{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T19:30:15Z","timestamp":1757619015452,"version":"3.44.0"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,7,17]],"date-time":"2025-07-17T00:00:00Z","timestamp":1752710400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,7,17]],"date-time":"2025-07-17T00:00:00Z","timestamp":1752710400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Fat and muscle mass are potential biomarkers of wellbeing and disease in oncology, but clinical measurement methods vary considerably. Here we evaluate the accuracy, precision and ability to track change for multiple deep learning (DL) models that quantify fat and muscle mass from abdominal MRI. Specifically, subcutaneous fat (SF), intra-abdominal fat (VF), external muscle (EM) and psoas muscle (PM) were evaluated using 15 convolutional neural network (CNN)-based and 4 transformer-based deep learning model architectures. There was negligible difference in the accuracy of human observers and all deep learning models in delineating SF or EM. Both of these tissues had excellent repeatability of their delineation. VF was measured most accurately by the human observers, then by CNN-based models, which outperformed transformer-based models. In distinction, PM delineation accuracy and repeatability was poor for all assessments. Repeatability limits of agreement determined when changes measured in individual patients were due to real change rather than test-retest variation. In summary, DL model accuracy and precision of delineating fat and muscle volumes varies between CNN-based and transformer-based models, between different tissues and in some cases with gender. These factors should be considered when investigators deploy deep learning methods to estimate biomarkers of fat and muscle mass.<\/jats:p>","DOI":"10.1038\/s41598-025-07867-w","type":"journal-article","created":{"date-parts":[[2025,7,17]],"date-time":"2025-07-17T18:03:54Z","timestamp":1752775434000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep learning models for deriving optimised measures of fat and muscle mass from MRI"],"prefix":"10.1038","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6012-7212","authenticated-orcid":false,"given":"Belvin","family":"Thomas","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"M. Adam","family":"Ali","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fatima M. H.","family":"Ali","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anthony","family":"Chung","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manjiri","family":"Joshi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sophia","family":"Maiguma-Wilson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gabrielle","family":"Reiff","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hadil","family":"Said","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pardis","family":"Zalmay","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Berks","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthew D.","family":"Blackledge","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"James P. B.","family":"O\u2019Connor","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,7,17]]},"reference":[{"key":"7867_CR1","doi-asserted-by":"publisher","first-page":"5280","DOI":"10.3390\/nu6115280","volume":"6","author":"M Ebadi","year":"2014","unstructured":"Ebadi, M. & Mazurak, V. C. Evidence and mechanisms of fat depletion in Cancer. Nutrients. 6, 5280\u20135297 (2014).","journal-title":"Nutrients"},{"key":"7867_CR2","doi-asserted-by":"publisher","first-page":"e2115274","DOI":"10.1001\/jamanetworkopen.2021.15274","volume":"4","author":"CA Fleming","year":"2021","unstructured":"Fleming, C. A. et al. Body composition, inflammation, and 5-year outcomes in colon cancer. JAMA Netw. Open. 4, e2115274\u2013e2115274 (2021).","journal-title":"JAMA Netw. Open."},{"key":"7867_CR3","doi-asserted-by":"publisher","first-page":"S28","DOI":"10.1016\/j.afos.2021.03.002","volume":"7","author":"PCM Au","year":"2021","unstructured":"Au, P. C. M. et al. Sarcopenia and mortality in cancer: A meta-analysis. Osteoporos. Sarcopenia. 7, S28\u2013S33 (2021).","journal-title":"Osteoporos. Sarcopenia"},{"key":"7867_CR4","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1007\/s13244-015-0414-0","volume":"6","author":"C Yip","year":"2015","unstructured":"Yip, C. et al. Imaging body composition in cancer patients: visceral obesity, sarcopenia and sarcopenic obesity May impact on clinical outcome. Insights Imaging. 6, 489\u2013497 (2015).","journal-title":"Insights Imaging"},{"key":"7867_CR5","doi-asserted-by":"publisher","first-page":"887","DOI":"10.1136\/jim-2018-000722","volume":"66","author":"M Borga","year":"2018","unstructured":"Borga, M. et al. Advanced body composition assessment: from body mass index to body composition profiling. J. Investig. Med. 66, 887\u2013895 (2018).","journal-title":"J. Investig. Med."},{"key":"7867_CR6","doi-asserted-by":"crossref","unstructured":"Baglietto, N., Vaquero-Crist\u00f3bal, R., Albaladejo-Saura, M., Mecherques-Carini, M. & Esparza-Ros, F. Assessing skeletal muscle mass and lean body mass: an analysis of the agreement among dual X-ray absorptiometry, anthropometry, and bioelectrical impedance. Front. Nutr. 11, (2024).","DOI":"10.3389\/fnut.2024.1445892"},{"key":"7867_CR7","doi-asserted-by":"publisher","first-page":"994S","DOI":"10.1093\/jn\/127.5.994S","volume":"127","author":"H Lukaski","year":"1997","unstructured":"Lukaski, H. Sarcopenia: Assessment of muscle Mass1. J. Nutr. 127, 994S\u2013997S (1997).","journal-title":"J. Nutr."},{"key":"7867_CR8","doi-asserted-by":"publisher","first-page":"112494","DOI":"10.1016\/j.nut.2024.112494","volume":"125","author":"JP Bennett","year":"2024","unstructured":"Bennett, J. P. et al. Advancing body composition assessment in patients with cancer: first comparisons of traditional versus multicompartment models. Nutrition. 125, 112494 (2024).","journal-title":"Nutrition"},{"key":"7867_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13244-019-0833-4","volume":"11","author":"A Yamamoto","year":"2020","unstructured":"Yamamoto, A. et al. Imaging spectrum of abnormal subcutaneous and visceral fat distribution. Insights Imaging. 11, 1\u201317 (2020).","journal-title":"Insights Imaging"},{"key":"7867_CR10","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/s42256-024-00807-9","volume":"6","author":"S Pai","year":"2024","unstructured":"Pai, S. et al. Foundation model for cancer imaging biomarkers. Nat. Mach. Intell. 6, 354\u2013367 (2024).","journal-title":"Nat. Mach. Intell."},{"key":"7867_CR11","doi-asserted-by":"publisher","first-page":"686","DOI":"10.1038\/s41416-020-01122-x","volume":"124","author":"A Echle","year":"2021","unstructured":"Echle, A. et al. Deep learning in cancer pathology: a new generation of clinical biomarkers. Br. J. Cancer. 124, 686\u2013696 (2021).","journal-title":"Br. J. Cancer"},{"key":"7867_CR12","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E. & Darrell, T. Fully convolutional networks for semantic segmentation. CoRR abs\/1411.4 (2014).","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"7867_CR13","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P. & Brox, T. U-Net: convolutional networks for biomedical image segmentation. CoRR  abs\/1505.0 (2015).","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"7867_CR14","doi-asserted-by":"crossref","unstructured":"\u00c7i\u00e7ek, \u00d6., Abdulkadir, A., Lienkamp, S. S., Brox, T. & Ronneberger O. 3D U-Net: learning dense volumetric segmentation from sparse annotation. CoRR abs\/1606.0 (2016).","DOI":"10.1007\/978-3-319-46723-8_49"},{"key":"7867_CR15","doi-asserted-by":"publisher","first-page":"568","DOI":"10.1109\/JBHI.2019.2912935","volume":"24","author":"S Guan","year":"2020","unstructured":"Guan, S., Khan, A. A., Sikdar, S. & Chitnis, P. V. Fully dense UNet for 2-D sparse photoacoustic tomography artifact removal. IEEE J. Biomed. Health Inf. 24, 568\u2013576 (2020).","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"7867_CR16","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1016\/j.neunet.2019.08.025","volume":"121","author":"N Ibtehaz","year":"2020","unstructured":"Ibtehaz, N. &  Rahman, M. S. MultiResUNet: Rethinking the U-Net architecture for multimodal biomedical image segmentation. Neural Netw. 121, 74\u201387 (2020).","journal-title":"Neural Netw."},{"key":"7867_CR17","doi-asserted-by":"crossref","unstructured":"Xiao, X., Lian, S., Luo, Z. & Li, S. Weighted Res-UNet for high-quality retina vessel segmentation. 2018 9th Int. Conf. Inf. Technol. Med. Educ. 327\u2013331 (2018).","DOI":"10.1109\/ITME.2018.00080"},{"key":"7867_CR18","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","volume":"18","author":"F Isensee","year":"2021","unstructured":"Isensee, F., Jaeger, P. F., Kohl, S. A. A., Petersen, J. & Maier-Hein, K. H. nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat. Methods. 18, 203\u2013211 (2021).","journal-title":"Nat. Methods"},{"key":"7867_CR19","doi-asserted-by":"publisher","first-page":"102802","DOI":"10.1016\/j.media.2023.102802","volume":"88","author":"F Shamshad","year":"2023","unstructured":"Shamshad, F. et al. Transformers in medical imaging: A survey. Med. Image Anal. 88, 102802 (2023).","journal-title":"Med. Image Anal."},{"key":"7867_CR20","doi-asserted-by":"crossref","unstructured":"Khan, R. F., Lee, B. D. & Lee, M. S. Transformers in medical image segmentation: a narrative review. Quant. Imaging Med. Surgery; Vol 13, No 12 (December 01, 2023) (2023).","DOI":"10.21037\/qims-23-542"},{"key":"7867_CR21","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1038\/nrclinonc.2016.162","volume":"14","author":"JPB O\u2019Connor","year":"2017","unstructured":"O\u2019Connor, J. P. B. et al. Imaging biomarker roadmap for cancer studies. Nat. Rev. Clin. Oncol. 14, 169\u2013186 (2017).","journal-title":"Nat. Rev. Clin. Oncol."},{"key":"7867_CR22","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1214\/ss\/1177011136","volume":"7","author":"A Gelman","year":"1992","unstructured":"Gelman, A. & Rubin, D. B. Inference from iterative simulation using multiple sequences. Stat. Sci. 7, 457\u2013472 (1992).","journal-title":"Stat. Sci."},{"key":"7867_CR23","doi-asserted-by":"crossref","unstructured":"Hatamizadeh, A. et al. Swin unetr: Swin Transformers for semantic segmentation of brain tumors in mri images. In International MICCAI Brainlesion Workshop 272\u2013284 (2021).","DOI":"10.1007\/978-3-031-08999-2_22"},{"key":"7867_CR24","doi-asserted-by":"crossref","unstructured":"Hatamizadeh, A. et al. Unetr: Transformers for 3d medical image segmentation. In Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 574\u2013584 (2022).","DOI":"10.1109\/WACV51458.2022.00181"},{"key":"7867_CR25","doi-asserted-by":"crossref","unstructured":"Isensee, F. et al. nnu-net revisited: A call for rigorous validation in 3d medical image segmentation. arXiv Prepr. arXiv2404.09556 (2024).","DOI":"10.1007\/978-3-031-72114-4_47"},{"key":"7867_CR26","first-page":"1","volume":"35","author":"Y Ji","year":"2022","unstructured":"Ji, Y. et al. AMOS: A large-scale abdominal multi-organ benchmark for versatile medical image segmentation. Adv. Neural Inf. Process. Syst. 35, 1\u201311 (2022).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"7867_CR27","doi-asserted-by":"publisher","unstructured":"Fathi Kazerooni, A. et al. BraTS-PEDs: Results of the multi-consortium international pediatric brain tumor segmentation challenge 2023. arXiv e-prints arXiv:2407.08855. https:\/\/doi.org\/10.48550\/arXiv.2407.08855 (2024).","DOI":"10.48550\/arXiv.2407.08855"},{"key":"7867_CR28","doi-asserted-by":"crossref","unstructured":"Roy, S. et al. MedNeXt: Transformer-driven scaling of ConvNets for medical image segmentation. In Medical Image Computing and Computer Assisted Intervention\u2014MICCAI 2023 (ed. Greenspan, H.) 405\u2013415 (Springer Nature Switzerland, 2023).","DOI":"10.1007\/978-3-031-43901-8_39"},{"key":"7867_CR29","doi-asserted-by":"crossref","unstructured":"He, Y. et al. SwinUNETR-V2: stronger Swin Transformers with stagewise convolutions for 3D medical image segmentation. In Medical Image Computing and Computer Assisted Intervention\u2014MICCAI 2023 (ed. Greenspan, H.) 416\u2013426 (Springer Nature Switzerland, 2023).","DOI":"10.1007\/978-3-031-43901-8_40"},{"key":"7867_CR30","unstructured":"Lee, H. H., Bao, S., Huo, Y. & Landman, B. A. 3D Ux-Net: a large kernel volumetric convnet modernizing hierarchical transformer for medical image segmentation. In 11th International Conference on Learning Representations, ICLR, 2023 (ICLR Proceedings, 2023)."},{"key":"7867_CR31","doi-asserted-by":"publisher","first-page":"4672","DOI":"10.1038\/s41467-018-07174-1","volume":"9","author":"GC Jayson","year":"2018","unstructured":"Jayson, G. C. et al. Plasma Tie2 is a tumor vascular response biomarker for VEGF inhibitors in metastatic colorectal cancer. Nat. Commun. 9, 4672 (2018).","journal-title":"Nat. Commun."},{"key":"7867_CR32","doi-asserted-by":"publisher","first-page":"297","DOI":"10.2307\/1932409","volume":"26","author":"LR Dice","year":"1945","unstructured":"Dice, L. R. Measures of the amount of ecologic association between species. Ecology. 26, 297\u2013302 (1945).","journal-title":"Ecology"},{"key":"7867_CR33","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1016\/j.compmedimag.2019.04.005","volume":"75","author":"SA Taghanaki","year":"2019","unstructured":"Taghanaki, S. A. et al. Combo loss: handling input and output imbalance in multi-organ segmentation. Comput. Med. Imaging Graph Off J. Comput. Med. Imaging Soc. 75, 24\u201333 (2019).","journal-title":"Comput. Med. Imaging Graph Off J. Comput. Med. Imaging Soc."},{"key":"7867_CR34","unstructured":"Cardoso, M. J. et al. MONAI: An open-source framework for deep learning in healthcare. ArXiv. abs\/2211.0 (2022)."},{"key":"7867_CR35","doi-asserted-by":"publisher","first-page":"903","DOI":"10.1109\/TMI.2004.828354","volume":"23","author":"SK Warfield","year":"2004","unstructured":"Warfield, S. K., Zou, K. H. & Wells, W. M. Simultaneous truth and performance level Estimation (STAPLE): an algorithm for the validation of image segmentation. IEEE Trans. Med. Imaging. 23, 903\u2013921 (2004).","journal-title":"IEEE Trans. Med. Imaging"},{"key":"7867_CR36","unstructured":"Stan Development Team. Stan Reference Manual, 2.36.0. (2025)."},{"key":"7867_CR37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1259\/bjro.20210083","volume":"4","author":"S Ye","year":"2022","unstructured":"Ye, S., Lim, J. Y. & Huang, W. Statistical considerations for repeatability and reproducibility of quantitative imaging biomarkers. BJR|Open 4, 1\u201318 (2022).","journal-title":"BJR|Open"},{"key":"7867_CR38","doi-asserted-by":"publisher","first-page":"372","DOI":"10.1016\/j.acra.2017.09.023","volume":"25","author":"NA Obuchowski","year":"2018","unstructured":"Obuchowski, N. A. Interpreting change in quantitative imaging biomarkers. Acad. Radiol. 25, 372\u2013379 (2018).","journal-title":"Acad. Radiol."},{"key":"7867_CR39","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1177\/0962280214537344","volume":"24","author":"DL Raunig","year":"2015","unstructured":"Raunig, D. L. et al. Quantitative imaging biomarkers: a review of statistical methods for technical performance assessment. Stat. Methods Med. Res. 24, 27\u201367 (2015).","journal-title":"Stat. Methods Med. Res."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-07867-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-07867-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-07867-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,7]],"date-time":"2025-09-07T13:09:27Z","timestamp":1757250567000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-07867-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,17]]},"references-count":39,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["7867"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-07867-w","relation":{},"ISSN":["2045-2322"],"issn-type":[{"type":"electronic","value":"2045-2322"}],"subject":[],"published":{"date-parts":[[2025,7,17]]},"assertion":[{"value":"30 January 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 June 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 July 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"25960"}}