In reporting of breast cancer pathology, mitosis detection and counting of mitotic cells are important factors that affect the tumor grade and the treatment of the patient. Mitotic cell counting requires standardization to a fixed field area. The total number of mitoses per 10 HPF is recorded. Normally, the count is performed manually by pathologists, but automating the process could reduce its time, minimize errors, and improve the comparability of results obtained in different pathology laboratories.
Mitosis detection is a complex process because only definite mitotic figures have to be counted; hyperchromatic and pyknotic nuclei are ignored since they are more likely to represent apoptosis rather than cells in mitosis [1]. Therefore, Virasoft uses an artificial intelligence method called convolutional neural networks (CNN) is used for mitosis detection in this analysis module.