Modified exponential particle swarm optimization algorithm for medical images segmentation

Abstract

Modified Exponential Particle Swarm Optimization algorithm is proposed for medical image segmentation. The main idea of the proposed Exponential Particle Swarm Optimization algorithm is to prevent local solutions and find correct global optimal solutions for medical images segmentation task. The execution time comparison is done with existing segmentation techniques. Found, that proposed method is superior to existing segmentation techniques, including graph-based algorithms. Images from Ossirix image dataset and real patients’ images were used for testing. Developed method was tested using the Ossirix benchmark with magnetic-resonance images with various nature and different quality. The results of method’s work and a comparison with competing segmentation methods (Fuzzy C-Means, Grow cut, Random Walker, Darwinian Particle Swarm Optimization, K-means Particle Swarm Optimization, Hybrid ant colony optimization-k-means algorithm) are presented in the form of a time table of segmentation methods. In all cases, the algorithm makes a better final segmentation time, comparing to the studied techniques (except Random Walker algorithm, which has lower segmentation quality on 15%).