A Systematic Approach to Identify the Breast Cancer Grades in Histopathological Images Using Deep Neural Networks

Abstract

Breast cancer can be recognized as one of the most well-known and life-threatening cancers impacting women and this has been identified as the second most common cancer across the world. According to registered data, there were over 2 million newly reported cases in 2020. The Deep Convolutional Neural Network has been identified as one of the most dominant and powerful deep learning approaches involved in the analysis of visual imagination. There are many shreds of evidence that indicate the appropriateness of this in medical imaging including breast cancer detection, lassification, and segmentation with higher accuracy rates. The main intent of the research is to develop an automated application that can determine the Nottingham Histologic Score of a given input histopathological image obtained from breast cancer or healthy tissues with DenseNet based architecture. Healthy or benign tissues are categorized as zero and cancerous tissues are categorized based on the grade obtained as one, two, or three. In this study, we were able to obtain more than 94% accuracy rates for each trained model including 2-predict, 3-predict, and 4-predict networks. Further, a desktop-based inference tool that allows us to perform breast cancer grading was also developed as a result of this study.