In this paper, we propose a novel two-level regression method for computing body mass distribution from a database of X-ray images, without scanning the new subject. Our approach first selects a suitable sample from the image database by minimizing a distance function based on the relationships between the new subject's body measurements and those of sample subjects. The X-ray image of the new subject is then predicted from the sample image using a feature-based transformation. Body mass distribution is computed directly from the predicted X-ray image. Our results surpass the accuracy of commonly used mass distribution regression methods in biomechanics literatures. In addition, by not scanning the new subject, we avoid all the radiation and cost involved in X-ray absorptiometry.

We address the volumetric reconstruction problem that takes as input a series of orthographic multi-energy x-ray images, producing as output a reconstructed model space consisting of uniform-size mass density voxels. Our approach solves the non-linear constrained optimization for mulation problem by constructing a compliant estimate of volumetric distribution, subject to projective and domain constraints, and minimizes variational irregularities. To resolve the inherent ambiguities of single-view formulation, an optional shape model may be introduced to aid the reconstruction process. We demonstrate our method’s practical usage as a new in-vivo method for estimating three dimensional body segmental compositions, and compare its results with those of existing methods.