DEMIX: Dual-Encoder Latent Masking Framework for Mixed Noise Reduction in Ultrasound Imaging

TL;DR

This paper introduces DEMIX, a dual-encoder framework inspired by diffusion models, that effectively reduces mixed noise and PSF distortions in ultrasound images, improving image quality and downstream segmentation performance.

Contribution

DEMIX is a novel dual-encoder denoising framework with a masked gated fusion mechanism, specifically designed for mixed noise and PSF distortions in ultrasound imaging, outperforming existing methods.

Findings

DEMIX outperforms state-of-the-art baselines in noise suppression.

DEMIX preserves fine structural details in ultrasound images.

DEMIX improves downstream segmentation accuracy.

Abstract

Ultrasound imaging is widely used in noninvasive medical diagnostics due to its efficiency, portability, and avoidance of ionizing radiation. However, its utility is limited by the quality of the signal. Signal-dependent speckle noise, signal-independent sensor noise, and non-uniform spatial blurring caused by the transducer and modeled by the point spread function (PSF) degrade the image quality. These degradations challenge conventional image restoration methods, which assume simplified noise models, and highlight the need for specialized algorithms capable of effectively reducing the degradations while preserving fine structural details. We propose DEMIX, a novel dual-encoder denoising framework with a masked gated fusion mechanism, for denoising ultrasound images degraded by mixed noise and further degraded by PSF-induced distortions. DEMIX is inspired by diffusion models and is characterized by a forward process and a deterministic reverse process. DEMIX adaptively assesses the different noise components, disentangles them in the latent space, and suppresses these components while compensating for PSF degradations. Extensive experiments on two ultrasound datasets, along with a downstream segmentation task, demonstrate that DEMIX consistently outperforms state-of-the-art baselines, achieving superior noise suppression and preserving structural details. The code will be made publicly available.