MDPG: Multi-domain Diffusion Prior Guidance for MRI Reconstruction

TL;DR

This paper introduces MDPG, a novel MRI reconstruction method that leverages multi-domain diffusion priors and advanced fusion techniques to improve image quality and data consistency in under-sampled MRI data.

Contribution

The paper proposes a multi-domain diffusion prior guidance framework using pre-trained latent diffusion models and introduces new fusion strategies for enhanced MRI reconstruction.

Findings

Significant improvement in MRI reconstruction quality on public datasets.

Effective integration of latent and image domain priors.

Enhanced data consistency through dual-domain fusion and k-space regularization.

Abstract

Magnetic Resonance Imaging (MRI) reconstruction is essential in medical diagnostics. As the latest generative models, diffusion models (DMs) have struggled to produce high-fidelity images due to their stochastic nature in image domains. Latent diffusion models (LDMs) yield both compact and detailed prior knowledge in latent domains, which could effectively guide the model towards more effective learning of the original data distribution. Inspired by this, we propose Multi-domain Diffusion Prior Guidance (MDPG) provided by pre-trained LDMs to enhance data consistency in MRI reconstruction tasks. Specifically, we first construct a Visual-Mamba-based backbone, which enables efficient encoding and reconstruction of under-sampled images. Then pre-trained LDMs are integrated to provide conditional priors in both latent and image domains. A novel Latent Guided Attention (LGA) is proposed for efficient fusion in multi-level latent domains. Simultaneously, to effectively utilize a prior in both the k-space and image domain, under-sampled images are fused with generated full-sampled images by the Dual-domain Fusion Branch (DFB) for self-adaption guidance. Lastly, to further enhance the data consistency, we propose a k-space regularization strategy based on the non-auto-calibration signal (NACS) set. Extensive experiments on two public MRI datasets fully demonstrate the effectiveness of the proposed methodology. The code is available at https://github.com/Zolento/MDPG.