Federated learning improves brain tumour detection by 33%
Intel Labs and the Perelman School of Medicine at the University of Pennsylvania (Penn Medicine) have completed a joint research study using federated learning – a distributed machine learning (ML) artificial intelligence (AI) approach – to improve global healthcare- and helping research institutions identify malignant human brain tumors.
The medical federated learning study, published in Nature communicationimaged a global data set from 71 institutions across six continents and demonstrated the ability to improve brain tumor detection by 33%.
In 2020, Intel and Penn Medicine announced the agreement to collaborate and use federated learning to improve tumor detection and improve treatment outcomes of a rare form of cancer called glioblastoma (GBM) – the most common and deadly adult brain tumor with a average survival of just 14 months after standard treatment. While treatment options have expanded over the past 20 years, there has not been an improvement in overall survival rates.
A new AI software platform called Federated Tumor Segmentation (FeTS) has been used by radiologists to determine the border of a tumor and improve the identification of the surgical area of tumors or ‘tumor core’. Radiologists annotated their data and used Open Federated Learning (OpenFL), an open source framework for training machine learning algorithms, to perform the federated training. The platform was trained on 3.7 million images from 6314 GBM patients across six continents – the largest brain tumor dataset to date.
Jason Martin, principal engineer at Intel Labs, said: “Federated learning has tremendous potential across numerous domains, particularly within healthcare, as demonstrated by our research with Penn Medicine. Its ability to protect sensitive information and data opens the door for future studies and collaborations, especially in cases where data sets would otherwise be inaccessible.”
Data accessibility has long been an issue in healthcare due to state and national data privacy laws in the US, including the Health Insurance Portability and Accountability Act (HIPAA). This has made medical research and data sharing at scale nearly impossible to achieve without compromising patient health information. Intel’s federated learning hardware and software meets data privacy concerns and preserves data integrity, privacy and security through confidential computing.
The Penn Medicine–Intel result was achieved by processing large volumes of data in a decentralized system that only allowed models of the raw data to be sent to the central server, rather than the data itself.
“All the computing power in the world can’t do much without enough data to analyze,” says Rob Enderle, principal analyst, Enderle Group.
“This inability to analyze data that has already been captured has significantly delayed the massive medical breakthroughs that AI has promised. This federated learning study shows a viable path for AI to advance and reach its potential as the most powerful tool to fight our toughest ailments.
“In this study, federated learning shows its potential as a paradigm shift in ensuring multi-institutional collaboration by enabling access to the largest and most diverse data set of glioblastoma patients ever considered in the literature, while all data at all times maintained within each institution,” said senior author Spyridon Bakas, PhD, assistant professor of Pathology and Laboratory Medicine and Radiology, at the Perelman School of Medicine at the University of Pennsylvania.
“The more data we can feed into machine learning models, the more accurate they become, which in turn can improve our ability to understand and treat even rare diseases, such as glioblastoma.”
Through this project, Intel Labs and Penn Medicine created a proof of concept for using federated learning to derive knowledge from data. The solution could significantly impact health care and other areas of study, especially among other types of cancer research.
