Nuance Communications, NVIDIA bring medical imaging AI models directly into clinical settings - The EE

Nuance Communications, NVIDIA bring medical imaging AI models directly into clinical settings

Nuance Communications, Inc., and NVIDIA has announced a partnership that puts AI-based diagnostic tools directly into the hands of radiologists and other clinicians at scale, enabling the delivery of improved patient care at lower costs.

The partnership brings together the nationwide scale of the Nuance Precision Imaging Network an AI-powered cloud platform that delivers patient insights from diagnostic imaging into clinical and administrative workflows and MONAI, an open-source and domain-specialised medical-imaging AI framework co-founded and accelerated by NVIDIA. Together, they enable the safe and effective validation, deployment and evaluation of medical imaging AI models.

Mass General Brigham is medical centres to use MONAI and the Nuance Precision Imaging Network to define a unique workflow that links medical-imaging model development, application packaging, deployment and clinical feedback for model refinement. It has more than 80,000 employees providing care to 1.5 million patients annually, with $2.3 billion (€2.22 billion) in annual research spending.

Using the combined offering, the medical centre has deployed a breast density AI model that has reduced the waiting period for results from several days to just 15 minutes. Women can now talk to a clinician about the results of their scan and discuss next steps before they leave the facility, rather than going through the stress and anxiety of waiting for results.

“With the combination of NVIDIA’s and Nuance’s technologies, our AI researchers can focus on training and developing their models rather than doing all the plumbing underneath,” says Dr. Keith J. Dreyer, chief data science officer, Mass General Brigham. “That makes it simpler to get AI-powered insights to our clinicians, so they can provide the best possible care, accelerate time to treatment and improve patient outcomes.”

The continuous clinic-to-research feedback loop reduces model adaptation times from years to weeks. Domain shifts in data now take weeks instead of months, and issue detection and repair takes minutes rather than hours. It has also allowed Mass General Brigham to reduce medical-imaging AI application development and maintenance costs.

“Adoption of radiology AI at scale has traditionally been constrained by the complexity of clinical workflows and the lack of standards, applications and deployment platforms,” says David Niewolny, director, healthcare business development, NVIDIA. “This partnership clears those barriers, enabling the extraordinary capabilities of AI to be delivered right at the point of care, faster than ever before.”

“The strategic partnership between Nuance and NVIDIA makes the process of deploying trained diagnostic imaging AI models into existing clinical applications at scale simpler for everyone. With this joint effort, we are effectively tackling the problem of how you get medical insights from the ‘bench’ to the bedside,” says Peter Durlach, executive vice president and chief strategy officer, Nuance Communications. “Imaging AI developers will now be able to deploy their solutions much faster, helping transform imaging workflows to improve patient outcomes and health system financial performance.”

Powered by Microsoft Azure, the Nuance Precision Imaging Network provides access to an entire ecosystem of AI-powered tools and insights within clinical workflows to more than 12,000 healthcare facilities and the 80% of U.S. radiologists who use Nuance’s PowerScribe radiology reporting and PowerShare image sharing solutions.

MONAI was built by the medical imaging community to transform research and AI applications into clinical impact. It includes MONAI Deploy, the accelerated processing pipeline that delivers MONAI Application Packages (MAPs), which easily integrate into healthcare systems, using interoperability standards such as DICOM, across data centre and cloud environments.

To learn more, read Nuance’s whitepaper here.

Follow us and Comment on Twitter @TheEE_io

By continuing to use the site, you agree to the use of cookies. more information

The cookie settings on this website are set to "allow cookies" to give you the best browsing experience possible. If you continue to use this website without changing your cookie settings or you click "Accept" below then you are consenting to this.

Close