[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-369783-105":59,"doc-detail-369783-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","deep-learning-model-for-predicting-extraprostatic-extension-of-prostate-cancer-based-on-he-stained-biopsy-digital-images","Deep learning model for predicting extraprostatic extension of prostate cancer based on H&E-stained biopsy digital images","","Background: Develop and validate a deep learning pipeline using prostate biopsy H&E slides to predict extraprostatic extension (EPE) in prostate cancer (PCa). Methods: 2592 preoperative H&E whole-slide images from 260 consecutive PCa patients were digitized, tumor regions annotated, and 224×224 patches extracted; patient-level training/testing used an 8:2 split with multiple instance learning. Results: ConvNeXt best tumor classification (ACC 0.965, AUC 0.981). EPE prediction reached AUC 0.943 (train) and 0.886 (test), key nuclear features linked to EPE, and predicted EPE probabilities correlated with biochemical recurrence (p=0.01). Conclusions: The model accurately predicts postoperative EPE from biopsy slides, enabling preoperative risk stratification to support personalized treatment.",{"@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":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/deep-learning-model-for-predicting-extraprostatic-extension-of-prostate-cancer-based-on-he-stained-biopsy-digital-images/369783/",{"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/deep-learning-model-for-predicting-extraprostatic-extension-of-prostate-cancer-based-on-he-stained-biopsy-digital-images/369783.png","ImageObject",300,407,{"name":92,"@type":93},"Grenda","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-17","2026-09-23",true,{"@type":102,"interactionType":103,"userInteractionCount":52},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What is the document’s main objective?","Question",{"text":112,"@type":113},"To develop and validate a deep learning pipeline that uses prostate biopsy H&E slides to predict extraprostatic extension (EPE) in prostate cancer patients.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How was the dataset built and split for training and testing?",{"text":117,"@type":113},"Whole-slide images from 260 consecutive patients (2592 biopsy H&E slides) were digitized, tumor regions annotated, and 224×224 pixel patches extracted; the dataset was randomly divided at the patient level into training and testing sets in an 8:2 ratio.",{"name":119,"@type":110,"acceptedAnswer":120},"Which model performed best and how accurate was the EPE prediction?",{"text":121,"@type":113},"ConvNeXt achieved the best tumor classification performance, and the EPE prediction model achieved AUCs of 0.943 on the training set and 0.886 on the test set.","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},369783,1790241517,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":52,"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":19,"preview_urls":146},7971474921005,"https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0","AnnAls of Medicine  \n2025, Vol. 57, no. 1, 2547094  \n[https://doi.org/10.1080/07853890.2025.2547094](https://doi.org/10.1080/07853890.2025.2547094)  \nRESEARCH ARTICLE     \nDeep learning model for predicting extraprostatic extension of prostate cancer based on H&E-stained biopsy digital images  \nPeiling Yua\\#, Nan Liub\\#, Dongli Fengc, Yi Jingd, MoYu Xiad, Hongyu Guoa, Yinan Yuana, Weilin Guoa, Yini Alatana, Siru Niea, Jinming Zhaoa, Hongbo Sua, Yuan Miaob* and Qi Miaoc*   \nadepartment of Pathology, the first Affiliated Hospital of china Medical University, shenyang, china; bdepartment of Pathology, the first Affiliated Hospital and college of Basic Medical sciences of china Medical University, shenyang, china; cdepartment of Radiology, The first Hospital of china Medical University, shenyang, liaoning, china; dneusoft Research of intelligent Healthcare Technology, [co. ltd](co. ltd), shenyang, china  \nABSTRACT  \nBackground: To develop and validate a deep learning pipeline using prostate biopsy H&E slides to predict extraprostatic extension (EPE) in prostate cancer (PCa) patients. Methods: A total of 2592 preoperative biopsy H&E slides from 260 consecutive PCa patients who underwent radical prostatectomy were collected from January 2019 to October 2023. Whole-slide images (WSIs) were digitized, tumor regions were annotated, and 224 × 224 pixel patches were extracted. The dataset was randomly divided into training and testing sets at the patient level in a ratio of 8:2. A tumor classification model and an EPE prediction model based on multiple instance learning were trained. Subsequently, we conducted an interpretability analysis of the EPE model and further carried out a correlation analysis between the predicted probabilities of the EPE and the biochemical recurrence (BCR) of the patients.  \nResults: The ConvNeXt model achieved the best performance in tumor classification, with an accuracy of 0.965 and an area under the curve (AUC) of 0.981 on the test set. For EPE prediction, the model achieved AUCs of 0.943 and 0.886 in the training and test sets, respectively. Key features identified by the model, such as nuclear characteristics, were significantly associated with EPE. Predicted EPE probabilities were strongly correlated with BCR (p = 0.01).  \nConclusions: The AI pathology model accurately predicts postoperative EPE via biopsy slides, achieving an AUC of 0.886 on the test set, offering a novel, feasible PCa preoperative risk stratification method to aid personalized treatment.  \nKEY MESSAGES  \n1. This study developed a deep learning pipeline based on biopsy H&E slides to predict extraprostatic extension (EPE) with high accuracy.  \n2. The model’s predictions were based on key pathological features like nuclear characteristics and were strongly correlated with biochemical recurrence.  \n3. This AI-based method offers a feasible tool for preoperative risk stratification and personalized treatment planning in prostate cancer.  \n1. Introduction  \nARTICLE HISTORY  \nReceived 19 May 2025 Revised 17 July 2025 Accepted 7 August 2025  \nKEYWORDS  \nProstate cancer; deep learning; extraprostatic extension; digital pathology; multiple instance learning  \nProstate cancer (PCa) is the most prevalent malignancies in the male urinary system globally, constituting approximately 15% of all male cancers [1] . It ranks second in incidence and the fifth in cancer-related mortality among man [1] . Extraprostatic extension (EPE)—defined as PCa spread through prostate capsule into periprostatic tissues—is observed in 15–40% of radical prostatectomy specimens and portends higher risks of positive surgical margins, biochemical recurrence, and the need for adjuvant therapies  \nCONTACT Yuan Miao  [cmumiaoyuan@163.com](cmumiaoyuan@163.com)  department of Pathology, the first Affiliated Hospital and college of Basic Medical sciences of china Medical University, shenyang, china; Qi Miao  [qmiao@cmu.edu.cn](qmiao@cmu.edu.cn)  department of Radiology, The firs","cbCaiqGQAbiRiVGL","https://ap.wps.com/l/cbCaiqGQAbiRiVGL","pdf",4342598,11,"English","# Abstract\n## Background and Methods\n## Results\n## Conclusions\n# Introduction\n## Clinical importance of EPE\n## Current prediction tools and limitations\n# Key messages","[{\"question\":\"What is the document’s main objective?\",\"answer\":\"To develop and validate a deep learning pipeline that uses prostate biopsy H\\u0026E slides to predict extraprostatic extension (EPE) in prostate cancer patients.\"},{\"question\":\"How was the dataset built and split for training and testing?\",\"answer\":\"Whole-slide images from 260 consecutive patients (2592 biopsy H\\u0026E slides) were digitized, tumor regions annotated, and 224×224 pixel patches extracted; the dataset was randomly divided at the patient level into training and testing sets in an 8:2 ratio.\"},{\"question\":\"Which model performed best and how accurate was the EPE prediction?\",\"answer\":\"ConvNeXt achieved the best tumor classification performance, and the EPE prediction model achieved AUCs of 0.943 on the training set and 0.886 on the test set.\"}]","Deep learning model for predicting extraprostatic extension of prostate cancer based on H&E-stained biopsy digital images | PDF",1790184522,28,[147,151,155,159],{"page_no":8,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/cd94130090e955694d74e9d6e75d8fa8.webp",983,1310,{"page_no":14,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/c295dccfd3724a88188667e7ba8b7921.webp",982,1309,{"page_no":81,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/0ea1a5d0e88b0b747f792f6353c72ffd.webp",981,1308,{"page_no":19,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/e8e67ce0e86ae4d7ec6ceb9695858409.webp",980,1306]