Automated detection of mitotic figures in histopathology images has seen vast improvements, thanks to modern deep learning-based pipelines. Application of these methods, however, is in practice limited by strong variability of images between labs. This results in a domain shift of the images, which causes a performance drop of the models. Hypothesizing that the scanner device plays a decisive role in this effect, we evaluated the susceptibility of a standard mitosis detection approach to the domain shift introduced by using a different whole slide scanner. Our work is based on the MICCAI-MIDOG challenge 2021 data set, which includes 200 tumor cases of human breast cancer and four scanners. Our work indicates that the domain shift induced not by biochemical variability but purely by the choice of acquisition device is underestimated so far. Models trained on images of the same scanner yielded an average F1 score of 0.683, while models trained on a single other scanner only yielded an average F1 score of 0.325. Training on another multidomain mitosis dataset led to mean F1 scores of 0.52. We found this not to be reflected by domain-shifts measured as proxy A distance-derived metric.
[1]
Koby Crammer,et al.
Analysis of Representations for Domain Adaptation
,
2006,
NIPS.
[2]
Matthias Gallé,et al.
To Annotate or Not? Predicting Performance Drop under Domain Shift
,
2019,
EMNLP.
[3]
Jaime S. Cardoso,et al.
Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support
,
2017,
Lecture Notes in Computer Science.
[4]
Gabriel Eilertsen,et al.
Measuring Domain Shift for Deep Learning in Histopathology
,
2020,
IEEE Journal of Biomedical and Health Informatics.