[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-346736-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-346736-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","mdpnet-a-multi-scale-difference-perception-network-for-esophageal-cancer-segmentation-in-ct-images","MDPNet: a multi-scale difference perception network for esophageal cancer segmentation in CT images","","Accurate segmentation of esophageal cancers in CT images is crucial for treatment planning but remains challenging due to variable tumor morphology, low contrast against surrounding tissues, and blurred boundaries. The study proposes MDPNet, a Multi-scale Difference Perception Network, combining Dynamic Feature Enhancement for global/local context fusion, Cross-level Difference Modeling to emphasize foreground–background differences, and a Multi-stage Foreground Enhancement scheme for progressive boundary refinement. Results on a self-built ECD 2D dataset and an external test set show superior performance and strong generalization potential, supporting decision-support use.",{"@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/mdpnet-a-multi-scale-difference-perception-network-for-esophageal-cancer-segmentation-in-ct-images/346736/",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/mdpnet-a-multi-scale-difference-perception-network-for-esophageal-cancer-segmentation-in-ct-images/346736.png","ImageObject",300,407,{"name":42,"@type":43},"Eliana","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-11-16","2026-09-22",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",5,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"Why is esophageal cancer segmentation in CT images difficult?","Question",{"text":63,"@type":64},"It is difficult because tumors vary in morphology, have low contrast with surrounding tissues, and exhibit blurred boundaries.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"What are the main components of MDPNet?",{"text":68,"@type":64},"MDPNet includes Dynamic Feature Enhancement for global/local fusion, Cross-level Difference Modeling to highlight foreground–background differences, and Multi-stage Foreground Enhancement to refine boundaries progressively.",{"name":70,"@type":61,"acceptedAnswer":71},"How was MDPNet evaluated and what were the results?",{"text":72,"@type":64},"The method was tested on a self-built ECD 2D dataset and an external test set, achieving Dice coefficients of 0.82 and 0.78 respectively, and demonstrating improved accuracy and generalization.","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},346736,1792209867,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,100,105,110,114,119,122,126],{"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":55,"doc_module":4,"doc_module_name":25,"category_name":97,"show_sort_weight":98,"slug":99},"Comic",60,"comic",{"id":101,"doc_module":4,"doc_module_name":25,"category_name":102,"show_sort_weight":103,"slug":104},6,"Technology",50,"technology",{"id":106,"doc_module":4,"doc_module_name":25,"category_name":107,"show_sort_weight":108,"slug":109},7,"Healthcare",40,"healthcare",{"id":111,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":112,"slug":113},8,30,"research-report",{"id":115,"doc_module":4,"doc_module_name":25,"category_name":116,"show_sort_weight":117,"slug":118},9,"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":55,"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":111,"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},4398048949847,"https://ap-avatar.wpscdn.com/avatar/400002536579ef2da7f?_k=1778318612642679267","Qi et al. BMC Medical Imaging (2026) 26:150 [https://doi.org/10.1186/s12880-026-02213-6](https://doi.org/10.1186/s12880-026-02213-6)  \nBMC Medical Imaging  \nRESEARCH Open Access  \nMDPNet: a multi-scale difference perception  network for esophageal cancer segmentation in CT images  \nFei Qi1, Qian Ye2, Chang Xu3, Jianlin Wang1 and Liugang Gao1*  \nAbstract  \nAccurate segmentation of esophageal cancers in CT images is crucial for disease treatment planning but remains difficult due to variable tumor morphology, low contrast with surrounding tissues, and blurred boundaries. We propose MDPNet, a Multi-scale Difference Perception Network for accurate esophageal cancer segmentation in CT images. MDPNet integrates three key modules, a Dynamic Feature Enhancement (DFE) strategy for global and local context fusion, a Cross-level Difference Modeling (CDM) module to highlight foreground–background differences, and a Multi-stage Foreground Enhancement (MFE) mechanism for progressive boundary refinement. Experiments on the self-built ECD 2D dataset and an external test set show that MDPNet achieves the best performance among state-of-the-art methods, with Dice coefficients of 0.82 and 0. 78, respectively. MDPNet effectively improves segmentation accuracy and generalization, demonstrating preliminary generalization capability on our multi-center test sets, suggesting its potential as a decision-support tool.  \nKeywords Esophageal cancer segmentation, Medical image segmentation, Multi-scale features, Difference perception, CT images  \nIntroduction  \nCurrently, esophageal cancer is one of the deadliest cancers worldwide, ranking seventh among the leading causes of cancer-related deaths [1]. Early symptoms of esophageal cancer are often subtle, and without regular health screenings, many patients do not receive timely treatment. Therefore, early diagnosis and precise treatment are crucial for improving patient survival rates [2].  \n*Correspondence:  \nLiugang Gao  \n[gaoliugang@126.com](gaoliugang@126.com)  \n1Center of Medical Physics, The Second People’s Hospital of Changzhou, The Third Affiliated Hospital of Nanjing Medical University, Changzhou, Jiangsu 213003, China  \n2College of Information Science and Engineering, Hohai University, Changzhou, Jiangsu 213200, China  \n3Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, Shanghai 201210, China  \nThe primary treatment for esophageal cancer is radiotherapy [3]. However, the most critical step in radiotherapy is to accurately delineate the treatment field, i.e., the gross tumor volume (GTV) [4]. As a non-invasive imaging technique, CT is widely used in the detection, quantitative assessment, and treatment planning of esophageal cancer due to its clear visualization of organ morphology [5, 6]. To locate the tumor target area before radiotherapy, doctors first need to determine the tumor’s location and the normal organs that need protection based on CT images taken during the venous phase. They then need to precisely outline the tumor target volume before proceeding with radiation therapy planning. Therefore, accurate delineation of tumor target volume is not only critical for disease assessment and treatment planning, but also directly impacts the reliability of downstream automated diagnostic and treatment processes [7, 8].  \n© The Author(s) 2026. Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commo","cbCaid0lAYbIAHi6","https://ap.wps.com/l/cbCaid0lAYbIAHi6","pdf",7568840,15,"English","# Abstract\n# Introduction","[{\"question\":\"Why is esophageal cancer segmentation in CT images difficult?\",\"answer\":\"It is difficult because tumors vary in morphology, have low contrast with surrounding tissues, and exhibit blurred boundaries.\"},{\"question\":\"What are the main components of MDPNet?\",\"answer\":\"MDPNet includes Dynamic Feature Enhancement for global/local fusion, Cross-level Difference Modeling to highlight foreground–background differences, and Multi-stage Foreground Enhancement to refine boundaries progressively.\"},{\"question\":\"How was MDPNet evaluated and what were the results?\",\"answer\":\"The method was tested on a self-built ECD 2D dataset and an external test set, achieving Dice coefficients of 0.82 and 0.78 respectively, and demonstrating improved accuracy and generalization.\"}]","MDPNet: a multi-scale difference perception network for esophageal cancer segmentation in CT images | PDF",1790062601,38,[147,151,155,159],{"page_no":22,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/25119c6f2092c741dd39d815f65d8814.webp",983,1310,{"page_no":26,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/3719de7d73dad9c737be211b8778800a.webp",982,1309,{"page_no":30,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/8025ef12ed512016cb8bc01b668b3b30.webp",981,1308,{"page_no":33,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/2c7a31aeebe53593ccbbce462b024c95.webp",980,1306]