Deep Learning Enables Large-Scale Shape and Appearance Modeling in Total-Body DXA Imaging
This work addresses the need for efficient and accurate body composition analysis in medical imaging, though it is incremental as it applies deep learning to an existing imaging modality.
The researchers tackled the problem of automating fiducial point placement on total-body DXA scans for body composition assessment, achieving 99.5% accuracy in keypoint placement on an external test dataset. They applied this method to analyze shape and appearance associations with health markers, generating new hypotheses on relationships to frailty, metabolic, and cardiometabolic health.
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.