DINO-CXR：一种基于视觉Transformer的用于胸部X光分类的自监督方法
DINO-CXR: A self supervised method based on vision transformer for chest X-ray classification
AI总结：
本文提出DINO-CXR，一种基于视觉Transformer的自监督方法，用于胸部X光分类，在肺炎和COVID-19检测中优于现有方法且所需标注数据更少。
摘要：
标注胸部X光数据集的有限可用性是医学影像方法开发中的一个重要瓶颈。自监督学习（SSL）可以通过在无标签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取得了有希望的结果，但在医学图像分析中却未得到太多关注。在这项工作中，我们提出了一种自监督方法DINO-CXR，这是对基于视觉Transformer的自监督方法DINO的一种新颖改编，用于胸部X光分类。我们进行了对比分析，以展示所提出方法在肺炎和COVID-19检测中的有效性。通过定量分析还表明，所提出的方法在准确率方面优于现有最先进的方法，并在AUC和F-1分数方面取得了可比的结果，同时所需的标注数据显著减少。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
