Journal Article

DKFZ-2022-01494

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png The Medical Segmentation Decathlon.

Antonelli, M. ; Reinke, A. (First author)DKFZ* ; Bakas, S. ; Farahani, K. ; Kopp-Schneider, A.DKFZ* ; Landman, B. A. ; Litjens, G. ; Menze, B. ; Ronneberger, O. ; Summers, R. M. ; van Ginneken, B. ; Bilello, M. ; Bilic, P. ; Christ, P. F. ; Do, R. K. G. ; Gollub, M. J. ; Heckers, S. H. ; Huisman, H. ; Jarnagin, W. R. ; McHugo, M. K. ; Napel, S. ; Pernicka, J. S. G. ; Rhode, K. ; Tobon-Gomez, C. ; Vorontsov, E. ; Meakin, J. A. ; Ourselin, S. ; Wiesenfarth, M.DKFZ* ; Arbeláez, P. ; Bae, B. ; Chen, S. ; Daza, L. ; Feng, J. ; He, B. ; Isensee, F.DKFZ* ; Ji, Y. ; Jia, F. ; Kim, I. ; Maier-Hein, K. ; Merhof, D. ; Pai, A. ; Park, B. ; Perslev, M. ; Rezaiifar, R. ; Rippel, O. ; Sarasua, I. ; Shen, W. ; Son, J. ; Wachinger, C. ; Wang, L. ; Wang, Y. ; Xia, Y. ; Xu, D. ; Xu, Z. ; Zheng, Y. ; Simpson, A. L. ; Maier-Hein, L. (Last author)DKFZ* ; Cardoso, M. J.

2022
Nature Publishing Group UK [London]

This record in other databases:  

Please use a persistent id in citations: doi:10.1038/s41467-022-30695-9

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.

Note: #EA:E130#LA:E130#

---

Contributing Institute(s):

1. E130 Intelligente Medizinische Systeme (E130)
2. C060 Biostatistik (C060)
3. E230 Medizinische Bildverarbeitung (E230)

Research Program(s):

1. 315 - Bildgebung und Radioonkologie (POF4-315) (POF4-315)

Appears in the scientific report 2022

---

Database coverage:
; ; ; Article Processing Charges ; BIOSIS Previews ; Biological Abstracts ; Clarivate Analytics Master Journal List ; Current Contents - Agriculture, Biology and Environmental Sciences ; Current Contents - Life Sciences ; Current Contents - Physical, Chemical and Earth Sciences ; DOAJ Seal ; Essential Science Indicators ; Fees ; IF >= 15 ; JCR ; SCOPUS ; Science Citation Index Expanded ; Web of Science Core Collection ; Zoological Record

---