Human chest imaging by real-time processing of electrical impedance data tomography

Real-time human chest imaging exploiting electrical impedance tomography (EIT) data is addressed in this work. Robust estimations of the lungs conductivity, directly related to their air/liquid content, are obtained by formulating the arising inverse problem within the learning-by-examples (LBE) framework. The partial least squares (PLS) algorithm is exploited to reduce the dimensionality of the feature space, while an adaptive sampling strategy is exploited to build an optimal training set of input/output pairs used to build a computationally efficient surrogate model of the inverse operator. Selected numerical results are shown to assess the effectiveness and the potentialities of the proposed LBE strategy.