A Two-Stage Imaging Framework Combining CNN and Physics-Informed Neural Networks for Full-Inverse Tomography: A Case Study in Electrical Impedance Tomography (EIT)
This work addresses the challenge of accurate and practical EIT reconstruction for medical or industrial imaging applications, representing an incremental improvement by hybridizing existing techniques.
The paper tackles the ill-posed inverse problem of reconstructing internal conductivities in Electrical Impedance Tomography (EIT) using boundary voltage measurements by proposing a two-stage hybrid learning framework that combines CNNs and Physics-Informed Neural Networks (PINNs). The result is a method that integrates data-driven and model-driven approaches to reconstruct conductivity distributions while adhering to physical laws, overcoming limitations of existing PINN-based methods that rely on impractical prior knowledge.
Electrical Impedance Tomography (EIT) is a highly ill-posed inverse problem, with the challenge of reconstructing internal conductivities using only boundary voltage measurements. Although Physics-Informed Neural Networks (PINNs) have shown potential in solving inverse problems, existing approaches are limited in their applicability to EIT, as they often rely on impractical prior knowledge and assumptions that cannot be satisfied in real-world scenarios. To address these limitations, we propose a two-stage hybrid learning framework that combines Convolutional Neural Networks (CNNs) and PINNs. This framework integrates data-driven and model-driven paradigms, blending supervised and unsupervised learning to reconstruct conductivity distributions while ensuring adherence to the underlying physical laws, thereby overcoming the constraints of existing methods.