Deep Learning Methods for Mitosis Detection in Breast Cancer Histopathological Images: A Comprehensive Review

In breast cancer histology, there are three important features for tumor grading, where the proliferation score presents a key component. The mitotic count strategy is among the used methods to predict this score. However, this task is tedious and time consuming for pathologists. To simplify their work, there is a recognized need for computer-aided diagnostic systems (CADs). Several attempts have been made to automate the mitosis detection based on both machine and deep learning (DL) methods. This study aims to provide the readers with a medical knowledge on mitosis detection and DL methods, review and compare the relevant literature on DL methods for mitosis detection on H&E histopathological images, and finally discuss the remaining challenges and some of the perspectives.