NYU School of Medicine releases dataset to help make MRI scans 10x faster

As part of a collaborative research project with Facebook, the NYU School of Medicine is releasing an open-source dataset aimed at using artificial intelligence to make MRI scans 10 times faster.

The initial dataset release includes more than 1.5 million anonymous MRIs of the knee, captured from 10,000 scans, as well as raw measurement data from nearly 1,600 scans. Future releases will include data from liver and brain scans.

In addition, Facebook AI Research and NYU will provide the larger scientific community with a suite of tools—including baseline metrics to compare results—and a leaderboard to keep track of progress as part of an organized challenge to be announced in the near future.

“We hope that the release of this landmark dataset, the largest-ever collection of fully-sampled MRI raw data, will provide researchers with the tools necessary to overcome the challenges inherent in accelerating MR imaging,” says Michael Recht, MD, chair of the Department of Radiology at NYU School of Medicine. “This work has the potential to not only help increase access to MR imaging, but also improve patient care worldwide.”

NYU Hospital

The effort, called fastMRI, is meant to speed up notoriously slow MRI machines which can take between15 minutes to more than an hour to conduct scans, versus less than a second or up to a minute—respectively—for X-ray and CT scans.

Also See: Faster CPU can accelerate ability to use AI on medical images

Recht announced the release of the dataset on Sunday during a plenary address at the 2018 Annual Meeting of the Radiological Society of North America in Chicago.

In his presentation at RSNA, he cited baseline results from Facebook AI Research and NYU Langone showing that acceleration of MRI by a factor of four is already possible. However, Recht emphasized that they were early results that require broad validation and that the ultimate goal is to make MRI scans 10 times faster.

“This collaboration focuses on applying the strengths of machine learning to reconstruct high-value images in new ways,” says Daniel Sodickson, MD, director of the Department of Radiology’s Center for Advanced Imaging Innovation and Research. “Rather than using existing images to train AI algorithms, we will radically change the way medical images are acquired in the first place.”

“Our aim is not merely enhanced data mining with AI, but rather creating new capabilities for medical visualization, to benefit human health,” added Sodickson.

For reprint and licensing requests for this article, click here.