Deep learning enabled fast 3D brain MRI at 0.055 tesla

• DOI: 10.1126/sciadv.adi9327
• Publication Date: 2023-09-22T17:58:33Z
• Authors: Christopher Man; Vick Lau; Shi Su; Yujiao Zhao; Linfang Xiao; Ye Ding; Gilberto K. K. Leung; Alex T. L. Leong; Ed X. Wu
• Keywords: Real-time MRI

In recent years, there has been an intensive development of portable ultralow-field magnetic resonance imaging (MRI) for low-cost, shielding-free, and point-of-care applications. However, its quality is poor scan time long. We propose a fast acquisition deep learning reconstruction framework to accelerate brain MRI at 0.055 tesla. The consists single average three-dimensional (3D) encoding with 2D partial Fourier sampling, reducing the T1- T2-weighted protocols 2.5 3.2 minutes, respectively. 3D leverages homogeneous anatomy available in high-field human data enhance image quality, reduce artifacts noise, improve spatial resolution synthetic 1.5-mm isotropic resolution. Our method successfully overcomes low-signal barrier, reconstructing fine anatomical structures that are reproducible within subjects consistent across two protocols. It enables whole-brain tesla, potential widespread biomedical