Dual-Domain Denoising Diffusion Probabilistic Model for Metal Artifact Reduction

In computed tomography (CT), the presence of metal parts in the scanned region results in metal artifacts in the reconstructed images, which can significantly impact diagnosis and treatment planning. Consequently, removing metal artifacts has been a critical area of research in clinical practice. In this paper, we propose a metal artifact reduction (MAR) algorithm based on dual-domain denoising diffusion probabilistic models (DDPM). Our approach begins with pre-processing with linear interpolation (LI) and refinement with a convolutional neural network (CNN) to generate an initial reprojection. Then, two DDPM networks are employed: one to synthesize the corrupted sinogram and the other to optimize the resultant images in the image domain. The experimental results show that our algorithm utilizes two specialized DDPMs and achieves superior performance. The sinogram-domain DDPM reconstructs a high-quality sinogram, while the image-domain DDPM effectively removes remaining artifacts. Synergistically, these contributions lead to a significant improvement in overall image quality. Furthermore, our method successfully addresses the hallucination issues observed in the generic DDPM, enhancing the applicability of DDPM in medical imaging.