Deep Learning Enables Large-Scale Shape and Appearance Modeling in Total-Body DXA Imaging

TL;DR

This paper introduces a deep learning approach for automatic keypoint placement on total-body DXA scans, enabling large-scale shape and appearance modeling that correlates with health markers and supports new health-related hypotheses.

Contribution

The study develops and validates a deep learning method for automatic fiducial point placement on TBDXA scans, facilitating large-scale shape and appearance modeling linked to health outcomes.

Findings

Achieved 99.5% correct keypoints on external dataset.

Identified associations between shape features and health biomarkers.

Generated new hypotheses on body composition and health relationships.

Abstract

Total-body dual X-ray absorptiometry (TBDXA) imaging is a relatively low-cost whole-body imaging modality, widely used for body composition assessment. We develop and validate a deep learning method for automatic fiducial point placement on TBDXA scans using 1,683 manually-annotated TBDXA scans. The method achieves 99.5% percentage correct keypoints in an external testing dataset. To demonstrate the value for shape and appearance modeling (SAM), our method is used to place keypoints on 35,928 scans for five different TBDXA imaging modes, then associations with health markers are tested in two cohorts not used for SAM model generation using two-sample Kolmogorov-Smirnov tests. SAM feature distributions associated with health biomarkers are shown to corroborate existing evidence and generate new hypotheses on body composition and shape's relationship to various frailty, metabolic, inflammation, and cardiometabolic health markers. Evaluation scripts, model weights, automatic point file generation code, and triangulation files are available at https://github.com/hawaii-ai/dxa-pointplacement.