Context-Aware Learning using Transferable Features for Classification of Breast Cancer Histology Images

TL;DR

This paper introduces a context-aware transfer learning approach using CNN features for breast cancer histology image classification, effectively handling small datasets and outperforming existing methods.

Contribution

It presents a novel framework combining CNN features with contextual information for improved classification on limited data.

Findings

Outperforms state-of-the-art breast cancer classification methods

Leverages CNN features with contextual information for small datasets

Demonstrates improved accuracy over previous approaches

Abstract

Convolutional neural networks (CNNs) have been recently used for a variety of histology image analysis. However, availability of a large dataset is a major prerequisite for training a CNN which limits its use by the computational pathology community. In previous studies, CNNs have demonstrated their potential in terms of feature generalizability and transferability accompanied with better performance. Considering these traits of CNN, we propose a simple yet effective method which leverages the strengths of CNN combined with the advantages of including contextual information, particularly designed for a small dataset. Our method consists of two main steps: first it uses the activation features of CNN trained for a patch-based classification and then it trains a separate classifier using features of overlapping patches to perform image-based classification using the contextual information. The proposed framework outperformed the state-of-the-art method for breast cancer classification.