{"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/iterative-fully-convolutional-neural-networks","title":"Iterative fully convolutional neural networks for automatic vertebra segmentation and identification","arxiv_id":"1804.04383","date":"2018-04-12","proceeding":null,"authors":["Nikolas Lessmann","Bram van Ginneken","Pim A. de Jong","Ivana Išgum"],"abstract":"Precise segmentation and anatomical identification of the vertebrae provides\nthe basis for automatic analysis of the spine, such as detection of vertebral\ncompression fractures or other abnormalities. Most dedicated spine CT and MR\nscans as well as scans of the chest, abdomen or neck cover only part of the\nspine. Segmentation and identification should therefore not rely on the\nvisibility of certain vertebrae or a certain number of vertebrae. We propose an\niterative instance segmentation approach that uses a fully convolutional neural\nnetwork to segment and label vertebrae one after the other, independently of\nthe number of visible vertebrae. This instance-by-instance segmentation is\nenabled by combining the network with a memory component that retains\ninformation about already segmented vertebrae. The network iteratively analyzes\nimage patches, using information from both image and memory to search for the\nnext vertebra. To efficiently traverse the image, we include the prior\nknowledge that the vertebrae are always located next to each other, which is\nused to follow the vertebral column. This method was evaluated with five\ndiverse datasets, including multiple modalities (CT and MR), various fields of\nview and coverages of different sections of the spine, and a particularly\nchallenging set of low-dose chest CT scans. The proposed iterative segmentation\nmethod compares favorably with state-of-the-art methods and is fast, flexible\nand generalizable.","url_abs":"http://arxiv.org/abs/1804.04383v3","url_pdf":"http://arxiv.org/pdf/1804.04383v3.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":"iterative-fully-convolutional-neural-networks","repo_url":"https://github.com/leohsuofnthu/Pytorch-IterativeFCN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"instance-segmentation","task_name":"Instance 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}