First successful MIDOG challenge at MICCAI 2021

The image shows a podium with the three MIDOG Challenge winners.

At this year’s MICCAI satellite events, the results of the first MIDOG (Mitosis Domain Generalization) challenge were presented. The goal of the challenge was to investigate and tackle the domain shift for different scanners for the task of mitosis detection for breast cancer. The 14 best performing teams presented their approaches live at the workshop, complemented by an invited talk by Tobias Heimann from Siemens Healthineers on “How to build trustworthy AI solutions”.

The challenge was only possible due to a multi-institute organizer team:

Marc Aubreville Technische Hochschule Ingolstadt, Germany
Christof Bertram Institute of Pathology, University of Veterinary Medicine, Vienna, Austria
Mitko Veta Medical Image Analysis Group, TU Eindhoven, The Netherlands
Nikolas Stathonikos Pathology Department, UMC Utrecht, The Netherlands
Robert Klopfleisch Institute of Veterinary Pathology, Freie Universität Berlin, Germany
Katharina Breininger Department Artificial Intelligence in Biomedical Engineering, Friedrich-Alexander- Universität Erlangen-Nürnberg, Germany
Natalie ter Hoeve Pathology Department, UMC Utrecht, The Netherlands
Francesco Ciompi Computational Pathology Group, Radboud UMC Nijmegen, The Netherlands
Andreas Maier Pattern Recognition Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany

We thank and congratulate all participants of the challenge and especially the three best performing approaches by Jahanifar et al. (Team TIA Centre, University of Warwick and University of Sheffield, UK), Yang et al. (Team AI_medical, Sichuan University and Tsinghua University, China) and Roy et al. (Team serendipidy, Tribvn Healthcare, France)!

The workshop was supported by Siemens Healthineers and Medical Data Donors e.V. We further thank Nvidia, and Amazon AWS to provide the challenge platform and the computational resources for the challenge!

Since we received multiple requests for a follow-up challenge, let’s see what the next year brings 😉