Left ventricle motion estimation for cardiac cine MRI using graph matching

A novel approach based on graph matching for myocardial motion estimation using cine MRI is presented in this paper. The dissimilarity measure between nodes and that between edges are defined to construct a cost function to measure the dissimilarity between two graphs. The sparsity constraint and affine constraint are introduced into the cost function. The alternating direction method of multipliers (ADMM) is employed to optimized the cost function. By evaluating the performance of our approach on the public cardiac dataset, experimental results show that our approach is more robust to estimate the correspondence between contours of LV than existed graph matching algorithms, which achieves more accurate motion estimation results.