Breast cancer histopathological image classification using Convolutional Neural Networks

TLDR

Conventional classification systems rely on laborious feature engineering, whereas deep learning—especially convolutional neural networks—automatically extracts discriminative features and has succeeded in many domains. The study conducts preliminary experiments using deep learning to classify breast cancer histopathological images from the BreaKHis dataset. The authors extract image patches for CNN training and combine these patches for final classification, enabling the use of high‑resolution histopathological images without adapting the CNN architecture. CNN performance surpasses that of prior hand‑crafted descriptor models, and fusing multiple CNNs with simple rules further improves recognition rates.

Abstract

The performance of most conventional classification systems relies on appropriate data representation and much of the efforts are dedicated to feature engineering, a difficult and time-consuming process that uses prior expert domain knowledge of the data to create useful features. On the other hand, deep learning can extract and organize the discriminative information from the data, not requiring the design of feature extractors by a domain expert. Convolutional Neural Networks (CNNs) are a particular type of deep, feedforward network that have gained attention from research community and industry, achieving empirical successes in tasks such as speech recognition, signal processing, object recognition, natural language processing and transfer learning. In this paper, we conduct some preliminary experiments using the deep learning approach to classify breast cancer histopathological images from BreaKHis, a publicly dataset available at http://web.inf.ufpr.br/vri/breast-cancer-database. We propose a method based on the extraction of image patches for training the CNN and the combination of these patches for final classification. This method aims to allow using the high-resolution histopathological images from BreaKHis as input to existing CNN, avoiding adaptations of the model that can lead to a more complex and computationally costly architecture. The CNN performance is better when compared to previously reported results obtained by other machine learning models trained with hand-crafted textural descriptors. Finally, we also investigate the combination of different CNNs using simple fusion rules, achieving some improvement in recognition rates.