Using Artificial Intelligence to Detect COVID-19 and Community-acquired Pneumonia Based on Pulmonary CT: Evaluation of the Diagnostic Accuracy
Using Artificial Intelligence to Detect COVID-19 and Community-acquired Pneumonia Based on Pulmonary CT: Evaluation of the Diagnostic Accuracy
复制标题
DOI：
10.1148/radiol.2020200905
复制
发表时间：
2020-08-01
期刊：
影响因子：
19.7
通讯作者：
Xia, Jun
中科院分区：
文献类型：
--
作者：
Li, Lin;Qin, Lixin;Xia, Jun
背景：自2020年初以来，2019冠状病毒病（COVID-19）在全球广泛传播。开发新型冠状病毒肺炎的胸部CT自动准确检测技术是迫切需要的。目的：研制新型冠状病毒肺炎胸部CT全自动检测框架并评价其性能。材料与方法：在这项回顾性的多中心研究中，我们开发了一种深度学习模型，即COVID-19检测神经网络（COVNet），用于提取胸部容积CT扫描的视觉特征，用于检测COVID-19。包括社区获得性肺炎（CAP）和其他非肺炎异常的CT扫描，以检验模型的稳健性。这些数据集是在2016年8月至2020年2月期间从六家医院收集的。诊断性能评估的面积下的接受者工作特征曲线，敏感性和特异性。结果：收集的数据集包括3322例患者的4352次胸部CT扫描。患者平均年龄（+/-标准差）为49岁+/- 15岁，男性略多于女性（分别为1838 vs 1484， P = 0.29）。独立测试集检测COVID-19的单次扫描灵敏度和特异度分别为90%（95%置信区间[CI]: 83%、94%；127次扫描114次）和96% （95% CI: 93%、98%；307次扫描294次），受试者工作特征曲线下面积为0.96 (P
Background: Coronavirus disease 2019 (COVID-19) has widely spread all over the world since the beginning of 2020. It is desirable to develop automatic and accurate detection of COVID-19 using chest CT.Purpose: To develop a fully automatic framework to detect COVID-19 using chest CT and evaluate its performance.Materials and Methods: In this retrospective and multicenter study, a deep learning model, the COVID-19 detection neural network (COVNet), was developed to extract visual features from volumetric chest CT scans for the detection of COVID-19. CT scans of community-acquired pneumonia (CAP) and other non-pneumonia abnormalities were included to test the robustness of the model. The datasets were collected from six hospitals between August 2016 and February 2020. Diagnostic performance was assessed with the area under the receiver operating characteristic curve, sensitivity, and specificity.Results: The collected dataset consisted of 4352 chest CT scans from 3322 patients. The average patient age (+/- standard deviation) was 49 years +/- 15, and there were slightly more men than women (1838 vs 1484, respectively; P =.29). The per-scan sensitivity and specificity for detecting COVID-19 in the independent test set was 90% (95% confidence interval [CI]: 83%, 94%; 114 of 127 scans) and 96% (95% CI: 93%, 98%; 294 of 307 scans), respectively, with an area under the receiver operating characteristic curve of 0.96 (P