Utility of an artificial intelligence-based lung CT airway model in the quantitative evaluation of large and small airway lesions in patients with chronic obstructive pulmonary disease
Abstract Background Accurate quantification of the extent of bronchial damage across various airway levels in chronic obstructive pulmonary disease (COPD) remains a challenge. In this study, artificial intelligence (AI) was employed to develop an airway segmentation model to investigate the morpholo...
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-08-01
|
| Series: | BMC Pulmonary Medicine |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12890-025-03848-x |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849344623615410176 |
|---|---|
| author | Zheng Liu Jing Li Bo Li Guozhen Yi Shaoqian Pang Ruinan Zhang Peixiu Li Zhaoping Yin Jing Zhang Bingxin Lv Jingjing Yan Jiao Ma |
| author_facet | Zheng Liu Jing Li Bo Li Guozhen Yi Shaoqian Pang Ruinan Zhang Peixiu Li Zhaoping Yin Jing Zhang Bingxin Lv Jingjing Yan Jiao Ma |
| author_sort | Zheng Liu |
| collection | DOAJ |
| description | Abstract Background Accurate quantification of the extent of bronchial damage across various airway levels in chronic obstructive pulmonary disease (COPD) remains a challenge. In this study, artificial intelligence (AI) was employed to develop an airway segmentation model to investigate the morphological changes of the central and peripheral airways in COPD patients and the effects of these airway changes on pulmonary function classification and acute COPD exacerbations. Methods Clinical data from a total of 340 patients with COPD and 73 healthy volunteers were collected and compiled. An AI-driven airway segmentation model was constructed using Convolutional Neural Regressor (CNR) and Airway Transfer Network (ATN) algorithms. The efficacy of the model was evaluated through support vector machine (SVM) and random forest regression approaches. Results The area under the receiver operating characteristic (ROC) curve (AUC) of the SVM in evaluating the COPD airway segmentation model was 0.96, with a sensitivity of 97% and a specificity of 92%, however, the AUC value of the SVM was 0.81 when it was replaced the healthy group by non-COPD outpatients. Compared with the healthy group, the grade and the total number of airway segmentation were decreased and the diameters of the right main bronchus and bilateral lobar bronchi of patients with COPD were smaller and the airway walls were thinner (all P < 0.01). However, the diameters of the subsegmental and small airway bronchi were increased, and airway walls were thickened, and the arc lengths were shorter ( all P < 0.01), especially in patients with severe COPD (all P < 0.05). Correlation and regression analysis showed that FEV1%pre was positively correlated with the diameters and airway wall thickness of the main and lobar airway, and the arc lengths of small airway bronchi (all P < 0.05). Airway wall thickness of the subsegment and small airway were found to have the greatest impact on the frequency of COPD exacerbations. Conclusion Artificial intelligence lung CT airway segmentation model is a non-invasive quantitative tool for measuring chronic obstructive pulmonary disease. The main changes in COPD patients are that the central airway diameter becomes narrower and the thickness becomes thinner. The arc length of the peripheral airway becomes shorter, and the diameter and airway wall thickness become larger, which is more obvious in severe patients. Pulmonary function classification and small and medium airway dysfunction are also affected by the diameter, thickness and arc length of large and small airways. Small airway remodeling is more significant in acute exacerbations of COPD. |
| format | Article |
| id | doaj-art-e18c2cc221d9499da492104f2b416a82 |
| institution | Kabale University |
| issn | 1471-2466 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Pulmonary Medicine |
| spelling | doaj-art-e18c2cc221d9499da492104f2b416a822025-08-20T03:42:37ZengBMCBMC Pulmonary Medicine1471-24662025-08-0125111410.1186/s12890-025-03848-xUtility of an artificial intelligence-based lung CT airway model in the quantitative evaluation of large and small airway lesions in patients with chronic obstructive pulmonary diseaseZheng Liu0Jing Li1Bo Li2Guozhen Yi3Shaoqian Pang4Ruinan Zhang5Peixiu Li6Zhaoping Yin7Jing Zhang8Bingxin Lv9Jingjing Yan10Jiao Ma11Department of Respiratory Medicine, Petroleum Clinical Medical College, Hebei Medical UniversityDepartment of Respiratory Medicine, Petroleum Clinical Medical College, Hebei Medical UniversityGENERTEC Intelligent Cloud Imaging Technology (Beijing) Co., LtdDepartment of Respiratory Medicine, Petroleum Clinical Medical College, Hebei Medical UniversityDepartment of Respiratory Medicine, Petroleum Clinical Medical College, Hebei Medical UniversityGENERTEC Intelligent Cloud Imaging Technology (Beijing) Co., LtdDepartment of Imaging, Petroleum Clinical Medical College, Hebei Medical UniversityDepartment of Respiratory, Panjin Liaoyou Gemstone Flower HospitalDepartment of Respiratory Medicine, North China Petroleum Administration General HospitalDepartment of Health Management, Petroleum Clinical Medical College, Hebei Medical UniversityDepartment of Respiratory Medicine, Petroleum Clinical Medical College, Hebei Medical UniversityDepartment of Respiratory Medicine, Petroleum Clinical Medical College, Hebei Medical UniversityAbstract Background Accurate quantification of the extent of bronchial damage across various airway levels in chronic obstructive pulmonary disease (COPD) remains a challenge. In this study, artificial intelligence (AI) was employed to develop an airway segmentation model to investigate the morphological changes of the central and peripheral airways in COPD patients and the effects of these airway changes on pulmonary function classification and acute COPD exacerbations. Methods Clinical data from a total of 340 patients with COPD and 73 healthy volunteers were collected and compiled. An AI-driven airway segmentation model was constructed using Convolutional Neural Regressor (CNR) and Airway Transfer Network (ATN) algorithms. The efficacy of the model was evaluated through support vector machine (SVM) and random forest regression approaches. Results The area under the receiver operating characteristic (ROC) curve (AUC) of the SVM in evaluating the COPD airway segmentation model was 0.96, with a sensitivity of 97% and a specificity of 92%, however, the AUC value of the SVM was 0.81 when it was replaced the healthy group by non-COPD outpatients. Compared with the healthy group, the grade and the total number of airway segmentation were decreased and the diameters of the right main bronchus and bilateral lobar bronchi of patients with COPD were smaller and the airway walls were thinner (all P < 0.01). However, the diameters of the subsegmental and small airway bronchi were increased, and airway walls were thickened, and the arc lengths were shorter ( all P < 0.01), especially in patients with severe COPD (all P < 0.05). Correlation and regression analysis showed that FEV1%pre was positively correlated with the diameters and airway wall thickness of the main and lobar airway, and the arc lengths of small airway bronchi (all P < 0.05). Airway wall thickness of the subsegment and small airway were found to have the greatest impact on the frequency of COPD exacerbations. Conclusion Artificial intelligence lung CT airway segmentation model is a non-invasive quantitative tool for measuring chronic obstructive pulmonary disease. The main changes in COPD patients are that the central airway diameter becomes narrower and the thickness becomes thinner. The arc length of the peripheral airway becomes shorter, and the diameter and airway wall thickness become larger, which is more obvious in severe patients. Pulmonary function classification and small and medium airway dysfunction are also affected by the diameter, thickness and arc length of large and small airways. Small airway remodeling is more significant in acute exacerbations of COPD.https://doi.org/10.1186/s12890-025-03848-xAirway modelAirway wall thicknessChronic obstructive pulmonary diseaseLung function gradeSupport vector machine |
| spellingShingle | Zheng Liu Jing Li Bo Li Guozhen Yi Shaoqian Pang Ruinan Zhang Peixiu Li Zhaoping Yin Jing Zhang Bingxin Lv Jingjing Yan Jiao Ma Utility of an artificial intelligence-based lung CT airway model in the quantitative evaluation of large and small airway lesions in patients with chronic obstructive pulmonary disease BMC Pulmonary Medicine Airway model Airway wall thickness Chronic obstructive pulmonary disease Lung function grade Support vector machine |
| title | Utility of an artificial intelligence-based lung CT airway model in the quantitative evaluation of large and small airway lesions in patients with chronic obstructive pulmonary disease |
| title_full | Utility of an artificial intelligence-based lung CT airway model in the quantitative evaluation of large and small airway lesions in patients with chronic obstructive pulmonary disease |
| title_fullStr | Utility of an artificial intelligence-based lung CT airway model in the quantitative evaluation of large and small airway lesions in patients with chronic obstructive pulmonary disease |
| title_full_unstemmed | Utility of an artificial intelligence-based lung CT airway model in the quantitative evaluation of large and small airway lesions in patients with chronic obstructive pulmonary disease |
| title_short | Utility of an artificial intelligence-based lung CT airway model in the quantitative evaluation of large and small airway lesions in patients with chronic obstructive pulmonary disease |
| title_sort | utility of an artificial intelligence based lung ct airway model in the quantitative evaluation of large and small airway lesions in patients with chronic obstructive pulmonary disease |
| topic | Airway model Airway wall thickness Chronic obstructive pulmonary disease Lung function grade Support vector machine |
| url | https://doi.org/10.1186/s12890-025-03848-x |
| work_keys_str_mv | AT zhengliu utilityofanartificialintelligencebasedlungctairwaymodelinthequantitativeevaluationoflargeandsmallairwaylesionsinpatientswithchronicobstructivepulmonarydisease AT jingli utilityofanartificialintelligencebasedlungctairwaymodelinthequantitativeevaluationoflargeandsmallairwaylesionsinpatientswithchronicobstructivepulmonarydisease AT boli utilityofanartificialintelligencebasedlungctairwaymodelinthequantitativeevaluationoflargeandsmallairwaylesionsinpatientswithchronicobstructivepulmonarydisease AT guozhenyi utilityofanartificialintelligencebasedlungctairwaymodelinthequantitativeevaluationoflargeandsmallairwaylesionsinpatientswithchronicobstructivepulmonarydisease AT shaoqianpang utilityofanartificialintelligencebasedlungctairwaymodelinthequantitativeevaluationoflargeandsmallairwaylesionsinpatientswithchronicobstructivepulmonarydisease AT ruinanzhang utilityofanartificialintelligencebasedlungctairwaymodelinthequantitativeevaluationoflargeandsmallairwaylesionsinpatientswithchronicobstructivepulmonarydisease AT peixiuli utilityofanartificialintelligencebasedlungctairwaymodelinthequantitativeevaluationoflargeandsmallairwaylesionsinpatientswithchronicobstructivepulmonarydisease AT zhaopingyin utilityofanartificialintelligencebasedlungctairwaymodelinthequantitativeevaluationoflargeandsmallairwaylesionsinpatientswithchronicobstructivepulmonarydisease AT jingzhang utilityofanartificialintelligencebasedlungctairwaymodelinthequantitativeevaluationoflargeandsmallairwaylesionsinpatientswithchronicobstructivepulmonarydisease AT bingxinlv utilityofanartificialintelligencebasedlungctairwaymodelinthequantitativeevaluationoflargeandsmallairwaylesionsinpatientswithchronicobstructivepulmonarydisease AT jingjingyan utilityofanartificialintelligencebasedlungctairwaymodelinthequantitativeevaluationoflargeandsmallairwaylesionsinpatientswithchronicobstructivepulmonarydisease AT jiaoma utilityofanartificialintelligencebasedlungctairwaymodelinthequantitativeevaluationoflargeandsmallairwaylesionsinpatientswithchronicobstructivepulmonarydisease |