{"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/fully-convolutional-networks-for-automated","title":"Fully Convolutional Networks for Automated Segmentation of Abdominal Adipose Tissue Depots in Multicenter Water-Fat MRI","arxiv_id":"1807.03122","date":"2018-06-26","proceeding":null,"authors":["Taro Langner","Anders Hedström","Katharina Mörwald","Daniel Weghuber","Anders Forslund","Peter Bergsten","Håkan Ahlström","Joel Kullberg"],"abstract":"Purpose: An approach for the automated segmentation of visceral adipose\ntissue (VAT) and subcutaneous adipose tissue (SAT) in multicenter water-fat MRI\nscans of the abdomen was investigated, using two different neural network\narchitectures.\n  Methods: The two fully convolutional network architectures U-Net and V-Net\nwere trained, evaluated and compared on the water-fat MRI data. Data of the\nstudy Tellus with 90 scans from a single center was used for a 10-fold\ncross-validation in which the most successful configuration for both networks\nwas determined. These configurations were then tested on 20 scans of the\nmulticenter study beta-cell function in JUvenile Diabetes and Obesity\n(BetaJudo), which involved a different study population and scanning device.\n  Results: The U-Net outperformed the used implementation of the V-Net in both\ncross-validation and testing. In cross-validation, the U-Net reached average\ndice scores of 0.988 (VAT) and 0.992 (SAT). The average of the absolute\nquantification errors amount to 0.67% (VAT) and 0.39% (SAT). On the\nmulti-center test data, the U-Net performs only slightly worse, with average\ndice scores of 0.970 (VAT) and 0.987 (SAT) and quantification errors of 2.80%\n(VAT) and 1.65% (SAT).\n  Conclusion: The segmentations generated by the U-Net allow for reliable\nquantification and could therefore be viable for high-quality automated\nmeasurements of VAT and SAT in large-scale studies with minimal need for human\nintervention. The high performance on the multicenter test data furthermore\nshows the robustness of this approach for data of different patient\ndemographics and imaging centers, as long as a consistent imaging protocol is\nused.","url_abs":"http://arxiv.org/abs/1807.03122v5","url_pdf":"http://arxiv.org/pdf/1807.03122v5.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":"fully-convolutional-networks-for-automated","repo_url":"https://github.com/tarolangner/fcn_vatsat","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"u-net","method_name":"U-Net"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}