论文标题
使用胸部CT扫描和深度学习来解释Covid-19检测
Explainable COVID-19 Detection Using Chest CT Scans and Deep Learning
论文作者
论文摘要
本文探讨了在胸部CT图像上训练的深度学习模型如何可以在快速自动化的过程中诊断为Covid-19受感染者。为此，我们采用先进的深层网络架构，并使用针对每个深度体系结构量身定制的定制输入提出转移学习策略，以实现最佳性能。我们在两个CT图像数据集上进行了大量实验集，即SARS-COV-2 CT-SCAN和COVID19-CT。获得的结果表明，与以前的研究相比，我们的模型表现出色，在该研究中，我们的最佳模型获得了平均准确性，精度，灵敏度，特异性和F1得分为99.4％，99.6％，99.8％，99.6％，99.6％和99.4％的SARS-COV-2数据集；和92.9％，91.3％，93.7％，92.2％和92.5％分别在COVID19-CT数据集中。此外，我们应用两种可视化技术来为模型的预测提供视觉解释。可视化显示了来自其他肺部疾病的COVID-19的CT图像的良好分离簇，以及Covid-19相关区域的准确局部定位。
This paper explores how well deep learning models trained on chest CT images can diagnose COVID-19 infected people in a fast and automated process. To this end, we adopt advanced deep network architectures and propose a transfer learning strategy using custom-sized input tailored for each deep architecture to achieve the best performance. We conduct extensive sets of experiments on two CT image datasets, namely the SARS-CoV-2 CT-scan and the COVID19-CT. The obtained results show superior performances for our models compared with previous studies, where our best models achieve average accuracy, precision, sensitivity, specificity and F1 score of 99.4%, 99.6%, 99.8%, 99.6% and 99.4% on the SARS-CoV-2 dataset; and 92.9%, 91.3%, 93.7%, 92.2% and 92.5% on the COVID19-CT dataset, respectively. Furthermore, we apply two visualization techniques to provide visual explanations for the models' predictions. The visualizations show well-separated clusters for CT images of COVID-19 from other lung diseases, and accurate localizations of the COVID-19 associated regions.
