IDOL-Net: An Interactive Dual-Domain Parallel Network for CT Metal Artifact Reduction

Abstract

Due to the presence of metallic implants, the imaging quality of computed tomography (CT) would be heavily degraded. With the rapid development of deep learning, several neural network models have been proposed for metal artifact reduction (MAR). Since the dual-domain MAR methods can leverage the hybrid information from both sinogram and image domains, they have significantly improved the performance compared to single domain methods. However, current dual-domain methods usually operate on both domains in a specific order, which implicitly imposes a certain priority prior into MAR and may ignore the latent information interaction between both domains. To address this problem, in this article, we propose a novel interactive dual-domain parallel network for CT MAR, dubbed as IDOL-Net. Specifically, different from existing dual-domain methods, the proposed IDOL-Net is composed of two modules. First, to obtain high-quality prior sinogram and image to guide following MAR, we propose a novel artifact disentanglement network that disentangles the noise and artifacts in sinogram and image domain, respectively. The follow-up refinement module consists of two parallel and interactive branches that simultaneously operate on image and sinogram, fully exploiting the latent information interaction between both domains. Extensive experiments on simulated and clinical artifacts data demonstrate that the proposed IDOL-Net outperforms several state-of-the-art models in both qualitative and quantitative aspects.