Bronchial wall parameters on CT in healthy never-smoking, smoking, COPD, and asthma populations: a systematic review and meta-analysis

Early Diagnosis of High-Risk Chronic Obstructive Pulmonary Disease Based on Quantitative High-Resolution Computed Tomography Measurements

Purpose

Quantitative computed tomography (QCT) techniques, focusing on airway anatomy and emphysema, may help to detect early structural changes of COPD disease. This retrospective study aims to identify high-risk COPD participants by using QCT measurements.

Patients and Methods

We enrolled 140 participants from the Second Affiliated Hospital of Shenyang Medical College who completed inspiratory high-resolution CT scans, pulmonary function tests (PFTs), and clinical characteristics recorded. They were diagnosed Non-COPD by PFT value of FEV1/FVC >70% and divided into two groups according percentage predicted FEV1 (FEV1%), low-risk COPD group: FEV1% ≥ 95%, high-risk group: 80% < FEV1% < 95%. The QCT measurements were analyzed by the Student's t-test (or Mann-Whitney U-test) method. Then, feature candidates were identified using the LASSO method. Meanwhile, the correlation between QCT measurements and PFTs was assessed by the Spearman rank correlation test. Furthermore, support vector machine (SVM) was performed to identify high-risk COPD participants. The performance of the models was evaluated in terms of accuracy (ACC), sensitivity (SEN), specificity (SPE), F1-score, and area under the ROC curve (AUC), with p <0.05 considered statistically significant.

Results

The SVM based on QCT measurements achieved good performance in identifying high-risk COPD patients with 85.71% of ACC, 88.34% of SEN, 84.00% of SPE, 83.33% of F1-score, and 0.93 of AUC. Further, QCT measurements integration of clinical data improved the performance with an ACC of 90.48%. The emphysema index (%LAA-950) of left lower lung was negatively correlated with PFTs (P < 0.001). The airway anatomy indexes of lumen diameter (LD) were correlated with PFTs.

Conclusion

QCT measurements combined with clinical information could provide an effective tool for an early diagnosis of high-risk COPD. The QCT indexes can be used to assess the pulmonary function status of high-risk COPD.

Morphometric analysis of airways in pre-COPD and mild COPD lungs using continuous surface representations of the bronchial lumen

Introduction: Chronic Obstructive Pulmonary Disease (COPD) is a prevalent respiratory disease that presents a high rate of underdiagnosis during onset and early stages. Studies have shown that in mild COPD patients, remodeling of the small airways occurs concurrently with morphological changes in the proximal airways. Despite this evidence, the geometrical study of the airway tree from computed tomography (CT) lung images remains underexplored due to poor representations and limited tools to characterize the airway structure. Methods: We perform a comprehensive morphometric study of the proximal airways based on geometrical measures associated with the different airway generations. To this end, we leverage the geometric flexibility of the Snakes IsoGeometric Analysis method to accurately represent and characterize the airway luminal surface and volume informed by CT images of the respiratory tree. Based on this framework, we study the airway geometry of smoking pre-COPD and mild COPD individuals. Results: Our results show a significant difference between groups in airway volume, length, luminal eccentricity, minimum radius, and surface-area-to-volume ratio in the most distal airways. Discussion: Our findings suggest a higher degree of airway narrowing and collapse in COPD patients when compared to pre-COPD patients. We envision that our work has the potential to deliver a comprehensive tool for assessing morphological changes in airway geometry that take place in the early stages of COPD.

Reproducibility of a combined artificial intelligence and optimal-surface graph-cut method to automate bronchial parameter extraction

OBJECTIVES

Computed tomography (CT)-based bronchial parameters correlate with disease status. Segmentation and measurement of the bronchial lumen and walls usually require significant manpower. We evaluate the reproducibility of a deep learning and optimal-surface graph-cut method to automatically segment the airway lumen and wall, and calculate bronchial parameters.

METHODS

A deep-learning airway segmentation model was newly trained on 24 Imaging in Lifelines (ImaLife) low-dose chest CT scans. This model was combined with an optimal-surface graph-cut for airway wall segmentation. These tools were used to calculate bronchial parameters in CT scans of 188 ImaLife participants with two scans an average of 3 months apart. Bronchial parameters were compared for reproducibility assessment, assuming no change between scans.

RESULTS

Of 376 CT scans, 374 (99%) were successfully measured. Segmented airway trees contained a mean of 10 generations and 250 branches. The coefficient of determination (R2) for the luminal area (LA) ranged from 0.93 at the trachea to 0.68 at the 6th generation, decreasing to 0.51 at the 8th generation. Corresponding values for Wall Area Percentage (WAP) were 0.86, 0.67, and 0.42, respectively. Bland-Altman analysis of LA and WAP per generation demonstrated mean differences close to 0; limits of agreement (LoA) were narrow for WAP and Pi10 (± 3.7% of mean) and wider for LA (± 16.4-22.8% for 2-6th generations). From the 7th generation onwards, there was a sharp decrease in reproducibility and a widening LoA.

CONCLUSION

The outlined approach for automatic bronchial parameter measurement on low-dose chest CT scans is a reliable way to assess the airway tree down to the 6th generation.

STATEMENT ON CLINICAL RELEVANCE

This reliable and fully automatic pipeline for bronchial parameter measurement on low-dose CT scans has potential applications in screening for early disease and clinical tasks such as virtual bronchoscopy or surgical planning, while also enabling the exploration of bronchial parameters in large datasets.

KEY POINTS

• Deep learning combined with optimal-surface graph-cut provides accurate airway lumen and wall segmentations on low-dose CT scans. • Analysis of repeat scans showed that the automated tools had moderate-to-good reproducibility of bronchial measurements down to the 6th generation airway. • Automated measurement of bronchial parameters enables the assessment of large datasets with less man-hours.

Quantitative CT Metrics for the Prediction of Therapeutic Effect in Asthma

Background: Few studies have explored the correlation between asthma medication and features on HRCT images. We aim to analyse the differences and temporal changes of lung function and airway resistance in asthma with diverse HRCT phenotypes in a short period after inhalation of budesonide/formoterol. Method: This observational study recruited 55 adult patients with varying severities of asthma. We performed detailed airway metrics measurements of chest CT scans, such as airway wall thickness (WT), wall area percentage (WA%), wall thickness percentage (T/OR), and airways with an inner perimeter of 10 mm (Pi10). The effect of lung structural features on asthma medication response was explored according to the WA% and T/OR twelve hours post-drug administration. Using multivariable regression models, we then assessed the influence of WA% on lung function. Results: WA% (p < 0.001) and T/OR (p < 0.001) significantly increased in asthma than in healthy control subjects. Compared to mild asthma, airway walls were further thickened (WA%, p = 0.023; T/OR: p = 0.029) and associated with lumen narrowing (Pi10, p = 0.055) in moderate to severe asthma. WA% and T/OR correlated well with lung function (FEV1, FVC, MMEF, and PEF) and airway resistance (R5, R20, Rp, and Fres). Regression analysis showed that MEF25 decreased with increasing age and WA% (R2 = 0.58, p < 0.001). Patients with thickened airway walls experienced a maximal increase in FVC, FEV1, and PEF at 2 h (p < 0.001) and a maximal decrease of R5, Z5, and Rp at 2 h (p < 0.001) in those with a thickened airway pattern. Conclusions: Asthma patients with different bronchial wall thicknesses exhibited variable lung function changes. Specifically, patients with thick airway wall patterns were more sensitive to inhaled budesonide in the short term.