{"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/almost-instant-brain-atlas-segmentation-for","title":"Almost instant brain atlas segmentation for large-scale studies","arxiv_id":"1711.00457","date":"2017-11-01","proceeding":null,"authors":["Alex Fedorov","Eswar Damaraju","Vince Calhoun","Sergey Plis"],"abstract":"Large scale studies of group differences in healthy controls and patients and\nscreenings for early stage disease prevention programs require processing and\nanalysis of extensive multisubject datasets. Complexity of the task increases\neven further when segmenting structural MRI of the brain into an atlas with\nmore than 50 regions. Current automatic approaches are time-consuming and\nhardly scalable; they often involve many error prone intermediate steps and\ndon't utilize other available modalities. To alleviate these problems, we\npropose a feedforward fully convolutional neural network trained on the output\nproduced by the state of the art models. Incredible speed due to available\npowerful GPUs neural network makes this analysis much easier and faster (from\n$>10$ hours to a minute). The proposed model is more than two orders of\nmagnitudes faster than the state of the art and yet as accurate. We have\nevaluated the network's performance by comparing it with the state of the art\nin the task of differentiating region volumes of healthy controls and patients\nwith schizophrenia on a dataset with 311 subjects. This comparison provides a\nstrong evidence that speed did not harm the accuracy. The overall quality may\nalso be increased by utilizing multi-modal datasets (not an easy task for other\nmodels) by simple adding more modalities as an input. Our model will be useful\nin large-scale studies as well as in clinical care solutions, where it can\nsignificantly reduce delay between the patient screening and the result.","url_abs":"http://arxiv.org/abs/1711.00457v1","url_pdf":"http://arxiv.org/pdf/1711.00457v1.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":"almost-instant-brain-atlas-segmentation-for","repo_url":"https://github.com/Entodi/meshnet-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}