Welcome to HCLS AI/ML Content Catalog

In a collaboration led by Stanford Health Department of Radiology, the AWS team worked with an international team of scientists to build FL-PedBrain, a federated learning platform developed for pediatric posterior fossa brain tumors, addressing the challenges of limited data sharing in medical AI studies.
The platform enables joint tumor classification and segmentation across 19 international sites without direct data sharing. FL-PedBrain’s performance is comparable to centralized data training, with only slight decreases in classification and segmentation accuracy. Notably, the platform demonstrates improved segmentation performance on external sites and explores the impact of data heterogeneity and imbalances in real-world scenarios.

Resources :

• Paper: An international study presenting a federated learning AI platform for pediatric brain tumors