This is the authors' abstract. We don't add key points for this paper.
Sparse View Computed Tomography (SVCT) is a promising technology for reducing radiation dose and improving scan speed by reducing the number of required X-ray projection images. However, the limited projection data used in SVCT often results in reconstructed images with noise and artifacts. We propose a dual-domain SVCT image reconstruction network that leverages both residual attention mechanisms and convolutional networks. The network utilizes information from both the sinogram and image domains, enabling complementary information supplementation. To further enhance image restoration, we integrate a residual attention mechanism into the Swin-Transformer architecture to mitigate feature collapse. Additionally, a parallel convolutional branch is incorporated to enhance feature extraction completeness.By leveraging the remote correlation capability of attention mechanisms and the local information extraction capabilities of convolutional networks, our model effectively extracts valuable information for reconstruction. This integration of local and global information effectively guides the reconstruction process. Experiments on the NIH-AAPM dataset demonstrate that our model effectively reduces artifacts and improves the reconstruction of complex structures, outperforming other learning-based reconstruction models.
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
He et al. (2024) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: