{"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/mbis-multivariate-bayesian-image-segmentation","title":"MBIS: Multivariate Bayesian Image Segmentation Tool","arxiv_id":"1404.0600","date":"2014-04-02","proceeding":null,"authors":["Oscar Esteban","Gert Wollny","Subrahmanyam Gorthi","Maria-J. Ledesma-Carbayo","Jean-Philippe Thiran","Andres Santos","Meritxell Bach-Cuadra"],"abstract":"We present MBIS (Multivariate Bayesian Image Segmentation tool), a clustering\ntool based on the mixture of multivariate normal distributions model. MBIS\nsupports multi-channel bias field correction based on a B-spline model. A\nsecond methodological novelty is the inclusion of graph-cuts optimization for\nthe stationary anisotropic hidden Markov random field model. Along with MBIS,\nwe release an evaluation framework that contains three different experiments on\nmulti-site data. We first validate the accuracy of segmentation and the\nestimated bias field for each channel. MBIS outperforms a widely used\nsegmentation tool in a cross-comparison evaluation. The second experiment\ndemonstrates the robustness of results on atlas-free segmentation of two image\nsets from scan-rescan protocols on 21 healthy subjects. Multivariate\nsegmentation is more replicable than the monospectral counterpart on\nT1-weighted images. Finally, we provide a third experiment to illustrate how\nMBIS can be used in a large-scale study of tissue volume change with increasing\nage in 584 healthy subjects. This last result is meaningful as multivariate\nsegmentation performs robustly without the need for prior knowledge","url_abs":"http://arxiv.org/abs/1404.0600v2","url_pdf":"http://arxiv.org/pdf/1404.0600v2.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":"mbis-multivariate-bayesian-image-segmentation","repo_url":"https://github.com/oesteban/MBIS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"image-segmentation","task_name":"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}