Classification of Breast Cancer Histology using Deep Learning

TL;DR

This paper presents a deep learning approach using fine-tuned Inception-v3 CNN for classifying breast cancer histology images into four categories, achieving high accuracy by focusing on nuclei-dense patches and majority voting.

Contribution

It introduces a nuclei density-based patch extraction method and applies transfer learning for improved breast cancer histology classification accuracy.

Findings

Achieved 85% four-class accuracy.

Achieved 93% two-class accuracy (non-cancer vs. carcinoma).

Improved upon previous benchmark results.

Abstract

Breast Cancer is a major cause of death worldwide among women. Hematoxylin and Eosin (H&E) stained breast tissue samples from biopsies are observed under microscopes for the primary diagnosis of breast cancer. In this paper, we propose a deep learning-based method for classification of H&E stained breast tissue images released for BACH challenge 2018 by fine-tuning Inception-v3 convolutional neural network (CNN) proposed by Szegedy et al. These images are to be classified into four classes namely, i) normal tissue, ii) benign tumor, iii) in-situ carcinoma and iv) invasive carcinoma. Our strategy is to extract patches based on nuclei density instead of random or grid sampling, along with rejection of patches that are not rich in nuclei (non-epithelial) regions for training and testing. Every patch (nuclei-dense region) in an image is classified in one of the four above mentioned categories. The class of the entire image is determined using majority voting over the nuclear classes. We obtained an average four class accuracy of 85% and an average two class (non-cancer vs. carcinoma) accuracy of 93%, which improves upon a previous benchmark by Araujo et al.