Abstract
Image reconstruction of Magnetic induction tomography (MIT) is an ill-posed problem. The non-linear characteristics lead many difficulties to its solution. In this paper, a method based on a Generative Adversarial Network (GAN) is presented to tackle these barriers. Firstly, the principle of MIT is analyzed. Then the process for finding the global optimum of conductivity distribution is described as a training process, and the GAN model is proposed. Finally, the image was reconstructed by a part of the model (the generator). All datasets are obtained from an eight-channel MIT model by COMSOL Multiphysics software. The voltage measurement samples are used as input to the trained network, and its output is an estimate for image reconstruction of the internal conductivity distribution. The results based on the proposed model and the traditional algorithms were compared, which have shown that average root mean squared error of reconstruction results obtained by the proposed method is 0.090, and the average correlation coefficient with original images is 0.940, better than corresponding indicators of BPNN and Tikhonov regularization algorithms. Accordingly, the GAN algorithm was able to fit the non-linear relationship between input and output, and visual images also show that it solved the usual problems of artifact in traditional algorithm and hot pixels in L2 regularization, which is of great significance for other ill-posed or non-linear problems.
Highlights
Magnetic induction tomography (MIT) is a kind of electromagnetic imaging technology based on the eddy current testing principle [1]
In view of the shortcomings of existing MIT image reconstruction methods, this paper proposed a novel MIT imaging algorithm based on generative adversarial networks
Where eddy current Je is composed of two parts, ε is the permittivity that can be ignored in the inverse problem and eddy current is mainly generated by the conductivity σ in the biological object, with physical modeling and finite element model (FEM) discretization, the deterministic MIT measurement model can be expressed as: V = F(σ) where V is a vector of the measured phase of boundary voltage, F is the forward model map of the internal conductivity distribution, which is usually linearized to the sensitivity matrix in traditional algorithms as V = Sσ
Summary
Magnetic induction tomography (MIT) is a kind of electromagnetic imaging technology based on the eddy current testing principle [1]. Because of its non-invasive and non-contact characteristics, MIT is suitable for geological exploration [5], industrial flaw detection [6], impurity detection [7], and medical imaging [8]. The research on it can be roughly divided into a positive problem and an inverse problem [9]. The former is to calculate the edge detection signals or the change of magnetic field according to the existing electrical characteristics of the object [10], while the latter is to use the detection signals to restore the conductivity distribution map (reconstruction). Due to the soft field effect of electromagnetic field and the limitation of detector, the inverse problem has to recover more complex electrical characteristics from very few signals, which is the key problem of MIT where underdetermination and nonlinearity coexist
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
