ResNet for Histopathologic Cancer Detection, the Deeper, the Better? | Journal of Data Science and Intelligent Systems

<!DOCTYPE html> <html lang="en" xml:lang="en"> <head> <meta charset="utf-8"> <meta name="viewport" content="width=device-width, initial-scale=1.0"> <title> ResNet for Histopathologic Cancer Detection, the Deeper, the Better? | Journal of Data Science and Intelligent Systems </title> <link rel="icon" href="https://ojs.bonviewpress.com/public/journals/7/favicon_en_US.png"> <meta name="generator" content="Open Journal Systems 3.4.0.7"> <meta name="gs_meta_revision" content="1.1"/> <meta name="citation_journal_title" content="Journal of Data Science and Intelligent Systems"/> <meta name="citation_journal_abbrev" content="JDSIS"/> <meta name="citation_issn" content="2972-3841"/> <meta name="citation_author" content="Ziying Wang"/> <meta name="citation_author_institution" content="School of Medical Imaging, Fujian Medical University, China"/> <meta name="citation_author" content="Jinghong Gao"/> <meta name="citation_author_institution" content="School of Medical Imaging, Fujian Medical University, China"/> <meta name="citation_author" content="Hangyi Kan"/> <meta name="citation_author_institution" content="School of Medical Imaging, Fujian Medical University, China"/> <meta name="citation_author" content="Yang Huang"/> <meta name="citation_author_institution" content="School of Medical Imaging, Fujian Medical University, China"/> <meta name="citation_author" content="Furong Tang"/> <meta name="citation_author_institution" content="School of Medicine, Tsinghua University, China"/> <meta name="citation_author" content="Wen Li"/> <meta name="citation_author_institution" content="Department of Pathology, Fujian Medical University Union Hospital, China"/> <meta name="citation_author" content="Fenglong Yang"/> <meta name="citation_author_institution" content="School of Medical Technology and Engineering, Fujian Medical University, China"/> <meta name="citation_title" content="ResNet for Histopathologic Cancer Detection, the Deeper, the Better?"/> <meta name="citation_language" content="en"/> <meta name="citation_date" content="2024"/> <meta name="citation_volume" content="2"/> <meta name="citation_issue" content="4"/> <meta name="citation_firstpage" content="212"/> <meta name="citation_lastpage" content="220"/> <meta name="citation_doi" content="10.47852/bonviewJDSIS3202744"/> <meta name="citation_abstract_html_url" content="https://ojs.bonviewpress.com/index.php/jdsis/article/view/744"/> <meta name="citation_abstract" xml:lang="en" content="Histopathological image classification has become one of the most challenging tasks for researchers, due to the varied categories and detailed differences within diseases. In this study, we investigate the critical role of network depth in histopathological image classification, utilizing deep residual convolutional neural networks (ResNet). We evaluate the efficacy of two transfer learning strategies using ResNet with varying layers (18, 34, 50, 152) pretrained on ImageNet. Specifically, we analyze whether a deeper network or the fine-tuning of all layers in pre-trained ResNets enhances performance compared to freezing most layers and training only the last layer. Conducted on Kaggle's dataset of 220,025 labeled histopathology patches, our findings reveal that increasing the depth of ResNet does not guarantee better accuracy (ResNet-34 AUC: 0.992 vs. ResNet-152 AUC: 0.989). Instead, dataset-specific semantic features and the cost of training should guide model selection. Furthermore, deep ResNet outperforms traditional logistic regression (ResNet AUC: up to 0.992 vs. logistic regression AUC: 0.775), showcasing superior generalization and robustness. Notably, the strategy of freezing most layers doesn't improve the accuracy and efficiency of transfer learning and the performance of both transfer strategies depends largely on the types of data. Overall, both methods produce satisfactory results in comparison to models trained from scratch or conventional machine learning models. 聽 Received: 17 January 2023 | Revised: 27 February 2023 | Accepted: 28 February 2023 聽 Conflicts of Interest The authors declare that they have no conflicts of interest to this work. 聽 Data Availability Statement The data that support the findings of this study are openly available in Kaggle HCD at https://www.kaggle.com/datasets/drbeane/hcd-cropped. 聽 Author Contribution Statement Ziying Wang:聽Methodology, Software, Formal analysis, Investigation, Data curation, Writing - original draft, Visualization. Jinghong Gao:聽Methodology, Software, Formal analysis, Writing - original draft, Visualization. Hangyi Kan:聽Validation, Investigation.聽Yang Huang: Formal analysis. Furong Tang: Writing - review &amp; editing, Funding acquisition. Wen Li:聽Conceptualization, Resources, Data curation, Supervision, Project administration. Fenglong Yang:聽Conceptualization, Writing - review &amp; editing, Supervision, Project administration, Funding acquisition."/> <meta name="citation_keywords" xml:lang="en" content="histopathological cancer"/> <meta name="citation_keywords" xml:lang="en" content="image classification"/> <meta name="citation_keywords" xml:lang="en" content=" residual neural network"/> <meta name="citation_keywords" xml:lang="en" content="transfer learning "/> <meta name="citation_pdf_url" content="https://ojs.bonviewpress.com/index.php/jdsis/article/download/744/339"/> <link rel="schema.DC" href="http://purl.org/dc/elements/1.1/" /> <meta name="DC.Creator.PersonalName" content="Ziying Wang"/> <meta name="DC.Creator.PersonalName" content="Jinghong Gao"/> <meta name="DC.Creator.PersonalName" content="Hangyi Kan"/> <meta name="DC.Creator.PersonalName" content="Yang Huang"/> <meta name="DC.Creator.PersonalName" content="Furong Tang"/> <meta name="DC.Creator.PersonalName" content="Wen Li"/> <meta name="DC.Creator.PersonalName" content="Fenglong Yang"/> <meta name="DC.Date.created" scheme="ISO8601" content="2023-03-03"/> <meta name="DC.Date.dateSubmitted" scheme="ISO8601" content="2023-02-16"/> <meta name="DC.Date.issued" scheme="ISO8601" content="2024-10-25"/> <meta name="DC.Date.modified" scheme="ISO8601" content="2024-11-05"/> <meta name="DC.Description" xml:lang="en" content="Histopathological image classification has become one of the most challenging tasks for researchers, due to the varied categories and detailed differences within diseases. In this study, we investigate the critical role of network depth in histopathological image classification, utilizing deep residual convolutional neural networks (ResNet). We evaluate the efficacy of two transfer learning strategies using ResNet with varying layers (18, 34, 50, 152) pretrained on ImageNet. Specifically, we analyze whether a deeper network or the fine-tuning of all layers in pre-trained ResNets enhances performance compared to freezing most layers and training only the last layer. Conducted on Kaggle's dataset of 220,025 labeled histopathology patches, our findings reveal that increasing the depth of ResNet does not guarantee better accuracy (ResNet-34 AUC: 0.992 vs. ResNet-152 AUC: 0.989). Instead, dataset-specific semantic features and the cost of training should guide model selection. Furthermore, deep ResNet outperforms traditional logistic regression (ResNet AUC: up to 0.992 vs. logistic regression AUC: 0.775), showcasing superior generalization and robustness. Notably, the strategy of freezing most layers doesn't improve the accuracy and efficiency of transfer learning and the performance of both transfer strategies depends largely on the types of data. Overall, both methods produce satisfactory results in comparison to models trained from scratch or conventional machine learning models. 聽 Received: 17 January 2023 | Revised: 27 February 2023 | Accepted: 28 February 2023 聽 Conflicts of Interest The authors declare that they have no conflicts of interest to this work. 聽 Data Availability Statement The data that support the findings of this study are openly available in Kaggle HCD at https://www.kaggle.com/datasets/drbeane/hcd-cropped. 聽 Author Contribution Statement Ziying Wang:聽Methodology, Software, Formal analysis, Investigation, Data curation, Writing - original draft, Visualization. Jinghong Gao:聽Methodology, Software, Formal analysis, Writing - original draft, Visualization. Hangyi Kan:聽Validation, Investigation.聽Yang Huang: Formal analysis. Furong Tang: Writing - review &amp; editing, Funding acquisition. Wen Li:聽Conceptualization, Resources, Data curation, Supervision, Project administration. Fenglong Yang:聽Conceptualization, Writing - review &amp; editing, Supervision, Project administration, Funding acquisition."/> <meta name="DC.Format" scheme="IMT" content="application/pdf"/> <meta name="DC.Identifier" content="744"/> <meta name="DC.Identifier.pageNumber" content="212-220"/> <meta name="DC.Identifier.DOI" content="10.47852/bonviewJDSIS3202744"/> <meta name="DC.Identifier.URI" content="https://ojs.bonviewpress.com/index.php/jdsis/article/view/744"/> <meta name="DC.Language" scheme="ISO639-1" content="en"/> <meta name="DC.Rights" content="Copyright (c) 2023 Authors"/> <meta name="DC.Rights" content="https://creativecommons.org/licenses/by/4.0/"/> <meta name="DC.Source" content="Journal of Data Science and Intelligent Systems"/> <meta name="DC.Source.ISSN" content="2972-3841"/> <meta name="DC.Source.Issue" content="4"/> <meta name="DC.Source.Volume" content="2"/> <meta name="DC.Source.URI" content="https://ojs.bonviewpress.com/index.php/jdsis"/> <meta name="DC.Subject" xml:lang="en" content="histopathological cancer"/> <meta name="DC.Subject" xml:lang="en" content="image classification"/> <meta name="DC.Subject" xml:lang="en" content=" residual neural network"/> <meta name="DC.Subject" xml:lang="en" content="transfer learning "/> <meta name="DC.Title" content="ResNet for Histopathologic Cancer Detection, the Deeper, the Better?"/> <meta name="DC.Type" content="Text.Serial.Journal"/> <meta name="DC.Type.articleType" content="Research Articles"/> <link rel="stylesheet" href="https://ojs.bonviewpress.com/index.php/jdsis/$$$call$$$/page/page/css?name=stylesheet" type="text/css" /><link rel="stylesheet" href="https://ojs.bonviewpress.com/index.php/jdsis/$$$call$$$/page/page/css?name=font" type="text/css" /><link rel="stylesheet" href="https://ojs.bonviewpress.com/lib/pkp/styles/fontawesome/fontawesome.css?v=3.4.0.7" type="text/css" /><style type="text/css">.pkp_structure_head { background: center / cover no-repeat url("https://ojs.bonviewpress.com/public/journals/7/homepageImage_en_US.png");}</style><link rel="stylesheet" href="https://ojs.bonviewpress.com/plugins/generic/doiInSummary/styles/doi.css?v=3.4.0.7" type="text/css" /><link rel="stylesheet" href="https://ojs.bonviewpress.com/plugins/generic/orcidProfile/css/orcidProfile.css?v=3.4.0.7" type="text/css" /><link rel="stylesheet" href="https://ojs.bonviewpress.com/public/journals/7/styleSheet.css?d=2023-01-16+16%3A41%3A36" type="text/css" /><link rel="stylesheet" href="https://ojs.bonviewpress.com/plugins/generic/citationStyleLanguage/css/citationStyleLanguagePlugin.css?v=3.4.0.7" type="text/css" /> </head> <body class="pkp_page_article pkp_op_view" dir="ltr"> <div class="pkp_structure_page"> <header class="pkp_structure_head" id="headerNavigationContainer" role="banner"> <nav class="cmp_skip_to_content" aria-label="Jump to content links"> <a href="#pkp_content_main">Skip to main content</a> <a href="#siteNav">Skip to main navigation menu</a> <a href="#pkp_content_footer">Skip to site footer</a> </nav> <div class="pkp_head_wrapper"> <div class="pkp_site_name_wrapper"> <button class="pkp_site_nav_toggle"> <span>Open Menu</span> </button> <div class="pkp_site_name"> <a href=" https://ojs.bonviewpress.com/index.php/jdsis/index " class="is_text">Journal of Data Science and Intelligent Systems</a> </div> </div> <nav class="pkp_site_nav_menu" aria-label="Site Navigation"> <a id="siteNav"></a> <div class="pkp_navigation_primary_row"> <div class="pkp_navigation_primary_wrapper"> <ul id="navigationPrimary" class="pkp_navigation_primary pkp_nav_list"> <li class=""> <a href="http://ojs.bonviewpress.com/index.php/jdsis/index"> HOME </a> </li> <li class=""> <a href="https://ojs.bonviewpress.com/index.php/jdsis/about"> ABOUT </a> <ul> <li class=""> <a href="https://ojs.bonviewpress.com/index.php/jdsis/aims_and_scope"> Aims and Scope </a> </li> <li class=""> <a href="https://ojs.bonviewpress.com/index.php/jdsis/JM"> Journal Metrics </a> </li> <li class=""> <a href="https://ojs.bonviewpress.com/index.php/jdsis/indexing"> Indexing & Abstracting </a> </li> <li class=""> <a href="https://ojs.bonviewpress.com/index.php/jdsis/about/privacy"> Privacy Statement </a> </li> <li class=""> <a href="https://ojs.bonviewpress.com/index.php/jdsis/contact"> Contact Us </a> </li> </ul> </li> <li class=""> <a href="https://ojs.bonviewpress.com/index.php/jdsis/browse"> BROWSE </a> <ul> <li class=""> <a href="https://ojs.bonviewpress.com/index.php/jdsis/issue/view/onlinefirst"> Online First </a> </li> <li class=""> <a href="https://ojs.bonviewpress.com/index.php/jdsis/issue/current"> Current Issue </a> </li> <li class=""> <a href="https://ojs.bonviewpress.com/index.php/jdsis/issue/archive"> All Issues </a> </li> </ul> </li> <li class=""> <a href="https://ojs.bonviewpress.com/index.php/jdsis/contribute"> CONTRIBUTE </a> <ul> <li class=""> <a href="https://ojs.bonviewpress.com/index.php/jdsis/about/submissions"> Author Guidelines </a> </li> <li class=""> <a href="https://ojs.bonviewpress.com/index.php/jdsis/oa"> Open Access </a> </li> <li class=""> <a href="https://ojs.bonviewpress.com/index.php/jdsis/peer_review_process"> Peer Review Process </a> </li> <li class=""> <a href="https://ojs.bonviewpress.com/index.php/jdsis/pe"> Publishing Ethics </a> </li> <li class=""> <a href="https://ojs.bonviewpress.com/index.php/jdsis/for_reviewers"> For Reviewers </a> </li> </ul> </li> <li class=""> <a href="https://ojs.bonviewpress.com/index.php/jdsis/edb"> EDITORIAL BOARD </a> </li> <li class=""> <a href="https://ojs.bonviewpress.com/index.php/jdsis/special_issues"> SPECIAL ISSUES </a> <ul> <li class=""> <a href="https://ojs.bonviewpress.com/index.php/jdsis/submittingproposal"> Submitting a Proposal </a> </li> </ul> </li> </ul> <div class="pkp_navigation_search_wrapper"> <a href="https://ojs.bonviewpress.com/index.php/index/search" class="pkp_search pkp_search_desktop"> <span class="fa fa-search" aria-hidden="true"></span> Search </a> </div> </div> </div> <div class="pkp_navigation_user_wrapper" id="navigationUserWrapper"> <ul id="navigationUser" class="pkp_navigation_user pkp_nav_list"> <li class="profile"> <a href="https://ojs.bonviewpress.com/index.php/jdsis/user/register"> Register </a> </li> <li class="profile"> <a href="https://ojs.bonviewpress.com/index.php/jdsis/browse"> BROWSE </a> </li> <li class="profile"> <a href="https://ojs.bonviewpress.com/index.php/jdsis/login"> Login </a> </li> </ul> </div> </nav> </div> </header> <div class="pkp_structure_content has_sidebar"> <div class="pkp_structure_main" role="main"> <a id="pkp_content_main"></a> <div class="page page_article"> <nav class="cmp_breadcrumbs" role="navigation" aria-label="You are here:"> <ol> <li> <a href="https://ojs.bonviewpress.com/index.php/jdsis/index"> Home </a> <span class="separator">/</span> </li> <li> <a href="https://ojs.bonviewpress.com/index.php/jdsis/issue/archive"> Archives </a> <span class="separator">/</span> </li> <li> <a href="https://ojs.bonviewpress.com/index.php/jdsis/issue/view/94"> Vol. 2 No. 4 (2024) </a> <span class="separator">/</span> </li> <li class="current" aria-current="page"> <span aria-current="page"> Research Articles </span> </li> </ol> </nav> <article class="obj_article_details"> <h1 class="page_title"> ResNet for Histopathologic Cancer Detection, the Deeper, the Better? </h1> <div class="row"> <div class="main_entry"> <section class="item authors"> <h2 class="pkp_screen_reader">Authors</h2> <ul class="authors"> <li> <span class="name"> Ziying Wang </span> <span class="affiliation"> School of Medical Imaging, Fujian Medical University, China </span> </li> <li> <span class="name"> Jinghong Gao </span> <span class="affiliation"> School of Medical Imaging, Fujian Medical University, China </span> </li> <li> <span class="name"> Hangyi Kan </span> <span class="affiliation"> School of Medical Imaging, Fujian Medical University, China </span> </li> <li> <span class="name"> Yang Huang </span> <span class="affiliation"> School of Medical Imaging, Fujian Medical University, China </span> </li> <li> <span class="name"> Furong Tang </span> <span class="affiliation"> School of Medicine, Tsinghua University, China </span> </li> <li> <span class="name"> Wen Li </span> <span class="affiliation"> Department of Pathology, Fujian Medical University Union Hospital, China </span> </li> <li> <span class="name"> Fenglong Yang </span> <span class="affiliation"> School of Medical Technology and Engineering, Fujian Medical University, China </span> </li> </ul> </section> <section class="item doi"> <h2 class="label"> DOI: </h2> <span class="value"> <a href="https://doi.org/10.47852/bonviewJDSIS3202744"> https://doi.org/10.47852/bonviewJDSIS3202744 </a> </span> </section> <section class="item keywords"> <h2 class="label"> Keywords: </h2> <span class="value"> histopathological cancer, image classification, residual neural network, transfer learning </span> </section> <section class="item abstract"> <h2 class="label">Abstract</h2> <p>Histopathological image classification has become one of the most challenging tasks for researchers, due to the varied categories and detailed differences within diseases. In this study, we investigate the critical role of network depth in histopathological image classification, utilizing deep residual convolutional neural networks (ResNet). We evaluate the efficacy of two transfer learning strategies using ResNet with varying layers (18, 34, 50, 152) pretrained on ImageNet. Specifically, we analyze whether a deeper network or the fine-tuning of all layers in pre-trained ResNets enhances performance compared to freezing most layers and training only the last layer. Conducted on Kaggle's dataset of 220,025 labeled histopathology patches, our findings reveal that increasing the depth of ResNet does not guarantee better accuracy (ResNet-34 AUC: 0.992 vs. ResNet-152 AUC: 0.989). Instead, dataset-specific semantic features and the cost of training should guide model selection. Furthermore, deep ResNet outperforms traditional logistic regression (ResNet AUC: up to 0.992 vs. logistic regression AUC: 0.775), showcasing superior generalization and robustness. Notably, the strategy of freezing most layers doesn't improve the accuracy and efficiency of transfer learning and the performance of both transfer strategies depends largely on the types of data. Overall, both methods produce satisfactory results in comparison to models trained from scratch or conventional machine learning models.</p> <p>聽</p> <p><strong>Received:</strong> 17 January 2023 <strong>| Revised: </strong>27 February 2023 <strong>| Accepted:</strong> 28 February 2023</p> <p>聽</p> <p><strong>Conflicts of Interest</strong></p> <p>The authors declare that they have no conflicts of interest to this work.</p> <p>聽</p> <p><strong>Data Availability Statement</strong></p> <p>The data that support the findings of this study are openly available in Kaggle HCD at <a href="https://www.kaggle.com/datasets/drbeane/hcd-cropped">https://www.kaggle.com/datasets/drbeane/hcd-cropped</a>.</p> <p>聽</p> <p><strong>Author Contribution Statement</strong></p> <p><strong>Ziying Wang:聽</strong>Methodology, Software, Formal analysis, Investigation, Data curation, Writing - original draft, Visualization. <strong>Jinghong Gao:聽</strong>Methodology, Software, Formal analysis, Writing - original draft, Visualization.<strong> Hangyi Kan:聽</strong>Validation, Investigation.聽<strong>Yang Huang: </strong>Formal analysis. <strong>Furong Tang: </strong>Writing - review & editing, Funding acquisition. <strong>Wen Li:聽</strong>Conceptualization, Resources, Data curation, Supervision, Project administration. <strong>Fenglong Yang:</strong>聽Conceptualization, Writing - review & editing, Supervision, Project administration, Funding acquisition.</p> </section> <br /><div class="separator"></div><div class="item abstract" id="trendmd-suggestions"></div><script defer src='//js.trendmd.com/trendmd.min.js' data-trendmdconfig='{"website_id":"89269", "element":"#trendmd-suggestions"}'></script> </div> <div class="entry_details"> <div class="item cover_image"> <div class="sub_item"> <a href="https://ojs.bonviewpress.com/index.php/jdsis/issue/view/94"> <img src="https://ojs.bonviewpress.com/public/journals/7/cover_issue_94_en.jpg" alt=""> </a> </div> </div> <div class="item galleys"> <h2 class="pkp_screen_reader"> Downloads </h2> <ul class="value galleys_links"> <li> <a class="obj_galley_link pdf" href="https://ojs.bonviewpress.com/index.php/jdsis/article/view/744/339"> PDF </a> </li> </ul> </div> <div class="item published"> <section class="sub_item"> <h2 class="label"> Published </h2> <div class="value"> <span>2023-03-03</span> </div> </section> </div> <div class="item issue"> <section class="sub_item"> <h2 class="label"> Issue </h2> <div class="value"> <a class="title" href="https://ojs.bonviewpress.com/index.php/jdsis/issue/view/94"> Vol. 2 No. 4 (2024) </a> </div> </section> <section class="sub_item"> <h2 class="label"> Section </h2> <div class="value"> Research Articles </div> </section> </div> <div class="item copyright"> <h2 class="label"> License </h2> <p>Copyright (c) 2023 Authors</p> <a rel="license" href="https://creativecommons.org/licenses/by/4.0/"><img alt="Creative Commons License" src="//i.creativecommons.org/l/by/4.0/88x31.png" /></a><p>This work is licensed under a <a rel="license" href="https://creativecommons.org/licenses/by/4.0/">Creative Commons Attribution 4.0 International License</a>.</p> </div> <div class="item citation"> <section class="sub_item citation_display"> <h2 class="label"> How to Cite </h2> <div class="value"> <div id="citationOutput" role="region" aria-live="polite"> <div class="csl-bib-body"> <div class="csl-entry">Wang, Z., Gao, J., Kan, H., Huang, Y., Tang, F., Li, W., & Yang, F. (2023). ResNet for Histopathologic Cancer Detection, the Deeper, the Better?. <i>Journal of Data Science and Intelligent Systems</i>, <i>2</i>(4), 212-220. <a href="https://doi.org/10.47852/bonviewJDSIS3202744">https://doi.org/10.47852/bonviewJDSIS3202744</a></div> </div> </div> <div class="citation_formats"> <button class="citation_formats_button label" aria-controls="cslCitationFormats" aria-expanded="false" data-csl-dropdown="true"> More Citation Formats </button> <div id="cslCitationFormats" class="citation_formats_list" aria-hidden="true"> <ul class="citation_formats_styles"> <li> <a aria-controls="citationOutput" href="https://ojs.bonviewpress.com/index.php/jdsis/citationstylelanguage/get/acm-sig-proceedings?submissionId=744&publicationId=1918&issueId=94" data-load-citation data-json-href="https://ojs.bonviewpress.com/index.php/jdsis/citationstylelanguage/get/acm-sig-proceedings?submissionId=744&publicationId=1918&issueId=94&return=json" > ACM </a> </li> <li> <a aria-controls="citationOutput" href="https://ojs.bonviewpress.com/index.php/jdsis/citationstylelanguage/get/acs-nano?submissionId=744&publicationId=1918&issueId=94" data-load-citation data-json-href="https://ojs.bonviewpress.com/index.php/jdsis/citationstylelanguage/get/acs-nano?submissionId=744&publicationId=1918&issueId=94&return=json" > ACS </a> </li> <li> <a aria-controls="citationOutput" href="https://ojs.bonviewpress.com/index.php/jdsis/citationstylelanguage/get/apa?submissionId=744&publicationId=1918&issueId=94" data-load-citation data-json-href="https://ojs.bonviewpress.com/index.php/jdsis/citationstylelanguage/get/apa?submissionId=744&publicationId=1918&issueId=94&return=json" > APA </a> </li> <li> <a aria-controls="citationOutput" href="https://ojs.bonviewpress.com/index.php/jdsis/citationstylelanguage/get/associacao-brasileira-de-normas-tecnicas?submissionId=744&publicationId=1918&issueId=94" data-load-citation data-json-href="https://ojs.bonviewpress.com/index.php/jdsis/citationstylelanguage/get/associacao-brasileira-de-normas-tecnicas?submissionId=744&publicationId=1918&issueId=94&return=json" > ABNT </a> </li> <li> <a aria-controls="citationOutput" href="https://ojs.bonviewpress.com/index.php/jdsis/citationstylelanguage/get/chicago-author-date?submissionId=744&publicationId=1918&issueId=94" data-load-citation data-json-href="https://ojs.bonviewpress.com/index.php/jdsis/citationstylelanguage/get/chicago-author-date?submissionId=744&publicationId=1918&issueId=94&return=json" > Chicago </a> </li> <li> <a aria-controls="citationOutput" href="https://ojs.bonviewpress.com/index.php/jdsis/citationstylelanguage/get/harvard-cite-them-right?submissionId=744&publicationId=1918&issueId=94" data-load-citation data-json-href="https://ojs.bonviewpress.com/index.php/jdsis/citationstylelanguage/get/harvard-cite-them-right?submissionId=744&publicationId=1918&issueId=94&return=json" > Harvard </a> </li> <li> <a aria-controls="citationOutput" href="https://ojs.bonviewpress.com/index.php/jdsis/citationstylelanguage/get/ieee?submissionId=744&publicationId=1918&issueId=94" data-load-citation data-json-href="https://ojs.bonviewpress.com/index.php/jdsis/citationstylelanguage/get/ieee?submissionId=744&publicationId=1918&issueId=94&return=json" > IEEE </a> </li> <li> <a aria-controls="citationOutput" href="https://ojs.bonviewpress.com/index.php/jdsis/citationstylelanguage/get/modern-language-association?submissionId=744&publicationId=1918&issueId=94" data-load-citation data-json-href="https://ojs.bonviewpress.com/index.php/jdsis/citationstylelanguage/get/modern-language-association?submissionId=744&publicationId=1918&issueId=94&return=json" > MLA </a> </li> <li> <a aria-controls="citationOutput" href="https://ojs.bonviewpress.com/index.php/jdsis/citationstylelanguage/get/turabian-fullnote-bibliography?submissionId=744&publicationId=1918&issueId=94" data-load-citation data-json-href="https://ojs.bonviewpress.com/index.php/jdsis/citationstylelanguage/get/turabian-fullnote-bibliography?submissionId=744&publicationId=1918&issueId=94&return=json" > Turabian </a> </li> <li> <a aria-controls="citationOutput" href="https://ojs.bonviewpress.com/index.php/jdsis/citationstylelanguage/get/vancouver?submissionId=744&publicationId=1918&issueId=94" data-load-citation data-json-href="https://ojs.bonviewpress.com/index.php/jdsis/citationstylelanguage/get/vancouver?submissionId=744&publicationId=1918&issueId=94&return=json" > Vancouver </a> </li> <li> <a aria-controls="citationOutput" href="https://ojs.bonviewpress.com/index.php/jdsis/citationstylelanguage/get/ama?submissionId=744&publicationId=1918&issueId=94" data-load-citation data-json-href="https://ojs.bonviewpress.com/index.php/jdsis/citationstylelanguage/get/ama?submissionId=744&publicationId=1918&issueId=94&return=json" > AMA </a> </li> </ul> <div class="label"> Download Citation </div> <ul class="citation_formats_styles"> <li> <a href="https://ojs.bonviewpress.com/index.php/jdsis/citationstylelanguage/download/ris?submissionId=744&publicationId=1918&issueId=94"> <span class="fa fa-download"></span> Endnote/Zotero/Mendeley (RIS) </a> </li> <li> <a href="https://ojs.bonviewpress.com/index.php/jdsis/citationstylelanguage/download/bibtex?submissionId=744&publicationId=1918&issueId=94"> <span class="fa fa-download"></span> BibTeX </a> </li> </ul> </div> </div> </div> </section> </div> <div class="item addthis"> <div class="value">  <div class="addthis_toolbox addthis_default_style "> <a class="addthis_button_preferred_1"></a> <a class="addthis_button_preferred_2"></a> <a class="addthis_button_preferred_3"></a> <a class="addthis_button_preferred_4"></a> <a class="addthis_button_compact"></a> <a class="addthis_counter addthis_bubble_style"></a> </div> <script type="text/javascript" src="//s7.addthis.com/js/250/addthis_widget.js#pubid="></script>  </div> </div> <div class="item funders" id="funding-data"> <h2 class="label">Funding data</h2> <div class="value"> <ul> <li> <a href="https://search.crossref.org/search/funders?id=501100001809&from_ui=yes">National Natural Science Foundation of China</a> <br /> Grant numbers 62102065 </li> <li> <a href="https://search.crossref.org/search/funders?id=501100001809&from_ui=yes">National Natural Science Foundation of China</a> <br /> Grant numbers 62271353 </li> <li> <a href="https://search.crossref.org/search/funders?id=501100001809&from_ui=yes">National Natural Science Foundation of China</a> <br /> Grant numbers 62001311 </li> <li> <a href="https://search.crossref.org/search/funders?id=501100018542&from_ui=yes">Natural Science Foundation of Sichuan Province</a> <br /> Grant numbers 2022NSFSC0926 </li> </ul> </div> </div> </div> </div> </article> <div id="articlesBySameAuthorList"> </div> </div> </div> <div class="pkp_structure_sidebar left" role="complementary"> <div class="pkp_block block_custom" id="customblock-journal-information"> <h2 class="title">Journal Information</h2> <div class="content"> <div class="journalcard__metrics border"><span class="sc-hwwEjo cdchLr"><strong>Editor-in-Chief:</strong> Shaojie Qiao, Chengdu University of Information Technology, China</span></div> <div class="journalcard__metrics border"><span class="sc-hwwEjo cdchLr"><strong>Frequency: </strong>Quarterly</span></div> <div class="journalcard__metrics border"><span class="sc-hwwEjo cdchLr"><strong>Submission to First Decision: </strong>25 days</span></div> <div class="journalcard__metrics border"><span class="sc-hwwEjo cdchLr"><strong>Submission to Acceptance: </strong>122 days</span></div> <div class="journalcard__metrics border"><strong><span class="sc-hwwEjo cdchLr">Accept to Publish: </span></strong><span class="sc-hwwEjo cdchLr">7 days</span></div> <div class="journalcard__metrics border"><span class="sc-hwwEjo cdchLr"><strong>Acceptance Rate: </strong>18%</span></div> <div class="journalcard__metrics border"><span class="sc-kPVwWT hZDpyF"><span class="sc-kPVwWT hZDpyF"><span class="sc-hwwEjo cdchLr"><strong>eISSN: </strong>2972-3841</span></span></span> <div class="journalcard__metrics border"> <p class="journalcard__metrics border">漏 2025  Bon View Publishing Pte Ltd.</p> </div> </div> </div> </div> <div class="pkp_block block_make_submission"> <h2 class="pkp_screen_reader"> Make a Submission </h2> <div class="content"> <a class="block_make_submission_link" href="https://ojs.bonviewpress.com/index.php/jdsis/about/submissions"> Make a Submission </a> </div> </div> <style type="text/css"> .block_announcements_article:not(:last-child) { padding-bottom: 1.5em; border-bottom: 1px solid; } .block_announcements_article { text-align: left; } .block_announcements #show-all{ font-style: italic; } </style> <div class="pkp_block block_announcements"> <h2 class="title">Announcements</h2> <div class="content"> <article class="block_announcements_article"> <h3 class="block_announcements_article_headline"> <a href="https://ojs.bonviewpress.com/index.php/jdsis/announcement/view/94"> JDSIS Has Been Officially Indexed in EBSCO </a> </h3> <time class="block_announcements_article_date" datetime="2024-11-07"> <strong>November 7, 2024</strong> </time> <div class="block_announcements_article_content"> <p>We are delighted to share with you that <em>Journal of Data Science and Intelligent Systems</em> 聽(eISSN: 2972-3841) has been officially indexed by EBSCO! The full text ingestion is still in progress and will be completed at January, 2025.</p> </div> </article> <article class="block_announcements_article"> <h3 class="block_announcements_article_headline"> <a href="https://ojs.bonviewpress.com/index.php/jdsis/announcement/view/72"> STM Membership Announcement </a> </h3> <time class="block_announcements_article_date" datetime="2024-04-24"> <strong>April 24, 2024</strong> </time> <div class="block_announcements_article_content"> <p>Bon View Publishing Pte. Ltd. proudly announces its membership in the esteemed聽<a href="https://www.stm-assoc.org/"><u>International Association of Scientific, Technical and Medical Publishers(STM)</u></a>, effective 2024. This collaboration marks a significant milestone in advancing global knowledge exchange and promoting cutting-edge research.</p> </div> </article> <a id="show-all" href="https://ojs.bonviewpress.com/index.php/jdsis/announcement">Show all announcements ...</a> </div> </div> <div class="pkp_block block_developed_by"> <div class="content"> <span class="title">Most Read</span> <ul class="most_read"> <li class="most_read_article"> <div class="most_read_article_title"><a href="https://ojs.bonviewpress.com/index.php/jdsis/article/view/1078">Fuzzy Logic and Neural Network-based Risk Assessment Model for Import and Export Enterprises: A Review</a></div> <div class="most_read_article_journal"><span class="fa fa-eye"></span> 2181</div> </li> <li class="most_read_article"> <div class="most_read_article_title"><a href="https://ojs.bonviewpress.com/index.php/jdsis/article/view/656">Applications of Quantum Computing in Health Sector</a></div> <div class="most_read_article_journal"><span class="fa fa-eye"></span> 2169</div> </li> <li class="most_read_article"> <div class="most_read_article_title"><a href="https://ojs.bonviewpress.com/index.php/jdsis/article/view/885">Analytic Network Process (ANP) Method: A Comprehensive Review of Applications, Advantages, and Limitations</a></div> <div class="most_read_article_journal"><span class="fa fa-eye"></span> 1627</div> </li> <li class="most_read_article"> <div class="most_read_article_title"><a href="https://ojs.bonviewpress.com/index.php/jdsis/article/view/983">3D-STCNN: Spatiotemporal Convolutional Neural Network Based on EEG 3D Features for Detecting Driving Fatigue</a></div> <div class="most_read_article_journal"><span class="fa fa-eye"></span> 1392</div> </li> <li class="most_read_article"> <div class="most_read_article_title"><a href="https://ojs.bonviewpress.com/index.php/jdsis/article/view/1293">Customer Segmentation Using Machine Learning Model: An Application of RFM Analysis</a></div> <div class="most_read_article_journal"><span class="fa fa-eye"></span> 1378</div> </li> </ul> </div> </div> <div class="pkp_block block_keyword_cloud"> <h2 class="title">Keywords</h2> <div class="content" id='wordcloud'></div> <script> function randomColor() { var cores = ['#1f77b4', '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2', '#7f7f7f', '#bcbd22', '#17becf']; return cores[Math.floor(Math.random()*cores.length)]; } document.addEventListener("DOMContentLoaded", function() { var keywords = [{"text":"survival analysis","size":1},{"text":"breast cancer","size":1},{"text":"classification","size":1},{"text":"neural networks","size":1},{"text":"data management","size":1},{"text":"redactable blockchain","size":1},{"text":"chameleon hash function","size":1},{"text":"dynamic trapdoor","size":1},{"text":"named entity recognition","size":1},{"text":"low resource","size":1},{"text":"iterated dilated convolution","size":1},{"text":"casual convolution","size":1},{"text":"multitask learning","size":1},{"text":"multiple sclerosis","size":1},{"text":"digital twin","size":1},{"text":"artificial intelligence","size":1},{"text":"precision medicine","size":1},{"text":"precision treatment","size":1},{"text":"machine learning","size":1},{"text":"rehabilitation","size":1},{"text":"quantum machine learning","size":1},{"text":"image classification","size":1},{"text":"quantum circuit","size":1},{"text":"small samples","size":1},{"text":"financial inclusion","size":1},{"text":"digital wallets","size":1},{"text":"caribbean sids","size":1},{"text":"sliding window","size":1},{"text":"human fall detection","size":1},{"text":"classification model","size":1},{"text":"tsfresh","size":1},{"text":"auto-sklearn","size":1},{"text":"nmr","size":1},{"text":"phase error correction","size":1},{"text":"nonlinear shrinkage","size":1},{"text":"optimization","size":1},{"text":"delta absolute net minimization","size":1},{"text":"reproducible research","size":1},{"text":"pseudorandom numbers","size":1},{"text":"energy consumption","size":1},{"text":"multivariate data","size":1},{"text":"principal component analysis","size":1},{"text":"categorical principal component analysis","size":1},{"text":"machine learning algorithms","size":1},{"text":"svc","size":1},{"text":"random forest classifier","size":1},{"text":"multinomial logistic regression","size":1},{"text":"regression tree","size":1},{"text":"anomaly detection","size":1},{"text":"outlier","size":1}]; var totalWeight = 0; var blockWidth = 300; var blockHeight = 200; var transitionDuration = 200; var length_keywords = keywords.length; var layout = d3.layout.cloud(); layout.size([blockWidth, blockHeight]) .words(keywords) .fontSize(function(d) { return fontSize(+d.size); }) .on('end', draw); var svg = d3.select("#wordcloud").append("svg") .attr("viewBox", "0 0 " + blockWidth + " " + blockHeight) .attr("width", '100%'); function update() { var words = layout.words(); fontSize = d3.scaleLinear().range([16, 34]); if (words.length) { fontSize.domain([+words[words.length - 1].size || 1, +words[0].size]); } } keywords.forEach(function(item,index){totalWeight += item.size;}); update(); function draw(words, bounds) { var width = layout.size()[0], height = layout.size()[1]; scaling = bounds ? Math.min( width / Math.abs(bounds[1].x - width / 2), width / Math.abs(bounds[0].x - width / 2), height / Math.abs(bounds[1].y - height / 2), height / Math.abs(bounds[0].y - height / 2), ) / 2 : 1; svg .append("g") .attr( "transform", "translate(" + [width >> 1, height >> 1] + ")scale(" + scaling + ")", ) .selectAll("text") .data(words) .enter().append("text") .style("font-size", function(d) { return d.size + "px"; }) .style("font-family", 'serif') .style("fill", randomColor) .style('cursor', 'pointer') .style('opacity', 0.7) .attr('class', 'keyword') .attr("text-anchor", "middle") .attr("transform", function(d) { return "translate(" + [d.x, d.y] + ")rotate(" + d.rotate + ")"; }) .text(function(d) { return d.text; }) .on("click", function(d, i){ window.location = "https://ojs.bonviewpress.com/index.php/index/search?query=QUERY_SLUG".replace(/QUERY_SLUG/, encodeURIComponent(''+d.text+'')); }) .on("mouseover", function(d, i) { d3.select(this).transition() .duration(transitionDuration) .style('font-size',function(d) { return (d.size + 3) + "px"; }) .style('opacity', 1); }) .on("mouseout", function(d, i) { d3.select(this).transition() .duration(transitionDuration) .style('font-size',function(d) { return d.size + "px"; }) .style('opacity', 0.7); }) .on('resize', function() { update() }); } layout.start(); }); </script> </div> </div> </div> <div class="pkp_structure_footer_wrapper" role="contentinfo"> <a id="pkp_content_footer"></a> <div class="pkp_structure_footer"> <div class="pkp_footer_content"> <p><a href="http://creativecommons.org/licenses/by/4.0/" rel="license"><img style="border-width: 0;" src="https://ojs.bonviewpress.com/public/site/images/admin/88x31.png" alt="Creative Commons License" width="88" height="31" /></a> 聽聽All site content, except where otherwise noted, is licensed under a <a href="http://creativecommons.org/licenses/by/4.0/" rel="license">Creative Commons Attribution 4.0 International License</a>.</p> <p>eISSN: 2972-3841 | Published by <a href="http://www.bonviewpress.com/">Bon View Publishing Pte Ltd.</a></p> <p><strong>Member of</strong></p> <p><img style="width: 997px; height: 62px;" src="https://bonview.oss-ap-southeast-1.aliyuncs.com/resource/ojs-logo-quanji.png" />聽</p> </div> <div class="pkp_brand_footer"> <a href="https://ojs.bonviewpress.com/index.php/jdsis/about/aboutThisPublishingSystem"> <img alt="More information about the publishing system, Platform and Workflow by OJS/PKP." src="https://ojs.bonviewpress.com/templates/images/ojs_brand.png"> </a> </div> </div> </div> </div> <script src="https://ojs.bonviewpress.com/lib/pkp/lib/vendor/components/jquery/jquery.min.js?v=3.4.0.7" type="text/javascript"></script><script src="https://ojs.bonviewpress.com/lib/pkp/lib/vendor/components/jqueryui/jquery-ui.min.js?v=3.4.0.7" type="text/javascript"></script><script src="https://ojs.bonviewpress.com/plugins/themes/default/js/lib/popper/popper.js?v=3.4.0.7" type="text/javascript"></script><script src="https://ojs.bonviewpress.com/plugins/themes/default/js/lib/bootstrap/util.js?v=3.4.0.7" type="text/javascript"></script><script src="https://ojs.bonviewpress.com/plugins/themes/default/js/lib/bootstrap/dropdown.js?v=3.4.0.7" type="text/javascript"></script><script src="https://ojs.bonviewpress.com/plugins/themes/default/js/main.js?v=3.4.0.7" type="text/javascript"></script><script src="https://ojs.bonviewpress.com/plugins/generic/citationStyleLanguage/js/articleCitation.js?v=3.4.0.7" type="text/javascript"></script><script src="https://d3js.org/d3.v4.js?v=3.4.0.7" type="text/javascript"></script><script src="https://cdn.jsdelivr.net/gh/holtzy/D3-graph-gallery@master/LIB/d3.layout.cloud.js?v=3.4.0.7" type="text/javascript"></script><script type="text/javascript"> (function (w, d, s, l, i) { w[l] = w[l] || []; var f = d.getElementsByTagName(s)[0], j = d.createElement(s), dl = l != 'dataLayer' ? '&l=' + l : ''; j.async = true; j.src = 'https://www.googletagmanager.com/gtag/js?id=' + i + dl; f.parentNode.insertBefore(j, f); function gtag(){dataLayer.push(arguments)}; gtag('js', new Date()); gtag('config', i); }) (window, document, 'script', 'dataLayer', 'UA-284252596-1'); </script> </body> </html>

CINXE.COM

ResNet for Histopathologic Cancer Detection, the Deeper, the Better? | Journal of Data Science and Intelligent Systems