Empirical study of brain segmentation using particle swarm optimization

This study uses an empirical study of the efficiency of Particle swarm optimization (PSO) in segmentation of brain abnormalities. Presently, segmentation poses one of the most challenging problems in medical imaging. Segmentation of Magnetic Resonance Imaging (MRI) images is an important part of brain imaging research. In this study, we used controlled experimental data as our testing data. The data is designed which that prior knowledge of the size of the abnormalities are known. This is done by cutting various shapes and sizes of various abnormalities and pasting it onto normal brain tissues, where the tissues and the background are divided into different categories. The segmentation is done with twenty data of each category. The knowledge of the size of the abnormalities by number of pixels are then used as the ground truth to compare with the PSO segmentation results. The proposed PSO technique is found to produce potential solutions to the current difficulties in detecting abnormalities in human brain tissue area as it produced promising segmentation outcomes for light abnormalities. Nevertheless, the PSO produced poor performance in dark abnormalities segmentation as it produces low correlation values in all conditions.