Mitosis domain generalization in histopathology images — The MIDOG challenge

Aubreville M, Stathonikos N, Bertram CA, Klopfleisch R, ter Hoeve N, Ciompi F, Wilm F, Marzahl C, Donovan TA, Maier A, Breen J, Ravikumar N, Chung Y, Park J, Nateghi R, Pourakpour F, Fick RH, Ben Hadj S, Jahanifar M, Shephard A, Dexl J, Wittenberg T, Kondo S, Lafarge MW, Koelzer VH, Liang J, Wang Y, Long X, Liu J, Razavi S, Khademi A, Yang S, Wang X, Erber R, Klang A, Lipnik K, Bolfa P, Dark MJ, Wasinger G, Veta M, Breininger K (2023)


Publication Type: Journal article

Publication year: 2023

Journal

Book Volume: 84

Article Number: 102699

DOI: 10.1016/j.media.2022.102699

Abstract

The density of mitotic figures (MF) within tumor tissue is known to be highly correlated with tumor proliferation and thus is an important marker in tumor grading. Recognition of MF by pathologists is subject to a strong inter-rater bias, limiting its prognostic value. State-of-the-art deep learning methods can support experts but have been observed to strongly deteriorate when applied in a different clinical environment. The variability caused by using different whole slide scanners has been identified as one decisive component in the underlying domain shift. The goal of the MICCAI MIDOG 2021 challenge was the creation of scanner-agnostic MF detection algorithms. The challenge used a training set of 200 cases, split across four scanning systems. As test set, an additional 100 cases split across four scanning systems, including two previously unseen scanners, were provided. In this paper, we evaluate and compare the approaches that were submitted to the challenge and identify methodological factors contributing to better performance. The winning algorithm yielded an F1 score of 0.748 (CI95: 0.704-0.781), exceeding the performance of six experts on the same task.

Authors with CRIS profile

Involved external institutions

Radboud University Nijmegen Medical Centre / Radboudumc of voluit Radboud Universitair Medisch Centrum (UMC) NL Netherlands (NL) Korea Advanced Institute of Science and Technology (KAIST) KR Korea, Republic of (KR) Universitätsspital Zürich (USZ) CH Switzerland (CH) Veterinärmedizinische Universität Wien (Vetmeduni Vienna) / University of Veterinary Medicine, Vienna AT Austria (AT) University of Leeds GB United Kingdom (GB) University Medical Centre Utrecht (UMC Utrecht) NL Netherlands (NL) Technische Hochschule Ingolstadt DE Germany (DE) Medizinische Universität Wien AT Austria (AT) Freie Universität Berlin DE Germany (DE) Xidian University CN China (CN) University of Warwick GB United Kingdom (GB) Toronto Metropolitan University / Ryerson University CA Canada (CA) Muroran Institute of Technology (MuIT) / 室蘭工業大学 JP Japan (JP) Xi’an Jiaotong-Liverpool University (XJTLU) CN China (CN) Shiraz University of Technology (SUTech) / دانشگاه صنعتی شیراز IR Iran, Islamic Republic of (IR) Eindhoven University of Technology / Technische Universiteit Eindhoven (TU/e) NL Netherlands (NL) Ross University School of Veterinary Medicine KN Saint Kitts And Nevis (KN) Fraunhofer-Institut für Integrierte Schaltungen (IIS) DE Germany (DE) National Brain Mapping Laboratory IR Iran, Islamic Republic of (IR) University of Florida US United States (USA) (US) Animal Medical Center (AMC) US United States (USA) (US) Tencent Holdings Ltd / 腾讯控股有限公司 CN China (CN) Sichuan University (SCU) / 四川大学 CN China (CN) Tribun Health FR France (FR)

How to cite

APA:

Aubreville, M., Stathonikos, N., Bertram, C.A., Klopfleisch, R., ter Hoeve, N., Ciompi, F.,... Breininger, K. (2023). Mitosis domain generalization in histopathology images — The MIDOG challenge. Medical Image Analysis, 84. https://dx.doi.org/10.1016/j.media.2022.102699

MLA:

Aubreville, Marc, et al. "Mitosis domain generalization in histopathology images — The MIDOG challenge." Medical Image Analysis 84 (2023).

BibTeX: Download