Marc Aubreville Marc Aubreville Nikolas Stathonikos Nikolas Stathonikos Taryn A. Donovan Taryn A. Donovan Robert Klopfleisch Robert Klopfleisch Jonas Ammeling Jonas Ammeling Jonathan Ganz Jonathan Ganz Frauke Wilm Frauke Wilm Mitko Veta Mitko Veta Samir Jabari Samir Jabari Markus Eckstein Markus Eckstein Jonas Annuscheit Jonas Annuscheit Christian Krumnow Christian Krumnow Engin Bozaba Engin Bozaba Sercan Cayir Sercan Cayir Hongyan Gu Hongyan Gu Xiang Anthony Chen Xiang Anthony Chen Mostafa Jahanifar Mostafa Jahanifar Adam Shepard Adam Shepard Satoshi Kondo Satoshi Kondo Sathosi Kasai Sathosi Kasai Sujatha Kotte Sujatha Kotte V. G. Saipradeep V. G. Saipradeep Maxime W. Lafarge Maxime W. Lafarge Viktor H. Koelzer Viktor H. Koelzer Ziyue Wang Ziyue Wang Yongbing Zhang Yongbing Zhang Xiyue Wang Xiyue Wang Katharina Breininger Katharina Breininger Christof A. Bertram Christof A. Bertram Elsevier 2024 Recognition of mitotic figures in histologic tumor specimens is highly relevant to patient outcome assessment. This task is challenging for algorithms and human experts alike, with deterioration of algorithmic performance under shifts in image representations. Considerable covariate shifts occur when assessment is performed on different tumor types, images are acquired using different digitization devices, or specimens are produced in different laboratories. This observation motivated the inception of the 2022 challenge on MItosis Domain Generalization (MIDOG 2022). The challenge provided annotated histologic tumor images from six different domains and evaluated the algorithmic approaches for mitotic figure detection provided by nine challenge participants on ten independent domains. Ground truth for mitotic figure detection was established in two ways: a three-expert majority vote and an independent, immunohistochemistry-assisted set of labels. This work represents an overview of the challenge tasks, the algorithmic strategies employed by the participants, and potential factors contributing to their success. With an F1 score of 0.764 for the top-performing team, we summarize that domain generalization across various tumor domains is possible with today's deep learning-based recognition pipelines. However, we also found that domain characteristics not present in the training set (feline as new species, spindle cell shape as new morphology and a new scanner) led to small but significant decreases in performance. When assessed against the immunohistochemistry-assisted reference standard, all methods resulted in reduced recall scores, with only minor changes in the order of participants in the ranking. PDFDocument eng 2025-07-24T09:25:58.927477Z 2024 Domain Generalization Histopathology Challenge Deep Learning Mitosis 2900878 b application/pdf http://creativecommons.org/licenses/by/4.0/