Attention-based dual-branch deep network for sparse-view computed tomography image reconstruction

Abstract

Background: The widespread application of X-ray computed tomography (CT) imaging in medical screening makes radiation safety a major concern for public health. Sparse-view CT is a promising solution to reduce the radiation dose. However, the reconstructed CT images obtained using sparse-view CT may suffer severe streaking artifacts and structural information loss. Methods: In this study, a novel attention-based dual-branch end-to-end deep network based on the attention mechanism. More specifically, an attention-based dual-branch network (ADB-Net) is proposed to solve the problem of CT image reconstruction. In this network, downsampled sinogram input is processed through 2 parallel branches (CT branch and signogram branch) of the ADB-Net to independently extract the distinct, high-level feature maps. These feature maps are fused in a specified attention module from 3 perspectives (channel, plane, and spatial) to allow complementary optimizations that can mitigate the streaking artifacts and the structure loss in sparse-view CT imaging. Results: Numerical simulations, an anthropomorphic thorax phantom, and in vivo preclinical experiments were conducted to verify the sparse-view CT imaging performance of the ADB-Net. The proposed network achieved a root-mean-square error (RMSE) of 20.6160, a structural similarity (SSIM) of 0.9257, and a peak signal-to-noise ratio (PSNR) of 38.8246 on numerical data. The visualization results demonstrate that this newly developed network can consistently remove the streaking artifacts while maintaining the fine structures. Conclusions: The proposed attention-based dual-branch deep network, ADB-Net, provides a promising alternative to reconstruct high-quality sparse-view CT images for low-dose CT imaging.

Towards full-stack deep learning-empowered data processing pipeline for synchrotron tomography experiments

“…In 2023, Gao et al. 74 proposed an attention-based dual branch (CT branch and sinogram branch) network called ADB-Net. For the sinogram branch, atrous spatial pyramid pooling (ASPP) combined with convolutional layers is applied on sinusoidal images for higher-level feature extraction globally.…”