Principal component analysis and artificial neural network approach to electrical impedance tomography problems approximated by multi-region boundary element method

The idea of electrical impedance tomography (EIT) is to evaluate conductivity or permittivity distribution inside the examined object by measuring the voltages between electrodes placed on its surface. In this paper, EIT as a default 3D diagnostic method of the breast cancer is suggested. The breast was modelled as a hemisphere consists of two spatially homogenous areas with different conductivity. In order to determine the distribution of potential in the breast model, a multi-region boundary element method (BEM) was implemented. In this paper, a multi-region BEM with quadratic interpolation function for the flat, triangular surface elements was introduced. The inverse problem solution provided the identification of the size and the position of the anomalies in the breast tissue. For this purpose the efficient method based on principal component analysis (PCA) and the artificial neural network (ANN) was used. PCA applied to EIT data allows reducing dimensionality of measured data for 3D space and removing the unused part of information, usually corresponding to noise and interrelated variables. ANN method allows to obtain the results of inverse problem solution in real-time.