Magnetic Resonance Imaging (MRI) produces excellent soft tissue contrast, albeit it is an inherently slow imaging modality. Promising deep learning methods have recently been proposed to reconstruct accelerated MRI scans. However, existing methods still suffer from various limitations regarding image fidelity, contextual sensitivity, and reliance on fully-sampled acquisitions for model training. To comprehensively address these limitations, we propose a novel self-supervised deep reconstruction model, named Self-Supervised Diffusion Reconstruction (SSDiffRecon). SSDiffRecon expresses a conditional diffusion process as an unrolled architecture that interleaves cross-attention transformers for reverse diffusion steps with data-consistency blocks for physics-driven processing. Unlike recent diffusion methods for MRI reconstruction, a self-supervision strategy is adopted to train SSDiffRecon using only undersampled k-space data. Comprehensive experiments on public brain MR datasets demonstrates the superiority of SSDiffRecon against state-of-the-art supervised, and self-supervised baselines in terms of reconstruction speed and quality. Implementation will be available at https://github.com/yilmazkorkmaz1/SSDiffRecon.

翻译：磁共振成像（MRI）虽然能产生优异的软组织对比度，但其本质上是一种成像速度较慢的模态。近期提出的深度学习方法在加速MRI扫描重建方面展现出前景，然而现有方法在图像保真度、上下文敏感度以及对全采样数据训练的依赖性等方面仍存在诸多局限。为全面解决这些问题，我们提出了一种新型自监督深度重建模型——自监督扩散重建（Self-Supervised Diffusion Reconstruction, SSDiffRecon）。SSDiffRecon将条件扩散过程表达为一种展开架构，该架构通过交替使用交叉注意力变换器实现反向扩散步骤，并结合数据一致性模块进行物理驱动处理。与近期用于MRI重建的扩散方法不同，SSDiffRecon采用自监督策略，仅利用欠采样k空间数据进行训练。在公开脑部MR数据集上的综合实验表明，SSDiffRecon在重建速度和质量方面均优于当前最先进的有监督及自监督基线方法。代码实现将发布于https://github.com/yilmazkorkmaz1/SSDiffRecon。