{"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/a-fixed-point-model-for-pancreas-segmentation","title":"A Fixed-Point Model for Pancreas Segmentation in Abdominal CT Scans","arxiv_id":"1612.08230","date":"2016-12-25","proceeding":null,"authors":["Yuyin Zhou","Lingxi Xie","Wei Shen","Yan Wang","Elliot K. Fishman","Alan L. Yuille"],"abstract":"Deep neural networks have been widely adopted for automatic organ\nsegmentation from abdominal CT scans. However, the segmentation accuracy of\nsome small organs (e.g., the pancreas) is sometimes below satisfaction,\narguably because deep networks are easily disrupted by the complex and variable\nbackground regions which occupies a large fraction of the input volume. In this\npaper, we formulate this problem into a fixed-point model which uses a\npredicted segmentation mask to shrink the input region. This is motivated by\nthe fact that a smaller input region often leads to more accurate segmentation.\nIn the training process, we use the ground-truth annotation to generate\naccurate input regions and optimize network weights. On the testing stage, we\nfix the network parameters and update the segmentation results in an iterative\nmanner. We evaluate our approach on the NIH pancreas segmentation dataset, and\noutperform the state-of-the-art by more than 4%, measured by the average\nDice-S{\\o}rensen Coefficient (DSC). In addition, we report 62.43% DSC in the\nworst case, which guarantees the reliability of our approach in clinical\napplications.","url_abs":"http://arxiv.org/abs/1612.08230v4","url_pdf":"http://arxiv.org/pdf/1612.08230v4.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":"a-fixed-point-model-for-pancreas-segmentation","repo_url":"https://github.com/198808xc/OrganSegC2F","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"caffe2","reach":null},{"paper_slug":"a-fixed-point-model-for-pancreas-segmentation","repo_url":"https://github.com/198808xc/OrganSegRSTN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"caffe2","reach":null},{"paper_slug":"a-fixed-point-model-for-pancreas-segmentation","repo_url":"https://github.com/twni2016/OrganSegRSTN_PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"organ-segmentation","task_name":"Organ Segmentation"},{"task_slug":"pancreas-segmentation","task_name":"Pancreas Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"}],"methods":[],"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}