|本期目录/Table of Contents|

[1]叶垚坤 姜家锁 叶靖 张丽莎 蒋巧会 丁贵苏 闵凌峰.基于CT的影像组学评估自发性气胸患者的预后[J].中华肺部疾病杂志,2023,(02):185-189.[doi:10.3877/cma.j.issn.1674-6902.2023.02.007 ]
　Ye Yaokun,Jiang Jiasuo,Ye Jing,et al.Evaluation of prognosis of patients with spontaneous pneumothorax by CT radiomics[J].,2023,(02):185-189.[doi:10.3877/cma.j.issn.1674-6902.2023.02.007 ]
点击复制

基于CT的影像组学评估自发性气胸患者的预后(PDF)

《中华肺部疾病杂志》[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2023年02期
页码:
185-189
栏目:
论著
出版日期:
2023-04-20

文章信息/Info

Title:
Evaluation of prognosis of patients with spontaneous pneumothorax by CT radiomics
作者:
叶垚坤 姜家锁 叶靖 张丽莎 蒋巧会 丁贵苏 闵凌峰
225001 扬州,扬州大学医学院附属苏北人民医院呼吸与危重症医学科
Author(s):
Ye Yaokun;  Jiang Jiasuo;  Ye Jing;  Zhang Lisha;  Jiang Qiaohui;  Din Guisu;  Min Lingfeng.
The Department of Respiratory and Critical Care Medicine, North Jiangsu People's Hospital affiliated to Yangzhou University Medical College, Yangzhou 225001, China
关键词:
电子计算机断层扫描;  影像组学;  自发性气胸;  最小绝对收缩和选择操作;  ROC曲线
Keywords:
CT;  Radiomics;  Spontaneous pneumothorax;  LASSO;  ROC curve
分类号:
R563
DOI:
10.3877/cma.j.issn.1674-6902.2023.02.007
摘要:
目的 应用CT影像组学评估自发性气胸患者的愈合时间,结合临床影响因素的分析,为难治性自发性气胸患者的诊疗提供一定的参考。方法 回顾性纳入2015年5月1日至2021年5月1日我院收治的147例自发性气胸患者的临床资料及治疗前的胸部计算机断层扫描(CT),共提取了2 264个影像组学特征,通过最小绝对收缩和选择操作(LASSO)回归分析,选择出最合适的生存预测特征,机器算法选择Bagging决策树,生成影像组学模型,以外部验证队列进行模型验证。分析患者的临床数据,用多因素Logistic回归分析评估临床影响因素。结果 wavelet_glcm_wavelet-llh-idmn、wavelet_firstorder_wavelet-hll-maximum、wavelet_glcm_wavelet-hll-imc2、log_glcm_log-sigma-2-0-mm-3d-idmn、wavelet_glcm_wavelet-hhl-imc2是最具特征的5个参数。训练集和外部验证集中的ROC曲线下面积分别为0.991和0.846。针对一般临床资料,结果显示,年龄和吸烟指数的差异有统计学意义(P<0.05); 多因素Logistic回归分析显示,吸烟指数是气胸患者预后的危险因素(P<0.05)。结论 CT影像组学建立的模型能够有效地识别难治性气胸的患者; 吸烟指数较高的气胸患者容易发展为难治性气胸。
Abstract:
Objective To evaluate the healing time of patients with spontaneous pneumothorax by CT radiomics, combined with the analysis of clinical influencing factors, to provide some reference for the diagnosis and treatment of patients with refractory spontaneous pneumothorax. Methods The clinical data of 45-75 years old patients with spontaneous pneumothorax in North Jiangsu People's Hospital from 2015 to 2021 and the chest computer tomography(CT)before treatment were retrospectively included. A total of 2264 radiomics features were extracted. The most appropriate survival prediction features were selected through least absolute contraction and selection operation(LASSO)regression analysis. Bagging decision tree was selected for machine algorithm to generate radiomics model. Model validation is performed with an external validation queue. The clinical data of patients were analyzed and the clinical influencing factors were evaluated by multifactor logistic regression analysis. Results wavelet_glcm_wavelet-llh-idmn、wavelet_firstorder_wavelet-hll-maximum、wavelet_glcm_wavelet-hll-imc2、log_glcm_log-sigma-2-0-mm-3d-idmn and wavelet_glcm_wavelet-hhl-imc2 are the most characteristic five parameters. The area under the ROC curve in the training set and the external validation set is 0.991 and 0.846 respectively. For general clinical data, chi square test results showed that for age and smoking index, the difference is statistically significant(P<0.05); Multivariate logistic regression analysis showed that smoking index was an independent risk factor for the prognosis of pneumothorax patients(P<0.05)Conclusion The model established by CT radiomics can effectively identify patients with refractory pneumothorax; Patients with high smoking index are more likely to develop refractory pneumothorax.

参考文献/References:

1 Eggeling S. Pneumothorax[J]. Zentralbl Chir, 2021, 146(1): 126-144.
2 Schnell J, Koryllos A, Lopez-Pastorini A, et al. Spontaneous pneumothorax[J]. Dtsch Arztebl Int, 2017, 114(44): 739-744.
3 Dzeljilji A, Rokicki W, Rokicki M, et al. New aspects in the diagnosis and treatment of primary spontaneous pneumothorax [J]. Kardiochir Torakochirurgia Pol, 2017, 14(1): 27-31.
4 中华医学会呼吸病学分会介入呼吸病学学组. 选择性支气管封堵术治疗难治性气胸专家共识 [J]. 中华结核和呼吸杂志, 2021, 44(5): 417-426.
5 Chee CB, Abisheganaden J, Yeo JK, et al. Persistent air-leak in spontaneous pneumothorax-clinical course and outcome [J]. Respir Med, 1998, 92(5): 757-761.
6 Lambin P, Rios-Velazquez E, Leijenaar R, et al. Radiomics: extracting more information from medical images using advanced feature analysis [J]. Eur J Cancer, 2012, 48(4): 441-446.
7 Tschopp JM, Bintcliffe O, Astoul P, et al. ERS task force statement: diagnosis and treatment of primary spontaneous pneumothorax[J]. Eur Respir J, 2015, 46(2): 321-335.
8 张正峰, 李祥彤, 刘林祥. 自发性气胸定量诊断的研究进展[J]. 医学影像学杂志, 2022, 32(1): 160-163.
9 Refaee T, Wu G, Ibrahim A, et al. The Emerging Role of Radiomics in COPD and Lung Cancer [J]. Respiration; international review of thoracic diseases, 2020, 99(2): 99-107.
10 范卫杰, 张 冬. 影像组学及深度学习在肺结节良恶性鉴别诊断中的新理念[J/CD]. 中华肺部疾病杂志(电子版), 2021, 14(5): 549-553.
11 Avanzo M, Stancanello J, Pirrone G, et al. Radiomics and deep learning in lung cancer [J]. Strahlenther Onkol, 2020, 196(10): 879-887.
12 Kim D, Eom SY, Shin CS, et al. The clinical effect of smoking and environmental factors in spontaneous pneumothorax: a case-crossover study in an Inland province [J]. Ther Adv Respir Dis, 2020, 14: 1753466620977408.
13 侍 管, 崔 永, 常 栋. 首次发作的原发性自发性气胸复发因素研究进展 [J]. 临床肺科杂志, 2016, 21(9): 1693-1695.
14 Cheng YL, Huang TW, Lin CK, et al. The impact of smoking in primary spontaneous pneumothorax[J]. J Thorac Cardiovasc Surg, 2009, 138(1): 192-195.
15 温俊策. 吸烟增加患自发性气胸的危险性 [J]. 国外医学(内科学分册), 1989,(4): 188.
16 Ghisalberti M, Guerrera F, De Vico A, et al. Age and clinical presentation for primary spontaneous pneumothorax[J]. Heart, lung & circulation, 2020, 29(11): 1648-1655.
17 Gupta D, Hansell A, Nichols T, et al. Epidemiology of pneumothorax in England[J]. Thorax, 2000, 55(8): 666-671.
18 黄建岭. 自发性气胸60例临床分析[J]. 中国社区医师(医学专业), 2011, 13(08): 30.
19 罗鸿波, 陈菱菱, 傅万颖. 自发性气胸139例临床分析[J]. 岭南急诊医学杂志, 2017, 22(4): 369-70,73.
20 Gerhardy BC, Simpson G. Conservative versus invasive management of secondary spontaneous pneumothorax: a retrospective cohort study[J]. Acute medicine & surgery, 2021, 8(1): e663.
21 张正峰, 李祥彤, 刘林祥. 自发性气胸定量诊断的研究进展[J]. 医学影像学杂志, 2022, 32(1): 160-163.
22 左志刚, 陈朋娥, 廖勇胜, 等. 自发性气胸术后血清NPY SP PGE2水平变化及与复发的关系[J]. 河北医学, 2022, 29(10): 1644-1649.
23 党玉涛, 王建利, 李 国, 等. 自发性气胸胸膜粘连带的影响因素研究[J]. 北京医学, 2022, 57(11): 1047-1050.
24 王慧林, 武玉荣. 自发性气胸肺复张时间探讨[J/CD]. 中华肺部疾病杂志(电子版), 2013, 6(3): 254-255.

备注/Memo

备注/Memo:
通信作者: 闵凌峰, Email: minlingfeng@163.com
更新日期/Last Update: 2023-04-20