关键词: 图像配准, 互信息, 神经网络, 粒子群优化

Abstract:

In this paper, a new reregistration method that based on shape information and gray information is introduced into the procedure of the CTMRI registration. Firstly, the frames of the two images to be registered are explained by the principle of mechanics decomposition, then we coarsely register the two images by their frames and as a result the error of the registration is constrained in a small region. Secondly, we reregister the two images that have been coarsely registered by means of the maximum mutual information (MMI), and finally an accurate registration result is obtained. The simulation result shows that, as this method combines the efficiency of the framebased registration method and the accuracy of the MMIbased registration method, this method is less time consuming and on the other side the registration accuracy is also guaranteed in comparison with other methods. Finally we successfully apply the present method to register the CT images and MRI images in a patient undergoing neurosurgery.

Key words: image registration;mutual information;neural network;particle swarm optimization