[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85308-en":3,"doc-seo-85308-105":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},85308,687197207919,"Theodora","https://ap-avatar.wpscdn.com/avatar/a000253d6f5f7c60be?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779446848396160552",8,"Research & Report","A Unified Framework for Comprehensive Cardiac CT Segmentation and Phenotyping","Comprehensive quantification of cardiac structures from computed tomography (CT) is constrained by measurement scalability, making routine use impractical. A unified framework is presented for cardiac CT segmentation and phenotyping, integrating a human-in-the-loop annotation pipeline, cardiac CT augmentation, and a self-supervised foundation model pre-trained on 60,000 unlabeled scans. The resulting dataset contains 1,598 cases across 14 structures and supports improved accuracy over open-source tools on five external datasets, especially with limited labeled data.","A Unified Framework for Comprehensive Cardiac CT Segmentation and Phenotyping: Human-in-the-Loop Data Annotation, Vision Foundation Model Development, Multicenter Evaluation and Clinical Validation  \nPooya Mohammadi Kazaj 1,2,3, Leo Fridolin Weber 1,2†, Wen Xie 1,2†, Seyed Amir Ahmad SafaviNaini†1,2, Anselm Stark 1,2, Giovanni Baj 1,2, Ali Mokhtari 1,2, Toshiya Yoshida4, Christoph Ryffel 1,2, Taishi Okuno4, Yoshihiro Akashi4, Ronny R Buechel5, Thomas Pilgrim 1, Waldo Valenzuela6, George CM Siontis 1, Xiaowei Xu7, Moritz Hundertmark 1, Stephan Windecker 1, Christoph Gräni 1,2*, Isaac Shiri 1,2*  \n1-Department of Cardiology, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland  \n2-Department of Digital Medicine, University of Bern, Bern, Switzerland  \n3-Graduate School for Cellular and Biomedical Sciences, University of Bern, Bern, Switzerland 4-Department of Cardiology, St. Marianna University School of Medicine, 2-16-1, Sugao, Miyamae-ku, Kawasaki, 216-8511, Japan  \n5-Department of Nuclear Medicine, Cardiac Imaging, University Hospital Zurich, Zurich, Switzerland  \n6-Institute for Diagnostic and Interventional Neuroradiology, Inselspital Bern, Bern, Switzerland 7-Guangdong Provincial People’s Hospital, Guangzhou, China  \n† Leo Fridolin Weber, Wen Xie, Seyed Amir Ahmad Safavi-Naini contributed equally to this work.  \n* Dr. Gräni and Dr. Shiri jointly supervised this work.  \n* Corresponding Author:  \nIsaac Shiri, PhD  \nDepartment of Cardiology Inselspital, Bern University Hospital University of Bern,  \nFreiburgstrasse CH-3010 Bern, Switzerland Email: [isaac.shirilord@unibe.ch](isaac.shirilord@unibe.ch)  \nAbstract  \nComprehensive quantification of cardiac structures from computed tomography (CT) remains limited not by data availability but by the scalability of measurements, which makes routine use impractical. Here we present a unified framework for comprehensive cardiac CT segmentation and phenotyping that combines a human-in-the-loop annotation pipeline, a cardiac CT augmentation technique, and a self-supervised foundation model pre-trained on 60,000 unlabeled cardiac CT scans. Using this approach, we assembled the largest and most comprehensive expert-annotated cardiac CT segmentation dataset to date, comprising 1598 cases and 14 distinct cardiac structures (1000 for training, 598 for the external test set) . Across five external datasets, the framework segmented all structures more accurately and comprehensively than existing open-source tools. Self-supervised pre-training improved labeling efficiency, with the most significant gains observed during external evaluation in the low-data regime. Benchmarking across convolutional, transformer, and state-space architectures showed comparable performance, indicating that data quality and pre-training, rather than architecture, drove accuracy. The framework was scaled to population-level phenotyping, with segmented anatomy that carries functionally relevant information about ventricular function and disease severity beyond demographic variables. By openly releasing the largest dataset with human labels, code, model weights, a CT augmentation library, and software, this work provides a reproducible foundation for opportunistic cardiac phenotyping from routinely acquired CT scans.  \nKeywords  \nCardiac, Segmentation, Computed Tomography, Foundation Model, Human-in-the-Loop  \n1. Introduction  \nComputed tomography (CT) provides high-resolution detailed anatomical imaging of the human body, and cardiac CT (CCT) acquisitions are specifically optimized to capture cardiac structure and function throughout the cardiac cycle. As the first-line test for numerous cardiovascular indications, CCT is now performed more than 1 million times annually in the United States1 alone, spanning coronary artery disease, valvular heart disease, and congenital heart disease, as well as pre-procedural planning and post-procedural follow-up of surgical and transcatheter heart interventio","cbCaiq5jbhNYGzc4","https://ap.wps.com/l/cbCaiq5jbhNYGzc4","pdf",15584109,3,1,91,"English","en",105,"# Abstract\n# Keywords\n# Introduction","[{\"question\":\"What problem does the unified framework address in cardiac CT analysis?\",\"answer\":\"It targets the bottleneck of measurement scalability in comprehensive cardiac CT quantification, which prevents routine use despite abundant imaging data.\"},{\"question\":\"What components are combined to enable segmentation and phenotyping?\",\"answer\":\"The framework integrates a human-in-the-loop annotation pipeline, a CT augmentation technique, and a self-supervised foundation model pre-trained on 60,000 unlabeled cardiac CT scans.\"},{\"question\":\"How large and comprehensive is the released segmentation dataset?\",\"answer\":\"The framework produced an expert-annotated dataset with 1,598 cases covering 14 distinct cardiac structures, including 1,000 for training and 598 for an external test set.\"}]",1784202385,229,{"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},"a-unified-framework-for-comprehensive-cardiac-ct-segmentation-and-phenotyping","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":20},"https://docshare.wps.com/document/research-report/",{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/a-unified-framework-for-comprehensive-cardiac-ct-segmentation-and-phenotyping/85308/",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","2026-07-22","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 the unified framework address in cardiac CT analysis?","Question",{"text":75,"@type":76},"It targets the bottleneck of measurement scalability in comprehensive cardiac CT quantification, which prevents routine use despite abundant imaging data.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What components are combined to enable segmentation and phenotyping?",{"text":80,"@type":76},"The framework integrates a human-in-the-loop annotation pipeline, a CT augmentation technique, and a self-supervised foundation model pre-trained on 60,000 unlabeled cardiac CT scans.",{"name":82,"@type":73,"acceptedAnswer":83},"How large and comprehensive is the released segmentation dataset?",{"text":84,"@type":76},"The framework produced an expert-annotated dataset with 1,598 cases covering 14 distinct cardiac structures, including 1,000 for training and 598 for an external test set.","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":47,"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"]