Semi-supervised Classification of Chest Radiographs.

To train deep learning models in a supervised fashion, we need a significant amount of training data, but in most medical imaging scenarios, there is a lack of annotated data available. In this paper, we compare state-of-the-art semi-supervised classification methods in a medical imaging scenario. We evaluate the performance of different approaches in a chest radiograph classification task using the ChestX-ray14 dataset. We adapted methods based on pseudo-labeling and consistency regularization to perform multi-label classification and to use a state-of-the-art model architecture in chest radiograph classification. Our proposed approaches resulted in average AUCs up to 0.6691 with only 25 labeled samples per class, and an average AUC of 0.7182 when using only 2% of the labeled data, achieving results superior to previous approaches on semi-supervised chest radiograph classification.