Diffusion models are a leading method for image generation and have been successfully applied in magnetic resonance imaging (MRI) reconstruction. Current diffusion-based reconstruction methods rely on coil sensitivity maps (CSM) to reconstruct multi-coil data. However, it is difficult to accurately estimate CSMs in practice use, resulting in degradation of the reconstruction quality. To address this issue, we propose a self-consistency-driven diffusion model inspired by the iterative self-consistent parallel imaging (SPIRiT), namely SPIRiT-Diffusion. Specifically, the iterative solver of the self-consistent term in SPIRiT is utilized to design a novel stochastic differential equation (SDE) for diffusion process. Then $\textit{k}$-space data can be interpolated directly during the reverse diffusion process, instead of using CSM to separate and combine individual coil images. This method indicates that the optimization model can be used to design SDE in diffusion models, driving the diffusion process strongly conforming with the physics involved in the optimization model, dubbed model-driven diffusion. The proposed SPIRiT-Diffusion method was evaluated on a 3D joint Intracranial and Carotid Vessel Wall imaging dataset. The results demonstrate that it outperforms the CSM-based reconstruction methods, and achieves high reconstruction quality at a high acceleration rate of 10.

翻译：扩散模型是图像生成的主流方法，并已成功应用于磁共振成像（MRI）重建。当前基于扩散的重建方法依赖于线圈灵敏度图（CSM）来重建多线圈数据。然而，实际应用中难以准确估计CSM，导致重建质量下降。为解决此问题，我们受迭代自一致性并行成像（SPIRiT）启发，提出了一种自一致性驱动的扩散模型，即SPIRiT-Diffusion。具体而言，利用SPIRiT中自一致性项的迭代求解器设计了一种新的随机微分方程（SDE）用于扩散过程。随后，在反向扩散过程中可直接对 k 空间数据进行插值，而无需使用CSM来分离和组合各线圈图像。该方法表明，优化模型可用于设计扩散模型中的SDE，从而使扩散过程高度符合优化模型中涉及的物理机制，我们称之为模型驱动扩散。所提出的SPIRiT-Diffusion方法在3D颅内与颈动脉血管壁联合成像数据集上进行了评估。结果表明，该方法优于基于CSM的重建方法，并在10倍高加速率下实现了高质量重建。