IEEE J Biomed Health Inform. 2020 Dec;24(12):3595-3605. doi: 10.1109/JBHI.2020.3037127. Epub 2020 Dec 4.
Currently, Coronavirus disease (COVID-19), one of the most infectious diseases in the 21st century, is diagnosed using RT-PCR testing, CT scans and/or Chest X-Ray (CXR) images. CT (Computed Tomography) scanners and RT-PCR testing are not available in most medical centers and hence in many cases CXR images become the most time/cost effective tool for assisting clinicians in making decisions. Deep learning neural networks have a great potential for building COVID-19 triage systems and detecting COVID-19 patients, especially patients with low severity. Unfortunately, current databases do not allow building such systems as they are highly heterogeneous and biased towards severe cases. This article is three-fold: (i) we demystify the high sensitivities achieved by most recent COVID-19 classification models, (ii) under a close collaboration with Hospital Universitario Clínico San Cecilio, Granada, Spain, we built COVIDGR-1.0, a homogeneous and balanced database that includes all levels of severity, from normal with Positive RT-PCR, Mild, Moderate to Severe. COVIDGR-1.0 contains 426 positive and 426 negative PA (PosteroAnterior) CXR views and (iii) we propose COVID Smart Data based Network (COVID-SDNet) methodology for improving the generalization capacity of COVID-classification models. Our approach reaches good and stable results with an accuracy of [Formula: see text], [Formula: see text], [Formula: see text] in severe, moderate and mild COVID-19 severity levels. Our approach could help in the early detection of COVID-19. COVIDGR-1.0 along with the severity level labels are available to the scientific community through this link https://dasci.es/es/transferencia/open-data/covidgr/.
目前，21 世纪传染性最强的疾病之一的冠状病毒病（COVID-19）是通过 RT-PCR 检测、CT 扫描和/或胸部 X 光（CXR）图像进行诊断的。大多数医疗中心都没有 CT（计算机断层扫描）扫描仪和 RT-PCR 检测，因此在许多情况下，CXR 图像成为协助临床医生做出决策的最具时效性和成本效益的工具。深度学习神经网络在构建 COVID-19 分诊系统和检测 COVID-19 患者，尤其是轻度患者方面具有巨大潜力。不幸的是，由于当前数据库高度异构且偏向于重症病例，因此无法构建此类系统。本文有三个方面：（i）我们揭开了大多数最近的 COVID-19 分类模型所实现的高敏感性的神秘面纱，（ii）与西班牙格拉纳达的 Hospital Universitario Clínico San Cecilio 密切合作，我们构建了 COVIDGR-1.0，这是一个同质且平衡的数据库，包括从 RT-PCR 检测阳性的正常、轻度、中度到重度的所有严重程度。COVIDGR-1.0 包含 426 张阳性和 426 张阴性 PA（前后）CXR 视图，（iii）我们提出了基于 COVID 智能数据的网络（COVID-SDNet）方法，用于提高 COVID 分类模型的泛化能力。我们的方法在严重、中度和轻度 COVID-19 严重程度水平上的准确率达到了[Formula: see text]、[Formula: see text]、[Formula: see text]，效果良好且稳定。我们的方法可以帮助早期发现 COVID-19。COVIDGR-1.0 及其严重程度标签可通过此链接 https://dasci.es/es/transferencia/open-data/covidgr/ 向科学界提供。
