{"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-liver-and-lesion-segmentation-in-ct","title":"Automatic Liver and Lesion Segmentation in CT Using Cascaded Fully Convolutional Neural Networks and 3D Conditional Random Fields","arxiv_id":"1610.02177","date":"2016-10-07","proceeding":null,"authors":["Patrick Ferdinand Christ","Mohamed Ezzeldin A. Elshaer","Florian Ettlinger","Sunil Tatavarty","Marc Bickel","Patrick Bilic","Markus Rempfler","Marco Armbruster","Felix Hofmann","Melvin D'Anastasi","Wieland H. Sommer","Seyed-Ahmad Ahmadi","Bjoern H. Menze"],"abstract":"Automatic segmentation of the liver and its lesion is an important step\ntowards deriving quantitative biomarkers for accurate clinical diagnosis and\ncomputer-aided decision support systems. This paper presents a method to\nautomatically segment liver and lesions in CT abdomen images using cascaded\nfully convolutional neural networks (CFCNs) and dense 3D conditional random\nfields (CRFs). We train and cascade two FCNs for a combined segmentation of the\nliver and its lesions. In the first step, we train a FCN to segment the liver\nas ROI input for a second FCN. The second FCN solely segments lesions from the\npredicted liver ROIs of step 1. We refine the segmentations of the CFCN using a\ndense 3D CRF that accounts for both spatial coherence and appearance. CFCN\nmodels were trained in a 2-fold cross-validation on the abdominal CT dataset\n3DIRCAD comprising 15 hepatic tumor volumes. Our results show that CFCN-based\nsemantic liver and lesion segmentation achieves Dice scores over 94% for liver\nwith computation times below 100s per volume. We experimentally demonstrate the\nrobustness of the proposed method as a decision support system with a high\naccuracy and speed for usage in daily clinical routine.","url_abs":"http://arxiv.org/abs/1610.02177v1","url_pdf":"http://arxiv.org/pdf/1610.02177v1.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-liver-and-lesion-segmentation-in-ct","repo_url":"https://github.com/IBBM/Cascaded-FCN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"automatic-liver-and-lesion-segmentation-in-ct","repo_url":"https://github.com/FelixGruen/tensorflow-u-net","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"automatic-liver-and-lesion-segmentation-in-ct","repo_url":"https://github.com/modelhub-ai/cascaded-fcn-liver","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"lesion-segmentation","task_name":"Lesion Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"}],"methods":[{"method_slug":"crf","method_name":"CRF"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"fcn","method_name":"FCN"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1610.02177","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}