Improved Particle Swarm Medical Image Segmentation Algorithm for Decision Making

Abstract

Improved particle swarm optimization (PSO) algorithm is proposed for medical image segmentation. The complexity of the proposed algorithm is estimated based on the drift theorem. Computer experiments have shown the linear complexity of the algorithm. Images from the Ossirix image dataset and real medical images were used for testing. Low (polinomial time complexity) allows to use the proposed algorithm for rapid decision-making (medical diagnosis). The population-based image segmentation methods such as PSO are well implemented at distributed computing systems, what allows increasing their efficiency even more.