Reconstruction of brain electrical impedance tomography images using particle swarm optimization

This paper proposes a particle swarm optimization technique for solving inverse problems to improve the reconstruction of brain electrical impedance tomography (EIT) images. A mesh of 2D head model comprising of 1024 elements is constructed using finite element method (FEM) and the EIT inverse problem is solved by varying the swarm sizes. The performance of the proposed PSO-EIT is evaluated in terms of fidelity measures, such as total relative error and signal to noise ratio (SNR) and the experimental results are compared with other known techniques such as genetic algorithm and modified Newton - Raphson (MNR) method. It can be seen from the experimental results that the proposed PSO-EIT yield significant results in terms of better reconstruction quality compared to other techniques reported in the literature. Thus the PSO-EIT scheme found to be a promising tool for solving reconstruction problem in brain imaging.