Predicting 3D body shape and body composition from conventional 2D photography

Abstract

Purpose Total and regional body composition are important indicators of health and mortality risk, but their measurement is usually restricted to controlled environments in clinical settings with expensive and specialized equipment. A method that approaches the accuracy of the current gold standard method, dual‐energy x‐ray absorptiometry (DXA), while only requiring input from widely available consumer grade equipment, would enable the measurement of these important biometrics in the wild, enabling data collection at a scale that would have previously been prohibitive in time and expense. We describe an algorithm for predicting three‐dimensional (3D) body shape and composition from a single frontal 2‐dimensional image acquired with a digital consumer camera. Methods Duplicate 3D optical scans, two‐dimensional (2D) optical images, and DXA whole‐body scans were available for 183 men and 233 women from the Shape Up! Adults Study. A principal component analysis vector basis was fit to 3D point clouds of a training subset of 152 men and 194 women. The relationship between this vector space and DXA‐derived body composition was modeled with linear regression. The principal component 3D shape was then fitted to match a silhouette extracted from a 2D photograph of a novel body. Body composition was predicted from the resulting 3D shape match using the linear mapping between the principal component parameters and the DXA metrics. Accuracy of body composition estimates from the silhouette method was evaluated against a simple model using height and weight as a baseline, and against DXA measurements as ground truth. Test‐retest precision of the silhouette method was evaluated using the duplicate 2D optical images and compared against precision of the duplicate DXA scans. Paired t‐tests were performed to detect significant differences between the sets. Results Results were reported on a held‐out set. Body composition prediction achieved R2s of 0.81 and 0.74 for percent fat prediction of males and females, respectively, on a held‐out test set consisting of 31 males and 39 females. Precision estimates for fat mass were 2.31% and 2.06% for males and females, respectively, compared to 1.26% and 0.68% for DXA scans. The t‐tests revealed no statistically significant differences between the silhouette method measurements and DXA measurements, or between retests. Conclusion Total and regional body composition measures can be estimated from a single frontal photograph of a human body. Body composition prediction using consumer level photography can enable early screening and monitoring of possible physiological indicators of metabolic disease in regions where medical imagery or clinical assessment is inaccessible.

A pose‐independent method for accurate and precise body composition from 3D optical scans

“…High (+3 SD) and low (−3 SD) states of each PC were generated by varying each PC separately with all others held as equal to zero. These PC weight vectors were inverted back to Cartesian space and added to the sex‐specific mean body shape for visualization (26).…”

DXA-Derived Adiposity and Lean Indices for Management of Cardiometabolic and Musculoskeletal Frailty: Data Interpretation Tricks and Reporting Tips

“…Although the authors properly acknowledged that the small sample size limited the strength of their study, they suggested that re-evaluation of DXA body composition calibration standard is required to optimize the accuracy of the method. Consistently, the recent studies performed with a Hologic device reported that the NHANES BCA calibration option was disabled for scan analysis (36)(37)(38)(39). Although further studies are required to establish whether the NHANES BCA calibration option should always be disabled or must be used in the selected subgroups of patients (e.g., obese patients), it is recommended that a serial evaluation of the same patient to assess the body composition changes is performed with the same software configuration (that should be specified in the report).…”

Estimating body fat distribution – a driver of cardiometabolic health – from silhouette images

“…Prior seminal studies have suggested that estimation of fat distribution using various proxies for medical imaging may be feasible, but have several limitations. [19][20][21][22][23][24][25][26][27][28] First, most studies in this area have focused on predicting overall fat and fat-free mass rather than specific fat depots, which is likely to be significantly more diffcult. [19][20][21][22][23]28 Second, no prior study has aimed to predict ratios between fat depots, which are poorly captured by BMI and waist circumference and hence may add the most clinical value.…”

“…[19][20][21][22][23][24][25][26][27][28] First, most studies in this area have focused on predicting overall fat and fat-free mass rather than specific fat depots, which is likely to be significantly more diffcult. [19][20][21][22][23]28 Second, no prior study has aimed to predict ratios between fat depots, which are poorly captured by BMI and waist circumference and hence may add the most clinical value. [24][25][26][27] Third, prior studies in this area have been limited by sample sizes of up to several hundred healthy participants, limiting the ability to perform robust cross-validation.…”