Shape analysis of training data for neural networks in Electrical Impedance Tomography.

Electrical Impedance Tomography (EIT) is a cost-effective and fast way to visualize dielectric properties of the human body, through the injection of alternating currents and measurement of the resulting potential on the bodies surface. However, this comes at the cost of low resolution as EIT is a non-linear ill-posed inverse problem. Recently Deep Learning methods have gained the interest in this field, as they provide a way to mimic non-linear functions. Most of the approaches focus on the structure of the Artificial Neural Networks (ANNs), while only glancing over the used training data. However, the structure of the training data is of great importance, as it needs to be simulated. In this work, we analyze the effect of basic shapes to be included as targets in the training data set. We compared inclusions of ellipsoids, cubes and octahedra as training data for ANNs in terms of reconstruction quality. For that, we used the well-established GREIT figures of merit on laboratory tank measurements. We found that ellipsoids resulted in the best reconstruction quality of EIT images. This shows that the choice of simulation data has an impact on the ANN reconstruction quality.Clinical relevance- This work helps to improve time independent EIT reconstruction, which in turn allows for extraction of time independent features of e.g., the lung.

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

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.