Hierarchical ResNeXt Models for Breast Cancer Histology Image Classification

TL;DR

This paper introduces a hierarchical CNN system for classifying breast cancer histology images, achieving high accuracy and competitive ranking in a challenge, thus advancing automated pathology analysis.

Contribution

The paper presents a novel hierarchical CNN architecture for histology image classification, demonstrating improved accuracy on benchmark datasets.

Findings

Achieved 99% accuracy on BACH dataset

Reached 81% accuracy in BACH challenge, ranking 8th

Validated effectiveness on extended small dataset

Abstract

Microscopic histology image analysis is a cornerstone in early detection of breast cancer. However these images are very large and manual analysis is error prone and very time consuming. Thus automating this process is in high demand. We proposed a hierarchical system of convolutional neural networks (CNN) that classifies automatically patches of these images into four pathologies: normal, benign, in situ carcinoma and invasive carcinoma. We evaluated our system on the BACH challenge dataset of image-wise classification and a small dataset that we used to extend it. Using a train/test split of 75%/25%, we achieved an accuracy rate of 0.99 on the test split for the BACH dataset and 0.96 on that of the extension. On the test of the BACH challenge, we've reached an accuracy of 0.81 which rank us to the 8th out of 51 teams.