Fully 3D Unrolled Magnetic Resonance Fingerprinting Reconstruction via Staged Pretraining and Implicit Gridding

TL;DR

This paper introduces SPUR-iG, a novel 3D unrolled MRI reconstruction method that combines implicit gridding and staged training to significantly improve speed and accuracy in high-resolution 3D MRF imaging.

Contribution

The paper presents a fully 3D deep unrolled reconstruction framework with a new implicit GROG-based data consistency and a three-stage training strategy, enabling large-scale 3D MRF reconstruction within practical compute limits.

Findings

Achieves up to 111x speedup in whole-brain reconstructions.

Improves quality of subspace coefficient maps over LLR and hybrid methods.

Attains T1 mapping accuracy comparable or superior to longer scan protocols.

Abstract

Magnetic Resonance Fingerprinting (MRF) enables fast quantitative imaging, yet reconstructing high-resolution 3D data remains computationally demanding. Non-Cartesian reconstructions require repeated non-uniform FFTs, and the commonly used Locally Low Rank (LLR) prior adds computational overhead and becomes insufficient at high accelerations. Learned 3D priors could address these limitations, but training them at scale is challenging due to memory and runtime demands. We propose SPUR-iG, a fully 3D deep unrolled subspace reconstruction framework that integrates efficient data consistency with a progressive training strategy. Data consistency leverages implicit GROG, which grids non-Cartesian data onto a Cartesian grid with an implicitly learned kernel, enabling FFT-based updates with minimal artifacts. Training proceeds in three stages: (1) pretraining a denoiser with extensive data augmentation, (2) greedy per-iteration unrolled training, and (3) final fine-tuning with gradient checkpointing. Together, these stages make large-scale 3D unrolled learning feasible within a reasonable compute budget. On a large in vivo dataset with retrospective undersampling, SPUR-iG improves subspace coefficient maps quality and quantitative accuracy at 1-mm isotropic resolution compared with LLR and a hybrid 2D/3D unrolled baseline. Whole-brain reconstructions complete in under 15-seconds, with up to $\times$111 speedup for 2-minute acquisitions. Notably, $T_1$ maps with our method from 30-second scans achieve accuracy on par with or exceeding LLR reconstructions from 2-minute scans. Overall, the framework improves both accuracy and speed in large-scale 3D MRF reconstruction, enabling efficient and reliable accelerated quantitative imaging.