[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-345476-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-345476-en":130},{"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","two-step-ensemble-convolutional-neural-networks-for-colonoscopic-biopsy-classification-resembling-pathologists-process","Two-Step Ensemble Convolutional Neural Networks for Colonoscopic Biopsy Classification Resembling Pathologists’ Process","","Colorectal cancer remains a leading cause of cancer mortality globally, making early detection via colonoscopy crucial. The article proposes a full ensemble deep-learning pipeline for classifying five diagnostic categories from colonoscopic biopsy whole slide images. A total of 18,922 labeled CRC WSIs support two models: a clustering-constrained attention multiple instance learning approach for multi-class tumor-related lesions and EfficientNet to separate non-tumor from hyperplastic polyps in a two-step workflow.",{"@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/two-step-ensemble-convolutional-neural-networks-for-colonoscopic-biopsy-classification-resembling-pathologists-process/345476/",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/two-step-ensemble-convolutional-neural-networks-for-colonoscopic-biopsy-classification-resembling-pathologists-process/345476.png","ImageObject",300,407,{"name":42,"@type":43},"Theodore","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-29","2026-09-22",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",9,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What is the main goal of the proposed method?","Question",{"text":63,"@type":64},"To classify five colorectal cancer diagnostic categories from colonoscopic biopsy whole slide images using an ensemble deep-learning pipeline resembling pathologists’ analysis.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How was the dataset prepared for training?",{"text":68,"@type":64},"A dataset of 18,922 CRC whole slide images was collected and labeled into non-tumor, hyperplastic polyp, adenoma, adenocarcinoma, and neuroendocrine tumor categories.",{"name":70,"@type":61,"acceptedAnswer":71},"What performance does the ensemble pipeline achieve?",{"text":72,"@type":64},"The model reports micro-, macro-, and weighted-F1-scores of 86.57%, 83.83%, and 86.86%, with neuroendocrine tumor classification achieving an F1-score of 87.18%.","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},345476,1790530416,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,115,119,122,126],{"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":55,"doc_module":4,"doc_module_name":25,"category_name":116,"show_sort_weight":117,"slug":118},"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":25,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":97,"slug":129},19,"General","general",{"code":4,"msg":82,"data":131},{"doc_id":79,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":112,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":139,"language":140,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":12,"update_tm":144,"read_time":145,"preview_page_count":33,"preview_urls":146},7971461740886,"https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2","J Korean Med Sci. 2026 May 25;41(20):e152 [https://doi.org/10.3346/jkms.2026.41.e152](https://doi.org/10.3346/jkms.2026.41.e152)[ ](https://doi.org/10.3346/jkms.2026.41.e152)eISSN 1598-6357·pISSN 1011-8934  \nOriginal Article  \nGastroenterology & Hepatology  \nReceived: Mar 20, 2025  \nAccepted: Aug 26, 2025  \nPublished online: Apr 9, 2026  \nAddress for Correspondence:  \nYosep Chong, MD, PhD  \nDepartment of Hospital Pathology, Uijeongbu St. Mary’s Hospital, College of Medicine, The Catholic University of Korea, 271 Cheonbo-ro, Uijeongbu 11765, Republic of Korea. [Email: ychong@catholic.ac.kr](Email: ychong@catholic.ac.kr)  \n© 2026 The Korean Academy of Medical Sciences.  \nThis is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License ([https://](https://)[ ](https://)[creativecommons.org/licenses/by-nc/4.0/](creativecommons.org/licenses/by-nc/4.0/)) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.  \nORCID iDs  \nHongjun Yoon  [https://orcid.org/0000-0002-4723-327X](https://orcid.org/0000-0002-4723-327X)[ ](https://orcid.org/0000-0002-4723-327X)Mohammad Rizwan Alam  [https://orcid.org/0000-0003-0147-4446](https://orcid.org/0000-0003-0147-4446)[ ](https://orcid.org/0000-0003-0147-4446)Nishant Thakur  [https://orcid.org/0000-0001-8761-0837](https://orcid.org/0000-0001-8761-0837)[ ](https://orcid.org/0000-0001-8761-0837)Sohyun Jeong  [https://orcid.org/0009-0002-8733-8567](https://orcid.org/0009-0002-8733-8567)[ ](https://orcid.org/0009-0002-8733-8567)Gisu Hwang  [https://orcid.org/0000-0003-1046-9286](https://orcid.org/0000-0003-1046-9286)[ ](https://orcid.org/0000-0003-1046-9286)Eun Jung Lee  [https://orcid.org/0000-0002-0931-9662](https://orcid.org/0000-0002-0931-9662)[ ](https://orcid.org/0000-0002-0931-9662)Yosep Chong  [https://orcid.org/0000-0001-8615-3064](https://orcid.org/0000-0001-8615-3064)  \nTwo-Step Ensemble Convolutional Neural Networks for Colonoscopic Biopsy Classification Resembling Pathologists’ Process  \nHongjun Yoon ,1 Mohammad Rizwan Alam ,2 Nishant Thakur ,2  \nSohyun Jeong ,1 Gisu Hwang ,1 Eun Jung Lee ,2,3 and Yosep Chong  2  \n1AI Lab, Deepnoid Inc., Seoul, Korea  \n2Department of Hospital Pathology, College of Medicine, The Catholic University of Korea, Seoul, Korea 3Department of Pathology, Shinwon Medical Foundation, Gwangmyeong, Korea  \nABSTRACT  \nBackground: Colorectal cancer (CRC) is a leading cause of mortality worldwide, and early examination via colonoscopy is increasingly used to prevent CRC mortality. Recently, studies have attempted utilizing artificial intelligence for the classification of CRC. However, datasets were limited in these studies, and the limited number of findings resulting from these studies are not specific to cancerous or noncancerous findings. We present a full pipeline of ensemble deep learning approach to classify five diagnostic categories. Through this pipeline, whole slide images (WSIs) exhibiting low quality can be filtered out before being processed by the computer-aided diagnosis system.  \nMethods: A dataset of 18,922 CRC WSIs collected and labeled as non-tumor, hyperplastic polyp, adenoma, adenocarcinoma, and neuroendocrine tumor (NET, carcinoid) . We developed two models: clustering-constrained attention multiple instance learning model was used to classify adenocarcinomas, adenomas, NET, and non-dysplastic lesion classes. EfficientNet then distinguished between non-tumor and hyperplastic polyp for WSIs classified as non-dysplastic lesion class in the first step.  \nResults: The proposed ensemble pipeline, which resembles the process of analysis from the pathologists, showed better performance even with multiple classes CRC. The micro-, macro-, and weighted-F1-scores were 86.57%, 83.83%, and 86.86%, respectively. Notably, the NET classification tasks scored an F1-score of 87.18% .  \nConclusion: The proposed ensemble model addresse","cbCaioSasNETXJBe","https://ap.wps.com/l/cbCaioSasNETXJBe","pdf",6954035,17,"English","# Abstract\n## Background\n## Methods\n## Results\n## Conclusion\n# Introduction\n# Funding\n# Disclosure\n# Data Availability Statement\n# Author Contributions\n# Keywords","[{\"question\":\"What is the main goal of the proposed method?\",\"answer\":\"To classify five colorectal cancer diagnostic categories from colonoscopic biopsy whole slide images using an ensemble deep-learning pipeline resembling pathologists’ analysis.\"},{\"question\":\"How was the dataset prepared for training?\",\"answer\":\"A dataset of 18,922 CRC whole slide images was collected and labeled into non-tumor, hyperplastic polyp, adenoma, adenocarcinoma, and neuroendocrine tumor categories.\"},{\"question\":\"What performance does the ensemble pipeline achieve?\",\"answer\":\"The model reports micro-, macro-, and weighted-F1-scores of 86.57%, 83.83%, and 86.86%, with neuroendocrine tumor classification achieving an F1-score of 87.18%.\"}]","Two-Step Ensemble Convolutional Neural Networks for Colonoscopic Biopsy Classification Resembling Pathologists’ Process | PDF",1790057776,43,[147,151,155,159],{"page_no":22,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/5a7ce325ed9449b458f0d2d89e4ec5ea.webp",983,1310,{"page_no":26,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/3b1c9e043225296f1025e92596020735.webp",982,1309,{"page_no":30,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/55b1c4fb09dec67b979c3e79fcbff12b.webp",981,1308,{"page_no":33,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/f330441793a27886e561be284e4ba53c.webp",980,1306]