The STOIC2021 COVID-19 AI challenge: Applying reusable training methodologies to private data

Luuk H. Boulogne, Julian Lorenz, Daniel Kienzle, Robin Schön, Katja Ludwig, Rainer Lienhart, Simon Jégou, Guang Li, Cong Chen, Qi Wang, Derik Shi, Mayug Maniparambil, Dominik Müller, Silvan Mertes, Niklas Schröter, Fabio Hellmann, Miriam Elia, Ine Dirks, Matías Nicolás Bossa, Abel Díaz Berenguer et al. (18 additional authors not shown)

Abstract: Highlights•STOIC2021, aimed at detecting severe COVID-19, was organized with 10,724 CT scans.•The T3 challenge format allows training on private data and ensures reusable methods.•CT scans and metadata of 2,000 COVID-19 subjects were released under CC-BY-NC 4.0.•The finalist codebases were released publicly under permissive licenses.