Fast and Accurate Solution of the Inverse Problem for Image Reconstruction Using Electrical Impedance Tomography

The goal in electrical impedance tomography is to obtain the electrical properties of different materials by applying an electrical current and measuring the resulting potential difference at the boundaries of the domain. While the numerical accuracy is technically limited by the size of the elements within the finite-element (FE) mesh, using a fine mesh will result in a computationally demanding reconstruction, especially when the region of interest (ROI) is not known. However, this situation is different when the location is known, when one can easily refine the FE model around the target, aiming for greater accuracy around the ROI. In this paper, an innovative approach estimates the location of the target object before solving the inverse problem, so that it becomes possible to refine only a specific area of the FE model. A powerful artificial intelligence method is used to obtain this region.

[1]  Jon Rigelsford.  Handbook of Neural Network Signal Processing , 2003 .

[2]  N. Holmer,et al.  Electrical Impedance Tomography , 1991 .

[3]  Marc Molinari,et al.  Optimal imaging with adaptive mesh refinement in electrical impedance tomography. , 2002, Physiological measurement.

[4]  Andreas Dedner,et al.  A Fast Parallel Solver for the Forward Problem in Electrical Impedance Tomography , 2015, IEEE Transactions on Biomedical Engineering.

[5]  Simon R Arridge,et al.  Comparison of methods for optimal choice of the regularization parameter for linear electrical impedance tomography of brain function , 2008, Physiological measurement.

[6]  William R B Lionheart,et al.  Uses and abuses of EIDORS: an extensible software base for EIT , 2006, Physiological measurement.

[7]  Antony Jameson,et al.  Comparison of Adaptive h and p Refinements for Spectral Difference Methods , 2010 .

[8]  Zhang Cao,et al.  An image reconstruction algorithm based on total variation with adaptive mesh refinement for ECT , 2007 .

[9]  Sébastien Martin,et al.  A Post-Processing Method for Three-Dimensional Electrical Impedance Tomography , 2017, Scientific Reports.

[10]  Sebastien Martin,et al.  Nonlinear Electrical Impedance Tomography Reconstruction Using Artificial Neural Networks and Particle Swarm Optimization , 2016, IEEE Transactions on Magnetics.

[11]  H. Ammari,et al.  Reconstruction of Small Inhomogeneities from Boundary Measurements , 2005 .

[12]  D. Djajaputra.  Electrical Impedance Tomography: Methods, History and Applications , 2005 .

[13]  Sébastien Martin,et al.  A novel post-processing scheme for two-dimensional electrical impedance tomography based on artificial neural networks , 2017, PloS one.

[14]  Sébastien Martin,et al.  On the influence of spread constant in radial basis networks for electrical impedance tomography , 2016, Physiological measurement.