Conditional Diffusion Model for Electrical Impedance Tomography

2025-01-10

AI Summary

Electrical impedance tomography (EIT) reconstruction suffers from severe ill-posedness and strong nonlinearity in its inverse problem, leading to high noise sensitivity and prominent artifacts—limiting its practical deployment in industrial inspection and medical imaging. To address this, we propose a Conditional Diffusion Model with Voltage Consistency (CDMVC), the first framework to deeply integrate diffusion-based generative priors with the EIT forward physics model. CDMVC enhances convergence via pre-reconstruction initialization, enforces data fidelity through a forward-voltage constraint network, and incorporates physics-driven consistency regularization during sampling. We construct an augmented dataset featuring complex concave targets and perform joint training on both synthetic and experimental data. Experiments demonstrate that CDMVC significantly improves spatial resolution and structural fidelity, achieves superior noise and artifact suppression, reduces reconstruction error by over 40%, and exhibits strong robustness and cross-shape generalization capability.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Responsible Web: Data and user privacy-enhancing technologies for the Web
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Electrical impedance tomography (EIT) is a non-invasive imaging technique, which has been widely used in the fields of industrial inspection, medical monitoring and tactile sensing. However, due to the inherent non-linearity and ill-conditioned nature of the EIT inverse problem, the reconstructed image is highly sensitive to the measured data, and random noise artifacts often appear in the reconstructed image, which greatly limits the application of EIT. To address this issue, a conditional diffusion model with voltage consistency (CDMVC) is proposed in this study. The method consists of a pre-imaging module, a conditional diffusion model for reconstruction, a forward voltage constraint network and a scheme of voltage consistency constraint during sampling process. The pre-imaging module is employed to generate the initial reconstruction. This serves as a condition for training the conditional diffusion model. Finally, based on the forward voltage constraint network, a voltage consistency constraint is implemented in the sampling phase to incorporate forward information of EIT, thereby enhancing imaging quality. A more complete dataset, including both common and complex concave shapes, is generated. The proposed method is validated using both simulation and physical experiments. Experimental results demonstrate that our method can significantly improves the quality of reconstructed images. In addition, experimental results also demonstrate that our method has good robustness and generalization performance.

Problem

• Electrical Impedance Tomography
• Image Quality
• Data Sensitivity

Innovation

• CDMVC
• Electrical Impedance Tomography
• Voltage Consistency Constraint