{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,19]],"date-time":"2026-10-19T16:43:10Z","timestamp":1792428190187,"version":"4.5.0"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2026,10,19]],"date-time":"2026-10-19T00:00:00Z","timestamp":1792368000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,10,19]],"date-time":"2026-10-19T00:00:00Z","timestamp":1792368000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Digit Imaging. Inform. med."],"DOI":"10.1007\/s10278-026-02364-6","type":"journal-article","created":{"date-parts":[[2026,10,19]],"date-time":"2026-10-19T16:33:02Z","timestamp":1792427582000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Annotation-Efficient Individual Muscle Segmentation from Dixon MRI: A Multi-Dataset Benchmark of Pretraining and Fat-Fraction Guidance"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6102-1636","authenticated-orcid":false,"given":"Arvind Channarayapatna","family":"Srinivasa","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shamshekhar S.","family":"Patil","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,10,19]]},"reference":[{"key":"2364_CR1","doi-asserted-by":"crossref","unstructured":"A.\u00a0J. Cruz-Jentoft et al., \u201cSarcopenia: revised European consensus on definition and diagnosis,\u201d Age and Ageing, vol.\u00a048, no.\u00a01, pp.\u00a016\u201331, 2019.","DOI":"10.1093\/ageing\/afz046"},{"key":"2364_CR2","doi-asserted-by":"crossref","unstructured":"B.\u00a0H. Goodpaster et al., \u201cThe loss of skeletal muscle strength, mass, and quality in older adults: the Health ABC study,\u201d J. Gerontol. A Biol. Sci. Med. Sci., vol.\u00a061, no.\u00a010, pp.\u00a01059\u20131064, 2006.","DOI":"10.1093\/gerona\/61.10.1059"},{"key":"2364_CR3","doi-asserted-by":"crossref","unstructured":"P.\u00a0J. Pickhardt et al., \u201cOpportunistic screening at abdominal CT: use of automated body composition biomarkers for added cardiometabolic value,\u201d RadioGraphics, vol.\u00a041, no.\u00a02, pp.\u00a0524\u2013542, 2021.","DOI":"10.1148\/rg.2021200056"},{"key":"2364_CR4","doi-asserted-by":"crossref","unstructured":"O.\u00a0Ronneberger, P.\u00a0Fischer, and T.\u00a0Brox, \u201cU-Net: Convolutional networks for biomedical image segmentation,\u201d in Proc. MICCAI, 2015.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"2364_CR5","doi-asserted-by":"crossref","unstructured":"F.\u00a0Isensee et al., \u201cnnU-Net: a self-configuring method for deep learning-based biomedical image segmentation,\u201d Nat. Methods, vol.\u00a018, pp.\u00a0203\u2013211, 2021.","DOI":"10.1038\/s41592-020-01008-z"},{"key":"2364_CR6","doi-asserted-by":"crossref","unstructured":"J.\u00a0Wasserthal et al., \u201cTotalSegmentator: robust segmentation of 104 anatomical structures in CT images,\u201d Radiol. Artif. Intell., vol.\u00a05, no.\u00a05, art.\u00a0e230024, 2023.","DOI":"10.1148\/ryai.230024"},{"key":"2364_CR7","unstructured":"Multimodal and multiethnic thigh-muscle MRI dataset and segmentation tool (HuashanMyo Han-Chinese, Folkh\u00e4lsan, and MyoSegmenTUM cohorts; $$11$$ labelled thigh muscles), code and data repository, Apache-2.0 licence, https:\/\/github.com\/Hirriririir\/Multimodal-Multiethnic-Thigh-Muscle-MRI-analysis (accessed 2026). Only the HuashanMyo cohort is used in this work."},{"key":"2364_CR8","doi-asserted-by":"publisher","unstructured":"MuscleMap Consortium, \u201cMuscleMap: an open-source, community-supported consortium for whole-body quantitative MRI of muscle,\u201d J. Imaging, vol.\u00a010, no.\u00a011, art.\u00a0262, 2024, https:\/\/doi.org\/10.3390\/jimaging10110262. Repository: https:\/\/github.com\/MuscleMap\/MuscleMap.","DOI":"10.3390\/jimaging10110262"},{"key":"2364_CR9","doi-asserted-by":"crossref","unstructured":"Z.\u00a0Ma et al., \u201cAATTCT-IDS: A benchmark abdominal adipose tissue CT image dataset for image denoising, semantic segmentation, and radiomics evaluation,\u201d Comput. Biol. Med., vol.\u00a0177, art.\u00a0108628, 2024.","DOI":"10.1016\/j.compbiomed.2024.108628"},{"key":"2364_CR10","doi-asserted-by":"crossref","unstructured":"D.\u00a0Karimi, S.\u00a0K. Warfield, and A.\u00a0Gholipour, \u201cTransfer learning in medical image segmentation: New insights from analysis of the dynamics of model parameters and learned representations,\u201d Artif. Intell. Med., vol.\u00a0116, art.\u00a0102078, 2021.","DOI":"10.1016\/j.artmed.2021.102078"},{"key":"2364_CR11","unstructured":"M.\u00a0Raghu, C.\u00a0Zhang, J.\u00a0Kleinberg, and S.\u00a0Bengio, \u201cTransfusion: Understanding transfer learning for medical imaging,\u201d in Proc. NeurIPS, 2019."},{"key":"2364_CR12","doi-asserted-by":"crossref","unstructured":"M.\u00a0Bibars et al., \u201cCross-modality transfer learning from CT to MRI for liver segmentation,\u201d in Proc. MIUA, 2023.","DOI":"10.1007\/978-3-031-48593-0_7"},{"key":"2364_CR13","doi-asserted-by":"crossref","unstructured":"Q.\u00a0Dou et al., \u201cUnsupervised cross-modality domain adaptation of ConvNets for biomedical image segmentation with adversarial loss,\u201d in Proc. IJCAI, 2018.","DOI":"10.24963\/ijcai.2018\/96"},{"key":"2364_CR14","doi-asserted-by":"crossref","unstructured":"Y.\u00a0Huo et al., \u201cSynSeg-Net: Synthetic segmentation without target modality ground truth,\u201d IEEE Trans. Med. Imag., vol.\u00a038, no.\u00a04, pp.\u00a01016\u20131025, 2019.","DOI":"10.1109\/TMI.2018.2876633"},{"key":"2364_CR15","unstructured":"H.\u00a0H\u00e4ntze et al., \u201cMRSegmentator: multi-modality segmentation of 40 classes in MRI and CT,\u201d arXiv:2405.06463, 2024."},{"key":"2364_CR16","doi-asserted-by":"publisher","unstructured":"N.\u00a0Casali et al., \u201cPositional contrastive learning for improved thigh muscle segmentation in MR images,\u201d NMR Biomed., vol.\u00a037, no.\u00a010, art.\u00a0e5197, 2024, https:\/\/doi.org\/10.1002\/nbm.5197.","DOI":"10.1002\/nbm.5197."},{"key":"2364_CR17","doi-asserted-by":"crossref","unstructured":"S.\u00a0Azizi et al., \u201cBig self-supervised models advance medical image classification,\u201d in Proc. IEEE\/CVF ICCV, 2021.","DOI":"10.1109\/ICCV48922.2021.00346"},{"key":"2364_CR18","doi-asserted-by":"publisher","unstructured":"A.\u00a0C. Srinivasa et al., \u201cAI-driven MR thigh scan analysis for body composition phenotypic classification of healthy older persons,\u201d Eur. J. Radiol. Artif. Intell., vol.\u00a05, art.\u00a0100049, 2025, https:\/\/doi.org\/10.1016\/j.ejrai.2025.100049.","DOI":"10.1016\/j.ejrai.2025.100049."},{"key":"2364_CR19","doi-asserted-by":"publisher","unstructured":"A.\u00a0C. Srinivasa et al., \u201cGAN-MRI enhanced multi-organ MRI segmentation: a deep learning perspective,\u201d Radiol. Phys. Technol., vol.\u00a018, no.\u00a04, pp.\u00a0949\u2013971, 2025, https:\/\/doi.org\/10.1007\/s12194-025-00938-7.","DOI":"10.1007\/s12194-025-00938-7."},{"key":"2364_CR20","doi-asserted-by":"crossref","unstructured":"M.\u00a0Hayat, S.\u00a0Aramvith, S.\u00a0Bhattacharjee, and N.\u00a0Ahmad, \u201cAttention GhostUNet++: Enhanced segmentation of adipose tissue and liver in CT images,\u201d arXiv:2504.11491, 2025.","DOI":"10.1109\/EMBC58623.2025.11254588"},{"key":"2364_CR21","doi-asserted-by":"publisher","unstructured":"V.\u00a0Wohlfarth, Y.\u00a0M. Kway, A.\u00a0Sood et al., \u201cDeep learning-based framework for comprehensive quantification of thigh and calf muscles and adipose tissues from MRI,\u201d Magn. Reson. Mater. Phys., vol.\u00a039, pp.\u00a0305\u2013318, 2026, https:\/\/doi.org\/10.1007\/s10334-025-01308-5.","DOI":"10.1007\/s10334-025-01308-5."},{"key":"2364_CR22","doi-asserted-by":"publisher","unstructured":"A.\u00a0Agosti et al., \u201cDeep learning for automatic segmentation of thigh and leg muscles from MRI,\u201d Magn. Reson. Mater. Phys., vol.\u00a035, no.\u00a03, pp.\u00a0467\u2013483, 2022, https:\/\/doi.org\/10.1007\/s10334-021-00967-4.","DOI":"10.1007\/s10334-021-00967-4."},{"key":"2364_CR23","doi-asserted-by":"crossref","unstructured":"H.\u00a0Guan and M.\u00a0Liu, \u201cDomain adaptation for medical image analysis: a survey,\u201d IEEE Trans. Biomed. Eng., vol.\u00a069, no.\u00a03, pp.\u00a01173\u20131185, 2022.","DOI":"10.1109\/TBME.2021.3117407"},{"key":"2364_CR24","doi-asserted-by":"crossref","unstructured":"Z.\u00a0Zhou et al., \u201cUNet++: A nested U-Net architecture for medical image segmentation,\u201d in Proc. DLMIA, 2018.","DOI":"10.1007\/978-3-030-00889-5_1"},{"key":"2364_CR25","doi-asserted-by":"crossref","unstructured":"L.-C. Chen et al., \u201cEncoder-decoder with atrous separable convolution for semantic image segmentation,\u201d in Proc. ECCV, 2018.","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"2364_CR26","unstructured":"E.\u00a0Xie et al., \u201cSegFormer: Simple and efficient design for semantic segmentation with transformers,\u201d in Proc. NeurIPS, 2021."},{"key":"2364_CR27","doi-asserted-by":"crossref","unstructured":"J.\u00a0Wang et al., \u201cDeep high-resolution representation learning for visual recognition,\u201d IEEE Trans. Pattern Anal. Mach. Intell., vol.\u00a043, no.\u00a010, pp.\u00a03349\u20133364, 2021.","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"2364_CR28","unstructured":"J.\u00a0Chen et al., \u201cTransUNet: Transformers make strong encoders for medical image segmentation,\u201d arXiv:2102.04306, 2021."},{"key":"2364_CR29","doi-asserted-by":"crossref","unstructured":"J.\u00a0Hu, L.\u00a0Shen, and G.\u00a0Sun, \u201cSqueeze-and-excitation networks,\u201d in Proc. IEEE\/CVF CVPR, 2018.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"2364_CR30","doi-asserted-by":"crossref","unstructured":"W.-G. Chang et al., \u201cDomain-specific batch normalization for unsupervised domain adaptation,\u201d in Proc. IEEE\/CVF CVPR, 2019.","DOI":"10.1109\/CVPR.2019.00753"},{"key":"2364_CR31","doi-asserted-by":"crossref","unstructured":"W.\u00a0T. Dixon, \u201cSimple proton spectroscopic imaging,\u201d Radiology, vol.\u00a0153, no.\u00a01, pp.\u00a0189\u2013194, 1984.","DOI":"10.1148\/radiology.153.1.6089263"},{"key":"2364_CR32","doi-asserted-by":"crossref","unstructured":"S.\u00a0B. Reeder, H.\u00a0H. Hu, and C.\u00a0B. Sirlin, \u201cProton density fat-fraction: a standardized MR-based biomarker of tissue fat concentration,\u201d J. Magn. Reson. Imaging, vol.\u00a036, no.\u00a05, pp.\u00a01011\u20131014, 2012.","DOI":"10.1002\/jmri.23741"},{"key":"2364_CR33","unstructured":"I.\u00a0Loshchilov and F.\u00a0Hutter, \u201cDecoupled weight decay regularization,\u201d in Proc. ICLR, 2019."},{"key":"2364_CR34","doi-asserted-by":"crossref","unstructured":"F.\u00a0Milletari, N.\u00a0Navab, and S.-A. Ahmadi, \u201cV-Net: Fully convolutional neural networks for volumetric medical image segmentation,\u201d in Proc. 3DV, 2016.","DOI":"10.1109\/3DV.2016.79"},{"key":"2364_CR35","doi-asserted-by":"crossref","unstructured":"O.\u00a0Russakovsky et al., \u201cImageNet large scale visual recognition challenge,\u201d Int. J. Comput. Vis., vol.\u00a0115, pp.\u00a0211\u2013252, 2015.","DOI":"10.1007\/s11263-015-0816-y"},{"key":"2364_CR36","doi-asserted-by":"crossref","unstructured":"K.\u00a0He, X.\u00a0Zhang, S.\u00a0Ren, and J.\u00a0Sun, \u201cDeep residual learning for image recognition,\u201d in Proc. IEEE CVPR, 2016.","DOI":"10.1109\/CVPR.2016.90"},{"key":"2364_CR37","doi-asserted-by":"crossref","unstructured":"Y.\u00a0Wu and K.\u00a0He, \u201cGroup normalization,\u201d in Proc. ECCV, 2018.","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"2364_CR38","unstructured":"D.\u00a0Ulyanov, A.\u00a0Vedaldi, and V.\u00a0Lempitsky, \u201cInstance normalization: the missing ingredient for fast stylization,\u201d arXiv:1607.08022, 2016."},{"key":"2364_CR39","unstructured":"I.\u00a0Loshchilov and F.\u00a0Hutter, \u201cSGDR: Stochastic gradient descent with warm restarts,\u201d in Proc. ICLR, 2017."},{"key":"2364_CR40","unstructured":"P.\u00a0Micikevicius et al., \u201cMixed precision training,\u201d in Proc. ICLR, 2018."},{"key":"2364_CR41","unstructured":"S.\u00a0Holm, \u201cA simple sequentially rejective multiple test procedure,\u201d Scand. J. Stat., vol.\u00a06, no.\u00a02, pp.\u00a065\u201370, 1979."},{"key":"2364_CR42","doi-asserted-by":"crossref","unstructured":"D.\u00a0J. Schuirmann, \u201cA comparison of the two one-sided tests procedure and the power approach for assessing the equivalence of average bioavailability,\u201d J. Pharmacokinet. Biopharm., vol.\u00a015, pp.\u00a0657\u2013680, 1987.","DOI":"10.1007\/BF01068419"},{"key":"2364_CR43","doi-asserted-by":"crossref","unstructured":"K.\u00a0He et al., \u201cMasked autoencoders are scalable vision learners,\u201d in Proc. IEEE\/CVF CVPR, 2022.","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"2364_CR44","doi-asserted-by":"crossref","unstructured":"P.\u00a0E. Shrout and J.\u00a0L. Fleiss, \u201cIntraclass correlations: uses in assessing rater reliability,\u201d Psychol. Bull., vol.\u00a086, no.\u00a02, pp.\u00a0420\u2013428, 1979.","DOI":"10.1037\/0033-2909.86.2.420"},{"key":"2364_CR45","doi-asserted-by":"crossref","unstructured":"J.\u00a0M. Bland and D.\u00a0G. Altman, \u201cStatistical methods for assessing agreement between two methods of clinical measurement,\u201d Lancet, vol.\u00a0327, no.\u00a08476, pp.\u00a0307\u2013310, 1986.","DOI":"10.1016\/S0140-6736(86)90837-8"},{"key":"2364_CR46","doi-asserted-by":"crossref","unstructured":"J.\u00a0Ma et al., \u201cSegment anything in medical images,\u201d Nat. Commun., vol.\u00a015, art.\u00a0654, 2024.","DOI":"10.1038\/s41467-024-44824-z"}],"container-title":["Journal of Imaging Informatics in Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10278-026-02364-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10278-026-02364-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10278-026-02364-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,19]],"date-time":"2026-10-19T16:33:10Z","timestamp":1792427590000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10278-026-02364-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,19]]},"references-count":46,"alternative-id":["2364"],"URL":"https:\/\/doi.org\/10.1007\/s10278-026-02364-6","relation":{},"ISSN":["2948-2933"],"issn-type":[{"value":"2948-2933","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,19]]},"assertion":[{"value":"22 July 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 September 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 September 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 October 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"This study used only publicly available, de-identified datasets released under their respective licences and involved no new recruitment or acquisition of human-participant data; no additional ethical approval was required.","order":1,"name":"Ethics","label":"Ethics Approval","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable. The study used publicly available, de-identified data and did not involve the recruitment of new human participants; no additional informed consent was required.","order":2,"name":"Ethics","label":"Consent to Participate","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable. This article does not contain any individual person\u2019s identifiable data in any form.","order":3,"name":"Ethics","label":"Consent for Publication","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","label":"Conflict of Interest","group":{"name":"EthicsHeading","label":"Declarations"}}]}}