Cardiac motion analysis in MRI for classification

Our proposed technique tries to perform rapid classification to diagnose the abnormalities in human myocardium and identify the left ventricle (LV) in the analyzed tagged MR images as pathological or normal. In this work, images are first analyzed using harmonic phase (HARP) analysis and synthetic tags are computed over the myocardium. The data is normalized for shift, scale and rotation invariance, and to perform a comparison between different myocardium having various tag lines and time frames. Cubic curves are fitted to the normalized tags and curvature parameters are compared at various regions of the myocardium. In this initial study, the curve parameters are examined with probability density function for multivariate normal distribution between normal and diseased hearts, such as left ventricles with dilated cardiomyopathy (DCM) and infarcted regions. Finally, the confusion matrix is evaluated to examine the correctness of the segmentation algorithm.