Domain Adversarial RetinaNet as a Reference Algorithm for the MItosis DOmain Generalization Challenge
This work addresses domain generalization for mitotic count assessment in histopathology, providing a baseline algorithm for a specific challenge.
The paper tackled the problem of domain shift in mitotic figure detection for histopathology by developing a domain adversarial training algorithm, achieving an F1 score of 0.7183 on a test set.
Assessing the Mitotic Count has a known high degree of intra- and inter-rater variability. Computer-aided systems have proven to decrease this variability and reduce labeling time. These systems, however, are generally highly dependent on their training domain and show poor applicability to unseen domains. In histopathology, these domain shifts can result from various sources, including different slide scanning systems used to digitize histologic samples. The MItosis DOmain Generalization challenge focused on this specific domain shift for the task of mitotic figure detection. This work presents a mitotic figure detection algorithm developed as a baseline for the challenge, based on domain adversarial training. On the challenge's test set, the algorithm scored an F$_1$ score of 0.7183. The corresponding network weights and code for implementing the network are made publicly available.