MotionDPS: Motion-Compensated 3D Brain MRI Reconstruction

TL;DR

MotionDPS introduces a Bayesian framework that jointly estimates 3D brain MRI images, motion parameters, and coil sensitivities from corrupted data, leveraging diffusion models for improved reconstruction and robustness.

Contribution

It presents a novel unsupervised method integrating diffusion models with physics-based optimization for motion-compensated MRI reconstruction.

Findings

Achieves superior image quality over classical methods.

Demonstrates robustness in severe motion and high acceleration scenarios.

Operates without requiring paired motion-free training data.

Abstract

Magnetic resonance imaging (MRI) is highly susceptible to patient motion due to its relatively long acquisition times and the fact that data are acquired sequentially in k-space. Even small patient movements introduce phase inconsistencies across measurements, leading to severe artifacts such as blurring, ghosting, and geometric distortions that can compromise diagnostic quality. Retrospective motion compensation remains challenging, particularly in accelerated acquisitions, due to the ill-posed nature of the joint reconstruction and motion estimation problem. In this work, we propose a unified Bayesian framework for motion-compensated 3D MRI that jointly estimates the anatomical image, rigid-body motion parameters, and coil sensitivity maps directly from motion-corrupted k-space data. Our approach integrates pretrained 3D complex-valued score-based diffusion models as expressive anatomical image priors within a physics-based forward model. Inference is performed by alternating diffusion posterior image updates with efficient proximal optimization steps for motion and coil sensitivity estimation, enabling fully unsupervised reconstruction without the need for paired motion-free training data. Experiments on simulated and real-motion brain MRI datasets demonstrate that the proposed method achieves improved image quality and motion robustness compared to state-of-the-art classical and learning-based motion correction techniques, particularly in the presence of severe motion and high acceleration.