GE Healthcare’s DL model receives FDA approval for cardiac MRI

GE Healthcare announced that the US Food and Drug Administration has approved Sonic DL, which leverages neural networks to accelerate image acquisition in magnetic resonance imaging for healthcare use.

why it matters

A significant downside to cardiac MRI is the need for patients to remain still and hold their breath during the imaging exam.

A new deep learning technology from GE called SonicDL could allow for high-quality cardiac images “in a single heartbeat,” according to a GE Healthcare announcement.

For patients who are challenged to hold their breath or have arrhythmia or advanced heart failure, this is “a game-changer heart,” said Dr. Gianluca Pontone, director of perioperative cardiology and cardiovascular imaging at the Centro Cardiologico Monzino in Milan, in the statement. Is.

He added that the approach “ensures an easier and more comfortable experience for patients during an MRI exam.”

GE Healthcare says the Sonic DL has the potential to reduce scan times by up to 83% compared to today’s gold standard, which can reduce or eliminate the need for repetitive patient breath holding and for cardiac MRI May expand the pool of eligible patients.

A video released by the company alongside the announcement shows comparable imaging of coverage of the entire heart in 59 seconds, compared to one minute and 42 seconds by conventional MRI.

For patients with breathing challenges, comparable imaging for whole-heart coverage with free breathing came in 51 seconds versus two minutes and 10 seconds with breath-hold and conventional MRI.

GE Healthcare claims that DL-driven imaging improves clarity despite arrhythmias, comparing imaging completed in 46 frames in 24 seconds with the Sonic DL versus 20 frames in one minute and 45 seconds with conventional MRI.

The company says it aims to expand Sonic DL and AIR Recon DL technology to all organs.

big trend

The technology leverages GE Healthcare’s AIR Recon DL, a deep-learning-based image reconstruction algorithm. Ji Xu, president and CEO of Global MR for GE Healthcare, says AI has already benefited more than 10 million patients.

“Chicago-area-based Dally Health & Care, which uses the technology, has reduced wait times, allowing them to see more patients sooner,” said Vignesh Shetty, SVP and GM, Edison AI and Platform for GE Healthcare. “

In December, Healthcare IT News Shetty about the pace of AI and its capabilities to address healthcare’s data challenges and improve health outcomes.

He said that doctors and patients are benefiting from the artificial intelligence embedded in medical devices.

“The goal is to have AI tools ready when and where they are needed to contribute to faster diagnosis and ideally better patient outcomes.”

Neural networks depend on a large number of parameters. The general development of AI in healthcare has focused much energy on advancing diagnostic techniques to detect heart disease.

In 2021, GE Healthcare partnered with the American College of Cardiology to collaborate on AI and digital technology in cardiac care. Collaboration prioritizes AI-powered services, such as image interpretation, risk prediction, and decision support.

Egil said, “We are eager to help shape the path of heart care – from early detection to treatment to follow-up at home – bringing our expertise in AI and digital technologies to top clinical leadership aid in advance risk prediction and decision making.” Samset, GE Healthcare’s chief technology scientist for cardiology solutions, in that partnership announcement.

On the record

“Sonic DL is a paradigm shift for MR enabling high-quality imaging in a single heartbeat,” Xue said in the statement. “This greatly increases patient access and improves clinical value for patients who need it most but previously could not be successfully scanned.”

Andrea Fox is a senior editor for Healthcare IT News.
Email: afox@himss.org
Healthcare IT News is a HIMSS Media publication.