Reconstruction of electrical impedance tomography images using particle swarm optimization, genetic algorithms and non-blind search

The fields of non-invasive imaging and e-health have been increasing in the last decades, due to the need of avoiding to exposure living tissues to ionizing radiation, increasing monitoring levels of critical patients, and promoting the increasing of quality life. Furthermore, the use of image-reconstruction devices based on ionizing radiation can result on several health problems for patients in case non-calibrated apparatus is employed. These needs have been strengthening the efforts to improve non-invasive methods like Electrical Impedance Tomography (EIT), a low-cost, non-invasive, portable, and safe of handling imaging technique. However, EIT image reconstruction is still an open problem, due to its nature as an ill-posed problem governed by the Equation of Poison. Several numerical methods are used in order to solve this equation without generating anatomically inconsistent results. Evolutionary methods can be used as alternatives to Gauss-Newton and Backprojection well-known approaches, which frequently generate low-resolution blurred images. Herein this work we present an EIT reconstruction method based on the optimization of the relative error of reconstruction using particle swarm optimization with non-blind search. We studied two forms of initialization: totally random and including an imperfect but anatomically consistent solution based on Gauss-Newton reconstruction method, according to Saha and Bandyopadhyay's criterion for non-blind initial search in optimization algorithms, in order to guide the iterative process to avoid anatomically inconsistent solutions. Our approach was compared with genetic algorithms. Results were quantitatively evaluated with ground-truth images using the relative mean squared error, showing that our results reached low error magnitudes. Qualitative evaluation also indicated that our results were morphologically consistent.