Semantic Diffusion Posterior Sampling for Cardiac Ultrasound Dehazing
This work addresses image quality issues in echocardiography for diagnosis and monitoring, but it is incremental as it applies a known method to a specific domain challenge.
The paper tackles haze degradation in cardiac ultrasound images by proposing a semantic-guided diffusion-based dehazing algorithm, which demonstrates strong performance on contrast and fidelity metrics in the MICCAI DehazingEcho2025 challenge dataset.
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.