基于物理模型的扩散模型，有效去除超声图像斑点噪声
IRSDE-Despeckle: A Physics-Grounded Diffusion Model for Generalizable Ultrasound Despeckling
- 用磁共振图像模拟生成带斑点的超声图像，构建监督训练数据
- 在模拟测试集上优于传统滤波和现有学习方法，保留解剖结构边缘
- 通过模型差异量化不确定性，识别易出错区域，适合临床部署
超声成像广泛用于实时、无创诊断，但斑点噪声及相关伪影会降低图像质量并影响判读。本文提出一种基于图像恢复随机微分方程框架的扩散模型，用于超声去斑点。为支持有监督训练，我们利用 Matlab UltraSound Toolbox 从无斑点的磁共振图像中仿真生成大量配对的超声图像数据。所提模型在重建去斑点图像的同时，保持解剖学上有意义的边缘与对比度。在独立的模拟测试集上，该方法持续优于经典滤波器和近期基于学习的去斑点基线模型。通过跨模型方差量化预测不确定性，发现较高不确定性与较高重建误差相关，可作为困难或易失败区域的实用指标。最后，评估了对仿真探头设置的敏感性，观察到域偏移现象，提示需多样化训练与适配以实现稳健的临床应用。
原文摘要 · Abstract (English)
Ultrasound imaging is widely used for real-time, noninvasive diagnosis, but speckle and related artifacts reduce image quality and can hinder interpretation. We present a diffusion-based ultrasound despeckling method built on the Image Restoration Stochastic Differential Equations framework. To enable supervised training, we curate large paired datasets by simulating ultrasound images from speckle-free magnetic resonance images using the Matlab UltraSound Toolbox. The proposed model reconstructs speckle-suppressed images while preserving anatomically meaningful edges and contrast. On a held-out simulated test set, our approach consistently outperforms classical filters and recent learning-based despeckling baselines. We quantify prediction uncertainty via cross-model variance and show that higher uncertainty correlates with higher reconstruction error, providing a practical indicator of difficult or failure-prone regions. Finally, we evaluate sensitivity to simulation probe settings and observe domain shift, motivating diversified training and adaptation for robust clinical deployment.
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。