Filter2Noise：基于注意力引导双边滤波的可解释自监督单图像降噪方法在低剂量CT中的应用

Filter2Noise: Interpretable Self-Supervised Single-Image Denoising for Low-Dose CT with Attention-Guided Bilateral Filtering

April 18, 2025

作者: Yipeng Sun, Linda-Sophie Schneider, Mingxuan Gu, Siyuan Mei, Chengze Ye, Fabian Wagner, Siming Bayer, Andreas Maier

cs.AI

摘要

在低剂量CT中，有效的去噪对于增强细微结构和低对比度病变至关重要，同时能够防止诊断错误。监督学习方法受限于有限的配对数据集，而自监督方法通常需要多张噪声图像，并依赖如U-Net等深度网络，对去噪机制的解释性较弱。为解决这些挑战，我们提出了一种可解释的自监督单图像去噪框架——Filter2Noise（F2N）。我们的方法引入了一种注意力引导的双边滤波器，该滤波器通过一个轻量级模块适应每个噪声输入，该模块预测空间变化的滤波器参数，这些参数可在训练后可视化和调整，以实现用户对特定感兴趣区域的去噪控制。为实现单图像训练，我们提出了一种新颖的下采样混洗策略，并引入了一种新的自监督损失函数，该函数将Noise2Noise的概念扩展到单图像，并解决了空间相关噪声的问题。在Mayo Clinic 2016低剂量CT数据集上，F2N在PSNR指标上领先于当前最佳的自监督单图像方法（ZS-N2N）4.59 dB，同时提升了透明度、用户控制能力和参数效率。这些特性为需要精确且可解释降噪的医疗应用提供了关键优势。我们的代码展示于https://github.com/sypsyp97/Filter2Noise.git。

English

Effective denoising is crucial in low-dose CT to enhance subtle structures and low-contrast lesions while preventing diagnostic errors. Supervised methods struggle with limited paired datasets, and self-supervised approaches often require multiple noisy images and rely on deep networks like U-Net, offering little insight into the denoising mechanism. To address these challenges, we propose an interpretable self-supervised single-image denoising framework -- Filter2Noise (F2N). Our approach introduces an Attention-Guided Bilateral Filter that adapted to each noisy input through a lightweight module that predicts spatially varying filter parameters, which can be visualized and adjusted post-training for user-controlled denoising in specific regions of interest. To enable single-image training, we introduce a novel downsampling shuffle strategy with a new self-supervised loss function that extends the concept of Noise2Noise to a single image and addresses spatially correlated noise. On the Mayo Clinic 2016 low-dose CT dataset, F2N outperforms the leading self-supervised single-image method (ZS-N2N) by 4.59 dB PSNR while improving transparency, user control, and parametric efficiency. These features provide key advantages for medical applications that require precise and interpretable noise reduction. Our code is demonstrated at https://github.com/sypsyp97/Filter2Noise.git .