Intel and UPenn researchers developing AI model to detect brain tumors

Intel Labs and the Perelman School of Medicine at the University of Pennsylvania are developing AI models that identify brain tumors. The technology is developed using a privacy-preserving technique called federated learning

This technique is a distributed machine learning approach that allows organizations to collaborate on deep learning projects without sharing patient data

According to the American Brain Tumor Association (ABTA), nearly 80,000 people are diagnosed with a brain tumor each year, with more than 4,600 of them being children.

The researchers are based in institutions in the U.S., Canada, UK, Germany, the Netherlands, Switzerland and India. Researchers claim that a federated-learning approach to medical-imaging AI could train a model to more than 99% of the accuracy of a model trained in the traditional, non-private method.

It is said that researchers need access to large amounts of relevant medical data to train and build a model to detect a brain tumor that could aid in early detection and better outcomes.

The new initiative builds on this research, using Intel software and hardware to implement federated learning.

The initiative will be funded by a three-year $1.2 million grant awarded to UPenn’s Dr. Spyridon Bakas by the Informatics Technology for Cancer Research (ITCR) program within the National Institutes of Health (NIH).