Zhang Xuan, Fang Chenyun, Qiao Zhiwei
School of Computer and Information Technology, Shanxi University, Taiyuan, Shanxi, China.
J Xray Sci Technol. 2025 Jan;33(1):157-166. doi: 10.1177/08953996241300016. Epub 2025 Jan 8.
Although computed tomography (CT) is widely employed in disease detection, X-ray radiation may pose a risk to the health of patients. Reducing the projection views is a common method, however, the reconstructed images often suffer from streak artifacts.
In previous related works, it can be found that the convolutional neural network (CNN) is proficient in extracting local features, while the Transformer is adept at capturing global information. To suppress streak artifacts for sparse-view CT, this study aims to develop a method that combines the advantages of CNN and Transformer.
In this paper, we propose a Multi-Attention and Dual-Branch Feature Aggregation U-shaped Transformer network (MAFA-Uformer), which consists of two branches: CNN and Transformer. Firstly, with a coordinate attention mechanism, the Transformer branch can capture the overall structure and orientation information to provide a global context understanding of the image under reconstruction. Secondly, the CNN branch focuses on extracting crucial local features of images through channel spatial attention, thus enhancing detail recognition capabilities. Finally, through a feature fusion module, the global information from the Transformer and the local features from the CNN are integrated effectively.
Experimental results demonstrate that our method achieves outstanding performance in terms of peak signal-to-noise ratio (PSNR), structural similarity (SSIM), and root mean square error (RMSE). Compared with Restormer, our model achieves significant improvements: PSNR increases by 0.76 dB, SSIM improves by 0.44%, and RMSE decreases by 8.55%.
Our method not only effectively suppresses artifacts but also better preserves details and features, thereby providing robust support for accurate diagnosis of CT images.
尽管计算机断层扫描（CT）在疾病检测中被广泛应用，但X射线辐射可能对患者健康构成风险。减少投影视图是一种常用方法，然而，重建图像常常会出现条纹伪影。
在以往相关工作中发现，卷积神经网络（CNN）擅长提取局部特征，而Transformer擅长捕捉全局信息。为了抑制稀疏视图CT中的条纹伪影，本研究旨在开发一种结合CNN和Transformer优点的方法。
在本文中，我们提出了一种多注意力和双分支特征聚合U型Transformer网络（MAFA-Uformer），它由两个分支组成：CNN和Transformer。首先，通过坐标注意力机制，Transformer分支可以捕捉整体结构和方向信息，以提供对重建图像的全局上下文理解。其次，CNN分支专注于通过通道空间注意力提取图像的关键局部特征，从而增强细节识别能力。最后，通过特征融合模块，有效地整合来自Transformer的全局信息和来自CNN的局部特征。
实验结果表明，我们的方法在峰值信噪比（PSNR）、结构相似性（SSIM）和均方根误差（RMSE）方面取得了优异的性能。与Restormer相比，我们的模型有显著改进：PSNR提高了0.76 dB，SSIM提高了0.44%，RMSE降低了8.55%。
我们的方法不仅有效地抑制了伪影，还更好地保留了细节和特征，从而为CT图像的准确诊断提供了有力支持。
