Semi-supervised learning for medical image classification using imbalanced training data

Abstract

Medical image classification is often challenging for two reasons: a lack of labelled examples due to expensive and time-consuming annotation protocols, and imbalanced class labels due to the relative scarcity of disease-positive individuals in the wider population. Semi-supervised learning (SSL) methods exist for dealing with a lack of labels, but they generally do not address the problem of class imbalance. In this study we propose Adaptive Blended Consistency Loss (ABCL), a drop-in replacement for consistency loss in perturbation-based SSL methods. ABCL counteracts data skew by adaptively mixing the target class distribution of the consistency loss in accordance with class frequency. Our experiments with ABCL reveal improvements to unweighted average recall on two different imbalanced medical image classification datasets when compared with existing consistency losses that are not designed to counteract class imbalance.

arXiv commentThis paper has 28 pages, 7 figures

References in corpus (12)

• SMOTE: Synthetic Minority Over-sampling Technique
• Unsupervised Data Augmentation for Consistency Training
• Temporal Ensembling for Semi-Supervised Learning
• CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning
• REFUGE Challenge: A Unified Framework for Evaluating Automated Methods for Glaucoma Assessment from Fundus Photographs
• Random Erasing Data Augmentation
• Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks
• Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning
• Automatic Skin Lesion Analysis using Large-scale Dermoscopy Images and Deep Residual Networks
• Dermatologist Level Dermoscopy Skin Cancer Classification Using Different Deep Learning Convolutional Neural Networks Algorithms
• Class-Imbalanced Semi-Supervised Learning
• DNN and CNN with Weighted and Multi-task Loss Functions for Audio Event Detection