Intel and Penn Medicine Conduct Cancer Study Using Federated Learning to Analyze (and Protect) Sensitive Medical Data at Scale – High Performance Computing News Analysis | inside the HPC

Calling it the largest federated learning study in the medical field to date, Intel Labs and Penn Medicine announced a joint research study to help international healthcare and research institutions identify malignant brain tumors. The study, which involved a global dataset from 71 institutions on six continents, improved brain tumor detection, the two organizations said.

Data accessibility has long been an issue in healthcare due to state and national data privacy laws, such as the Health Insurance Portability and Accountability Act (HIPAA). Large-scale medical research and data sharing has been nearly impossible to achieve without compromising patient health information. But Intel said its Federated Learning – a distributed machine learning approach – hardware and software are compliant with data privacy concerns and preserve data integrity, confidentiality and security through confidential computing. .

The Penn Medicine-Intel result was achieved by processing large volumes of data in a decentralized system using Intel’s Federated Learning technology combined with Intel Software Guard Extensions (SGX), which removes barriers to sharing data that has historically prevented collaboration on similar cancer and disease research. . Intel said the system addresses data privacy issues by keeping raw data in the data holders’ compute infrastructure and only allowing model updates computed from that data to be sent to a central server. or to an aggregator, not to the data itself.

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

According to lead author Spyridon Bakas, PhD, assistant professor of pathology and laboratory medicine and radiology at Penn Medicine (formerly called Perelman School of Medicine at the University of Pennsylvania), “In this study, federated learning shows its potential as a paradigm shift in securing multi-institutional collaborations by enabling access to the largest and most diverse dataset of glioblastoma patients ever considered in the literature, while all data is kept at each institution at all times.The more data we can feed into machine learning models, the more accurate they become, which can improve our ability to understand and treat even rare diseases, such as glioblastoma.

To advance disease treatment, researchers need access to vast 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 the healthcare industry can realize when multisite data silos are unlocked. Benefits include early detection of disease, which could improve quality of life or increase a patient’s lifespan.

“Federated learning has tremendous potential in many areas, especially in healthcare, as our research with Penn Medicine shows,” said Jason Martin, Principal Engineer, Intel Labs. “Its ability to protect sensitive information and data opens the door to 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 world, and we look forward to continuing to explore the promise of federated learning.

In 2020, Intel and Penn Medicine announced the agreement to cooperate and use federated learning to improve tumor detection and improve treatment outcomes for a rare form of cancer called glioblastoma (GBM), the tumor most common and deadliest adult stroke with a median survival of just 14 months after standard therapy. Although treatment options have expanded over the past 20 years, there has been no improvement in overall survival rates. The research was funded by the National Cancer Institute’s Computing Technology for Cancer Research Program of the National Institutes of Health.

Penn Medicine and 71 international healthcare/research institutions have used Intel Federated Learning hardware and software to improve detection of rare cancer boundaries. A new state-of-the-art AI software platform called Federated Tumor Segmentation (FeTS) has been used by radiologists to determine the boundary of a tumor and improve the identification of the “operable region” of tumors or “heart of the tumor”. The radiologists annotated their data and used Open Federated Learning (OpenFL), an open source framework for training machine learning algorithms, to run the federated training. The platform was trained on 3.7 million images of 6,314 GBM patients across six continents, the largest brain tumor dataset to date.

Through this project, Intel Labs and Penn Medicine created a proof of concept for using federated learning to gain insights from data. The solution may significantly affect health care and other fields of study, especially among other types of cancer research. Specifically, Intel developed the OpenFL open-source project to enable customers to take cross-silo federated learning into the real world and confidently deploy it on Intel SGX. Additionally, the new FeTS initiative was established as a collaborative network to provide a platform for continued development and to encourage collaboration with the FeTS platform and Intel’s OpenFL open source toolkit, both available on GitHub.

source: Intel