Breast Cancer Classification on Histopathological Images Affected by Data Imbalance Using Active Learning and Deep Convolutional Neural Network

摘要

In this work, we propose an algorithm for training deep neural networks for classification of breast cancer in histopathological images affected by data unbalance with support of active learning. The output of the neural network on unlabeled samples is used to calculate weighted information entropy. It is utilized as uncertainty score for automatic selecting both samples with high and low confidence. A number of low confidence samples that are selected in each iteration is manually labeled by pathologist. A threshold that decays over iteration number is used to decide which high confidence samples should be concatenated with manually labeled samples and then used in fine-tuning of convolutional neural network. The neural network can optionally be trained using weighted cross-entropy loss to better cope with bias towards the majority class.