Multimodality Rigid Medical Image Registration Through Improved Particle Swarm Optimization

Multimodality medical images registration based on contour feature points and improved particle swarm optimization is presented for clinical diagnosis and therapy planning.The image edges are first detected by using Canny operator,then the contour feature points are extracted by ISODATA algorithm,and translation parameters are calculated by using improved particle swarm optimization algorithm.Experiments show that this approach is efficient and can avoid local minimum.