Publikationsdatenbank

Domain generalization across tumor types, laboratories, and species — Insights from the 2022 edition of the Mitosis Domain Generalization Challenge (2024)

Art

Zeitschriftenartikel / wissenschaftlicher Beitrag

Autoren

Aubreville, Marc

Stathonikos, Nikolas

Donovan, Taryn A.

Klopfleisch, Robert (WE 12)

Ammeling, Jonas

Ganz, Jonathan

Wilm, Frauke

Veta, Mitko

Jabari, Samir

Eckstein, Markus

Annuscheit, Jonas

Krumnow, Christian

Bozaba, Engin

Çayır, Sercan

Gu, Hongyan

Chen, Xiang ‘Anthony’

Jahanifar, Mostafa

Shephard, Adam

Kondo, Satoshi

Kasai, Satoshi

Kotte, Sujatha

Saipradeep, V.G.

Lafarge, Maxime W.

Koelzer, Viktor H.

Wang, Ziyue

Zhang, Yongbing

Yang, Sen

Wang, Xiyue

Breininger, Katharina

Bertram, Christof A.

Quelle

Medical image analysis

Bandzählung: 94

Seiten: 103155

ISSN: 1361-8415

Sprache

Englisch

Verweise

URL (Volltext): https://linkinghub.elsevier.com/retrieve/pii/S136184152400080X

DOI: 10.1016/j.media.2024.103155

Pubmed: 38537415

Kontakt

Institut für Tierpathologie

Robert-von-Ostertag-Str. 15
14163 Berlin
+49 30 838 62450
pathologie@vetmed.fu-berlin.de

Abstract / Zusammenfassung

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.