Federated learning helps better detect brain tumor

In 2020, Intel and Penn Medicine announced an agreement to collaborate and use federated learning to improve tumor detection and improve treatment outcomes for a rare cancer: glioblastoma (GBM). This is the most common and deadly brain tumor in adults, with a median survival of just 14 months after standard treatment. Although treatment options have expanded over the past 20 years, overall survival has not improved. The research was funded by the National Institutes of Health’s National Cancer Institute Informatics Technology for Cancer Research program.

Access to medical data

To improve disease treatment, researchers need access to large amounts of medical data, in most cases datasets that exceed the threshold that an institution can produce. Research demonstrates the effectiveness of federated learning at scale and the potential benefits healthcare can realize when multi-site data silos are opened. Benefits include early diagnosis of the disease, which can improve the quality of life or extend a patient’s lifespan.

However, data accessibility has long been an issue in healthcare due to national data protection laws, such as the General Data Protection Regulation (GDPR) in the Netherlands. This has made it nearly impossible to carry out medical research and data sharing at scale without compromising patient health information. Intel’s federated learning hardware and software claims to meet data privacy requirements and protect data integrity, privacy, and security through confidential computing.

Federated learning potential

“Federated learning has tremendous potential in many fields, particularly in healthcare, as our research with Penn Medicine shows,” said Jason Martin, lead engineer, Intel Labs. “The ability to protect sensitive information and data opens the door for future studies and collaborations, especially in cases where datasets would otherwise be inaccessible. Our work with Penn Medicine has the potential to positively impact patients around the globe. world and look forward to further exploring the promise of federated learning.”

The Penn Medicine-Intel achievement was achieved by processing large amounts of data in a decentralized system. This was done using Intel Federated Learning Technology in conjunction with Intel Software Guard Extensions (SGX). This technology removes barriers to data sharing that previously hindered collaboration in similar cancer and disease research. The system solves many data privacy issues by keeping the raw data within its hospital network and only allowing model updates calculated from that data to be sent to a central server or aggregator, not the raw data.

Maintain control over your data

MC Erasmus works since 2020 at the studio. Erasmus MC radiologist Prof. Dr. Smits and biomedical researcher Dr. Van der Voort say the federated learning study has enabled UMC to help improve automated tumor detection without having to submit patient data. “Automated tumor detection is an important step in tailoring and monitoring a treatment and to develop this methodology it is essential to use data from many different institutions. With this partnership, we have been able to do this easily, while maintaining control over our data.”

Federated learning offers a breakthrough in ensuring safe multi-agency collaborations, says senior author Spyridon Bakas, PhD, assistant professor of pathology and laboratory medicine and radiology, at the University of Pennsylvania Perelman School of Medicine. “It allows access to the largest and most diverse data set ever seen in the literature. And this while all data is stored within each institution itself at all times. The more data we can feed into machine learning models, the more accurate they become. This in turn will improve our ability to understand and treat even rare diseases, such as glioblastoma.”

The results of the Penn Medicine-Intel Labs study have been published in the peer-reviewed journal, Nature Communications.