Scaling Neuroscience Research using Federated Learning
This addresses privacy and regulatory barriers in neuroscience research by enabling collaborative model training without sharing raw data, though it is incremental as it builds on existing Federated Learning methods.
The paper tackles the problem of analyzing biomedical data under privacy constraints by using Federated Learning to train a brain age prediction model on distributed MRI scans, achieving faster convergence with a Semi-Synchronous protocol in heterogeneous environments.
The amount of biomedical data continues to grow rapidly. However, the ability to analyze these data is limited due to privacy and regulatory concerns. Machine learning approaches that require data to be copied to a single location are hampered by the challenges of data sharing. Federated Learning is a promising approach to learn a joint model over data silos. This architecture does not share any subject data across sites, only aggregated parameters, often in encrypted environments, thus satisfying privacy and regulatory requirements. Here, we describe our Federated Learning architecture and training policies. We demonstrate our approach on a brain age prediction model on structural MRI scans distributed across multiple sites with diverse amounts of data and subject (age) distributions. In these heterogeneous environments, our Semi-Synchronous protocol provides faster convergence.