Multimodality Medical Image Registration Using Hybrid Optimization Algorithm

Optimization of a similarity metric is a essential component in multimodality medical image registration. In this paper, a hybrid optimization algorithm is proposed. When dealing with multimodality medical images, the authors search the best matching parameters by applying mutual information as similarity measure and hybrid optimization algorithm as search strategy. The registration results prove that the subvoxel accuracy can be achieved and this method is an efficient registration one which can avoid getting into the local optimum.