NVIDIA Launches Medical AI Computing Platform

PinIt

The solution is an AI computing platform for medical devices that combines hardware systems and optimized libraries for data processing and AI.

NVIDIA recently extended its support for AI applied to medical problems by enhancing NVIDIA Clara, its healthcare application framework for AI-powered imaging, genomics, and the development and deployment of smart sensors.

Download Now: Building Real-time Location Applications on Massive Datasets

It now offers the NVIDIA Clara Holoscan MGX platform, which expands NVIDIA’s current medical device ecosystem to provide medical-grade reference architecture and long-term support. The extension is expected to help drive medical innovation in the coming years. The solution is an AI computing platform for medical devices that combines hardware systems for low-latency sensor and network connectivity, optimized libraries for data processing and AI, and core microservices to run streaming, imaging, and other applications, from embedded to edge to cloud.

See also: FDA Clears Aneurysm Detecting Artificial Intelligence Tool

Designed for medical regulatory compliance

Delivering real-time AI comes with increased scrutiny over faster, wider data sharing. NVIDIA’s platform brings together pre-trained models and a scalable microservices framework within the same platform, which would allow researchers and health providers to productize AI-driven healthcare solutions.

It enables faster processing with embedded security features designed specifically for sensitive healthcare datasets. These controllers monitor operations and provide remote software updates or system recovery.

The expanded platform will enable innovation in healthcare through accelerated computing, but also with advanced visualizations so critical in fields like drug discovery and surgery. It makes it easier for companies to productize AI-enabled solutions, particularly in a medical device setting where scale is not just critical to business but to patient outcomes.

Users also receive 10-year long-term software support, along with hardware reference design. And thanks to improved sensors, users can leverage real-time insight to provide assistance even in high-touch applications such as robotic surgery.

The first users to build on the new platform include Advantech, RYOYO Electro, and Onyx Healthcare, among several others. It includes NVIDIA Jetson AGX Orin Industrial module, NVIDIA RTX A6000 GPU, and NVIDIA ConnectX-7 SmartNIC network adapter. There is also a high GPU processing path to support high throughput instruments. Researchers and developers have the option to embed Clara Holoscan MGX directly into the device or connect to an existing install of medical devices for greater flexibility in deployment paths.

Download Now: Building Real-time Location Applications on Massive Datasets
Elizabeth Wallace

About Elizabeth Wallace

Elizabeth Wallace is a Nashville-based freelance writer with a soft spot for data science and AI and a background in linguistics. She spent 13 years teaching language in higher ed and now helps startups and other organizations explain - clearly - what it is they do.

Leave a Reply

Your email address will not be published.