Intel and Penn Medicine Collaborate on AI Technology to Detect Brain Tumors

AI Advancements in Brain Tumor Detection: A Collaborative Approach

Artificial intelligence has already outperformed doctors in identifying breast, lung, and skin cancers. Now, researchers from Intel and the University of Pennsylvania are focusing on brain tumors. By utilizing Intel’s cutting-edge AI hardware and software, Penn Medicine will lead a collaborative effort with 29 international healthcare and research institutions to develop an AI model using the largest brain tumor dataset to date — all while safeguarding sensitive patient information.

This groundbreaking project employs a technique known as federated learning, which allows algorithms to be trained across decentralized servers. This means hospitals can collaborate without directly sharing patient data. Institutions from the US, Canada, the UK, Germany, the Netherlands, Switzerland, and India will collectively create a dataset much larger than any single entity could achieve alone.

“AI shows great promise for the early detection of brain tumors, but it requires more data than any single medical center holds to realize its full potential,” said Jason Martin, Intel principal engineer, in a press release.

While the timeline for model development remains uncertain, the initiative is backed by a three-year, $1.2 million grant from the National Institutes of Health (NIH). According to the American Brain Tumor Association (ABTA), approximately 80,000 individuals will be diagnosed with a brain tumor this year, including over 4,600 children. This collaborative effort aims to enhance early detection and improve outcomes for those affected by this serious condition.