Metal Artifact Reduction

Metal artifact reduction (MAR) aims to improve the quality of computed tomography (CT) images degraded by the presence of metallic implants, enabling more accurate diagnoses and treatment planning. Current research heavily utilizes deep learning, employing various architectures like UNets, Transformers, and diffusion models, often operating in dual or even quad domains (image, sinogram, and their Fourier transforms) to leverage complementary information. These advancements address limitations of previous methods by incorporating physical models of X-ray interaction with metals and improving generalization across diverse datasets. Successful MAR techniques are crucial for improving the accuracy and reliability of medical imaging in numerous clinical applications.