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

2026-02-26

AI Summary

This work addresses the limitations of existing plug-and-play (PnP) diffusion prior methods in medical image reconstruction, which often suffer from steady-state bias and fail to strictly enforce physical measurement constraints due to neglecting historical information—particularly under severe degradation. The authors propose a dual-coupled PnP diffusion framework that, for the first time, recovers dual variables within the diffusion prior by integrating ADMM optimization with an integral feedback mechanism, ensuring asymptotic convergence of reconstructions onto the exact data manifold. Additionally, a spectral homogenization module is introduced to modulate residual components in the frequency domain, aligning structured residuals with the white-noise assumption inherent to diffusion models. This approach effectively overcomes the bias–hallucination trade-off, achieving state-of-the-art fidelity in both CT and MRI reconstruction while significantly accelerating convergence and eliminating steady-state bias and hallucinatory artifacts.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Calibration & Uncertainty Quantification
• Search and Optimization: Non-convex Optimization

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

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, which restores the classical dual variable to provide integral feedback, theoretically guaranteeing asymptotic convergence to the exact data manifold. 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.

Problem

• Plug-and-Play Diffusion
• Medical Image Reconstruction
• Steady-State Bias
• Structured Artifacts
• AWGN Assumption

Innovation

• Plug-and-Play Diffusion
• Dual Variable Coupling
• Spectral Homogenization
• Medical Image Reconstruction
• ADMM