Medical imaging AI platform being built by collaboration

King’s College London and Nvidia are working together on a radiology AI platform whereby the former will use Nvidia’s 2-petaflop supercomputers developed specifically for AI research, DGX-2 systems, and Nvidia’s Clara AI toolkit, together with their own in-house imaging system NiftyNet, and third-party imaging technologies from partners. The platform will hopefully facilitate the automation of parts of NHS radiology assessment.
Professor Sebastien Ourselin, head of the School of Biomedical Engineering & Imaging Sciences at King’s College London, said: “This centre marks a significant chapter in the future of AI-enabled NHS hospitals, and the infrastructure is an essential part of building new AI tools which will benefit patients and the healthcare system as a whole. The Nvidia DGX-2 AI system’s large memory and massive computing power make it possible for us to tackle training of large, 3D datasets in minutes instead of days while keeping the data secure on the premises of the hospital.”