Imaging Study of COVID-19 Patients with Diabetes Mellitus by Computed Tomograpgh Quantitative Indicators Based on Deep Learning
-
摘要: 目的:探讨基于深度学习的CT定量指标对糖尿病合并新型冠状病毒感染(COVID-19)患者肺部感染的影像学特征分析。资料与方法:回顾性纳入2022年12月至2023年1月首都医科大学附属北京世纪坛医院感染科收治的COVID-19患者的临床及影像学数据,根据患者的糖尿病史分为糖尿病组及非糖尿病组,通过单因素分析两组的临床及CT定量影像学特征。结果:共纳入112例COVID-19患者,年龄26~95岁,平均(70.4±14.4)岁,女性占比44.6%(50/112例)。在临床方面,糖尿病组的C反应蛋白水平明显升高。在定量指标方面,糖尿病组患者的全肺及左肺病灶数目、病灶体积、病灶占比更大,糖尿病组的纵隔淋巴结数目更多;此外,糖尿病组患者的磨玻璃病灶及实性病灶体积更大,其磨玻璃实性病灶体积比更小。在影像学征象方面,糖尿病组患者的病灶形态呈大片状、束带状比例更高,其存在晕征、空气支气管征、空气潴留征、马赛克灌注及胸膜下黑带的比例更高。结论:糖尿病合并COVID-19患者的肺部病变具有相对的特征性,基于深度学习的CT定量指标显示糖尿病组的COVID-19患者肺部受累的病变范围更大、程度更重,其实性病灶成分占比相对增加。Abstract: Objective: To investigate the imaging characteristics of coronavirus disease 2019 (COVID-19) patients with diabetes mellitus using deep learning-based quantitative computed tomograpgh (CT) indicators. Materials and methods: The clinical and imaging data of 112 COVID-19 patients admitted to the Department of Infection, Beijing Shijitan Hospital, Capital Medical University, from December 2022 to January 2023 were retrospectively collected. The patients were divided into diabetic and non-diabetic groups according to their diabetes history, and the clinical and quantitative CT imaging characteristics of the two groups were analyzed using univariate analysis. Results: A total of 112 patients with COVID-19, aged 26-95 years (mean, (70.4±14.4) years), were included in the study, and 44.6% (50/112 cases) were female. In terms of clinical features, C-reactive protein levels were significantly higher in the diabetic group. In terms of CT quantitative indicators, patients in the diabetic group had higher number of whole lung and left lung lesions, lesion volume, and mediastinal lymph nodes than patients in the non-diabetic group. In addition, patients in the diabetic group had a larger volume of ground glass opacity and solid opacity, and patients in the diabetic group had a smaller volume ratio of ground glass opacity and solid opacity in terms of imaging signs, patients in the diabetic group had a higher proportion of lesions with large patchy and banded patterns, and they had a higher proportion of halo signs, air bronchial signs, air trapping signs, mosaic perfusion signs, and subpleural black bands. Conclusion: Pulmonary lesions in patients with diabetes combined with COVID-19 have characteristic features, and deep learning-based quantitative CT indicators, particularly the solid opacity observed in the lungs, can provide valuable information on the extent and severity of lesions in these patients.
-
Keywords:
- deep learning /
- chest CT /
- coronavirus disease 2019 /
- diabetes mellitus
-
-
图 1 糖尿病合并COVID-19患者的胸部CT病灶征象
患者,男,82岁,发热、咳嗽、咳痰3日就诊,既往合并糖尿病病史,就诊时C反应蛋白为82.61 mg/L、淋巴细胞百分比10.30%、中性粒细胞百分比为85.10%。(a)~(c)显示了基于深度学习的CT定量软件对病灶的划分;(d)~(f)显示了患者胸部CT病灶呈斑片状、大片状、束带状分布,可见马赛克灌注((d)星号)、铺路石征((d)箭头)、胸膜下黑带((e)箭头)及胸膜凹陷征((f)箭头)。
Figure 1. Chest CT lesion signs in COVID-19 patients with diabetes mellitus
表 1 糖尿病合并COVID-19患者的临床资料
Table 1 Clinical information of COVID-19 patients with diabetes mellitus
临床指标 组别 统计检验 糖尿病组(39例) 非糖尿病组(73例) $Z/\chi ^2 $ P 年龄/岁($M(Q_1,Q_3)$) 73.0(66.0,84.0) 70.0(62.0,79.5) -1.607 0.108 性别(男,例(%)) 25(64.1) 37(50.7) 1.852 0.174 发病时间/天($M(Q_1,Q_3)$) 7(5.0,10.0) 7(5.5,10.0) -1.122 0.262 临床症状/例(%) 发热 39(100.0) 73(100.0) - - 喘憋 8(20.5) 14(19.2) 0.029 0.865 咳嗽 36(92.3) 67(91.8) - 1.000 咳痰 20(51.3) 37(50.7) 0.004 0.952 咽痛 16(41.0) 30(41.1) <0.001 0.994 流涕 11(28.2) 26(35.6) 0.631 0.427 肌痛 4(10.3) 4(5.5) - 0.446 实验室指标/(指标值$(M(Q_1,Q_3)$) C反应蛋白/(mg/L) 35.2(14.2,76.9) 19.9(5.6,44.5) -2.519 0.012 白细胞/(×109/L) 6.4(4.5,7.8) 6.4(5.0,8.0) -0.684 0.494 淋巴细胞百分比/% 21.0(13.3,26.4) 22.8(16.3,32.1) -1.374 0.169 单核细胞百分比/% 6.3(5.1,9.4) 7.0(5.7,9.0) -0.785 0.432 中性粒细胞百分比/% 70.1(64.3,81.5) 66.4(58.2,75.5) -1.817 0.069 淋巴细胞/(×109/L) 1.3(0.8,1.9) 1.4(1.1,1.9) -1.655 0.098 单核细胞/(×109/L) 0.4(0.3,0.6) 0.5(0.4,0.6) -1.705 0.088 中性粒细胞/(×109/L) 4.2(3.2,6.0) 4.1(3.1,5.8) -0.037 0.971 表 2 糖尿病合并COVID-19患者的CT影像定量指标情况
Table 2 Quantitative CT imaging indicators in COVID-19 patients with diabetes mellitus
病变分布 组别 统计检验 糖尿病组(39例) 非糖尿病组(73例) $Z/\chi^2 $ P 病灶数目/(个,$M(Q_1,Q_3)$) 全肺 8.0(5.0,12.0) 6.0(3.0,9.0) -2.269 0.023 左肺 4.0(2.0,6.0) 2.0(2.0,4.0) -2.373 0.018 右肺 3.0(3.0,7.0) 3.0(2.0,5.0) -1.569 0.117 病灶体积/(cm3,$M(Q_1,Q_3)$) 全肺 317.3(69.9,666.4) 152.3(26.3,378.6) -2.648 0.008 左肺 133.0(24.2,320.6) 36.0(5.9,130.3) -3.387 0.001 右肺 134.2(31.8,397.6) 97.8(11.0,242.5) -1.793 0.073 病灶占比/(%,$M(Q_1,Q_3)$) 全肺 9.3(1.7,19.0) 4.1(0.6,9.5) -2.602 0.009 左肺 10.3(1.4,17.3) 2.1(0.4,6.7) -3.232 0.001 右肺 7.2(1.2,25.2) 3.8(0.6,10.3) -1.862 0.063 磨玻璃病灶体积/(cm3,$M(Q_1,Q_3)$) 254.7(62.9,487.5) 125.3(23.3,311.7) -2.483 0.013 实性病灶体积/(cm3, $M(Q_1,Q_3)$) 52.9(6.7,172.2) 18.1(2.2,53.9) -3.020 0.003 磨玻璃病灶占比/(%, $M(Q_1,Q_3)$) 82.6(73.1,91.5) 85.8(79.9,93.7) -2.180 0.029 实性病灶占比/(%, $M(Q_1,Q_3)$) 17.4(8.5,26.9) 14.2(6.3,20.1) -2.177 0.029 磨玻璃实性病灶体积比/(%,$M(Q_1,Q_3)$) 4.8(2.7,10.8) 6.0(4.0,15.0) -2.171 0.030 纵隔淋巴结/(个,$M(Q_1,Q_3)$) 2.0(1.0,3.0) 1.0(0,2.0) -3.848 <0.001 表 3 糖尿病合并COVID-19患者的胸部CT病灶征象情况
Table 3 Chest CT lesion signs in COVID-19 patients with diabetes mellitus
影像指标 组别 统计检验 糖尿病组(39例) 非糖尿病组(73例) $\chi^2 $ P 分布模式/(例(%)) 支气管血管束分布 0(0.0) 2(2.7) 2.605 0.107 胸膜下分布 3(7.7) 14(19.2) - 0.542 混合分布 36(92.3) 57(78.1) 4.062 0.044 病变形态/(例(%)) 结节状 26(66.7) 49(68.1) 0.022 0.881 斑片状 37(94.9) 70(95.9) - 1.000 大片状 29(74.4) 38(52.1) 5.261 0.022 束带状 22(56.4) 23(31.5) 6.559 0.010 特殊征象/(例(%)) 晕征 37(94.9) 54(74.0) 7.288 0.007 反晕征 18(46.2) 30(41.1) 0.266 0.606 蜂窝征 2(5.1) 4(5.5) - 1.000 铺路石征 24(61.5) 35(47.9) 1.884 0.170 空气支气管征 34(87.2) 49(67.1) 5.329 0.021 空气潴留征 18(46.2) 19(26.0) 4.655 0.031 马赛克灌注 28(71.8) 28(38.4) 11.369 0.001 胸膜下线 15(38.5) 23(31.5) 0.548 0.459 胸膜凹陷征 26(66.7) 44(60.3) 0.443 0.506 胸膜下黑带 30(76.9) 35(47.9) 8.765 0.003 -
[1] BAI Y, YAO L, WEI T, et al. Presumed asymptomatic carrier transmission of COVID-19[J]. Journal of the American Medical Association, 2020, 323(14): 1406−1407. doi: 10.1001/jama.2020.2565
[2] GUAN W J, NI Z Y, HU Y, et al. Clinical characteristics of coronavirus disease 2019 in China[J]. New England Journal of Medicine, 2020, 382(18): 1708−1720. doi: 10.1056/NEJMoa2002032
[3] CHEN Y, GONG X, WANG L, et al. Effects of hypertension, diabetes and coronary heart disease on COVID-19 diseases severity: A systematic review and meta-analysis[J]. Cold Spring Harbor Laboratory Press, 2020.
[4] WU C, CHEN X, CAI Y, et al. Risk factors associated with acute respiratory distress syndrome and death in patients with coronavirus disease 2019 pneumonia in Wuhan, China[J]. JAMA Internal Medicine, 2020, 180(7): 2020, 180(7): 934-943.
[5] RANGANKAR V, KOGANTI D V, LAMGHARE P, et al. Correlation between CT severity scoring and diabetes mellitus in patients with COVID-19 infection[J]. Cureus, 2021, 13(12): e20199.
[6] 杜丹, 谢元亮, 李惠, 等. 人工智能定量测量对新型冠状病毒肺炎患者胸部CT炎性病灶动态变化的评估价值[J]. 中华放射学杂志, 2021,55(3): 250−256. doi: 10.3760/cma.j.cn112149-20200330-00474 DU D, XIE Y L, LI H, et al. The value of quantitative artificial intelligence measurement in evaluation of CT dynamic changes for COVID-19[J]. Chinese Journal of Radiology, 2021, 55(3): 250−256. (in Chinese). doi: 10.3760/cma.j.cn112149-20200330-00474
[7] 朱桐, 黄璐, 严祥虎, 等. 基于机器学习的CT定量指标与新型冠状病毒肺炎临床分型及肺损伤严重程度的相关性研究[J]. 中华放射学杂志, 2021, 55(3): 239-244. ZHU T, HUANG L, YAN X H, et al. Correlation study between quantitative characteristics of CT lung opacification based on machine learning and clinical subtypes and severity of lung injury of COVID-19[J]. Chinese Journal of Radiology, 2021, 55(3): 239-244. (in Chinese).
[8] 中华人民共和国国家卫生健康委员会. 新型冠状病毒感染诊疗方案(试行第十版)[J]. 中华临床感染病杂志, 2023,16(1): 1−9. doi: 10.3760/cma.j.issn.1674-2397.2023.01.001 [9] 中华医学会糖尿病学分会, 国家基层糖尿病防治管理办公室. 国家基层糖尿病防治管理指南(2022)[J]. 中华内科杂志, 2022,61(3): 249−262. doi: 10.3760/cma.j.cn112138-20220120-000063 [10] 孙莹, 李玲, 刘晓燕, 等. 早期新型冠状病毒肺炎的胸部薄层平扫CT表现特征[J]. CT理论与应用研究, 2023,32(1): 131−138. DOI: 10.15953/j.ctta.2023.006. SUN Y, LI L, LIU X Y, et al. Imaging features of early COVID-19 on chest thin-slice non-enhanced CT[J]. CT Theory and Applications, 2023, 32(1): 131−138. DOI: 10.15953/j.ctta.2023.006. (in Chinese).
[11] DEBI H, ITU Z T, AMIN M T, et al. Association of serum C-reactive protein (CRP) and D-dimer concentration on the severity of COVID-19 cases with or without diabetes: A systematic review and meta-analysis[J]. Expert Review of Endocrinology & Metabolism, 2022, 17(1): 83−93.
[12] CAUSSY C, PATTOU F, WALLET F, et al. Prevalence of obesity among adult inpatients with COVID-19 in France[J]. Lancet Diabetes Endocrinol, 2020, 8(7): 562−564. doi: 10.1016/S2213-8587(20)30160-1
[13] WANG G, WU C, ZHANG Q, et al. C-reactive protein level may predict the risk of COVID-19 aggravation[J]. Open Forum Infectious Diseases, 2020, 7(5): ofaa153. DOI: 10.1093/ofid/ofaa153.
[14] 孙明谨, 李雪锋, 陈世清, 等. 2型糖尿病血清C反应蛋白及血白细胞变化[J]. 中国医师杂志, 2005,7(11): 2. SUN M J, LI X F, CHEN S Q, et al. Changes of serum C-reactive protein and white blood cells in type 2 diabetes mellitus[J]. Journal of Chinese Physician, 2005, 7(11): 2. (in Chinese).
[15] ERENER S. Diabetes, infection risk and COVID-19[J]. Molecular Metabolism, 2020, 39: 101044. doi: 10.1016/j.molmet.2020.101044
[16] 相萍萍, 韦晓, 刘超. 新型冠状病毒肺炎与糖尿病: 我们何去何从?[J]. 国际内分泌代谢杂志, 2022,(1): 50−53. doi: 10.3760/cma.j.cn121383-20201116-11033 XIANG P P, WEI X, LIU C. New coronavirus pneumonia and diabetes: Where shall we go?[J]. International Journal of Endocrinology and Metabolism, 2022, (1): 50−53. (in Chinese). doi: 10.3760/cma.j.cn121383-20201116-11033
[17] BERNHEIM A, MEI X, HUANG M, et al. Chest CT findings in coronavirus disease-19 (COVID-19): Relationship to duration of infection[J]. Radiology, 2020, 295(3): 200463. doi: 10.1148/radiol.2020200463
[18] KOH H, MOH A, YEOH E, et al. Diabetes predicts severity of COVID-19 infection in a retrospective cohort: A mediatory role of the inflammatory biomarker C-reactive protein[J]. Journal of Medical Virology, 2021, 93(5): 3023−3032. doi: 10.1002/jmv.26837
[19] 王菁, 纪小奇, 姚莉. 2型糖尿病合并感染发生MODS的危险因素分析[J]. 中华内分泌外科杂志, 2019,13(3): 5. doi: 10.3760/cma.j.issn.1674-6090.2019.03.003 WANG J, JI X Q, YAO L. Analysis of risk factors for multiple organ dysfunction syndrome in patients with type 2 diabetes mellitus complicated with infection[J]. Chinese Journal of Endocrine Surgery, 2019, 13(3): 5. (in Chinese). doi: 10.3760/cma.j.issn.1674-6090.2019.03.003