{"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/quicknat-a-fully-convolutional-network-for","title":"QuickNAT: A Fully Convolutional Network for Quick and Accurate Segmentation of Neuroanatomy","arxiv_id":"1801.04161","date":"2018-01-12","proceeding":null,"authors":["Abhijit Guha Roy","Sailesh Conjeti","Nassir Navab","Christian Wachinger"],"abstract":"Whole brain segmentation from structural magnetic resonance imaging (MRI) is\na prerequisite for most morphological analyses, but is computationally intense\nand can therefore delay the availability of image markers after scan\nacquisition. We introduce QuickNAT, a fully convolutional, densely connected\nneural network that segments a \\revision{MRI brain scan} in 20 seconds. To\nenable training of the complex network with millions of learnable parameters\nusing limited annotated data, we propose to first pre-train on auxiliary labels\ncreated from existing segmentation software. Subsequently, the pre-trained\nmodel is fine-tuned on manual labels to rectify errors in auxiliary labels.\nWith this learning strategy, we are able to use large neuroimaging repositories\nwithout manual annotations for training. In an extensive set of evaluations on\neight datasets that cover a wide age range, pathology, and different scanners,\nwe demonstrate that QuickNAT achieves superior segmentation accuracy and\nreliability in comparison to state-of-the-art methods, while being orders of\nmagnitude faster. The speed up facilitates processing of large data\nrepositories and supports translation of imaging biomarkers by making them\navailable within seconds for fast clinical decision making.","url_abs":"http://arxiv.org/abs/1801.04161v2","url_pdf":"http://arxiv.org/pdf/1801.04161v2.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":"quicknat-a-fully-convolutional-network-for","repo_url":"https://github.com/abhi4ssj/QuickNATv2","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"quicknat-a-fully-convolutional-network-for","repo_url":"https://github.com/CaelynCheung1996/QuickNAT_tensorflow_V2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"quicknat-a-fully-convolutional-network-for","repo_url":"https://github.com/SenthilCaesar/CNN-Brain-MRI-Segmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"quicknat-a-fully-convolutional-network-for","repo_url":"https://github.com/ai-med/QuickNATv2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"quicknat-a-fully-convolutional-network-for","repo_url":"https://github.com/ai-med/quickNAT_pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"quicknat-a-fully-convolutional-network-for","repo_url":"https://github.com/pnlbwh/CNN-Diffusion-MRIBrain-Segmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"brain-segmentation","task_name":"Brain Segmentation"},{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}