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

Can Deniz Bezek; Orcun Goksel

eess.IVApr 2, 2026

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

Authors: Can Deniz Bezek, Orcun Goksel

Organizations: Department of Information Technology, Uppsala University, Sweden

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.

Figures & tables

Figure 1: Deep learning approaches in image reconstruction (a) without using the imaging model, (b,c) using it disjointly, and (d) jointly with data consistency in a plug-and-play (PnP) framework. (e) Our proposed iterative dual-domain denoising framework (DenOiS), alternating between observation and solution domain refinement. (f) Illustration on an ultrasound application for speed-of-sound imaging from incomplete and noisy observations with an inexact model.

Input	$L_{2}$ -TV		$L_{1}$ -TV		Unet [ 5 ]		Dolce [ 14 ]		Unet( $\mathcal{M}_{\text{U}}$ )		$\mathbf{\mathcal{R}_{\text{D}}}$
$\mathbf{b}^{\prime}$	11.95	( 36.25 )	10.39	( 32.37 )	10.73	( 42.31 )	6.75	( 15.73 )	43.35	( 37.27 )	6.78	( 18.31 )
$\mathcal{M}_{\text{U}}(\mathbf{b}^{\prime})$	8.45	( 32.23 )	8.13	( 30.43 )	34.82	( 42.27 )	10.15	( 14.46 )	7.01	( 21.22 )	7.21	( 14.35 )
$\mathcal{M}_{\text{U}}(\mathbf{b}^{\prime},\mathcal{P})$	8.36	( 31.39 )	7.70	( 27.35 )	34.23	( 42.27 )	10.42	( 17.56 )	6.70	( 19.38 )	7.21	( 12.28 )
$\mathcal{M}_{\text{U}}(\mathbf{b}^{\prime},\mathcal{P},\mathrm{A}^{\prime}\mathbf{x}^{\prime})$	8.26	( 30.12 )	8.04	( 28.19 )	34.20	( 42.27 )	11.78	( 27.42 )	7.10	( 24.10 )	7.55	( 11.53 )
$\mathcal{M}_{\text{D}}(\mathbf{b}^{\prime})$	9.44	( 31.04 )	9.11	( 28.87 )	34.95	( 42.27 )	11.86	( 22.65 )	6.97	( 18.04 )	8.29	( 13.16 )
$\mathcal{M}_{\text{D}}(\mathbf{b}^{\prime},\mathcal{P})$	8.58	( 30.32 )	8.27	( 28.23 )	34.33	( 42.27 )	10.97	( 23.62 )	6.34	( 16.58 )	7.43	( 11.67 )

Table 1: In-silico results on (C 2 ) reporting RMSE (ACE). Gray marks baseline configurations. Rows are observation and columns are reconstruction approaches.

Input	$L_{2}$ -TV		$L_{1}$ -TV		Dolce [ 14 ]		Unet( $\mathcal{M}_{\text{U}}$ )		$\mathbf{\mathcal{R}_{\text{D}}}$
$\mathbf{b}^{\prime}$	18.04	( 37.56 )	21.94	( 28.01 )	14.13	( 28.80 )	34.36	( 29.96 )	13.71	( 16.34 )
$\mathcal{M}_{\text{U}}(\mathbf{b}^{\prime})$	13.60	( 38.41 )	13.60	( 38.25 )	10.87	( 35.83 )	14.14	( 42.10 )	10.26	( 24.45 )
$\mathcal{M}_{\text{U}}(\mathbf{b}^{\prime},\mathcal{P})$	13.12	( 38.93 )	13.18	( 38.74 )	11.22	( 38.25 )	14.94	( 40.60 )	10.61	( 23.85 )
$\mathcal{M}_{\text{U}}(\mathbf{b}^{\prime},\mathcal{P},\mathrm{A}^{\prime}\mathbf{x}^{\prime})$	13.93	( 34.32 )	13.94	( 33.21 )	12.11	( 31.47 )	13.49	( 30.80 )	10.62	( 15.09 )
$\mathcal{M}_{\text{D}}(\mathbf{b}^{\prime})$	12.95	( 36.27 )	12.88	( 35.81 )	11.69	( 35.18 )	14.69	( 39.52 )	10.04	( 21.98 )
$\mathcal{M}_{\text{D}}(\mathbf{b}^{\prime},\mathcal{P})$	14.01	( 34.90 )	13.99	( 34.78 )	10.51	( 30.31 )	16.50	( 40.03 )	9.79	( 20.18 )

Table 2: Real phantom data results reporting RMSE (ACE). Values within half a standard deviation of the best results 9.79

\pm

5.54 (13.48

\pm

4.0) are highlighted. Gray marks baseline configurations.

Panel of Figure 2 — Figure 2: (a) Sample reconstructions for C 2 and phantom data, with RMSE (ACE) values reported. (b) An in-vivo breast cancer example reporting $\mathrm{\Delta}\mathrm{c}$ / gCNR. (c) Corrections of two acquired observations with different $\mathcal{M}_{\text{D}}$ variants.

Explore similar work

Plug-and-Play Diffusion Meets ADMM: Dual-Variable Coupling for Robust Medical Image Reconstruction
Feb 26, 2026Chenhe Du, Xuanyu Tian, Qing Wu +4Image Reconstruction Diffusion-Based Inverse Problems
ShanghaiTech University · Shanghai Jiao Tong University
Pyramid Self-Contrastive Learning for Single-shot Test-time Ultrasound Image Denoising
May 12, 2026Jiajing Zhang, Bingze Dai, Xi Zhang +2Self-Supervised Image Denoising Test-Time Adaptation
Department of Electrical and Computer Engineering, The University of Hong Kong, Hong Kong · Department of Biomedical Engineering, Duke University, North Carolina, United States
IRSDE-Despeckle: A Physics-Grounded Diffusion Model for Generalizable Ultrasound Despeckling
Feb 26, 2026Shuoqi Chen, Yujia Wu, Geoffrey P. LukeUltrasound Imaging Image Denoising
Thayer School of Engineering, Dartmouth College, Hanover, NH, USA

Feb 26, 2026J/K move · Enter open · S save

Plug-and-Play Diffusion Meets ADMM: Dual-Variable Coupling for Robust Medical Image Reconstruction

Chenhe Du, Xuanyu Tian, Qing Wu, Muyu Liu+3

ShanghaiTech University · Shanghai Jiao Tong University

Image Reconstruction Diffusion-Based Inverse Problems Diffusion MRI Alternating Direction Method of Multipliers

Open paper AskPDF arXiv

Plug-and-Play diffusion prior (PnPDP) frameworks have emerged as a powerful paradigm for solving imaging inverse problems by treating pretrained generative models as modular priors. However, we identify a critical flaw in prevailing PnP solvers (e.g., based on HQS or Proximal Gradient): they function as memoryless operators, updating estimates solely based on instantaneous gradients. This lack of historical tracking inevitably leads to non-vanishing steady-state bias, where the reconstruction fails to strictly satisfy physical measurements under heavy corruption. To resolve this, we propose Dual-Coupled PnP Diffusion (DC-PnPDP), which restores the classical dual variable to provide integral feedback, progressively enforce agreement between the data-consistency and prior. However, this rigorous geometric coupling introduces a secondary challenge: the accumulated dual residuals exhibit spectrally colored, structured artifacts that violate the Additive White Gaussian Noise (AWGN) assumption of diffusion priors, causing severe hallucinations. To bridge this gap, we introduce Spectral Homogenization (SH), a frequency-domain adaptation mechanism that modulates these structured residuals into statistically compliant pseudo-AWGN inputs. This effectively aligns the solver's rigorous optimization trajectory with the denoiser's valid statistical manifold. Extensive experiments on CT and MRI reconstruction demonstrate that our approach resolves the bias-hallucination trade-off, achieving state-of-the-art fidelity with significantly accelerated convergence. The code is available at https://github.com/duchenhe/DC-PnPDP

Abstract

Explore similar work

Plug-and-Play Diffusion Meets ADMM: Dual-Variable Coupling for Robust Medical Image Reconstruction

Pyramid Self-Contrastive Learning for Single-shot Test-time Ultrasound Image Denoising

IRSDE-Despeckle: A Physics-Grounded Diffusion Model for Generalizable Ultrasound Despeckling