Deep learning enabled fast 3D brain MRI at 0.055 tesla

Abstract

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

Whole-body magnetic resonance imaging at 0.05 Tesla

“…We designed a partial Fourier super-resolution (PF-SR) method that integrates image reconstruction and super-resolution (fig. S3) ( 26 ). The PF-SR model, consisting of multiscale feature extraction, spatial attention, and reconstruction functions, was experimentally validated by comparing 0.055 T brain images to 3 T images from the same subjects ( 26 ).…”

“…S3) ( 26 ). The PF-SR model, consisting of multiscale feature extraction, spatial attention, and reconstruction functions, was experimentally validated by comparing 0.055 T brain images to 3 T images from the same subjects ( 26 ). In this study, we demonstrated PF-SR reconstruction for whole-body MRI at 0.05 T. The data acquisitions typically involved 3D encoding with k-space partial Fourier sampling.…”

“…Recent studies from our group (23,26) and others (22) have demonstrated the possibility of a deep learning MRI reconstruction and superresolution approach for brain ULF MRI by exploiting large-scale high-field brain MRI data. In this study, we have implemented and demonstrated such an image formation method, PF-SR (26), applied to brain, spine, liver, and knee imaging, illustrating the ability of such data-driven image formation in enhancing image resolution while suppressing noise and artifacts. Our previous studies (23,26) and the preliminary brain and spine tests using synthetic datasets in this study have also shown the potential of applying this approach to datasets that contain brain and spine lesions.…”

“…Utilizing deep learning for enhanced image formation at 0.05 Tesla MR signal at 0.05 T is several orders of magnitude weaker than at 3 T, the standard highfield strength, due to its proportionality to field strength squared (B 0 2 ) (32), causing high image noise and poor resolution in ULF MRI. To overcome this challenge, we turned to computing and devised deep learning-based reconstruction methods for ULF MRI image formation that are driven by the large-scale high-field MRI data (23,26). We designed a partial Fourier super-resolution (PF-SR) method that integrates image reconstruction and super-resolution (fig.…”

“…We demonstrated the wide-ranging applicability of this scanner for imaging various anatomical structures, including the brain, spine, abdomen, heart, lungs, and extremities. Furthermore, we demonstrated the promise of deep learning 3D image formation on this whole-body ULF MRI platform by learning from large-scale high-field MRI data, using a method we developed ( 26 ).…”