articleNature CommunicationsDec 5, 2022GOLD OA

Federated learning enables big data for rare cancer boundary detection

SPSarthak PatiUBUjjwal BaidBEBrandon EdwardsMSMicah ShellerSWShih‐Han Wang

Technical University of Munich · University of Pennsylvania · +110 more institutions

PubMed
Indexed incrossrefdatacitedoajpubmed

Abstract

Although machine learning (ML) has shown promise across disciplines, out-of-sample generalizability is concerning. This is currently addressed by sharing multi-site data, but such centralization is challenging/infeasible to scale due to various limitations. Federated ML (FL) provides an alternative paradigm for accurate and generalizable ML, by only sharing numerical model updates. Here we present the largest FL study to-date, involving data from 71 sites across 6 continents, to generate an automatic tumor boundary detector for the rare disease of glioblastoma, reporting the largest such dataset in the literature (n = 6, 314). We demonstrate a 33% delineation improvement for the surgically targetable tumor,…

Citation impact

327
total citations
FWCI
44.21
Percentile
100%
References
113
Citations per year

Authors

279

Topics & keywords

Topics
Keywords
  • Generalizability theory
  • Computer science
  • Glioblastoma
  • Machine learning
  • Data sharing
  • Scale (ratio)
  • Sample (material)
  • Task (project management)
UN Sustainable Development Goals
  • Partnerships for the goals
No related works found for this paper.

Funding