Deep Learning Enables Large-Scale Shape and Appearance Modeling in Total-Body DXA Imaging
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915446118154240 |
|---|---|
| author | Bunnell, Arianna Cataldi, Devon Glaser, Yannik Wolfgruber, Thomas K. Heymsfield, Steven Zonderman, Alan B. Kelly, Thomas L. Sadowski, Peter Shepherd, John A. |
| author_facet | Bunnell, Arianna Cataldi, Devon Glaser, Yannik Wolfgruber, Thomas K. Heymsfield, Steven Zonderman, Alan B. Kelly, Thomas L. Sadowski, Peter Shepherd, John A. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_10132 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Deep Learning Enables Large-Scale Shape and Appearance Modeling in Total-Body DXA Imaging Bunnell, Arianna Cataldi, Devon Glaser, Yannik Wolfgruber, Thomas K. Heymsfield, Steven Zonderman, Alan B. Kelly, Thomas L. Sadowski, Peter Shepherd, John A. Computer Vision and Pattern Recognition 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. |
| title | Deep Learning Enables Large-Scale Shape and Appearance Modeling in Total-Body DXA Imaging |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.10132 |