Medical image fusion, a subject which involves information science~ computer science and medical imaging, is a new hot spot in medical image processing. As the basic issue of medical image fusion, medical image registration has very important meaning. It is the first step of image fusion, and its precision influenced the effect of image fusion directly. CT and MRI images are common-used in medical diagnosis. The registration and fusion between them are significant. In this paper, the medical image registration is at first deeply researched, and two methods, contour-based image registration and correlation-based image registration are discussed in details, analyzed their features and compared their advantages and disadvantages. After image registration the fusion method is presented. The space-structure fusion and the pixel-gray level fusion methods are introduced. Both methods have got better results. Many images and big amount of data have been used to prove the accuracy of our methods in this paper. At last, we discuss the further research goal and direction.
|