{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T16:32:41Z","timestamp":1781109161374,"version":"3.54.1"},"reference-count":36,"publisher":"Public Library of Science (PLoS)","issue":"1","license":[{"start":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T00:00:00Z","timestamp":1767312000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100014718","name":"Innovative Research Group Project of the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["81771546 and 82271674"],"award-info":[{"award-number":["81771546 and 82271674"]}],"id":[{"id":"10.13039\/100014718","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Postgraduate Innovative Project of Central South University","award":["2024XQLH062"],"award-info":[{"award-number":["2024XQLH062"]}]},{"name":"Postgraduate Innovative Project of Central South University","award":["2024XQLH104"],"award-info":[{"award-number":["2024XQLH104"]}]},{"name":"Postgraduate Innovative Project of Central South University","award":["2024XQLH144"],"award-info":[{"award-number":["2024XQLH144"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Endometrial 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 inter-class AUROCs of 0.9876 for EC, 0.9600 for AEH, 0.9771 for EH, and 0.9855 for NE, and outperformed other algorithms such as TransMSL, CLAM, and ABMIL (average accuracy\u2009=\u20090.8914). 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.<\/jats:p>","DOI":"10.1371\/journal.pone.0340186","type":"journal-article","created":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T18:42:02Z","timestamp":1767379322000},"page":"e0340186","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":2,"title":["Weakly supervised deep multi-instance learning for classification of endometrial lesions on hematoxylin and eosin-stained whole-slide images"],"prefix":"10.1371","volume":"21","author":[{"given":"Zhixian","family":"Zhou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaqi","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianglong","family":"Du","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hansheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nian","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengniang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Cui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6947-1159","authenticated-orcid":true,"given":"Chun","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"issue":"9484","key":"pone.0340186.ref001","doi-asserted-by":"crossref","first-page":"491","DOI":"10.1016\/S0140-6736(05)67063-8","article-title":"Endometrial cancer","volume":"366","author":"F Amant","year":"2005","journal-title":"Lancet"},{"key":"pone.0340186.ref002","doi-asserted-by":"crossref","first-page":"118670","DOI":"10.1016\/j.lfs.2020.118670","article-title":"The role of sialyltransferases in gynecological malignant tumors","volume":"263","author":"Y Zhang","year":"2020","journal-title":"Life Sci"},{"issue":"1","key":"pone.0340186.ref003","doi-asserted-by":"crossref","first-page":"618","DOI":"10.1080\/21691401.2023.2274047","article-title":"Advances in screening and diagnostic lab-on-chip tools for gynaecological cancers - a review","volume":"51","author":"S Nujhat","year":"2023","journal-title":"Artif Cells Nanomed Biotechnol"},{"issue":"12","key":"pone.0340186.ref004","doi-asserted-by":"crossref","first-page":"4025","DOI":"10.1111\/cas.13819","article-title":"Efficacy of liquid-based genetic diagnosis of endometrial cancer","volume":"109","author":"M Matsuura","year":"2018","journal-title":"Cancer Sci"},{"issue":"12","key":"pone.0340186.ref005","doi-asserted-by":"crossref","first-page":"1459","DOI":"10.4103\/0366-6999.183431","article-title":"Role of Liquid-based Cytology and Cell Block in the Diagnosis of Endometrial Lesions","volume":"129","author":"H Zhang","year":"2016","journal-title":"Chin Med J (Engl)"},{"issue":"12","key":"pone.0340186.ref006","doi-asserted-by":"crossref","first-page":"997","DOI":"10.1177\/014107688407701201","article-title":"Endometrial cytology","volume":"77","author":"A Morse","year":"1984","journal-title":"J R Soc Med"},{"issue":"14","key":"pone.0340186.ref007","doi-asserted-by":"crossref","first-page":"1854","DOI":"10.3390\/ani12141854","article-title":"Collagen Type III as a Possible Blood Biomarker of Fibrosis in Equine Endometrium","volume":"12","author":"J Alpoim-Moreira","year":"2022","journal-title":"Animals (Basel)"},{"issue":"16","key":"pone.0340186.ref008","doi-asserted-by":"crossref","first-page":"17028","DOI":"10.1002\/cam4.6338","article-title":"Micro-histology combined with cytology improves the diagnostic accuracy of endometrial lesions","volume":"12","author":"Y Wang","year":"2023","journal-title":"Cancer Med"},{"issue":"7","key":"pone.0340186.ref009","doi-asserted-by":"crossref","first-page":"988","DOI":"10.1097\/PAS.0000000000001705","article-title":"Atypical Endometrial Hyperplasia, Low-grade: \u201cMuch ADO About Nothing\u201d","volume":"45","author":"E D\u2019Angelo","year":"2021","journal-title":"Am J Surg Pathol"},{"key":"pone.0340186.ref010","doi-asserted-by":"crossref","first-page":"1139858","DOI":"10.3389\/fendo.2023.1139858","article-title":"Progestin plus metformin improves outcomes in patients with endometrial hyperplasia and early endometrial cancer more than progestin alone: a meta-analysis","volume":"14","author":"F Shao","year":"2023","journal-title":"Front Endocrinol (Lausanne)"},{"issue":"24","key":"pone.0340186.ref011","article-title":"Progestin Resistance and Corresponding Management of Abnormal Endometrial Hyperplasia and Endometrial Carcinoma","volume":"14","author":"M Lv","year":"2022","journal-title":"Cancers (Basel)"},{"issue":"1","key":"pone.0340186.ref012","doi-asserted-by":"crossref","DOI":"10.3390\/cancers16010172","article-title":"Concurrent endometrial cancer in women with atypical endometrial hyperplasia: what is the predictive value of patient characteristics?","volume":"16","author":"L Giannella","year":"2023","journal-title":"Cancers (Basel)"},{"issue":"1","key":"pone.0340186.ref013","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1006\/gyno.1997.4911","article-title":"Concomitant endometrial hyperplasia in patients with endometrial carcinoma","volume":"69","author":"F G\u00fccer","year":"1998","journal-title":"Gynecol Oncol"},{"issue":"3","key":"pone.0340186.ref014","doi-asserted-by":"crossref","first-page":"735","DOI":"10.1097\/AOG.0000000000005297","article-title":"Management of Endometrial Intraepithelial Neoplasia or Atypical Endometrial Hyperplasia: ACOG Clinical Consensus No. 5","volume":"142","year":"2023","journal-title":"Obstet Gynecol"},{"issue":"5","key":"pone.0340186.ref015","doi-asserted-by":"crossref","first-page":"762","DOI":"10.1111\/his.14609","article-title":"Key changes to the World Health Organization (WHO) classification of female genital tumours introduced in the 5th edition (2020)","volume":"80","author":"WG McCluggage","year":"2022","journal-title":"Histopathology"},{"issue":"22","key":"pone.0340186.ref016","doi-asserted-by":"crossref","first-page":"2353","DOI":"10.1001\/jama.2016.17438","article-title":"Adapting to Artificial Intelligence: Radiologists and Pathologists as Information Specialists","volume":"316","author":"S Jha","year":"2016","journal-title":"JAMA"},{"issue":"9","key":"pone.0340186.ref017","doi-asserted-by":"crossref","first-page":"100400","DOI":"10.1016\/j.xcrm.2021.100400","article-title":"Predicting endometrial cancer subtypes and molecular features from histopathology images using multi-resolution deep learning models","volume":"2","author":"R Hong","year":"2021","journal-title":"Cell Rep Med"},{"issue":"1","key":"pone.0340186.ref018","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1186\/s12967-020-02660-x","article-title":"Deep learning model for classifying endometrial lesions","volume":"19","author":"Y Zhang","year":"2021","journal-title":"J Transl Med"},{"issue":"3","key":"pone.0340186.ref019","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0248526","article-title":"Automated system for diagnosing endometrial cancer by adopting deep-learning technology in hysteroscopy","volume":"16","author":"Y Takahashi","year":"2021","journal-title":"PLoS One"},{"issue":"7","key":"pone.0340186.ref020","doi-asserted-by":"crossref","first-page":"1962","DOI":"10.1038\/s41591-024-02993-w","article-title":"Prediction of recurrence risk in endometrial cancer with multimodal deep learning","volume":"30","author":"S Volinsky-Fremond","year":"2024","journal-title":"Nat Med"},{"issue":"1","key":"pone.0340186.ref021","doi-asserted-by":"crossref","first-page":"5915","DOI":"10.1038\/s41467-021-26216-9","article-title":"Annotation-efficient deep learning for automatic medical image segmentation","volume":"12","author":"S Wang","year":"2021","journal-title":"Nat Commun"},{"issue":"1","key":"pone.0340186.ref022","doi-asserted-by":"crossref","first-page":"4973","DOI":"10.1038\/s41467-024-49017-2","article-title":"AI-based histopathology image analysis reveals a distinct subset of endometrial cancers","volume":"15","author":"A Darbandsari","year":"2024","journal-title":"Nat Commun"},{"issue":"1","key":"pone.0340186.ref023","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1038\/s41746-024-01131-7","article-title":"Deep learning to assess microsatellite instability directly from histopathological whole slide images in endometrial cancer","volume":"7","author":"C-W Wang","year":"2024","journal-title":"NPJ Digit Med"},{"issue":"2","key":"pone.0340186.ref024","article-title":"Interpretable deep learning model to predict the molecular classification of endometrial cancer from haematoxylin and eosin-stained whole-slide images: a combined analysis of the PORTEC randomised trials and clinical cohorts","volume":"5","author":"S Fremond","year":"2023","journal-title":"Lancet Digit Health"},{"issue":"1","key":"pone.0340186.ref025","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1109\/TPAMI.1982.4767203","article-title":"Threshold selection using quadtrees","volume":"4","author":"AY Wu","year":"1982","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"6","key":"pone.0340186.ref026","doi-asserted-by":"crossref","first-page":"555","DOI":"10.1038\/s41551-020-00682-w","article-title":"Data-efficient and weakly supervised computational pathology on whole-slide images","volume":"5","author":"MY Lu","year":"2021","journal-title":"Nat Biomed Eng"},{"key":"pone.0340186.ref027","first-page":"14318","article-title":"Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning","volume":"2021","author":"B Li","year":"2021","journal-title":"Conf Comput Vis Pattern Recognit Workshops"},{"issue":"2","key":"pone.0340186.ref028","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","article-title":"nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation","volume":"18","author":"F Isensee","year":"2021","journal-title":"Nat Methods"},{"key":"pone.0340186.ref029","doi-asserted-by":"crossref","first-page":"101563","DOI":"10.1016\/j.media.2019.101563","article-title":"Hover-Net: Simultaneous segmentation and classification of nuclei in multi-tissue histology images","volume":"58","author":"S Graham","year":"2019","journal-title":"Med Image Anal"},{"issue":"13","key":"pone.0340186.ref030","doi-asserted-by":"crossref","first-page":"2449","DOI":"10.3390\/cancers16132449","article-title":"Deep Residual Learning-Based Classification with Identification of Incorrect Predictions and Quantification of Cellularity and Nuclear Morphological Features in Digital Pathological Images of Common Astrocytic Tumors","volume":"16","author":"Y-C Chen","year":"2024","journal-title":"Cancers (Basel)"},{"issue":"12","key":"pone.0340186.ref031","doi-asserted-by":"crossref","DOI":"10.1016\/j.modpat.2023.100326","article-title":"Pathomic Features Reveal Immune and Molecular Evolution From Lung Preneoplasia to Invasive Adenocarcinoma","volume":"36","author":"P Chen","year":"2023","journal-title":"Mod Pathol"},{"issue":"2","key":"pone.0340186.ref032","first-page":"232","article-title":"New concepts for an old problem: the diagnosis of endometrial hyperplasia","volume":"23","author":"PA Sanderson","year":"2017","journal-title":"Hum Reprod Update"},{"issue":"1","key":"pone.0340186.ref033","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1136\/jcp.2004.021071","article-title":"EIN and WHO94","volume":"58","author":"JPA Baak","year":"2005","journal-title":"J Clin Pathol"},{"issue":"3","key":"pone.0340186.ref034","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1006\/gyno.1999.5580","article-title":"Endometrial intraepithelial neoplasia (EIN): will it bring order to chaos? The Endometrial Collaborative Group","volume":"76","author":"GL Mutter","year":"2000","journal-title":"Gynecol Oncol"},{"issue":"11","key":"pone.0340186.ref035","doi-asserted-by":"crossref","first-page":"8877","DOI":"10.1007\/s00432-023-04838-4","article-title":"Deep learning-based methods for classification of microsatellite instability in endometrial cancer from HE-stained pathological images","volume":"149","author":"Y Zhang","year":"2023","journal-title":"J Cancer Res Clin Oncol"},{"issue":"1","key":"pone.0340186.ref036","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s41666-020-00082-4","article-title":"Federated Learning for Healthcare Informatics","volume":"5","author":"J Xu","year":"2021","journal-title":"J Healthc Inform Res"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0340186","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T18:42:08Z","timestamp":1767379328000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0340186"}},"subtitle":[],"editor":[{"given":"Jin Su","family":"Kim","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,1,2]]},"references-count":36,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1,2]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0340186","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,2]]}}}