[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-333967-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-333967-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","swinunecct-bidirectional-hashbased-agent-transformer-for-cervical-cancer-mri-image-multitask-learning","SwinUNeCCt: bidirectional hashbased agent transformer for cervical cancer MRI image multitask learning","","SwinUNeCCt is proposed to enable accurate cervical cancer lesion segmentation from dynamic contrast-enhanced MRI while reducing manual workload and subjectivity. The work builds a pathology-validated dataset from 122 patients, each with 100 pelvic MRI scans, annotated by medical professionals. The model introduces a bidirectional hash-based agent multi-head self-attention to better connect local and global MRI features and lowers attention complexity. Compared with state-of-the-art 3D models, it achieves the top performance in segmentation metrics (HD95 6.25, IoU 0.669, DSC 0.802) and maintains computational efficiency (442.7 GFLOPs, 71.2M parameters), with strong results for both segmentation-only and segmentation-plus-classification settings.",{"@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/swinunecct-bidirectional-hashbased-agent-transformer-for-cervical-cancer-mri-image-multitask-learning/333967/",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/swinunecct-bidirectional-hashbased-agent-transformer-for-cervical-cancer-mri-image-multitask-learning/333967.png","ImageObject",300,407,{"name":42,"@type":43},"River Wang","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-11-04","2026-09-21",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},"Why is automatic cervical cancer MRI segmentation needed?","Question",{"text":63,"@type":64},"Manual segmentation of MRI lesions is time-consuming and subjective, and accurate delineation is important for lesion volume measurement, radiotherapy targeting, surgical planning, and radiomics analysis.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How is the dataset for the study constructed?",{"text":68,"@type":64},"The MRI data come from cervical cancer patients diagnosed by pathology. Strict inclusion/exclusion criteria are applied, and the dataset includes 122 patients with 100 pelvic dynamic contrast-enhanced MRI scans per patient, with annotations completed by medical professionals.",{"name":70,"@type":61,"acceptedAnswer":71},"What key components distinguish SwinUNeCCt?",{"text":72,"@type":64},"SwinUNeCCt uses a bidirectional hash-based agent multi-head self-attention to optimize interactions between local and global features, and it reduces the computational complexity of the self-attention mechanism.","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},333967,1790173819,{"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":4},1099514067438,"https://ap-avatar.wpscdn.com/avatar/100002539ee87300030?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780474512215547542","[www. nature.com/scientificreports](www. nature.com/scientificreports)  \nOPEN  \nSwinUNeCCt: bidirectional hashbased agent transformer for cervical cancer MRI image multitask learning  \nChongshuangYang1,2,7, Zhuoyi Tan3,7􀀍, YiJie Wang4, Ran Bi5, Tianliang Shi1, Jing Yang1, Chao Huang1, Peng Jiang1 & Xiangyang Fu6  \nCervical cancer is the fourth most common malignant tumor among women globally, posing a significant threat to women’s health. In 2022, approximately 600,000 new cases were reported, and 340,000 deaths occurred due to cervical cancer. Magnetic resonance imaging (MRI) is the preferred imaging method for diagnosing, staging, and evaluating cervical cancer. However, manual segmentation of MRI images is time-consuming and subjective. Therefore, there is an urgent need for automatic segmentation models to identify cervical cancer lesions in MRI scans accurately.  \nAll MRIs in our research are from cervical cancer patients diagnosed by pathology at Tongren City People’s Hospital. Strict data selection criteria and clearly defined inclusion and exclusion conditions were established to ensure data consistency and accuracy of research results. The dataset contains imaging data from 122 cervical cancer patients, with each patient having 100 pelvic dynamic contrastenhanced MRI scans. Annotations were jointly completed by medical professionals from Universiti Putra Malaysia and the Radiology Department of Tongren City People’s Hospital to ensure data accuracy and reliability. Additionally, a novel computer-aided diagnosis model named SwinUNeCCtis proposed. This model incorporates (i) A bidirectional hash-based agent multi-head self-attention mechanism, which optimizes the interaction between local and global features in MRI, aiding in more accurate lesion identification. (ii) Reduced computational complexity of the self-attention mechanism. The effectiveness of the SwinUNeCCt model has been validated through comparisons with state-ofthe-art 3D medical models, including nnUnet, TransBTS, nnFormer, UnetR, UnesT, SwinUNetR, and SwinUNeLCsT. In semantic segmentation tasks without a classification module, the SwinUNeCCt model demonstrates excellent performance across multiple key metrics: achieving a 95HD of  \n6.25, an IoU of 0.669, and a DSC of 0.802, all of which are the best results among the compared models. Simultaneously, SwinUNeCCt strikes a good balance between computational efficiency and model complexity, requiring only 442.7 GFLOPs of computational power and 71.2 M parameters. Furthermore, in semantic segmentation tasks that include a classification module, the SwinUNeCCt model also exhibits powerful recognition capabilities. Although this slightly increases computational overhead and model complexity, its performance surpasses other comparative models. The SwinUNeCCt model demonstrates excellent performance in semantic segmentation tasks, achieving the best results among state-of-the-art 3D medical models across multiple key metrics. It balances computational efficiency and model complexity well, maintaining high performance even with the inclusion of a classification module.  \nKeywords Multi-task learning, Cervical cancer, Segmentation, Classification  \n1Department of Radiology, Tongren People’s Hospital, Tongren 554300, Guizhou Province, China. 2Department of Radiology, Faculty of Medicine and Health Sciences, Universiti Putra Malaysia, 43400 Serdang, Malaysia. 3Faculty of Computer Science and Information Technology, Universiti Putra Malaysia, 43400 Serdang, Malaysia. 4School of Business and Economics, Universiti Putra Malaysia, 43400 Seri Kembangan, Serdang, Malaysia. 5SAS Institute Inc, 100 SAS Campus Drive, Cary, NC 27513-2414, USA. 6Department of Radiology, Wanshan District People’s Hospital, Tongren 554300, Guizhou Province, China. 7These authors contributed equally to this work: ChongshuangYang and Zhuoyi Tan. 􀀍 [email: joeytansmessages@gmail.com](email: joeytansmessages@gmail.com)  \n[www. nature.com/scientificrep","cbCaigDJp8xPUWgN","https://ap.wps.com/l/cbCaigDJp8xPUWgN","pdf",3643150,14,"English","# Introduction\n## Clinical motivation and imaging need\n## Dataset description and annotation\n## Proposed model: SwinUNeCCt\n## Experimental evaluation and results\n## Performance and efficiency comparison\n# Abbreviations","[{\"question\":\"Why is automatic cervical cancer MRI segmentation needed?\",\"answer\":\"Manual segmentation of MRI lesions is time-consuming and subjective, and accurate delineation is important for lesion volume measurement, radiotherapy targeting, surgical planning, and radiomics analysis.\"},{\"question\":\"How is the dataset for the study constructed?\",\"answer\":\"The MRI data come from cervical cancer patients diagnosed by pathology. Strict inclusion/exclusion criteria are applied, and the dataset includes 122 patients with 100 pelvic dynamic contrast-enhanced MRI scans per patient, with annotations completed by medical professionals.\"},{\"question\":\"What key components distinguish SwinUNeCCt?\",\"answer\":\"SwinUNeCCt uses a bidirectional hash-based agent multi-head self-attention to optimize interactions between local and global features, and it reduces the computational complexity of the self-attention mechanism.\"}]","SwinUNeCCt: bidirectional hashbased agent transformer for cervical cancer MRI image multitask learning | PDF",1790004803,35]