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

作者：Yonatan Urman, Mark Nishimura, Daniel R. Abraham, Xiaozhi Cao, Kawin Setsompop · 发表于：Magnetic Resonance in Medicine · 年份：2026 · DOI：10.1002/mrm.70500 · 研究领域：Advanced MRI Techniques and Applications、Lanthanide and Transition Metal Complexes、Functional Brain Connectivity Studies

ABSTRACT Purpose Magnetic Resonance Fingerprinting (MRF) enables rapid quantitative imaging, but high‐resolution 3D reconstructions remain computationally expensive due to the NUFFTs required at every iteration, and the commonly used Locally Low Rank (LLR) regularization becomes ineffective at high acceleration. Learned 3D priors could address these limitations, but training them at scale is challenging due to memory and runtime constraints. This work proposes SPUR‐iG, a fully 3D deep unrolled subspace reconstruction framework that provides fast, high‐quality reconstruction for high‐resolution non‐Cartesian 3D MRF, while keeping training time computationally tractable. Methods SPUR‐iG leverages implicit GROG‐based data consistency (DC), which grids non‐Cartesian k‐space using a learned family of kernels, enabling efficient FFT‐based DC with minimal artifacts. To make 3D unrolled training more efficient, we introduce a staged training strategy that keeps computation tractable while progressively improving reconstruction quality. We evaluate the method on a large in vivo dataset, as well as on cross‐vendor out‐of‐distribution data. Results At 1 mm isotropic resolution, SPUR‐iG outperforms LLR and a state‐of‐the‐art hybrid 2D‐3D unrolled baseline in subspace coefficient quality and / accuracy. Whole‐brain reconstructions complete in under 15 s, providing up to a 111 speedup for 2‐min scans relative to LLR. Notably, SPUR‐iG reconstructions from 30‐s acquisitions achieve mean accu...