CT artificial intelligence assessment of pulmonary function in chronic obstructive pulmonary diseases
10.3969/j.issn.1673-9701.2025.06.001
- VernacularTitle:慢性阻塞性肺疾病肺功能的CT人工智能评估
- Author:
Haonan FU
1
;
Shanshan ZHANG
;
Minge ZHANG
;
Zishan LIU
;
Hai YANG
Author Information
1. 浙江省台州医院台州恩泽医疗中心(集团)恩泽医院放射科,浙江台州 317000
- Publication Type:Journal Article
- Keywords:
Chronic obstructive pulmonary disease;
Artificial intelligence;
Lung function;
Quantitative computed tomography
- From:
China Modern Doctor
2025;63(6):1-5,78
- CountryChina
- Language:Chinese
-
Abstract:
Objective To analyse correlation between automatic quantification of emphysema and lung function based on artificial intelligence(AI)model algorithm by chest computed tomography(CT)in patients with chronic obstructive pulmonary disease(COPD).Methods The clinical and imaging data of hospitalized COPD patients who received chest CT plain scan in Taizhou Hospital of Zhejiang Province,Enze Hospital of Taizhou Enze Medical Center(Group)from December 2020 to May 2021 were retrospectively collected,patients were classified into five levels of ventilator-function decline.By using the AI model,the extent of emphysema lesions in COPD patients were calculated,low-attenuation areas below-950HU were identified and their low attenuation area percentage(LAA％)were calculated.Combined with the output results of AI model and whether each variable met the characteristics of normal distribution,Pearson correlation coefficient between percentage of measured forced expiratory volume at the end of 1 second to estimated value(FEV1％)and LAA％of each lung lobe,and the Spearman correlation coefficient between FEV1 as a percentage of forced vital capacity(FEV1/FVC)and LAA％of each lung lobe in patients with different COPD grades were calculated respectively.Results There was a negative correlation between total lung LAA％and FEV1/FVC in moderate COPD(r=-0.632,P=0.001).Total lung LAA％in very severe COPD was negatively correlated with both FEV1/FVC and FEV1％(r=-0.562,P=0.045 and r=-0.701,P=0.004).The results of lung segment analysis showed that LAA％of the left upper lung lobe was more strongly correlated with pulmonary function indicators in extremely severe COPD(r=-0.650,P=0.016 andr=-0.731,P=0.002).The correlation between left inferior lobe LAA％and FEV1/FVC was stronger correlation in patients with moderate COPD(r=-0.712,P=0.000).In smoking patients,LAA％was moderate correlated with FEV1(r=-0.534,P=0.006),and LAA％was moderate correlated with FEV1/FVC(r=-0.564,P=0.003).Conclusion AI-based emphysema quantification results have a good correlation with FEV1/FVC and FEV1％,which can provide strong support for the diagnosis and classification of COPD based on CT plain scan images.
