Deep Dual-Domain United Guiding Learning With Global-Local Transformer-Convolution U-Net for LDCT Reconstruction

Due to the potential harmful risks caused by the excessive X-ray radiation dose, low dose has emerged as one of the major rules of computed tomography (CT) for clinical applications. However, reducing radiation dose severely leads to degraded reconstructed CT image quality with noises and artifacts, and it may seriously hamper clinical diagnosis. Currently, model-driven deep learning (DL)-based dual-domain learning with expert knowledge can reconstruct CT images from projections acquired in nonideal conditions, and they have been demonstrated with inspired performance in low-dose CT (LDCT) reconstruction. However, because of domain-progressive strategy, these dual-domain methods are prone to produce seriously secondary artifacts and suffer from subtle structural degeneration. In this article, we propose a novel deep dual-domain united guiding learning framework, i.e., DUGL-Net. First, we put forward a domain-guiding strategy. The projection-domain network plays the guiding role on image-domain network to effectively enhance overall network stability and powerfully avoid secondary artifacts. Second, we elaborately design a global-local transformer-convolution U-Net, i.e., GL-TCUNet, as the base network in both projection domain and image domain for reinforcing dual-domain model learning. This efficiently leverages the advantages of Swin transformer and convolutional neural network (CNN) to suppress noises and artifacts. Finally, the proposed DUGL-Net is evaluated on the 2016 NIH-AAPM-Mayo clinic LDCT Grand Challenge dataset and real data, and our results validate that the proposed method outperforms the state-of-the-art (SOTA) competing methods. This efficient, accurate, and reliable LDCT denoising technique has great potential for clinical applications.