{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T10:19:14Z","timestamp":1785406754953,"version":"3.56.0"},"posted":{"date-parts":[[2026,6,6]]},"group-title":"Health Informatics","reference-count":49,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T00:00:00Z","timestamp":1780704000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/publicdomain\/zero\/1.0\/"}],"funder":[{"award":["R01DK129809"],"award-info":[{"award-number":["R01DK129809"]}],"id":[{"id":"https:\/\/ror.org\/00adh9b73","id-type":"ROR","asserted-by":"publisher"}]},{"award":["R56AG089080"],"award-info":[{"award-number":["R56AG089080"]}],"id":[{"id":"https:\/\/ror.org\/049v75w11","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,6,6]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>Accurate assessment of body composition is important to risk stratification and management of metabolic, musculoskeletal, and aging-related diseases, yet reference modalities such as Dual-energy X-ray absorptiometry (DXA) are costly and impractical for frequent monitoring. Commodity 3D body scans offer a low-cost, radiation-free alternative, but extracting meaningful and predictive shape features from scans remains challenging due to nonuniform point density, variable body size and cross-device differences. We introduce BodyMAE, a self-supervised, surface-area aware masked autoencoder for metric-scale 3D body scans. The pipeline integrates area-adjusted sampling, a long-range focused encoder, and a lightweight decoder regularized to promote locally uniform reconstructions. Trained and evaluated on 917 paired 3D body scans paired with clinical DXA reports, BodyMAE achieves strong accuracy on fat percentage (root-mean-square error (RMSE) 3.825 percentage points, R\u00b2 0.908), fat mass (RMSE 3.694 kg, R\u00b2 0.968), and lean mass (RMSE 3.608 kg, R\u00b2 0.901), with competitive performance on bone mineral content (RMSE 0.284 kg, R\u00b2 0.754).We also assess feature stability across pretrained baselines, finding higher retrieval accuracy for our representations (Top-1 90.131%). These results indicate that combining metric-aware sampling, long-range relational encoding, and local geometric regularization enables accurate body composition estimation from 3D body scans, as validated by comparisons to DXA-derived measurements.<\/jats:p>","DOI":"10.64898\/2026.06.04.26354925","type":"posted-content","created":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T21:45:16Z","timestamp":1780782316000},"source":"Crossref","is-referenced-by-count":0,"title":["BodyMAE: A Surface-Area Aware Masked Autoencoder for Body Composition Estimation from 3D Body Scans"],"prefix":"10.64898","author":[{"given":"Yijiang","family":"Zheng","sequence":"first","affiliation":[{"name":"Department of Computer Science, The George Washington University, Washington, DC, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Boyuan","family":"Feng","sequence":"additional","affiliation":[{"name":"Department of Computer Science, The George Washington University, Washington, DC, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruting","family":"Cheng","sequence":"additional","affiliation":[{"name":"Department of Computer Science, The George Washington University, Washington, DC, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuhui","family":"Qiu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, The George Washington University, Washington, DC, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuoxin","family":"Long","sequence":"additional","affiliation":[{"name":"Department of Statistics, The George Washington University, Washington, DC, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Khashayar","family":"Vaziri","sequence":"additional","affiliation":[{"name":"Department of Surgery, The George Washington University Medical Faculty Associates, Washington, DC, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James","family":"Hahn","sequence":"additional","affiliation":[{"name":"Department of Computer Science, The George Washington University, Washington, DC, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026060904051286000_2026.06.04.26354925v1.1","doi-asserted-by":"crossref","unstructured":"Oh, Y. H. et al. Changes in Body Composition Are Associated with Metabolic Changes and the Risk of Metabolic Syndrome. Journal of Clinical Medicine 10, 745 (2021).","DOI":"10.3390\/jcm10040745"},{"key":"2026060904051286000_2026.06.04.26354925v1.2","doi-asserted-by":"crossref","unstructured":"Nematollahi, M. A. et al. Body composition predicts hypertension using machine learning methods: a cohort study. Scientific reports 13, (2023).","DOI":"10.1038\/s41598-023-34127-6"},{"key":"2026060904051286000_2026.06.04.26354925v1.3","first-page":"678","article-title":"Increased Visceral Adipose Tissue Is an Independent Predictor for Future Development of Atherogenic Dyslipidemia","volume":"101","year":"2015","journal-title":"The Journal of Clinical Endocrinology & Metabolism"},{"key":"2026060904051286000_2026.06.04.26354925v1.4","doi-asserted-by":"crossref","first-page":"463","DOI":"10.3390\/livers3030033","article-title":"Relationship between Non-Alcoholic Fatty Liver Disease and Visceral Fat Measured by Imaging-Based Body Composition Analysis: A Systematic Review","volume":"3","year":"2023","journal-title":"Livers"},{"key":"2026060904051286000_2026.06.04.26354925v1.5","doi-asserted-by":"crossref","unstructured":"Moon, J. S. , Yoon, J. S. , Won, K. C. & Lee, H. W . The Role of Skeletal Muscle in Development of Nonalcoholic Fatty Liver Disease. Diabetes & Metabolism Journal 37, 278 (2013).","DOI":"10.4093\/dmj.2013.37.4.278"},{"key":"2026060904051286000_2026.06.04.26354925v1.6","doi-asserted-by":"crossref","unstructured":"Smit, A. E. , Meijer, O. C. & Winter, E. M . The multi-faceted nature of age-associated osteoporosis. Bone Reports 20, 101750 (2024).","DOI":"10.1016\/j.bonr.2024.101750"},{"key":"2026060904051286000_2026.06.04.26354925v1.7","doi-asserted-by":"publisher","DOI":"10.1093\/ageing\/afy169"},{"key":"2026060904051286000_2026.06.04.26354925v1.8","doi-asserted-by":"crossref","unstructured":"Fumagalli, I. A. et al. Automated CT Analysis of Body Composition as a Frailty Biomarker in Abdominal Surgery. JAMA Surgery 159, 766 (2024).","DOI":"10.1001\/jamasurg.2024.0628"},{"key":"2026060904051286000_2026.06.04.26354925v1.9","doi-asserted-by":"publisher","DOI":"10.3390\/nu13082493"},{"key":"2026060904051286000_2026.06.04.26354925v1.10","doi-asserted-by":"crossref","first-page":"1265","DOI":"10.1038\/ejcn.2016.109","article-title":"Clinical anthropometrics and body composition from 3D whole-body surface scans","volume":"70","year":"2016","journal-title":"European journal of clinical nutrition"},{"key":"2026060904051286000_2026.06.04.26354925v1.11","doi-asserted-by":"crossref","first-page":"848","DOI":"10.1109\/JBHI.2024.3510519","article-title":"D3BT: Dynamic 3D Body Transformer for Body Fat Percentage Assessment","volume":"29","year":"2025","journal-title":"IEEE journal of biomedical and health informatics"},{"key":"2026060904051286000_2026.06.04.26354925v1.12","doi-asserted-by":"crossref","unstructured":"Tian, I. Y. , et al. 3D convolutional deep learning for nonlinear estimation of body composition from whole body morphology. npj Digital Medicine 8, (2025).","DOI":"10.1038\/s41746-025-01469-6"},{"key":"2026060904051286000_2026.06.04.26354925v1.13","doi-asserted-by":"publisher","DOI":"10.1016\/j.jocd.2013.08.018"},{"key":"2026060904051286000_2026.06.04.26354925v1.14","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-010-1845-0"},{"key":"2026060904051286000_2026.06.04.26354925v1.15","first-page":"2716","article-title":"Liver Fat Assessment with Body Shape","volume":"2022","year":"2022","journal-title":"Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference"},{"key":"2026060904051286000_2026.06.04.26354925v1.16","doi-asserted-by":"crossref","unstructured":"Zheng, Y. , Zhang, X. , Hahn, J. K. & Long, Z . 3D Body shape for regional and appendicular body composition estimation. Proceedings of SPIE--the International Society for Optical Engineering 12464, 92 (2023).","DOI":"10.1117\/12.2653964"},{"key":"2026060904051286000_2026.06.04.26354925v1.17","doi-asserted-by":"crossref","first-page":"872","DOI":"10.1038\/s41430-023-01289-5","article-title":"Translating digital anthropometry measurements obtained from different 3D body image scanners","volume":"77","year":"2023","journal-title":"European Journal of Clinical Nutrition"},{"key":"2026060904051286000_2026.06.04.26354925v1.18","doi-asserted-by":"crossref","first-page":"972","DOI":"10.1038\/s41430-023-01309-4","article-title":"Associations between 3D surface scanner derived anthropometric measurements and body composition in a cross-sectional study","volume":"77","year":"2023","journal-title":"European Journal of Clinical Nutrition"},{"key":"2026060904051286000_2026.06.04.26354925v1.19","doi-asserted-by":"crossref","first-page":"59","DOI":"10.5152\/erp.2023.22135185","article-title":"Clinical Role of Three-Dimensional Body Scanners in Presenting Direct Anthropometrics for Estimation of Body Composition: Three-Dimensional Body Scanner and Body Composition","volume":"27","year":"2023","journal-title":"Endocrinology Research and Practice"},{"key":"2026060904051286000_2026.06.04.26354925v1.20","first-page":"4338","article-title":"Deep Learning for 3D Point Clouds: A Survey","volume":"43","year":"2020","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2026060904051286000_2026.06.04.26354925v1.21","doi-asserted-by":"crossref","first-page":"4997","DOI":"10.1109\/TVCG.2023.3281781","article-title":"What\u2019s the Situation With Intelligent Mesh Generation: A Survey and Perspectives","volume":"30","year":"2024","journal-title":"IEEE transactions on visualization and computer graphics"},{"key":"2026060904051286000_2026.06.04.26354925v1.22","doi-asserted-by":"crossref","unstructured":"Yip, M. , Stahl, A. & Schellewald, C . Robust Hole-Detection in Triangular Meshes Irrespective of the Presence of Singular Vertices. Computer-Aided Design 170, 103696 (2024).","DOI":"10.1016\/j.cad.2024.103696"},{"key":"2026060904051286000_2026.06.04.26354925v1.23","doi-asserted-by":"crossref","unstructured":"Wong, M. C. et al. Evaluation of body shape as a human body composition assessment in isolated conditions and remote environments. npj Microgravity 10, (2024).","DOI":"10.1038\/s41526-024-00412-5"},{"key":"2026060904051286000_2026.06.04.26354925v1.24","doi-asserted-by":"crossref","unstructured":"Qiao, C. , et al. Prediction of total and regional body composition from 3D body shape. npj Digital Medicine 7, (2024).","DOI":"10.1038\/s41746-024-01289-0"},{"key":"2026060904051286000_2026.06.04.26354925v1.25","unstructured":"Qi, C. R. , Su, H. , Mo, K. & Guibas, L. J . PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation. Proc. IEEE Conf. Comput. Vis. Pattern Recognit. 652\u2013660 (2017)."},{"key":"2026060904051286000_2026.06.04.26354925v1.26","unstructured":"Qi, C. R. , Yi, L. , Su, H. & Guibas, L. J . PointNet++: Deep hierarchical feature learning on point sets in a metric space. Adv. Neural Inf. Process. Syst. 30 (2017)."},{"key":"2026060904051286000_2026.06.04.26354925v1.27","doi-asserted-by":"crossref","unstructured":"Choy, C. , Gwak, J. & Savarese, S . 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. 3070\u20133079 (2019).","DOI":"10.1109\/CVPR.2019.00319"},{"key":"2026060904051286000_2026.06.04.26354925v1.28","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3322958"},{"key":"2026060904051286000_2026.06.04.26354925v1.29","doi-asserted-by":"crossref","unstructured":"Zhao, H. , Jiang, L. , Jia, J. , Torr, P. H. S. & Koltun, V. Point Transformer. In Proc. IEEE\/CVF Int. Conf. Comput. Vis. (ICCV), 16259\u201316268 (2021).","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"2026060904051286000_2026.06.04.26354925v1.30","doi-asserted-by":"crossref","unstructured":"Wu, X. et al. Point Transformer V3: Simpler, Faster, Stronger. Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. 4840\u20134851 (2024).","DOI":"10.1109\/CVPR52733.2024.00463"},{"key":"2026060904051286000_2026.06.04.26354925v1.31","doi-asserted-by":"crossref","unstructured":"Yu, X. et al. Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling. Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. 19313\u201319322 (2022).","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"2026060904051286000_2026.06.04.26354925v1.32","doi-asserted-by":"crossref","unstructured":"Pang, Y. et al. Masked Autoencoders for Point Cloud Self-supervised Learning. In European Conference on Computer Vision (ECCV), 604\u2013621 (2022).","DOI":"10.1007\/978-3-031-20086-1_35"},{"key":"2026060904051286000_2026.06.04.26354925v1.33","first-page":"27061","article-title":"Point-M2AE: Multi-Scale Masked Autoencoders for Hierarchical Point Cloud Pre-Training","volume":"35","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"2026060904051286000_2026.06.04.26354925v1.34","first-page":"574","article-title":"PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding","volume":"12348","year":"2020","journal-title":"European Conference on Computer Vision (ECCV), LNCS"},{"key":"2026060904051286000_2026.06.04.26354925v1.35","doi-asserted-by":"crossref","unstructured":"Wu, Z. et al. 3D ShapeNets: A Deep Representation for Volumetric Shapes. Proc. IEEE Conf. Comput. Vis. Pattern Recognit. 1912\u20131920 (2015).","DOI":"10.1109\/CVPR.2015.7298801"},{"key":"2026060904051286000_2026.06.04.26354925v1.36","unstructured":"Chang, A. X. , et al. ShapeNet: An Information-Rich 3D Model Repository. arXiv preprint arXiv:1512.03012 (2015)."},{"key":"2026060904051286000_2026.06.04.26354925v1.37","doi-asserted-by":"publisher","DOI":"10.1137\/S0036144599352836"},{"key":"2026060904051286000_2026.06.04.26354925v1.38","doi-asserted-by":"crossref","unstructured":"Wang, X. et al. Repulsion Loss: Detecting Pedestrians in a Crowd. Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. 7774\u20137783 (2018).","DOI":"10.1109\/CVPR.2018.00811"},{"key":"2026060904051286000_2026.06.04.26354925v1.39","doi-asserted-by":"crossref","unstructured":"Yu, L. , Li, X. , Fu, C.-W. , Cohen-Or, D. & Heng, P.-A . PU-Net: Point Cloud Upsampling Network. Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. 2790\u20132799 (2018).","DOI":"10.1109\/CVPR.2018.00295"},{"key":"2026060904051286000_2026.06.04.26354925v1.40","doi-asserted-by":"crossref","unstructured":"Yang, Y. et al. Semantic Parametric Reshaping of Human Body Models. In Proc. 2nd Int. Conf. 3D Vision (3DV), 41\u201348 (2014).","DOI":"10.1109\/3DV.2014.47"},{"issue":"5","key":"2026060904051286000_2026.06.04.26354925v1.41","first-page":"7","volume-title":"Proceedings of the 3rd International Digital Human Modeling Conference","volume":"2","year":"2014"},{"key":"2026060904051286000_2026.06.04.26354925v1.42","doi-asserted-by":"crossref","unstructured":"Cheng, R. , et al. Maternal and fetal health status assessment by using machine learning on optical 3D body scans. arXiv preprint arXiv:2504.05627 (2025).","DOI":"10.1007\/s11517-025-03473-0"},{"key":"2026060904051286000_2026.06.04.26354925v1.43","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrad.2016.04.004"},{"key":"2026060904051286000_2026.06.04.26354925v1.44","doi-asserted-by":"crossref","unstructured":"Lu, Y. , Younes, N. , Hahn, J. K. & Zhao, S . Accurate nonrigid 3D human body surface reconstruction using commodity depth sensors. Computer Animation and Virtual Worlds 29, (2018).","DOI":"10.1002\/cav.1807"},{"key":"2026060904051286000_2026.06.04.26354925v1.45","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC53108.2024.10782470"},{"key":"2026060904051286000_2026.06.04.26354925v1.46","first-page":"421","article-title":"Enhanced body composition estimation from 3D body scans","volume":"1","year":"2025","journal-title":"Proceedings of the 18th International Joint Conference on Biomedical Engineering Systems and Technologies"},{"key":"2026060904051286000_2026.06.04.26354925v1.47","first-page":"33330","article-title":"Point transformer v2: Grouped vector attention and partition-based pooling","volume":"35","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"2026060904051286000_2026.06.04.26354925v1.48","doi-asserted-by":"crossref","unstructured":"Huang, D. , Cogill, S. , Hsia, R. Y. , Yang, S. & Kim, D . Development and external validation of a pretrained deep learning model for the prediction of non-accidental trauma. npj Digital Medicine 6, (2023).","DOI":"10.1038\/s41746-023-00875-y"},{"key":"2026060904051286000_2026.06.04.26354925v1.49","doi-asserted-by":"crossref","unstructured":"Huang, S.-C. et al. Self-supervised learning for medical image classification: a systematic review and implementation guidelines. NPJ digital medicine 6, (2023).","DOI":"10.1038\/s41746-023-00811-0"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.06.04.26354925","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T11:05:38Z","timestamp":1781003138000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.64898\/2026.06.04.26354925"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,6]]},"references-count":49,"URL":"https:\/\/doi.org\/10.64898\/2026.06.04.26354925","relation":{},"subject":[],"published":{"date-parts":[[2026,6,6]]},"subtype":"preprint"}}