A Swarm-based Approach To Medical Image Analysis
Image segmentation is an indispensable part of the visualization of human tissues, particularly during analysis of Magnetic Resonance (MR) images. Unfortunately images always contain a significant amount of noise due to operator performance, equipment, and the environment can lead to serious inaccuracies with segmentation. A segmentation technique based on an extension to the traditional C-means (FCM) clustering algorithm is proposed in this paper. A neighborhood attraction, which is dependent on the relative location and features of neighboring pixels considered.. The degree of attraction is optimized by a Particle Swarm Optimization model. Paper demonstrates the superiority of the proposed technique to FCM-based method. This segmentation method is component of an MR image-based classification system for tumors, currently being developed.
