Lung Volume Estimation based on Bioimpedance Measurement and Neural Network

Abstract

Lung volume is an indicator used for evaluating how healthy of lungs are. Apart from using expensive equipment, lung volume can be determined by bioimpedance obtained by measuring at several regions around the chest. The bioimpedance values are usually used by the Electrical Impedance Tomography (EIT) technique, which transforms the several bioimpedance values into an image of conductivity distribution. EIT is inexpensive and can be used to monitor lungs in real-time. However, EIT is computation expensive and cannot provide the lung volume directly. In this study, the neural network technique was used to estimate the left- and the right-lung volume by using the bioimpedance values as used in EIT. Two network architectures were investigated by simulation. The result shows that neural networks can efficiently estimate lung volumes with the error of less than 0.78 ml and with a correlation of higher than 0.99. Even adding noise to the degree of 40 dB signal-to-noise ratio, the performance was still satisfactory. Two-layer network architecture was also sufficient for this lung application. © 2022 IEEE.