Active Learning for Breast Cancer Identification

TL;DR

This paper introduces reversed active learning (RAL), a novel training strategy that improves CNN accuracy in breast cancer image classification by effectively removing mislabeled data, achieving higher diagnostic precision.

Contribution

The paper proposes a new reversed active learning approach for training CNNs that enhances breast cancer classification accuracy by filtering out mislabeled images.

Findings

RAL increases CNN accuracy from 93.75% to 96.25%.

The method effectively removes mislabeled images from training data.

Improves diagnostic accuracy in breast cancer image classification.

Abstract

Breast cancer is the second most common malignancy among women and has become a major public health problem in current society. Traditional breast cancer identification requires experienced pathologists to carefully read the breast slice, which is laborious and suffers from inter-observer variations. Consequently, an automatic classification framework for breast cancer identification is worthwhile to develop. Recent years witnessed the development of deep learning technique. Increasing number of medical applications start to use deep learning to improve diagnosis accuracy. In this paper, we proposed a novel training strategy, namely reversed active learning (RAL), to train network to automatically classify breast cancer images. Our RAL is applied to the training set of a simple convolutional neural network (CNN) to remove mislabeled images. We evaluate the CNN trained with RAL on publicly available ICIAR 2018 Breast Cancer Dataset (IBCD). The experimental results show that our RAL increases the slice-based accuracy of CNN from 93.75% to 96.25%.