One-dimensional convolutional neural network (1D-CNN) image reconstruction for electrical impedance tomography

Xiuyan Li; Rengui Lu; Qi Wang; Jianming Wang; Xiaojie Duan; Yukuan Sun; Xiaojie Li; Yong Zhou

doi:10.1063/5.0025881

One-dimensional convolutional neural network (1D-CNN) image reconstruction for electrical impedance tomography

Rev Sci Instrum. 2020 Dec 1;91(12):124704. doi: 10.1063/5.0025881.

Authors

Xiuyan Li¹, Rengui Lu¹, Qi Wang², Jianming Wang¹, Xiaojie Duan¹, Yukuan Sun¹, Xiaojie Li², Yong Zhou¹

Affiliations

¹ School of Electronics and Information Engineering, Tianjin Key Laboratory of Optoelectronic Detection Technology and Systems, Tianjin Polytechnic University, Tianjin 300387, China.
² School of Life Science, Tianjin Polytechnic University, Tianjin 300387, China.

PMID: 33380008
DOI: 10.1063/5.0025881

Abstract

In recent years, due to the strong autonomous learning ability of neural network algorithms, they have been applied for electrical impedance tomography (EIT). Although their imaging accuracy is greatly improved compared with traditional algorithms, generalization for both simulation and experimental data is required to be improved. According to the characteristics of voltage data collected in EIT, a one-dimensional convolutional neural network (1D-CNN) is proposed to solve the inverse problem of image reconstruction. Abundant samples are generated with numerical simulation to improve the edge-preservation of reconstructed images. The TensorFlow-graphics processing unit environment and Adam optimizer are used to train and optimize the network, respectively. The reconstruction results of the new network are compared with the Deep Neural Network (DNN) and 2D-CNN to prove the effectiveness and edge-preservation. The anti-noise and generalization capabilities of the new network are also validated. Furthermore, experiments with the EIT system are carried out to verify the practicability of the new network. The average image correlation coefficient of the new network increases 0.0320 and 0.0616 compared with the DNN and 2D-CNN, respectively, which demonstrates that the proposed method could give better reconstruction results, especially for the distribution of complex geometries.