A Rotational Invariant Neural Network for Electrical Impedance Tomography Imaging without Reference Voltage: RF-REIM-NET

Abstract

Background: Electrical Impedance Tomography (EIT) is a radiation-free technique for image reconstruction. However, as the inverse problem of EIT is non-linear and ill-posed, the reconstruction of sharp conductivity images poses a major problem. With the emergence of artificial neural networks (ANN), their application in EIT has recently gained interest. Methodology: We propose an ANN that can solve the inverse problem without the presence of a reference voltage. At the end of the ANN, we reused the dense layers multiple times, considering that the EIT exhibits rotational symmetries in a circular domain. To avoid bias in training data, the conductivity range used in the simulations was greater than expected in measurements. We also propose a new method that creates new data samples from existing training data. Results: We show that our ANN is more robust with respect to noise compared with the analytical Gauss–Newton approach. The reconstruction results for EIT phantom tank measurements are also clearer, as ringing artefacts are less pronounced. To evaluate the performance of the ANN under real-world conditions, we perform reconstructions on an experimental pig study with computed tomography for comparison. Conclusions: Our proposed ANN can reconstruct EIT images without the need of a reference voltage.

Editorial: Multidimensional physiology: novel techniques and discoveries with bioimpedance measurements

“…Advancements in machine learning and artificial intelligence: The application of machine learning and artificial intelligence algorithms to bioimpedance data holds immense potential. Several recent publications highlight the use of machine learning and artificial intelligence to analyze the measurements and provide useful feedback ( Rixen et al, 2022 ; Baran et al, 2023 ; Yang et al, 2023 ). By leveraging these techniques, researchers can develop predictive models, identify complex patterns, and enhance decision-making in clinical settings.…”

Comparison of Machine Learning Classifiers for the Detection of Breast Cancer in an Electrical Impedance Tomography Setup

“…Simulations serve as a non-invasive and cost-effective alternative, allowing for the generation of diverse training data and the exploration of imaging parameters, crucial for refining EIT systems in breast cancer detection. For the training data we have used the general approach explained by Rixen et al, where they were able to produce EIT images from real-world measurements, but trained the ANN using only simulated data [17]. We used finite element method (FEM) simulation for the open source Electrical Impedance Tomography and Diffuse Optical Tomography Reconstruction Software (EIDORS) library [18].…”

Editorial on Special Issue “Artificial Intelligence in Image-Based Screening, Diagnostics, and Clinical Care of Cardiopulmonary Diseases”

“…Recently, artificial neural networks (ANN) have gained prominence in tackling the inverse problem in EIT imaging. Rixen et al [ 45 ] proposed an ANN model to resolve the EIT inverse problem. The authors reused the dense layers in the ANN model multiple times while considering the rotational symmetries exhibited by the EIT in the circular domain.…”