Zenk M, Baid U, Pati S, Linardos A, Edwards B, Sheller M, Foley P, Aristizabal A, Zimmerer D, Gruzdev A, Martin J, Shinohara RT, Reinke A, Isensee F, Parampottupadam S, Parekh K, Floca R, Kassem H, Baheti B, Thakur S, Chung V, Kushibar K, Lekadir K, Jiang M, Yin Y, Yang H, Liu Q, Chen C, Dou Q, Heng PA, Zhang X, Zhang S, Khan MI, Azeem MA, Jafaritadi M, Alhoniemi E, Kontio E, Khan SA, Mächler L, Ezhov I, Kofler F, Shit S, Paetzold JC, Loehr T, Wiestler B, Peiris H, Pawar K, Zhong S, Chen Z, Hayat M, Egan G, Harandi M, Isik Polat E, Polat G, Kocyigit A, Temizel A, Tuladhar A, Tyagi L, Souza R, Forkert ND, Mouches P, Wilms M, Shambhat V, Maurya A, Danannavar SS, Kalla R, Anand VK, Krishnamurthi G, Nalawade S, Ganesh C, Wagner B, Reddy D, Das Y, Yu FF, Fei B, Madhuranthakam AJ, Maldjian J, Singh G, Ren J, Zhang W, An N, Hu Q, Zhang Y, Zhou Y, Siomos V, Tarroni G, Passerrat-Palmbach J, Rawat A, Zizzo G, Kadhe SR, Epperlein JP, Braghin S, Wang Y, Kanagavelu R, Wei Q, Yang Y, Liu Y, Kotowski K, Adamski S, Machura B, Malara W, Zarudzki L, Nalepa J, Shi Y, Gao H, Avestimehr S, Yan Y, Akbar AS, Kondrateva E, Yang H, Li Z, Wu HY, Roth J, Saueressig C, Milesi A, Nguyen QD, Gruenhagen NJ, Huang TM, Ma J, Singh HSH, Pan NY, Zhang D, Zeineldin RA, Futrega M, Yuan Y, Conte GM, Feng X, Pham QD, Xia Y, Jiang Z, Luu HM, Dobko M, Carré A, Tuchinov B, Mohy-ud-Din H, Alam S, Singh A, Shah N, Wang W, Sako C, Bilello M, Ghodasara S, Mohan S, Davatzikos C, Calabrese E, Rudie J, Villanueva-Meyer J, Cha S, Hess C, Mongan J, Ingalhalikar M, Jadhav M, Pandey U, Saini J, Huang RY, Chang K, To MS, Bhardwaj S, Chong C, Agzarian M, Kozubek M, Lux F, Michálek J, Matula P, Ker^kovský M, Kopr^ivová T, Dostál M, Vybíhal V, Pinho MC, Holcomb J, Metz M, Jain R, Lee MD, Lui YW, Tiwari P, Verma R, Bareja R, Yadav I, Chen J, Kumar N, Gusev Y, Bhuvaneshwar K, Sayah A, Bencheqroun C, Belouali A, Madhavan S, Colen RR, Kotrotsou A, Vollmuth P, Brugnara G, Preetha CJ, Sahm F, Bendszus M, Wick W, Mahajan A, Balaña C, Capellades J, Puig J, Choi YS, Lee SK, Chang JH, Ahn SS, Shaykh HF, Herrera-Trujillo A, Trujillo M, Escobar W, Abello A, Bernal J, Gómez J, LaMontagne P, Marcus DS, Milchenko M, Nazeri A, Landman B, Ramadass K, Xu K, Chotai S, Chambless LB, Mistry A, Thompson RC, Srinivasan A, Bapuraj JR, Rao A, Wang N, Yoshiaki O, Moritani T, Turk S, Lee J, Prabhudesai S, Garrett J, Larson M, Jeraj R, Li H, Weiss T, Weller M, Bink A, Pouymayou B, Sharma S, Tseng TC, Adabi S, Xavier Falcão A, Martins SB, Teixeira BC, Sprenger F, Menotti D, Lucio DR, Niclou SP, Keunen O, Hau AC, Pelaez E, Franco-Maldonado H, Loayza F, Quevedo S, McKinley R, Slotboom J, Radojewski P, Meier R, Wiest R, Trenkler J, Pichler J, Necker G, Haunschmidt A, Meckel S, Guevara P, Torche E, Mendoza C, Vera F, Ríos E, López E, Velastin SA, Choi J, Baek S, Kim Y, Ismael H, Allen B, Buatti JM, Zampakis P, Panagiotopoulos V, Tsiganos P, Alexiou S, Haliassos I, Zacharaki EI, Moustakas K, Kalogeropoulou C, Kardamakis DM, Luo B, Poisson LM, Wen N, Vallières M, Loutfi MAL, Fortin D, Lepage M, Morón F, Mandel J, Shukla G, Liem S, Alexandre GS, Lombardo J, Palmer JD, Flanders AE, Dicker AP, Ogbole G, Oyekunle D, Odafe-Oyibotha O, Osobu B, Shu’aibu Hikima M, Soneye M, Dako F, Dorcas A, Murcia D, Fu E, Haas R, Thompson JA, Ormond DR, Currie S, Fatania K, Frood R, Simpson AL, Peoples JJ, Hu R, Cutler D, Moraes FY, Tran A, Hamghalam M, Boss MA, Gimpel J, Kattil Veettil D, Schmidt K, Cimino L, Price C, Bialecki B, Marella S, Apgar C, Jakab A, Weber MA, Colak E, Kleesiek J, Freymann JB, Kirby JS, Maier-Hein L, Albrecht J, Mattson P, Karargyris A, Shah P, Menze B, Maier-Hein K, Bakas S (2025)
Publication Type: Journal article
Publication year: 2025
Book Volume: 16
Article Number: 6274
Journal Issue: 1
DOI: 10.1038/s41467-025-60466-1
Computational competitions are the standard for benchmarking medical image analysis algorithms, but they typically use small curated test datasets acquired at a few centers, leaving a gap to the reality of diverse multicentric patient data. To this end, the Federated Tumor Segmentation (FeTS) Challenge represents the paradigm for real-world algorithmic performance evaluation. The FeTS challenge is a competition to benchmark (i) federated learning aggregation algorithms and (ii) state-of-the-art segmentation algorithms, across multiple international sites. Weight aggregation and client selection techniques were compared using a multicentric brain tumor dataset in realistic federated learning simulations, yielding benefits for adaptive weight aggregation, and efficiency gains through client sampling. Quantitative performance evaluation of state-of-the-art segmentation algorithms on data distributed internationally across 32 institutions yielded good generalization on average, albeit the worst-case performance revealed data-specific modes of failure. Similar multi-site setups can help validate the real-world utility of healthcare AI algorithms in the future.
APA:
Zenk, M., Baid, U., Pati, S., Linardos, A., Edwards, B., Sheller, M.,... Bakas, S. (2025). Towards fair decentralized benchmarking of healthcare AI algorithms with the Federated Tumor Segmentation (FeTS) challenge. Nature Communications, 16(1). https://doi.org/10.1038/s41467-025-60466-1
MLA:
Zenk, Maximilian, et al. "Towards fair decentralized benchmarking of healthcare AI algorithms with the Federated Tumor Segmentation (FeTS) challenge." Nature Communications 16.1 (2025).
BibTeX: Download