Non-intrusive Body Composition Assessment from Full-body mmWave Scans

2026-05-08

AI Summary

This study addresses the limitations of existing body composition assessment methods—such as CT and MRI—which are costly and invasive, hindering widespread adoption. To overcome these challenges, this work proposes the first use of millimeter-wave radar for non-contact, privacy-preserving body composition estimation. By leveraging both synthetic and real millimeter-wave point clouds in conjunction with a parametric human body model and multi-task learning, the method enables whole-body shape reconstruction without requiring subjects to disrobe, while simultaneously predicting visceral fat volume and body fat percentage. Evaluated on real-world data, the approach achieves mean absolute errors of 1.0 liter for visceral fat volume and 3.2% for body fat percentage, demonstrating its feasibility and accuracy for practical applications.

Abstract

Body composition assessment (BCA) provides detailed information about the distribution of different tissue types in the body, enabling more precise characterization of individuals than BMI or weight alone. Consistent and frequent BCA would be valuable for personalized medicine, but the gold standard methods for BCA, such as CT and MRI, are only practical for opportunistic monitoring of patients with clinical indications for imaging and are not suitable for routine use in the general population. Here, we consider an imaging modality which is not currently used in medical applications: millimeter wave (mmWave) radar. Commonly used in security settings, mmWave scans enable fast, non-intrusive, and privacy-preserving reconstruction of full body shape without the need to remove clothing. To demonstrate the feasibility of fast and convenient BCA from mmWave scans, we present a method for BCA value regression using a multi-task learning strategy that leverages synthetic mmWave-like point clouds derived from clinical imaging and parametric human models. We evaluate the model on a pilot cohort of real mmWave scans with bioimpedance-derived body fat measurements, supporting the feasibility of estimating VAT and body fat percentage (BFP) from mmWave data acquired through clothing in a standing posture. We find that the model can predict VAT and BFP with a mean absolute error of 1.0 L and 3.2\%, respectively, demonstrating the potential of mmWave scanning for routine BCA in a wide range of settings.

Problem

• Body Composition Assessment
• mmWave radar
• non-intrusive
• routine monitoring
• personalized medicine

Innovation

• mmWave radar
• body composition assessment
• non-intrusive sensing
• multi-task learning
• synthetic point clouds