Objective. Electrical impedance tomography (EIT) is a non-invasive technique that constitutes a promising tool for real-time imaging and long-term monitoring of the ventilation distribution at bedside. However, clinical monitoring and diagnostic evaluations depend on various methods to assess ventilation-dependent parameters useful for ventilation therapy. This study develops an automatic, robust, and rapidly accessible method for lung segmentation that can be used to define appropriate regions-of-interest (ROIs) within EIT images. Approach. To date, available methods for patients with defected lungs have the disadvantage of not being able to identify lung regions because of their poor ventilation responses. Furthermore, the challenges related to the identification of lung areas in EIT images are attributed to the low spatial resolution of EIT. In this study, a U-Net-based automatic lung segmentation model is used as a postprocessor to transform the original EIT image to a lung ROI image and refine the inherent conductivity distribution of the original EIT image. The trained U-Net network is capable of performing an automatic segmentation of conductivity changes in EIT images without requiring prior information. Main results. The experimental design of this study was based on a finite element method (FEM) phantom used to assess the feasibility and effectiveness of the proposed method, and evaluation of the trained models on the test dataset was performed using the Dice similarity coefficient (DSC) and the mean absolute error (MAE). The FEM experimental results yielded values of 0.0065 for MAE, and values >0.99 for DSC in simulations. Significance. The use of a deep-learning-based approach attained automatic and convenient segmentation of lung ROIs into distinguishable images, which represents a direct benefit for regional lung ventilation-dependent parameter extraction and analysis. However, further investigations and validation are warranted in real human datasets with different physiology conditions with CT cross-section dataset to refine the suggested model.
All Science Journal Classification (ASJC) codes