Two-Step Domain Adaptation for Mitotic Cell Detection in Histopathology Images

Mitotic figure count is an important prognostic factor for breast cancer grading. However, the mitotic identification often suffers from the domain variations. We propose a two-step domain-invariant mitosis detection method based on Faster RCNN and a convolutional neural network (CNN). We generate various domain-shifted versions of existing histopathology images using a stain augmentation technique, enabling our method to effectively learn various stain domains and achieve better generalization. The performance of our method is evaluated on the preliminary test and final test sets of the MIDOG-2021 challenge, resulting in F1 score of 68.95% and 67.64% respectively. The experimental results demonstrate that the proposed mitosis detection method can achieve promising performance for domain-shifted histopathology images.