寻优方法在医学图像配准中性能比较研究  

A performance comparison study of optimization methods for registration of medical images

作　　者：潘梅森[1] 江建军[2] 周慧灿[1] 聂方彦[1] 

机构地区：[1]湖南文理学院计算机科学与技术学院,湖南常德415000 [2]湖南文理学院图书馆,湖南常德415000

出　　处：《湖南文理学院学报（自然科学版）》2011年第3期44-49,61,共7页Journal of Hunan University of Arts and Science(Science and Technology)

基　　金：湖南省教育厅优秀青年基金项目(No.09B071)

摘　　要：医学图像配准是以相似性测度为目标函数,通过多参数优化方法寻找最佳变换参数的过程.本文以MI为相似性测度,通过分别使用Powell算法和PSO法等方法寻优得到最佳变换参数,并对它们的性能进行了比较.实验结果表明,Powell法适合于单、多模态配准;虽然PSO法能成功配准,但是寻优效率有待提高,有必要在精度和时间效率之间进行适当折中.Medical image registration,in essence,is the process that the similarity metric is referred to as the objective function,and the multi-parameter optimization method as the tool for obtaining the optimal transform parameters.In this paper,by use of the mutual information as the similarity metric,two optimization methods including the Powell method and the particle swarm optimization method（PSO） are exerted to explore the optimal transform parameters respectively,and their optimizing performances are evaluated and compared.The experimental results reveal that the Powell and PSO methods can cater to both the mono-modality and the multi-modality medical image registrations.Unfortunately,however,the running time of PSO is relatively longer and needs to be substantially reduced.So in order to improve the optimization efficiency,it is very necessary for PSO to counterbalance the registration accuracy and the running time.

关 键 词：医学图像配准 互信息 寻优方法 变换参数 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]