最大互信息法在人脑MR-PET图像配准中的应用  

Application of Maximal Mutual Information in MR-PET Human Brain Image Registration

作　　者：赵富强[1] 于红玉[2] 

机构地区：[1]北京首都医科大学生物医学工程系北京100054 [2]北京首都医科大学生物医学工程系北京100054

出　　处：《仪器仪表学报》2000年第z1期-,共3页Chinese Journal of Scientific Instrument

摘　　要：多模医学图像配准在3—D医学图像处理中具有重要的意义。例如，通过对不同模式图像能够为医疗诊断提供更加全面的互补信息。最大互信息算法是基于体素的配准方法中的一种，它是近几年发展起来的受到许多学者关注的的一种配准算法。由于最大互信息法不需要对不同成像模式下的图像灰度间的关系作任何假设，也不需要对图像进行分割或其它预处理，被广泛用于CT—MR、PET—MR等图像的配准。本文应用最大互信息法对3—D MR—PET进行了配准，取得了满意的结果。Registration of multimodality images is a fundamental task in numerous applications in three-dimensional (3-D) medical image processing.Clinical diagnosis,as well as therapy and evaluation,increasingly rely on images from multiple modalities providing partly complementary information.This paper describes an automated approcch to register MR-PET brain images by maximization of mutual information.The MI registration criterion presented here states that the MI of the image intensity values of correponding voxel pairs is maximal if the images are geometrically aligned.Because no assumptions are made regarding the nature of the relation between the image intensities in both modalities,this criterion is very useful and powerful and can be applied automatically without prior segmentation on a large variety of applications.

关 键 词：医学图像配准 最大互信息 

分 类 号：TH7-55[机械工程—仪器科学与技术]