Answers are grounded in this paper and cite their sources.
Demonstrates improved image reconstruction of electrical properties in tissues, suggesting better medical imaging capabilities.
Complex-valued electrical impedance tomography (Cv-EIT) has insights that visual the electrical properties (conductivities and permittivity) of various healthy and injured organizations/tissues, which is a promising technique in industrial and medical imaging. Nevertheless, the most of current research mainly focused on the conductivity parameter, ignoring the influence of the impact on the permittivity. To address the above challenges, a novel learning-based Cv-EIT image reconstruction method is proposed, referred as DeepcomplexEIT, which could reconstruct the distributions of conductivity and permittivity simultaneously with the multi-physics information interactions. The DeepcomplexEIT is designed to obtain the high-quality complex-valued admittivity distributions by leveraging the advantages of both convolutional neural networks and Transformers. In details, (1) the U-shaped architecture is modified using depth-separable convolution and pooling in complex-valued domain, (2) the two-dimensional filter with learnable cut-off frequency is proposed for featuring the multi-frequency information in the spatial and spectral domain, (3) a novel complex-valued Vision Transformer and cross-domain attention are designed for featuring the local-global multi-scale information with the multi-physics interactions and complementation. Our extended experiments demonstrate that DeepcomplexEIT outperforms state-of-the-art complex-valued models in terms of the complicated shape features and multi-phase distributions with respect to the admittivity. The performances are evaluated using the tank phantoms with 16-electrode EIT system and about 67 dB SNR, where the average quantitative metrics (conductivity/permittivity) are RMSE 1.982/0.946, SSIM 0.992/0.994 with multi-phase inclusions as well as RMSE 2.593/2.506, SSIM 0.989/0.992 with lung-shaped inclusions, respectively. Overall, the DeepComplexEIT are expected to further promote the multi-parameter visualization in the practical applications.
No takes yet. Share an insight, caveat, or question.
Wang et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: