ÌÇÐÄ´«Ã½

Skip to main content
 
Notice: Users may be experiencing issues with displaying some pages on stanfordhealthcare.org. We are working closely with our technical teams to resolve the issue as quickly as possible. Thank you for your patience.
ÌÇÐÄ´«Ã½

An international study presenting a federated learning AI platform for pediatric brain tumors.

ÌÇÐÄ´«Ã½

An international study presenting a federated learning AI platform for pediatric brain tumors. Nature communications Lee, E. H., Han, M., Wright, J., Kuwabara, M., Mevorach, J., Fu, G., Choudhury, O., Ratan, U., Zhang, M., Wagner, M. W., Goetti, R., Toescu, S., Perreault, S., Dogan, H., Altinmakas, E., Mohammadzadeh, M., Szymanski, K. A., Campen, C. J., Lai, H., Eghbal, A., Radmanesh, A., Mankad, K., Aquilina, K., Said, M., Vossough, A., Oztekin, O., Ertl-Wagner, B., Poussaint, T., Thompson, E. M., Ho, C. Y., Jaju, A., Curran, J., Ramaswamy, V., Cheshier, S. H., Grant, G. A., Wong, S. S., Moseley, M. E., Lober, R. M., Wilms, M., Forkert, N. D., Vitanza, N. A., Miller, J. H., Prolo, L. M., Yeom, K. W. 2024; 15 (1): 7615

Abstract

While multiple factors impact disease, artificial intelligence (AI) studies in medicine often use small, non-diverse patient cohorts due to data sharing and privacy issues. Federated learning (FL) has emerged as a solution, enabling training across hospitals without direct data sharing. Here, we present FL-PedBrain, an FL platform for pediatric posterior fossa brain tumors, and evaluate its performance on a diverse, realistic, multi-center cohort. Pediatric brain tumors were targeted due to the scarcity of such datasets, even in tertiary care hospitals. Our platform orchestrates federated training for joint tumor classification and segmentation across 19 international sites. FL-PedBrain exhibits less than a 1.5% decrease in classification and a 3% reduction in segmentation performance compared to centralized data training. FL boosts segmentation performance by 20 to 30% on three external, out-of-network sites. Finally, we explore the sources of data heterogeneity and examine FL robustness in real-world scenarios with data imbalances.

View details for

View details for

View details for