MITOS-RCNN: A Novel Approach to Mitotic Figure Detection in Breast Cancer Histopathology Images using Region Based Convolutional Neural Networks

TL;DR

MITOS-RCNN is a new deep learning model designed to accurately detect mitotic figures in breast cancer histopathology images, improving precision and recall over previous methods and aiding in cancer prognosis.

Contribution

The paper introduces MITOS-RCNN, a region-based CNN tailored for small object detection in histopathology images, outperforming prior models in mitotic figure detection tasks.

Findings

Achieved an F-measure score of 0.955, the highest in the field.

Outperformed all previous models in major challenges and datasets.

Improved accuracy by 6.11% over prior best models.

Abstract

Studies estimate that there will be 266,120 new cases of invasive breast cancer and 40,920 breast cancer induced deaths in the year of 2018 alone. Despite the pervasiveness of this affliction, the current process to obtain an accurate breast cancer prognosis is tedious and time consuming, requiring a trained pathologist to manually examine histopathological images in order to identify the features that characterize various cancer severity levels. We propose MITOS-RCNN: a novel region based convolutional neural network (RCNN) geared for small object detection to accurately grade one of the three factors that characterize tumor belligerence described by the Nottingham Grading System: mitotic count. Other computational approaches to mitotic figure counting and detection do not demonstrate ample recall or precision to be clinically viable. Our models outperformed all previous participants in the ICPR 2012 challenge, the AMIDA 2013 challenge and the MITOS-ATYPIA-14 challenge along with recently published works. Our model achieved an F-measure score of 0.955, a 6.11% improvement in accuracy from the most accurate of the previously proposed models.