LIR-Net:Learnable Iterative Reconstruction Network for Fan Beam CT Sparse-View Reconstruction

In computed tomography (CT), although sparse sampling of projections effectively mitigates radiation problems, the quality of CT images is severely compromised. Recovering high-quality CT images from sparsely sampled data is a challenging task. Recently, “Iterative Theory + Deep Learning” schemes have shown promising results in CT reconstruction tasks. In this paper, we propose an Iterative Reconstruction Network Model based on learnable projection operators (LIR-NET). Unlike existing image domain iteration schemes that fuse information from the projection domain, LIR-Net achieves joint optimization and iteration of dual-domain data. The dual-domain subnetwork uses a replaceable and lightweight U-net. We propose an Enhanced Aligned Loss (EAL) scheme to speed up convergence in the projection domain subnet. A designed last-iteration Sparse Truth Bootstrap (STB) module improves data distortion, while Bit-plane Codec (BC) is combined to enhance the noise discovery and removal capability of the image domain subnet. Extensive experiments based on the dataset from the “Low Dose CT Image and Projection Data (LDCT-and-Projection data)” show that our approach outperforms the best available solutions in both quantitative and qualitative evaluations. Moreover, the robustness of the proposed scheme has been tested and validated on an additional dataset. Our code and data are available at https://github.com/YB-Cheng/LIR-Net .