The Reading Room: NYU Langone and Facebook AI Partner for Faster MRIs

Through a partnership with Facebook AI, researchers at NYU Langone Health have trained a neural network that can create MRI images in a fraction of the time needed for standard scans.

In a study published in the American Journal of Roentgenology, the team revealed the radiologists reading the resulting images detected the same abnormalities with the accelerated scans as they did with traditional images.

For more coverage based on industry expert insights and research, subscribe to the Diagnostic Imaging e-Newsletter here.

To reach this determination, they examined two sets of knee MRI scans from 108 patients and created two sets of images -- one using the standard approach and one using the accelerated MRI artificial intelligence model. Based on their analysis, they determined that their 3T fastMRI protocol used four times less data and could produce an image quicker, requiring the patient to spend less time in the scanner.

The goal, Recht said, is to one day apply accelerated MRI to other organs, including the brain.