM283.1 385.88c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06v-47.06h47.06zm0-23.72c-25.9 0-47.06-21.16-47.06-47.06 0-25.9 21.16-47.06 47.06-47.06h117.84c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06H283.1z"/></svg>slack</a> </p> </li> </ul> </div> </div> </div>  </div> </footer> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/member_acknowledgement.js"></script> </body> </html>

CINXE.COM

Search | arXiv e-print repository