Deep Learning Enables Large-Scale Shape and Appearance Modeling in Total-Body DXA Imaging
By: Arianna Bunnell , Devon Cataldi , Yannik Glaser and more
Potential Business Impact:
Helps doctors understand body health from X-rays.
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.
Similar Papers
Deep Learning-Based BMD Estimation from Radiographs with Conformal Uncertainty Quantification
CV and Pattern Recognition
Finds bone weakness from knee X-rays.
Predicting Anthropometric Body Composition Variables Using 3D Optical Imaging and Machine Learning
Machine Learning (CS)
Measures body fat and muscle from 3D pictures.
A weakly-supervised deep learning model for fast localisation and delineation of the skeleton, internal organs, and spinal canal on Whole-Body Diffusion-Weighted MRI (WB-DWI)
CV and Pattern Recognition
Helps doctors find cancer faster using body scans.