Structural and Functional Image Registration Using Maximum Mutual Information
The technique of medical image radiography is developed for clinical diagnosis and application. Multi-modality image registration is designed to combine the information of medical image from different modalities and record at different times. The purpose is to register medical images such as magnetic resonance images (MRI) and positron emission tomography (PET) images using maximum mutual information (MI). The image registration system is designed as two phases: estimation of MI and image registration. One of the phases, MI is estimated the by statistical dependence or information redundancy between the image intensity of corresponding voxels in both images. The other phase is the parameters of the geometric transformation that are iteratively obtained by estimation of MI. In this paper, 2-D and 3-D registration techniques were developed and applied to medical image studies. The results show that it will be effective to use this study in image registration. The method is both accomplishable and suitable for clinical application.