Nature Communications (Sep 2024)
An international study presenting a federated learning AI platform for pediatric brain tumors
- Edward H. Lee,
- Michelle Han,
- Jason Wright,
- Michael Kuwabara,
- Jacob Mevorach,
- Gang Fu,
- Olivia Choudhury,
- Ujjwal Ratan,
- Michael Zhang,
- Matthias W. Wagner,
- Robert Goetti,
- Sebastian Toescu,
- Sebastien Perreault,
- Hakan Dogan,
- Emre Altinmakas,
- Maryam Mohammadzadeh,
- Kathryn A. Szymanski,
- Cynthia J. Campen,
- Hollie Lai,
- Azam Eghbal,
- Alireza Radmanesh,
- Kshitij Mankad,
- Kristian Aquilina,
- Mourad Said,
- Arastoo Vossough,
- Ozgur Oztekin,
- Birgit Ertl-Wagner,
- Tina Poussaint,
- Eric M. Thompson,
- Chang Y. Ho,
- Alok Jaju,
- John Curran,
- Vijay Ramaswamy,
- Samuel H. Cheshier,
- Gerald A. Grant,
- S. Simon Wong,
- Michael E. Moseley,
- Robert M. Lober,
- Mattias Wilms,
- Nils D. Forkert,
- Nicholas A. Vitanza,
- Jeffrey H. Miller,
- Laura M. Prolo,
- Kristen W. Yeom
Affiliations
- Edward H. Lee
- Department of Neurosurgery, Stanford University School of Medicine
- Michelle Han
- Department of Neurosurgery, Stanford University School of Medicine
- Jason Wright
- Department of Radiology, Seattle Children’s Hospital
- Michael Kuwabara
- Department of Radiology, Phoenix Children’s Hospital
- Jacob Mevorach
- Amazon Web Services
- Gang Fu
- Amazon Web Services
- Olivia Choudhury
- Amazon Web Services
- Ujjwal Ratan
- Amazon Web Services
- Michael Zhang
- Department of Neurosurgery, Stanford University School of Medicine
- Matthias W. Wagner
- Department of Diagnostic and Interventional Neuroradiology, University Hospital Augsburg
- Robert Goetti
- Department of Medical Imaging, The Children’s Hospital at Westmead
- Sebastian Toescu
- Great Ormond Street Hospital for Children
- Sebastien Perreault
- Division of Child Neurology, Department of Pediatrics, Centre Hospitalier Universitaire Sainte-Justine, Université de Montréal
- Hakan Dogan
- Department of Radiology, Koç University School of Medicine
- Emre Altinmakas
- Department of Diagnostic, Molecular and Interventional Radiology, Icahn School of Medicine at Mount Sinai
- Maryam Mohammadzadeh
- Department of Radiology, Tehran University of Medical Sciences
- Kathryn A. Szymanski
- Department of Radiology, Phoenix Children’s Hospital
- Cynthia J. Campen
- Department of Neurology, Lucile Packard Children’s Hospital, Stanford University Medical School
- Hollie Lai
- Department of Radiology, Children’s Hospital of Orange County
- Azam Eghbal
- Department of Radiology, Children’s Hospital of Orange County
- Alireza Radmanesh
- Department of Radiology, New York University Grossman School of Medicine
- Kshitij Mankad
- Great Ormond Street Hospital for Children
- Kristian Aquilina
- Great Ormond Street Hospital for Children
- Mourad Said
- Radiology Department, Centre International Carthage Médicale
- Arastoo Vossough
- Department of Neurology, Children’s Hospital of Philadelphia
- Ozgur Oztekin
- Department of Neuroradiology, Tepecik Education and Research Hospital
- Birgit Ertl-Wagner
- Department of Diagnostic and Interventional Radiology, The Hospital for Sick Children
- Tina Poussaint
- Department of Radiology, Boston Children’s Hospital
- Eric M. Thompson
- Department of Neurosurgery, Duke Children’s Hospital & Health Center
- Chang Y. Ho
- Department of Radiology & Imaging Sciences, Riley Children’s Hospital
- Alok Jaju
- Department of Radiology, Phoenix Children’s Hospital
- John Curran
- Department of Radiology, Phoenix Children’s Hospital
- Vijay Ramaswamy
- Division of Haematology/Oncology, Department of Pediatrics, The Hospital for Sick Children
- Samuel H. Cheshier
- Department of Neurosurgery, University of Utah School of Medicine
- Gerald A. Grant
- Department of Neurosurgery, Duke Children’s Hospital & Health Center
- S. Simon Wong
- Department of Electrical Engineering, Stanford University
- Michael E. Moseley
- Department of Radiology, Lucas Center, Stanford University
- Robert M. Lober
- Division of Neurosurgery, Dayton Children’s Hospital
- Mattias Wilms
- Departments of Pediatrics, Community Health Sciences, and Radiology, University of Calgary
- Nils D. Forkert
- Hotchkiss Brain Institute, University of Calgary
- Nicholas A. Vitanza
- Ben Towne Center for Childhood Cancer Research, Seattle Children’s Research Institute
- Jeffrey H. Miller
- Department of Radiology, Phoenix Children’s Hospital
- Laura M. Prolo
- Department of Neurosurgery, Stanford University School of Medicine
- Kristen W. Yeom
- Department of Neurosurgery, Stanford University School of Medicine
- DOI
- https://doi.org/10.1038/s41467-024-51172-5
- Journal volume & issue
-
Vol. 15,
no. 1
pp. 1 – 11
Abstract
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.
