Value of CT findings in predicting transformation of clinical types of COVID-19

doi:10.3969/j.issn.1006-7795.2020.03.004

Abstract

Abstract: Objective To explore the value of artificial intelligence (AI) in computed tomography (CT) prediction for outcome of 2019 Coronavirus disease (COVID-19). Methods The initial and first follow-up CT imaging of 62 cases with common COVID-19 pneumonia diagnosed in Beijing Ditan Hospital, Capital Medical University from January 25 to February 17, 2020 were retrospectively analyzed. Ratio of male:female was 31:31. Based on the fact whether patients' conditions had deteriorated into severe type, all the cases were stratified into common type group (51 cases) and deteriorated type group (11cases). Differences of quantitative CT findings by AI in two groups of patients were analyzed. Results Based on initial CT, the percentage of volume of inflammatory lesions to volume of lungs in deteriorated group was 3.3% (1.6%, 7.2%), higher than that of common group. Sensitivity and specificity of diagnose for deteriorated cases reached the best diagnostic value by setting cut-off value as 2.0%. The sensitivity was 72.7%, specificity was 66.7%, and area under a receiver operating characteristic (ROC) curve was 0.744. On first follow-up CT, significant difference was observed on the change of lesion volume. Compared to common type group, percentage of lesion volume in lungs increased significantly to 10.0% (8.9%, 18.1%). The sensitivity (90.9%) and specificity (78.4%) of diagnose for deteriorated cases reached the best diagnostic value by setting cut-off value of increased percentage of lesions in lungs as 2.65%. Area under ROC was 0.896. Changes on percentage of ground glass opacity and consolidation in lesions were significantly different between the groups (P<0.05). Conclusions AI has a profound value in CT prediction for outcome of COVID-2019. It can help in early warning for severe and critical type of patients. The percentage of volume of lesions in lungs and rapidly increase may predict outcome of COVID-19.

Key words: artificial intelligence, COVID-19, tomography, X-ray computed

CLC Number:

R563.1

Lyu Zhibin, Guan Chunshuang, Yan Shuo, Chen Qiyi, Li Jingjing, Zhang Yujun, Chen Budong, Xie Ruming. Value of CT findings in predicting transformation of clinical types of COVID-19[J]. Journal of Capital Medical University, 2020, 41(3): 340-344.

0
/ / Recommend

Add to citation manager EndNote|Reference Manager|ProCite|BibTeX|RefWorks

URL: https://journal03.magtech.org.cn/Jweb_sdykdxxb/EN/10.3969/j.issn.1006-7795.2020.03.004

https://journal03.magtech.org.cn/Jweb_sdykdxxb/EN/Y2020/V41/I3/340

References

[1] 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)[2020-04-20]. http://www.nhc.gov.cn/yzygj/s7653p/202003/46c9294a7dfe4cef80dc7f5912eb1989.shtml.
[2] 萧毅, 郭佑民, 刘士远. 医学影像在新型冠状病毒肺炎诊治中的作用及思考[J/OL]. 中华放射学杂志.(2020-02-12)[2020-04-20].http://rs.yiigle.com/yufabiao/1180540.htm.
[3] 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/OL]. 中华放射学杂志.(2020-02-11)[2020-04-20].http://rs.yiigle.com/yufabiao/1180145.htm.
[4] 中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. (2020-02-08)[2020-04-20].http://rs.yiigle.com/yufabiao/1180115.htm. DOI:10.3760/cma.j.issn.1005-1201.2020.0001.
[5] 程晓光,冯素臣,夏国光,等. SARS的胸部CT早期表现[J]. 中华放射学杂志,2003,37(9):790-793.
[6] 吕志彬, 关春爽, 闫铄, 等. CT在预测新型冠状病毒肺炎临床分型转变中的价值[J/OL]. 中华放射学杂志.(2020-03-13)[2020-04-20].http://rs.yiigle.com/yufabiao/1184753.htm.
[7] Pan F,Ye T,Sun P,et al. Time course of lung changes on chest CT during recovery from 2019 novel coronavirus (COVID-19) pneumonia[J]. Radiology,2020,13:200370.
[8] Litjens G, Kooi T, Bejnordi B E, et al. A survey on deep learning in medical image analysis[J]. Med Image Anal, 2017, 42:60-88.
[9] 刘士远, 萧毅. 基于深度学习的人工智能对医学影像学的挑战和机遇[J]. 中华放射学杂志,2017,51(12):899-901.
[10] Cicero M, Bilbily A,Colak E, et al. Training and validating a deep convolutional neural network for computer-aided detection and classification of abnormalities on frontal chest radiographs[J]. Invest Radiol,2017,52(5):281-287.

[1]	Zhang Shu, Wang Kai, Yang Zihao, Qiao Zhen, Li Xiaotong, Yuan Leilei, Ai Lin. Application of ¹¹C-MET PET/CT in screening isocitric dehydrogenase and 1p/19q status in supratentorial lower-grade gliomas [J]. Journal of Capital Medical University, 2022, 43(6): 826-833.
[2]	Zhang Li, Li Bing, Tong Guansheng. Prediction of tumor histopathological grade using a modified peritoneal cancer index by ¹⁸F-FDG PET/CT(PET-PCI)in patients with pseudomyxoma peritonei [J]. Journal of Capital Medical University, 2022, 43(6): 834-839.
[3]	Geng Yiqiang, Liu Jiajin, Wu Shina, Sun Shuwei, Zhao Dong, Song Jingbin, Sun Yabing, Wang Ruimin. Evaluation of the effect of NEMA NU 2-2018 Standards in performance test of PET/CT system [J]. Journal of Capital Medical University, 2022, 43(6): 840-844.
[4]	Yang Sen, Wang Ling, Liu Peng, Jin Chaoling, Li Honglei, Fu Liping. Comparison of continuous-bed-motion and step-and-shoot acquisition modes on ¹⁸F-FDG PET/CT imaging [J]. Journal of Capital Medical University, 2022, 43(6): 854-860.
[5]	Wang Man, Hou Yaqin, Cui Bixiao, Bi Sheng, Wang Bojun, Zhang Chun, Lu Jie. Value of ^99mTc-MIBI SPECT/CT in pre-operative diagnosis of primary hyperparathyroidism [J]. Journal of Capital Medical University, 2022, 43(6): 861-866.
[6]	Luo Shiyu, Li Mei, Luo Sha, Wang Shuang, Zhang Juan, Li Meng, Nan Xiao, Xian Junfang. Application value of ¹⁸F-FDG PET/CT in differential diagnosis of choroidal melanoma and choroidal metastatic carcinoma [J]. Journal of Capital Medical University, 2022, 43(6): 867-872.
[7]	Guo Yuehong, Huang Jingwei, Chang Yuting, Yang Minfu. Value of ^{99 m}Tc-MIBI SPECT planar imaging and tomographic imaging in diagnosis of primary hyperparathyroidism [J]. Journal of Capital Medical University, 2022, 43(6): 873-879.
[8]	Xu Yang, Wang Kai, Chen Qiang, Ai Lin. Advances about molecular imaging of nuclear medicine in diagnosis and treatment of glioma [J]. Journal of Capital Medical University, 2022, 43(6): 880-885.
[9]	Lyu Han, Zhao Pengfei, Yin Hongxia, Wang Zhenchang. The innovation and application of key technologies in the otological radiology——The Second Prize of 2020 National Science and Technology Progress [J]. Journal of Capital Medical University, 2022, 43(1): 13-16.
[10]	Wang Li, Shi Zhao, Kong Xiang, Yang Liu, Liu Ya, Luo Song, Zhang Longjiang. Association between A1 segment dysplasia, bifurcation angles of anterior cerebral artery and the formation of anterior communicating aneurysms [J]. Journal of Capital Medical University, 2022, 43(1): 61-66.
[11]	Sun Penghui, Li Yingying, Liu Xin, Jia Xuejia, Jia Xiuqin, Yang Qi. Prediction on neurological deterioration based on imaging features in patients with stroke-associated pneumonia [J]. Journal of Capital Medical University, 2022, 43(1): 74-81.
[12]	Wang Yumei, Wang Yan, Zhou Yimin, Xu Shanshan, Yang Yanlin, Zhang Linlin, Zhou Jianxin. The feasibility of positive end-expiratory pressure selection based on prolonged expiration in the model of acute respiratory distress syndrome [J]. Journal of Capital Medical University, 2021, 42(6): 903-908.
[13]	Guo Xiaochuan, Zhang Weijing, Wang Bin, Wang Weixia, Huang Lefu, Cao Baoping, Zhong Kaili. The efficacy and prognostic value of maximum standard uptake on baseline ¹⁸ F-FDG PET/CT in B-cell non-Hodgkin's lymphoma [J]. Journal of Capital Medical University, 2021, 42(5): 829-835.
[14]	Li Xue, Ning Yanzhe, Jia Hongxiao. Identification and intervention strategies for anxiety with traditional Chinese medicine during COVID-19 pneumonia pandemics [J]. Journal of Capital Medical University, 2021, 42(3): 399-403.
[15]	Liu Shanshan, Chen Xu, Li Yaqiong, Yuan Xiaofei, Yu Hongye, Fang Meng. Investigation of depression and anxiety and their influencing factors among adolescents in Beijing during the coronavirus disease 2019 epidemic [J]. Journal of Capital Medical University, 2021, 42(3): 412-417.