PERFORMANCE COMPARISON OF THE POWELL AND PSO METHODS FOR MEDICAL IMAGE ALIGNMENT
Meisen Pan, Zhang Fen · Biomedical Engineering Applications Basis and Communications · 2017
In the course of aligning medical images, the similarity metric (also called alignment function) is regarded as the objective function, and the optimization method as the tool for exploring the optimal transformation parameters. In this paper, the medical image alignment is represented first and then the optimization methods are depicted in detail. With this description, by the use of the mutual information (MI) as the similarity metric, the Powell method and the particle swarm optimization (PSO) method are employed to seek the optimal transformation parameters respectively, and their optimization performances are estimated and compared. The experimental results show that the Powell and PSO methods can cater to both the multi-modality medical image alignments.