https://phaidra.vetmeduni.ac.at/o:2258 A comprehensive multi-domain dataset for mitotic figure detection Aubreville, Marc Marc Aubreville 0000-0002-5294-5247 Technische Hochschule Ingolstadt Bertram, Christof A. Christof A. Bertram 0000-0002-2402-9997 University of Veterinary Medicine Vienna Klopfleisch, Robert Robert Klopfleisch 0000-0002-6308-0568 Freie Universität Berlin van Diest, Paul J. Paul J. van Diest Friedrich-Alexander-Universität Erlangen-Nürnberg Ammeling, Jonas Jonas Ammeling Technische Hochschule Ingolstadt Ganz, Jonathan Jonathan Ganz Technische Hochschule Ingolstadt Veta, Mitko Mitko Veta Eindhoven University of Technology Jabari, Samir Samir Jabari Friedrich-Alexander-Universität Erlangen-Nürnberg Donovan, Taryn A. Taryn A. Donovan Schwarzman Animal Medical Center Breininger, Katharina Katharina Breininger 0000-0001-7600-5869 Friedrich-Alexander-Universität Erlangen-Nürnberg Wilm, Frauke Frauke Wilm 0000-0002-9065-0554 Friedrich-Alexander-Universität Erlangen-Nürnberg Stathonikos, Nikolas Nikolas Stathonikos University Medical Center Utrecht Nature Portfolio text eng The prognostic value of mitotic figures in tumor tissue is well-established for many tumor types and automating this task is of high research interest. However, especially deep learning-based methods face performance deterioration in the presence of domain shifts, which may arise from different tumor types, slide preparation and digitization devices. We introduce the MIDOG++ dataset, an extension of the MIDOG 2021 and 2022 challenge datasets. We provide region of interest images from 503 histological specimens of seven different tumor types with variable morphology with in total labels for 11,937 mitotic figures: breast carcinoma, lung carcinoma, lymphosarcoma, neuroendocrine tumor, cutaneous mast cell tumor, cutaneous melanoma, and (sub)cutaneous soft tissue sarcoma. The specimens were processed in several laboratories utilizing diverse scanners. We evaluated the extent of the domain shift by using state-of-the-art approaches, observing notable differences in single-domain training. In a leave-one-domain-out setting, generalizability improved considerably. This mitotic figure dataset is the first that incorporates a wide domain shift based on different tumor types, laboratories, whole slide image scanners, and species. Breast-Cancer; Classification; System; Stage; Count http://creativecommons.org/licenses/by/4.0/ https://phaidra.vetmeduni.ac.at/api/object/o:2258/download 10.1038/s41597-023-02327-4 https://phaidra.vetmeduni.ac.at/o:605 application/pdf Scientific Data 10(1) (2023) Scientific Data 10 1 1.29 MB 2023