-
目前在全球多国蔓延的新型冠状病毒肺炎(corona virus disease 2019,COVID-19),其病毒属于β属冠状病毒[1]。胸部CT 对COVID-19的诊断具有较高价值[2-3]。根据《新型冠状病毒感染的肺炎诊疗方案(试行第五版)》[4]可将患者临床分型分为轻型、普通型、重型和危重型。COVID-19病死者多为重症(重型、危重型)患者,因此,对普通型患者临床转归的研究就显得尤为重要。人工智能(artificial intelligence,AI)技术强大的数据分析和特征识别能力可为影像医师提供快速有效的帮助。本研究基于深度学习的AI技术对42例不同临床转归的普通型COVID-19患者的胸部CT资料进行回顾性分析,以提高对COVID-19转归的影像认识。
-
由表1可知,A、B2组患者的性别差异无统计学意义(χ2=0.016,P=1.000),B组患者的年龄(t=5.64,P<0.001)和中位年龄(Z=4.261,P<0.001)均高于A组,且差异有统计学意义。
组别 年龄(岁) 性别(例, %) 感染肺叶病灶分布(例, %) $ \bar x\pm s $ M(P25,P75) 范围 男性 女性 双肺 左肺 右肺 无病灶 A组(n=29) 41.17±13.66 41.0(32.5, 51.5) 17个月~70 14(48.3) 15(51.7) 23(79.3) 2(6.9) 2(6.9) 2(6.9) B组(n=13) 65.62±11.24 67.0(56.5, 72.5) 45~86 6(46.2) 7(53.8) 13(100.0) 0(0.0) 0(0.0) 0(0.0) 检验值 t=5.64 Z=4.261 χ2=0.016 Fisher's确切概率法 P值 <0.001 <0.001 1.000 0.418 注:表中,A组:未转为重症的COVID-19患者;B组:转为重症的COVID-19患者。COVID-19:新型冠状病毒肺炎 表 1 42例COVID-19患者的一般资料
Table 1. General information of 42 patients with COVID-19
由表2可知,B组患者感染肺叶数以及各肺叶感染体积占比(各肺叶感染体积占相应肺叶总体积的百分比)、总感染体积占比(总感染体积占总肺叶体积的百分比)均高于A组,且差异有统计学意义(Z=2.505~3.605,均P<0.05),以双肺下叶感染较多,右肺中叶较少(表1、2)。
组别 感染肺叶数(个) 感染体积占比(%) 右肺上叶 右肺中叶 右肺下叶 左肺上叶 左肺下叶 总感染体积 A组(n=29) 5.0(2.0, 5.0) 0.50(0.00, 2.60) 0.14(0.00, 2.58) 0.83(0.17, 6.10) 0.34(0.02, 3.07) 1.48(0.11, 5.44) 1.66(0.53, 4.91) B组(n=13) 5.0(5.0, 5.0) 8.63(1.43, 40.65) 2.60(0.61, 9.18) 22.18(1.82, 44.08) 6.40(1.99, 14.84) 24.20(3.29, 52.93) 15.00(6.79, 24.28) Z值 2.511 2.908 2.329 2.505 3.202 3.227 3.605 P值 0.012 0.004 0.020 0.012 0.001 0.001 0.001 注:表中,A组:未转为重症的COVID-19患者;B组:转为重症的COVID-19患者。COVID-19:新型冠状病毒肺炎 表 2 2组COVID-19患者感染肺叶数和各肺叶感染体积占比的比较[M(P25,P75)]
Table 2. Statistical table of the number of infected pulmonary lobes and the proportion of infected pulmonary lobes in 2 groups of COVID-19 (M (P25, P75))
2组患者的肺部总体积差异无统计学意义(Z=1.456,P=0.146);B组患者右肺上叶、中叶、下叶,左肺上叶、下叶感染体积及双肺总感染体积均高于A组,且差异有统计学意义(Z=2.301~3.254,均P<0.05)(表3)。B组患者在不同CT值阈值范围内的肺部感染体积占比均高于A组患者,且差异有统计学意义(Z=3.115~3.578,均P<0.05)(表4)。
组别 感染体积 总感染体积 肺部总体积 右肺上叶 右肺中叶 右肺下叶 左肺上叶 左肺下叶 A组(n=29) 5.83
(0.12, 35.62)0.21
(0.00, 11.55)16.18
(1.50, 67.20)5.10
(0.19, 26.46)8.80
(1.34, 67.99)59.00
(20.63, 283.18)4163.33
(3207.62, 5747.33)B组(n=13) 62.29
(9.43, 208.17)10.19
(3.52, 27.72)132.85
(21.27, 329.16)24.19
(18.11, 246.96)153.26
(26.22, 323.94)403.29
(244.00, 865.72)3749.35
(2509.74, 4347.69)Z值 2.956 2.312 2.301 3.254 2.889 3.088 1.456 P值 0.003 0.021 0.021 0.001 0.004 0.002 0.146 注:表中,A组:未转为重症的COVID-19患者;B组:转为重症的COVID-19患者。COVID-19:新型冠状病毒肺炎 表 3 2组COVID-19患者各肺叶感染体积的比较[M(P25,P75),cm3]
Table 3. Comparison of infection volume of each lobe in 2 groups of patients with COVID-19 (M (P25, P75), cm3)
组别 (−1000~
−570)HU(−570~
−470)HU(−470~
−370)HU(−370~
−270)HU(−270~
−170)HU(−170~
−70)HU(−70~
30)HU(30~
60)HU(60~
1000)HUA组(n=29) 0.96
(0.28, 3.54)7.98
(2.01, 30.27)8.18
(2.11, 25.31)7.82
(2.33, 30.8)7.59
(2.23, 28.66)7.40
(2.00, 27.50)5.66
(1.14, 20.59)3.97
(0.56, 15.67)1.95
(0.34, 9.70)B组(n=13) 7.93
(4.08, 15.62)37.44
(24.20, 49.31)38.82
(24.38, 56.63)40.06
(20.41, 63.06)40.66
(18.60, 66.26)42.15
(17.71, 61.83)38.32
(14.89, 50.59)35.12
(10.59, 44.9)21.26
(7.73, 30.82)Z值 3.578 3.115 3.279 3.442 3.415 3.224 3.347 3.225 3.225 P值 <0.001 0.002 0.001 0.001 0.001 0.001 0.001 0.001 0.001 注:表中,A组:未转为重症的COVID-19患者;B组:转为重症的COVID-19患者。COVID-19:新型冠状病毒肺炎 表 4 2组COVID-19患者在不同CT阈值范围的肺部感染体积占比的比较[M(P25,P75),%]
Table 4. Statistical table of infected proportion with different CT thresholds in 2 groups of COVID-19 (M (P25, P75), %)
-
CT显像结果显示,B组病灶均为双肺分布,A组有2例患者的早期胸部CT无异常,后复查出现肺炎表现;2组患者的病灶均以双肺分布的磨玻璃密度影(ground glass opacity,GGO)实变为主。A组患者CT的主要表现为以双肺或单侧肺2个及2个以上肺叶分布为主、呈大小不等的片状GGO和实变影,部分较淡薄,病灶形态多不规则,部分呈扇形、楔形、类圆形病灶(图1、2),胸膜下、肺叶外周带分布多见,右肺中叶受累相对少见,亦可仅见于一个肺叶(图1中C、D);均未见胸腔积液及纵隔、肺门淋巴结肿大。B组均呈现出以双肺胸膜下及肺野外周带分布为主的GGO(图3、4中A、B)和实变影,由于患者机体抵抗力不同,病变进展为重型、危重型,肺泡内渗出增多,密度增高,部分形成肺实变,病变范围扩大,表现为双肺分布的斑片状、大片状实变和GGO,以胸膜下为主,在后期修复愈合过程中,纤维成分形成多发纤维条索(图4中C)。
图 1 普通型新型冠状病毒肺炎未转归重症患者的胸部CT(A、C、E、G)及其AI病灶识别勾画图像(B、D、F、H)
Figure 1. Chest CT(A, C, E, G)and artificial intelligence focus recognition delineation(B, D, F, H)images of COVID-19 common type that were not converted to severe case
图 2 普通型新型冠状病毒肺炎未转归重症患者(女性,24岁)的胸部CT及其AI病灶识别勾画图像
Figure 2. Chest CT and artificial intelligence focus recognition delineation images of COVID-19 common type that was not converted to severe case(female,24 years old)
基于深度学习的新型冠状病毒肺炎转归胸部CT评价
Chest CT evaluation of COVID-19 outcome based on deep learning
-
摘要:
目的 分析基于深度学习的新型冠状病毒肺炎(COVID-19)不同临床转归患者胸部CT的差异,以提高对COVID-19转归的影像认识。 方法 回顾性分析2020年1月25日至3月29日来自内蒙古自治区COVID-19病例库的42例COVID-19患者(临床分型为普通型)的胸部CT资料,其中,男性20例、女性22例,年龄17个月~86岁[(48.74±17.18)岁]。根据是否转为重症(重型或危重型)将患者分为未转为重症的A组(n=29)和转为重症的B组(n=13),比较2组患者年龄、性别及基于深度学习的胸部CT表现,评价感染肺叶病灶分布,累及肺叶侧别、数目,感染肺叶病灶体积,密度(CT值)和感染肺叶病灶体积占比等资料的差异。计量资料的比较采用两独立样本t检验、Mann-Whitney U非参数检验;计数资料的比较采用卡方检验或Fisher's确切概率法。 结果 2组患者的性别差异无统计学意义(χ2=0.016,P=1.000)。B组患者的年龄高于A组[(65.62±11.24)岁对(41.17±13.66)岁 ],且差异有统计学意义(t=5.64,P<0.001)。B组患者感染肺叶数以及各肺叶感染体积占比、总感染体积占比均高于A组,且差异有统计学意义(Z=2.505~3.605,均P<0.05)。2组患者肺部总体积差异无统计学意义(Z=1.456,P=0.146),B组患者各肺叶感染体积及双肺总感染体积均高于A组,且差异有统计学意义(Z=2.301~3.254,均P<0.05);B组患者在各CT阈值范围内的肺部感染体积占比均高于A组,且差异有统计学意义(Z=3.115~3.578,均P<0.05)。胸部CT和人工智能病灶识别图的图像结果显示,病灶均以磨玻璃密度影、实变为主,双肺下叶感染较多,右肺中叶较少。 结论 转为重症的COVID-19患者的胸部CT明显有别于未转为重症的患者。基于深度学习的人工智能可尽早评估有重症转归倾向的患者,有助于COVID-19重症率的控制。 -
关键词:
- 新型冠状病毒肺炎 /
- 深度学习 /
- 人工智能 /
- 体层摄影术,X线计算机 /
- 临床转归
Abstract:Objective To analyze variations in the chest CT of different clinical outcomes of corona virus disease 2019 (COVID-19) based on deep learning and improve the understanding on COVID-19 imaging. Methods The chest CT of 42 cases (the clinical classification was common type) of COVID-19 in Inner Mongolia Autonomous Region collected from January 25, 2020 to March 29, 2020 were examined. The cases included 20 males and 22 females, with ages ranging from 17 months to 86 (48.74±17.18) years. The patients were divided into group A, which included those did not progress to severe disease (n=29), and group B, which included those who progressed to severe/critical disease (n=13). Differences in age, gender, lesion distribution, sides, number, volume, density (CT value), and proportion of lesion volume as detected by chest CT were compared between the two groups by deep learning. Two independent samples t test and Mann-Whitney U nonparametric tests were used to compare measurement data, and the χ2 and Fisher's exact tests were used to compare count data. Results No statistical difference in gender was noted between the two groups (χ2=0.016, P=1.000). The mean age of group B was higher than that of group A (65.62±11.24 years vs. 41.17±13.66 years), and a statistical difference was observed in each group (t=5.64, P<0.001). The number of infected pulmonary lobes, proportion of infection volume in each pulmonary lobe, and proportion of total infection volume were higher in group B than in group A, and a statistical difference was noted in each group (Z=2.505−3.605, all P<0.05). No statistical difference in total lung volume between the two groups was observed (Z=1.456, P=0.146). The size of infection in each lobe and the total volume of infection in both lungs in group B were greater than those in group A, and a statistical difference was found in each group (Z=2.301−3.254, all P<0.05). The proportion of lesions in group B within the threshold range of all CT values was higher than that in group A, and a statistical difference was observed in each group (Z=3.115−3.578, all P<0.05). The results of chest CT and artificial intelligence lesion recognition mapping revealed that lesions in serious cases are mainly characterized with ground glass opacity and consolidation. Moreover, the lesions frequently involved the lower lobes of the lungs and less commonly affected the middle lobe of the right lung. Conclusions The chest CT of patients with COVID-19 who progressed to severe disease and those who did not showed significant differences. Artificial intelligence based on deep learning can assess patients with a tendency to progress to severe/critical disease early and contribute to the improved management of severe COVID-19. -
Key words:
- COVID-2019 /
- Deep learning /
- Artificial intelligence /
- Tomography, X-ray computed /
- Clinical outcome
-
表 1 42例COVID-19患者的一般资料
Table 1. General information of 42 patients with COVID-19
组别 年龄(岁) 性别(例, %) 感染肺叶病灶分布(例, %) $ \bar x\pm s $ M(P25,P75) 范围 男性 女性 双肺 左肺 右肺 无病灶 A组(n=29) 41.17±13.66 41.0(32.5, 51.5) 17个月~70 14(48.3) 15(51.7) 23(79.3) 2(6.9) 2(6.9) 2(6.9) B组(n=13) 65.62±11.24 67.0(56.5, 72.5) 45~86 6(46.2) 7(53.8) 13(100.0) 0(0.0) 0(0.0) 0(0.0) 检验值 t=5.64 Z=4.261 χ2=0.016 Fisher's确切概率法 P值 <0.001 <0.001 1.000 0.418 注:表中,A组:未转为重症的COVID-19患者;B组:转为重症的COVID-19患者。COVID-19:新型冠状病毒肺炎 表 2 2组COVID-19患者感染肺叶数和各肺叶感染体积占比的比较[M(P25,P75)]
Table 2. Statistical table of the number of infected pulmonary lobes and the proportion of infected pulmonary lobes in 2 groups of COVID-19 (M (P25, P75))
组别 感染肺叶数(个) 感染体积占比(%) 右肺上叶 右肺中叶 右肺下叶 左肺上叶 左肺下叶 总感染体积 A组(n=29) 5.0(2.0, 5.0) 0.50(0.00, 2.60) 0.14(0.00, 2.58) 0.83(0.17, 6.10) 0.34(0.02, 3.07) 1.48(0.11, 5.44) 1.66(0.53, 4.91) B组(n=13) 5.0(5.0, 5.0) 8.63(1.43, 40.65) 2.60(0.61, 9.18) 22.18(1.82, 44.08) 6.40(1.99, 14.84) 24.20(3.29, 52.93) 15.00(6.79, 24.28) Z值 2.511 2.908 2.329 2.505 3.202 3.227 3.605 P值 0.012 0.004 0.020 0.012 0.001 0.001 0.001 注:表中,A组:未转为重症的COVID-19患者;B组:转为重症的COVID-19患者。COVID-19:新型冠状病毒肺炎 表 3 2组COVID-19患者各肺叶感染体积的比较[M(P25,P75),cm3]
Table 3. Comparison of infection volume of each lobe in 2 groups of patients with COVID-19 (M (P25, P75), cm3)
组别 感染体积 总感染体积 肺部总体积 右肺上叶 右肺中叶 右肺下叶 左肺上叶 左肺下叶 A组(n=29) 5.83
(0.12, 35.62)0.21
(0.00, 11.55)16.18
(1.50, 67.20)5.10
(0.19, 26.46)8.80
(1.34, 67.99)59.00
(20.63, 283.18)4163.33
(3207.62, 5747.33)B组(n=13) 62.29
(9.43, 208.17)10.19
(3.52, 27.72)132.85
(21.27, 329.16)24.19
(18.11, 246.96)153.26
(26.22, 323.94)403.29
(244.00, 865.72)3749.35
(2509.74, 4347.69)Z值 2.956 2.312 2.301 3.254 2.889 3.088 1.456 P值 0.003 0.021 0.021 0.001 0.004 0.002 0.146 注:表中,A组:未转为重症的COVID-19患者;B组:转为重症的COVID-19患者。COVID-19:新型冠状病毒肺炎 表 4 2组COVID-19患者在不同CT阈值范围的肺部感染体积占比的比较[M(P25,P75),%]
Table 4. Statistical table of infected proportion with different CT thresholds in 2 groups of COVID-19 (M (P25, P75), %)
组别 (−1000~
−570)HU(−570~
−470)HU(−470~
−370)HU(−370~
−270)HU(−270~
−170)HU(−170~
−70)HU(−70~
30)HU(30~
60)HU(60~
1000)HUA组(n=29) 0.96
(0.28, 3.54)7.98
(2.01, 30.27)8.18
(2.11, 25.31)7.82
(2.33, 30.8)7.59
(2.23, 28.66)7.40
(2.00, 27.50)5.66
(1.14, 20.59)3.97
(0.56, 15.67)1.95
(0.34, 9.70)B组(n=13) 7.93
(4.08, 15.62)37.44
(24.20, 49.31)38.82
(24.38, 56.63)40.06
(20.41, 63.06)40.66
(18.60, 66.26)42.15
(17.71, 61.83)38.32
(14.89, 50.59)35.12
(10.59, 44.9)21.26
(7.73, 30.82)Z值 3.578 3.115 3.279 3.442 3.415 3.224 3.347 3.225 3.225 P值 <0.001 0.002 0.001 0.001 0.001 0.001 0.001 0.001 0.001 注:表中,A组:未转为重症的COVID-19患者;B组:转为重症的COVID-19患者。COVID-19:新型冠状病毒肺炎 -
[1] Zhu N, Zhang DY, Wang WL, et al. A novel coronavirus from patients with pneumonia in china, 2019[J]. N Engl J Med, 2020, 382(8): 727−733. DOI: 10.1056/NEJMoa2001017. [2] 中华医学会放射学分会. 新型冠状病毒肺炎的放射学诊断: 中华医学会放射学分会专家推荐意见(第一版)[J/OL]. 中华放射学杂志, 2020, 54(00): E001−E001[2020-04-28]. rs.yiigle.com/yufabiao/1180115.htm. DOI: 10.3760/cma.j.issn.1005-1201.2020.0001.
Chinese Society of Imaging Technology. Infection prevention in radiological examination of novel coronavirus pneumonia: expert recommendation from the Chinese Society of Imaging Technology (First edition)[J/OL]. Chin J Radiol, 2020, 54 (00): E001−E001 [2020-04-28]. rs.yiigle.com/yufabiao/1180115.htm. DOI: 10.3760/cma.j.issn.1005-1201.2020.0001.[3] Chung M, Bernheim A, Mei XY, et al. CT Imaging features of 2019 novel coronavirus (2019-nCoV)[J]. Radiology, 2020, 295(1): 202−207. DOI: 10.1148/radiol.2020200230. [4] 中华人民共和国国家卫生健康委员会. 新型冠状病毒感染的肺炎诊疗方案(试行第五版)[EB/OL]. (2020-02-04)[2020-04-28]. http://www.nhc.gov.cn/yzygj/s7653p/202002/3b09b894ac9b4204a79db5b8912d4440/files/7260301a393845fc87fcf6dd52965ecb.pdf.
National Health Commission of the People's Republic of China. Diagnosis and treatment plan for pneumonia for novel coronavirus-infected pneumonia (trial Fifth edition)[EB/OL]. (2020-02-04)[2020-04-28]. http://www.nhc.gov.cn/yzygj/s7653p/202002/3b09b894ac9b4204a79db5b8912d4440/files/7260301a393845fc87fcf6dd52965ecb.pdf.[5] Li Q, Guan XH, Wu P, et al. Early transmission dynamics in Wuhan, China, of novel coronavirus-infected pneumonia[J]. N Engl J Med, 2020, 382(13): 1199−1207. DOI: 10.1056/NEJMoa2001316. [6] Munster VJ, Koopmans M, van Doremalen N, et al. A novel coronavirus emerging in China—key questions for impact assessment[J]. N Engl J Med, 2020, 382(8): 692−694. DOI: 10.1056/NEJMp2000929. [7] Huang CL, Wang YM, Li XW, et al. Clinical features of patients infected with 2019 novel coronavirus in Wuhan, China[J]. Lancet, 2020, 395(10223): 497−506. DOI: 10.1016/S0140-6736(20)30183-5. [8] 中华人民共和国国家卫生健康委员会. 新型冠状病毒肺炎诊疗方案(试行第七版)[EB/OL]. (2020-03-04)[2020-04-28]. http://www.nhc.gov.cn/yzygj/s7653p/202003/46c9294a7dfe4cef80dc7f5912eb1989/files/ce3e6945832a438eaae415350a8ce964.pdf.
National Health Commission of the People's Republic of China. COVID-19 diagnosis and treatment plan (trial Seventh edition)[EB/OL]. (2020-03-04)[2020-04-28]. http://www.nhc.gov.cn/yzygj/s7653p/202003/46c9294a7dfe4cef80dc7f5912eb1989/files/ce3e6945832a438eaae415350a8ce964.pdf.[9] Ai T, Yang ZL, Hou HY, et al. Correlation of chest CT and RT-PCR testing for coronavirus disease 2019 (COVID-19) in China: a report of 1014 cases[J]. Radiology, 2020, 296(2): E32−E40. DOI: 10.1148/radiol.2020200642. [10] Fang YC, Zhang HQ, Xie JC, et al. Sensitivity of chest CT for COVID-19: comparison to RT-PCR[J]. Radiology, 2020, 296(2): E115−E117. DOI: 10.1148/radiol.2020200432. [11] 靳英辉, 蔡林, 程真顺, 等. 新型冠状病毒(2019-nCoV)感染的肺炎诊疗快速建议指南(标准版)[J]. 解放军医学杂志, 2020, 45(1): 1−20. DOI: 10.11855/j.issn.0577-7402.2020.01.01.
Jin YH, Cai L, Cheng ZS, et al. A rapid advice guideline for the diagnosis and treatment of 2019 novel coronavirus (2019-nCoV) infected pneumonia (standard version)[J]. Med J Chin PLA, 2020, 45(1): 1−20. DOI: 10.11855/j.issn.0577-7402.2020.01.01.[12] 贾凯丽, 王雪梅. 医学影像人工智能新进展[J]. 国际放射医学核医学杂志, 2020, 44(1): 27−31. DOI: 10.3760/cma.j.issn.1673-4114.2020.01.007.
Jia KL, Wang XM. New progress in medical imaging artificial intelligence[J]. Int J Radiat Med Nucl Med, 2020, 44(1): 27−31. DOI: 10.3760/cma.j.issn.1673-4114.2020.01.007.[13] Kermany DS, Goldbaum M, Cai WJ, et al. Identifying medical diagnoses and treatable diseases by image-based deep learning[J]. Cell, 2018, 172(5): 1122−1131. DOI: 10.1016/j.cell.2018.02.010. [14] Yang S, Jiang L, Cao Z, et al. Deep learning for detecting corona virus disease 2019 (COVID-19) on highresolution computed tomography: a pilot study[J]. Ann Transl Med, 2020, 8(7): 450. DOI: 10.21037/atm.2020.03.132. [15] Nicholls JM, Poon LL, Lee KC, et al. Lung pathology of fatal severe acute respiratory syndrome[J]. Lancet, 2003, 361(9371): 1773−1778. DOI: 10.1016/s0140-6736(03)13413-7. [16] 钟琦, 李志, 沈晓勇, 等. 2019冠状病毒病(COVID-19)不同临床分型患者胸部CT影像学特征[J]. 浙江大学学报: 医学版, 2020, 49(2): 198−202. DOI: 10.3785/j.issn.1008-9292.2020.03.05.
Zhong Q, Li Z, Shen XY, et al. CT imaging features of patients with different clinical types of COVID-19[J]. J Zhejiang Univ (Med Sci), 2020, 49(2): 198−202. DOI: 10.3785/j.issn.1008-9292.2020.03.05.[17] Koo HJ, Lim S, Choe J, et al. Radiographic and CT features of viral pneumonia[J]. Radiographics, 2018, 38(3): 719−739. DOI: 10.1148/rg.2018170048. [18] 黄璐, 韩瑞, 于朋鑫, 等. 新型冠状病毒肺炎不同临床分型间CT和临床表现的相关性研究[J]. 中华放射学杂志, 2020, 54(4): 300−304. DOI: 10.3760/cma.j.cn112149-20200205-00087.
Huang L, Han R, Yu PX, et al. A correlation study of CT and clinical features of different clinical types of COVID-19[J]. Chin J Radiol, 2020, 54(4): 300−304. DOI: 10.3760/cma.j.cn112149-20200205-00087.[19] Corman VM, Landt O, Kaiser M, et al. Detection of 2019 novel coronavirus (2019-nCoV) by real-time RT-PCR[J]. Euro Surveill, 2020, 25(3): 2000045. DOI: 10.2807/1560-7917.ES.2020.25.3.2000045. [20] Lee N, Hui D, Wu A, et al. A major outbreak of severe acute respiratory syndrome in Hong Kong[J]. N Engl J Med, 2003, 348(20): 1986−1994. DOI: 10.1056/NEJMoa030685. [21] Das KM, Lee EY, AI Jawder SE, et al. Acute middle east respiratory syndrome coronavirus: temporal lung changes observed on the chest radiographs of 55 patients[J]. AJR Am J Roentgenol, 2015, 205(3): W267−274. DOI: 10.2214/AJR.15.14445.