NYU releases open-source MRI dataset as part of Facebook collaboration
NYU School of Medicine’s Department of Radiology announced it will release more than 1.5 million anonymous MR images from its fastMRI collaboration with Facebook AI Research (FAIR), a partnership focused on using AI to speed up MRIs.
Michael P. Recht, MD, chair and the Louis Marx Professor of Radiology at NYU Langone Health, announced the release on Sunday, Nov. 25, during the RSNA 2018 annual meeting opening address.
This first release is the largest-ever open source dataset, according to an NYU Langone Health statement. It consists of knee images taken from 10,000 scans and “raw measurement data” from nearly 1,600 additional scans, according to the release.
“We hope that the release of this landmark data set, 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,” Recht said in the statement. “This work has the potential to not only help increase access to MR imaging, but also improve patient care worldwide.”
NYU School of Medicine Department of Radiology’s Center for Advanced Imaging Innovation and Research (CAI2R) and FAIR announced their collaborative project in August. They aim to foster the development of AI technology to make MRI scans 10 times faster.
Matt joined Chicago’s TriMed team in 2018 covering all areas of health imaging after two years reporting on the hospital field. He holds a bachelor’s in English from UIC, and enjoys a good cup of coffee and an interesting documentary.