Multi-Scale Frequency-Enhanced Deep D-bar Method for Electrical Impedance Tomography
This work addresses image quality issues in EIT for medical or industrial imaging, but it is incremental as it builds on the existing D-bar method with deep learning enhancements.
The paper tackled the low contrast and resolution in Electrical Impedance Tomography (EIT) reconstructions using the D-bar method by proposing a deep learning-based approach with multi-scale frequency enhancement and spatial consistency, achieving notable improvements in imaging quality on KIT4 and ACT4 datasets.
The regularized D-bar method is a popular method for solving Electrical Impedance Tomography (EIT) problems due to its efficiency and simplicity. It utilizes the low-pass truncated scattering data in the non-linear Fourier domain to solve the associated D-bar integral equations, yielding a smooth conductivity approximation. However, the D-bar reconstruction often presents low contrast and resolution due to the absence of accurate high-frequency information and the ill-posedness of the problem. In this paper, we propose a deep learning-based supervised approach for real-time EIT reconstruction. Based on the D-bar method, we propose to utilize both multi-scale frequency enhancement and spatial consistency for a high image quality reconstruction. Additionally, we propose a fixed-point iteration for solving discrete D-bar systems on GPUs for fast computation. Numerical results are performed for both the continuum model and complete electrode model simulation on KIT4 and ACT4 datasets to demonstrate notable improvements in absolute EIT imaging quality.