EIT-CDAE: A 2-D Electrical Impedance Tomography Image Reconstruction Method Based on Auto Encoder Technique

Abstract

Electrical Impedance Tomography is considered to be an alternative substitution to CT and MRI technologies as it is a non-invasive, safe medical imaging technology, and free of ionizing or heating radiation. Similar to CT and MRI technologies, reconstructing a two-dimensional EIT image is also considered an ill-posed and non-linear inverse problem, where the image quality is highly sensitive to the measurement data, and often random noise artifacts appear in the image with the different non-linear algorithms. Therefore, in this work, we have proposed a new EIT image reconstruction algorithm based on the convolution denoising autoencoder (CDAE) deep learning algorithm. Our EIT-CDAE used a convolutional neural network in the encoder and decoder network. From our experimental data using phantom data, our EIT-CDAE model has reconstructed a better EIT image quality, removing any noise artifacts, making it more robust compared to the conventional stacked autoencoder and traditional non-linear algorithms. The source code is available in the github: https://github.com/yongfu-li/eit-cdae-algorithm.