[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-419363-105":59,"doc-detail-419363-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","weakly-supervised-deep-multi-instance-learning-for-classification-of-endometrial-lesions-on-hematoxylin-and-eosin-stained-whole-slide-images","Weakly supervised deep multi-instance learning for classification of endometrial lesions on hematoxylin and eosin-stained whole-slide images","","Endometrial cancer (EC) is the most common gynecological malignancy, yet screening and diagnostic methods remain limited. This work proposes a weakly supervised deep multi-instance learning model (DSMIL) to classify hematoxylin and eosin-stained whole-slide images of endometrial tissue. Across 885 WSIs from 442 patients spanning EC, AEH, EH, and normal endometrium, DSMIL reaches strong AUROC and outperforms prior algorithms. Attention heatmaps and downstream segmentation support characterization of atypical glandular epithelial cells with morphologic differences from normal.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":35,"@type":76,"position":81},"https://docshare.wps.com/document/healthcare/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/weakly-supervised-deep-multi-instance-learning-for-classification-of-endometrial-lesions-on-hematoxylin-and-eosin-stained-whole-slide-images/419363/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/weakly-supervised-deep-multi-instance-learning-for-classification-of-endometrial-lesions-on-hematoxylin-and-eosin-stained-whole-slide-images/419363.png","ImageObject",300,407,{"name":92,"@type":93},"Stanford","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-04","2026-09-28",true,{"@type":102,"interactionType":103,"userInteractionCount":34},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What problem does the DSMIL model address in this study?","Question",{"text":112,"@type":113},"It targets the need for more reliable computer-aided screening and diagnosis of endometrial lesions from hematoxylin-and-eosin whole-slide images, where current approaches and human judgment are limited.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How was the dataset constructed for classification?",{"text":117,"@type":113},"The study analyzed 885 WSIs from 442 patients covering four categories: EC, atypical endometrial hyperplasia (AEH), endometrial hyperplasia without atypia (EH), and normal endometrium (NE).",{"name":119,"@type":110,"acceptedAnswer":120},"What do the results indicate about model performance and interpretability?",{"text":121,"@type":113},"DSMIL achieves high AUROC for four-class classification, and attention heatmaps highlight regions linked to pathological features; additional tools help characterize atypical glandular epithelial cells by morphological changes.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},419363,1791162622,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":34,"category_name":35,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":34,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":144,"read_time":145,"preview_page_count":4},2336477552062,"https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d","OPEN ACCESS  \nCitation: Zhou Z, Guo J, Du X, Li H, Xie N, Liu C, et al. (2026) Weakly supervised deep multi-instance learning for classification of endometrial lesions on hematoxylin and eosinstained whole-slide images. PLoS One 21(1): e0340186. [https://doi.org/10.1371/journal](https://doi.org/10.1371/journal). pone.0340186  \nEditor: Jin Su Kim, Korea Institute of Radiological and Medical Sciences, KOREA, REPUBLIC OF  \nReceived: September 5, 2025  \nAccepted: December 17, 2025  \nPublished: January 2, 2026  \nCopyright: © 2026 Zhou et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.  \nData availability statement: Due to the privacy requirements of clinical data, the data cannot be publicly shared. However, eligible researchers can obtain the data from the Clinical Research Ethics Committee of the Second  \nRESEARCH ARTICLE  \nWeakly supervised deep multi-instance learning for classification of endometrial lesions on hematoxylin and eosin-stained whole-slide images  \nZhixian Zhou1,2, Jiaqi Guo3, Xianglong Du3, Hansheng Li3, Nian Xie1,2, Chengniang Liu1,2, Hao He3, Lin Yang4, Lei Cui3☯*, Chun Fu1,2☯*  \n1 Department of Obstetrics and Gynecology, The Second Xiangya Hospital of Central South University, Changsha, China, 2 Clinical Research Center for Gynecological Disease in Hunan Province, Changsha, China, 3 School of Information Science and Technology, Northwest University, Xi’an, China, 4 School of Engineering, Westlake University, Hangzhou, China  \n☯ These authors contributed equally to this work.  \n* [fuchun0814@csu.edu.cn](fuchun0814@csu.edu.cn) (CF); [leicui@nwu.edu.cn](leicui@nwu.edu.cn) (LC)  \nAbstract  \nEndometrial cancer (EC) is the most common gynecological malignancy, yet reliable screening and diagnostic approaches remain limited. We developed a weakly supervised deep multi-instance learning model (DSMIL) to classify hematoxylin and eosin-stained whole-slide images (WSIs) of endometrial tissue. A total of 885 WSIs from 442 patients, including EC, atypical endometrial hyperplasia (AEH), endometrial hyperplasia without atypia (EH), and normal endometrium (NE), were analyzed. DSMIL achieved an average AUROC of 0.9776 for four-class classification, with interclass AUROCs of 0.9876 for EC, 0.9600 forAEH, 0.9771 for EH, and 0.9855 for NE, and outperformed other algorithms such as TransMSL, CLAM, and ABMIL (average accuracy = 0.8914) . Attention heatmaps highlighted regions associated with pathological features, while nnU-Net v2 combined with HoverNet enabled identification of atypical glandular epithelial cells, which showed increased density, size, and perimeter but reduced axis ratios compared with normal cells. These results suggest that DSMIL provides a reliable computational pathology approach for the classification of endometrial lesions and the characterization of atypical cells.  \n1. Introduction  \nEndometrial cancer (EC) is the most common gynecological cancer among women worldwide, and its incidence and mortality are on the rise [ 1 ,2] . There are currently no mature and effective screening methods for EC [3–6] . It is crucial to identify endometrial lesions early and accurately so that accurate treatment options can be selected and fertility can be preserved, improving patients’ quality of life and reducing EC risk.  \nPLOS One | [https://doi.org/10.1371/journal.pone.0340186](https://doi.org/10.1371/journal.pone.0340186) January 2, 2026 1 / 15  \nXiangya Hospital, Central South University (contact Tel: +86 731 8529 2476) .  \nFunding: This research was supported by the National Natural Science Foundation Project of China (81771546 and 82271674) . Supported By Postgraduate Innovative Project of Central South University (2024XQLH062, 2024XQLH104, 2024XQLH144) . The fundershad no role in study design, data collection and analysis, dec","cbCaivDqlMqzSpCO","https://ap.wps.com/l/cbCaivDqlMqzSpCO","pdf",1824222,15,"English","# Abstract\n# Introduction","[{\"question\":\"What problem does the DSMIL model address in this study?\",\"answer\":\"It targets the need for more reliable computer-aided screening and diagnosis of endometrial lesions from hematoxylin-and-eosin whole-slide images, where current approaches and human judgment are limited.\"},{\"question\":\"How was the dataset constructed for classification?\",\"answer\":\"The study analyzed 885 WSIs from 442 patients covering four categories: EC, atypical endometrial hyperplasia (AEH), endometrial hyperplasia without atypia (EH), and normal endometrium (NE).\"},{\"question\":\"What do the results indicate about model performance and interpretability?\",\"answer\":\"DSMIL achieves high AUROC for four-class classification, and attention heatmaps highlight regions linked to pathological features; additional tools help characterize atypical glandular epithelial cells by morphological changes.\"}]","Weakly supervised deep multi-instance learning for classification of endometrial lesions on hematoxylin and eosin-stained whole-slide images | PDF",1790616730,38]