A Learning-Based 3D EIT Image Reconstruction Method
This addresses the challenge of accurate 3D imaging in EIT, which is important for medical or industrial applications, but appears incremental as it extends learning-based methods to 3D.
The paper tackles the problem of 3D Electrical Impedance Tomography (EIT) image reconstruction, where existing methods struggle with performance and noise robustness due to increased dimensionality, and presents TN-Net, a learning-based approach that shows superior performance and generalization ability compared to prevailing algorithms.
Deep learning has been widely employed to solve the Electrical Impedance Tomography (EIT) image reconstruction problem. Most existing physical model-based and learning-based approaches focus on 2D EIT image reconstruction. However, when they are directly extended to the 3D domain, the reconstruction performance in terms of image quality and noise robustness is hardly guaranteed mainly due to the significant increase in dimensionality. This paper presents a learning-based approach for 3D EIT image reconstruction, which is named Transposed convolution with Neurons Network (TN-Net). Simulation and experimental results show the superior performance and generalization ability of TN-Net compared with prevailing 3D EIT image reconstruction algorithms.