{"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/nonlinear-markov-random-fields-learned-via","title":"Nonlinear Markov Random Fields Learned via Backpropagation","arxiv_id":"1902.10747","date":"2019-02-27","proceeding":null,"authors":["Mikael Brudfors","Yaël Balbastre","John Ashburner"],"abstract":"Although convolutional neural networks (CNNs) currently dominate competitions\non image segmentation, for neuroimaging analysis tasks, more classical\ngenerative approaches based on mixture models are still used in practice to\nparcellate brains. To bridge the gap between the two, in this paper we propose\na marriage between a probabilistic generative model, which has been shown to be\nrobust to variability among magnetic resonance (MR) images acquired via\ndifferent imaging protocols, and a CNN. The link is in the prior distribution\nover the unknown tissue classes, which are classically modelled using a Markov\nrandom field. In this work we model the interactions among neighbouring pixels\nby a type of recurrent CNN, which can encode more complex spatial interactions.\nWe validate our proposed model on publicly available MR data, from different\ncentres, and show that it generalises across imaging protocols. This result\ndemonstrates a successful and principled inclusion of a CNN in a generative\nmodel, which in turn could be adapted by any probabilistic generative approach\nfor image segmentation.","url_abs":"http://arxiv.org/abs/1902.10747v2","url_pdf":"http://arxiv.org/pdf/1902.10747v2.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":"nonlinear-markov-random-fields-learned-via","repo_url":"https://github.com/WCHN/Label-Training","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"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}