基于最大互信息的人脑mr_pet图像配准方法.pdfVIP

第 20 卷 　第 4 期 北京生物医学工程 Vol20 　No 4 2001 年 　12 月 Beijing Biomedical Engineering Dec. 　2001 基于最大互信息的人脑 MRPET 图像配准方法 1 1 2 1 杨 　虎 　马斌荣 　任海萍 　沈晋慧 　　摘 　要 　利用最大互信息法进行多模医学图像配准近来成为了医学图像处理领域的热点。MR 和 PET 图像配 准对研究神经组织的结构功能关系和引导神经外科手术有着重要的指导意义。本文描述了一种基于互信息的人 脑 MRPET 图像配准方法。我们将这种方法应用于图像的几何对准并给出了初步的评估结果。由于不需要对不同 成像模式下的图像灰度间的关系作任何假设 , 最大互信息法是一种稳健性强 , 可广泛应用于基于体素的多模图 像的配准方法。 关键词 　最大互信息 　配准 　图像分割 中图分类号　R31804 文献标识码 A 文章编号 (2001) Method of Human Brain MRPET Image Registration Using Maximal Mutual Information 　YANG Hu , MA Binrong , REN Haiping , SHEN Jinhui 　1 Dept . of Biomedical Engineering , Capital University of Medical Sciences , Beijing 　100054 　2 Can cer Hospital , Chinese Academy of Medical Science Beijing , 100021 There has recently been considerable interest in medical image processing community in the use of maximal mutual informa 【Abstract 】　 tion for automatic registration of images from different modalities. Applyication of registration methods to MR and PET images is very important in neurology to study structurefunction relationships and to guide neurosurgery. In this paper is described an automated mutual informationbased meth od for human brain MRPET image registration. We have applied this method to the problem of geometric alignment of autoradiographs. Preliminary evaluation results are presented below based on our experiments. Because no conditions are required regarding the nature of the relation between im age intensities of both modalities , Maximal mutual informationbased method is very robust and may be