{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/automated-cardiovascular-magnetic-resonance","title":"Automated cardiovascular magnetic resonance image analysis with fully convolutional networks","arxiv_id":"1710.09289","date":"2017-10-25","proceeding":null,"authors":["Wenjia Bai","Matthew Sinclair","Giacomo Tarroni","Ozan Oktay","Martin Rajchl","Ghislain Vaillant","Aaron M. Lee","Nay Aung","Elena Lukaschuk","Mihir M. Sanghvi","Filip Zemrak","Kenneth Fung","Jose Miguel Paiva","Valentina Carapella","Young Jin Kim","Hideaki Suzuki","Bernhard Kainz","Paul M. Matthews","Steffen E. Petersen","Stefan K. Piechnik","Stefan Neubauer","Ben Glocker","Daniel Rueckert"],"abstract":"Cardiovascular magnetic resonance (CMR) imaging is a standard imaging\nmodality for assessing cardiovascular diseases (CVDs), the leading cause of\ndeath globally. CMR enables accurate quantification of the cardiac chamber\nvolume, ejection fraction and myocardial mass, providing information for\ndiagnosis and monitoring of CVDs. However, for years, clinicians have been\nrelying on manual approaches for CMR image analysis, which is time consuming\nand prone to subjective errors. It is a major clinical challenge to\nautomatically derive quantitative and clinically relevant information from CMR\nimages. Deep neural networks have shown a great potential in image pattern\nrecognition and segmentation for a variety of tasks. Here we demonstrate an\nautomated analysis method for CMR images, which is based on a fully\nconvolutional network (FCN). The network is trained and evaluated on a\nlarge-scale dataset from the UK Biobank, consisting of 4,875 subjects with\n93,500 pixelwise annotated images. The performance of the method has been\nevaluated using a number of technical metrics, including the Dice metric, mean\ncontour distance and Hausdorff distance, as well as clinically relevant\nmeasures, including left ventricle (LV) end-diastolic volume (LVEDV) and\nend-systolic volume (LVESV), LV mass (LVM); right ventricle (RV) end-diastolic\nvolume (RVEDV) and end-systolic volume (RVESV). By combining FCN with a\nlarge-scale annotated dataset, the proposed automated method achieves a high\nperformance on par with human experts in segmenting the LV and RV on short-axis\nCMR images and the left atrium (LA) and right atrium (RA) on long-axis CMR\nimages.","url_abs":"http://arxiv.org/abs/1710.09289v4","url_pdf":"http://arxiv.org/pdf/1710.09289v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"automated-cardiovascular-magnetic-resonance","repo_url":"https://github.com/baiwenjia/ukbb_cardiac","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"fcn","method_name":"FCN"},{"method_slug":"max-pooling","method_name":"Max Pooling"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}