AI Insight
Researchers developed BodyMAE, a self-supervised machine learning system that estimates body composition metrics from low-cost 3D body scans with accuracy approaching clinical-grade DXA scanning. Testing on 917 paired scans and DXA reports, the system achieved strong predictions for fat percentage, fat mass, and lean mass, with root-mean-square errors of 3.8 percentage points, 3.7 kg, and 3.6 kg respectively. The method addresses technical challenges in processing 3D body scan data through surface-area aware sampling and specialized neural network architecture.
Why it matters
This technology could enable frequent, affordable body composition monitoring without radiation exposure, making health tracking more accessible for managing metabolic diseases, sarcopenia, and obesity. The approach offers a practical alternative to expensive DXA scans that require specialized facilities and trained operators.
Understand the Science
⚠️ Preprint – Noch nicht peer-reviewed
Dieser Artikel wurde noch nicht von unabhängigen Experten begutachtet. Die Ergebnisse sind vorläufig und sollten mit Vorsicht interpretiert werden.
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^2 0.908), fat mass (RMSE 3.694 kg, R^2 0.968), and lean mass (RMSE 3.608 kg, R^2 0.901), with competitive performance on bone mineral content (RMSE 0.284 kg, R^2 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.
Source: BodyMAE: A Surface-Area Aware Masked Autoencoder for Body Composition Estimation from 3D Body Scans