In the myocardial perfusion image

the location and shape of the heart changes with respiration and heartbeat. Meanwhile

the image intensity also changes as the contrast agent flowing in the heart chambers. It is difficult to apply the traditional registration methods

such as cross correlation and mutual information to the registration of myocardial perfusion images. In this paper

we introduce Markov random fields(MRF)to tackle this problem. In the Markov energy function

the image block is normalized to get rid of the intensity change effect. In order to remove the accumulated error

which is common in registration of image series

a pseudo ground-truth image is calculated as template for each of the myocardial perfusion images. The accumulated error can be removed by warping each myocardial perfusion image to its corresponding pseudo ground-truth image. Experimental results demonstrate that our method can effectively correct the displacement and deformation of the myocardial perfusion image.