[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-340156-105":3,"detail-sidebar-cat-0-en-105":73,"doc-detail-340156-en":122},{"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":66,"head_meta":68,"extra_data":70,"updated_unix":72},105,"en","detection-of-breast-cancer-in-digital-breast-tomosynthesis-with-vision-transformers","Detection of breast cancer in digital breast tomosynthesis with vision transformers","","Digital Breast Tomosynthesis (DBT) enables three-dimensional visualization that improves lesion discernibility and diagnostic precision versus conventional 2D mammography. The study proposes an advanced computer-aided detection system using vision transformers for DBT, extracting attributes from 2D slices and post-processing across neighboring slices to classify the full 3D scan. Trained and validated on 3,831 DBT scans and tested on 685, Swin Transformer outperformed ResNet101 and a vanilla Vision Transformer, achieving AUC 0.934 ± 0.026 at 384×384.",{"@graph":14,"@context":65},[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/detection-of-breast-cancer-in-digital-breast-tomosynthesis-with-vision-transformers/340156/",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/detection-of-breast-cancer-in-digital-breast-tomosynthesis-with-vision-transformers/340156.png","ImageObject",300,407,{"name":42,"@type":43},"Rowan","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-23","2026-09-21",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",10,{"@type":57,"mainEntity":58},"FAQPage",[59],{"name":60,"@type":61,"acceptedAnswer":62},"Which model performed best and under what image resolution?","Question",{"text":63,"@type":64},"The Swin Transformer outperformed ResNet101 and a vanilla Vision Transformer, achieving an AUC of 0.934 ± 0.026 at 384×384 resolution.","Answer","https://schema.org",{"og:url":32,"og:type":67,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":69,"canonical":32},"index,follow",{"doc_id":71,"site_id":7},340156,1790156510,{"code":4,"msg":74,"data":75},"success",[76,80,84,88,93,98,103,107,112,115,118],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":77,"show_sort_weight":78,"slug":79},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":81,"show_sort_weight":82,"slug":83},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Exam",70,"exam",{"id":89,"doc_module":4,"doc_module_name":25,"category_name":90,"show_sort_weight":91,"slug":92},5,"Comic",60,"comic",{"id":94,"doc_module":4,"doc_module_name":25,"category_name":95,"show_sort_weight":96,"slug":97},6,"Technology",50,"technology",{"id":99,"doc_module":4,"doc_module_name":25,"category_name":100,"show_sort_weight":101,"slug":102},7,"Healthcare",40,"healthcare",{"id":104,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":105,"slug":106},8,30,"research-report",{"id":108,"doc_module":4,"doc_module_name":25,"category_name":109,"show_sort_weight":110,"slug":111},9,"Religion & Spirituality",20,"religion-spirituality",{"id":110,"doc_module":4,"doc_module_name":25,"category_name":113,"show_sort_weight":110,"slug":114},"World Cup","world-cup",{"id":55,"doc_module":4,"doc_module_name":25,"category_name":116,"show_sort_weight":55,"slug":117},"Lifestyle","lifestyle",{"id":119,"doc_module":4,"doc_module_name":25,"category_name":120,"show_sort_weight":89,"slug":121},19,"General","general",{"code":4,"msg":74,"data":123},{"doc_id":71,"user_id":124,"nickname":42,"user_avatar":125,"doc_module":4,"category_id":104,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":126,"file_id":127,"file_url":128,"file_type":129,"file_size":130,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":131,"language":132,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":133,"faqs":134,"seo_title":135,"seo_description":12,"update_tm":136,"read_time":105,"preview_page_count":33,"preview_urls":137},1099514067415,"https://ap-avatar.wpscdn.com/avatar/100002539d78ffe74a7?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779092875211072502","[www. nature.com/scientificreports](www. nature.com/scientificreports)  \nOPEN  \nDetection of breast cancer in digital breast tomosynthesis with vision transformers  \nIdan Kassis1􀀍, Dror Lederman2,5, Gal Ben-Arie3,5, Maia Giladi Rosenthal4, Ilan Shelef3 & Yaniv Zigel1,5  \nDigital Breast Tomosynthesis (DBT) has revolutionized more traditional breast imaging through its three-dimensional (3D) visualization capability that significantly enhances lesion discernibility, reduces tissue overlap, and improves diagnostic precision as compared to conventional two-dimensional (2D)  \nmammography. In this study, we propose an advanced Computer-Aided Detection (CAD) system that harnesses the power of vision transformers to augment DBT’s diagnostic efficiency. This scheme uses a neural network to glean attributes from the 2D slices of DBT followed by post-processing that considers features from neighboring slices to categorize the entire 3D scan. By leveraging a transfer learning technique, we trained and validated our CAD framework on a unique dataset consisting of 3,831 DBT scans and subsequently tested it on 685 scans. Of the architectures tested, the Swin Transformer outperformed the ResNet101 and vanilla Vision Transformer. It achieved an impressive AUC score of 0.934 ± 0.026 at a resolution of 384 × 384. Increasing the image resolution from 224 to 384 not only maintained vital image attributes but also led to a marked improvement in performance (p-value = 0.0003). The Mean Teacher algorithm, a semi-supervised method using both labeled and unlabeled DBT slices, showed no significant improvement over the supervised approach. Comprehensive analyses across different lesion types, sizes, and patient ages revealed consistent performance. The integration of attention mechanisms yielded a visual narrative of the model’s decision-making process that highlighted the prioritized regions during assessments. These findings should significantly propel the methodologies employed in DBT image analysis by setting a new benchmark for breast cancer diagnostic precision.  \nBreast cancer ranks as the most prevalent malignancy among women worldwide and imposes a substantial burden on the overall health of the population1,2. About one in eight women will be diagnosed with breast cancer at some point. Early diagnosis is a crucial, pivotal strategy in lessening breast cancer’s overall disease burden and mortality rates, and can prevent deaths through effective detection and state-of-the-art cancer treatment3,4. Therefore, the preventive behaviors and screening programs implemented worldwide are essential to curbing breast cancer incidence rates and initiating early treatment5.  \nMammography, which is currently the predominant screening and diagnostic tool, entails using low-dose X-rays to visualize the breast tissues. It is the prime noninvasive, instrumental method for the early detection of numerous breast cancers6. However, the two-dimensional nature of mammography, as compared to the threedimensional structure of the breast, can make tumor detection difficult, particularly for dense breasts7,8. DBTis an emerging technique that addresses the limitations caused by overlapping structures in mammography9. In DBT, multiple projection views are acquired as the X-ray source moves along a predefined trajectory that typically spans an angular range of 60°. The obtained projection views are reconstructed to provide sections that parallel the breast . Overall, DBT has shown promise in improving the diagnostic accuracy of breast cancer detection in specific subgroups of women, including those with dense breasts10. During standard screening, mammograms and tomosynthesis are typically obtained in the Craniocaudal (CC) and Medial-lateral-oblique (MLO) views to enable a comprehensive examination of the whole breast tissue and increase the potential detection rate for abnormalities11. Nevertheless, the manual interpretation of DBT by radiologists presents inherent limitatio","cbCairyQAW2IZPP4","https://ap.wps.com/l/cbCairyQAW2IZPP4","pdf",2463748,12,"English","# Introduction\n## Background on breast cancer and screening\n## Mammography limitations and the role of DBT\n## CAD and deep learning approaches for DBT","[{\"question\":\"Which model performed best and under what image resolution?\",\"answer\":\"The Swin Transformer outperformed ResNet101 and a vanilla Vision Transformer, achieving an AUC of 0.934 ± 0.026 at 384×384 resolution.\"}]","Detection of breast cancer in digital breast tomosynthesis with vision transformers | PDF",1790034567,[138,142,146,150],{"page_no":22,"url":139,"width":140,"height":141},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/a4a415ec244d65e2cb066bb7e246b4b5.webp",983,1291,{"page_no":26,"url":143,"width":144,"height":145},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/394a2fd2bee57a67f7097f0eeff27ffc.webp",982,1290,{"page_no":30,"url":147,"width":148,"height":149},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/8ad8218aa41d09d250516d7cd44e754c.webp",981,1289,{"page_no":33,"url":151,"width":152,"height":153},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/e2561da09b62bf238a2be795b6dd5a52.webp",980,1287]