[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-336430-105":59,"doc-detail-336430-en":131},{"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":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","using-multi-label-ensemble-cnn-classifiers-to-mitigate-labelling-inconsistencies-in-patch-level-gleason-grading","Using multi-label ensemble CNN classifiers to mitigate labelling inconsistencies in patch-level Gleason grading","","This paper presents a multi-label ensemble deep-learning approach to improve patch-level Gleason grading accuracy in prostate histopathology images, targeting label inconsistencies in the SICAPv2 dataset caused by majority voting on patch labels. The method combines three one-vs-all deep models to learn diverse visual features and predict the presence of Gleason grades G3, G4, and G5 for each patch. Transfer learning fine-tunes a ResNet18 variant selected via extensive ablation, achieving at least 14% higher accuracy and 4% higher F1-score than prior single-label classifiers.",{"@graph":69,"@context":123},[70,84,106],{"@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/using-multi-label-ensemble-cnn-classifiers-to-mitigate-labelling-inconsistencies-in-patch-level-gleason-grading/336430/",{"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/using-multi-label-ensemble-cnn-classifiers-to-mitigate-labelling-inconsistencies-in-patch-level-gleason-grading/336430.png","ImageObject",300,407,{"name":92,"@type":93},"Maeve","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-14","2026-09-21",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",13,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What problem does the study address in Gleason grading?","Question",{"text":113,"@type":114},"The study addresses prevalent label inconsistencies in the SICAPv2 prostate dataset, where patch-level labels are produced via a majority voting scheme.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How does the proposed model mitigate label inconsistencies?",{"text":118,"@type":114},"It uses a multi-label ensemble of three one-vs-all deep learning models to learn diverse features and predict the presence of Gleason grades G3, G4, and G5 for each patch.",{"name":120,"@type":111,"acceptedAnswer":121},"What CNN architecture and training strategy are used?",{"text":122,"@type":114},"The approach employs transfer learning to fine-tune a ResNet18 CNN variant, chosen after an extensive ablation study.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},336430,1790445487,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":145,"read_time":26,"preview_page_count":19,"preview_urls":146},5909877438554,"https://ap-avatar.wpscdn.com/avatar/5600025385ad2bf12a7?_k=1778553567797529272","PLOS ONE  \nOPEN ACCESS  \nCitation: Butt MA, Kaleem MF, Bilal M, Hanif MS (2024) Using multi-label ensemble CNN classifiersto mitigate labelling inconsistencies in patch-level Gleason grading. PLoS ONE 19(7): e0304847 .  \n[https://doi.org/10.1371/journal.pone.0304847](https://doi.org/10.1371/journal.pone.0304847)  \n[Editor:](Editor: Hadeel K)[ Hadeel K](Editor: Hadeel K). Aljobouri, Al-Nahrain University, IRAQ  \nReceived: March 1, 2024  \nAccepted: May 21, 2024  \nPublished: July 5, 2024  \nPeer Review History: PLOS recognizes the benefits of transparency in the peer review process; therefore, we enable the publication of all of the content of peer review and author responses alongside final, published articles. The editorial history of this article is available here:  \n[https://doi.org/10.1371/journal.pone.0304847](https://doi.org/10.1371/journal.pone.0304847)  \n[Copyright:](Copyright:) © [2024](2024) Butt 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: Publicly available datasets were analyzed in this study. This data can be found here: [https://data.mendeley.com/](https://data.mendeley.com/)[ ](https://data.mendeley.com/)[datasets/9xxm58dvs3/2](datasets/9xxm58dvs3/2 The results presented in)[ The results presented in](datasets/9xxm58dvs3/2 The results presented in)[ ](datasets/9xxm58dvs3/2 The results presented in)this paper can be reproduced through the source  \nRESEARCH ARTICLE  \nUsing multi-label ensemble CNN classifiers to mitigate labelling inconsistencies in patchlevel Gleason grading  \nMuhammad Asim Butt1 *, Muhammad Farhat Kaleem2, Muhammad Bilal3,4, Muhammad Shehzad Hanif3,4  \n1 Department of Electrical Engineering, University of Management and Technology, Lahore, Pakistan,  \n2 School of Engineering, University of Management and Technology, Lahore, Pakistan, 3 Center of Excellence in Intelligent Engineering Systems, King Abdulaziz University, Jeddah, Saudi Arabia,  \n4 Department of Electrical and Computer Engineering, King Abdulaziz University, Jeddah, Saudi Arabia  \n* [asim.butt@umt.edu.pk](asim.butt@umt.edu.pk)  \nAbstract  \nThis paper presents a novel approach to enhance the accuracy of patch-level Gleason grading in prostate histopathology images, a critical task in the diagnosis and prognosis of prostate cancer. This study shows that the Gleason grading accuracy can be improved by addressing the prevalent issue of label inconsistencies in the SICAPv2 prostate dataset, which employs a majority voting scheme for patch-level labels. We propose a multi-label ensemble deep-learning classifier that effectively mitigates these inconsistencies and yields more accurate results than the state-of-the-art works. Specifically, our approach leverages the strengths of three different one-vs-all deep learning models in an ensemble to learn diverse features from the histopathology images to individually indicate the presence of one or more Gleason grades (G3, G4, and G5) in each patch. These deep learning models have been trained using transfer learning to fine-tune a variant of the ResNet18 CNN classifier chosen after an extensive ablation study. Experimental results demonstrate that our multilabel ensemble classifier significantly outperforms traditional single-label classifiers reported in the literature by at least 14% and 4% on accuracy and f1-score metrics respectively. These results underscore the potential of our proposed machine learning approach to improve the accuracy and consistency of prostate cancer grading.  \nIntroduction  \nProstate cancer is one of the most common types of cancer in men, posing significant challenges in diagnosis and treatment. Traditional diagnostic methods, such as biopsy followed by histopathological examination, are invasive and subject to inter-observer variability. With t","cbCaisGH7gNVB5tR","https://ap.wps.com/l/cbCaisGH7gNVB5tR","pdf",3162662,24,"English","# Abstract\n# Introduction","[{\"question\":\"What problem does the study address in Gleason grading?\",\"answer\":\"The study addresses prevalent label inconsistencies in the SICAPv2 prostate dataset, where patch-level labels are produced via a majority voting scheme.\"},{\"question\":\"How does the proposed model mitigate label inconsistencies?\",\"answer\":\"It uses a multi-label ensemble of three one-vs-all deep learning models to learn diverse features and predict the presence of Gleason grades G3, G4, and G5 for each patch.\"},{\"question\":\"What CNN architecture and training strategy are used?\",\"answer\":\"The approach employs transfer learning to fine-tune a ResNet18 CNN variant, chosen after an extensive ablation study.\"}]","Using multi-label ensemble CNN classifiers to mitigate labelling inconsistencies in patch-level Gleason grading | PDF",1790015024,[147,151,155,159],{"page_no":8,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/aa6291a5fac0f963e88002adda852f77.webp",983,1272,{"page_no":14,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/dc8fa427cbeecb977293fd76981cd88f.webp",982,1270,{"page_no":81,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/4fcb34ec7e5eb3b98fd719a8774ae051.webp",981,1269,{"page_no":19,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/a745c1a2c505dce13ea44d4ba2a10895.webp",980,1268]