Calderon-Ramirez Saul, Yang Shengxiang, Moemeni Armaghan, Colreavy-Donnelly Simon, Elizondo David A, Oala Luis, Rodriguez-Capitan Jorge, Jimenez-Navarro Manuel, Lopez-Rubio Ezequiel, Molina-Cabello Miguel A
School of Computer Science and InformaticsDe Montfort University Leicester LE1 9BH U.K.
Instituto Tecnologico de Costa Rica Cartago 30101 Costa Rica.
IEEE Access. 2021 Jun 2;9:85442-85454. doi: 10.1109/ACCESS.2021.3085418. eCollection 2021.
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.
在这项工作中，我们实现了一个基于胸部X光图像的COVID-19感染检测系统，并进行不确定性估计。不确定性估计对于医学应用中计算机辅助诊断工具的安全使用至关重要。具有高不确定性的模型估计应由训练有素的放射科医生仔细分析。我们旨在通过MixMatch半监督框架使用未标记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、蒙特卡洛随机失活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。与大多数以前使用的指标不同，该指标具有统计相关性，以前的指标通常忽略不确定性估计的分布。我们的测试结果表明，使用未标记数据时，不确定性估计有显著改善。使用蒙特卡洛随机失活方法可获得最佳结果。
