DenOiS: Dual-Domain Denoising of Observation and Solution in Ultrasound Image Reconstruction

TL;DR

DenOiS is a novel framework that enhances ultrasound image reconstruction by denoising both measurements and solutions, improving robustness and generalization from simulated training to real data.

Contribution

It introduces a dual-domain denoising approach combining observation refinement and diffusion-based PnP reconstruction, addressing noise and model inaccuracies.

Findings

Achieves high-fidelity ultrasound images from noisy, incomplete data.

Generalizes well from simulation-trained models to real-world data.

Outperforms traditional methods in speed-of-sound imaging tasks.

Abstract

Medical imaging aims to recover underlying tissue properties, using inexact (simplified/linearized) imaging models and often from inaccurate and incomplete measurements. Analytical reconstruction methods rely on hand-crafted regularization, sensitive to noise assumptions and parameter tuning. Among deep learning alternatives, plug-and-play (PnP) approaches learn regularization while incorporating imaging physics during inference, outperforming purely data-driven methods. The performance of all these approaches, however, still strongly depends on measurement quality and imaging model accuracy. In this work, we propose DenOiS, a framework that denoises both input observations and resulting solution in their respective domains. It consists of an observation refinement strategy that corrects degraded measurements while compensating for imaging model simplifications, and a diffusion-based PnP reconstruction approach that remains robust under missing measurements. DenOiS enables generalization to real data from training only in simulations, resulting in high-fidelity image reconstruction with noisy observations and inexact imaging models. We demonstrate this for speed-of-sound imaging as a challenging setting of quantitative ultrasound image reconstruction.