Federated learning enables big data for rare cancer boundary detection

Pati S, Baid U, Edwards B, Sheller M, Wang SH, Reina GA, Foley P, Gruzdev A, Karkada D, Davatzikos C, Sako C, Ghodasara S, Bilello M, Mohan S, Vollmuth P, Brugnara G, Preetha CJ, Sahm F, Maier-Hein K, Zenk M, Bendszus M, Wick W, Calabrese E, Rudie J, Villanueva-Meyer J, Cha S, Ingalhalikar M, Jadhav M, Pandey U, Saini J, Garrett J, Larson M, Jeraj R, Currie S, Frood R, Fatania K, Huang RY, Chang K, Quintero CB, Capellades J, Puig J, Trenkler J, Pichler J, Necker G, Haunschmidt A, Meckel S, Shukla G, Liem S, Alexander GS, Lombardo J, Palmer JD, Flanders AE, Dicker AP, Sair HI, Jones CK, Venkataraman A, Jiang M, So TY, Chen C, Heng PA, Dou Q, Kozubek M, Lux F, Michálek J, Matula P, Keřkovský M, Kopřivová T, Dostál M, Vybíhal V, Vogelbaum MA, Mitchell JR, Farinhas J, Maldjian JA, Yogananda CGB, Pinho MC, Reddy D, Holcomb J, Wagner BC, Ellingson BM, Cloughesy TF, Raymond C, Oughourlian T, Hagiwara A, Wang C, To MS, Bhardwaj S, Chong C, Agzarian M, Falcão AX, Martins SB, Teixeira BC, Sprenger F, Menotti D, Lucio DR, LaMontagne P, Marcus D, Wiestler B, Kofler F, Ezhov I, Metz M, Jain R, Lee M, Lui YW, McKinley R, Slotboom J, Radojewski P, Meier R, Wiest R, Murcia D, Fu E, Haas R, Thompson J, Ormond DR, Badve C, Sloan AE, Vadmal V, Waite K, Colen RR, Pei L, Ak M, Srinivasan A, Bapuraj JR, Rao A, Wang N, Yoshiaki O, Moritani T, Turk S, Lee J, Prabhudesai S, Morón F, Mandel J, Kamnitsas K, Glocker B, Dixon LV, Williams M, Zampakis P, Panagiotopoulos V, Tsiganos P, Alexiou S, Haliassos I, Zacharaki EI, Moustakas K, Kalogeropoulou C, Kardamakis DM, Choi YS, Lee SK, Chang JH, Ahn SS, Luo B, Poisson L, Wen N, Tiwari P, Verma R, Bareja R, Yadav I, Chen J, Kumar N, Smits M, van der Voort SR, Alafandi A, Incekara F, Wijnenga MM, Kapsas G, Gahrmann R, Schouten JW, Dubbink HJ, Vincent AJ, van den Bent MJ, French PJ, Klein S, Yuan Y, Sharma S, Tseng TC, Adabi S, Niclou SP, Keunen O, Hau AC, Vallières M, Fortin D, Lepage M, Landman B, Ramadass K, Xu K, Chotai S, Chambless LB, Mistry A, Thompson RC, Gusev Y, Bhuvaneshwar K, Sayah A, Bencheqroun C, Belouali A, Madhavan S, Booth TC, Chelliah A, Modat M, Shuaib H, Dragos C, Abayazeed A, Kolodziej K, Hill M, Abbassy A, Gamal S, Mekhaimar M, Qayati M, Reyes M, Park JE, Yun J, Kim HS, Mahajan A, Muzi M, Benson S, Beets-Tan RG, Teuwen J, Herrera-Trujillo A, Trujillo M, Escobar W, Abello A, Bernal J, Gómez J, Choi J, Baek S, Kim Y, Ismael H, Allen B, Buatti JM, Kotrotsou A, Li H, Weiss T, Weller M, Bink A, Pouymayou B, Shaykh HF, Saltz J, Prasanna P, Shrestha S, Mani KM, Payne D, Kurc T, Pelaez E, Franco-Maldonado H, Loayza F, Quevedo S, Guevara P, Torche E, Mendoza C, Vera F, Ríos E, López E, Velastin SA, Ogbole G, Soneye M, Oyekunle D, Odafe-Oyibotha O, Osobu B, Shu’aibu M, Dorcas A, Dako F, Simpson AL, Hamghalam M, Peoples JJ, Hu R, Tran A, Cutler D, Moraes FY, Boss MA, Gimpel J, Veettil DK, Schmidt K, Bialecki B, Marella S, Price C, Cimino L, Apgar C, Shah P, Menze B, Barnholtz-Sloan JS, Martin J, Bakas S (2022)

Publication Type: Journal article

Publication year: 2022

Journal

Book Volume: 13

Article Number: 7346

Journal Issue: 1

DOI: 10.1038/s41467-022-33407-5

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, and 23% for the complete tumor extent, over a publicly trained model. We anticipate our study to: 1) enable more healthcare studies informed by large diverse data, ensuring meaningful results for rare diseases and underrepresented populations, 2) facilitate further analyses for glioblastoma by releasing our consensus model, and 3) demonstrate the FL effectiveness at such scale and task-complexity as a paradigm shift for multi-site collaborations, alleviating the need for data-sharing.

Involved external institutions

Penn Medicine United States (USA) (US) Vanderbilt University United States (USA) (US) Queen's University Canada (CA) Georgetown University United States (USA) (US) King’s College London United Kingdom (GB) American College of Radiology United States (USA) (US) Stoke Mandeville Hospital United Kingdom (GB) NEOSOMA - EMS-Training Germany (DE) Intel Corporation United States (USA) (US) Cairo University / جامعة القاهرة Egypt (EG) Technische Universität München (TUM) Germany (DE) National Cancer Institute (NCI) United States (USA) (US) University of Pennsylvania (UPenn) United States (USA) (US) Universität Bern Switzerland (CH) Asan Medical Center / 서울아산병원 Korea, Republic of (KR) Clatterbridge Cancer Centre United Kingdom (GB) University of Washington United States (USA) (US) Netherlands Cancer Institute - Antoni van Leeuwenhoek Hospital (NKI / NKI-AVL) Netherlands (NL) Clínica Imbanaco Quirónsalud Colombia (CO) Universitätsspital Zürich (USZ) Switzerland (CH) Erasmus University Medical Center (MC) Netherlands (NL) University of Alabama at Birmingham (UAB) United States (USA) (US) University of Michigan United States (USA) (US) Baylor College of Medicine United States (USA) (US) University of Patras (UPATRAS) Greece (GR) Imperial College London / The Imperial College of Science, Technology and Medicine United Kingdom (GB) University of California Los Angeles (UCLA) United States (USA) (US) Flinders Medical Centre Australia (AU) Imperial College Healthcare NHS Trust United Kingdom (GB) Yonsei University Health System (YUHS) Korea, Republic of (KR) University of Valle / Universidad del Valle (Univalle) Colombia (CO) Henry Ford Health System (HFHS) United States (USA) (US) University of Iowa United States (USA) (US) University Hospital Brno Czech Republic (CZ) University College Hospital Nigeria (NG) Luxembourg Institute of Health (CRP-Santé) Luxembourg (LU) University of Lagos Nigeria (NG) Université de Sherbrooke Canada (CA) Obafemi Awolowo University Nigeria (NG) Escuela Superior Politécnica del Litoral (ESPOL) Ecuador (EC) Universidad Católica de Cuenca Poland (PL) Universidad de Concepcion Chile (CL) Icahn School of Medicine at Mount Sinai United States (USA) (US) State University of New York at Albany (UNY Albany / UAlbany) United States (USA) (US) Case Western Reserve University United States (USA) (US) Sociedad de Lucha Contra el Cáncer del Ecuador (SOLCE) Ecuador (EC) University of Colorado Anschutz Medical Campus United States (USA) (US) University of Alberta Canada (CA) H. Lee Moffitt Cancer Center & Research Institute United States (USA) (US) University Hospitals of Cleveland / Case Western Reserve University Hospital United States (USA) (US) University of Texas Southwestern Medical Center (UT Southwestern) United States (USA) (US) University of Pittsburgh United States (USA) (US) Alberta Machine Intelligence Institute (Amii) Canada (CA) Universidade Federal do Paraná (UFPR) Brazil (BR) New York University (NYU) United States (USA) (US) University of Texas MD Anderson Cancer Center United States (USA) (US) Inselspital, Universitätsspital Bern Switzerland (CH) University of Zurich / Universität Zürich (UZH) Switzerland (CH) University of Pittsburgh Medical Center (UPMC) United States (USA) (US) Queen Mary University of London United Kingdom (GB) Masaryk University Czech Republic (CZ) Hospital INC – Neurological Institute of Curitiba / Hospital INC – Instituto de Neurologia de Curitiba Brazil (BR) Washington University in St. Louis United States (USA) (US) MedStar Georgetown University Hospital United States (USA) (US) Instituto Federal de Educação, Ciência e Tecnologia de Sergipe (IFS) Brazil (BR) Ohio State University United States (USA) (US) Thomas Jefferson University Hospitals United States (USA) (US) Johns Hopkins Hospital United States (USA) (US) Johns Hopkins University (JHU) United States (USA) (US) The Chinese University of Hong Kong (CUHK) China (CN) Universitätsklinikum Heidelberg Germany (DE) Deutsches Krebsforschungszentrum (DKFZ) Germany (DE) University of California San Francisco (UCSF) United States (USA) (US) Symbiosis International University (SIU) India (IN) National Institute of Mental Health and Neuroscience (NIMHANS) India (IN) Universidade Estadual de Campinas (UNICAMP) / University of Campinas Brazil (BR) University of Wisconsin - Madison United States (USA) (US) Leeds Teaching Hospitals NHS Trust United Kingdom (GB) Harvard University United States (USA) (US) Massachusetts General Hospital United States (USA) (US) Catalan Institute of Oncology / Institut Català d'Oncologia (ICO) Spain (ES) Consorci Mar Parc de Salut de Barcelona Spain (ES) Hospital Universitari Dr. Josep Trueta Spain (ES) Kepler Universitätsklinikum (KUK) Austria (AT) University of Maryland School of Pharmacy United States (USA) (US)

How to cite

APA:

Pati, S., Baid, U., Edwards, B., Sheller, M., Wang, S.H., Reina, G.A.,... Bakas, S. (2022). Federated learning enables big data for rare cancer boundary detection. Nature Communications, 13(1). https://doi.org/10.1038/s41467-022-33407-5

MLA:

Pati, Sarthak, et al. "Federated learning enables big data for rare cancer boundary detection." Nature Communications 13.1 (2022).

BibTeX: Download