{"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/unsupervised-body-part-regression-via","title":"Unsupervised Body Part Regression via Spatially Self-ordering Convolutional Neural Networks","arxiv_id":"1707.03891","date":"2017-07-12","proceeding":null,"authors":["Ke Yan","Le Lu","Ronald M. Summers"],"abstract":"Automatic body part recognition for CT slices can benefit various medical\nimage applications. Recent deep learning methods demonstrate promising\nperformance, with the requirement of large amounts of labeled images for\ntraining. The intrinsic structural or superior-inferior slice ordering\ninformation in CT volumes is not fully exploited. In this paper, we propose a\nconvolutional neural network (CNN) based Unsupervised Body part Regression\n(UBR) algorithm to address this problem. A novel unsupervised learning method\nand two inter-sample CNN loss functions are presented. Distinct from previous\nwork, UBR builds a coordinate system for the human body and outputs a\ncontinuous score for each axial slice, representing the normalized position of\nthe body part in the slice. The training process of UBR resembles a\nself-organization process: slice scores are learned from inter-slice\nrelationships. The training samples are unlabeled CT volumes that are abundant,\nthus no extra annotation effort is needed. UBR is simple, fast, and accurate.\nQuantitative and qualitative experiments validate its effectiveness. In\naddition, we show two applications of UBR in network initialization and anomaly\ndetection.","url_abs":"http://arxiv.org/abs/1707.03891v2","url_pdf":"http://arxiv.org/pdf/1707.03891v2.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":"unsupervised-body-part-regression-via","repo_url":"https://github.com/Gabsha/ssbr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"unsupervised-body-part-regression-via","repo_url":"https://github.com/mic-dkfz/bodypartregression","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"anomaly-detection","task_name":"Anomaly Detection"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}