In this work we implement a COVID-19 infection detection system based on chest X-ray images with uncertainty estimation. Uncertainty estimation is vital for safe usage of computer aided diagnosis tools in medical applications. Model estimations with high uncertainty should be carefully analyzed by a trained radiologist. We aim to improve uncertainty estimations using unlabelled data through the MixMatch semi-supervised framework. We test popular uncertainty estimation approaches, comprising Softmax scores, Monte-Carlo dropout and deterministic uncertainty quantification. To compare the reliability of the uncertainty estimates, we propose the usage of the Jensen-Shannon distance between the uncertainty distributions of correct and incorrect estimations. This metric is statistically relevant, unlike most previously used metrics, which often ignore the distribution of the uncertainty estimations. Our test results show a significant improvement in uncertainty estimates when using unlabelled data. The best results are obtained with the use of the Monte Carlo dropout method.

中文翻译：

---

通过半监督深度学习改进使用胸部 X 射线图像进行 COVID-19 检测的不确定性估计


在这项工作中，我们实现了一种基于胸部 X 射线图像和不确定性估计的 COVID-19 感染检测系统。不确定性估计对于在医疗应用中安全使用计算机辅助诊断工具至关重要。具有高不确定性的模型估计应由经过培训的放射科医生仔细分析。我们的目标是通过 MixMatch 半监督框架使用未标记的数据来改进不确定性估计。我们测试了流行的不确定性估计方法，包括 Softmax 分数、蒙特卡罗 dropout 和确定性不确定性量化。为了比较不确定性估计的可靠性，我们建议使用正确和错误估计的不确定性分布之间的 Jensen-Shannon 距离。该指标具有统计相关性，与以前使用的大多数指标不同，后者通常忽略不确定性估计的分布。我们的测试结果表明，使用未标记的数据时，不确定性估计有显着改善。使用蒙特卡罗 dropout 方法可以获得最佳结果。