{"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/interactive-medical-image-segmentation-via","title":"Interactive Medical Image Segmentation via Point-Based Interaction and Sequential Patch Learning","arxiv_id":"1804.10481","date":"2018-04-27","proceeding":null,"authors":["Jinquan Sun","Yinghuan Shi","Yang Gao","Lei Wang","Luping Zhou","Wanqi Yang","Dinggang Shen"],"abstract":"Due to low tissue contrast, irregular object appearance, and unpredictable\nlocation variation, segmenting the objects from different medical imaging\nmodalities (e.g., CT, MR) is considered as an important yet challenging task.\nIn this paper, we present a novel method for interactive medical image\nsegmentation with the following merits. (1) Our design is fundamentally\ndifferent from previous pure patch-based and image-based segmentation methods.\nWe observe that during delineation, the physician repeatedly check the\ninside-outside intensity changing to determine the boundary, which indicates\nthat comparison in an inside-outside manner is extremely important. Thus, we\ninnovatively model our segmentation task as learning the representation of the\nbi-directional sequential patches, starting from (or ending in) the given\ncentral point of the object. This can be realized by our proposed ConvRNN\nnetwork embedded with a gated memory propagation unit. (2) Unlike previous\ninteractive methods (requiring bounding box or seed points), we only ask the\nphysician to merely click on the rough central point of the object before\nsegmentation, which could simultaneously enhance the performance and reduce the\nsegmentation time. (3) We utilize our method in a multi-level framework for\nbetter performance. We systematically evaluate our method in three different\nsegmentation tasks including CT kidney tumor, MR prostate, and PROMISE12\nchallenge, showing promising results compared with state-of-the-art methods.\nThe code is available here:\n\\href{https://github.com/sunalbert/Sequential-patch-based-segmentation}{Sequential-patch-based-segmentation}.","url_abs":"http://arxiv.org/abs/1804.10481v2","url_pdf":"http://arxiv.org/pdf/1804.10481v2.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":"interactive-medical-image-segmentation-via","repo_url":"https://github.com/sunalbert/Sequential-patch-based-segmentation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"medical-image-segmentation","task_name":"Medical Image Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}