Non-rigid Motion Correction for MRI Reconstruction via Coarse-To-Fine Diffusion Models

TL;DR

This paper introduces a novel MRI reconstruction method that uses a coarse-to-fine diffusion model within an alternating minimization framework to effectively correct non-rigid motion artifacts, even with highly undersampled data.

Contribution

It presents a new joint reconstruction and motion correction approach employing a bespoke diffusion model with a coarse-to-fine strategy, improving robustness over standard methods.

Findings

Effective correction of non-rigid motion artifacts in MRI

Robust performance on highly undersampled data (64x)

Applicable across various sampling patterns and protocols

Abstract

Magnetic Resonance Imaging (MRI) is highly susceptible to motion artifacts due to the extended acquisition times required for k-space sampling. These artifacts can compromise diagnostic utility, particularly for dynamic imaging. We propose a novel alternating minimization framework that leverages a bespoke diffusion model to jointly reconstruct and correct non-rigid motion-corrupted k-space data. The diffusion model uses a coarse-to-fine denoising strategy to capture large overall motion and reconstruct the lower frequencies of the image first, providing a better inductive bias for motion estimation than that of standard diffusion models. We demonstrate the performance of our approach on both real-world cine cardiac MRI datasets and complex simulated rigid and non-rigid deformations, even when each motion state is undersampled by a factor of 64x. Additionally, our method is agnostic to sampling patterns, anatomical variations, and MRI scanning protocols, as long as some low frequency components are sampled during each motion state.