{"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/explainable-cardiac-pathology-classification","title":"Explainable cardiac pathology classification on cine MRI with motion characterization by semi-supervised learning of apparent flow","arxiv_id":"1811.03433","date":"2018-11-08","proceeding":null,"authors":["Qiao Zheng","Hervé Delingette","Nicholas Ayache"],"abstract":"We propose a method to classify cardiac pathology based on a novel approach\nto extract image derived features to characterize the shape and motion of the\nheart. An original semi-supervised learning procedure, which makes efficient\nuse of a large amount of non-segmented images and a small amount of images\nsegmented manually by experts, is developed to generate pixel-wise apparent\nflow between two time points of a 2D+t cine MRI image sequence. Combining the\napparent flow maps and cardiac segmentation masks, we obtain a local apparent\nflow corresponding to the 2D motion of myocardium and ventricular cavities.\nThis leads to the generation of time series of the radius and thickness of\nmyocardial segments to represent cardiac motion. These time series of motion\nfeatures are reliable and explainable characteristics of pathological cardiac\nmotion. Furthermore, they are combined with shape-related features to classify\ncardiac pathologies. Using only nine feature values as input, we propose an\nexplainable, simple and flexible model for pathology classification. On ACDC\ntraining set and testing set, the model achieves 95% and 94% respectively as\nclassification accuracy. Its performance is hence comparable to that of the\nstate-of-the-art. Comparison with various other models is performed to outline\nsome advantages of our model.","url_abs":"http://arxiv.org/abs/1811.03433v2","url_pdf":"http://arxiv.org/pdf/1811.03433v2.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":"explainable-cardiac-pathology-classification","repo_url":"https://github.com/julien-zheng/CardiacMotionFlow","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"cardiac-segmentation","task_name":"Cardiac Segmentation"},{"task_slug":"classification","task_name":"General Classification"},{"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":{"syntology_url":"https://syntology.ai/paper/1811.03433","atlas_url":"https://app.syntology.ai/?focus=1811.03433","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}