Class-Specific Distribution Alignment for Semi-Supervised Medical Image Classification
This addresses the problem of limited annotated data and class imbalance in medical image classification for healthcare applications, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackled semi-supervised medical image classification with imbalanced class distributions by proposing Class-Specific Distribution Alignment (CSDA) and a Variable Condition Queue (VCQ) module, achieving competitive performance on three public datasets including HAM10000, CheXpert, and Kvasir.
Despite the success of deep neural networks in medical image classification, the problem remains challenging as data annotation is time-consuming, and the class distribution is imbalanced due to the relative scarcity of diseases. To address this problem, we propose Class-Specific Distribution Alignment (CSDA), a semi-supervised learning framework based on self-training that is suitable to learn from highly imbalanced datasets. Specifically, we first provide a new perspective to distribution alignment by considering the process as a change of basis in the vector space spanned by marginal predictions, and then derive CSDA to capture class-dependent marginal predictions on both labeled and unlabeled data, in order to avoid the bias towards majority classes. Furthermore, we propose a Variable Condition Queue (VCQ) module to maintain a proportionately balanced number of unlabeled samples for each class. Experiments on three public datasets HAM10000, CheXpert and Kvasir show that our method provides competitive performance on semi-supervised skin disease, thoracic disease, and endoscopic image classification tasks.