Left Ventricle Motion Estimation in Cine MRI With Multilayer Iterative Deformable Graph Matching.

Quantifying regional myocardial motion and deformation from cardiac magnetic resonance imaging (MRI) plays an important role in clinical applications. In this paper, we present a novel approach for the estimation of left ventricle myocardial motion based on iterative deformable graph matching for cine MRI. Graph matching is a shape matching approach that can be used to determine the correspondence between two objects. However, existing graph matching algorithms are unsuitable for applications with large deformations. In this paper, we propose an iterative deformable graph matching framework for estimating the correspondence between points extracted from left ventricle myocardium at the end-diastolic and endsystolic phases to estimate cardiac motion. A new cost function for graph matching is defined to measure the discrepancy between the nodes and edges of two graphs under a transformation. By introducing a spatial transformation with a sparsity constraint, we can estimate a robust deformation field, alleviating the influence of inevitable graph mismatches. The correspondence between points is then updated by mapping the source graph using the estimated transformation. The cost function is optimized by alternatively optimizing for correspondence and spatial transformation. Furthermore, we propose a multilayer framework to improve correspondence accuracy using a bottom-up matching procedure. This framework estimates the deformation field between an image at the end-systolic phase and an image at the end-diastolic phase in an MRI sequence. Evaluations of two public cardiac datasets indicate that the proposed framework outperforms traditional graph matching algorithms in accuracy and robustness.