Nvidia has partnered with the American College of Radiology (ACR) to offer an open artificial intelligence (AI) platform for the development of diagnostic algorithms.
Called Clara AI, the computational platform will be integrated with ACR Data Science Institute’s ACR AI-LAB. It will help radiologists devise and deploy medical imaging workflows and instruments, as well as create AI algorithms using their own data and facilities.
The programme was piloted for three months at Massachusetts General Hospital, Ohio State University (OSU), and the Center for Clinical Data Science (CCDS) at Brigham and Women’s Hospital.
Nvidia healthcare vice-president Kimberly Powell said: “Nvidia builds platforms that democratise the use of AI and we purpose-built the Clara AI toolkit to give every radiologist the opportunity to develop AI tools that are customised to their patients and their clinical practice.
“Our successful pilot with the ACR is the first of many that will make AI more accessible to the entire field of radiology.”
During the pilot study, OSU used the Clara AI toolkit to access a pre-trained model created by CCDS. The model labelled the university's data for further testing and improving the algorithm.
This research led to the development of a cardiac computed tomography (CT) angiography model. The shared approach was said to have minimised algorithm training, validation and testing.
The software was also said to facilitate data aggregation, image annotation, image pre-processing and transformation, as well as algorithm transfer and computing.
OSU Wexner Medical Center radiology and medical imaging informatics department chair Richard White said: “Enabling a network of artificial intelligence between hospitals will create more robust algorithms, greater efficiencies and likely lead to better patient outcomes.”
Nvidia Clara platform also powers GE Healthcare’s Edison AI platform and the Nuance AI Marketplace, which support AI-LAB and help deploy AI within the radiology workflow.