[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-340966-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-340966-en":131},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","direct-three-dimensional-segmentation-of-prostate-glands-with-nnu-net","Direct three-dimensional segmentation of prostate glands with nnU-Net","","The paper presents a direct, efficient 3D gland-segmentation approach for prostate cancer risk assessment using nnU-Net. Standard Gleason grading relies on limited 2D histology sections and suffers from interobserver variability and incomplete sampling, motivating 3D computational analysis. A model is trained from 3D masks generated previously by ITAS3D on light-sheet microscopy datasets with an inexpensive fluorescent H&E analog. Results show high accuracy with limited training data, simpler and faster operation than ITAS3D, and robust performance on lower-resolution inputs.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/direct-three-dimensional-segmentation-of-prostate-glands-with-nnu-net/340966/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/direct-three-dimensional-segmentation-of-prostate-glands-with-nnu-net/340966.png","ImageObject",300,407,{"name":42,"@type":43},"Finn","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-31","2026-09-22",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",11,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"Why is 3D segmentation of prostate glands important for prostate cancer risk assessment?","Question",{"text":63,"@type":64},"Standard Gleason grading is based on morphology in thin 2D sections, which undersamples tissue and can be ambiguous, leading to variability and imperfect outcome correlation. 3D segmentation supports volumetric feature quantification for improved computational prognostic analysis.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"What dataset and staining approach does the method use?",{"text":68,"@type":64},"The model uses open-top light-sheet microscopy datasets of human prostate biopsies stained with a fluorescent analog of hematoxylin and eosin (H&E).",{"name":70,"@type":61,"acceptedAnswer":71},"How does nnU-Net improve over the prior ITAS3D pipeline?",{"text":72,"@type":64},"nnU-Net uses previously generated 3D gland masks as training data to enable a direct end-to-end segmentation model. Compared with ITAS3D, it is simpler and faster and maintains good accuracy even with lower-resolution inputs.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},340966,1790535997,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,115,120,123,127],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":25,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":112,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":113,"slug":114},8,30,"research-report",{"id":116,"doc_module":4,"doc_module_name":25,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":25,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":25,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":128,"doc_module":4,"doc_module_name":25,"category_name":129,"show_sort_weight":97,"slug":130},19,"General","general",{"code":4,"msg":82,"data":132},{"doc_id":79,"user_id":133,"nickname":42,"user_avatar":134,"doc_module":4,"category_id":112,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":140,"language":141,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":12,"update_tm":145,"read_time":113,"preview_page_count":33,"preview_urls":146},34359740700684,"https://ap-avatar.wpscdn.com/avatar/1f400023980c374ae676?_k=1777273430885731487","RESEARCH PAPER  \nDirect three-dimensional segmentation of prostate  \nglands with nnU-Net  \nRui Wang  ,a Sarah S. L. Chow  ,a Robert B. Serafin,a Weisi Xie  ,a Qinghua Han,b Elena Baraznenok,a,b Lydia Lan,b,c Kevin W. Bishop  ,a,b  \nand Jonathan T. C. Liua,b,d,*  \naUniversity of Washington, Department of Mechanical Engineering, Seattle, Washington, United States  \nbUniversity of Washington, Department of Bioengineering, Seattle, Washington, United States  \ncUniversity of Washington, Department of Biology, Seattle, Washington, United States dUniversity of Washington, Department of Laboratory Medicine and Pathology, Seattle, Washington,  \nUnited States  \nABSTRACT. Significance: In recent years, we and others have developed non-destructive methods to obtain three-dimensional (3D) pathology datasets of clinical biopsies and surgical specimens. For prostate cancer risk stratification (prognostication), standardof-care Gleason grading is based on examining the morphology of prostate glands in thin 2D sections. This motivates us to perform 3D segmentation of prostate glands in our 3D pathology datasets for the purposes of computational analysis of 3D glandular features that could offer improved prognostic performance.  \nAim: To facilitate prostate cancer risk assessment, we developed a computationally efficient and accurate deep learning model for 3D gland segmentation based on open-top light-sheet microscopy datasets of human prostate biopsies stained with a fluorescent analog of hematoxylin and eosin (H&E) .  \nApproach: For 3D gland segmentation based on our H&E-analog 3D pathology datasets, we previously developed a hybrid deep learning and computer visionbased pipeline, called image translation-assisted segmentation in 3D (ITAS3D), which required a complex two-stage procedure and tedious manual optimization of parameters. To simplify this procedure, we use the 3D gland-segmentation masks previously generated by ITAS3D as training datasets for a direct end-to-end deep learning-based segmentation model, nnU-Net. The inputs to this model are 3D pathology datasets of prostate biopsies rapidly stained with an inexpensive fluorescent analog of H&E and the outputs are 3D semantic segmentation masks of the gland epithelium, gland lumen, and surrounding stromal compartments within the tissue.  \nResults: nnU-Net demonstrates remarkable accuracy in 3D gland segmentationseven with limited training data. Moreover, compared with the previous ITAS3D pipeline, nnU-Net operation is simpler and faster, and it can maintain good accuracy even with lower-resolution inputs.  \nConclusions: Our trained DL-based 3D segmentation model will facilitate future studies to demonstrate the value of computational 3D pathology for guiding critical treatment decisions for patients with prostate cancer.  \n© The Authors. Published by SPIE under a Creative Commons Attribution 4.0 International License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI. [DOI: 10.1117/1.JBO.29.3.036001]  \nKeywords: computational three-dimensional pathology; gland segmentation; prostate cancer; deep learning; biomedical image processing  \nPaper 230376GR received Dec. 1, 2023; revised Feb. 6, 2024; accepted Feb. 9, 2024; published Mar.  \n1, 2024 .  \n*Address all correspondence to Jonathan T. C. Liu, [jonliu@uw.edu](jonliu@uw.edu)  \nJournal of Biomedical Optics 036001-1 March 2024 • Vol. 29(3)  \nWang et al.: Direct three-dimensional segmentation of prostate glands with nnU-Net  \n1 Introduction  \nProstate cancer is the most prevalent form of cancer and is the second leading cause of cancerrelated deaths among men in the United States.1 Every year, nearly 250,000 men are diagnosed with this disease in the United States. Morbidity and mortality rates are low, but there is a fraction of prostate cancer cases that are potentially lethal and for whom aggressive treatments are warranted. To determine whether a pa","cbCaivJCsZcZqfmU","https://ap.wps.com/l/cbCaivJCsZcZqfmU","pdf",4721227,12,"English","# Abstract\n# Introduction\n## Background and motivation for 3D pathology\n## Limitations of Gleason grading and conventional histology","[{\"question\":\"Why is 3D segmentation of prostate glands important for prostate cancer risk assessment?\",\"answer\":\"Standard Gleason grading is based on morphology in thin 2D sections, which undersamples tissue and can be ambiguous, leading to variability and imperfect outcome correlation. 3D segmentation supports volumetric feature quantification for improved computational prognostic analysis.\"},{\"question\":\"What dataset and staining approach does the method use?\",\"answer\":\"The model uses open-top light-sheet microscopy datasets of human prostate biopsies stained with a fluorescent analog of hematoxylin and eosin (H\\u0026E).\"},{\"question\":\"How does nnU-Net improve over the prior ITAS3D pipeline?\",\"answer\":\"nnU-Net uses previously generated 3D gland masks as training data to enable a direct end-to-end segmentation model. Compared with ITAS3D, it is simpler and faster and maintains good accuracy even with lower-resolution inputs.\"}]","Direct three-dimensional segmentation of prostate glands with nnU-Net | PDF",1790039730,[147,151,155,159],{"page_no":22,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/4f267d9d135350a274d603d804a4218a.webp",983,1272,{"page_no":26,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/0ec86df15d1b6d4bee3b9c2f2d8b4243.webp",982,1270,{"page_no":30,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/aeb55d1e86baee12390fb6a71a25c203.webp",981,1269,{"page_no":33,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/7d2cc57bdd00c8091e97213917462b17.webp",980,1268]