Brain electrical impedance tomography method based on GAN

Abstract

The invention relates to a brain electrical impedance tomography method based on GAN, which comprises the following steps: 1) acquiring original data, acquiring a boundary voltage sequence through anexperimental device, and performing grid subdivision on an object field area to obtain a corresponding real conductivity distribution diagram as sample data; 2) preprocessing data, performing normalization processing on the acquired boundary voltage sequence and converting the sequence into a two-dimensional graph; 3) constructing a generative adversarial network, and training the network by usinga sample data set to obtain a nonlinear mapping relationship between the boundary measurement voltage sequence and the conductivity distribution sequence; and 4) generating a corresponding conductivity distribution diagram from the untrained voltage sequence through the trained network. According to the method, the nonlinear problem during electrical impedance tomography inverse problem solving is solved, the precision of reconstructed images is improved, the noise immunity is high, the requirement for the noise immunity of an imaging system is lowered, and the imaging speed is high.

Description

technical field [0001] The invention belongs to the technical field of biomedical imaging, and relates to deep learning and image reconstruction, in particular to a GAN-based brain electrical impedance tomography method. Background technique [0002] Bioelectrical impedance tomography (Electrical Impedance Tomography, EIT) technology is a non-invasive detection imaging technology. Its principle is to apply a weak current to the surface electrode of the human body and measure the voltage value on other electrodes. According to the voltage The relationship between the electrical conductivity and the current reconstructs the image of the conductivity distribution or its change inside the object field. Due to the characteristics of non-radiation, non-invasive, fast imaging speed and low cost, EIT has broad application prospects in the field of medical imaging. [0003] The EIT image reconstruction process has nonlinear, ill-posed and ill-posed problems, which makes image recons...

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the lack of high accuracy of existing reconstructed images, the present invention provides a high-precision GAN-based brain electrical impedance tomography method. Compared with shallow artificial neural networks, deep learning has more hidden Layer, with excellent feature learning ability, can realize complex function approximation by learning a deep nonlinear network structure, and express complex functions with fewer parameters

Images