{"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/unbiased-shape-compactness-for-segmentation","title":"Unbiased Shape Compactness for Segmentation","arxiv_id":"1704.08908","date":"2017-04-28","proceeding":null,"authors":["Jose Dolz","Ismail Ben Ayed","Christian Desrosiers"],"abstract":"We propose to constrain segmentation functionals with a dimensionless,\nunbiased and position-independent shape compactness prior, which we solve\nefficiently with an alternating direction method of multipliers (ADMM).\nInvolving a squared sum of pairwise potentials, our prior results in a\nchallenging high-order optimization problem, which involves dense (fully\nconnected) graphs. We split the problem into a sequence of easier sub-problems,\neach performed efficiently at each iteration: (i) a sparse-matrix inversion\nbased on Woodbury identity, (ii) a closed-form solution of a cubic equation and\n(iii) a graph-cut update of a sub-modular pairwise sub-problem with a sparse\ngraph. We deploy our prior in an energy minimization, in conjunction with a\nsupervised classifier term based on CNNs and standard regularization\nconstraints. We demonstrate the usefulness of our energy in several medical\napplications. In particular, we report comprehensive evaluations of our fully\nautomated algorithm over 40 subjects, showing a competitive performance for the\nchallenging task of abdominal aorta segmentation in MRI.","url_abs":"http://arxiv.org/abs/1704.08908v2","url_pdf":"http://arxiv.org/pdf/1704.08908v2.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":"unbiased-shape-compactness-for-segmentation","repo_url":"https://github.com/josedolz/UnbiasedShapeCompactness","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"segmentation","task_name":"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}