用解剖先验引导降噪，保留重要结构同时去噪
BioAtt: Anatomical Prior Driven Low-Dose CT Denoising
- 将医学视觉语言模型提取的解剖先验融入注意力机制
- 在多个解剖区域上提升SSIM、PSNR、RMSE指标
- 注意力图显示改进源于解剖引导而非模型变复杂
基于深度学习的低剂量CT（LDCT）去噪方法显著提升了图像质量。然而，现有模型因纯数据驱动的注意力机制，常过度平滑重要解剖细节。为此，我们提出新型LDCT去噪框架BioAtt，其核心创新在于利用预训练医学视觉语言模型BiomedCLIP提取的解剖先验分布，指导去噪模型关注解剖相关区域，在抑制噪声的同时保留临床相关结构。主要贡献包括：BioAtt在多个解剖区域上优于基线与注意力模型，在SSIM、PSNR、RMSE指标上均表现更优；通过将解剖先验直接嵌入空间注意力，引入新架构范式；注意力图直观验证性能提升源于解剖引导，而非模型复杂度增加。
原文摘要 · Abstract (English)
Deep-learning-based denoising methods have significantly improved Low-Dose CT (LDCT) image quality. However, existing models often over-smooth important anatomical details due to their purely data-driven attention mechanisms. To address this challenge, we propose a novel LDCT denoising framework, BioAtt. The key innovation lies in attending anatomical prior distributions extracted from the pretrained vision-language model BiomedCLIP. These priors guide the denoising model to focus on anatomically relevant regions to suppress noise while preserving clinically relevant structures. We highlight three main contributions: BioAtt outperforms baseline and attention-based models in SSIM, PSNR, and RMSE across multiple anatomical regions. The framework introduces a new architectural paradigm by embedding anatomic priors directly into spatial attention. Finally, BioAtt attention maps provide visual confirmation that the improvements stem from anatomical guidance rather than increased model complexity.
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。