[论文解读] Severity Assessment of Coronavirus Disease 2019 (COVID-19) Using Quantitative Features from Chest CT Images

Zhenyu Tang, Wei Zhao+5 more|arXiv (Cornell University)|Mar 26, 2020

COVID-19 diagnosis using AI参考文献 19被引用 149

一句话总结

本论文开发了随机森林模型，基于胸部 CT 定量特征自动将 COVID-19 的严重程度分为非重症与重症，在对 176 例患者进行 3-fold 交叉验证时，取得了较高的 AUC 和准确率。

ABSTRACT

Background: Chest computed tomography (CT) is recognized as an important tool for COVID-19 severity assessment. As the number of affected patients increase rapidly, manual severity assessment becomes a labor-intensive task, and may lead to delayed treatment. Purpose: Using machine learning method to realize automatic severity assessment (non-severe or severe) of COVID-19 based on chest CT images, and to explore the severity-related features from the resulting assessment model. Materials and Method: Chest CT images of 176 patients (age 45.3$\pm$16.5 years, 96 male and 80 female) with confirmed COVID-19 are used, from which 63 quantitative features, e.g., the infection volume/ratio of the whole lung and the volume of ground-glass opacity (GGO) regions, are calculated. A random forest (RF) model is trained to assess the severity (non-severe or severe) based on quantitative features. Importance of each quantitative feature, which reflects the correlation to the severity of COVID-19, is calculated from the RF model. Results: Using three-fold cross validation, the RF model shows promising results, i.e., 0.933 of true positive rate, 0.745 of true negative rate, 0.875 of accuracy, and 0.91 of area under receiver operating characteristic curve (AUC). The resulting importance of quantitative features shows that the volume and its ratio (with respect to the whole lung volume) of ground glass opacity (GGO) regions are highly related to the severity of COVID-19, and the quantitative features calculated from the right lung are more related to the severity assessment than those of the left lung. Conclusion: The RF based model can achieve automatic severity assessment (non-severe or severe) of COVID-19 infection, and the performance is promising. Several quantitative features, which have the potential to reflect the severity of COVID-19, were revealed.

研究动机与目标

• 推动快速、自动化的严重程度评估，以帮助 COVID-19 患者的及时治疗。
• 研究能够反映疾病严重程度的量化 CT 衍生特征。
• 基于影像特征构建并评估一个机器学习模型，以区分非重症和重症病例。

提出的方法

• 提取63个量化 CT 特征，包括全肺感染体积和磨玻璃影 (GGO) 指标。
• 训练随机森林分类器以预测严重程度（非重症 vs 重症）。
• 从 RF 模型中计算特征重要性，以揭示与严重程度相关的特征。
• 使用三折交叉验证进行评估，以报告性能指标。

实验结果

研究问题

• RQ1 定量 CT 衍生特征是否能够区分非重症和重症 COVID-19？
• RQ2 哪些 CT 特征（以及肺部左右半球的贡献）最能预测严重程度？
• RQ3 在所提供的数据集上，随机森林模型的自动严重度评估性能有多好？

主要发现

• RF 模型达到 0.933 的真正阳性率（TPR）。
• RF 模型达到 0.745 的真阴性率（TNR）。
• RF 模型达到 0.875 的总体准确率。
• RF 模型达到 0.91 的 ROC 曲线下面积（AUC）。
• 磨玻璃样影（GGO）区域的体积和体积比与严重程度有强相关。
• 来自右肺的特征对严重程度的相关性比来自左肺的特征更强。