BioAtt: Anatomical Prior Driven Low-Dose CT Denoising
This addresses the challenge of preserving clinically relevant structures in medical imaging for healthcare applications, representing a novel method rather than an incremental improvement.
The paper tackled the problem of over-smoothing anatomical details in low-dose CT denoising by proposing BioAtt, a framework that uses anatomical priors from BiomedCLIP to guide attention, resulting in improved SSIM, PSNR, and RMSE across multiple anatomical regions.
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.