Data-driven approaches for electrical impedance tomography image segmentation from partial boundary data

TL;DR

This paper introduces three neural network-based data-driven methods for electrical impedance tomography image segmentation from partial boundary data, demonstrating their effectiveness through a competitive challenge.

Contribution

It presents three novel data-driven reconstruction approaches for EIT, including a post-processing method that won first place at KTC2023, and compares their performance.

Findings

The post-processing approach achieved first place at KTC2023.

All methods were trained on synthetic data for fair comparison.

The approaches show promising results for EIT image segmentation.

Abstract

Electrical impedance tomography (EIT) plays a crucial role in non-invasive imaging, with both medical and industrial applications. In this paper, we present three data-driven reconstruction methods for EIT imaging. These three approaches were originally submitted to the Kuopio tomography challenge 2023 (KTC2023). First, we introduce a post-processing approach, which achieved first place at KTC2023. Further, we present a fully learned and a conditional diffusion approach. All three methods are based on a similar neural network as a backbone and were trained using a synthetically generated data set, providing with an opportunity for a fair comparison of these different data-driven reconstruction methods.