[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85840-en":3,"doc-seo-85840-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},85840,8796095461610,"Oliver","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","BiLoG-Net: A Bi-Context Location-Guided Network for Breast Mass Segmentation and Malignancy Classification in Mammography","Breast cancer remains the most commonly diagnosed malignancy among women worldwide, while accurate detection and characterization of breast masses in mammography is hindered by subtle intensity variations, heterogeneous tissue densities, and indistinct lesion boundaries. BiLoG-Net addresses these issues with a deep learning framework that jointly performs segmentation and malignancy classification via bi-context location-aware feature modeling and segmentation-guided attention. A tightly coupled multi-task design reduces error propagation by reinforcing pixel-level localization and image-level diagnosis. Evaluated on CBIS-DDSM and INBreast, it achieves Dice scores of 94.20% and 93.10%, classification accuracies of 95.20% and 93.60%, and AUC values of 97.10% and 96.00%.","arXiv :2607 . 10188v1 [ cs .CV] 11 Jul 2026  \n[http://doi.org/10.32604/cmes.2026.000000](http://doi.org/10.32604/cmes.2026.000000)  \nARTICLE  \nBiLoG-Net: A Bi-Context Location-Guided Network for Breast Mass Segmentation and Malignancy Classification in Mammography  \nAbu Fatema Mohammad Abdun Noor 1,5 , Md Imam Ahasan2,5 , Md Samiul Ahasan3 , Kah Ong Michael Goh4,* , S M Hasan Mahmud1,* , Raihana Zannat6  \n1Department of Software Engineering, Daffodil International University, Dhaka, Bangladesh  \n2 College of Computer Science, Chongqing University, Chongqing, China  \n3School of Computer Science and Technology, Xidian University, Xi’an, China  \n4 Center for Image and Vision Computing, COE for Artificial Intelligence, Faculty of Information Science & Technology, Multimedia University, Jalan Ayer Keroh Lama, Melaka, 75450 Malaysia  \n5BricksCloud AI, Uttara, Dhaka, Bangladesh  \n6Department of Information and Communication Technology, Mawlana Bhashani Science & Technology University  \n*[Corresponding Authors: Kah Ong Michael Goh. Email: michael.goh@mmu.edu.my](Corresponding Authors: Kah Ong Michael Goh. Email: michael.goh@mmu.edu.my); S M Hasan Mahmud. Email: [drhasan.swe@diu.edu.bd](drhasan.swe@diu.edu.bd)  \nVersion July 14, 2026 submitted to Comput Model Eng Sci  \nABSTRACT: Breast cancer remains the most commonly diagnosed malignancy among women worldwide, yet accurate detection and characterization of breast masses in mammography remain challenging due to subtle intensity variations, heterogeneous tissue densities, and indistinct lesion boundaries that complicate radiological interpretation. To address these limitations, we propose BiLoG-Net, a deep learning framework that jointly performs breast mass segmentation and malignancy classification through bi-context location-aware feature modeling and segmentation-guided attention mechanisms. Our architecture integrates a novel encoder-decoder paradigm with Fire-based feature extraction, lightweight global and local feature enhancement modules, and adaptive location-aware gating to simultaneously capture long-range contextual dependencies and fine-grained boundary-sensitive details. Unlike conventional multi-stage pipelines, our tightly coupled multi-task design enables mutual reinforcement between pixel-level localization and image-level diagnosis, reducing error propagation while producing spatially grounded malignancy predictions. Evaluated on CBIS-DDSM and INBreast benchmarks, BiLoG-Net achieves state-of-the-art performance with Dice scores of 94.20% and 93.10%, classification accuracies of 95.20% and 93.60%, and AUC values of 97.10% and 96.00%, respectively, substantially outperforming existing CNN and transformer-based baselines. By combining precise boundary delineation with reliable malignancy assessment in a single end-to-end model, this work holds strong potential for clinical computer-aided detection systems, helping radiologists prioritize suspicious cases and improve screening efficiency in busy clinical settings.  \nKEYWORDS: Mammography; breast cancer detection; U-Net; multi-task learning; computer-aided diagnosis.  \n1 Introduction  \nThe latest official data shows that breast cancer is now more common than lung cancer. Breast cancer is the primary cause of cancer mortality among females. By 2026 [1], breast, bowel, and lung cancers will bethe most frequently diagnosed kinds of cancer in American women. Since peaking in 1989 [2], the incidence of breast cancer deaths in women has decreased by 43% . The annual decrease in breast cancer mortality fell  \n© 2026 by the Authors. Submitted to Comput Model Eng Sci for under a Creative Commons Attribution 4.0 International License, which permitted unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.  \nby approximately 2–3% in the 1990 s to 1% in 2024 [3] . Non-invasive breast cancer may remain localized inside a particular organ or structure, such as a duct or lobule, with","cbCaibaH7Ev3Fjje","https://ap.wps.com/l/cbCaibaH7Ev3Fjje","pdf",7108798,2,1,23,"English","en",105,"# Introduction\n## Breast cancer background and clinical challenges\n# Proposed Method\n## BiLoG-Net joint segmentation and classification framework\n# Experiments and Results\n## Benchmarks and performance metrics","[{\"question\":\"What problem does BiLoG-Net target in mammography?\",\"answer\":\"BiLoG-Net targets accurate breast mass segmentation and malignancy classification despite subtle intensity variations, heterogeneous tissue densities, and unclear lesion boundaries that complicate radiological interpretation.\"},{\"question\":\"How does BiLoG-Net combine segmentation and malignancy classification?\",\"answer\":\"It uses a tightly coupled multi-task design that jointly performs pixel-level localization and image-level diagnosis, using bi-context location-aware feature modeling and segmentation-guided attention to enable mutual reinforcement and reduce error propagation.\"},{\"question\":\"What performance did BiLoG-Net achieve on CBIS-DDSM and INBreast?\",\"answer\":\"On CBIS-DDSM it reaches Dice 94.20% and  classification accuracy 95.20% with AUC 97.10%, and on INBreast it reaches Dice 93.10% and classification accuracy 93.60% with AUC 96.00%, outperforming cited CNN and transformer baselines.\"}]",1784206633,58,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"bilog-net-a-bi-context-location-guided-network-for-breast-mass-segmentation-and-malignancy-classification-in-mammography","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,47,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":20},"https://docshare.wps.com/document/","Document",{"item":48,"name":12,"@type":43,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/bilog-net-a-bi-context-location-guided-network-for-breast-mass-segmentation-and-malignancy-classification-in-mammography/85840/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-26","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does BiLoG-Net target in mammography?","Question",{"text":75,"@type":76},"BiLoG-Net targets accurate breast mass segmentation and malignancy classification despite subtle intensity variations, heterogeneous tissue densities, and unclear lesion boundaries that complicate radiological interpretation.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does BiLoG-Net combine segmentation and malignancy classification?",{"text":80,"@type":76},"It uses a tightly coupled multi-task design that jointly performs pixel-level localization and image-level diagnosis, using bi-context location-aware feature modeling and segmentation-guided attention to enable mutual reinforcement and reduce error propagation.",{"name":82,"@type":73,"acceptedAnswer":83},"What performance did BiLoG-Net achieve on CBIS-DDSM and INBreast?",{"text":84,"@type":76},"On CBIS-DDSM it reaches Dice 94.20% and  classification accuracy 95.20% with AUC 97.10%, and on INBreast it reaches Dice 93.10% and classification accuracy 93.60% with AUC 96.00%, outperforming cited CNN and transformer baselines.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]