Magnetic resonance image segmentation based on two-dimensional exponential entropy and a parameter free PSO

In this paper, a magnetic resonance image (MRI) segmentation method based on two-dimensional exponential entropy (2DEE) and parameter free particle swarm optimization (PSO) is proposed. The 2DEE technique does not consider only the distribution of the gray level information but also takes advantage of the spatial information using the 2D-histogram. The problem with this method is its time-consuming computation that is an obstacle in real time applications for instance. We propose to use a parameter free PSO algorithm called TRIBES, that was proved efficient for combinatorial and non convex optimization. The experiments on segmentation of MRI images proved that the proposed method can achieve a satisfactory segmentation with a low computation cost.