Multi-modality Medical Image Registration Based On Mutual Information Of Feature Points

With the rapid development of imaging technology, the modality medical images have been used widely in clinical diagnoses and surgical therapies. Integrating those images is helpful to improve the accuracy of clinical diagnoses and surgical therapies. Image registration is the key part of integration, It is a geometrical transformation and can rectifies two images according to the corresponding features.This paper introduces several geometrical transformations, optimization methods and similarity measures. According to whether extracting images' feature or not, we divide present methods into two parts, feature extraction based methods and voxel similarity based methods. Given the head images characteristic of CT and MRI, we present a new registration strategy which include a coarse registration and accurate registration. Firstly, we attain coarse registration by matching the contour of two images, then we adopt MI(Mutual Inormation) as cost function, PV(Partial volume Interplation) as interpolation, a new combined optimization algorithm that we give as our optimization algorithm to search the best registration parameters. Theories and experiments indicated that this method have the advantages of high precision and good robust.