DICE: Diffusion Consensus Equilibrium for Sparse-view CT Reconstruction

2025-09-17

AI Summary

Sparse-view CT reconstruction suffers from severe ill-posedness due to extreme undersampling, rendering conventional iterative methods inadequate for modeling the complex structural priors inherent in medical images. To address this, we propose Diffusion Consensus Equilibrium (DICE), the first framework integrating a two-agent consensus equilibrium mechanism into the diffusion model sampling process. DICE decouples prior learning from data consistency enforcement: a diffusion model provides expressive structural priors, while a proximal operator ensures exact projection fidelity via constrained optimization. These components are jointly optimized through alternating updates. Evaluated under diverse sparse-view settings—including 15, 30, and 60 views, as well as uniform and non-uniform angular sampling—DICE consistently outperforms state-of-the-art methods. It achieves superior reconstruction accuracy, enhanced fine-detail recovery, and improved robustness to noise, establishing new performance benchmarks in sparse-view CT reconstruction.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Security and Privacy: Data transparency and provenance
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Sparse-view computed tomography (CT) reconstruction is fundamentally challenging due to undersampling, leading to an ill-posed inverse problem. Traditional iterative methods incorporate handcrafted or learned priors to regularize the solution but struggle to capture the complex structures present in medical images. In contrast, diffusion models (DMs) have recently emerged as powerful generative priors that can accurately model complex image distributions. In this work, we introduce Diffusion Consensus Equilibrium (DICE), a framework that integrates a two-agent consensus equilibrium into the sampling process of a DM. DICE alternates between: (i) a data-consistency agent, implemented through a proximal operator enforcing measurement consistency, and (ii) a prior agent, realized by a DM performing a clean image estimation at each sampling step. By balancing these two complementary agents iteratively, DICE effectively combines strong generative prior capabilities with measurement consistency. Experimental results show that DICE significantly outperforms state-of-the-art baselines in reconstructing high-quality CT images under uniform and non-uniform sparse-view settings of 15, 30, and 60 views (out of a total of 180), demonstrating both its effectiveness and robustness.

Problem

• Reconstructing sparse-view CT images from undersampled data
• Integrating generative priors with measurement consistency constraints
• Improving reconstruction quality under limited projection views

Innovation

• Integrates two-agent consensus equilibrium framework
• Combines data-consistency proximal operator enforcement
• Uses diffusion model prior at each step