一种基于小波与概率估计的医学图像配准方法  

Medical Image Registration Methods Based on Wavelet Transformation and Probability Estimate

作　　者：康晓东[1,2] 孙越恒[2] 乔清理[3] 于瑞国[2] 李昌青[4] 

机构地区：[1]天津医科大学医学影像学系,天津300070 [2]天津大学计算机科学与技术学院,天津300072 [3]天津医科大学生物医学工程系,天津300070 [4]天津大学电子信息工程学院,天津300072

出　　处：《计算机科学》2009年第9期281-282,286,共3页Computer Science

基　　金：国家自然科学基金(No.60603027);天津市应用基础研究计划(No.05YFJMJC11700)资助

摘　　要：为提高医学图像配准效果,提出了一种基于小波变换和互信息的配准方法。以小波变换对源图像进行二级分解,并在每个分解层对其子带分量分别进行贝叶斯最大验后概率估计,求概率估计的回归参数,得到配准图像的各小波子带分量,再进行小波逆变换,实现对源医学图像的配准。To improve the performance of medical image registration, a new method based on wavelet transformation and probability estimate was proposed in this paper. Two-step decomposition of the original images was obtained by using the wavelet transformation. Bayesian maximum a posterior （MAP） probability estimate was performed separately for the sub-band component of each decomposition layer. Each wavelet sub-band component of image registration was got by probability estimating on the parameter. Original medical image registration was realized by wavelet＇s inversing transformation at last.

关 键 词：医学图像配准 小波变换 贝叶斯 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]