# A Data-Constrained and Physics-Guided Conditional Diffusion Model for Electrical Impedance Tomography Image Reconstruction

## TL;DR

A new model for electrical impedance tomography improves image accuracy and robustness using physics and data constraints, enabling better medical and industrial imaging.

## Contribution

A multi-source conditional diffusion model with physics-guided priors and data constraints for EIT image reconstruction is introduced.

## Key findings

- MS-CDM outperforms existing methods in reconstruction accuracy and noise robustness.
- The model achieves cross-system generalization without retraining on real EIT platforms.
- Hybrid Swin–Mamba network captures both local and global image features effectively.

## Abstract

A multi-source conditional diffusion model is developed for electrical impedance tomography, enabling stable and accurate image reconstruction.A hybrid Swin–Mamba denoising network is introduced to efficiently capture both local structural details and global spatial consistency.The framework shows strong robustness and cross-system generalization across multiple real water tank platforms without retraining.The method enables noise-tolerant and high-resolution imaging for real-time medical and industrial sensing applications.

A multi-source conditional diffusion model is developed for electrical impedance tomography, enabling stable and accurate image reconstruction.

A hybrid Swin–Mamba denoising network is introduced to efficiently capture both local structural details and global spatial consistency.

The framework shows strong robustness and cross-system generalization across multiple real water tank platforms without retraining.

The method enables noise-tolerant and high-resolution imaging for real-time medical and industrial sensing applications.

Electrical impedance tomography (EIT) provides noninvasive, high-temporal-resolution imaging for medical and industrial applications. However, accurate image reconstruction remains challenging due to the severe ill-posedness and nonlinearity of the inverse problem, as well as the limited robustness of existing single-source learning-based methods in real measurement scenarios. To address these limitations, a data-constrained and physics-guided Multi-Source Conditional Diffusion Model (MS-CDM) is proposed for EIT image reconstruction. Unlike conventional conditional diffusion methods that rely on a single measurement or an image prior, MS-CDM utilizes boundary voltage measurements as data-driven constraints and incorporates coarse reconstructions as physics-guided structural priors. This multi-source conditioning strategy provides complementary guidance during the reverse diffusion process, enabling balanced recovery of fine boundary details and global topological consistency. To support this framework, a Hybrid Swin–Mamba Denoising U-Net is developed, combining hierarchical window-based self-attention for local spatial modeling with bidirectional state-space modeling for efficient global dependency capture. Extensive experiments on simulated datasets and three real EIT experimental platforms demonstrate that MS-CDM consistently outperforms state-of-the-art numerical, supervised, and diffusion-based methods in terms of reconstruction accuracy, structural consistency, and noise robustness. Moreover, the proposed model exhibits robust cross-system applicability without system-specific retraining under multi-protocol training, highlighting its practical applicability in diverse real-world EIT scenarios.