Semantic Diffusion Posterior Sampling for Cardiac Ultrasound Dehazing

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Stevens, Tristan S. W., Nolan, Oisín, van Sloun, Ruud J. G.
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912551839727616
author Stevens, Tristan S. W.
Nolan, Oisín
van Sloun, Ruud J. G.
author_facet Stevens, Tristan S. W.
Nolan, Oisín
van Sloun, Ruud J. G.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_17326
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Semantic Diffusion Posterior Sampling for Cardiac Ultrasound Dehazing
Stevens, Tristan S. W.
Nolan, Oisín
van Sloun, Ruud J. G.
Image and Video Processing
Computer Vision and Pattern Recognition
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.
title Semantic Diffusion Posterior Sampling for Cardiac Ultrasound Dehazing
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.17326