Innovation

GE, NVIDIA build AI-powered CT scanner that processes images 2x faster

The two companies announced a number of new health products using artificial intelligence to gain faster, more accurate diagnoses and improve data collection and analysis.

GE Healthcare and NVIDIA are partnering to deliver a host of new health products that use artificial intelligence (AI) to improve patient care and data collection, the companies announced at RSNA on Monday.

NVIDIA's AI technologies will be integrated into GE Healthcare's 500,000 imaging devices globally. The new Revolution Frontier CT system taps NVIDIA's AI computing platform to process images twice as fast as its predecessor. The machine is FDA approved, and is expected to deliver better clinical outcomes in liver lesion detection and kidney lesion identification due to its speed, according to a press release. This could also reduce the need for unnecessary follow-up appointments.

The Vivid E95 4D Ultrasound System, also announced at RSNA, uses NVIDIA GPUs to provide fast, accurate visualization and quantification while streaming workflows across an imaging platform. The NVIDIA GPUs accelerate reconstruction and visualization of blood flow, and improve both 2D and 4D imaging.

SEE: IT leader's guide to the future of artificial intelligence (Tech Pro Research)

The companies also announced a new GE Healthcare Applied Intelligence platform, which will use NVIDIA GPUs, the NVIDIA CUDA parallel computing platform, and the NVIDIA GPU Cloud container registry to speed the creation, deployment, and consumption of deep learning algorithms in healthcare analytic applications. The platform can then be integrated into clinical and operational workflows and equipment, the release noted.

The average hospital generates 50 petabytes of data annually, through medical images, clinical charts and sensors, and operational and financial sources. However, less than 3% of this data is actionable, tagged, or analyzed, according to the release. Partnerships like this one can help hospitals make better use of their information with powerful applications and the fast processing speeds of GPUs.

"Healthcare is changing at remarkable speed, and the technologies that will transform the industry should reflect that pace," said Kieran Murphy, President and CEO of GE Healthcare. "By partnering with NVIDIA, GE Healthcare will be able to deliver devices of the future - intelligent machines capable of empowering providers to improve the speed and accuracy of diagnoses for patients around the world."

NVIDIA has created AI solutions for a number of fields, perhaps most notably those for autonomous vehicles. In healthcare, deep learning solutions can be used to design more sophisticated neural networks for medical applications, according to the release, including real-time medical condition assessments, point-of-care interventions, and predictive analytics for clinical decision-making. The new tools released with GE Healthcare will also aim to drive lower radiation doses for patients, as well as faster exam times and higher-quality medical imaging.

The health tech space is growing rapidly, with several companies and medical institutions making strides in improving patient care thanks to technology. On Monday, also at RSNA, Stratasys unveiled BioMimics—fully functional, 3D printed models of the human heart and bones to improve medical device testing and education. And medical institutions such as the Sutter Health Network are using Google Glass and other technologies to increase efficiency and improve patient care.

The 3 big takeaways for TechRepublic readers

1. GE Healthcare and NVIDIA are partnering to deliver a number of new health products that use artificial intelligence to improve patient care and data collection.

2. The new Revolution Frontier CT system uses NVIDIA's AI computing platform to process images twice as fast as its predecessor.

3. The companies also announced a new ultrasound machine and AI platform for healthcare providers.

istock-697650898.jpg
Image: iStockphoto/everythingpossible

Also see

About Alison DeNisco Rayome

Alison DeNisco Rayome is a Staff Writer for TechRepublic. She covers CXO, cybersecurity, and the convergence of tech and the workplace.

Editor's Picks

Free Newsletters, In your Inbox