3D Human Body Surface Reconstruction and Composition Assessment
Open AccessBody composition can be assessed in many different ways. High-end medical equipment, such as Dual-energy X-ray Absorptiometry (DXA), Computed Tomography (CT) and Magnetic Resonance Imaging (MRI), offers high-fidelity two-dimensional (2D) pixel-level or three-dimensional (3D) voxel-level assessment but is prohibitive in cost. In the case of DXA and CT, the approach exposes users to ionizing radiation. Whole-body Air Displacement Plethysmography (BOD POD) can accurately estimate body density, but the assessment is limited to the whole-body Body Fat Percentage (BFP). In the last decade, 3D modeling techniques enjoyed a booming development in both hardware and software. Optical 3D human body surface scan and reconstruction techniques, such as using depth cameras, have brought new opportunities for improving body composition assessment by intelligently analyzing body shape features. In this dissertation, we first present a cost-effective and easy-to-use 3D body reconstruction system using consumer-grade depth sensors, which provides reconstructed body shapes with a high degree of accuracy and reliability appropriate for medical applications. Our surface registration framework integrates the articulated motion assumption, global loop closure constraint, and a general as-rigid-as-possible deformation model. We designed and conducted a rigorous accuracy validation test for the proposed non-rigid human body reconstruction system. Our results show excellent agreement between the measurements obtained from the 3D reconstruction and those that were obtained manually.Then we present shape-based body composition prediction models to assess body composition in different dimensionalities and functionalities.In the one-dimensional body composition prediction, i.e., the whole-body BFP prediction, we introduce the novel concept of “visual cue” by analyzing the second-order shape descriptors—surface curvature, which effectively reflects the degree of leanness of the body shape. We first establish our baseline regression model for feature selection of the zeroth-order shape descriptors. Then, we use the visual cue as a shape-prior to improve the baseline prediction. We compare our results with the clinical BFP estimation instrument—the BOD POD. The result shows that our prediction model, on the average, outperforms the BOD POD by 20.28% in prediction accuracy. In the two-dimensional body composition prediction, we present a novel supervised inference model to predict the pixel-level body composition using 3D geometry features and body density. First, we use body density to model a fat distribution base prediction. Then, we use a Bayesian network to infer the probability of the base prediction bias with 3D geometry features. Finally, we correct the bias using non-parametric regression. We compare our method, in terms of pixel-level body composition assessment, with the current state-of-the-art prediction models. Our method outperforms those prediction models by 52.69% on average. In the three-dimensional body composition prediction, we present a novel shape-based voxel-level body composition extrapolation method using multimodality registration. First, we optimize shape compliance between a generic body composition template and the 3D body shape. Then, we optimize data compliance between the shape-optimized body composition template and a body composition reference from the DXA pixel-level body composition assessment. We evaluate the performance of our method with different subjects. On average, the Root Mean Square Error (RMSE) of our body composition extrapolation is 1.19%, and the R-squared value between our estimation and the ground truth is 0.985. The experimental result showsthat our algorithm can robustly estimate voxel-level body composition for 3D body shapes with a high degree of accuracy.In the visceral adipose tissue (VAT) prediction, we first present a highly innovative functional feature selection method for the VAT prediction. Our method selects the optimal sub-interval, i.e., region of interest (ROI), of a functional feature. For each sub-interval, we evaluate the overfitting risk by calculating the necessary sample size to achieve a specified statistical power. Combining with a model accuracy measure, we rank these sub-intervals and select the ROI. The proposed method has been compared with other state-of-the-art feature selection methods and the results show that our proposed ROI selection method achieves the best performance. Then, based on the ROI selected, we propose an innovative shape-based hybrid VAT prediction model. The most appealing benefit of our method is to robustly handle the lack of knowledge about gender and demographics. First, we train a baseline VAT prediction model for each gender separately. Second, we train a classifier to predict the gender likelihood and a classifier to predict the shape likelihood of being overestimated in VAT baseline prediction. Third, we integrate the gender likelihood and shape likelihood into the baseline models to derive one hybrid VAT prediction model. We compare our prediction model with other state-of-the-art VAT prediction methods. The result shows that our method outperforms the comparison methods by 21.8% on average.
- All rights reserved
Notice to Authors
If you are the author of this work and you have any questions about the information on this page, please use the Contact form to get in touch with us.