Nvidia supercomputing platform to ‘revolutionize’ medical imaging

Nvidia supercomputing platform to ‘revolutionize’ medical imaging

Market news |
By Rich Pell

The medical imaging supercomputer – called “Project Clara” – is aimed at updating the capabilities of millions of medical imaging instruments installed around the world. With about three million such instruments currently installed, and with only a couple hundred thousand new ones sold each year, it would otherwise take decades to update this install base, says the company.

Medical imaging instruments have been used for early detection and improvement of patient outcomes for more than four decades, with innovation coming from improvements in detector technology and, more recently, parallel computing. In addition, deep learning technology is now dominating, with more than half of new research in medical imaging applications involving artificial intelligence (AI), enabling advanced image analysis and quantification.

For example, says the company, a recent algorithm called V-Net uses 3D volumetric segmentation and can automatically measure the volume of blood flowing through the heart. Fifteen years ago, this algorithm would have required a $10 million computer that consumed 500 kW of power; today, however, it can run on a few Tesla V100 GPUs.

By taking advantage of such advancements in computation, Project Clara is designed to renew the capabilities of today’s installed medical imaging machines in place. Being both virtual and remote, Clara can run many computational instruments simultaneously, and it leverages NVIDIA vGPUs to enable multi-user access.

It can also perform the computation for any instrument – whether computed tomography (CT), magnetic resonance (MR), ultrasound, X-ray, or mammography. In addition, Clara is scalable; it uses Kubernetes on GPUs to efficiently scale compute with demand.

As part of Project Clara, the company says it is working with dozens of healthcare companies, startups, and research hospitals to help improve their AI applications, including AutoMap and V-Net. AutoMap can shorten acquisition time of MRI and boosts image quality, while V-Net can automatically measure anatomy and assess functionality.

“New technologies are transforming healthcare,” says Dr. Greg Zaharchuk, founder of Subtle Medical, which is working on dozens of applications in medical imaging and which recently won more than a quarter of a million dollars in the healthcare category in Nvidia’s Inception program awards. “NVIDIA’s vision for a virtualized imaging supercomputer is an exciting new chapter that will revolutionize our ability to deliver AI-powered healthcare.”


Related articles:
Deep learning improves medical imaging
GE, Nvidia partner on next-gen intelligent healthcare
AI more effective than humans at analyzing heart scans
Google algorithm predicts cardiovascular risk from eye images
Algorithm beats radiologists in diagnosing x-rays

If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :    eeNews on Google News


Linked Articles