Project Clara aims to build radiology supercomputing platform
A new initiative aims to make the power of supercomputing available to legacy imaging scanners currently being used by healthcare organizations.
Called Project Clara, the effort, started by NVIDIA, is intended to develop a virtualized data center that would be available on a remote basis, able to handle the images from multiple modalities and by several users at the same time, using a medical imaging supercomputer.
Executives at NVIDIA, a developer of graphics processing unit technology, say the idea is to address the obsolescence of older imaging scanners that can’t be updated with newer generations of graphical processing unit (GPU) technology or supercomputer technology. Because these modalities can’t be updated, they have limited access to new developments in imaging, such as artificial intelligence and image processing technologies that are easily incorporated into new systems.
The company says it’s building on 10 years of medical imaging research and is working with development partners to “re-imagine how computing can improve medical imaging.” The partners include research hospitals (including Massachusetts General Hospital and Johns Hopkins), healthcare companies and startups in imaging technology.
In a demonstration of the Project Clara technology, NVIDIA took a ultrasound scan taken 15 years ago, which uses grayscale pixels, and compared it to a modern ultrasound scan, which renders an image of a fetus with accurate flesh tones. The initiative’s technology enables the older image to be streamed to a data center, which uses advanced IT to produce a modern volumetric of the fetus; then, applying additional AI technology to the scan, radiologists are able to infer details about structures, such as the left ventricle of the heart, which was segmented out in three-dimensional views.
The technology is intended to be virtual, remote and universal, performing computations for a variety of imaging equipment, such as CT, MR, ultrasound, X-ray or mammography.
“New technologies are transforming healthcare,” said Greg Zaharchuk, MD, founder of Subtle Medical, one of the companies partnering on the project. “NVIDIA’s vision for a virtualized imaging supercomputer is an exciting new chapter that will revolutionize our ability to deliver AI-powered healthcare,” says, Zaharchuk, who is also a radiologist and associate professor in radiology at Stanford University.