In this paper we present an integrated image registration algorithm for segmenting the heart muscle, the myocardium (MC). A sequence of magnetic resonance (MR) images of heart are acquired after injection of a contrast agent. An analysis of the perfusion of the contrast agent into myocardium is utilized to study its viability. Such a study requires segmentation of MC in each of the images acquired which is a difficult task due to rapidly changing contrast image the images. In this paper we present an information theoretic registration framework which integrates two channels of information, the pixel intensities and the local gradient information, to reliably and accurately segment the myocardium. In our framework, the physician hand draws contours representing the inner (the endocardium) and the outer (the epicardium) boundaries of the myocardium. These hand drawn contours are then propagated to the other images in the sequence of images acquired to segment the MC.