Non Rigid Image Registration Using B-Spline Grid for Image Deformation

A new approach for the non-rigid registration is presented. Here two contrast enhanced images were used. The global motion of the image is modeled by an affine transformation while the local image motion is described by a free-form deformation (FFD) based on B-splines. Normalized mutual information is used as a voxel-based similarity measure which is insensitive to intensity changes as a result of the contrast enhancement. Registration is achieved by minimizing a cost function, which represents a combination of the cost associated with the smoothness of the transformation and the cost associated with the image similarity. We have compared the results of the proposed nonrigid registration algorithm by using steepest gradient optimizer and least square non-linear optimizer with various levels. Also we have compared the results of the proposed non-rigid registration algorithm to those obtained using affine registration techniques. The results clearly indicate that the non-rigid registration algorithm is much better and able to recover the motion and deformation of the image than affine registration algorithm.