The Medical Segmentation Decathlon

Michela Antonelli (), Annika Reinke, Spyridon Bakas, Keyvan Farahani, Annette Kopp-Schneider, Bennett A. Landman, Geert Litjens, Bjoern Menze, Olaf Ronneberger, Ronald M. Summers, Bram Ginneken, Michel Bilello, Patrick Bilic, Patrick F. Christ, Richard K. G. Do, Marc J. Gollub, Stephan H. Heckers, Henkjan Huisman, William R. Jarnagin, Maureen K. McHugo, Sandy Napel, Jennifer S. Golia Pernicka, Kawal Rhode, Catalina Tobon-Gomez, Eugene Vorontsov, James A. Meakin, Sebastien Ourselin, Manuel Wiesenfarth, Pablo Arbeláez, Byeonguk Bae, Sihong Chen, Laura Daza, Jianjiang Feng, Baochun He, Fabian Isensee, Yuanfeng Ji, Fucang Jia, Ildoo Kim, Klaus Maier-Hein, Dorit Merhof, Akshay Pai, Beomhee Park, Mathias Perslev, Ramin Rezaiifar, Oliver Rippel, Ignacio Sarasua, Wei Shen, Jaemin Son, Christian Wachinger, Liansheng Wang, Yan Wang, Yingda Xia, Daguang Xu, Zhanwei Xu, Yefeng Zheng, Amber L. Simpson, Lena Maier-Hein and M. Jorge Cardoso
Additional contact information
Michela Antonelli: King’s College London
Annika Reinke: German Cancer Research Center (DKFZ)
Spyridon Bakas: University of Pennsylvania
Keyvan Farahani: National Cancer Institute (NIH)
Annette Kopp-Schneider: German Cancer Research Center (DKFZ)
Bennett A. Landman: Vanderbilt University
Geert Litjens: Radboud Institute for Health Sciences
Bjoern Menze: University of Zurich
Olaf Ronneberger: DeepMind
Ronald M. Summers: National Institutes of Health Clinical Center (NIH)
Bram Ginneken: Radboud Institute for Health Sciences
Michel Bilello: University of Pennsylvania
Patrick Bilic: Technische Universität München
Patrick F. Christ: Technische Universität München
Richard K. G. Do: Memorial Sloan Kettering Cancer Center
Marc J. Gollub: Memorial Sloan Kettering Cancer Center
Stephan H. Heckers: Vanderbilt University Medical Center
Henkjan Huisman: Radboud Institute for Health Sciences
William R. Jarnagin: Memorial Sloan Kettering Cancer Center
Maureen K. McHugo: Vanderbilt University Medical Center
Sandy Napel: Stanford University
Jennifer S. Golia Pernicka: Memorial Sloan Kettering Cancer Center
Kawal Rhode: King’s College London
Catalina Tobon-Gomez: King’s College London
Eugene Vorontsov: École Polytechnique de Montréal
James A. Meakin: Radboud Institute for Health Sciences
Sebastien Ourselin: King’s College London
Manuel Wiesenfarth: German Cancer Research Center (DKFZ)
Pablo Arbeláez: Universidad de los Andes
Byeonguk Bae: VUNO Inc.
Sihong Chen: Tencent Jarvis Lab
Laura Daza: Universidad de los Andes
Jianjiang Feng: Tsinghua University
Baochun He: Chinese Academy of Sciences
Fabian Isensee: German Cancer Research Center (DKFZ)
Yuanfeng Ji: Xiamen University
Fucang Jia: Chinese Academy of Sciences
Ildoo Kim: Kakao Brain
Klaus Maier-Hein: Cerebriu A/S
Dorit Merhof: RWTH Aachen University
Akshay Pai: Cerebriu A/S
Beomhee Park: VUNO Inc.
Mathias Perslev: University of Copenhagen
Ramin Rezaiifar: MaaDoTaa.com
Oliver Rippel: RWTH Aachen University
Ignacio Sarasua: University Hospital
Wei Shen: Shanghai Jiao Tong University
Jaemin Son: VUNO Inc.
Christian Wachinger: University Hospital
Liansheng Wang: Xiamen University
Yan Wang: East China Normal University
Yingda Xia: Johns Hopkins University
Daguang Xu: NVIDIA
Zhanwei Xu: Tsinghua University
Yefeng Zheng: Tencent Jarvis Lab
Amber L. Simpson: Queen’s University
Lena Maier-Hein: German Cancer Research Center (DKFZ)
M. Jorge Cardoso: King’s College London

Nature Communications, 2022, vol. 13, issue 1, 1-13

Abstract: Abstract International challenges have become the de facto standard for comparative assessment of image analysis algorithms. Although segmentation is the most widely investigated medical image processing task, the various challenges have been organized to focus only on specific clinical tasks. We organized the Medical Segmentation Decathlon (MSD)—a biomedical image analysis challenge, in which algorithms compete in a multitude of both tasks and modalities to investigate the hypothesis that a method capable of performing well on multiple tasks will generalize well to a previously unseen task and potentially outperform a custom-designed solution. MSD results confirmed this hypothesis, moreover, MSD winner continued generalizing well to a wide range of other clinical problems for the next two years. Three main conclusions can be drawn from this study: (1) state-of-the-art image segmentation algorithms generalize well when retrained on unseen tasks; (2) consistent algorithmic performance across multiple tasks is a strong surrogate of algorithmic generalizability; (3) the training of accurate AI segmentation models is now commoditized to scientists that are not versed in AI model training.

Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (5)

Downloads: (external link)
https://www.nature.com/articles/s41467-022-30695-9 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:13:y:2022:i:1:d:10.1038_s41467-022-30695-9

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-022-30695-9

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().