A Simultaneous Framework for Recovering Three Dimensional Shape and Nonrigid Motion from Cardiac Image Sequences

Quantitative assessment of the shape and motion variability of the heart has important implications for the diagnosis and treatment of cardiac diseases. In this paper, we present a unified methodology which simultaneously recovers the shape and motion of the left ventricle, including the endo-, epi-, and mid-wall myocardium. The left ventricle is modeled as an isotropic linear elastic material, and represented by volumetric mesh constructed from the Delaunay triangulation of the sampling points. Specifically, the evolution forces imposed on the myocardium are individually constructed for each nodal point through the integration of the data-driven edginess measures, the prior spatial distributions of the myocardial tissues, the temporal coherence of the image-derived salient features, and the cyclic motion characteristics of the heart. The dense displacement field can then be estimated when the total energy of the elastic body is minimized at equilibrium. Experiments on 3D human magnetic resonance image sequences of healthy and pathological subjects show the accuracy and robustness of the strategy