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 92 results for author: <span class="mathjax">Roth, H</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/cs" aria-role="search"> Searching in archive <strong>cs</strong>. <a href="/search/?searchtype=author&query=Roth%2C+H">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="Roth, H"> </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=Roth%2C+H&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="Roth, H"> <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=Roth%2C+H&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Roth%2C+H&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Roth%2C+H&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </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/2411.12915">arXiv:2411.12915</a> <span> [<a href="https://arxiv.org/pdf/2411.12915">pdf</a>, <a href="https://arxiv.org/format/2411.12915">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> </div> </div> <p class="title is-5 mathjax"> VILA-M3: Enhancing Vision-Language Models with Medical Expert Knowledge </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nath%2C+V">Vishwesh Nath</a>, <a href="/search/cs?searchtype=author&query=Li%2C+W">Wenqi Li</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+D">Dong Yang</a>, <a href="/search/cs?searchtype=author&query=Myronenko%2C+A">Andriy Myronenko</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+M">Mingxin Zheng</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+Y">Yao Lu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Z">Zhijian Liu</a>, <a href="/search/cs?searchtype=author&query=Yin%2C+H">Hongxu Yin</a>, <a href="/search/cs?searchtype=author&query=Law%2C+Y+M">Yee Man Law</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+Y">Yucheng Tang</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+P">Pengfei Guo</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+C">Can Zhao</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Z">Ziyue Xu</a>, <a href="/search/cs?searchtype=author&query=He%2C+Y">Yufan He</a>, <a href="/search/cs?searchtype=author&query=Heinrich%2C+G">Greg Heinrich</a>, <a href="/search/cs?searchtype=author&query=Aylward%2C+S">Stephen Aylward</a>, <a href="/search/cs?searchtype=author&query=Edgar%2C+M">Marc Edgar</a>, <a href="/search/cs?searchtype=author&query=Zephyr%2C+M">Michael Zephyr</a>, <a href="/search/cs?searchtype=author&query=Molchanov%2C+P">Pavlo Molchanov</a>, <a href="/search/cs?searchtype=author&query=Turkbey%2C+B">Baris Turkbey</a>, <a href="/search/cs?searchtype=author&query=Roth%2C+H">Holger Roth</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+D">Daguang Xu</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="2411.12915v1-abstract-short" style="display: inline;"> Generalist vision language models (VLMs) have made significant strides in computer vision, but they fall short in specialized fields like healthcare, where expert knowledge is essential. In traditional computer vision tasks, creative or approximate answers may be acceptable, but in healthcare, precision is paramount.Current large multimodal models like Gemini and GPT-4o are insufficient for medica… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.12915v1-abstract-full').style.display = 'inline'; document.getElementById('2411.12915v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.12915v1-abstract-full" style="display: none;"> Generalist vision language models (VLMs) have made significant strides in computer vision, but they fall short in specialized fields like healthcare, where expert knowledge is essential. In traditional computer vision tasks, creative or approximate answers may be acceptable, but in healthcare, precision is paramount.Current large multimodal models like Gemini and GPT-4o are insufficient for medical tasks due to their reliance on memorized internet knowledge rather than the nuanced expertise required in healthcare. VLMs are usually trained in three stages: vision pre-training, vision-language pre-training, and instruction fine-tuning (IFT). IFT has been typically applied using a mixture of generic and healthcare data. In contrast, we propose that for medical VLMs, a fourth stage of specialized IFT is necessary, which focuses on medical data and includes information from domain expert models. Domain expert models developed for medical use are crucial because they are specifically trained for certain clinical tasks, e.g. to detect tumors and classify abnormalities through segmentation and classification, which learn fine-grained features of medical data$-$features that are often too intricate for a VLM to capture effectively especially in radiology. This paper introduces a new framework, VILA-M3, for medical VLMs that utilizes domain knowledge via expert models. Through our experiments, we show an improved state-of-the-art (SOTA) performance with an average improvement of ~9% over the prior SOTA model Med-Gemini and ~6% over models trained on the specific tasks. Our approach emphasizes the importance of domain expertise in creating precise, reliable VLMs for medical applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.12915v1-abstract-full').style.display = 'none'; document.getElementById('2411.12915v1-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 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/2411.03670">arXiv:2411.03670</a> <span> [<a href="https://arxiv.org/pdf/2411.03670">pdf</a>, <a href="https://arxiv.org/format/2411.03670">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> </div> </div> <p class="title is-5 mathjax"> Touchstone Benchmark: Are We on the Right Way for Evaluating AI Algorithms for Medical Segmentation? </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bassi%2C+P+R+A+S">Pedro R. A. S. Bassi</a>, <a href="/search/cs?searchtype=author&query=Li%2C+W">Wenxuan Li</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+Y">Yucheng Tang</a>, <a href="/search/cs?searchtype=author&query=Isensee%2C+F">Fabian Isensee</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zifu Wang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+J">Jieneng Chen</a>, <a href="/search/cs?searchtype=author&query=Chou%2C+Y">Yu-Cheng Chou</a>, <a href="/search/cs?searchtype=author&query=Kirchhoff%2C+Y">Yannick Kirchhoff</a>, <a href="/search/cs?searchtype=author&query=Rokuss%2C+M">Maximilian Rokuss</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+Z">Ziyan Huang</a>, <a href="/search/cs?searchtype=author&query=Ye%2C+J">Jin Ye</a>, <a href="/search/cs?searchtype=author&query=He%2C+J">Junjun He</a>, <a href="/search/cs?searchtype=author&query=Wald%2C+T">Tassilo Wald</a>, <a href="/search/cs?searchtype=author&query=Ulrich%2C+C">Constantin Ulrich</a>, <a href="/search/cs?searchtype=author&query=Baumgartner%2C+M">Michael Baumgartner</a>, <a href="/search/cs?searchtype=author&query=Roy%2C+S">Saikat Roy</a>, <a href="/search/cs?searchtype=author&query=Maier-Hein%2C+K+H">Klaus H. Maier-Hein</a>, <a href="/search/cs?searchtype=author&query=Jaeger%2C+P">Paul Jaeger</a>, <a href="/search/cs?searchtype=author&query=Ye%2C+Y">Yiwen Ye</a>, <a href="/search/cs?searchtype=author&query=Xie%2C+Y">Yutong Xie</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+J">Jianpeng Zhang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Ziyang Chen</a>, <a href="/search/cs?searchtype=author&query=Xia%2C+Y">Yong Xia</a>, <a href="/search/cs?searchtype=author&query=Xing%2C+Z">Zhaohu Xing</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+L">Lei Zhu</a> , et al. (28 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="2411.03670v1-abstract-short" style="display: inline;"> How can we test AI performance? This question seems trivial, but it isn't. Standard benchmarks often have problems such as in-distribution and small-size test sets, oversimplified metrics, unfair comparisons, and short-term outcome pressure. As a consequence, good performance on standard benchmarks does not guarantee success in real-world scenarios. To address these problems, we present Touchstone… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.03670v1-abstract-full').style.display = 'inline'; document.getElementById('2411.03670v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.03670v1-abstract-full" style="display: none;"> How can we test AI performance? This question seems trivial, but it isn't. Standard benchmarks often have problems such as in-distribution and small-size test sets, oversimplified metrics, unfair comparisons, and short-term outcome pressure. As a consequence, good performance on standard benchmarks does not guarantee success in real-world scenarios. To address these problems, we present Touchstone, a large-scale collaborative segmentation benchmark of 9 types of abdominal organs. This benchmark is based on 5,195 training CT scans from 76 hospitals around the world and 5,903 testing CT scans from 11 additional hospitals. This diverse test set enhances the statistical significance of benchmark results and rigorously evaluates AI algorithms across various out-of-distribution scenarios. We invited 14 inventors of 19 AI algorithms to train their algorithms, while our team, as a third party, independently evaluated these algorithms on three test sets. In addition, we also evaluated pre-existing AI frameworks--which, differing from algorithms, are more flexible and can support different algorithms--including MONAI from NVIDIA, nnU-Net from DKFZ, and numerous other open-source frameworks. We are committed to expanding this benchmark to encourage more innovation of AI algorithms for the medical domain. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.03670v1-abstract-full').style.display = 'none'; document.getElementById('2411.03670v1-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 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">Accepted to NeurIPS-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/2408.01979">arXiv:2408.01979</a> <span> [<a href="https://arxiv.org/pdf/2408.01979">pdf</a>, <a href="https://arxiv.org/format/2408.01979">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</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"> Shaping Rewards, Shaping Routes: On Multi-Agent Deep Q-Networks for Routing in Satellite Constellation Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Roth%2C+M+M+H">Manuel M. H. Roth</a>, <a href="/search/cs?searchtype=author&query=Hegde%2C+A">Anupama Hegde</a>, <a href="/search/cs?searchtype=author&query=Delamotte%2C+T">Thomas Delamotte</a>, <a href="/search/cs?searchtype=author&query=Knopp%2C+A">Andreas Knopp</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="2408.01979v1-abstract-short" style="display: inline;"> Effective routing in satellite mega-constellations has become crucial to facilitate the handling of increasing traffic loads, more complex network architectures, as well as the integration into 6G networks. To enhance adaptability as well as robustness to unpredictable traffic demands, and to solve dynamic routing environments efficiently, machine learning-based solutions are being considered. For… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.01979v1-abstract-full').style.display = 'inline'; document.getElementById('2408.01979v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.01979v1-abstract-full" style="display: none;"> Effective routing in satellite mega-constellations has become crucial to facilitate the handling of increasing traffic loads, more complex network architectures, as well as the integration into 6G networks. To enhance adaptability as well as robustness to unpredictable traffic demands, and to solve dynamic routing environments efficiently, machine learning-based solutions are being considered. For network control problems, such as optimizing packet forwarding decisions according to Quality of Service requirements and maintaining network stability, deep reinforcement learning techniques have demonstrated promising results. For this reason, we investigate the viability of multi-agent deep Q-networks for routing in satellite constellation networks. We focus specifically on reward shaping and quantifying training convergence for joint optimization of latency and load balancing in static and dynamic scenarios. To address identified drawbacks, we propose a novel hybrid solution based on centralized learning and decentralized control. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.01979v1-abstract-full').style.display = 'none'; document.getElementById('2408.01979v1-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 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 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">5 pages, 5 figures, to be published in proceedings of European Space Agency SPAICE Conference 2024, https://spaice.esa.int/</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> C.2.1 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.13632">arXiv:2407.13632</a> <span> [<a href="https://arxiv.org/pdf/2407.13632">pdf</a>, <a href="https://arxiv.org/format/2407.13632">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="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> </div> </div> <p class="title is-5 mathjax"> Data Alchemy: Mitigating Cross-Site Model Variability Through Test Time Data Calibration </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Parida%2C+A">Abhijeet Parida</a>, <a href="/search/cs?searchtype=author&query=Alomar%2C+A">Antonia Alomar</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+Z">Zhifan Jiang</a>, <a href="/search/cs?searchtype=author&query=Roshanitabrizi%2C+P">Pooneh Roshanitabrizi</a>, <a href="/search/cs?searchtype=author&query=Tapp%2C+A">Austin Tapp</a>, <a href="/search/cs?searchtype=author&query=Ledesma-Carbayo%2C+M">Maria Ledesma-Carbayo</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Z">Ziyue Xu</a>, <a href="/search/cs?searchtype=author&query=Anwar%2C+S+M">Syed Muhammed Anwar</a>, <a href="/search/cs?searchtype=author&query=Linguraru%2C+M+G">Marius George Linguraru</a>, <a href="/search/cs?searchtype=author&query=Roth%2C+H+R">Holger R. Roth</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="2407.13632v1-abstract-short" style="display: inline;"> Deploying deep learning-based imaging tools across various clinical sites poses significant challenges due to inherent domain shifts and regulatory hurdles associated with site-specific fine-tuning. For histopathology, stain normalization techniques can mitigate discrepancies, but they often fall short of eliminating inter-site variations. Therefore, we present Data Alchemy, an explainable stain n… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.13632v1-abstract-full').style.display = 'inline'; document.getElementById('2407.13632v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.13632v1-abstract-full" style="display: none;"> Deploying deep learning-based imaging tools across various clinical sites poses significant challenges due to inherent domain shifts and regulatory hurdles associated with site-specific fine-tuning. For histopathology, stain normalization techniques can mitigate discrepancies, but they often fall short of eliminating inter-site variations. Therefore, we present Data Alchemy, an explainable stain normalization method combined with test time data calibration via a template learning framework to overcome barriers in cross-site analysis. Data Alchemy handles shifts inherent to multi-site data and minimizes them without needing to change the weights of the normalization or classifier networks. Our approach extends to unseen sites in various clinical settings where data domain discrepancies are unknown. Extensive experiments highlight the efficacy of our framework in tumor classification in hematoxylin and eosin-stained patches. Our explainable normalization method boosts classification tasks' area under the precision-recall curve(AUPR) by 0.165, 0.545 to 0.710. Additionally, Data Alchemy further reduces the multisite classification domain gap, by improving the 0.710 AUPR an additional 0.142, elevating classification performance further to 0.852, from 0.545. Our Data Alchemy framework can popularize precision medicine with minimal operational overhead by allowing for the seamless integration of pre-trained deep learning-based clinical tools across multiple sites. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.13632v1-abstract-full').style.display = 'none'; document.getElementById('2407.13632v1-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 July, 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">accepted to Machine Learning in Medical Imaging (MLMI 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/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/cs?searchtype=author&query=Tang%2C+Y">Yucheng Tang</a>, <a href="/search/cs?searchtype=author&query=He%2C+Y">Yufan He</a>, <a href="/search/cs?searchtype=author&query=Nath%2C+V">Vishwesh Nath</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+P">Pengfeig Guo</a>, <a href="/search/cs?searchtype=author&query=Deng%2C+R">Ruining Deng</a>, <a href="/search/cs?searchtype=author&query=Yao%2C+T">Tianyuan Yao</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Quan Liu</a>, <a href="/search/cs?searchtype=author&query=Cui%2C+C">Can Cui</a>, <a href="/search/cs?searchtype=author&query=Yin%2C+M">Mengmeng Yin</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Z">Ziyue Xu</a>, <a href="/search/cs?searchtype=author&query=Roth%2C+H">Holger Roth</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+D">Daguang Xu</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+H">Haichun Yang</a>, <a href="/search/cs?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/2407.02604">arXiv:2407.02604</a> <span> [<a href="https://arxiv.org/pdf/2407.02604">pdf</a>, <a href="https://arxiv.org/format/2407.02604">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey 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="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> </div> </div> <p class="title is-5 mathjax"> D-Rax: Domain-specific Radiologic assistant leveraging multi-modal data and eXpert model predictions </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nisar%2C+H">Hareem Nisar</a>, <a href="/search/cs?searchtype=author&query=Anwar%2C+S+M">Syed Muhammad Anwar</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+Z">Zhifan Jiang</a>, <a href="/search/cs?searchtype=author&query=Parida%2C+A">Abhijeet Parida</a>, <a href="/search/cs?searchtype=author&query=Sanchez-Jacob%2C+R">Ramon Sanchez-Jacob</a>, <a href="/search/cs?searchtype=author&query=Nath%2C+V">Vishwesh Nath</a>, <a href="/search/cs?searchtype=author&query=Roth%2C+H+R">Holger R. Roth</a>, <a href="/search/cs?searchtype=author&query=Linguraru%2C+M+G">Marius George Linguraru</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="2407.02604v2-abstract-short" style="display: inline;"> Large vision language models (VLMs) have progressed incredibly from research to applicability for general-purpose use cases. LLaVA-Med, a pioneering large language and vision assistant for biomedicine, can perform multi-modal biomedical image and data analysis to provide a natural language interface for radiologists. While it is highly generalizable and works with multi-modal data, it is currently… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.02604v2-abstract-full').style.display = 'inline'; document.getElementById('2407.02604v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.02604v2-abstract-full" style="display: none;"> Large vision language models (VLMs) have progressed incredibly from research to applicability for general-purpose use cases. LLaVA-Med, a pioneering large language and vision assistant for biomedicine, can perform multi-modal biomedical image and data analysis to provide a natural language interface for radiologists. While it is highly generalizable and works with multi-modal data, it is currently limited by well-known challenges that exist in the large language model space. Hallucinations and imprecision in responses can lead to misdiagnosis which currently hinder the clinical adaptability of VLMs. To create precise, user-friendly models in healthcare, we propose D-Rax -- a domain-specific, conversational, radiologic assistance tool that can be used to gain insights about a particular radiologic image. In this study, we enhance the conversational analysis of chest X-ray (CXR) images to support radiological reporting, offering comprehensive insights from medical imaging and aiding in the formulation of accurate diagnosis. D-Rax is achieved by fine-tuning the LLaVA-Med architecture on our curated enhanced instruction-following data, comprising of images, instructions, as well as disease diagnosis and demographic predictions derived from MIMIC-CXR imaging data, CXR-related visual question answer (VQA) pairs, and predictive outcomes from multiple expert AI models. We observe statistically significant improvement in responses when evaluated for both open and close-ended conversations. Leveraging the power of state-of-the-art diagnostic models combined with VLMs, D-Rax empowers clinicians to interact with medical images using natural language, which could potentially streamline their decision-making process, enhance diagnostic accuracy, and conserve their time. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.02604v2-abstract-full').style.display = 'none'; document.getElementById('2407.02604v2-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 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 2 July, 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">accepted to the MICCAI 2024 Second International Workshop on Foundation Models for General Medical AI</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.00031">arXiv:2407.00031</a> <span> [<a href="https://arxiv.org/pdf/2407.00031">pdf</a>, <a href="https://arxiv.org/format/2407.00031">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> </div> </div> <p class="title is-5 mathjax"> Supercharging Federated Learning with Flower and NVIDIA FLARE </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Roth%2C+H+R">Holger R. Roth</a>, <a href="/search/cs?searchtype=author&query=Beutel%2C+D+J">Daniel J. Beutel</a>, <a href="/search/cs?searchtype=author&query=Cheng%2C+Y">Yan Cheng</a>, <a href="/search/cs?searchtype=author&query=Marques%2C+J+F">Javier Fernandez Marques</a>, <a href="/search/cs?searchtype=author&query=Pan%2C+H">Heng Pan</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+C">Chester Chen</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zhihong Zhang</a>, <a href="/search/cs?searchtype=author&query=Wen%2C+Y">Yuhong Wen</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+S">Sean Yang</a>, <a href="/search/cs?searchtype=author&query=Isaac"> Isaac</a>, <a href="/search/cs?searchtype=author&query=Yang"> Yang</a>, <a href="/search/cs?searchtype=author&query=Hsieh%2C+Y">Yuan-Ting Hsieh</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Z">Ziyue Xu</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+D">Daguang Xu</a>, <a href="/search/cs?searchtype=author&query=Lane%2C+N+D">Nicholas D. Lane</a>, <a href="/search/cs?searchtype=author&query=Feng%2C+A">Andrew Feng</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="2407.00031v2-abstract-short" style="display: inline;"> Several open-source systems, such as Flower and NVIDIA FLARE, have been developed in recent years while focusing on different aspects of federated learning (FL). Flower is dedicated to implementing a cohesive approach to FL, analytics, and evaluation. Over time, Flower has cultivated extensive strategies and algorithms tailored for FL application development, fostering a vibrant FL community in re… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.00031v2-abstract-full').style.display = 'inline'; document.getElementById('2407.00031v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.00031v2-abstract-full" style="display: none;"> Several open-source systems, such as Flower and NVIDIA FLARE, have been developed in recent years while focusing on different aspects of federated learning (FL). Flower is dedicated to implementing a cohesive approach to FL, analytics, and evaluation. Over time, Flower has cultivated extensive strategies and algorithms tailored for FL application development, fostering a vibrant FL community in research and industry. Conversely, FLARE has prioritized the creation of an enterprise-ready, resilient runtime environment explicitly designed for FL applications in production environments. In this paper, we describe our initial integration of both frameworks and show how they can work together to supercharge the FL ecosystem as a whole. Through the seamless integration of Flower and FLARE, applications crafted within the Flower framework can effortlessly operate within the FLARE runtime environment without necessitating any modifications. This initial integration streamlines the process, eliminating complexities and ensuring smooth interoperability between the two platforms, thus enhancing the overall efficiency and accessibility of FL applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.00031v2-abstract-full').style.display = 'none'; document.getElementById('2407.00031v2-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 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 21 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">Added a figure comparing running a Flower application natively or within FLARE</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.14900">arXiv:2405.14900</a> <span> [<a href="https://arxiv.org/pdf/2405.14900">pdf</a>, <a href="https://arxiv.org/format/2405.14900">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 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/10.1016/j.media.2024.103206.">10.1016/j.media.2024.103206. <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Fair Evaluation of Federated Learning Algorithms for Automated Breast Density Classification: The Results of the 2022 ACR-NCI-NVIDIA Federated Learning Challenge </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Schmidt%2C+K">Kendall Schmidt</a>, <a href="/search/cs?searchtype=author&query=Bearce%2C+B">Benjamin Bearce</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+K">Ken Chang</a>, <a href="/search/cs?searchtype=author&query=Coombs%2C+L">Laura Coombs</a>, <a href="/search/cs?searchtype=author&query=Farahani%2C+K">Keyvan Farahani</a>, <a href="/search/cs?searchtype=author&query=Elbatele%2C+M">Marawan Elbatele</a>, <a href="/search/cs?searchtype=author&query=Mouhebe%2C+K">Kaouther Mouhebe</a>, <a href="/search/cs?searchtype=author&query=Marti%2C+R">Robert Marti</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+R">Ruipeng Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yao Zhang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yanfeng Wang</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+Y">Yaojun Hu</a>, <a href="/search/cs?searchtype=author&query=Ying%2C+H">Haochao Ying</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Y">Yuyang Xu</a>, <a href="/search/cs?searchtype=author&query=Testagrose%2C+C">Conrad Testagrose</a>, <a href="/search/cs?searchtype=author&query=Demirer%2C+M">Mutlu Demirer</a>, <a href="/search/cs?searchtype=author&query=Gupta%2C+V">Vikash Gupta</a>, <a href="/search/cs?searchtype=author&query=Ak%C3%BCnal%2C+%C3%9C">脺nal Ak眉nal</a>, <a href="/search/cs?searchtype=author&query=Bujotzek%2C+M">Markus Bujotzek</a>, <a href="/search/cs?searchtype=author&query=Maier-Hein%2C+K+H">Klaus H. Maier-Hein</a>, <a href="/search/cs?searchtype=author&query=Qin%2C+Y">Yi Qin</a>, <a href="/search/cs?searchtype=author&query=Li%2C+X">Xiaomeng Li</a>, <a href="/search/cs?searchtype=author&query=Kalpathy-Cramer%2C+J">Jayashree Kalpathy-Cramer</a>, <a href="/search/cs?searchtype=author&query=Roth%2C+H+R">Holger R. Roth</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="2405.14900v1-abstract-short" style="display: inline;"> The correct interpretation of breast density is important in the assessment of breast cancer risk. AI has been shown capable of accurately predicting breast density, however, due to the differences in imaging characteristics across mammography systems, models built using data from one system do not generalize well to other systems. Though federated learning (FL) has emerged as a way to improve the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.14900v1-abstract-full').style.display = 'inline'; document.getElementById('2405.14900v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.14900v1-abstract-full" style="display: none;"> The correct interpretation of breast density is important in the assessment of breast cancer risk. AI has been shown capable of accurately predicting breast density, however, due to the differences in imaging characteristics across mammography systems, models built using data from one system do not generalize well to other systems. Though federated learning (FL) has emerged as a way to improve the generalizability of AI without the need to share data, the best way to preserve features from all training data during FL is an active area of research. To explore FL methodology, the breast density classification FL challenge was hosted in partnership with the American College of Radiology, Harvard Medical School's Mass General Brigham, University of Colorado, NVIDIA, and the National Institutes of Health National Cancer Institute. Challenge participants were able to submit docker containers capable of implementing FL on three simulated medical facilities, each containing a unique large mammography dataset. The breast density FL challenge ran from June 15 to September 5, 2022, attracting seven finalists from around the world. The winning FL submission reached a linear kappa score of 0.653 on the challenge test data and 0.413 on an external testing dataset, scoring comparably to a model trained on the same data in a central location. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.14900v1-abstract-full').style.display = 'none'; document.getElementById('2405.14900v1-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 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 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">16 pages, 9 figures</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Medical Image Analysis Volume 95, July 2024, 103206 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.03636">arXiv:2405.03636</a> <span> [<a href="https://arxiv.org/pdf/2405.03636">pdf</a>, <a href="https://arxiv.org/format/2405.03636">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</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"> Federated Learning Privacy: Attacks, Defenses, Applications, and Policy Landscape - A Survey </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhao%2C+J+C">Joshua C. Zhao</a>, <a href="/search/cs?searchtype=author&query=Bagchi%2C+S">Saurabh Bagchi</a>, <a href="/search/cs?searchtype=author&query=Avestimehr%2C+S">Salman Avestimehr</a>, <a href="/search/cs?searchtype=author&query=Chan%2C+K+S">Kevin S. Chan</a>, <a href="/search/cs?searchtype=author&query=Chaterji%2C+S">Somali Chaterji</a>, <a href="/search/cs?searchtype=author&query=Dimitriadis%2C+D">Dimitris Dimitriadis</a>, <a href="/search/cs?searchtype=author&query=Li%2C+J">Jiacheng Li</a>, <a href="/search/cs?searchtype=author&query=Li%2C+N">Ninghui Li</a>, <a href="/search/cs?searchtype=author&query=Nourian%2C+A">Arash Nourian</a>, <a href="/search/cs?searchtype=author&query=Roth%2C+H+R">Holger R. Roth</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="2405.03636v1-abstract-short" style="display: inline;"> Deep learning has shown incredible potential across a vast array of tasks and accompanying this growth has been an insatiable appetite for data. However, a large amount of data needed for enabling deep learning is stored on personal devices and recent concerns on privacy have further highlighted challenges for accessing such data. As a result, federated learning (FL) has emerged as an important pr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.03636v1-abstract-full').style.display = 'inline'; document.getElementById('2405.03636v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.03636v1-abstract-full" style="display: none;"> Deep learning has shown incredible potential across a vast array of tasks and accompanying this growth has been an insatiable appetite for data. However, a large amount of data needed for enabling deep learning is stored on personal devices and recent concerns on privacy have further highlighted challenges for accessing such data. As a result, federated learning (FL) has emerged as an important privacy-preserving technology enabling collaborative training of machine learning models without the need to send the raw, potentially sensitive, data to a central server. However, the fundamental premise that sending model updates to a server is privacy-preserving only holds if the updates cannot be "reverse engineered" to infer information about the private training data. It has been shown under a wide variety of settings that this premise for privacy does {\em not} hold. In this survey paper, we provide a comprehensive literature review of the different privacy attacks and defense methods in FL. We identify the current limitations of these attacks and highlight the settings in which FL client privacy can be broken. We dissect some of the successful industry applications of FL and draw lessons for future successful adoption. We survey the emerging landscape of privacy regulation for FL. We conclude with future directions for taking FL toward the cherished goal of generating accurate models while preserving the privacy of the data from its participants. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.03636v1-abstract-full').style.display = 'none'; document.getElementById('2405.03636v1-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 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 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">Submitted to ACM Computing Surveys</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> I.2; H.4; I.5 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.07792">arXiv:2402.07792</a> <span> [<a href="https://arxiv.org/pdf/2402.07792">pdf</a>, <a href="https://arxiv.org/format/2402.07792">other</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="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> </div> <p class="title is-5 mathjax"> Empowering Federated Learning for Massive Models with NVIDIA FLARE </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Roth%2C+H+R">Holger R. Roth</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Z">Ziyue Xu</a>, <a href="/search/cs?searchtype=author&query=Hsieh%2C+Y">Yuan-Ting Hsieh</a>, <a href="/search/cs?searchtype=author&query=Renduchintala%2C+A">Adithya Renduchintala</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+I">Isaac Yang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zhihong Zhang</a>, <a href="/search/cs?searchtype=author&query=Wen%2C+Y">Yuhong Wen</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+S">Sean Yang</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+K">Kevin Lu</a>, <a href="/search/cs?searchtype=author&query=Kersten%2C+K">Kristopher Kersten</a>, <a href="/search/cs?searchtype=author&query=Ricketts%2C+C">Camir Ricketts</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+D">Daguang Xu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+C">Chester Chen</a>, <a href="/search/cs?searchtype=author&query=Cheng%2C+Y">Yan Cheng</a>, <a href="/search/cs?searchtype=author&query=Feng%2C+A">Andrew Feng</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="2402.07792v1-abstract-short" style="display: inline;"> In the ever-evolving landscape of artificial intelligence (AI) and large language models (LLMs), handling and leveraging data effectively has become a critical challenge. Most state-of-the-art machine learning algorithms are data-centric. However, as the lifeblood of model performance, necessary data cannot always be centralized due to various factors such as privacy, regulation, geopolitics, copy… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.07792v1-abstract-full').style.display = 'inline'; document.getElementById('2402.07792v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.07792v1-abstract-full" style="display: none;"> In the ever-evolving landscape of artificial intelligence (AI) and large language models (LLMs), handling and leveraging data effectively has become a critical challenge. Most state-of-the-art machine learning algorithms are data-centric. However, as the lifeblood of model performance, necessary data cannot always be centralized due to various factors such as privacy, regulation, geopolitics, copyright issues, and the sheer effort required to move vast datasets. In this paper, we explore how federated learning enabled by NVIDIA FLARE can address these challenges with easy and scalable integration capabilities, enabling parameter-efficient and full supervised fine-tuning of LLMs for natural language processing and biopharmaceutical applications to enhance their accuracy and robustness. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.07792v1-abstract-full').style.display = 'none'; document.getElementById('2402.07792v1-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 February, 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/2311.01939">arXiv:2311.01939</a> <span> [<a href="https://arxiv.org/pdf/2311.01939">pdf</a>, <a href="https://arxiv.org/format/2311.01939">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> A Quantitative Autonomy Quantification Framework for Fully Autonomous Robotic Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gyagenda%2C+N">Nasser Gyagenda</a>, <a href="/search/cs?searchtype=author&query=Roth%2C+H">Hubert Roth</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="2311.01939v2-abstract-short" style="display: inline;"> Although autonomous functioning facilitates deployment of robotic systems in domains that admit limited human oversight on our planet and beyond, finding correspondence between task requirements and autonomous capability is still an open challenge. Consequently, a number of methods for quantifying autonomy have been proposed over the last three decades, but to our knowledge all these have no disce… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.01939v2-abstract-full').style.display = 'inline'; document.getElementById('2311.01939v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2311.01939v2-abstract-full" style="display: none;"> Although autonomous functioning facilitates deployment of robotic systems in domains that admit limited human oversight on our planet and beyond, finding correspondence between task requirements and autonomous capability is still an open challenge. Consequently, a number of methods for quantifying autonomy have been proposed over the last three decades, but to our knowledge all these have no discernment of sub-mode features of variation of autonomy and some are based on metrics that violet the Goodhart's law. This paper focuses on the full autonomous mode and proposes a quantitative autonomy assessment framework based on task requirements. The framework starts by establishing robot task characteristics from which three autonomy metrics, namely requisite capability set, reliability and responsiveness are derived. These characteristics were founded on the realization that robots ultimately replace human skilled workers, from which a relationship between human job and robot task characteristics was established. Additionally, mathematical functions mapping metrics to autonomy as a two-part measure, namely of level and degree of autonomy are also presented. The distinction between level and degree of autonomy stemmed from the acknowledgment that autonomy is not just a question of existence, but also one of performance of requisite capability. The framework has been demonstrated on two case studies, namely autonomous vehicle at an on-road dynamic driving task and the DARPA subterranean challenge rules analysis. The framework provides not only a tool for quantifying autonomy, but also a regulatory interface and common language for autonomous systems developers and users. Its greatest feature is the ability to monitor system integrity when implemented online. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.01939v2-abstract-full').style.display = 'none'; document.getElementById('2311.01939v2-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 3 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">10 pages, 5 figures and 6 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2310.01467">arXiv:2310.01467</a> <span> [<a href="https://arxiv.org/pdf/2310.01467">pdf</a>, <a href="https://arxiv.org/format/2310.01467">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> </div> </div> <p class="title is-5 mathjax"> FedBPT: Efficient Federated Black-box Prompt Tuning for Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sun%2C+J">Jingwei Sun</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Z">Ziyue Xu</a>, <a href="/search/cs?searchtype=author&query=Yin%2C+H">Hongxu Yin</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+D">Dong Yang</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+D">Daguang Xu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yiran Chen</a>, <a href="/search/cs?searchtype=author&query=Roth%2C+H+R">Holger R. Roth</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="2310.01467v1-abstract-short" style="display: inline;"> Pre-trained language models (PLM) have revolutionized the NLP landscape, achieving stellar performances across diverse tasks. These models, while benefiting from vast training data, often require fine-tuning on specific data to cater to distinct downstream tasks. However, this data adaptation process has inherent security and privacy concerns, primarily when leveraging user-generated, device-resid… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.01467v1-abstract-full').style.display = 'inline'; document.getElementById('2310.01467v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.01467v1-abstract-full" style="display: none;"> Pre-trained language models (PLM) have revolutionized the NLP landscape, achieving stellar performances across diverse tasks. These models, while benefiting from vast training data, often require fine-tuning on specific data to cater to distinct downstream tasks. However, this data adaptation process has inherent security and privacy concerns, primarily when leveraging user-generated, device-residing data. Federated learning (FL) provides a solution, allowing collaborative model fine-tuning without centralized data collection. However, applying FL to finetune PLMs is hampered by challenges, including restricted model parameter access, high computational requirements, and communication overheads. This paper introduces Federated Black-box Prompt Tuning (FedBPT), a framework designed to address these challenges. FedBPT does not require the clients to access the model parameters. By focusing on training optimal prompts and utilizing gradient-free optimization methods, FedBPT reduces the number of exchanged variables, boosts communication efficiency, and minimizes computational and storage costs. Experiments highlight the framework's ability to drastically cut communication and memory costs while maintaining competitive performance. Ultimately, FedBPT presents a promising solution for efficient, privacy-preserving fine-tuning of PLM in the age of large language models. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.01467v1-abstract-full').style.display = 'none'; document.getElementById('2310.01467v1-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 October, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2308.04070">arXiv:2308.04070</a> <span> [<a href="https://arxiv.org/pdf/2308.04070">pdf</a>, <a href="https://arxiv.org/format/2308.04070">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="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> ConDistFL: Conditional Distillation for Federated Learning from Partially Annotated Data </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+P">Pochuan Wang</a>, <a href="/search/cs?searchtype=author&query=Shen%2C+C">Chen Shen</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+W">Weichung Wang</a>, <a href="/search/cs?searchtype=author&query=Oda%2C+M">Masahiro Oda</a>, <a href="/search/cs?searchtype=author&query=Fuh%2C+C">Chiou-Shann Fuh</a>, <a href="/search/cs?searchtype=author&query=Mori%2C+K">Kensaku Mori</a>, <a href="/search/cs?searchtype=author&query=Roth%2C+H+R">Holger R. Roth</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="2308.04070v1-abstract-short" style="display: inline;"> Developing a generalized segmentation model capable of simultaneously delineating multiple organs and diseases is highly desirable. Federated learning (FL) is a key technology enabling the collaborative development of a model without exchanging training data. However, the limited access to fully annotated training data poses a major challenge to training generalizable models. We propose "ConDistFL… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.04070v1-abstract-full').style.display = 'inline'; document.getElementById('2308.04070v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.04070v1-abstract-full" style="display: none;"> Developing a generalized segmentation model capable of simultaneously delineating multiple organs and diseases is highly desirable. Federated learning (FL) is a key technology enabling the collaborative development of a model without exchanging training data. However, the limited access to fully annotated training data poses a major challenge to training generalizable models. We propose "ConDistFL", a framework to solve this problem by combining FL with knowledge distillation. Local models can extract the knowledge of unlabeled organs and tumors from partially annotated data from the global model with an adequately designed conditional probability representation. We validate our framework on four distinct partially annotated abdominal CT datasets from the MSD and KiTS19 challenges. The experimental results show that the proposed framework significantly outperforms FedAvg and FedOpt baselines. Moreover, the performance on an external test dataset demonstrates superior generalizability compared to models trained on each dataset separately. Our ablation study suggests that ConDistFL can perform well without frequent aggregation, reducing the communication cost of FL. Our implementation will be available at https://github.com/NVIDIA/NVFlare/tree/dev/research/condist-fl. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.04070v1-abstract-full').style.display = 'none'; document.getElementById('2308.04070v1-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> 8 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/2305.10655">arXiv:2305.10655</a> <span> [<a href="https://arxiv.org/pdf/2305.10655">pdf</a>, <a href="https://arxiv.org/format/2305.10655">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 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/10.1007/978-3-031-17027-0_2">10.1007/978-3-031-17027-0_2 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> DeepEdit: Deep Editable Learning for Interactive Segmentation of 3D Medical Images </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Diaz-Pinto%2C+A">Andres Diaz-Pinto</a>, <a href="/search/cs?searchtype=author&query=Mehta%2C+P">Pritesh Mehta</a>, <a href="/search/cs?searchtype=author&query=Alle%2C+S">Sachidanand Alle</a>, <a href="/search/cs?searchtype=author&query=Asad%2C+M">Muhammad Asad</a>, <a href="/search/cs?searchtype=author&query=Brown%2C+R">Richard Brown</a>, <a href="/search/cs?searchtype=author&query=Nath%2C+V">Vishwesh Nath</a>, <a href="/search/cs?searchtype=author&query=Ihsani%2C+A">Alvin Ihsani</a>, <a href="/search/cs?searchtype=author&query=Antonelli%2C+M">Michela Antonelli</a>, <a href="/search/cs?searchtype=author&query=Palkovics%2C+D">Daniel Palkovics</a>, <a href="/search/cs?searchtype=author&query=Pinter%2C+C">Csaba Pinter</a>, <a href="/search/cs?searchtype=author&query=Alkalay%2C+R">Ron Alkalay</a>, <a href="/search/cs?searchtype=author&query=Pieper%2C+S">Steve Pieper</a>, <a href="/search/cs?searchtype=author&query=Roth%2C+H+R">Holger R. Roth</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+D">Daguang Xu</a>, <a href="/search/cs?searchtype=author&query=Dogra%2C+P">Prerna Dogra</a>, <a href="/search/cs?searchtype=author&query=Vercauteren%2C+T">Tom Vercauteren</a>, <a href="/search/cs?searchtype=author&query=Feng%2C+A">Andrew Feng</a>, <a href="/search/cs?searchtype=author&query=Quraini%2C+A">Abood Quraini</a>, <a href="/search/cs?searchtype=author&query=Ourselin%2C+S">Sebastien Ourselin</a>, <a href="/search/cs?searchtype=author&query=Cardoso%2C+M+J">M. Jorge Cardoso</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="2305.10655v1-abstract-short" style="display: inline;"> Automatic segmentation of medical images is a key step for diagnostic and interventional tasks. However, achieving this requires large amounts of annotated volumes, which can be tedious and time-consuming task for expert annotators. In this paper, we introduce DeepEdit, a deep learning-based method for volumetric medical image annotation, that allows automatic and semi-automatic segmentation, and… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.10655v1-abstract-full').style.display = 'inline'; document.getElementById('2305.10655v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.10655v1-abstract-full" style="display: none;"> Automatic segmentation of medical images is a key step for diagnostic and interventional tasks. However, achieving this requires large amounts of annotated volumes, which can be tedious and time-consuming task for expert annotators. In this paper, we introduce DeepEdit, a deep learning-based method for volumetric medical image annotation, that allows automatic and semi-automatic segmentation, and click-based refinement. DeepEdit combines the power of two methods: a non-interactive (i.e. automatic segmentation using nnU-Net, UNET or UNETR) and an interactive segmentation method (i.e. DeepGrow), into a single deep learning model. It allows easy integration of uncertainty-based ranking strategies (i.e. aleatoric and epistemic uncertainty computation) and active learning. We propose and implement a method for training DeepEdit by using standard training combined with user interaction simulation. Once trained, DeepEdit allows clinicians to quickly segment their datasets by using the algorithm in auto segmentation mode or by providing clicks via a user interface (i.e. 3D Slicer, OHIF). We show the value of DeepEdit through evaluation on the PROSTATEx dataset for prostate/prostatic lesions and the Multi-Atlas Labeling Beyond the Cranial Vault (BTCV) dataset for abdominal CT segmentation, using state-of-the-art network architectures as baseline for comparison. DeepEdit could reduce the time and effort annotating 3D medical images compared to DeepGrow alone. Source code is available at https://github.com/Project-MONAI/MONAILabel <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.10655v1-abstract-full').style.display = 'none'; document.getElementById('2305.10655v1-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 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/2303.16520">arXiv:2303.16520</a> <span> [<a href="https://arxiv.org/pdf/2303.16520">pdf</a>, <a href="https://arxiv.org/format/2303.16520">other</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="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"> Fair Federated Medical Image Segmentation via Client Contribution Estimation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jiang%2C+M">Meirui Jiang</a>, <a href="/search/cs?searchtype=author&query=Roth%2C+H+R">Holger R Roth</a>, <a href="/search/cs?searchtype=author&query=Li%2C+W">Wenqi Li</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+D">Dong Yang</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+C">Can Zhao</a>, <a href="/search/cs?searchtype=author&query=Nath%2C+V">Vishwesh Nath</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+D">Daguang Xu</a>, <a href="/search/cs?searchtype=author&query=Dou%2C+Q">Qi Dou</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Z">Ziyue Xu</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="2303.16520v1-abstract-short" style="display: inline;"> How to ensure fairness is an important topic in federated learning (FL). Recent studies have investigated how to reward clients based on their contribution (collaboration fairness), and how to achieve uniformity of performance across clients (performance fairness). Despite achieving progress on either one, we argue that it is critical to consider them together, in order to engage and motivate more… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.16520v1-abstract-full').style.display = 'inline'; document.getElementById('2303.16520v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2303.16520v1-abstract-full" style="display: none;"> How to ensure fairness is an important topic in federated learning (FL). Recent studies have investigated how to reward clients based on their contribution (collaboration fairness), and how to achieve uniformity of performance across clients (performance fairness). Despite achieving progress on either one, we argue that it is critical to consider them together, in order to engage and motivate more diverse clients joining FL to derive a high-quality global model. In this work, we propose a novel method to optimize both types of fairness simultaneously. Specifically, we propose to estimate client contribution in gradient and data space. In gradient space, we monitor the gradient direction differences of each client with respect to others. And in data space, we measure the prediction error on client data using an auxiliary model. Based on this contribution estimation, we propose a FL method, federated training via contribution estimation (FedCE), i.e., using estimation as global model aggregation weights. We have theoretically analyzed our method and empirically evaluated it on two real-world medical datasets. The effectiveness of our approach has been validated with significant performance improvements, better collaboration fairness, better performance fairness, and comprehensive analytical studies. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.16520v1-abstract-full').style.display = 'none'; document.getElementById('2303.16520v1-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 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 at CVPR 2023</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2303.16270">arXiv:2303.16270</a> <span> [<a href="https://arxiv.org/pdf/2303.16270">pdf</a>, <a href="https://arxiv.org/format/2303.16270">other</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> </div> </div> <p class="title is-5 mathjax"> Communication-Efficient Vertical Federated Learning with Limited Overlapping Samples </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sun%2C+J">Jingwei Sun</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Z">Ziyue Xu</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+D">Dong Yang</a>, <a href="/search/cs?searchtype=author&query=Nath%2C+V">Vishwesh Nath</a>, <a href="/search/cs?searchtype=author&query=Li%2C+W">Wenqi Li</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+C">Can Zhao</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+D">Daguang Xu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yiran Chen</a>, <a href="/search/cs?searchtype=author&query=Roth%2C+H+R">Holger R. Roth</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="2303.16270v2-abstract-short" style="display: inline;"> Federated learning is a popular collaborative learning approach that enables clients to train a global model without sharing their local data. Vertical federated learning (VFL) deals with scenarios in which the data on clients have different feature spaces but share some overlapping samples. Existing VFL approaches suffer from high communication costs and cannot deal efficiently with limited overl… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.16270v2-abstract-full').style.display = 'inline'; document.getElementById('2303.16270v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2303.16270v2-abstract-full" style="display: none;"> Federated learning is a popular collaborative learning approach that enables clients to train a global model without sharing their local data. Vertical federated learning (VFL) deals with scenarios in which the data on clients have different feature spaces but share some overlapping samples. Existing VFL approaches suffer from high communication costs and cannot deal efficiently with limited overlapping samples commonly seen in the real world. We propose a practical vertical federated learning (VFL) framework called \textbf{one-shot VFL} that can solve the communication bottleneck and the problem of limited overlapping samples simultaneously based on semi-supervised learning. We also propose \textbf{few-shot VFL} to improve the accuracy further with just one more communication round between the server and the clients. In our proposed framework, the clients only need to communicate with the server once or only a few times. We evaluate the proposed VFL framework on both image and tabular datasets. Our methods can improve the accuracy by more than 46.5\% and reduce the communication cost by more than 330$\times$ compared with state-of-the-art VFL methods when evaluated on CIFAR-10. Our code will be made publicly available at \url{https://nvidia.github.io/NVFlare/research/one-shot-vfl}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.16270v2-abstract-full').style.display = 'none'; document.getElementById('2303.16270v2-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 March, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 28 March, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2211.02701">arXiv:2211.02701</a> <span> [<a href="https://arxiv.org/pdf/2211.02701">pdf</a>, <a href="https://arxiv.org/format/2211.02701">other</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="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"> MONAI: An open-source framework for deep learning in healthcare </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Cardoso%2C+M+J">M. Jorge Cardoso</a>, <a href="/search/cs?searchtype=author&query=Li%2C+W">Wenqi Li</a>, <a href="/search/cs?searchtype=author&query=Brown%2C+R">Richard Brown</a>, <a href="/search/cs?searchtype=author&query=Ma%2C+N">Nic Ma</a>, <a href="/search/cs?searchtype=author&query=Kerfoot%2C+E">Eric Kerfoot</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yiheng Wang</a>, <a href="/search/cs?searchtype=author&query=Murrey%2C+B">Benjamin Murrey</a>, <a href="/search/cs?searchtype=author&query=Myronenko%2C+A">Andriy Myronenko</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+C">Can Zhao</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+D">Dong Yang</a>, <a href="/search/cs?searchtype=author&query=Nath%2C+V">Vishwesh Nath</a>, <a href="/search/cs?searchtype=author&query=He%2C+Y">Yufan He</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Z">Ziyue Xu</a>, <a href="/search/cs?searchtype=author&query=Hatamizadeh%2C+A">Ali Hatamizadeh</a>, <a href="/search/cs?searchtype=author&query=Myronenko%2C+A">Andriy Myronenko</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+W">Wentao Zhu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yun Liu</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+M">Mingxin Zheng</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+Y">Yucheng Tang</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+I">Isaac Yang</a>, <a href="/search/cs?searchtype=author&query=Zephyr%2C+M">Michael Zephyr</a>, <a href="/search/cs?searchtype=author&query=Hashemian%2C+B">Behrooz Hashemian</a>, <a href="/search/cs?searchtype=author&query=Alle%2C+S">Sachidanand Alle</a>, <a href="/search/cs?searchtype=author&query=Darestani%2C+M+Z">Mohammad Zalbagi Darestani</a>, <a href="/search/cs?searchtype=author&query=Budd%2C+C">Charlie Budd</a> , et al. (32 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="2211.02701v1-abstract-short" style="display: inline;"> Artificial Intelligence (AI) is having a tremendous impact across most areas of science. Applications of AI in healthcare have the potential to improve our ability to detect, diagnose, prognose, and intervene on human disease. For AI models to be used clinically, they need to be made safe, reproducible and robust, and the underlying software framework must be aware of the particularities (e.g. geo… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.02701v1-abstract-full').style.display = 'inline'; document.getElementById('2211.02701v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2211.02701v1-abstract-full" style="display: none;"> Artificial Intelligence (AI) is having a tremendous impact across most areas of science. Applications of AI in healthcare have the potential to improve our ability to detect, diagnose, prognose, and intervene on human disease. For AI models to be used clinically, they need to be made safe, reproducible and robust, and the underlying software framework must be aware of the particularities (e.g. geometry, physiology, physics) of medical data being processed. This work introduces MONAI, a freely available, community-supported, and consortium-led PyTorch-based framework for deep learning in healthcare. MONAI extends PyTorch to support medical data, with a particular focus on imaging, and provide purpose-specific AI model architectures, transformations and utilities that streamline the development and deployment of medical AI models. MONAI follows best practices for software-development, providing an easy-to-use, robust, well-documented, and well-tested software framework. MONAI preserves the simple, additive, and compositional approach of its underlying PyTorch libraries. MONAI is being used by and receiving contributions from research, clinical and industrial teams from around the world, who are pursuing applications spanning nearly every aspect of healthcare. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.02701v1-abstract-full').style.display = 'none'; document.getElementById('2211.02701v1-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 November, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2022. </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">www.monai.io</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2210.13291">arXiv:2210.13291</a> <span> [<a href="https://arxiv.org/pdf/2210.13291">pdf</a>, <a href="https://arxiv.org/format/2210.13291">other</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="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="Networking and Internet Architecture">cs.NI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</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/10.48550/arXiv.2210.13291">10.48550/arXiv.2210.13291 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> NVIDIA FLARE: Federated Learning from Simulation to Real-World </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Roth%2C+H+R">Holger R. Roth</a>, <a href="/search/cs?searchtype=author&query=Cheng%2C+Y">Yan Cheng</a>, <a href="/search/cs?searchtype=author&query=Wen%2C+Y">Yuhong Wen</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+I">Isaac Yang</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Z">Ziyue Xu</a>, <a href="/search/cs?searchtype=author&query=Hsieh%2C+Y">Yuan-Ting Hsieh</a>, <a href="/search/cs?searchtype=author&query=Kersten%2C+K">Kristopher Kersten</a>, <a href="/search/cs?searchtype=author&query=Harouni%2C+A">Ahmed Harouni</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+C">Can Zhao</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+K">Kevin Lu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zhihong Zhang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+W">Wenqi Li</a>, <a href="/search/cs?searchtype=author&query=Myronenko%2C+A">Andriy Myronenko</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+D">Dong Yang</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+S">Sean Yang</a>, <a href="/search/cs?searchtype=author&query=Rieke%2C+N">Nicola Rieke</a>, <a href="/search/cs?searchtype=author&query=Quraini%2C+A">Abood Quraini</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+C">Chester Chen</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+D">Daguang Xu</a>, <a href="/search/cs?searchtype=author&query=Ma%2C+N">Nic Ma</a>, <a href="/search/cs?searchtype=author&query=Dogra%2C+P">Prerna Dogra</a>, <a href="/search/cs?searchtype=author&query=Flores%2C+M">Mona Flores</a>, <a href="/search/cs?searchtype=author&query=Feng%2C+A">Andrew Feng</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="2210.13291v3-abstract-short" style="display: inline;"> Federated learning (FL) enables building robust and generalizable AI models by leveraging diverse datasets from multiple collaborators without centralizing the data. We created NVIDIA FLARE as an open-source software development kit (SDK) to make it easier for data scientists to use FL in their research and real-world applications. The SDK includes solutions for state-of-the-art FL algorithms and… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2210.13291v3-abstract-full').style.display = 'inline'; document.getElementById('2210.13291v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2210.13291v3-abstract-full" style="display: none;"> Federated learning (FL) enables building robust and generalizable AI models by leveraging diverse datasets from multiple collaborators without centralizing the data. We created NVIDIA FLARE as an open-source software development kit (SDK) to make it easier for data scientists to use FL in their research and real-world applications. The SDK includes solutions for state-of-the-art FL algorithms and federated machine learning approaches, which facilitate building workflows for distributed learning across enterprises and enable platform developers to create a secure, privacy-preserving offering for multiparty collaboration utilizing homomorphic encryption or differential privacy. The SDK is a lightweight, flexible, and scalable Python package. It allows researchers to apply their data science workflows in any training libraries (PyTorch, TensorFlow, XGBoost, or even NumPy) in real-world FL settings. This paper introduces the key design principles of NVFlare and illustrates some use cases (e.g., COVID analysis) with customizable FL workflows that implement different privacy-preserving algorithms. Code is available at https://github.com/NVIDIA/NVFlare. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2210.13291v3-abstract-full').style.display = 'none'; document.getElementById('2210.13291v3-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> 28 April, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 24 October, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2022. </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 at the International Workshop on Federated Learning, NeurIPS 2022, New Orleans, USA (https://federated-learning.org/fl-neurips-2022); Revised version v2: added Key Components list, system metrics for homomorphic encryption experiment; Extended v3 for journal submission</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> IEEE Data Eng. Bull., Vol. 46, No. 1, 2023 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2209.06285">arXiv:2209.06285</a> <span> [<a href="https://arxiv.org/pdf/2209.06285">pdf</a>, <a href="https://arxiv.org/format/2209.06285">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> </div> </div> <p class="title is-5 mathjax"> Warm Start Active Learning with Proxy Labels \& Selection via Semi-Supervised Fine-Tuning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nath%2C+V">Vishwesh Nath</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+D">Dong Yang</a>, <a href="/search/cs?searchtype=author&query=Roth%2C+H+R">Holger R. Roth</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+D">Daguang Xu</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="2209.06285v1-abstract-short" style="display: inline;"> Which volume to annotate next is a challenging problem in building medical imaging datasets for deep learning. One of the promising methods to approach this question is active learning (AL). However, AL has been a hard nut to crack in terms of which AL algorithm and acquisition functions are most useful for which datasets. Also, the problem is exacerbated with which volumes to label first when the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2209.06285v1-abstract-full').style.display = 'inline'; document.getElementById('2209.06285v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2209.06285v1-abstract-full" style="display: none;"> Which volume to annotate next is a challenging problem in building medical imaging datasets for deep learning. One of the promising methods to approach this question is active learning (AL). However, AL has been a hard nut to crack in terms of which AL algorithm and acquisition functions are most useful for which datasets. Also, the problem is exacerbated with which volumes to label first when there is zero labeled data to start with. This is known as the cold start problem in AL. We propose two novel strategies for AL specifically for 3D image segmentation. First, we tackle the cold start problem by proposing a proxy task and then utilizing uncertainty generated from the proxy task to rank the unlabeled data to be annotated. Second, we craft a two-stage learning framework for each active iteration where the unlabeled data is also used in the second stage as a semi-supervised fine-tuning strategy. We show the promise of our approach on two well-known large public datasets from medical segmentation decathlon. The results indicate that the initial selection of data and semi-supervised framework both showed significant improvement for several AL strategies. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2209.06285v1-abstract-full').style.display = 'none'; document.getElementById('2209.06285v1-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> 13 September, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2022. </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">12 pages, 5 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2209.05984">arXiv:2209.05984</a> <span> [<a href="https://arxiv.org/pdf/2209.05984">pdf</a>, <a href="https://arxiv.org/format/2209.05984">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</span> </div> </div> <p class="title is-5 mathjax"> Distributed SDN-based Load-balanced Routing for Low Earth Orbit Satellite Constellation Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Roth%2C+M+M+H">Manuel M. H. Roth</a>, <a href="/search/cs?searchtype=author&query=Brandt%2C+H">Hartmut Brandt</a>, <a href="/search/cs?searchtype=author&query=Bischl%2C+H">Hermann Bischl</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="2209.05984v1-abstract-short" style="display: inline;"> With the current trend towards low Earth orbit mega-constellations with inter-satellite links, efficient routing in such highly dynamic space-borne networks is becoming increasingly important. Due to the distinct network topology, specifically tailored solutions are required. Firstly, the relative movement of the constellation causes frequent handover events between the satellites and the terminal… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2209.05984v1-abstract-full').style.display = 'inline'; document.getElementById('2209.05984v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2209.05984v1-abstract-full" style="display: none;"> With the current trend towards low Earth orbit mega-constellations with inter-satellite links, efficient routing in such highly dynamic space-borne networks is becoming increasingly important. Due to the distinct network topology, specifically tailored solutions are required. Firstly, the relative movement of the constellation causes frequent handover events between the satellites and the terminals on ground. Furthermore, unevenly distributed traffic demands lead to geographical hot spots. The physical size of the network also implies significant propagation delays. Therefore, monitoring the dynamic topology changes and link loads on a network-wide basis for routing purposes is typically impractical with massive signaling overhead. To address these issues, we propose a distributed load-balanced routing scheme based on Software Defined Networking. The approach divides the large-scale network into sub-sections, called clusters. In order to minimize signaling overhead, packets are forwarded between these clusters according to geographical heuristics. Within each cluster active Quality of Service-aware load-balancing is applied. The responsible on-board network controller forwards routing instructions based on the network state information in its cluster. We also analyze specific design choices for the clusters and the interfaces between them. The protocol has been implemented in a system-level simulator and compared to a source-routed benchmark solution. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2209.05984v1-abstract-full').style.display = 'none'; document.getElementById('2209.05984v1-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> 13 September, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2208.10553">arXiv:2208.10553</a> <span> [<a href="https://arxiv.org/pdf/2208.10553">pdf</a>, <a href="https://arxiv.org/ps/2208.10553">ps</a>, <a href="https://arxiv.org/format/2208.10553">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="Cryptography and Security">cs.CR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> </div> <p class="title is-5 mathjax"> Split-U-Net: Preventing Data Leakage in Split Learning for Collaborative Multi-Modal Brain Tumor Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Roth%2C+H+R">Holger R. Roth</a>, <a href="/search/cs?searchtype=author&query=Hatamizadeh%2C+A">Ali Hatamizadeh</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Z">Ziyue Xu</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+C">Can Zhao</a>, <a href="/search/cs?searchtype=author&query=Li%2C+W">Wenqi Li</a>, <a href="/search/cs?searchtype=author&query=Myronenko%2C+A">Andriy Myronenko</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+D">Daguang Xu</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="2208.10553v2-abstract-short" style="display: inline;"> Split learning (SL) has been proposed to train deep learning models in a decentralized manner. For decentralized healthcare applications with vertical data partitioning, SL can be beneficial as it allows institutes with complementary features or images for a shared set of patients to jointly develop more robust and generalizable models. In this work, we propose "Split-U-Net" and successfully apply… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2208.10553v2-abstract-full').style.display = 'inline'; document.getElementById('2208.10553v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2208.10553v2-abstract-full" style="display: none;"> Split learning (SL) has been proposed to train deep learning models in a decentralized manner. For decentralized healthcare applications with vertical data partitioning, SL can be beneficial as it allows institutes with complementary features or images for a shared set of patients to jointly develop more robust and generalizable models. In this work, we propose "Split-U-Net" and successfully apply SL for collaborative biomedical image segmentation. Nonetheless, SL requires the exchanging of intermediate activation maps and gradients to allow training models across different feature spaces, which might leak data and raise privacy concerns. Therefore, we also quantify the amount of data leakage in common SL scenarios for biomedical image segmentation and provide ways to counteract such leakage by applying appropriate defense strategies. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2208.10553v2-abstract-full').style.display = 'none'; document.getElementById('2208.10553v2-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> 26 September, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 22 August, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2022. </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 DeCaF 2022 held in conjunction with MICCAI 2022</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2204.00631">arXiv:2204.00631</a> <span> [<a href="https://arxiv.org/pdf/2204.00631">pdf</a>, <a href="https://arxiv.org/format/2204.00631">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> <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"> UNetFormer: A Unified Vision Transformer Model and Pre-Training Framework for 3D Medical Image Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hatamizadeh%2C+A">Ali Hatamizadeh</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Z">Ziyue Xu</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+D">Dong Yang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+W">Wenqi Li</a>, <a href="/search/cs?searchtype=author&query=Roth%2C+H">Holger Roth</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+D">Daguang Xu</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="2204.00631v2-abstract-short" style="display: inline;"> Vision Transformers (ViT)s have recently become popular due to their outstanding modeling capabilities, in particular for capturing long-range information, and scalability to dataset and model sizes which has led to state-of-the-art performance in various computer vision and medical image analysis tasks. In this work, we introduce a unified framework consisting of two architectures, dubbed UNetFor… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2204.00631v2-abstract-full').style.display = 'inline'; document.getElementById('2204.00631v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2204.00631v2-abstract-full" style="display: none;"> Vision Transformers (ViT)s have recently become popular due to their outstanding modeling capabilities, in particular for capturing long-range information, and scalability to dataset and model sizes which has led to state-of-the-art performance in various computer vision and medical image analysis tasks. In this work, we introduce a unified framework consisting of two architectures, dubbed UNetFormer, with a 3D Swin Transformer-based encoder and Convolutional Neural Network (CNN) and transformer-based decoders. In the proposed model, the encoder is linked to the decoder via skip connections at five different resolutions with deep supervision. The design of proposed architecture allows for meeting a wide range of trade-off requirements between accuracy and computational cost. In addition, we present a methodology for self-supervised pre-training of the encoder backbone via learning to predict randomly masked volumetric tokens using contextual information of visible tokens. We pre-train our framework on a cohort of $5050$ CT images, gathered from publicly available CT datasets, and present a systematic investigation of various components such as masking ratio and patch size that affect the representation learning capability and performance of downstream tasks. We validate the effectiveness of our pre-training approach by fine-tuning and testing our model on liver and liver tumor segmentation task using the Medical Segmentation Decathlon (MSD) dataset and achieve state-of-the-art performance in terms of various segmentation metrics. To demonstrate its generalizability, we train and test the model on BraTS 21 dataset for brain tumor segmentation using MRI images and outperform other methods in terms of Dice score. Code: https://github.com/Project-MONAI/research-contributions <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2204.00631v2-abstract-full').style.display = 'none'; document.getElementById('2204.00631v2-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 April, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 1 April, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2022. </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">Tech. report, 12 pages, 3 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2203.12362">arXiv:2203.12362</a> <span> [<a href="https://arxiv.org/pdf/2203.12362">pdf</a>, <a href="https://arxiv.org/format/2203.12362">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</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> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</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/10.1016/j.media.2024.103207">10.1016/j.media.2024.103207 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> MONAI Label: A framework for AI-assisted Interactive Labeling of 3D Medical Images </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Diaz-Pinto%2C+A">Andres Diaz-Pinto</a>, <a href="/search/cs?searchtype=author&query=Alle%2C+S">Sachidanand Alle</a>, <a href="/search/cs?searchtype=author&query=Nath%2C+V">Vishwesh Nath</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+Y">Yucheng Tang</a>, <a href="/search/cs?searchtype=author&query=Ihsani%2C+A">Alvin Ihsani</a>, <a href="/search/cs?searchtype=author&query=Asad%2C+M">Muhammad Asad</a>, <a href="/search/cs?searchtype=author&query=P%C3%A9rez-Garc%C3%ADa%2C+F">Fernando P茅rez-Garc铆a</a>, <a href="/search/cs?searchtype=author&query=Mehta%2C+P">Pritesh Mehta</a>, <a href="/search/cs?searchtype=author&query=Li%2C+W">Wenqi Li</a>, <a href="/search/cs?searchtype=author&query=Flores%2C+M">Mona Flores</a>, <a href="/search/cs?searchtype=author&query=Roth%2C+H+R">Holger R. Roth</a>, <a href="/search/cs?searchtype=author&query=Vercauteren%2C+T">Tom Vercauteren</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+D">Daguang Xu</a>, <a href="/search/cs?searchtype=author&query=Dogra%2C+P">Prerna Dogra</a>, <a href="/search/cs?searchtype=author&query=Ourselin%2C+S">Sebastien Ourselin</a>, <a href="/search/cs?searchtype=author&query=Feng%2C+A">Andrew Feng</a>, <a href="/search/cs?searchtype=author&query=Cardoso%2C+M+J">M. Jorge Cardoso</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="2203.12362v2-abstract-short" style="display: inline;"> The lack of annotated datasets is a major bottleneck for training new task-specific supervised machine learning models, considering that manual annotation is extremely expensive and time-consuming. To address this problem, we present MONAI Label, a free and open-source framework that facilitates the development of applications based on artificial intelligence (AI) models that aim at reducing the t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.12362v2-abstract-full').style.display = 'inline'; document.getElementById('2203.12362v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2203.12362v2-abstract-full" style="display: none;"> The lack of annotated datasets is a major bottleneck for training new task-specific supervised machine learning models, considering that manual annotation is extremely expensive and time-consuming. To address this problem, we present MONAI Label, a free and open-source framework that facilitates the development of applications based on artificial intelligence (AI) models that aim at reducing the time required to annotate radiology datasets. Through MONAI Label, researchers can develop AI annotation applications focusing on their domain of expertise. It allows researchers to readily deploy their apps as services, which can be made available to clinicians via their preferred user interface. Currently, MONAI Label readily supports locally installed (3D Slicer) and web-based (OHIF) frontends and offers two active learning strategies to facilitate and speed up the training of segmentation algorithms. MONAI Label allows researchers to make incremental improvements to their AI-based annotation application by making them available to other researchers and clinicians alike. Additionally, MONAI Label provides sample AI-based interactive and non-interactive labeling applications, that can be used directly off the shelf, as plug-and-play to any given dataset. Significant reduced annotation times using the interactive model can be observed on two public datasets. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.12362v2-abstract-full').style.display = 'none'; document.getElementById('2203.12362v2-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> 28 April, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 23 March, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2203.11894">arXiv:2203.11894</a> <span> [<a href="https://arxiv.org/pdf/2203.11894">pdf</a>, <a href="https://arxiv.org/format/2203.11894">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="Cryptography and Security">cs.CR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</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"> GradViT: Gradient Inversion of Vision Transformers </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hatamizadeh%2C+A">Ali Hatamizadeh</a>, <a href="/search/cs?searchtype=author&query=Yin%2C+H">Hongxu Yin</a>, <a href="/search/cs?searchtype=author&query=Roth%2C+H">Holger Roth</a>, <a href="/search/cs?searchtype=author&query=Li%2C+W">Wenqi Li</a>, <a href="/search/cs?searchtype=author&query=Kautz%2C+J">Jan Kautz</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+D">Daguang Xu</a>, <a href="/search/cs?searchtype=author&query=Molchanov%2C+P">Pavlo Molchanov</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="2203.11894v3-abstract-short" style="display: inline;"> In this work we demonstrate the vulnerability of vision transformers (ViTs) to gradient-based inversion attacks. During this attack, the original data batch is reconstructed given model weights and the corresponding gradients. We introduce a method, named GradViT, that optimizes random noise into naturally looking images via an iterative process. The optimization objective consists of (i) a loss o… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.11894v3-abstract-full').style.display = 'inline'; document.getElementById('2203.11894v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2203.11894v3-abstract-full" style="display: none;"> In this work we demonstrate the vulnerability of vision transformers (ViTs) to gradient-based inversion attacks. During this attack, the original data batch is reconstructed given model weights and the corresponding gradients. We introduce a method, named GradViT, that optimizes random noise into naturally looking images via an iterative process. The optimization objective consists of (i) a loss on matching the gradients, (ii) image prior in the form of distance to batch-normalization statistics of a pretrained CNN model, and (iii) a total variation regularization on patches to guide correct recovery locations. We propose a unique loss scheduling function to overcome local minima during optimization. We evaluate GadViT on ImageNet1K and MS-Celeb-1M datasets, and observe unprecedentedly high fidelity and closeness to the original (hidden) data. During the analysis we find that vision transformers are significantly more vulnerable than previously studied CNNs due to the presence of the attention mechanism. Our method demonstrates new state-of-the-art results for gradient inversion in both qualitative and quantitative metrics. Project page at https://gradvit.github.io/. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.11894v3-abstract-full').style.display = 'none'; document.getElementById('2203.11894v3-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> 27 March, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 22 March, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2022. </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'22 Accepted Paper</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2203.10144">arXiv:2203.10144</a> <span> [<a href="https://arxiv.org/pdf/2203.10144">pdf</a>, <a href="https://arxiv.org/format/2203.10144">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> </div> </div> <p class="title is-5 mathjax"> Closing the Generalization Gap of Cross-silo Federated Medical Image Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xu%2C+A">An Xu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+W">Wenqi Li</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+P">Pengfei Guo</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+D">Dong Yang</a>, <a href="/search/cs?searchtype=author&query=Roth%2C+H">Holger Roth</a>, <a href="/search/cs?searchtype=author&query=Hatamizadeh%2C+A">Ali Hatamizadeh</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+C">Can Zhao</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+D">Daguang Xu</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+H">Heng Huang</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Z">Ziyue Xu</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="2203.10144v2-abstract-short" style="display: inline;"> Cross-silo federated learning (FL) has attracted much attention in medical imaging analysis with deep learning in recent years as it can resolve the critical issues of insufficient data, data privacy, and training efficiency. However, there can be a generalization gap between the model trained from FL and the one from centralized training. This important issue comes from the non-iid data distribut… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.10144v2-abstract-full').style.display = 'inline'; document.getElementById('2203.10144v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2203.10144v2-abstract-full" style="display: none;"> Cross-silo federated learning (FL) has attracted much attention in medical imaging analysis with deep learning in recent years as it can resolve the critical issues of insufficient data, data privacy, and training efficiency. However, there can be a generalization gap between the model trained from FL and the one from centralized training. This important issue comes from the non-iid data distribution of the local data in the participating clients and is well-known as client drift. In this work, we propose a novel training framework FedSM to avoid the client drift issue and successfully close the generalization gap compared with the centralized training for medical image segmentation tasks for the first time. We also propose a novel personalized FL objective formulation and a new method SoftPull to solve it in our proposed framework FedSM. We conduct rigorous theoretical analysis to guarantee its convergence for optimizing the non-convex smooth objective function. Real-world medical image segmentation experiments using deep FL validate the motivations and effectiveness of our proposed method. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.10144v2-abstract-full').style.display = 'none'; document.getElementById('2203.10144v2-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 February, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 18 March, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2022. </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 2022</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2203.06338">arXiv:2203.06338</a> <span> [<a href="https://arxiv.org/pdf/2203.06338">pdf</a>, <a href="https://arxiv.org/format/2203.06338">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"> Auto-FedRL: Federated Hyperparameter Optimization for Multi-institutional Medical Image Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Guo%2C+P">Pengfei Guo</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+D">Dong Yang</a>, <a href="/search/cs?searchtype=author&query=Hatamizadeh%2C+A">Ali Hatamizadeh</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+A">An Xu</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Z">Ziyue Xu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+W">Wenqi Li</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+C">Can Zhao</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+D">Daguang Xu</a>, <a href="/search/cs?searchtype=author&query=Harmon%2C+S">Stephanie Harmon</a>, <a href="/search/cs?searchtype=author&query=Turkbey%2C+E">Evrim Turkbey</a>, <a href="/search/cs?searchtype=author&query=Turkbey%2C+B">Baris Turkbey</a>, <a href="/search/cs?searchtype=author&query=Wood%2C+B">Bradford Wood</a>, <a href="/search/cs?searchtype=author&query=Patella%2C+F">Francesca Patella</a>, <a href="/search/cs?searchtype=author&query=Stellato%2C+E">Elvira Stellato</a>, <a href="/search/cs?searchtype=author&query=Carrafiello%2C+G">Gianpaolo Carrafiello</a>, <a href="/search/cs?searchtype=author&query=Patel%2C+V+M">Vishal M. Patel</a>, <a href="/search/cs?searchtype=author&query=Roth%2C+H+R">Holger R. Roth</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="2203.06338v2-abstract-short" style="display: inline;"> Federated learning (FL) is a distributed machine learning technique that enables collaborative model training while avoiding explicit data sharing. The inherent privacy-preserving property of FL algorithms makes them especially attractive to the medical field. However, in case of heterogeneous client data distributions, standard FL methods are unstable and require intensive hyperparameter tuning t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.06338v2-abstract-full').style.display = 'inline'; document.getElementById('2203.06338v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2203.06338v2-abstract-full" style="display: none;"> Federated learning (FL) is a distributed machine learning technique that enables collaborative model training while avoiding explicit data sharing. The inherent privacy-preserving property of FL algorithms makes them especially attractive to the medical field. However, in case of heterogeneous client data distributions, standard FL methods are unstable and require intensive hyperparameter tuning to achieve optimal performance. Conventional hyperparameter optimization algorithms are impractical in real-world FL applications as they involve numerous training trials, which are often not affordable with limited compute budgets. In this work, we propose an efficient reinforcement learning (RL)-based federated hyperparameter optimization algorithm, termed Auto-FedRL, in which an online RL agent can dynamically adjust hyperparameters of each client based on the current training progress. Extensive experiments are conducted to investigate different search strategies and RL agents. The effectiveness of the proposed method is validated on a heterogeneous data split of the CIFAR-10 dataset as well as two real-world medical image segmentation datasets for COVID-19 lesion segmentation in chest CT and pancreas segmentation in abdominal CT. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.06338v2-abstract-full').style.display = 'none'; document.getElementById('2203.06338v2-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 August, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 11 March, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2202.06924">arXiv:2202.06924</a> <span> [<a href="https://arxiv.org/pdf/2202.06924">pdf</a>, <a href="https://arxiv.org/format/2202.06924">other</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="Cryptography and Security">cs.CR</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="Distributed, Parallel, and Cluster Computing">cs.DC</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/TMI.2023.3239391">10.1109/TMI.2023.3239391 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Do Gradient Inversion Attacks Make Federated Learning Unsafe? </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hatamizadeh%2C+A">Ali Hatamizadeh</a>, <a href="/search/cs?searchtype=author&query=Yin%2C+H">Hongxu Yin</a>, <a href="/search/cs?searchtype=author&query=Molchanov%2C+P">Pavlo Molchanov</a>, <a href="/search/cs?searchtype=author&query=Myronenko%2C+A">Andriy Myronenko</a>, <a href="/search/cs?searchtype=author&query=Li%2C+W">Wenqi Li</a>, <a href="/search/cs?searchtype=author&query=Dogra%2C+P">Prerna Dogra</a>, <a href="/search/cs?searchtype=author&query=Feng%2C+A">Andrew Feng</a>, <a href="/search/cs?searchtype=author&query=Flores%2C+M+G">Mona G. Flores</a>, <a href="/search/cs?searchtype=author&query=Kautz%2C+J">Jan Kautz</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+D">Daguang Xu</a>, <a href="/search/cs?searchtype=author&query=Roth%2C+H+R">Holger R. Roth</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="2202.06924v3-abstract-short" style="display: inline;"> Federated learning (FL) allows the collaborative training of AI models without needing to share raw data. This capability makes it especially interesting for healthcare applications where patient and data privacy is of utmost concern. However, recent works on the inversion of deep neural networks from model gradients raised concerns about the security of FL in preventing the leakage of training da… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2202.06924v3-abstract-full').style.display = 'inline'; document.getElementById('2202.06924v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2202.06924v3-abstract-full" style="display: none;"> Federated learning (FL) allows the collaborative training of AI models without needing to share raw data. This capability makes it especially interesting for healthcare applications where patient and data privacy is of utmost concern. However, recent works on the inversion of deep neural networks from model gradients raised concerns about the security of FL in preventing the leakage of training data. In this work, we show that these attacks presented in the literature are impractical in FL use-cases where the clients' training involves updating the Batch Normalization (BN) statistics and provide a new baseline attack that works for such scenarios. Furthermore, we present new ways to measure and visualize potential data leakage in FL. Our work is a step towards establishing reproducible methods of measuring data leakage in FL and could help determine the optimal tradeoffs between privacy-preserving techniques, such as differential privacy, and model accuracy based on quantifiable metrics. Code is available at https://nvidia.github.io/NVFlare/research/quantifying-data-leakage. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2202.06924v3-abstract-full').style.display = 'none'; document.getElementById('2202.06924v3-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 January, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 14 February, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2022. </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">Revised version; Accepted to IEEE Transactions on Medical Imaging; Improved and reformatted version of https://www.researchsquare.com/article/rs-1147182/v2; Added NVFlare reference</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2201.01266">arXiv:2201.01266</a> <span> [<a href="https://arxiv.org/pdf/2201.01266">pdf</a>, <a href="https://arxiv.org/format/2201.01266">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"> Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Images </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hatamizadeh%2C+A">Ali Hatamizadeh</a>, <a href="/search/cs?searchtype=author&query=Nath%2C+V">Vishwesh Nath</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+Y">Yucheng Tang</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+D">Dong Yang</a>, <a href="/search/cs?searchtype=author&query=Roth%2C+H">Holger Roth</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+D">Daguang Xu</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="2201.01266v1-abstract-short" style="display: inline;"> Semantic segmentation of brain tumors is a fundamental medical image analysis task involving multiple MRI imaging modalities that can assist clinicians in diagnosing the patient and successively studying the progression of the malignant entity. In recent years, Fully Convolutional Neural Networks (FCNNs) approaches have become the de facto standard for 3D medical image segmentation. The popular "U… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2201.01266v1-abstract-full').style.display = 'inline'; document.getElementById('2201.01266v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2201.01266v1-abstract-full" style="display: none;"> Semantic segmentation of brain tumors is a fundamental medical image analysis task involving multiple MRI imaging modalities that can assist clinicians in diagnosing the patient and successively studying the progression of the malignant entity. In recent years, Fully Convolutional Neural Networks (FCNNs) approaches have become the de facto standard for 3D medical image segmentation. The popular "U-shaped" network architecture has achieved state-of-the-art performance benchmarks on different 2D and 3D semantic segmentation tasks and across various imaging modalities. However, due to the limited kernel size of convolution layers in FCNNs, their performance of modeling long-range information is sub-optimal, and this can lead to deficiencies in the segmentation of tumors with variable sizes. On the other hand, transformer models have demonstrated excellent capabilities in capturing such long-range information in multiple domains, including natural language processing and computer vision. Inspired by the success of vision transformers and their variants, we propose a novel segmentation model termed Swin UNEt TRansformers (Swin UNETR). Specifically, the task of 3D brain tumor semantic segmentation is reformulated as a sequence to sequence prediction problem wherein multi-modal input data is projected into a 1D sequence of embedding and used as an input to a hierarchical Swin transformer as the encoder. The swin transformer encoder extracts features at five different resolutions by utilizing shifted windows for computing self-attention and is connected to an FCNN-based decoder at each resolution via skip connections. We have participated in BraTS 2021 segmentation challenge, and our proposed model ranks among the top-performing approaches in the validation phase. Code: https://monai.io/research/swin-unetr <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2201.01266v1-abstract-full').style.display = 'none'; document.getElementById('2201.01266v1-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 January, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2022. </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">13 pages, 3 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2111.14791">arXiv:2111.14791</a> <span> [<a href="https://arxiv.org/pdf/2111.14791">pdf</a>, <a href="https://arxiv.org/format/2111.14791">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="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Self-Supervised Pre-Training of Swin Transformers for 3D Medical Image Analysis </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tang%2C+Y">Yucheng Tang</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+D">Dong Yang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+W">Wenqi Li</a>, <a href="/search/cs?searchtype=author&query=Roth%2C+H">Holger Roth</a>, <a href="/search/cs?searchtype=author&query=Landman%2C+B">Bennett Landman</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+D">Daguang Xu</a>, <a href="/search/cs?searchtype=author&query=Nath%2C+V">Vishwesh Nath</a>, <a href="/search/cs?searchtype=author&query=Hatamizadeh%2C+A">Ali Hatamizadeh</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="2111.14791v2-abstract-short" style="display: inline;"> Vision Transformers (ViT)s have shown great performance in self-supervised learning of global and local representations that can be transferred to downstream applications. Inspired by these results, we introduce a novel self-supervised learning framework with tailored proxy tasks for medical image analysis. Specifically, we propose: (i) a new 3D transformer-based model, dubbed Swin UNEt TRansforme… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2111.14791v2-abstract-full').style.display = 'inline'; document.getElementById('2111.14791v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2111.14791v2-abstract-full" style="display: none;"> Vision Transformers (ViT)s have shown great performance in self-supervised learning of global and local representations that can be transferred to downstream applications. Inspired by these results, we introduce a novel self-supervised learning framework with tailored proxy tasks for medical image analysis. Specifically, we propose: (i) a new 3D transformer-based model, dubbed Swin UNEt TRansformers (Swin UNETR), with a hierarchical encoder for self-supervised pre-training; (ii) tailored proxy tasks for learning the underlying pattern of human anatomy. We demonstrate successful pre-training of the proposed model on 5,050 publicly available computed tomography (CT) images from various body organs. The effectiveness of our approach is validated by fine-tuning the pre-trained models on the Beyond the Cranial Vault (BTCV) Segmentation Challenge with 13 abdominal organs and segmentation tasks from the Medical Segmentation Decathlon (MSD) dataset. Our model is currently the state-of-the-art (i.e. ranked 1st) on the public test leaderboards of both MSD and BTCV datasets. Code: https://monai.io/research/swin-unetr <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2111.14791v2-abstract-full').style.display = 'none'; document.getElementById('2111.14791v2-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> 28 March, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 29 November, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2021. </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'22 Accepted Paper</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2111.07535">arXiv:2111.07535</a> <span> [<a href="https://arxiv.org/pdf/2111.07535">pdf</a>, <a href="https://arxiv.org/format/2111.07535">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"> T-AutoML: Automated Machine Learning for Lesion Segmentation using Transformers in 3D Medical Imaging </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+D">Dong Yang</a>, <a href="/search/cs?searchtype=author&query=Myronenko%2C+A">Andriy Myronenko</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+X">Xiaosong Wang</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Z">Ziyue Xu</a>, <a href="/search/cs?searchtype=author&query=Roth%2C+H+R">Holger R. Roth</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+D">Daguang Xu</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="2111.07535v1-abstract-short" style="display: inline;"> Lesion segmentation in medical imaging has been an important topic in clinical research. Researchers have proposed various detection and segmentation algorithms to address this task. Recently, deep learning-based approaches have significantly improved the performance over conventional methods. However, most state-of-the-art deep learning methods require the manual design of multiple network compon… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2111.07535v1-abstract-full').style.display = 'inline'; document.getElementById('2111.07535v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2111.07535v1-abstract-full" style="display: none;"> Lesion segmentation in medical imaging has been an important topic in clinical research. Researchers have proposed various detection and segmentation algorithms to address this task. Recently, deep learning-based approaches have significantly improved the performance over conventional methods. However, most state-of-the-art deep learning methods require the manual design of multiple network components and training strategies. In this paper, we propose a new automated machine learning algorithm, T-AutoML, which not only searches for the best neural architecture, but also finds the best combination of hyper-parameters and data augmentation strategies simultaneously. The proposed method utilizes the modern transformer model, which is introduced to adapt to the dynamic length of the search space embedding and can significantly improve the ability of the search. We validate T-AutoML on several large-scale public lesion segmentation data-sets and achieve state-of-the-art performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2111.07535v1-abstract-full').style.display = 'none'; document.getElementById('2111.07535v1-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, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2021. </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 at ICCV 2021</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2111.01556">arXiv:2111.01556</a> <span> [<a href="https://arxiv.org/pdf/2111.01556">pdf</a>, <a href="https://arxiv.org/format/2111.01556">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="Quantitative Methods">q-bio.QM</span> </div> </div> <p class="title is-5 mathjax"> Accounting for Dependencies in Deep Learning Based Multiple Instance Learning for Whole Slide Imaging </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Myronenko%2C+A">Andriy Myronenko</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Z">Ziyue Xu</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+D">Dong Yang</a>, <a href="/search/cs?searchtype=author&query=Roth%2C+H">Holger Roth</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+D">Daguang Xu</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="2111.01556v1-abstract-short" style="display: inline;"> Multiple instance learning (MIL) is a key algorithm for classification of whole slide images (WSI). Histology WSIs can have billions of pixels, which create enormous computational and annotation challenges. Typically, such images are divided into a set of patches (a bag of instances), where only bag-level class labels are provided. Deep learning based MIL methods calculate instance features using… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2111.01556v1-abstract-full').style.display = 'inline'; document.getElementById('2111.01556v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2111.01556v1-abstract-full" style="display: none;"> Multiple instance learning (MIL) is a key algorithm for classification of whole slide images (WSI). Histology WSIs can have billions of pixels, which create enormous computational and annotation challenges. Typically, such images are divided into a set of patches (a bag of instances), where only bag-level class labels are provided. Deep learning based MIL methods calculate instance features using convolutional neural network (CNN). Our proposed approach is also deep learning based, with the following two contributions: Firstly, we propose to explicitly account for dependencies between instances during training by embedding self-attention Transformer blocks to capture dependencies between instances. For example, a tumor grade may depend on the presence of several particular patterns at different locations in WSI, which requires to account for dependencies between patches. Secondly, we propose an instance-wise loss function based on instance pseudo-labels. We compare the proposed algorithm to multiple baseline methods, evaluate it on the PANDA challenge dataset, the largest publicly available WSI dataset with over 11K images, and demonstrate state-of-the-art results. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2111.01556v1-abstract-full').style.display = 'none'; document.getElementById('2111.01556v1-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> 1 November, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2021. </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">MICCAI 2021</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2108.08537">arXiv:2108.08537</a> <span> [<a href="https://arxiv.org/pdf/2108.08537">pdf</a>, <a href="https://arxiv.org/format/2108.08537">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> </div> </div> <p class="title is-5 mathjax"> Multi-task Federated Learning for Heterogeneous Pancreas Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shen%2C+C">Chen Shen</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+P">Pochuan Wang</a>, <a href="/search/cs?searchtype=author&query=Roth%2C+H+R">Holger R. Roth</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+D">Dong Yang</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+D">Daguang Xu</a>, <a href="/search/cs?searchtype=author&query=Oda%2C+M">Masahiro Oda</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+W">Weichung Wang</a>, <a href="/search/cs?searchtype=author&query=Fuh%2C+C">Chiou-Shann Fuh</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+P">Po-Ting Chen</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+K">Kao-Lang Liu</a>, <a href="/search/cs?searchtype=author&query=Liao%2C+W">Wei-Chih Liao</a>, <a href="/search/cs?searchtype=author&query=Mori%2C+K">Kensaku Mori</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="2108.08537v1-abstract-short" style="display: inline;"> Federated learning (FL) for medical image segmentation becomes more challenging in multi-task settings where clients might have different categories of labels represented in their data. For example, one client might have patient data with "healthy'' pancreases only while datasets from other clients may contain cases with pancreatic tumors. The vanilla federated averaging algorithm makes it possibl… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2108.08537v1-abstract-full').style.display = 'inline'; document.getElementById('2108.08537v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2108.08537v1-abstract-full" style="display: none;"> Federated learning (FL) for medical image segmentation becomes more challenging in multi-task settings where clients might have different categories of labels represented in their data. For example, one client might have patient data with "healthy'' pancreases only while datasets from other clients may contain cases with pancreatic tumors. The vanilla federated averaging algorithm makes it possible to obtain more generalizable deep learning-based segmentation models representing the training data from multiple institutions without centralizing datasets. However, it might be sub-optimal for the aforementioned multi-task scenarios. In this paper, we investigate heterogeneous optimization methods that show improvements for the automated segmentation of pancreas and pancreatic tumors in abdominal CT images with FL settings. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2108.08537v1-abstract-full').style.display = 'none'; document.getElementById('2108.08537v1-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 August, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2021. </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 MICCAI DCL Workshop 2021</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> I.4.6 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2107.08111">arXiv:2107.08111</a> <span> [<a href="https://arxiv.org/pdf/2107.08111">pdf</a>, <a href="https://arxiv.org/format/2107.08111">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"> Federated Whole Prostate Segmentation in MRI with Personalized Neural Architectures </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Roth%2C+H+R">Holger R. Roth</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+D">Dong Yang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+W">Wenqi Li</a>, <a href="/search/cs?searchtype=author&query=Myronenko%2C+A">Andriy Myronenko</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+W">Wentao Zhu</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Z">Ziyue Xu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+X">Xiaosong Wang</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+D">Daguang Xu</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="2107.08111v1-abstract-short" style="display: inline;"> Building robust deep learning-based models requires diverse training data, ideally from several sources. However, these datasets cannot be combined easily because of patient privacy concerns or regulatory hurdles, especially if medical data is involved. Federated learning (FL) is a way to train machine learning models without the need for centralized datasets. Each FL client trains on their local… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2107.08111v1-abstract-full').style.display = 'inline'; document.getElementById('2107.08111v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2107.08111v1-abstract-full" style="display: none;"> Building robust deep learning-based models requires diverse training data, ideally from several sources. However, these datasets cannot be combined easily because of patient privacy concerns or regulatory hurdles, especially if medical data is involved. Federated learning (FL) is a way to train machine learning models without the need for centralized datasets. Each FL client trains on their local data while only sharing model parameters with a global server that aggregates the parameters from all clients. At the same time, each client's data can exhibit differences and inconsistencies due to the local variation in the patient population, imaging equipment, and acquisition protocols. Hence, the federated learned models should be able to adapt to the local particularities of a client's data. In this work, we combine FL with an AutoML technique based on local neural architecture search by training a "supernet". Furthermore, we propose an adaptation scheme to allow for personalized model architectures at each FL client's site. The proposed method is evaluated on four different datasets from 3D prostate MRI and shown to improve the local models' performance after adaptation through selecting an optimal path through the AutoML supernet. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2107.08111v1-abstract-full').style.display = 'none'; document.getElementById('2107.08111v1-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 July, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2021. </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">MICCAI 2021 accepted</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2107.05471">arXiv:2107.05471</a> <span> [<a href="https://arxiv.org/pdf/2107.05471">pdf</a>, <a href="https://arxiv.org/format/2107.05471">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"> The Power of Proxy Data and Proxy Networks for Hyper-Parameter Optimization in Medical Image Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nath%2C+V">Vishwesh Nath</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+D">Dong Yang</a>, <a href="/search/cs?searchtype=author&query=Hatamizadeh%2C+A">Ali Hatamizadeh</a>, <a href="/search/cs?searchtype=author&query=Abidin%2C+A+A">Anas A. Abidin</a>, <a href="/search/cs?searchtype=author&query=Myronenko%2C+A">Andriy Myronenko</a>, <a href="/search/cs?searchtype=author&query=Roth%2C+H">Holger Roth</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+D">Daguang Xu</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="2107.05471v1-abstract-short" style="display: inline;"> Deep learning models for medical image segmentation are primarily data-driven. Models trained with more data lead to improved performance and generalizability. However, training is a computationally expensive process because multiple hyper-parameters need to be tested to find the optimal setting for best performance. In this work, we focus on accelerating the estimation of hyper-parameters by prop… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2107.05471v1-abstract-full').style.display = 'inline'; document.getElementById('2107.05471v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2107.05471v1-abstract-full" style="display: none;"> Deep learning models for medical image segmentation are primarily data-driven. Models trained with more data lead to improved performance and generalizability. However, training is a computationally expensive process because multiple hyper-parameters need to be tested to find the optimal setting for best performance. In this work, we focus on accelerating the estimation of hyper-parameters by proposing two novel methodologies: proxy data and proxy networks. Both can be useful for estimating hyper-parameters more efficiently. We test the proposed techniques on CT and MR imaging modalities using well-known public datasets. In both cases using one dataset for building proxy data and another data source for external evaluation. For CT, the approach is tested on spleen segmentation with two datasets. The first dataset is from the medical segmentation decathlon (MSD), where the proxy data is constructed, the secondary dataset is utilized as an external validation dataset. Similarly, for MR, the approach is evaluated on prostate segmentation where the first dataset is from MSD and the second dataset is PROSTATEx. First, we show higher correlation to using full data for training when testing on the external validation set using smaller proxy data than a random selection of the proxy data. Second, we show that a high correlation exists for proxy networks when compared with the full network on validation Dice score. Third, we show that the proposed approach of utilizing a proxy network can speed up an AutoML framework for hyper-parameter search by 3.3x, and by 4.4x if proxy data and proxy network are utilized together. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2107.05471v1-abstract-full').style.display = 'none'; document.getElementById('2107.05471v1-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, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2104.10195">arXiv:2104.10195</a> <span> [<a href="https://arxiv.org/pdf/2104.10195">pdf</a>, <a href="https://arxiv.org/format/2104.10195">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"> Auto-FedAvg: Learnable Federated Averaging for Multi-Institutional Medical Image Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xia%2C+Y">Yingda Xia</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+D">Dong Yang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+W">Wenqi Li</a>, <a href="/search/cs?searchtype=author&query=Myronenko%2C+A">Andriy Myronenko</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+D">Daguang Xu</a>, <a href="/search/cs?searchtype=author&query=Obinata%2C+H">Hirofumi Obinata</a>, <a href="/search/cs?searchtype=author&query=Mori%2C+H">Hitoshi Mori</a>, <a href="/search/cs?searchtype=author&query=An%2C+P">Peng An</a>, <a href="/search/cs?searchtype=author&query=Harmon%2C+S">Stephanie Harmon</a>, <a href="/search/cs?searchtype=author&query=Turkbey%2C+E">Evrim Turkbey</a>, <a href="/search/cs?searchtype=author&query=Turkbey%2C+B">Baris Turkbey</a>, <a href="/search/cs?searchtype=author&query=Wood%2C+B">Bradford Wood</a>, <a href="/search/cs?searchtype=author&query=Patella%2C+F">Francesca Patella</a>, <a href="/search/cs?searchtype=author&query=Stellato%2C+E">Elvira Stellato</a>, <a href="/search/cs?searchtype=author&query=Carrafiello%2C+G">Gianpaolo Carrafiello</a>, <a href="/search/cs?searchtype=author&query=Ierardi%2C+A">Anna Ierardi</a>, <a href="/search/cs?searchtype=author&query=Yuille%2C+A">Alan Yuille</a>, <a href="/search/cs?searchtype=author&query=Roth%2C+H">Holger Roth</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="2104.10195v1-abstract-short" style="display: inline;"> Federated learning (FL) enables collaborative model training while preserving each participant's privacy, which is particularly beneficial to the medical field. FedAvg is a standard algorithm that uses fixed weights, often originating from the dataset sizes at each client, to aggregate the distributed learned models on a server during the FL process. However, non-identical data distribution across… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2104.10195v1-abstract-full').style.display = 'inline'; document.getElementById('2104.10195v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2104.10195v1-abstract-full" style="display: none;"> Federated learning (FL) enables collaborative model training while preserving each participant's privacy, which is particularly beneficial to the medical field. FedAvg is a standard algorithm that uses fixed weights, often originating from the dataset sizes at each client, to aggregate the distributed learned models on a server during the FL process. However, non-identical data distribution across clients, known as the non-i.i.d problem in FL, could make this assumption for setting fixed aggregation weights sub-optimal. In this work, we design a new data-driven approach, namely Auto-FedAvg, where aggregation weights are dynamically adjusted, depending on data distributions across data silos and the current training progress of the models. We disentangle the parameter set into two parts, local model parameters and global aggregation parameters, and update them iteratively with a communication-efficient algorithm. We first show the validity of our approach by outperforming state-of-the-art FL methods for image recognition on a heterogeneous data split of CIFAR-10. Furthermore, we demonstrate our algorithm's effectiveness on two multi-institutional medical image analysis tasks, i.e., COVID-19 lesion segmentation in chest CT and pancreas segmentation in abdominal CT. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2104.10195v1-abstract-full').style.display = 'none'; document.getElementById('2104.10195v1-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 April, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2103.15954">arXiv:2103.15954</a> <span> [<a href="https://arxiv.org/pdf/2103.15954">pdf</a>, <a href="https://arxiv.org/format/2103.15954">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> </div> </div> <p class="title is-5 mathjax"> DiNTS: Differentiable Neural Network Topology Search for 3D Medical Image Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=He%2C+Y">Yufan He</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+D">Dong Yang</a>, <a href="/search/cs?searchtype=author&query=Roth%2C+H">Holger Roth</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+C">Can Zhao</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+D">Daguang Xu</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="2103.15954v1-abstract-short" style="display: inline;"> Recently, neural architecture search (NAS) has been applied to automatically search high-performance networks for medical image segmentation. The NAS search space usually contains a network topology level (controlling connections among cells with different spatial scales) and a cell level (operations within each cell). Existing methods either require long searching time for large-scale 3D image da… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2103.15954v1-abstract-full').style.display = 'inline'; document.getElementById('2103.15954v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2103.15954v1-abstract-full" style="display: none;"> Recently, neural architecture search (NAS) has been applied to automatically search high-performance networks for medical image segmentation. The NAS search space usually contains a network topology level (controlling connections among cells with different spatial scales) and a cell level (operations within each cell). Existing methods either require long searching time for large-scale 3D image datasets, or are limited to pre-defined topologies (such as U-shaped or single-path). In this work, we focus on three important aspects of NAS in 3D medical image segmentation: flexible multi-path network topology, high search efficiency, and budgeted GPU memory usage. A novel differentiable search framework is proposed to support fast gradient-based search within a highly flexible network topology search space. The discretization of the searched optimal continuous model in differentiable scheme may produce a sub-optimal final discrete model (discretization gap). Therefore, we propose a topology loss to alleviate this problem. In addition, the GPU memory usage for the searched 3D model is limited with budget constraints during search. Our Differentiable Network Topology Search scheme (DiNTS) is evaluated on the Medical Segmentation Decathlon (MSD) challenge, which contains ten challenging segmentation tasks. Our method achieves the state-of-the-art performance and the top ranking on the MSD challenge leaderboard. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2103.15954v1-abstract-full').style.display = 'none'; document.getElementById('2103.15954v1-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 March, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2021. </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">CVPR2021 oral</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2103.10504">arXiv:2103.10504</a> <span> [<a href="https://arxiv.org/pdf/2103.10504">pdf</a>, <a href="https://arxiv.org/format/2103.10504">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"> UNETR: Transformers for 3D Medical Image Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hatamizadeh%2C+A">Ali Hatamizadeh</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+Y">Yucheng Tang</a>, <a href="/search/cs?searchtype=author&query=Nath%2C+V">Vishwesh Nath</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+D">Dong Yang</a>, <a href="/search/cs?searchtype=author&query=Myronenko%2C+A">Andriy Myronenko</a>, <a href="/search/cs?searchtype=author&query=Landman%2C+B">Bennett Landman</a>, <a href="/search/cs?searchtype=author&query=Roth%2C+H">Holger Roth</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+D">Daguang Xu</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="2103.10504v3-abstract-short" style="display: inline;"> Fully Convolutional Neural Networks (FCNNs) with contracting and expanding paths have shown prominence for the majority of medical image segmentation applications since the past decade. In FCNNs, the encoder plays an integral role by learning both global and local features and contextual representations which can be utilized for semantic output prediction by the decoder. Despite their success, the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2103.10504v3-abstract-full').style.display = 'inline'; document.getElementById('2103.10504v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2103.10504v3-abstract-full" style="display: none;"> Fully Convolutional Neural Networks (FCNNs) with contracting and expanding paths have shown prominence for the majority of medical image segmentation applications since the past decade. In FCNNs, the encoder plays an integral role by learning both global and local features and contextual representations which can be utilized for semantic output prediction by the decoder. Despite their success, the locality of convolutional layers in FCNNs, limits the capability of learning long-range spatial dependencies. Inspired by the recent success of transformers for Natural Language Processing (NLP) in long-range sequence learning, we reformulate the task of volumetric (3D) medical image segmentation as a sequence-to-sequence prediction problem. We introduce a novel architecture, dubbed as UNEt TRansformers (UNETR), that utilizes a transformer as the encoder to learn sequence representations of the input volume and effectively capture the global multi-scale information, while also following the successful "U-shaped" network design for the encoder and decoder. The transformer encoder is directly connected to a decoder via skip connections at different resolutions to compute the final semantic segmentation output. We have validated the performance of our method on the Multi Atlas Labeling Beyond The Cranial Vault (BTCV) dataset for multi-organ segmentation and the Medical Segmentation Decathlon (MSD) dataset for brain tumor and spleen segmentation tasks. Our benchmarks demonstrate new state-of-the-art performance on the BTCV leaderboard. Code: https://monai.io/research/unetr <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2103.10504v3-abstract-full').style.display = 'none'; document.getElementById('2103.10504v3-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 October, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 18 March, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2021. </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 IEEE Winter Conference on Applications of Computer Vision (WACV) 2022</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2101.02323">arXiv:2101.02323</a> <span> [<a href="https://arxiv.org/pdf/2101.02323">pdf</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> </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/TMI.2020.3048055">10.1109/TMI.2020.3048055 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Diminishing Uncertainty within the Training Pool: Active Learning for Medical Image Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nath%2C+V">Vishwesh Nath</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+D">Dong Yang</a>, <a href="/search/cs?searchtype=author&query=Landman%2C+B+A">Bennett A. Landman</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+D">Daguang Xu</a>, <a href="/search/cs?searchtype=author&query=Roth%2C+H+R">Holger R. Roth</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="2101.02323v1-abstract-short" style="display: inline;"> Active learning is a unique abstraction of machine learning techniques where the model/algorithm could guide users for annotation of a set of data points that would be beneficial to the model, unlike passive machine learning. The primary advantage being that active learning frameworks select data points that can accelerate the learning process of a model and can reduce the amount of data needed to… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2101.02323v1-abstract-full').style.display = 'inline'; document.getElementById('2101.02323v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2101.02323v1-abstract-full" style="display: none;"> Active learning is a unique abstraction of machine learning techniques where the model/algorithm could guide users for annotation of a set of data points that would be beneficial to the model, unlike passive machine learning. The primary advantage being that active learning frameworks select data points that can accelerate the learning process of a model and can reduce the amount of data needed to achieve full accuracy as compared to a model trained on a randomly acquired data set. Multiple frameworks for active learning combined with deep learning have been proposed, and the majority of them are dedicated to classification tasks. Herein, we explore active learning for the task of segmentation of medical imaging data sets. We investigate our proposed framework using two datasets: 1.) MRI scans of the hippocampus, 2.) CT scans of pancreas and tumors. This work presents a query-by-committee approach for active learning where a joint optimizer is used for the committee. At the same time, we propose three new strategies for active learning: 1.) increasing frequency of uncertain data to bias the training data set; 2.) Using mutual information among the input images as a regularizer for acquisition to ensure diversity in the training dataset; 3.) adaptation of Dice log-likelihood for Stein variational gradient descent (SVGD). The results indicate an improvement in terms of data reduction by achieving full accuracy while only using 22.69 % and 48.85 % of the available data for each dataset, respectively. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2101.02323v1-abstract-full').style.display = 'none'; document.getElementById('2101.02323v1-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, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2021. </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">19 pages, 13 figures, Transactions of Medical Imaging</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> IEEE Transactions on Medical Imaging, 2020 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2011.11750">arXiv:2011.11750</a> <span> [<a href="https://arxiv.org/pdf/2011.11750">pdf</a>, <a href="https://arxiv.org/format/2011.11750">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"> Federated Semi-Supervised Learning for COVID Region Segmentation in Chest CT using Multi-National Data from China, Italy, Japan </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+D">Dong Yang</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Z">Ziyue Xu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+W">Wenqi Li</a>, <a href="/search/cs?searchtype=author&query=Myronenko%2C+A">Andriy Myronenko</a>, <a href="/search/cs?searchtype=author&query=Roth%2C+H+R">Holger R. Roth</a>, <a href="/search/cs?searchtype=author&query=Harmon%2C+S">Stephanie Harmon</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+S">Sheng Xu</a>, <a href="/search/cs?searchtype=author&query=Turkbey%2C+B">Baris Turkbey</a>, <a href="/search/cs?searchtype=author&query=Turkbey%2C+E">Evrim Turkbey</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+X">Xiaosong Wang</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+W">Wentao Zhu</a>, <a href="/search/cs?searchtype=author&query=Carrafiello%2C+G">Gianpaolo Carrafiello</a>, <a href="/search/cs?searchtype=author&query=Patella%2C+F">Francesca Patella</a>, <a href="/search/cs?searchtype=author&query=Cariati%2C+M">Maurizio Cariati</a>, <a href="/search/cs?searchtype=author&query=Obinata%2C+H">Hirofumi Obinata</a>, <a href="/search/cs?searchtype=author&query=Mori%2C+H">Hitoshi Mori</a>, <a href="/search/cs?searchtype=author&query=Tamura%2C+K">Kaku Tamura</a>, <a href="/search/cs?searchtype=author&query=An%2C+P">Peng An</a>, <a href="/search/cs?searchtype=author&query=Wood%2C+B+J">Bradford J. Wood</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+D">Daguang Xu</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="2011.11750v1-abstract-short" style="display: inline;"> The recent outbreak of COVID-19 has led to urgent needs for reliable diagnosis and management of SARS-CoV-2 infection. As a complimentary tool, chest CT has been shown to be able to reveal visual patterns characteristic for COVID-19, which has definite value at several stages during the disease course. To facilitate CT analysis, recent efforts have focused on computer-aided characterization and di… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2011.11750v1-abstract-full').style.display = 'inline'; document.getElementById('2011.11750v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2011.11750v1-abstract-full" style="display: none;"> The recent outbreak of COVID-19 has led to urgent needs for reliable diagnosis and management of SARS-CoV-2 infection. As a complimentary tool, chest CT has been shown to be able to reveal visual patterns characteristic for COVID-19, which has definite value at several stages during the disease course. To facilitate CT analysis, recent efforts have focused on computer-aided characterization and diagnosis, which has shown promising results. However, domain shift of data across clinical data centers poses a serious challenge when deploying learning-based models. In this work, we attempt to find a solution for this challenge via federated and semi-supervised learning. A multi-national database consisting of 1704 scans from three countries is adopted to study the performance gap, when training a model with one dataset and applying it to another. Expert radiologists manually delineated 945 scans for COVID-19 findings. In handling the variability in both the data and annotations, a novel federated semi-supervised learning technique is proposed to fully utilize all available data (with or without annotations). Federated learning avoids the need for sensitive data-sharing, which makes it favorable for institutions and nations with strict regulatory policy on data privacy. Moreover, semi-supervision potentially reduces the annotation burden under a distributed setting. The proposed framework is shown to be effective compared to fully supervised scenarios with conventional data sharing instead of model weight sharing. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2011.11750v1-abstract-full').style.display = 'none'; document.getElementById('2011.11750v1-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 November, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2020. </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 with minor revision to Medical Image Analysis</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2009.13148">arXiv:2009.13148</a> <span> [<a href="https://arxiv.org/pdf/2009.13148">pdf</a>, <a href="https://arxiv.org/format/2009.13148">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"> Automated Pancreas Segmentation Using Multi-institutional Collaborative Deep Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+P">Pochuan Wang</a>, <a href="/search/cs?searchtype=author&query=Shen%2C+C">Chen Shen</a>, <a href="/search/cs?searchtype=author&query=Roth%2C+H+R">Holger R. Roth</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+D">Dong Yang</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+D">Daguang Xu</a>, <a href="/search/cs?searchtype=author&query=Oda%2C+M">Masahiro Oda</a>, <a href="/search/cs?searchtype=author&query=Misawa%2C+K">Kazunari Misawa</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+P">Po-Ting Chen</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+K">Kao-Lang Liu</a>, <a href="/search/cs?searchtype=author&query=Liao%2C+W">Wei-Chih Liao</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+W">Weichung Wang</a>, <a href="/search/cs?searchtype=author&query=Mori%2C+K">Kensaku Mori</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="2009.13148v1-abstract-short" style="display: inline;"> The performance of deep learning-based methods strongly relies on the number of datasets used for training. Many efforts have been made to increase the data in the medical image analysis field. However, unlike photography images, it is hard to generate centralized databases to collect medical images because of numerous technical, legal, and privacy issues. In this work, we study the use of federat… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2009.13148v1-abstract-full').style.display = 'inline'; document.getElementById('2009.13148v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2009.13148v1-abstract-full" style="display: none;"> The performance of deep learning-based methods strongly relies on the number of datasets used for training. Many efforts have been made to increase the data in the medical image analysis field. However, unlike photography images, it is hard to generate centralized databases to collect medical images because of numerous technical, legal, and privacy issues. In this work, we study the use of federated learning between two institutions in a real-world setting to collaboratively train a model without sharing the raw data across national boundaries. We quantitatively compare the segmentation models obtained with federated learning and local training alone. Our experimental results show that federated learning models have higher generalizability than standalone training. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2009.13148v1-abstract-full').style.display = 'none'; document.getElementById('2009.13148v1-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> 28 September, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2020. </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 MICCAI DCL Workshop 2020</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2009.12437">arXiv:2009.12437</a> <span> [<a href="https://arxiv.org/pdf/2009.12437">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> <p class="title is-5 mathjax"> Democratizing Artificial Intelligence in Healthcare: A Study of Model Development Across Two Institutions Incorporating Transfer Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gupta1%2C+V">Vikash Gupta1</a>, <a href="/search/cs?searchtype=author&query=Roth%2C+H">Holger Roth</a>, <a href="/search/cs?searchtype=author&query=Buch3%2C+V">Varun Buch3</a>, <a href="/search/cs?searchtype=author&query=Rockenbach%2C+M+A+B+C">Marcio A. B. C. Rockenbach</a>, <a href="/search/cs?searchtype=author&query=White%2C+R+D">Richard D White</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+D">Dong Yang</a>, <a href="/search/cs?searchtype=author&query=Laur%2C+O">Olga Laur</a>, <a href="/search/cs?searchtype=author&query=Ghoshhajra%2C+B">Brian Ghoshhajra</a>, <a href="/search/cs?searchtype=author&query=Dayan%2C+I">Ittai Dayan</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+D">Daguang Xu</a>, <a href="/search/cs?searchtype=author&query=Flores%2C+M+G">Mona G. Flores</a>, <a href="/search/cs?searchtype=author&query=Erdal%2C+B+S">Barbaros Selnur Erdal</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="2009.12437v1-abstract-short" style="display: inline;"> The training of deep learning models typically requires extensive data, which are not readily available as large well-curated medical-image datasets for development of artificial intelligence (AI) models applied in Radiology. Recognizing the potential for transfer learning (TL) to allow a fully trained model from one institution to be fine-tuned by another institution using a much small local data… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2009.12437v1-abstract-full').style.display = 'inline'; document.getElementById('2009.12437v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2009.12437v1-abstract-full" style="display: none;"> The training of deep learning models typically requires extensive data, which are not readily available as large well-curated medical-image datasets for development of artificial intelligence (AI) models applied in Radiology. Recognizing the potential for transfer learning (TL) to allow a fully trained model from one institution to be fine-tuned by another institution using a much small local dataset, this report describes the challenges, methodology, and benefits of TL within the context of developing an AI model for a basic use-case, segmentation of Left Ventricular Myocardium (LVM) on images from 4-dimensional coronary computed tomography angiography. Ultimately, our results from comparisons of LVM segmentation predicted by a model locally trained using random initialization, versus one training-enhanced by TL, showed that a use-case model initiated by TL can be developed with sparse labels with acceptable performance. This process reduces the time required to build a new model in the clinical environment at a different institution. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2009.12437v1-abstract-full').style.display = 'none'; document.getElementById('2009.12437v1-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 September, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2020. </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, pre-print</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> I.2.10 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2009.11988">arXiv:2009.11988</a> <span> [<a href="https://arxiv.org/pdf/2009.11988">pdf</a>, <a href="https://arxiv.org/format/2009.11988">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> </div> </div> <p class="title is-5 mathjax"> Going to Extremes: Weakly Supervised Medical Image Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Roth%2C+H+R">Holger R Roth</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+D">Dong Yang</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Z">Ziyue Xu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+X">Xiaosong Wang</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+D">Daguang Xu</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="2009.11988v1-abstract-short" style="display: inline;"> Medical image annotation is a major hurdle for developing precise and robust machine learning models. Annotation is expensive, time-consuming, and often requires expert knowledge, particularly in the medical field. Here, we suggest using minimal user interaction in the form of extreme point clicks to train a segmentation model which, in effect, can be used to speed up medical image annotation. An… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2009.11988v1-abstract-full').style.display = 'inline'; document.getElementById('2009.11988v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2009.11988v1-abstract-full" style="display: none;"> Medical image annotation is a major hurdle for developing precise and robust machine learning models. Annotation is expensive, time-consuming, and often requires expert knowledge, particularly in the medical field. Here, we suggest using minimal user interaction in the form of extreme point clicks to train a segmentation model which, in effect, can be used to speed up medical image annotation. An initial segmentation is generated based on the extreme points utilizing the random walker algorithm. This initial segmentation is then used as a noisy supervision signal to train a fully convolutional network that can segment the organ of interest, based on the provided user clicks. Through experimentation on several medical imaging datasets, we show that the predictions of the network can be refined using several rounds of training with the prediction from the same weakly annotated data. Further improvements are shown utilizing the clicked points within a custom-designed loss and attention mechanism. Our approach has the potential to speed up the process of generating new training datasets for the development of new machine learning and deep learning-based models for, but not exclusively, medical image analysis. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2009.11988v1-abstract-full').style.display = 'none'; document.getElementById('2009.11988v1-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 September, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2020. </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">13 pages, 6 figures, 1 table</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2009.10325">arXiv:2009.10325</a> <span> [<a href="https://arxiv.org/pdf/2009.10325">pdf</a>, <a href="https://arxiv.org/format/2009.10325">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> </div> </div> <p class="title is-5 mathjax"> Learning Image Labels On-the-fly for Training Robust Classification Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+X">Xiaosong Wang</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Z">Ziyue Xu</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+D">Dong Yang</a>, <a href="/search/cs?searchtype=author&query=Tam%2C+L">Leo Tam</a>, <a href="/search/cs?searchtype=author&query=Roth%2C+H">Holger Roth</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+D">Daguang Xu</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="2009.10325v2-abstract-short" style="display: inline;"> Current deep learning paradigms largely benefit from the tremendous amount of annotated data. However, the quality of the annotations often varies among labelers. Multi-observer studies have been conducted to study these annotation variances (by labeling the same data for multiple times) and its effects on critical applications like medical image analysis. This process indeed adds an extra burden… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2009.10325v2-abstract-full').style.display = 'inline'; document.getElementById('2009.10325v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2009.10325v2-abstract-full" style="display: none;"> Current deep learning paradigms largely benefit from the tremendous amount of annotated data. However, the quality of the annotations often varies among labelers. Multi-observer studies have been conducted to study these annotation variances (by labeling the same data for multiple times) and its effects on critical applications like medical image analysis. This process indeed adds an extra burden to the already tedious annotation work that usually requires professional training and expertise in the specific domains. On the other hand, automated annotation methods based on NLP algorithms have recently shown promise as a reasonable alternative, relying on the existing diagnostic reports of those images that are widely available in the clinical system. Compared to human labelers, different algorithms provide labels with varying qualities that are even noisier. In this paper, we show how noisy annotations (e.g., from different algorithm-based labelers) can be utilized together and mutually benefit the learning of classification tasks. Specifically, the concept of attention-on-label is introduced to sample better label sets on-the-fly as the training data. A meta-training based label-sampling module is designed to attend the labels that benefit the model learning the most through additional back-propagation processes. We apply the attention-on-label scheme on the classification task of a synthetic noisy CIFAR-10 dataset to prove the concept, and then demonstrate superior results (3-5% increase on average in multiple disease classification AUCs) on the chest x-ray images from a hospital-scale dataset (MIMIC-CXR) and hand-labeled dataset (OpenI) in comparison to regular training paradigms. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2009.10325v2-abstract-full').style.display = 'none'; document.getElementById('2009.10325v2-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 October, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 22 September, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2020. </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">v2: Minor Corrections</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2009.01871">arXiv:2009.01871</a> <span> [<a href="https://arxiv.org/pdf/2009.01871">pdf</a>, <a href="https://arxiv.org/format/2009.01871">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/10.1007/978-3-030-60548-3_18">10.1007/978-3-030-60548-3_18 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Federated Learning for Breast Density Classification: A Real-World Implementation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Roth%2C+H+R">Holger R. Roth</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+K">Ken Chang</a>, <a href="/search/cs?searchtype=author&query=Singh%2C+P">Praveer Singh</a>, <a href="/search/cs?searchtype=author&query=Neumark%2C+N">Nir Neumark</a>, <a href="/search/cs?searchtype=author&query=Li%2C+W">Wenqi Li</a>, <a href="/search/cs?searchtype=author&query=Gupta%2C+V">Vikash Gupta</a>, <a href="/search/cs?searchtype=author&query=Gupta%2C+S">Sharut Gupta</a>, <a href="/search/cs?searchtype=author&query=Qu%2C+L">Liangqiong Qu</a>, <a href="/search/cs?searchtype=author&query=Ihsani%2C+A">Alvin Ihsani</a>, <a href="/search/cs?searchtype=author&query=Bizzo%2C+B+C">Bernardo C. Bizzo</a>, <a href="/search/cs?searchtype=author&query=Wen%2C+Y">Yuhong Wen</a>, <a href="/search/cs?searchtype=author&query=Buch%2C+V">Varun Buch</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+M">Meesam Shah</a>, <a href="/search/cs?searchtype=author&query=Kitamura%2C+F">Felipe Kitamura</a>, <a href="/search/cs?searchtype=author&query=Mendon%C3%A7a%2C+M">Matheus Mendon莽a</a>, <a href="/search/cs?searchtype=author&query=Lavor%2C+V">Vitor Lavor</a>, <a href="/search/cs?searchtype=author&query=Harouni%2C+A">Ahmed Harouni</a>, <a href="/search/cs?searchtype=author&query=Compas%2C+C">Colin Compas</a>, <a href="/search/cs?searchtype=author&query=Tetreault%2C+J">Jesse Tetreault</a>, <a href="/search/cs?searchtype=author&query=Dogra%2C+P">Prerna Dogra</a>, <a href="/search/cs?searchtype=author&query=Cheng%2C+Y">Yan Cheng</a>, <a href="/search/cs?searchtype=author&query=Erdal%2C+S">Selnur Erdal</a>, <a href="/search/cs?searchtype=author&query=White%2C+R">Richard White</a>, <a href="/search/cs?searchtype=author&query=Hashemian%2C+B">Behrooz Hashemian</a>, <a href="/search/cs?searchtype=author&query=Schultz%2C+T">Thomas Schultz</a> , et al. (18 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="2009.01871v3-abstract-short" style="display: inline;"> Building robust deep learning-based models requires large quantities of diverse training data. In this study, we investigate the use of federated learning (FL) to build medical imaging classification models in a real-world collaborative setting. Seven clinical institutions from across the world joined this FL effort to train a model for breast density classification based on Breast Imaging, Report… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2009.01871v3-abstract-full').style.display = 'inline'; document.getElementById('2009.01871v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2009.01871v3-abstract-full" style="display: none;"> Building robust deep learning-based models requires large quantities of diverse training data. In this study, we investigate the use of federated learning (FL) to build medical imaging classification models in a real-world collaborative setting. Seven clinical institutions from across the world joined this FL effort to train a model for breast density classification based on Breast Imaging, Reporting & Data System (BI-RADS). We show that despite substantial differences among the datasets from all sites (mammography system, class distribution, and data set size) and without centralizing data, we can successfully train AI models in federation. The results show that models trained using FL perform 6.3% on average better than their counterparts trained on an institute's local data alone. Furthermore, we show a 45.8% relative improvement in the models' generalizability when evaluated on the other participating sites' testing data. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2009.01871v3-abstract-full').style.display = 'none'; document.getElementById('2009.01871v3-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 October, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 3 September, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2020. </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 at the 1st MICCAI Workshop on "Distributed And Collaborative Learning"; add citation to Fig. 1 & 2 and update Fig. 5; fix typo in affiliations</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> In: Albarqouni S. et al. (eds) Domain Adaptation and Representation Transfer, and Distributed and Collaborative Learning. DART 2020, DCL 2020. Lecture Notes in Computer Science, vol 12444. Springer, Cham </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2006.16806">arXiv:2006.16806</a> <span> [<a href="https://arxiv.org/pdf/2006.16806">pdf</a>, <a href="https://arxiv.org/format/2006.16806">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> </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/10.1016/j.media.2020.101766">10.1016/j.media.2020.101766 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Uncertainty-aware multi-view co-training for semi-supervised medical image segmentation and domain adaptation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xia%2C+Y">Yingda Xia</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+D">Dong Yang</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+Z">Zhiding Yu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+F">Fengze Liu</a>, <a href="/search/cs?searchtype=author&query=Cai%2C+J">Jinzheng Cai</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+L">Lequan Yu</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+Z">Zhuotun Zhu</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+D">Daguang Xu</a>, <a href="/search/cs?searchtype=author&query=Yuille%2C+A">Alan Yuille</a>, <a href="/search/cs?searchtype=author&query=Roth%2C+H">Holger Roth</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="2006.16806v1-abstract-short" style="display: inline;"> Although having achieved great success in medical image segmentation, deep learning-based approaches usually require large amounts of well-annotated data, which can be extremely expensive in the field of medical image analysis. Unlabeled data, on the other hand, is much easier to acquire. Semi-supervised learning and unsupervised domain adaptation both take the advantage of unlabeled data, and the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2006.16806v1-abstract-full').style.display = 'inline'; document.getElementById('2006.16806v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2006.16806v1-abstract-full" style="display: none;"> Although having achieved great success in medical image segmentation, deep learning-based approaches usually require large amounts of well-annotated data, which can be extremely expensive in the field of medical image analysis. Unlabeled data, on the other hand, is much easier to acquire. Semi-supervised learning and unsupervised domain adaptation both take the advantage of unlabeled data, and they are closely related to each other. In this paper, we propose uncertainty-aware multi-view co-training (UMCT), a unified framework that addresses these two tasks for volumetric medical image segmentation. Our framework is capable of efficiently utilizing unlabeled data for better performance. We firstly rotate and permute the 3D volumes into multiple views and train a 3D deep network on each view. We then apply co-training by enforcing multi-view consistency on unlabeled data, where an uncertainty estimation of each view is utilized to achieve accurate labeling. Experiments on the NIH pancreas segmentation dataset and a multi-organ segmentation dataset show state-of-the-art performance of the proposed framework on semi-supervised medical image segmentation. Under unsupervised domain adaptation settings, we validate the effectiveness of this work by adapting our multi-organ segmentation model to two pathological organs from the Medical Segmentation Decathlon Datasets. Additionally, we show that our UMCT-DA model can even effectively handle the challenging situation where labeled source data is inaccessible, demonstrating strong potentials for real-world applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2006.16806v1-abstract-full').style.display = 'none'; document.getElementById('2006.16806v1-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> 28 June, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2020. </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">19 pages, 6 figures, to appear in Medical Image Analysis. This article is an extension of the conference paper arXiv:1811.12506</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Medical Image Analysis, 2020 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2006.12575">arXiv:2006.12575</a> <span> [<a href="https://arxiv.org/pdf/2006.12575">pdf</a>, <a href="https://arxiv.org/format/2006.12575">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="Distributed, Parallel, and Cluster Computing">cs.DC</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="Neural and Evolutionary Computing">cs.NE</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"> LAMP: Large Deep Nets with Automated Model Parallelism for Image Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhu%2C+W">Wentao Zhu</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+C">Can Zhao</a>, <a href="/search/cs?searchtype=author&query=Li%2C+W">Wenqi Li</a>, <a href="/search/cs?searchtype=author&query=Roth%2C+H">Holger Roth</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Z">Ziyue Xu</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+D">Daguang Xu</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="2006.12575v3-abstract-short" style="display: inline;"> Deep Learning (DL) models are becoming larger, because the increase in model size might offer significant accuracy gain. To enable the training of large deep networks, data parallelism and model parallelism are two well-known approaches for parallel training. However, data parallelism does not help reduce memory footprint per device. In this work, we introduce Large deep 3D ConvNets with Automated… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2006.12575v3-abstract-full').style.display = 'inline'; document.getElementById('2006.12575v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2006.12575v3-abstract-full" style="display: none;"> Deep Learning (DL) models are becoming larger, because the increase in model size might offer significant accuracy gain. To enable the training of large deep networks, data parallelism and model parallelism are two well-known approaches for parallel training. However, data parallelism does not help reduce memory footprint per device. In this work, we introduce Large deep 3D ConvNets with Automated Model Parallelism (LAMP) and investigate the impact of both input's and deep 3D ConvNets' size on segmentation accuracy. Through automated model parallelism, it is feasible to train large deep 3D ConvNets with a large input patch, even the whole image. Extensive experiments demonstrate that, facilitated by the automated model parallelism, the segmentation accuracy can be improved through increasing model size and input context size, and large input yields significant inference speedup compared with sliding window of small patches in the inference. Code is available\footnote{https://monai.io/research/lamp-automated-model-parallelism}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2006.12575v3-abstract-full').style.display = 'none'; document.getElementById('2006.12575v3-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 September, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 22 June, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2020. </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">MICCAI 2020 Early Accepted paper. Code is available\footnote{https://monai.io/research/lamp-automated-model-parallelism}</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2006.12434">arXiv:2006.12434</a> <span> [<a href="https://arxiv.org/pdf/2006.12434">pdf</a>, <a href="https://arxiv.org/format/2006.12434">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"> Cardiac Segmentation on Late Gadolinium Enhancement MRI: A Benchmark Study from Multi-Sequence Cardiac MR Segmentation Challenge </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhuang%2C+X">Xiahai Zhuang</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+J">Jiahang Xu</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+X">Xinzhe Luo</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+C">Chen Chen</a>, <a href="/search/cs?searchtype=author&query=Ouyang%2C+C">Cheng Ouyang</a>, <a href="/search/cs?searchtype=author&query=Rueckert%2C+D">Daniel Rueckert</a>, <a href="/search/cs?searchtype=author&query=Campello%2C+V+M">Victor M. Campello</a>, <a href="/search/cs?searchtype=author&query=Lekadir%2C+K">Karim Lekadir</a>, <a href="/search/cs?searchtype=author&query=Vesal%2C+S">Sulaiman Vesal</a>, <a href="/search/cs?searchtype=author&query=RaviKumar%2C+N">Nishant RaviKumar</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yashu Liu</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+G">Gongning Luo</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+J">Jingkun Chen</a>, <a href="/search/cs?searchtype=author&query=Li%2C+H">Hongwei Li</a>, <a href="/search/cs?searchtype=author&query=Ly%2C+B">Buntheng Ly</a>, <a href="/search/cs?searchtype=author&query=Sermesant%2C+M">Maxime Sermesant</a>, <a href="/search/cs?searchtype=author&query=Roth%2C+H">Holger Roth</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+W">Wentao Zhu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jiexiang Wang</a>, <a href="/search/cs?searchtype=author&query=Ding%2C+X">Xinghao Ding</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+X">Xinyue Wang</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+S">Sen Yang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+L">Lei 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="2006.12434v2-abstract-short" style="display: inline;"> Accurate computing, analysis and modeling of the ventricles and myocardium from medical images are important, especially in the diagnosis and treatment management for patients suffering from myocardial infarction (MI). Late gadolinium enhancement (LGE) cardiac magnetic resonance (CMR) provides an important protocol to visualize MI. However, automated segmentation of LGE CMR is still challenging, d… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2006.12434v2-abstract-full').style.display = 'inline'; document.getElementById('2006.12434v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2006.12434v2-abstract-full" style="display: none;"> Accurate computing, analysis and modeling of the ventricles and myocardium from medical images are important, especially in the diagnosis and treatment management for patients suffering from myocardial infarction (MI). Late gadolinium enhancement (LGE) cardiac magnetic resonance (CMR) provides an important protocol to visualize MI. However, automated segmentation of LGE CMR is still challenging, due to the indistinguishable boundaries, heterogeneous intensity distribution and complex enhancement patterns of pathological myocardium from LGE CMR. Furthermore, compared with the other sequences LGE CMR images with gold standard labels are particularly limited, which represents another obstacle for developing novel algorithms for automatic segmentation of LGE CMR. This paper presents the selective results from the Multi-Sequence Cardiac MR (MS-CMR) Segmentation challenge, in conjunction with MICCAI 2019. The challenge offered a data set of paired MS-CMR images, including auxiliary CMR sequences as well as LGE CMR, from 45 patients who underwent cardiomyopathy. It was aimed to develop new algorithms, as well as benchmark existing ones for LGE CMR segmentation and compare them objectively. In addition, the paired MS-CMR images could enable algorithms to combine the complementary information from the other sequences for the segmentation of LGE CMR. Nine representative works were selected for evaluation and comparisons, among which three methods are unsupervised methods and the other six are supervised. The results showed that the average performance of the nine methods was comparable to the inter-observer variations. The success of these methods was mainly attributed to the inclusion of the auxiliary sequences from the MS-CMR images, which provide important label information for the training of deep neural networks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2006.12434v2-abstract-full').style.display = 'none'; document.getElementById('2006.12434v2-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 July, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 22 June, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2020. </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">14 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2006.05847">arXiv:2006.05847</a> <span> [<a href="https://arxiv.org/pdf/2006.05847">pdf</a>, <a href="https://arxiv.org/format/2006.05847">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> </div> </div> <p class="title is-5 mathjax"> Searching Learning Strategy with Reinforcement Learning for 3D Medical Image Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+D">Dong Yang</a>, <a href="/search/cs?searchtype=author&query=Roth%2C+H">Holger Roth</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Z">Ziyue Xu</a>, <a href="/search/cs?searchtype=author&query=Milletari%2C+F">Fausto Milletari</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+L">Ling Zhang</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+D">Daguang Xu</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="2006.05847v1-abstract-short" style="display: inline;"> Deep neural network (DNN) based approaches have been widely investigated and deployed in medical image analysis. For example, fully convolutional neural networks (FCN) achieve the state-of-the-art performance in several applications of 2D/3D medical image segmentation. Even the baseline neural network models (U-Net, V-Net, etc.) have been proven to be very effective and efficient when the training… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2006.05847v1-abstract-full').style.display = 'inline'; document.getElementById('2006.05847v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2006.05847v1-abstract-full" style="display: none;"> Deep neural network (DNN) based approaches have been widely investigated and deployed in medical image analysis. For example, fully convolutional neural networks (FCN) achieve the state-of-the-art performance in several applications of 2D/3D medical image segmentation. Even the baseline neural network models (U-Net, V-Net, etc.) have been proven to be very effective and efficient when the training process is set up properly. Nevertheless, to fully exploit the potentials of neural networks, we propose an automated searching approach for the optimal training strategy with reinforcement learning. The proposed approach can be utilized for tuning hyper-parameters, and selecting necessary data augmentation with certain probabilities. The proposed approach is validated on several tasks of 3D medical image segmentation. The performance of the baseline model is boosted after searching, and it can achieve comparable accuracy to other manually-tuned state-of-the-art segmentation approaches. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2006.05847v1-abstract-full').style.display = 'none'; document.getElementById('2006.05847v1-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 June, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2020. </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">9 pages, 1 figures</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Published at MICCAI 2019 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2005.14355">arXiv:2005.14355</a> <span> [<a href="https://arxiv.org/pdf/2005.14355">pdf</a>, <a href="https://arxiv.org/format/2005.14355">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 Foreground Boundaries for Medical Image Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+D">Dong Yang</a>, <a href="/search/cs?searchtype=author&query=Roth%2C+H">Holger Roth</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+X">Xiaosong Wang</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Z">Ziyue Xu</a>, <a href="/search/cs?searchtype=author&query=Myronenko%2C+A">Andriy Myronenko</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+D">Daguang Xu</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="2005.14355v1-abstract-short" style="display: inline;"> Object segmentation plays an important role in the modern medical image analysis, which benefits clinical study, disease diagnosis, and surgery planning. Given the various modalities of medical images, the automated or semi-automated segmentation approaches have been used to identify and parse organs, bones, tumors, and other regions-of-interest (ROI). However, these contemporary segmentation appr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2005.14355v1-abstract-full').style.display = 'inline'; document.getElementById('2005.14355v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2005.14355v1-abstract-full" style="display: none;"> Object segmentation plays an important role in the modern medical image analysis, which benefits clinical study, disease diagnosis, and surgery planning. Given the various modalities of medical images, the automated or semi-automated segmentation approaches have been used to identify and parse organs, bones, tumors, and other regions-of-interest (ROI). However, these contemporary segmentation approaches tend to fail to predict the boundary areas of ROI, because of the fuzzy appearance contrast caused during the imaging procedure. To further improve the segmentation quality of boundary areas, we propose a boundary enhancement loss to enforce additional constraints on optimizing machine learning models. The proposed loss function is light-weighted and easy to implement without any pre- or post-processing. Our experimental results validate that our loss function are better than, or at least comparable to, other state-of-the-art loss functions in terms of segmentation accuracy. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2005.14355v1-abstract-full').style.display = 'none'; document.getElementById('2005.14355v1-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> 28 May, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2020. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Report number:</span> MIDL/2020/ExtendedAbstract/PAlQnIVKLY </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2004.13629">arXiv:2004.13629</a> <span> [<a href="https://arxiv.org/pdf/2004.13629">pdf</a>, <a href="https://arxiv.org/ps/2004.13629">ps</a>, <a href="https://arxiv.org/format/2004.13629">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> </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/10.1007/978-3-030-00937-3_21">10.1007/978-3-030-00937-3_21 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Colon Shape Estimation Method for Colonoscope Tracking using Recurrent Neural Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Oda%2C+M">Masahiro Oda</a>, <a href="/search/cs?searchtype=author&query=Roth%2C+H+R">Holger R. Roth</a>, <a href="/search/cs?searchtype=author&query=Kitasaka%2C+T">Takayuki Kitasaka</a>, <a href="/search/cs?searchtype=author&query=Furukawa%2C+K">Kazuhiro Furukawa</a>, <a href="/search/cs?searchtype=author&query=Miyahara%2C+R">Ryoji Miyahara</a>, <a href="/search/cs?searchtype=author&query=Hirooka%2C+Y">Yoshiki Hirooka</a>, <a href="/search/cs?searchtype=author&query=Goto%2C+H">Hidemi Goto</a>, <a href="/search/cs?searchtype=author&query=Navab%2C+N">Nassir Navab</a>, <a href="/search/cs?searchtype=author&query=Mori%2C+K">Kensaku Mori</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="2004.13629v1-abstract-short" style="display: inline;"> We propose an estimation method using a recurrent neural network (RNN) of the colon's shape where deformation was occurred by a colonoscope insertion. Colonoscope tracking or a navigation system that navigates physician to polyp positions is needed to reduce such complications as colon perforation. Previous tracking methods caused large tracking errors at the transverse and sigmoid colons because… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2004.13629v1-abstract-full').style.display = 'inline'; document.getElementById('2004.13629v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2004.13629v1-abstract-full" style="display: none;"> We propose an estimation method using a recurrent neural network (RNN) of the colon's shape where deformation was occurred by a colonoscope insertion. Colonoscope tracking or a navigation system that navigates physician to polyp positions is needed to reduce such complications as colon perforation. Previous tracking methods caused large tracking errors at the transverse and sigmoid colons because these areas largely deform during colonoscope insertion. Colon deformation should be taken into account in tracking processes. We propose a colon deformation estimation method using RNN and obtain the colonoscope shape from electromagnetic sensors during its insertion into the colon. This method obtains positional, directional, and an insertion length from the colonoscope shape. From its shape, we also calculate the relative features that represent the positional and directional relationships between two points on a colonoscope. Long short-term memory is used to estimate the current colon shape from the past transition of the features of the colonoscope shape. We performed colon shape estimation in a phantom study and correctly estimated the colon shapes during colonoscope insertion with 12.39 (mm) estimation error. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2004.13629v1-abstract-full').style.display = 'none'; document.getElementById('2004.13629v1-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 April, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2020. </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 paper as a poster presentation at MICCAI 2018 (International Conference on Medical Image Computing and Computer-Assisted Intervention), Granada, Spain</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Published in Proceedings of MICCAI 2018, LNCS 11073, pp 176-184 </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=Roth%2C+H&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Roth%2C+H&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Roth%2C+H&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </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