Mitosis domain generalization in histopathology images — The MIDOG challenge

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 F 1 score of 0.748 (CI95: 0.704-0.781), exceeding the performance of six experts on the same task. • MIDOG is the first challenge to address domain generalization in histopathology. • The main task was mitosis detection in breast cancer, an important prognostic marker. • The challenge dataset features 300 cases, 6 scanners, and more than 2500 mitosis. • This makes it the – to date – largest and most diverse labeled dataset on this task. • The results of the top methods were comparable to expert pathologists.