{"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/automatic-l3-slice-detection-in-3d-ct-images","title":"Automatic L3 slice detection in 3D CT images using fully-convolutional networks","arxiv_id":"1811.09244","date":"2018-11-22","proceeding":null,"authors":["Fahdi Kanavati","Shah Islam","Eric O. Aboagye","Andrea Rockall"],"abstract":"The analysis of single CT slices extracted at the third lumbar vertebra (L3)\nhas garnered significant clinical interest in the past few years, in particular\nin regards to quantifying sarcopenia (muscle loss). In this paper, we propose\nan efficient method to automatically detect the L3 slice in 3D CT images. Our\nmethod works with images with a variety of fields of view, occlusions, and\nslice thicknesses. 3D CT images are first converted into 2D via Maximal\nIntensity Projection (MIP), reducing the dimensionality of the problem. The MIP\nimages are then used as input to a 2D fully-convolutional network to predict\nthe L3 slice locations in the form of 2D confidence maps. In addition we\npropose a variant architecture with less parameters allowing 1D confidence map\nprediction and slightly faster prediction time without loss of accuracy.\nQuantitative evaluation of our method on a dataset of 1006 3D CT images yields\na median error of 1mm, similar to the inter-rater median error of 1mm obtained\nfrom two annotators, demonstrating the effectiveness of our method in\nefficiently and accurately detecting the L3 slice.","url_abs":"http://arxiv.org/abs/1811.09244v1","url_pdf":"http://arxiv.org/pdf/1811.09244v1.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":"automatic-l3-slice-detection-in-3d-ct-images","repo_url":"https://github.com/fk128/sarcopenia-ai","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}