[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-349789-105":59,"doc-detail-349789-en":134},{"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":127,"head_meta":129,"extra_data":131,"updated_unix":133},105,"en","application-of-deep-learning-technology-in-breast-cancer-a-systematic-review-segmentation-detection-and-classification-approaches","Application of deep learning technology in breast cancer - a systematic review - segmentation, detection, and classification approaches","","Objective: provide a critical, clinically oriented synthesis of recent deep learning developments for breast cancer imaging across major modalities, emphasizing model architectures, dataset characteristics, methodological quality, and implications for clinical translation. Methods: PRISMA-guided searches of PubMed, Scopus, Web of Science, ScienceDirect, and Google Scholar for 2020–2024 studies; 65 works using CNNs, Transformers, or hybrid models were included; datasets were profiled and quality assessed using QUADAS-2. Results: CNNs often achieved >90% median accuracy and high Dice/IoU for segmentation; Transformers showed gains with global context and volumetric inputs. Conclusions: current evidence promises early detection and workflow efficiency but is limited by retrospective, single-centre, biased and heterogeneous designs, with insufficient external/prospective validation.",{"@graph":69,"@context":126},[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/application-of-deep-learning-technology-in-breast-cancer-a-systematic-review-segmentation-detection-and-classification-approaches/349789/",{"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/application-of-deep-learning-technology-in-breast-cancer-a-systematic-review-segmentation-detection-and-classification-approaches/349789.png","ImageObject",300,407,{"name":92,"@type":93},"Hazel","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-04","2026-09-22",true,{"@type":102,"interactionType":103,"userInteractionCount":52},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118,122],{"name":109,"@type":110,"acceptedAnswer":111},"What is the study objective?","Question",{"text":112,"@type":113},"To synthesize recent deep learning progress for breast cancer imaging in a clinically oriented, critical way, focusing on architectures, datasets, methodological quality, and translation implications.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How were studies selected and evaluated?",{"text":117,"@type":113},"Using PRISMA guidelines, the authors searched major databases for 2020–2024 publications and included 65 studies; dataset characteristics were profiled and study quality and risk of bias were assessed with QUADAS-2.",{"name":119,"@type":110,"acceptedAnswer":120},"What are the main findings about segmentation, detection, and classification approaches?",{"text":121,"@type":113},"CNN-based systems often achieved high accuracy and strong AUCs for classification and strong Dice/IoU for segmentation using U-Net variants; Transformers and hybrids showed advantages when global context or volumetric/multi-view data mattered.",{"name":123,"@type":110,"acceptedAnswer":124},"What limitations limit clinical readiness according to the review?",{"text":125,"@type":113},"Most included studies were retrospective, single-centre, and class-imbalanced with narrow demographics, heterogeneous reference standards, and limited external or prospective validation, raising concerns about bias, overfitting, fairness, and robustness.","https://schema.org",{"og:url":83,"og:type":128,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":130,"canonical":83},"index,follow",{"doc_id":132,"site_id":62},349789,1790418148,{"code":4,"msg":5,"data":135},{"doc_id":132,"user_id":136,"nickname":92,"user_avatar":137,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":138,"file_id":139,"file_url":140,"file_type":141,"file_size":142,"view_count":52,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":143,"language":144,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":145,"faqs":146,"seo_title":147,"seo_description":67,"update_tm":148,"read_time":149,"preview_page_count":24,"preview_urls":150},137441390410,"https://ap-avatar.wpscdn.com/avatar/2000252f4ab5702993?_k=1776741390130283984","Gao et al. BioMedical Engineering OnLine (2026) 25:19  \n[https://doi.org/10.1186/s12938-025-01502-5](https://doi.org/10.1186/s12938-025-01502-5)  \nBioMedical Engineering OnLine  \nREVIEW Open Access  \nApplication of deep learning technology in breast cancer: a systematic review  \nof segmentation, detection, and classification approaches  \nShuo Gao1,3 , Jia Liu2, Linqian Li3,4,5, Di Yang6, Yafei Miao6, Xu Zhang8, Qianqian Han9, Yasong Shi 1, Jianguo Wu1 and Ke Zhang3,4,5,7*  \n*Correspondence: [93391@qq.com](93391@qq.com)  \n1 Information Center, Affiliated Hospital of Hebei University, Baoding, China  \n2 Medical Affairs Department, Affiliated Hospital of Hebei University, Baoding, China  \n3 Basic Research Key Laboratory of General Surgery for Digital Medicine, Affiliated Hospital of Hebei University, Baoding, China  \n4 Institute of Life Science and Green Development, Hebei University, Baoding, China  \n5 3D Image and 3D Printing Center, Affiliated Hospital of Hebei University, Baoding, China  \n6 Clinical Medical College of Hebei University, Affiliated Hospital of Hebei University, Baoding, China  \n7 Thoracic Surgery Department, Affiliated Hospital of Hebei University, Baoding, China  \n8 Ultrasound Department, Affiliated Hospital of Hebei University, Baoding, China  \n9 Breast Surgery, Affiliated Hospital of Hebei University, Baoding, China  \nAbstract  \nObjective: To provide a critical and clinically oriented synthesis of recent deep learning developments for breast cancer imaging across major modalities, with emphasis on model architectures, dataset characteristics, methodological quality, and implications for clinical translation.  \nMethods: Following PRISMA guidelines, we systematically searched PubMed, Scopus, Web of Science, ScienceDirect, and Google Scholar for studies published from 2020 to 2024 on deep learning applied to breast imaging. Sixty-five studies using convolutional neural networks (CNNs), Transformers, or hybrid architectures were included. Datasets were comparatively profiled, and study quality and risk of bias were appraised using QUADAS-2 .  \nResults: CNN-based classifiers, particularly on mammography and pathology, commonly achieved median accuracies above 90% and AUCs around or above 0 . 95, while CNN detectors reported high sensitivities and mid-90% accuracies, supporting their potential role as second readers. CNN-derived U-Net variants dominated segmentation tasks, yielding high Dice and IoU values for tumour and fibroglandular-tissue delineation. Transformer and hybrid models showed advantages when global context, multi-view inputs or volumetric data were critical (e. g. dense breasts, DBT, DCE-MRI), where they improved lesion localisation and patient-level risk stratification. However, QUADAS-2 and dataset profiling revealed substantial limitations: most studies were retrospective, single-centre and class-imbalanced, with narrow demographic representation, heterogeneous reference standards and scarce external or prospective validation. These factors raise concerns about bias, overfitting, fairness and robustness in realworld deployment. Only a minority of studies systematically addressed interpretability, workflow integration or regulatory requirements.  \nConclusions: Deep learning offers considerable promise to support early detection, risk stratification and workflow efficiency across breast imaging modalities, with CNNsand Transformers providing complementary strengths for local fine-detail versus global contextual modelling. Nevertheless, the current evidence base is constrained  \n© The Author(s) 2025. 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 mat","cbCaidC0dcmpg2R0","https://ap.wps.com/l/cbCaidC0dcmpg2R0","pdf",2503539,48,"English","# Abstract\n## Objective\n## Methods\n## Results\n## Conclusions\n# Keywords\n# Introduction","[{\"question\":\"What is the study objective?\",\"answer\":\"To synthesize recent deep learning progress for breast cancer imaging in a clinically oriented, critical way, focusing on architectures, datasets, methodological quality, and translation implications.\"},{\"question\":\"How were studies selected and evaluated?\",\"answer\":\"Using PRISMA guidelines, the authors searched major databases for 2020–2024 publications and included 65 studies; dataset characteristics were profiled and study quality and risk of bias were assessed with QUADAS-2.\"},{\"question\":\"What are the main findings about segmentation, detection, and classification approaches?\",\"answer\":\"CNN-based systems often achieved high accuracy and strong AUCs for classification and strong Dice/IoU for segmentation using U-Net variants; Transformers and hybrids showed advantages when global context or volumetric/multi-view data mattered.\"},{\"question\":\"What limitations limit clinical readiness according to the review?\",\"answer\":\"Most included studies were retrospective, single-centre, and class-imbalanced with narrow demographics, heterogeneous reference standards, and limited external or prospective validation, raising concerns about bias, overfitting, fairness, and robustness.\"}]","Application of deep learning technology in breast cancer - a systematic review - segmentation, detection, and classification approaches | PDF",1790085580,121,[151,155,159,163,167],{"page_no":8,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/0c7404bfb53ebc44c212fd800a2905c2.webp",983,1305,{"page_no":14,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/ff6cbba5c759b6df33d1bfe158ef8fed.webp",982,1304,{"page_no":81,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/53e88990fced1ac0cc817a216f283477.webp",981,1303,{"page_no":19,"url":164,"width":165,"height":166},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/8f9283006f24c3e0341fe31307f4c41b.webp",980,1301,{"page_no":24,"url":168,"width":169,"height":170},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/0ea31e89b2041a8285e5ded2b1d0f970.webp",979,1300]