Multi-Scale Frequency-Enhanced Deep D-bar Method for Electrical Impedance Tomography

TL;DR

This paper introduces a deep learning-enhanced D-bar method for Electrical Impedance Tomography that improves image contrast and resolution by incorporating multi-scale frequency enhancement and spatial consistency, enabling real-time high-quality reconstructions.

Contribution

It presents a novel deep learning framework integrated with the D-bar method, utilizing multi-scale frequency enhancement and fixed-point GPU computation for superior EIT imaging.

Findings

Significant improvement in image contrast and resolution.

Real-time reconstruction capability demonstrated on simulated datasets.

Enhanced imaging quality over traditional D-bar methods.

Abstract

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.