Health News

GE Healthcare's DL model for cardiac MRI gains FDA clearance

GE Healthcare announced that the U.S. Food and Drug Administration has cleared Sonic DL, which leverages a neural network to accelerate image acquisition in magnetic resonance imaging, for healthcare use. 


The need for patients to stay still and hold their breath during the imaging exam is a significant downside for cardiac MRI.

A new deep learning technology from GE called Sonic DL can allow for high-quality cardiac images “in a single heartbeat,” according to a GE Healthcare announcement this past week announcing that the tool received FDA 510(k) clearance.

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

He added that the approach “ensures a smoother and more comfortable experience for patients during MRI exams.”

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

A video the company released coinciding with the announcement shows comparable imaging of whole heart coverage 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 at 51 seconds versus two minutes and 10 seconds with breath-holding and conventional MRI. 

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

The company says its goal is to expand Sonic DL and AIR Recon DL technology across all anatomies.


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

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

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

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

“The goal is to have AI tools ready when and where they’re needed to contribute to faster diagnoses and, ideally, better patient outcomes.”

Neural networks rely on a massive number of parameters. General development for AI in Healthcare has focused a lot of energy on furthering diagnostic technologies for the detection of heart disease.

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

“We are eager to help shape the heart care pathway – from early detection to treatment to follow-up at home – by combining our expertise in AI and digital technologies with top clinical leadership to advance risk prediction and decision-making support,” said Eigil Samset, GE Healthcare chief technology scientist for cardiology solutions in that partnership announcement. 


“Sonic DL is a paradigm shift for MR enabling high-quality imaging in a single heartbeat,” said Xue in the statement. “It greatly expands patient access and improves diagnostic value for patients who need it the most but previously couldn’t be scanned successfully.”

Andrea Fox is senior editor of Healthcare IT News.
Email: [email protected]

Healthcare IT News is a HIMSS Media publication.

Source: Read Full Article