TY  - JOUR
AU  - Antonelli, Michela
AU  - Reinke, Annika
AU  - Bakas, Spyridon
AU  - Farahani, Keyvan
AU  - Kopp-Schneider, Annette
AU  - Landman, Bennett A
AU  - Litjens, Geert
AU  - Menze, Bjoern
AU  - Ronneberger, Olaf
AU  - Summers, Ronald M
AU  - van Ginneken, Bram
AU  - Bilello, Michel
AU  - Bilic, Patrick
AU  - Christ, Patrick F
AU  - Do, Richard K G
AU  - Gollub, Marc J
AU  - Heckers, Stephan H
AU  - Huisman, Henkjan
AU  - Jarnagin, William R
AU  - McHugo, Maureen K
AU  - Napel, Sandy
AU  - Pernicka, Jennifer S Golia
AU  - Rhode, Kawal
AU  - Tobon-Gomez, Catalina
AU  - Vorontsov, Eugene
AU  - Meakin, James A
AU  - Ourselin, Sebastien
AU  - Wiesenfarth, Manuel
AU  - Arbeláez, Pablo
AU  - Bae, Byeonguk
AU  - Chen, Sihong
AU  - Daza, Laura
AU  - Feng, Jianjiang
AU  - He, Baochun
AU  - Isensee, Fabian
AU  - Ji, Yuanfeng
AU  - Jia, Fucang
AU  - Kim, Ildoo
AU  - Maier-Hein, Klaus
AU  - Merhof, Dorit
AU  - Pai, Akshay
AU  - Park, Beomhee
AU  - Perslev, Mathias
AU  - Rezaiifar, Ramin
AU  - Rippel, Oliver
AU  - Sarasua, Ignacio
AU  - Shen, Wei
AU  - Son, Jaemin
AU  - Wachinger, Christian
AU  - Wang, Liansheng
AU  - Wang, Yan
AU  - Xia, Yingda
AU  - Xu, Daguang
AU  - Xu, Zhanwei
AU  - Zheng, Yefeng
AU  - Simpson, Amber L
AU  - Maier-Hein, Lena
AU  - Cardoso, M Jorge
TI  - The Medical Segmentation Decathlon.
JO  - Nature Communications
VL  - 13
IS  - 1
SN  - 2041-1723
CY  - [London]
PB  - Nature Publishing Group UK
M1  - DKFZ-2022-01494
SP  - 4128
PY  - 2022
N1  - #EA:E130#LA:E130#
AB  - 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.
LB  - PUB:(DE-HGF)16
C6  - pmid:35840566
DO  - DOI:10.1038/s41467-022-30695-9
UR  - https://inrepo02.dkfz.de/record/180698
ER  -