Database of Diffusion MRI Brain Scans at 64 mT and 3 T

Published

January 7, 2026

Author(s)

Andrew Dienstfrey, Zydrunas Gimbutas, Joe Chalfoun, Adele Peskin, Kalina Jordanova, Kathryn Keenan, Stephen Ogier

Abstract

Low-field magnetic resonance imaging offers the promise to significantly increase access to in vivo soft tissue imaging. The technology is both portable and low-cost in relation to the high-field scanners in clinical use today. However, these gains are accompanied by a degradation in image resolution and contrast. Many researchers are investigating machine learning processing pipelines to help restore image quality. Such studies require a well-curated data collection to train their models. In the following we describe a database of brain scans designed for this task. Diffusion-weighted brain scans were acquired for twenty participants on both a 3 T and a 64 mT scanner. In addition, a T1-weighted scan was acquired on the 3 T system for morphological tissue identification. The data from both systems are co-registered and processed in a consistent manner. The resulting database contains diffusion-weighted images, mean diffusivity maps, and tissue parcellation all reported at a resolution consistent with low-field scanners in use today. This database is made available to the public in its entirety to provide a foundation for training and validating machine learning approaches to enhance the quality of low-field magnetic resonance imaging.

Citation

NIST Interagency/Internal Report (NISTIR) - 8580

Report Number

8580

NIST Pub Series

NIST Interagency/Internal Report (NISTIR)

Pub Type

NIST Pubs

Download Paper

Local Download

Keywords

low-field magnetic resonance imaging, diffusion magnetic resonance imaging, brain scan database, machine learning

Citation

Dienstfrey, A. , Gimbutas, Z. , Chalfoun, J. , Peskin, A. , Jordanova, K. , Keenan, K. and Ogier, S. (2026), Database of Diffusion MRI Brain Scans at 64 mT and 3 T, NIST Interagency/Internal Report (NISTIR), National Institute of Standards and Technology, Gaithersburg, MD, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=959155 (Accessed January 8, 2026)