{"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/automatic-cardiac-disease-assessment-on-cine","title":"Automatic Cardiac Disease Assessment on cine-MRI via Time-Series Segmentation and Domain Specific Features","arxiv_id":"1707.00587","date":"2017-07-03","proceeding":null,"authors":["Fabian Isensee","Paul Jaeger","Peter M. Full","Ivo Wolf","Sandy Engelhardt","Klaus H. Maier-Hein"],"abstract":"Cardiac magnetic resonance imaging improves on diagnosis of cardiovascular\ndiseases by providing images at high spatiotemporal resolution. Manual\nevaluation of these time-series, however, is expensive and prone to biased and\nnon-reproducible outcomes. In this paper, we present a method that addresses\nnamed limitations by integrating segmentation and disease classification into a\nfully automatic processing pipeline. We use an ensemble of UNet inspired\narchitectures for segmentation of cardiac structures such as the left and right\nventricular cavity (LVC, RVC) and the left ventricular myocardium (LVM) on each\ntime instance of the cardiac cycle. For the classification task, information is\nextracted from the segmented time-series in form of comprehensive features\nhandcrafted to reflect diagnostic clinical procedures. Based on these features\nwe train an ensemble of heavily regularized multilayer perceptrons (MLP) and a\nrandom forest classifier to predict the pathologic target class. We evaluated\nour method on the ACDC dataset (4 pathology groups, 1 healthy group) and\nachieve dice scores of 0.945 (LVC), 0.908 (RVC) and 0.905 (LVM) in a\ncross-validation over the training set (100 cases) and 0.950 (LVC), 0.923 (RVC)\nand 0.911 (LVM) on the test set (50 cases). We report a classification accuracy\nof 94% on a training set cross-validation and 92% on the test set. Our results\nunderpin the potential of machine learning methods for accurate, fast and\nreproducible segmentation and computer-assisted diagnosis (CAD).","url_abs":"http://arxiv.org/abs/1707.00587v2","url_pdf":"http://arxiv.org/pdf/1707.00587v2.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":"automatic-cardiac-disease-assessment-on-cine","repo_url":"https://github.com/MIC-DKFZ/ACDC2017","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"diagnostic","task_name":"Diagnostic"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series","task_name":"Time Series Analysis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}