Semantic Diffusion Posterior Sampling for Cardiac Ultrasound Dehazing

TL;DR

This paper introduces a novel semantic-guided diffusion-based algorithm for dehazing cardiac ultrasound images, significantly improving image clarity in challenging cases by leveraging semantic segmentation and generative priors.

Contribution

The work presents a new diffusion posterior sampling method guided by semantic segmentation and trained on clean data, tailored for echocardiography dehazing tasks.

Findings

Strong performance on challenge dataset across contrast and fidelity metrics

Effective integration of semantic segmentation into diffusion dehazing

Code availability for reproducibility and further research

Abstract

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.