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.
| Original language | English (US) |
|---|---|
| Article number | 7346 |
| Journal | Nature communications |
| Volume | 13 |
| Issue number | 1 |
| DOIs | |
| State | Published - Dec 2022 |
ASJC Scopus subject areas
- General Chemistry
- General Biochemistry, Genetics and Molecular Biology
- General Physics and Astronomy
Fingerprint
Dive into the research topics of 'Federated learning enables big data for rare cancer boundary detection'. Together they form a unique fingerprint.Cite this
- APA
- Standard
- Harvard
- Vancouver
- Author
- BIBTEX
- RIS
In: Nature communications, Vol. 13, No. 1, 7346, 12.2022.
Research output: Contribution to journal › Article › peer-review
}
TY - JOUR
T1 - Federated learning enables big data for rare cancer boundary detection
AU - Pati, Sarthak
AU - Baid, Ujjwal
AU - Edwards, Brandon
AU - Sheller, Micah
AU - Wang, Shih Han
AU - Reina, G. Anthony
AU - Foley, Patrick
AU - Gruzdev, Alexey
AU - Karkada, Deepthi
AU - Davatzikos, Christos
AU - Sako, Chiharu
AU - Ghodasara, Satyam
AU - Bilello, Michel
AU - Mohan, Suyash
AU - Vollmuth, Philipp
AU - Brugnara, Gianluca
AU - Preetha, Chandrakanth J.
AU - Sahm, Felix
AU - Maier-Hein, Klaus
AU - Zenk, Maximilian
AU - Bendszus, Martin
AU - Wick, Wolfgang
AU - Calabrese, Evan
AU - Rudie, Jeffrey
AU - Villanueva-Meyer, Javier
AU - Cha, Soonmee
AU - Ingalhalikar, Madhura
AU - Jadhav, Manali
AU - Pandey, Umang
AU - Saini, Jitender
AU - Garrett, John
AU - Larson, Matthew
AU - Jeraj, Robert
AU - Currie, Stuart
AU - Frood, Russell
AU - Fatania, Kavi
AU - Huang, Raymond Y.
AU - Chang, Ken
AU - Quintero, Carmen Balaña
AU - Capellades, Jaume
AU - Puig, Josep
AU - Trenkler, Johannes
AU - Pichler, Josef
AU - Necker, Georg
AU - Haunschmidt, Andreas
AU - Meckel, Stephan
AU - Shukla, Gaurav
AU - Liem, Spencer
AU - Alexander, Gregory S.
AU - Lombardo, Joseph
AU - Palmer, Joshua D.
AU - Flanders, Adam E.
AU - Dicker, Adam P.
AU - Sair, Haris I.
AU - Jones, Craig K.
AU - Venkataraman, Archana
AU - Jiang, Meirui
AU - So, Tiffany Y.
AU - Chen, Cheng
AU - Heng, Pheng Ann
AU - Dou, Qi
AU - Kozubek, Michal
AU - Lux, Filip
AU - Michálek, Jan
AU - Matula, Petr
AU - Keřkovský, Miloš
AU - Kopřivová, Tereza
AU - Dostál, Marek
AU - Vybíhal, Václav
AU - Vogelbaum, Michael A.
AU - Mitchell, J. Ross
AU - Farinhas, Joaquim
AU - Maldjian, Joseph A.
AU - Yogananda, Chandan Ganesh Bangalore
AU - Pinho, Marco C.
AU - Reddy, Divya
AU - Holcomb, James
AU - Wagner, Benjamin C.
AU - Ellingson, Benjamin M.
AU - Cloughesy, Timothy F.
AU - Raymond, Catalina
AU - Oughourlian, Talia
AU - Hagiwara, Akifumi
AU - Wang, Chencai
AU - To, Minh Son
AU - Bhardwaj, Sargam
AU - Chong, Chee
AU - Agzarian, Marc
AU - Falcão, Alexandre Xavier
AU - Martins, Samuel B.
AU - Teixeira, Bernardo C.A.
AU - Sprenger, Flávia
AU - Menotti, David
AU - Lucio, Diego R.
AU - LaMontagne, Pamela
AU - Marcus, Daniel
AU - Wiestler, Benedikt
AU - Kofler, Florian
AU - Ezhov, Ivan
AU - Metz, Marie
AU - Jain, Rajan
AU - Lee, Matthew
AU - Lui, Yvonne W.
AU - McKinley, Richard
AU - Slotboom, Johannes
AU - Radojewski, Piotr
AU - Meier, Raphael
AU - Wiest, Roland
AU - Murcia, Derrick
AU - Fu, Eric
AU - Haas, Rourke
AU - Thompson, John
AU - Ormond, David Ryan
AU - Badve, Chaitra
AU - Sloan, Andrew E.
AU - Vadmal, Vachan
AU - Waite, Kristin
AU - Colen, Rivka R.
AU - Pei, Linmin
AU - Ak, Murat
AU - Srinivasan, Ashok
AU - Bapuraj, J. Rajiv
AU - Rao, Arvind
AU - Wang, Nicholas
AU - Yoshiaki, Ota
AU - Moritani, Toshio
AU - Turk, Sevcan
AU - Lee, Joonsang
AU - Prabhudesai, Snehal
AU - Morón, Fanny
AU - Mandel, Jacob
AU - Kamnitsas, Konstantinos
AU - Glocker, Ben
AU - Dixon, Luke V.M.
AU - Williams, Matthew
AU - Zampakis, Peter
AU - Panagiotopoulos, Vasileios
AU - Tsiganos, Panagiotis
AU - Alexiou, Sotiris
AU - Haliassos, Ilias
AU - Zacharaki, Evangelia I.
AU - Moustakas, Konstantinos
AU - Kalogeropoulou, Christina
AU - Kardamakis, Dimitrios M.
AU - Choi, Yoon Seong
AU - Lee, Seung Koo
AU - Chang, Jong Hee
AU - Ahn, Sung Soo
AU - Luo, Bing
AU - Poisson, Laila
AU - Wen, Ning
AU - Tiwari, Pallavi
AU - Verma, Ruchika
AU - Bareja, Rohan
AU - Yadav, Ipsa
AU - Chen, Jonathan
AU - Kumar, Neeraj
AU - Smits, Marion
AU - van der Voort, Sebastian R.
AU - Alafandi, Ahmed
AU - Incekara, Fatih
AU - Wijnenga, Maarten M.J.
AU - Kapsas, Georgios
AU - Gahrmann, Renske
AU - Schouten, Joost W.
AU - Dubbink, Hendrikus J.
AU - Vincent, Arnaud J.P.E.
AU - van den Bent, Martin J.
AU - French, Pim J.
AU - Klein, Stefan
AU - Yuan, Yading
AU - Sharma, Sonam
AU - Tseng, Tzu Chi
AU - Adabi, Saba
AU - Niclou, Simone P.
AU - Keunen, Olivier
AU - Hau, Ann Christin
AU - Vallières, Martin
AU - Fortin, David
AU - Lepage, Martin
AU - Landman, Bennett
AU - Ramadass, Karthik
AU - Xu, Kaiwen
AU - Chotai, Silky
AU - Chambless, Lola B.
AU - Mistry, Akshitkumar
AU - Thompson, Reid C.
AU - Gusev, Yuriy
AU - Bhuvaneshwar, Krithika
AU - Sayah, Anousheh
AU - Bencheqroun, Camelia
AU - Belouali, Anas
AU - Madhavan, Subha
AU - Booth, Thomas C.
AU - Chelliah, Alysha
AU - Modat, Marc
AU - Shuaib, Haris
AU - Dragos, Carmen
AU - Abayazeed, Aly
AU - Kolodziej, Kenneth
AU - Hill, Michael
AU - Abbassy, Ahmed
AU - Gamal, Shady
AU - Mekhaimar, Mahmoud
AU - Qayati, Mohamed
AU - Reyes, Mauricio
AU - Park, Ji Eun
AU - Yun, Jihye
AU - Kim, Ho Sung
AU - Mahajan, Abhishek
AU - Muzi, Mark
AU - Benson, Sean
AU - Beets-Tan, Regina G.H.
AU - Teuwen, Jonas
AU - Herrera-Trujillo, Alejandro
AU - Trujillo, Maria
AU - Escobar, William
AU - Abello, Ana
AU - Bernal, Jose
AU - Gómez, Jhon
AU - Choi, Joseph
AU - Baek, Stephen
AU - Kim, Yusung
AU - Ismael, Heba
AU - Allen, Bryan
AU - Buatti, John M.
AU - Kotrotsou, Aikaterini
AU - Li, Hongwei
AU - Weiss, Tobias
AU - Weller, Michael
AU - Bink, Andrea
AU - Pouymayou, Bertrand
AU - Shaykh, Hassan F.
AU - Saltz, Joel
AU - Prasanna, Prateek
AU - Shrestha, Sampurna
AU - Mani, Kartik M.
AU - Payne, David
AU - Kurc, Tahsin
AU - Pelaez, Enrique
AU - Franco-Maldonado, Heydy
AU - Loayza, Francis
AU - Quevedo, Sebastian
AU - Guevara, Pamela
AU - Torche, Esteban
AU - Mendoza, Cristobal
AU - Vera, Franco
AU - Ríos, Elvis
AU - López, Eduardo
AU - Velastin, Sergio A.
AU - Ogbole, Godwin
AU - Soneye, Mayowa
AU - Oyekunle, Dotun
AU - Odafe-Oyibotha, Olubunmi
AU - Osobu, Babatunde
AU - Shu’aibu, Mustapha
AU - Dorcas, Adeleye
AU - Dako, Farouk
AU - Simpson, Amber L.
AU - Hamghalam, Mohammad
AU - Peoples, Jacob J.
AU - Hu, Ricky
AU - Tran, Anh
AU - Cutler, Danielle
AU - Moraes, Fabio Y.
AU - Boss, Michael A.
AU - Gimpel, James
AU - Veettil, Deepak Kattil
AU - Schmidt, Kendall
AU - Bialecki, Brian
AU - Marella, Sailaja
AU - Price, Cynthia
AU - Cimino, Lisa
AU - Apgar, Charles
AU - Shah, Prashant
AU - Menze, Bjoern
AU - Barnholtz-Sloan, Jill S.
AU - Martin, Jason
AU - Bakas, Spyridon
N1 - Publisher Copyright: © 2022, The Author(s).
PY - 2022/12
Y1 - 2022/12
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85143349702&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85143349702&partnerID=8YFLogxK
U2 - 10.1038/s41467-022-33407-5
DO - 10.1038/s41467-022-33407-5
M3 - Article
C2 - 36470898
AN - SCOPUS:85143349702
SN - 2041-1723
VL - 13
JO - Nature communications
JF - Nature communications
IS - 1
M1 - 7346
ER -