基于混合互信息和改进粒子群优化算法的医学图像配准方法

Medical Image Registration Algorithm Based on Mixed Mutual Information and Improved Particle Swarm Optimization

为满足医学图像辅助诊断与治疗的需要,提出一种基于混合互信息和改进粒子群优化算法的医学图像配准方法。在每次迭代时,首先使用基于Renyi熵的改进粒子群优化算法对图像进行全局搜索,再使用基于Shannon熵的Powell算法对当前得到的最优解进行局部寻优。实验图像为60幅模拟图像和10幅临床图像,对70幅图像进行单模态和多模态的医学图像配准实验,所提出算法的单模态医学图像配准结果均达到亚像素级。在多模态医学图像配准实验中,采用5种性能指标,评价配准结果的质量。同3种医学图像配准算法进行比较,结果显示新算法除计算时间外,其他4项指标均为最优,MI指数、NMI指数和CC指数的均值分别为1.338 6、1.363 1和0.837 8。主观和客观分析显示,所提出算法在精确度和收敛速度方面均优越于其他配准算法。

A novel medical image registration method based on mixed mutual information and improved particle swarm optimization algorithm was proposed. During each iteration of the proposed algorithm, the improved particle swarm optimization algorithm based on Renyi＇ s entropy was adopted firstly in global searching phase. Then the mutual information measure based on Shannon＇ s entropy was taken as the objective function while the Powell algorithm was used to obtain the optimal solution in local searching phase. The mono-modality medical image registration accuracy including sixty simulated images and ten clinical medical images is improved to sub- pixel level by the proposed algorithm. Comparing with the other three algorithms in the experiment of multi- modality medical image registration, the quality of the registered image was evaluated by five kinds of objective criterions, the proposed algorithm was optimal for the four object indexes except for computation time, the mean of MI, NMI and CC index was 1. 338 6, 1. 363 1 and 0. 837 8 respectively, subjective and objective analysis of the results showed that the proposed algorithm has the advantage in accuracy and effectiveness over other image registration methods.