改进头脑风暴优化算法与Powell算法结合的医学图像配准

针对现有医学图像配准算法精度较差、易陷入局部极值和收敛速度慢的问题，结合多分辨率分析，提出改进头脑风暴优化（MBSO）算法与Powell算法结合的图像配准算法。MBSO算法通过改变个体生成方式调节参与局部和全局搜索的个体比例，应用可变步长加强搜索能力，达到跳出局部最优和加速收敛的目的。首先，在低分辨率层利用MBSO算法进行全局搜索；然后，将搜索结果作为Powell算法的初始点在高分辨率层进一步搜索；最后，在原始图像层利用Powell算法搜索并定位全局最优值。与粒子群优化（PSO）算法、蚁群优化（ACO）算法、遗传算法（GA）与Powell算法结合算法相比，所提算法平均均方根误差分别减小了20.89%、30.46%和18.54%，平均配准时间分别缩短了17.86%、27.05%和26.60%，并且达到了100%的成功率。实验结果表明，所提算法具有很强的鲁棒性，能够快速、准确完成医学图像配准任务。

Medical image registration by integrating modified brain storm optimization algorithm and Powell algorithm

Aiming at the problems of poor accuracy, easy to fall into local maximum and slow convergence in existing medical image registration methods, based on multi-resolution analysis, a hybrid algorithm of Modified Brain Storm Optimization (MBSO) and Powell algorithm was proposed. MBSO algorithm, the proportion of individuals participating in local and global search was adjusted by changing the way of individual generation, and variable step size was adopted to enhance search ability, to achieve the purpose of accelerating convergence and jumping out of local optimum. Firstly, the MBSO algorithm was used to search globally in the low resolution layer. Then the result was used as the start point of Powell algorithm to search in the high resolution layer. Finally, Powell algorithm was used to search and locate the globally optimal value in the original image layer. Compared with the Particle Swarm Optimization (PSO) algorithm, Ant Colony Optimization (ACO) algorithm, Genetic Algorithm (GA) combined with Powell algorithm, the average root mean square error of the proposed algorithm decreased by 20.89%, 30.46% and 18.54%, and the average registration time reduced by 17.86%, 27.05% and 26.60% with success rate of 100%. The experimental results show that the proposed algorithm has good robustness and can accomplish the medical image registration task quickly and accurately.