Intensity-based registration of medical images

We propose an intensity-based image registration technique for medical images. The registration is performed by the use of a measure based on the entropy of conditional probabilities. To achieve the registration, we define a modified conditional entropy (MCE) computed from the joint histograms for the area intensities of two given images. To evaluate the performance, we conduct various experiments with our method as well as existing methods based on the mutual information (MI) criteria. We evaluate the precision of MI- and MCE-based measurements by comparing the registration obtained from magnetic resonance (MR) images and transformed MR/transformed CT images. The experimental results show that the proposed method is faster and more accurate than MI optimization method.