Silicon Valley tech company gains FDA approval for AI-powered image cleanup tool

Menlo Park, California-based Subtle Medical announced Tuesday, Oct. 15, that it’s the first to score FDA approval for an AI-fueled technology to enhance MRI images.

SubtleMR, as the product is called, is an image-processing software that deploys deep-learning algorithms to bolster images created by any scanner. Currently, several imaging centers and universities, including the University of California, San Francisco, are testing it for clinical use, according to a company announcement.

"One of the most exciting things about deep-learning reconstruction is how it redefines the usual negotiation between exam time and image quality. This could lead to significant downstream value for imaging operations and for patient experience," Christopher Hess, MD, chair of the Department of Radiology and Biomedical Imaging at UCSF, said in a statement.

The AI-powered technology can be integrated with any brand of MRI or picture archiving and communication system. And it can prove useful for imaging patients who have a hard time sitting still for long stretches of time, eliminating the need for costly and time-consuming re-scans.

Subtle Medical said that it is first and only company to receive FDA clearance for technology that uses artificial intelligence to enhance medical images. Last year, the Food and Drug Administration also approved its SubtlePET, which helps to enhance pictures produced by positron-emission tomography.

Subtle CEO and founder Enhao Gong called this week’s news an “important milestone for the company.”

Marty Stempniak

Marty Stempniak has covered healthcare since 2012, with his byline appearing in the American Hospital Association's member magazine, Modern Healthcare and McKnight's. Prior to that, he wrote about village government and local business for his hometown newspaper in Oak Park, Illinois. He won a Peter Lisagor and Gold EXCEL awards in 2017 for his coverage of the opioid epidemic. 

Around the web

The ACR hopes these changes, including the addition of diagnostic performance feedback, will help reduce the number of patients with incidental nodules lost to follow-up each year.

And it can do so with almost 100% accuracy as a first reader, according to a new large-scale analysis.

The patient, who was being cared for in the ICU, was not accompanied or monitored by nursing staff during his exam, despite being sedated.