Quantification of Delayed Enhancement MR Images

Delayed Enhancement MR is an imaging technique by which non-viable (dead) myocardial tissues appear with increased signal intensity. The extent of non-viable tissue in the left ventricle (LV) of the heart is a direct indicator of patient survival rate. In this paper we propose a two-stage method for quantifying the extent of non-viable tissue. First, we segment the myocardium in the DEMR images. Then, we classify the myocardial pixels as corresponding to viable or non-viable tissue. Segmentation of the myocardium is challenging because we cannot reliably predict its intensity characteristics. Worse, it may be impossible to distinguish the infracted tissues from the ventricular blood pool. Therefore, we make use of MR Cine images acquired in the same session (in which the myocardium has a more predictable appearance) in order to create a prior model of the myocardial borders. Using image features in the DEMR images and this prior we are able to segment the myocardium consistently. In the second stage of processing, we employ a Support Vector Machine to distinguish viable from non-viable pixels based on training from an expert.