Correction of Failure Data Under Electrode Disconnection for Accurate Electrical Impedance Tomography

Abstract

In the dynamic monitoring with electrical impedance tomography (EIT), some unavoidable factors lead to electrode disconnection. Failure data are measured which greatly affects image reconstruction quality. To enhance the accuracy of lung imaging in the presence of electrode disconnection, this work presents a novel failure data correction approach based on shallow convolutional neural network (sCNN). Electrode disconnection is first identified by calculating the average relative change in the measured voltage. Then the method is applied for failure data correction caused by the disconnected electrode. The performance of the proposed method when the electrode is disconnected is evaluated by comparing the predicted data with the normal data. It is found that mean relative boundary voltage variation when the proposed method is used is very similar to the normal case. Besides, the deviation rate of the predicted voltage data approximates 0. Furthermore, image reconstruction of conductivity distribution is investigated for five different models, and disconnection of one electrode and two electrodes are considered. Also, we have tested the robustness of the proposed method to noise interruption. Both quantitative and qualitative evaluations show that reconstructed images are much better when the voltage data corrected by the proposed method is used for image reconstruction. The shape and size of the reconstructed lung are basically the same with the true object. In addition, there are almost no artifacts. To further estimate the proposed method, a phantom experimental validation is carried out. This work offers a choice for accurate image reconstruction of conductivity distribution under electrode disconnection in the lung EIT.