Mask-Guided Spatial–Temporal Graph Neural Network for Multifrequency Electrical Impedance Tomography

Abstract

Multi-frequency Electrical Impedance Tomography (mfEIT) is an emerging biomedical imaging modality that exploits frequency-dependent electrical properties. The mfEIT-image-reconstruction problem for cell imaging is particularly challenging due to weak signals from miniaturized sensors and high sensitivity to modelling errors. Existing approaches are primarily based on the linearized model and few are applied to the miniaturized setup. Here we report a Mask-guided Spatial-Temporal Graph Neural Network (M-STGNN) to reconstruct mfEIT images in cell culture imaging. The M-STGNN captures simultaneously spatial and frequency correlations, and the spatial correlation is further constrained by geometric structures from auxiliary binary masks, such as CT or microscopic images. We validate the mfEIT approach through numerical simulations and experiments on MCF-7 human breast cancer cell aggregates. The results demonstrate the superiority of M-STGNN over the state of the art with an improvement of approximately 10.7% under the experimental setup. It can be readily extended to multi-modal biomedical imaging applications.