提出轻量级网络同时降噪低剂量PET与CT图像。
Hybrid Swin Attention Networks for Simultaneously Low-Dose PET and CT Denoising
- 结合高效全局注意力与混合上采样，提升特征捕捉能力。
- 在公开数据集上优于现有方法，模型小巧适合部署。
- 适合临床实用，兼顾性能与计算效率。
低剂量计算机断层扫描（LDCT）和正电子发射断层扫描（PET）通过显著降低辐射暴露，成为传统成像方式的安全替代方案。然而，当前方法常面临训练稳定性与计算效率之间的权衡。本文提出一种新型混合Swin注意力网络（HSANet），融合高效全局注意力（EGA）模块与混合上采样模块，以克服上述局限。EGA模块增强空间与通道间交互，提升网络捕捉相关特征的能力；混合上采样模块则降低对噪声过拟合的风险。我们在公开的LDCT/PET数据集上验证该方法。实验结果表明，相较于最先进方法，HSANet在保持轻量化模型规模的同时，实现了更优的去噪性能，适用于配备标准显存的GPU部署。因此，本方法在实际临床应用中展现出巨大潜力。
原文摘要 · Abstract (English)
Low-dose computed tomography (LDCT) and positron emission tomography (PET) have emerged as safer alternatives to conventional imaging modalities by significantly reducing radiation exposure. However, current approaches often face a trade$-$off between training stability and computational efficiency. In this study, we propose a novel Hybrid Swin Attention Network (HSANet), which incorporates Efficient Global Attention (EGA) modules and a hybrid upsampling module to address these limitations. The EGA modules enhance both spatial and channel-wise interaction, improving the network's capacity to capture relevant features, while the hybrid upsampling module mitigates the risk of overfitting to noise. We validate the proposed approach using a publicly available LDCT/PET dataset. Experimental results demonstrate that HSANet achieves superior denoising performance compared to state of the art methods, while maintaining a lightweight model size suitable for deployment on GPUs with standard memory configurations. Thus, our approach demonstrates significant potential for practical, real-world clinical applications.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。