Electrical impedance tomography image reconstruction for lung monitoring based on ensemble learning algorithms.

Abstract

Electrical impedance tomography (EIT) is a promising non-invasive imaging technique that visualizes the electrical conductivity of an anatomic structure to form based on measured boundary voltages. However, the EIT inverse problem for the image reconstruction is nonlinear and highly ill-posed. Therefore, in this work, a simulated dataset that mimics the human thorax was generated with boundary voltages based on given conductivity distributions. To overcome the challenges of image reconstruction, an ensemble learning method was proposed. The ensemble method combines several convolutional neural network models, which are the simple Convolutional Neural Network (CNN) model, AlexNet, AlexNet with residual block, and the modified AlexNet model. The ensemble models' weights selection was based on average technique giving the best coefficient of determination (R² score). The reconstruction quality is quantitatively evaluated by calculating the root mean square error (RMSE), the coefficient of determination (R² score), and the image correlation coefficient (ICC). The proposed method's best performance is an RMSE of 0.09404, an R² score of 0.926186, and an ICC of 0.95783 using an ensemble model. The proposed method is promising as it can construct valuable images for clinical EIT applications and measurements compared to previous studies.