Facebook, NYU Pin Hope of Faster MRIs on Artificial Intelligence

Xconomy San Francisco — 

The long, sometimes painful wait to complete an MRI may soon be cut down dramatically—and we might have Facebook and its artificial intelligence unit to thank for it.

The social media giant announced Monday that it is working with the radiology department at New York University’s School of Medicine to potentially use artificial intelligence software to speed up the process for taking a magnetic resonance imaging (MRI) scan. In a blog post from its engineering website, Facebook said it hopes its A.I. programs may be able to make the process, which can take longer than an hour, up to 10 times as fast.

The NYU radiology department is providing Facebook’s artificial intelligence group with 3 million MRI images of the knee, brain, and liver, from about 10,000 clinical cases (which are anonymous), the blog post says. Facebook intends to use its software to study the images, so that the A.I. program can learn the construction of human body parts, as CNN reported.

The goal is eventually to take faster MRIs, which may have noise and obstructions, and use the A.I. to complete the images, the blog post says. An A.I.-focused group at the NYU medical school began working in 2016 on a method of using software to improve the speed of MRI scans, and Facebook got involved soon after. The Facebook group believes the technology could be used in other areas of medicine, such as CT scans, too.

Other big groups, including GE and IBM, are using A.I. tools for similar purposes. Radiology contractor Intrinsic Imaging, which is based in both Boston and San Antonio, TX, said in 2017 it has had an uptick in recent years of the number of clients that want help assessing the accuracy of A.I. software used to diagnose conditions such as cancer in X-rays, CT scans, and other healthcare imaging.

Other companies in the sector include Israel- and Massachusetts-based MaxQ-AI (formerly called MedyMatch), which uses A.I. software to classify images; Israel-based Zebra Medical Vision, a company with a large database of medical images that aims to help radiologists detect overlooked indications, among other things; and Seoul-based Lunit, which is developing technology to help physicians make clinical decisions, not just diagnoses.