Semi-supervised learning for medical image classification using imbalanced training data
This addresses a specific issue in medical imaging where data is often imbalanced, but it is incremental as it builds on existing SSL methods.
The paper tackled the problem of class imbalance in semi-supervised medical image classification by proposing the Adaptive Blended Consistency Loss (ABCL), which improved unweighted average recall on two imbalanced datasets.
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.