Medical Image Registration Based on Renyi's Quadratic Mutual Information

In this paper, a medical image registration based on Renyi's quadratic mutual information is proposed. Firstly, the initial values (i.e. the translation and rotation parameters) for aligning the floating image with the reference image are obtained by computing the medical image centroids and moments. Then, when exploring the optimal geometric transformation parameters, the Renyi's quadratic mutual information is taken as the similarity criterion between the reference and floating images. Finally, the Simplex method, as multi-parameter optimization one, is used to search the optimal registering values in the experiments. The experimental results reveal that, the proposed method has a lower computational load, faster registration and better registration accuracy compared with the registration method based on the Shannon mutual information. It can cater to both mono-modality and multi-modality image registrations.