The limited availability of labeled chest X-ray datasets is a significant bottleneck in the development of medical imaging methods. Self-supervised learning (SSL) can mitigate this problem by training models on unlabeled data. Furthermore, self-supervised pretraining has yielded promising results in visual recognition of natural images but has not been given much consideration in medical image analysis. In this work, we propose a self-supervised method, DINO-CXR, which is a novel adaptation of a self-supervised method, DINO, based on a vision transformer for chest X-ray classification. A comparative analysis is performed to show the effectiveness of the proposed method for both pneumonia and COVID-19 detection. Through a quantitative analysis, it is also shown that the proposed method outperforms state-of-the-art methods in terms of accuracy and achieves comparable results in terms of AUC and F-1 score while requiring significantly less labeled data.

翻译：标记性胸部X光数据集的有限可用性是医学影像方法发展的重大瓶颈。自监督学习（SSL）可通过在未标记数据上训练模型来缓解这一问题。此外，自监督预训练在自然图像的视觉识别中已取得显著成果，但在医学图像分析中尚未得到足够重视。本研究提出一种自监督方法DINO-CXR，这是对基于视觉Transformer的自监督方法DINO的改进，专门用于胸部X光分类。通过对比分析，展示了所提方法在肺炎和COVID-19检测中的有效性。定量分析表明，该方法在准确率上优于现有最先进方法，在AUC和F-1分数上取得可比较的结果，同时所需标记数据显著更少。