Regularized Shallow Image Prior for Electrical Impedance Tomography

TL;DR

This paper introduces a novel regularized shallow image prior method for Electrical Impedance Tomography that combines untrained neural networks with hand-crafted regularizations, improving image quality with less complexity.

Contribution

It proposes a shallow MLP-based UNNP approach combined with hand-crafted regularizations for EIT, offering comparable performance to deep methods with simpler architecture.

Findings

Significantly improved EIT image quality over traditional methods.

Effective structure preservation in reconstructed images.

Comparable performance to deep image prior with less neural network complexity.

Abstract

Untrained Neural Network Prior (UNNP) based algorithms have gained increasing popularity in tomographic imaging, as they offer superior performance compared to hand-crafted priors and do not require training. UNNP-based methods usually rely on deep architectures which are known for their excellent feature extraction ability compared to shallow ones. Contrary to common UNNP-based approaches, we propose a regularized shallow image prior method that combines UNNP with hand-crafted prior for Electrical Impedance Tomography (EIT). Our approach employs a 3-layer Multi-Layer Perceptron (MLP) as the UNNP in regularizing 2D and 3D EIT inversion. We demonstrate the influence of two typical hand-crafted regularizations when representing the conductivity distribution with shallow MLPs. We show considerably improved EIT image quality compared to conventional regularization algorithms, especially in structure preservation. The results suggest that combining the shallow image prior and the hand-crafted regularization can achieve similar performance to the Deep Image Prior (DIP) but with less architectural dependency and complexity of the neural network.