Two-Stage Convolutional Neural Network for Breast Cancer Histology Image Classification

TL;DR

This paper introduces a two-stage CNN approach for classifying breast cancer histology images, achieving a significant accuracy improvement by combining patch-based feature extraction with whole-image classification.

Contribution

The novel two-stage CNN method effectively combines local patch features and global image context for improved classification accuracy.

Findings

Achieved 95% accuracy on BACH dataset

Outperformed previous methods with 77% accuracy

Proposed patch-based two-network architecture

Abstract

This paper explores the problem of breast tissue classification of microscopy images. Based on the predominant cancer type the goal is to classify images into four categories of normal, benign, in situ carcinoma, and invasive carcinoma. Given a suitable training dataset, we utilize deep learning techniques to address the classification problem. Due to the large size of each image in the training dataset, we propose a patch-based technique which consists of two consecutive convolutional neural networks. The first "patch-wise" network acts as an auto-encoder that extracts the most salient features of image patches while the second "image-wise" network performs classification of the whole image. The first network is pre-trained and aimed at extracting local information while the second network obtains global information of an input image. We trained the networks using the ICIAR 2018 grand challenge on BreAst Cancer Histology (BACH) dataset. The proposed method yields 95 % accuracy on the validation set compared to previously reported 77 % accuracy rates in the literature. Our code is publicly available at https://github.com/ImagingLab/ICIAR2018