基于去噪正则化的快速MRI重建一致性模型
Consistency Models for Fast MRI Reconstruction Using Regularization by Denoising
查看机构详情
- University of Minnesota（明尼苏达大学）
- Center for Magnetic Resonance Research（磁共振研究中心）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
本研究提出CM-RED方法，将一致性模型整合到去噪正则化框架中，仅用4次网络函数评估，在fastMRI数据集上实现优于现有方法的快速高质量MRI重建。
中文摘要 AI 辅助
扩散模型（DMs）已成为MRI重建中强大的生成先验，取得了良好效果，但基于DM的方法需要大量迭代优化，限制了实际部署。一致性模型（CMs）提供了一种有吸引力的替代方案，旨在单次完成扩散轨迹映射，实现更快生成。本研究提出CM-RED，一种新型MRI重建方法，将预训练CM整合到去噪正则化（RED）框架中。该方法基于加速近端梯度RED（RED-APG），在更新步骤中进一步引入受控噪声注入，以增强生成多样性并加速收敛。在fastMRI膝关节和大脑数据集上的大量实验表明，CM-RED在多个解剖结构、对比度权重、加速因子和欠采样模式下，仅使用4次网络函数评估（NFEs）即可实现高质量重建。所提方法在定量指标和视觉保真度上均持续优于现有基于DM和CM的方法，且对超参数变化具有强鲁棒性，凸显CM-RED是一种高效且有效的加速MRI重建生成框架。源代码和预训练模型可在该httpsURL处公开获取。
英文摘要
Diffusion models (DMs) have emerged as powerful generative priors for MRI reconstruction with promising results. Yet DM-based methods require extensive iterative refinement, limiting their practical deployment. Consistency models (CMs) provide a compelling alternative, aiming to map out the diffusion trajectory in a single pass, enabling faster generation. In this work, we propose CM-RED, a novel MRI reconstruction method that integrates a pretrained CM into the regularization by denoising (RED) scheme. Our method builds on accelerated proximal gradient RED (RED-APG), and further incorporates controlled noise injection during the update steps to enhance generative diversity and accelerate convergence. Extensive experiments on the fastMRI knee and brain datasets demonstrate that CM-RED achieves high-quality reconstructions across multiple anatomies, contrast weights, acceleration factors, and undersampling patterns, using only 4 network function evaluations (NFEs). The proposed method consistently outperforms existing DM- and CM-based approaches in both quantitative metrics and visual fidelity, and exhibits strong robustness to hyperparameter variations, highlighting CM-RED as an efficient and effective generative framework for accelerated MRI reconstruction. The source code and pretrained models are publicly available at https://github.com/MerveGulle/CM-RED.
