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 van Ginneken, Michel Bilello, Patrick Bilic, Patrick Ferdinand Christ, Richard Kinh Gian, Marc J. Gollub, Stephan Heckers, Henkjan Huisman, William R. Jarnagin, Maureen McHugo, Sandy Napel, Jennifer S. Golia Pernicka, Kawal Rhode, Catalina Tobon‐Gomez, Eugene Vorontsov, James Meakin, Sébastien 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, R. Rezaiifar, Oliver Rippel, Ignacio Sarasúa, Wei Shen, Jaemin Son, Christian Wachinger, Liansheng Wang, Yan Wang, Yingda Xia, Daguang Xu, Zhanwei Xu, Yefeng Zheng, Amber L. Simpson, Lena Maier‐Hein, M. Jorge Cardoso
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.