目的: 探讨人工智能(AI)在不同临床分型新型冠状病毒肺炎CT影像定量评价中的应用价值。方法: 以2021年10月到2022年6月间进行胸部CT检查的169例COVID-19患者为研究对象,并分为重症组14例和非重症组155例。收集并回顾性分析患者的一般资料及影像学信息,并在“新冠肺炎CT影像AI定性辅助诊断系统”的辅助下测量并计算各研究对象的病变体积分数、磨玻璃密度影(ground-glass opacities,GGO)体积分数、实变影体积分数、GGO+实变影体积分数以及铺路石征体积分数。采用Mann-Whitney U检验的方法进行两组数据的比较;采用受试者工作特征曲线(ROC)评估上述指标对重症型患者的诊断效能。结果: 两组研究对象的病变体积分数和GGO体积分数差异具有统计学意义(P＜0.05),而两组实变影体积分数、GGO+实变影体积分数以及铺路石征体积分数的差异无统计学意义(P＞0.05)。病变体积分数和GGO体积分数进行COVID-19临床分型的敏感度分别为1.000、0.600,特异度分别为0.822、0.923 。结论: AI辅助下测量的病变体积分数和GGO体积分数是进行COVID-19临床分型的敏感指标。
Objective: To explore the application value of artificial intelligence (AI) in quantitative evaluation of CT images of different clinical types of COVID-19. Methods: A total of 169 patients with COVID-19 who underwent chest CT examination between October 2021 and June 2022 were included in the study, and were divided into a severe group of 14 cases and a non-severe group of 155 cases. The general data and imaging information of the COVID-19 patients were collected and analyzed retrospectively. The lesion volume fraction, GGO volume fraction, consolidation volume fraction, GGO + consolidation volume fraction and crazy-paving pattern volume fraction were measured and calculated with the assistance of the “AI qualitative auxiliary diagnosis system for CT images of COVID-19” provided by BIOMIND. Mann-whitney U test was used to compare the data of the two groups. The receiver operating characteristic curve (ROC) was used to evaluate the diagnostic efficacy of the above indexes in severe patients. Results: There were significant differences in lesion volume fraction and GGO volume fraction between the two groups (P＜0.05). However, there was no significant difference in the volume fraction of consolidation, GGO + consolidation and crazy-paving pattern (P＞0.05). The sensitivity of lesion volume fraction and GGO volume fraction for clinical classification of COVID-19 was 1 and 0.6, and the specificity was 0.822 and 0.923, respectively. Conclusion: The lesion volume fraction and GGO volume fraction calculated with the assistance of AI are sensitive indicators for clinical classification of COVID-19.
[1] Zhu N, Zhang D, Wang W, et al. A novel coronavirus from patients with pneumonia in China, 2019[J]. N Engl J Med, 2020, 382(8):727-733.
[2] Ai T, Yang Z, Hou H, 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):32-40.
[3] Chung M, Bernheim A, Mei X, et al. CT imaging features of 2019 novel coronavirus (2019-nCoV)[J]. Radiology, 2020,295(1):202-207.
[4] Gieraerts C, Dangis A, Janssen L, et al. Prognostic value and reproducibility of AI-assisted analysis of lung involvement in COVID-19 on low-dose submillisievert chest CT: sample size implications for clinical trials[J]. Radiol Cardiothorac Imaging, 2020, 2(5):200441.
[5] Cui J, Li F, Shi ZL. Origin and evolution of pathogenic coronaviruses[J]. Nat Rev Microbiol, 2019, 17(3):181-192.
[6] Khan M, Adil SF, Alkhathlan HZ, et al. COVID-19: A global challenge with old history, epidemiology and progress so far[J]. Molecules, 2020, 26(1):39.
[7] Li Q, Guan X, 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.
[8] Liu C, Cai J, Zhang M, et al. Clinical characteristics and ct imaging features of COVID-19 on admission: a retrospective study[J]. Curr Med Imaging, 2021, 17(11):1324-1329.
[9] 史河水, 韩小雨, 樊艳青, 等. 新型冠状病毒(2019-nCoV)感染的肺炎临床特征及影像学表现[J]. 临床放射学杂志, 2020, 39(1):8-11.
[10] 蒋潘虹, 阮嘉雯, 俞慕华, 等. 新型冠状病毒(SARS-CoV-2)变异的研究进展[J]. 中国人兽共患病学报, 2022, 38(2):157-164.
[11] 芦鸿曦, 刘刚, 陈歆. 世界卫生组织关注的新型冠状病毒变异株病毒学特征分析[J]. 新发传染病电子杂志, 2022, 7(1):88-91.
[12] 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]. 中华放射学杂志, 2020, 54(4):279-285.
[13] Chen Q, Luo L. Manual severity evaluation methods for novel coronavirus pneumonia based on computed tomography imaging[J]. Radiol Infect Dis, 2021, 8:158-67.
[14] Yin X, Min X, Nan Y, et al. Assessment of the severity of coronavirus disease: quantitative computed tomography parameters versus semiquantitative visual score[J]. Korean J Radiol, 2020, 21(8):998-1006.
[15] Pan Y, Guan H, Zhou S, et al. Initial ct findings and temporal changes in patients with the novel coronavirus pneumonia (2019-nCoV): a study of 63 patients in Wuhan, China[J]. Eur Radiol, 2020, 30(6):3306-3309.
