A device‐agnostic shape model for automated body composition estimates from 3D optical scans

Abstract

Background: Many predictors of morbidity caused by metabolic disease are associated with body shape. 3D optical (3DO) scanning captures body shape and has been shown to accurately and precisely predict body composition variables associated with mortality risk. 3DO is safer, less expensive, and more accessible than criterion body composition assessment methods such as dual-energy X-ray absorptiometry (DXA). However, 3DO scanning has not been standardized across manufacturers for pose, mesh resolution, and post processing methods. Purpose: We introduce a scanner-agnostic algorithm that automatically fits a topologically consistent human mesh to 3DO scanned point clouds and predicts clinically important body metrics using a standardized body shape model. Our models transform raw scans captured by any 3DO scanner into fixed topology meshes with anatomical consistency, standardizing the outputs of 3DO scans across manufacturers and allowing for the use of common prediction models across scanning devices. Methods: A fixed-topology body mesh template was automatically registered to 848 training scans from three different 3DO systems. Participants were between 18 and 89 years old with body mass index ranging from 14 to 52 kg/m 2 . Scans were registered by first performing a coarse nearest neighbor alignment between the template and the input scan with an anatomically constrained principal component analysis (PCA) domain deformation using a device and gender specific bootstrap basis trained on 70 seed scans each. The template mesh was then optimized to fit the target with a smooth per-vertex surface-to-surface deformation. A combined unified PCA model was created from the superset of all automatically fit training scans including all three devices. Body composition predictions to DXA measurements were learned from the training mesh PCA coefficients using linear regression. Using this final unified model, we tested the accuracy of our body composition models on a withheld sample of 562 scans by fitting a PCA parameterized template mesh to each raw scan and predicting the expected body composition metrics from the principal components using the learned regression model. Results: We achieved coefficients of determination (R 2 ) above 0.8 on all nine fat and lean predictions except female visceral fat (0.77). R 2 was as high as 0.94 (total fat and lean, trunk fat), and all root-mean-squared errors were below Abbreviations: 3DO, 3-dimensional optical; 60k, 60 001 vertex mesh template; BMI, body mass index; DXA, dual X-ray absorptiometry; PCA, principal component analysis.

Machine learning-based obesity classification considering 3D body scanner measurements

“…The selected features affect the classification of obesity more than the unselected features. We also compared with the model provided by Tian et al 52 . Denotes, Tian's model is a regression model, not a classification model, and we obtained results by dividing it by the criteria of the Table 3 .…”

Prediction of Total and Regional Body Composition from 3D Body Shape

“…This would provide better prediction of metabolic health and identify people at high risk of disease in the long term so that remedial action can be taken. Significant works in recent years have focused on the development of 3D optical (3DO) scanning 9 to estimate body composition [10][11][12][13] . 3DO scanners use depth sensors by projecting infrared patterns onto the scan subject to rapidly construct a 3D point cloud using multiview stereo, and subsequently capture 3D surface shape information.…”

“…Rather than predicting body composition from anthropometric measurements alone, 3D body shape as a whole provides more visual and implicit cues for predicting body composition more accurately. Additional 3D shape cues can either be additional landmark diameters, circumferences, surface areas and volumes from 3DO scans 14 , or parameters of a PCA shape space [11][12][13] . More recently, Leong et al 15 use a variational autoencoder (VAE) 16 to learn latent DXA encoding, and map 3DO scans to pseudo-DXA images.…”

Accuracy and Precision of 3D Optical Imaging for Body Composition and their Associations to Metabolic Markers by Age, BMI, and Ethnicity

“…They showed that body shape descriptors by the 3DO mesh were more predictive of body composition as compared to DXA and were correlated to metabolic biomarkers (23). Since then, the methodology to obtain these body shape descriptors have improved by incorporating automated processing methods, agnostic models across multiple 3DO scanners, pose-independent models, and a 2D to 3D pipeline (24)(25)(26)(27). Although much has been accomplished in this field in a short amount of time, 3DO body composition has not been evaluated at the subgroup level.…”