Titel (eng)

A comprehensive multi-domain dataset for mitotic figure detection

Autor*in

Marc Aubreville   Technische Hochschule Ingolstadt

Christof A. Bertram   University of Veterinary Medicine Vienna

Robert Klopfleisch   Freie Universität Berlin

Paul J. van Diest   Friedrich-Alexander-Universität Erlangen-Nürnberg

Jonas Ammeling   Technische Hochschule Ingolstadt

Jonathan Ganz   Technische Hochschule Ingolstadt

Mitko Veta   Eindhoven University of Technology

Samir Jabari   Friedrich-Alexander-Universität Erlangen-Nürnberg

Taryn A. Donovan   Schwarzman Animal Medical Center

Katharina Breininger   Friedrich-Alexander-Universität Erlangen-Nürnberg

Frauke Wilm   Friedrich-Alexander-Universität Erlangen-Nürnberg

Nikolas Stathonikos   University Medical Center Utrecht

Verlag

Nature Portfolio

Beschreibung (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.

Sprache des Objekts

Englisch

Datum

2023

Rechte

Dieses Werk bzw. dieser Inhalt steht unter einer
CC BY 4.0 - Creative Commons Namensnennung 4.0 International Lizenz.

CC BY 4.0 International

http://creativecommons.org/licenses/by/4.0/

Klassifikation

Breast-Cancer; Classification; System; Stage; Count

Mitglied in der/den Collection(s) (1)