Intel Labs revealed today information about a National Institutes of Health-funded program that will use artificial intelligence to detect brain tumors without sacrificing privacy. The announcement comes during Brain Tumor Awareness Month. Intel Labs is partnering with Penn Medicine, otherwise known as the Perelman School of Medicine at the University of Pennsylvania, for this machine learning project.
Intel Labs will be working with 29 international medical centers in the USA, United Kingdom, India, Canada, Germany and Switzerland. The artificial intelligence project will make use of federated learning, which means that all patient data will remain at the data centers of the hospitals or research organization for maximum privacy. Meanwhile the algorithm operates across decentralized servers, enabling all of the institutions to work together with a larger set of data.
Jason Martin, a principal engineer at Intel, stated, “AI shows great promise for the early detection of brain tumors, but it will require more data than any single medical center holds to reach its full potential.” With more than two dozen medical centers, the amount of data used in the machine learning project will be unprecedented.
The Hospital of the University of Pennsylvania, Vanderbilt University, Queen’s University, Technical University of Munich, University of Bern, King’s College London, Washington University in St. Louis, the University of Pittsburgh Medical Center and Tata Memorial Hospital will all be participating in the first phase of the machine learning project. The project is being partially funded using a $1.2 million National Institutes of Health grant.
The American Brain Tumor Association noted that close to 80,000 individuals, including 4,600 children, are expected to be diagnosed with a brain tumor in 2020. Having a better detection model could enable much earlier detection and significantly improve outcomes.