[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-335631-105":59,"doc-detail-335631-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","masked-image-modeling-meets-self-distillation-a-transformer-based-prostate-gland-segmentation-framework-for-pathology-slides","Masked Image Modeling Meets Self-Distillation - A Transformer-Based Prostate Gland Segmentation Framework for Pathology Slides","","Prostate cancer grading depends on accurate analysis of whole-slide pathology images, where gland-level morphology and growth patterns guide Gleason scoring. Reliable prostate gland segmentation remains limited because manual annotation is impractical for large whole-slide images and automated methods still struggle to capture gland-specific representations. This study proposes a dual-path Swin Transformer U-Net segmentation framework using masked image modeling for self-supervised pretraining and tumor-guided self-distillation to fuse tumor patch labels into the encoder. Training uses heterogeneous biopsy and surgical specimens and is evaluated on PANDA and SICAPv2.",{"@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/masked-image-modeling-meets-self-distillation-a-transformer-based-prostate-gland-segmentation-framework-for-pathology-slides/335631/",{"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/masked-image-modeling-meets-self-distillation-a-transformer-based-prostate-gland-segmentation-framework-for-pathology-slides/335631.png","ImageObject",300,407,{"name":92,"@type":93},"Clementine","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-27","2026-09-21",true,{"@type":102,"interactionType":103,"userInteractionCount":29},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"Why is prostate gland segmentation important for prostate cancer analysis?","Question",{"text":112,"@type":113},"Gland segmentation supports grading and downstream machine learning tasks by providing quantitative, gland-focused representations instead of relying on cell-level or manually defined regions of interest.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does the proposed framework learn without extensive human annotation?",{"text":117,"@type":113},"It uses masked image modeling for large-scale self-supervised pretraining, uniting heterogeneous biopsy and surgical data to improve generalization.",{"name":119,"@type":110,"acceptedAnswer":120},"What is tumor-guided self-distillation in this work?",{"text":121,"@type":113},"A self-distillation step uses binary tumor labels at the patch level to fuse tumor information into the encoder, making it more suitable for the gland segmentation task.","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},335631,1790143740,{"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":29,"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":41,"preview_page_count":4},1374391974564,"https://ap-avatar.wpscdn.com/avatar/14000253aa45c000a9e?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779874745381141002","cancers   \nArticle  \nMasked Image Modeling Meets Self-Distillation: A Transformer-Based Prostate Gland Segmentation Framework for Pathology Slides  \nHaoyue Zhang 1, Sushant Patkar 1, Rosina Lis 1, Maria J. Merino 2, Peter A. Pinto 3, Peter L. Choyke 1, Baris Turkbey 1 and Stephanie Harmon 1, *  \nCitation: Zhang, H.; Patkar, S.; Lis, R.; Merino, M.J.; Pinto, P.A.; Choyke, P.L.; Turkbey, B.; Harmon, S. Masked Image Modeling Meets SelfDistillation: A Transformer-Based Prostate Gland Segmentation Framework for Pathology Slides. Cancers 2024, 16, 3897. [https://](https://)[ ](https://)[doi.org/10.3390/cancers16233897](doi.org/10.3390/cancers16233897)  \nAcademic Editor: José I. López  \nReceived: 16 October 2024  \nRevised: 14 November 2024  \nAccepted: 19 November 2024  \nPublished: 21 November 2024  \nCopyright: © 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) .  \n1 Artificial Intelligence Resource, Molecular Imaging Branch, National Cancer Institute, Bethesda, MD 20814, USA; [harry.zhang@nih.gov](harry.zhang@nih.gov) (H.Z.); [sushant.patkar@nih.gov](sushant.patkar@nih.gov) (S.P.); [rosina.lis@nih.gov](rosina.lis@nih.gov) (R.L.); [pchoyke@nih.gov](pchoyke@nih.gov) (P.L.C.); [ismail.turkbey@nih.gov](ismail.turkbey@nih.gov) (B.T.)  \n2 Translational Surgical Pathology Section, National Cancer Institute, National Institutes of Health, Bethesda, MD 20814, USA; [mjmerino@mail.nih.gov](mjmerino@mail.nih.gov)  \n3 Urologic Oncology Branch, National Cancer Institute, National Institutes of Health, Bethesda, MD 20814, USA; [pintop@mail.nih.gov](pintop@mail.nih.gov)  \n* Correspondence: [stephanie.harmon@nih.gov](stephanie.harmon@nih.gov)  \nSimple Summary: The accurate characterization of prostate cancer glands is vital for diagnosis and grading, and the segmentation of these glands is critical for quantitative analysis and machine learning models. Human annotation is unrealistic given the size of whole-slide images, yet there lacksa reliable fully automated segmentation framework. This study addressed the limitations of previous state-of-the-art approaches reported on this task, popular segmentation frameworks, and foundational models. Our proposed framework leverages the strength of self-supervised and self-distillation to achieve a high segmentation performance, offering a reliable prostate gland segmentation to pave the way for better downstream analysis of whole-slide images.  \nAbstract: Detailed evaluation of prostate cancer glands is an essential yet labor-intensive step in grading prostate cancer. Gland segmentation can serve as a valuable preliminary step for machinelearning-based downstream tasks, such as Gleason grading, patient classification, cancer biomarker building, and survival analysis. Despite its importance, there is currently a lack of a reliable gland segmentation model for prostate cancer. Without accurate gland segmentation, researchers rely on celllevel or human-annotated regions of interest for pathomic and deep feature extraction. This approach is sub-optimal, as the extracted features are not explicitly tailored to gland information. Although foundational segmentation models have gained a lot of interest, we demonstrated the limitations of this approach. This work proposes a prostate gland segmentation framework that utilizes a dual-path Swin Transformer UNet structure and leverages Masked Image Modeling for large-scale self-supervised pretaining. A tumor-guided self-distillation step further fused the binary tumor labels of each patch to the encoder to ensure the encoders are suitable for the gland segmentation step. We united heterogeneous data sources for self-supervised training, including biopsy and surgical specimens, to ref","cbCaia5RJ53PLbD7","https://ap.wps.com/l/cbCaia5RJ53PLbD7","pdf",6808822,12,"English","# Simple Summary\n# Abstract\n# Keywords\n# 1. Introduction","[{\"question\":\"Why is prostate gland segmentation important for prostate cancer analysis?\",\"answer\":\"Gland segmentation supports grading and downstream machine learning tasks by providing quantitative, gland-focused representations instead of relying on cell-level or manually defined regions of interest.\"},{\"question\":\"How does the proposed framework learn without extensive human annotation?\",\"answer\":\"It uses masked image modeling for large-scale self-supervised pretraining, uniting heterogeneous biopsy and surgical data to improve generalization.\"},{\"question\":\"What is tumor-guided self-distillation in this work?\",\"answer\":\"A self-distillation step uses binary tumor labels at the patch level to fuse tumor information into the encoder, making it more suitable for the gland segmentation task.\"}]","Masked Image Modeling Meets Self-Distillation - A Transformer-Based Prostate Gland Segmentation Framework for Pathology Slides | PDF",1790011721]