A viscous fluid model for multimodal non-rigid image registration using mutual information

Abstract

We propose a multimodal free form registration algorithm based on maximization of mutual information. Images to be aligned are modeled as a viscous fluid that deforms under the influence of forces derived from the gradient of the mutual information registration criterion. Parzen windowing is used to estimate the joint intensity probability of the images to be matched. The method was verified by for registration of simulated T1-T1, T1-T2 and T1-PD images with known ground truth deformation. The results show that the root mean square difference being the recovered and the ground truth deformation is smaller than 1 voxel.