Generative deep learning furthers the understanding of local distributions of fat and muscle on body shape and health using 3D surface scans
Open Access
- 30 January 2024
- journal article
- research article
- Published by Springer Nature in Communications Medicine
- Vol. 4 (1) , 1-9
Abstract
Background: Body shape, an intuitive health indicator, is deterministically driven by body composition. We developed and validated a deep learning model that generates accurate dual-energy X-ray absorptiometry (DXA) scans from three-dimensional optical body scans (3DO), enabling compositional analysis of the whole body and specified subregions. Previous works on generative medical imaging models lack quantitative validation and only report quality metrics.Methods: Our model was self-supervised pretrained on two large clinical DXA datasets and fine-tuned using the Shape Up! Adults study dataset. Model-predicted scans from a holdout test set were evaluated using clinical commercial DXA software for compositional accuracy.Results: Predicted DXA scans achieveR2of 0.73, 0.89, and 0.99 and RMSEs of 5.32, 6.56, and 4.15 kg for total fat mass (FM), fat-free mass (FFM), and total mass, respectively. Custom subregion analysis results inR2s of 0.70–0.89 for left and right thigh composition. We demonstrate the ability of models to produce quantitatively accurate visualizations of soft tissue and bone, confirming a strong relationship between body shape and composition.Conclusions: This work highlights the potential of generative models in medical imaging and reinforces the importance of quantitative validation for assessing their clinical utility.Keywords
Funding Information
- U.S. Department of Health & Human Services | NIH | National Institute of Diabetes and Digestive and Kidney Diseases (R01DK109008)
- Artificial Intelligence/Machine Learning Consortium to Advance Health Equity and Researcher Diversity (AIM-AHEAD) program
This publication has 57 references indexed in Scilit:
- Computational Medicine: Translating Models to Clinical CareScience Translational Medicine, 2012
- The ratio of visceral to subcutaneous fat, a metric of body fat distribution, is a unique correlate of cardiometabolic riskDiabetologia, 2012
- Validation of the body scanner as a measuring tool for a rapid quantification of body shapeSkin Research and Technology, 2009
- 3. Quality and Performance Measures in Bone DensitometryJournal of the ICRU, 2009
- Dual-Energy X-ray Aborptiometry Assessment in Children and Adolescents with Diseases that May Affect the Skeleton: The 2007 ISCD Pediatric Official PositionsJournal of Clinical Densitometry, 2008
- Regional Body Composition Changes Exhibit Opposing Effects on Coronary Heart Disease Risk FactorsArteriosclerosis, Thrombosis, and Vascular Biology, 2004
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004
- Strength and Muscle Quality in a Well‐Functioning Cohort of Older Adults: The Health, Aging and Body Composition StudyJournal of the American Geriatrics Society, 2003
- Accurate assessment of precision errors: How to measure the reproducibility of bone densitometry techniquesOsteoporosis International, 1995
- Bone “mass” and the “mechanostat”: A proposalThe Anatomical Record, 1987