Optimizing Sampling Patterns for Compressed Sensing MRI with Diffusion Generative Models

TL;DR

This paper introduces a novel method to optimize k-space sampling patterns in accelerated MRI using diffusion models, significantly improving reconstruction quality by jointly designing sampling and reconstruction strategies.

Contribution

It presents a new approach to optimize sampling patterns specifically for diffusion-based MRI reconstruction, overcoming computational challenges with a single-step posterior estimate and greedy selection.

Findings

Optimized sampling patterns outperform fixed and baseline patterns.

Diffusion models with learned sampling achieve higher-quality MRI reconstructions.

Method is effective across multiple anatomies and acceleration factors.

Abstract

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. While 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. In this work, 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 to using fixed and learned baseline patterns.