Learning optimized sampling patterns for accelerated MRI reconstruction via diffusion models

Magnetic resonance imaging (MRI) is a powerful medical imaging modality, but long acquisition times limit throughput, patient comfort, and clinical accessibility. Diffusion-based generative models serve as strong image priors for reducing scan time with accelerated MRI reconstruction and offer robustness across variations in the acquisition model. However, most existing diffusion-based approaches do not exploit the unique ability in MRI to jointly design both the sampling pattern and the reconstruction method. Although prior learning-based approaches have optimized sampling patterns for end-to-end unrolled networks, analogous methods for diffusion-based reconstruction have not been established due to the computational burden of posterior sampling. We propose a method to optimize $k$ -space sampling patterns for accelerated multi-coil MRI reconstruction using diffusion models as priors.

We introduce a training objective based on a single-step posterior mean estimate that avoids backpropagation through an expensive iterative reconstruction process. Then, we present a greedy strategy for learning Cartesian sampling patterns that selects informative $k$ -space locations using gradient information from a pre-trained diffusion model while enforcing spatial diversity among samples.

Experimental results across multiple anatomies and acceleration factors demonstrate that diffusion models using the optimized sampling patterns achieve higher-quality reconstructions in comparison with using fixed and learned baseline patterns.

We propose a method to learn sampling patterns for accelerating MRI with diffusion-based generative models and posterior sampling reconstruction.