{"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/automated-sub-cortical-brain-structure","title":"Automated sub-cortical brain structure segmentation combining spatial and deep convolutional features","arxiv_id":"1709.09075","date":"2017-09-26","proceeding":null,"authors":["Kaisar Kushibar","Sergi Valverde","Sandra Gonzalez-Villa","Jose Bernal","Mariano Cabezas","Arnau Oliver","Xavier Llado"],"abstract":"Sub-cortical brain structure segmentation in Magnetic Resonance Images (MRI)\nhas attracted the interest of the research community for a long time because\nmorphological changes in these structures are related to different\nneurodegenerative disorders. However, manual segmentation of these structures\ncan be tedious and prone to variability, highlighting the need for robust\nautomated segmentation methods. In this paper, we present a novel convolutional\nneural network based approach for accurate segmentation of the sub-cortical\nbrain structures that combines both convolutional and prior spatial features\nfor improving the segmentation accuracy. In order to increase the accuracy of\nthe automated segmentation, we propose to train the network using a restricted\nsample selection to force the network to learn the most difficult parts of the\nstructures. We evaluate the accuracy of the proposed method on the public\nMICCAI 2012 challenge and IBSR 18 datasets, comparing it with different\navailable state-of-the-art methods and other recently proposed deep learning\napproaches. On the MICCAI 2012 dataset, our method shows an excellent\nperformance comparable to the best challenge participant strategy, while\nperforming significantly better than state-of-the-art techniques such as\nFreeSurfer and FIRST. On the IBSR 18 dataset, our method also exhibits a\nsignificant increase in the performance with respect to not only FreeSurfer and\nFIRST, but also comparable or better results than other recent deep learning\napproaches. Moreover, our experiments show that both the addition of the\nspatial priors and the restricted sampling strategy have a significant effect\non the accuracy of the proposed method. In order to encourage the\nreproducibility and the use of the proposed method, a public version of our\napproach is available to download for the neuroimaging community.","url_abs":"http://arxiv.org/abs/1709.09075v1","url_pdf":"http://arxiv.org/pdf/1709.09075v1.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":"automated-sub-cortical-brain-structure","repo_url":"https://github.com/NIC-VICOROB/sub-cortical_segmentation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"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}