Image Reconstruction in Electrical Impedance Tomography Based on Structure-Aware Sparse Bayesian Learning

Abstract

Electrical impedance tomography (EIT) is developed to investigate the internal conductivity changes of an object through a series of boundary electrodes, and has become increasingly attractive in a broad spectrum of applications. However, the design of optimal tomography image reconstruction algorithms has not achieved the adequate level of progress and matureness. In this paper, we propose an efficient and high-resolution EIT image reconstruction method in the framework of sparse Bayesian learning. Significant performance improvement is achieved by imposing structure-aware priors on the learning process to incorporate the prior knowledge that practical conductivity distribution maps exhibit clustered sparsity and intra-cluster continuity. The proposed method not only achieves high-resolution estimation and preserves the shape information even in low signal-to-noise ratio scenarios but also avoids the time-consuming parameter tuning process. The effectiveness of the proposed algorithm is validated through comparisons with state-of-the-art techniques using extensive numerical simulation and phantom experiment results.

B-Spline-Based Sharp Feature Preserving Shape Reconstruction Approach for Electrical Impedance Tomography

“…EIT reconstruction methods can be divided into statistical and deterministic methods. Within the statistical methods, a prior model for the target is written explicitly and the solution of the image reconstruction problem is sought via a posterior probability distribution [2], [3]. In deterministic methods, regularization techniques have usually been adopted in order to stabilize the inversion [4], [5] Most commonly, regularization methods impose (explicitly or implicitly) sophisticated prior knowledge by appropriately regularizing the unknown parameters utilizing some matrix norm.…”

Fundamentals, Recent Advances, and Future Challenges in Bioimpedance Devices for Healthcare Applications

“…The consideration of alternate solution spaces, such as the logarithmic conductivity, has proven to be more robust to the initial guess and yield faster convergence [311]. With regard to EIT image resolution, resampling-based methods [312] and sparse Bayesian learning [313] have been suggested to improve the quality of EIT image reconstruction. In other words, multiple information fusion methods are approached to address the limitations of EIT.…”

Scaffold-Based 3-D Cell Culture Imaging Using a Miniature Electrical Impedance Tomography Sensor

“…In this work, we demonstrate a pioneering study of scaffold-based 3-D cell culture imaging using a miniature-planar Electrical Impedance Tomography (EIT) sensor. EIT is an electrical field based tomographic modality which performs the recovery of the conductivity within interior of a domain based on boundary-applied currents and induced voltage measurements [8][9][10][11]. EIT has been investigated extensively in biomedical imaging [11,12] and industrial process imaging [11,13] with many successful cases.…”