用语义引导的扩散模型，提升心脏超声图像去雾效果。
Semantic Diffusion Posterior Sampling for Cardiac Ultrasound Dehazing
- 结合语义分割与扩散模型，从模糊图像重建清晰影像
- 在DehazingEcho2025数据集上显著提升对比度与保真度
- 适合医疗影像增强、超声图像处理研究人员参考
超声心动图在心脏成像中具有核心作用，可提供动态心脏视图，对诊断和监测至关重要。然而，多重路径回波常导致图像模糊，尤其在难成像患者中更为明显。本文针对MICCAI Dehazing Echocardiography Challenge (DehazingEcho2025) 提出一种语义引导的扩散去雾算法。方法将模糊输入的像素级语义分割结果融入扩散后验采样框架，并以清洁超声数据训练的生成先验进行引导。在挑战赛数据集上的定量评估显示，该方法在对比度与保真度指标上表现优异。提交算法的代码已公开于 https://github.com/tristan-deep/semantic-diffusion-echo-dehazing。
原文摘要 · Abstract (English)
Echocardiography plays a central role in cardiac imaging, offering dynamic views of the heart that are essential for diagnosis and monitoring. However, image quality can be significantly degraded by haze arising from multipath reverberations, particularly in difficult-to-image patients. In this work, we propose a semantic-guided, diffusion-based dehazing algorithm developed for the MICCAI Dehazing Echocardiography Challenge (DehazingEcho2025). Our method integrates a pixel-wise noise model, derived from semantic segmentation of hazy inputs into a diffusion posterior sampling framework guided by a generative prior trained on clean ultrasound data. Quantitative evaluation on the challenge dataset demonstrates strong performance across contrast and fidelity metrics. Code for the submitted algorithm is available at https://github.com/tristan-deep/semantic-diffusion-echo-dehazing.
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。