A Virtual Electrode-Based Enhanced GREIT Method for Electrical Impedance Tomography

Traditional lung electrical impedance imaging devices require the placement of measurement electrodes around the chest, which is inconvenient for clinical application in patients in a supine position. To address this issue, this study proposes a virtual electrode-based level set combined with GREIT algorithm (VESL-GREIT) for pulmonary impedance tomography. It utilizes measurement data from electrodes placed on only one side of the chest and generates full electrode measurement data using a deep learning network. The improved GREIT algorithm is then employed for image reconstruction. Acting as a "gray box," VESL-GREIT not only takes advantage of prior information about the lungs but also enhances the robustness and generalizability of the algorithm. Simulation experiments demonstrate that with a measurement signal-to-noise ratio (SNR) above 20 dB, the imaging relative error (RE) and structure correlation coefficient (CC) change slowly, indicating high robustness of the algorithm. Physical model experiments show that compared to traditional dynamic electrical impedance imaging algorithms, the proposed algorithm achieves an RE of 0.167 and a structure CC of 0.886, enabling more accurate characterization of lung ventilation status. This research contributes to promoting the clinical application and dissemination of lung electrical impedance imaging monitoring methods and provides a new approach for open dynamic electrical impedance imaging.