Follow-up of CT-derived airway wall thickness: Correcting for changes in inspiration level improves reliability

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.

Imaging-derived biomarkers in Asthma: Current status and future perspectives

Asthma is a common disorder affecting around 315 million individuals worldwide. The heterogeneity of asthma is becoming increasingly important in the era of personalized treatment and response assessment. Several radiological imaging modalities are available in asthma including chest x-ray, computed tomography (CT) and magnetic resonance imaging (MRI) scanning. In addition to qualitative imaging, quantitative imaging could play an important role in asthma imaging to identify phenotypes with distinct disease course and response to therapy, including biologics. MRI in asthma is mainly performed in research settings given cost, technical challenges, and there is a need for standardization. Imaging analysis applications of artificial intelligence (AI) to subclassify asthma using image analysis have demonstrated initial feasibility, though additional work is necessary to inform the role of AI in clinical practice.

Treatment Trials in Young Patients with Chronic Obstructive Pulmonary Disease and Pre-Chronic Obstructive Pulmonary Disease Patients: Time to Move Forward

Chronic obstructive pulmonary disease (COPD) is the end result of a series of dynamic and cumulative gene-environment interactions over a lifetime. The evolving understanding of COPD biology provides novel opportunities for prevention, early diagnosis, and intervention. To advance these concepts, we propose therapeutic trials in two major groups of subjects: "young" individuals with COPD and those with pre-COPD. Given that lungs grow to about 20 years of age and begin to age at approximately 50 years, we consider "young" patients with COPD those patients in the age range of 20-50 years. Pre-COPD relates to individuals of any age who have respiratory symptoms with or without structural and/or functional abnormalities, in the absence of airflow limitation, and who may develop persistent airflow limitation over time. We exclude from the current discussion infants and adolescents because of their unique physiological context and COPD in older adults given their representation in prior randomized controlled trials (RCTs). We highlight the need of RCTs focused on COPD in young patients or pre-COPD to reduce disease progression, providing innovative approaches to identifying and engaging potential study subjects. We detail approaches to RCT design, including potential outcomes such as lung function, patient-reported outcomes, exacerbations, lung imaging, mortality, and composite endpoints. We critically review study design components such as statistical powering and analysis, duration of study treatment, and formats to trial structure, including platform, basket, and umbrella trials. We provide a call to action for treatment RCTs in 1) young adults with COPD and 2) those with pre-COPD at any age.

Automatic quantitative analysis of pulmonary vascular morphology in CT images

PURPOSE

Vascular remodeling is a significant pathological feature of various pulmonary diseases, which may be assessed by quantitative computed tomography (CT) imaging. The purpose of this study was therefore to develop and validate an automatic method for quantifying pulmonary vascular morphology in CT images.

METHODS

The proposed method consists of pulmonary vessel extraction and quantification. For extracting pulmonary vessels, a graph-cuts-based method is proposed which considers appearance (CT intensity) and shape (vesselness from a Hessian-based filter) features, and incorporates distance to the airways into the cost function to prevent false detection of airway walls. For quantifying the extracted pulmonary vessels, a radius histogram is generated by counting the occurrence of vessel radii, calculated from a distance transform-based method. Subsequently, two biomarkers, slope α and intercept β, are calculated by linear regression on the radius histogram. A public data set from the VESSEL12 challenge was used to independently evaluate the vessel extraction. The quantitative analysis method was validated using images of a three-dimensional (3D) printed vessel phantom, scanned by a clinical CT scanner and a micro-CT scanner (to obtain a gold standard). To confirm the association between imaging biomarkers and pulmonary function, 77 scleroderma patients were investigated with the proposed method.

RESULTS

In the independent evaluation with the public data set, our vessel segmentation method obtained an area under the receiver operating characteristic (ROC) curve of 0.976. The median radius difference between clinical and micro-CT scans of a 3D printed vessel phantom was 0.062 ± 0.020 mm, with interquartile range of 0.199 ± 0.050 mm. In the studied patient group, a significant correlation between diffusion capacity for carbon monoxide and the biomarkers, α (R = -0.27, P = 0.018) and β (R = 0.321, P = 0.004), was obtained.

CONCLUSION

In conclusion, the proposed method was validated independently using a public data set resulting in an area under the ROC curve of 0.976 and using a 3D printed vessel phantom data set, showing a vessel sizing error of 0.062 mm (0.16 in-plane pixel units). The correlation between imaging biomarkers and diffusion capacity in a clinical data set confirmed an association between lung structure and function. This quantification of pulmonary vascular morphology may be helpful in understanding the pathophysiology of pulmonary vascular diseases.

Longitudinal airway remodeling in active and past smokers in a lung cancer screening population

OBJECTIVES

To longitudinally investigate smoking cessation-related changes of quantitative computed tomography (QCT)-based airway metrics in a group of heavy smokers.

METHODS

CT scans were acquired in a lung cancer screening population over 4 years at 12-month intervals in 284 long-term ex-smokers (ES), 405 continuously active smokers (CS), and 31 subjects who quitted smoking within 2 years after baseline CT (recent quitters, RQ). Total diameter (TD), lumen area (LA), and wall percentage (WP) of 1st-8th generation airways were computed using airway analysis software. Inter-group comparison was performed using Mann-Whitney U test or Student's t test (two groups), and ANOVA or ANOVA on ranks with Dunn's multiple comparison test (more than two groups), while Fisher's exact test or chi-squared test was used for categorical data. Multiple linear regression was used for multivariable analysis.

RESULTS

At any time, TD and LA were significantly higher in ES than CS, for example, in 5th-8th generation airways at baseline with 6.24 mm vs. 5.93 mm (p < 0.001) and 15.23 mm² vs. 13.51 mm² (p < 0.001), respectively. RQ showed higher TD (6.15 mm vs. 5.93 mm, n.s.) and significantly higher LA (14.77 mm² vs. 13.51 mm², p < 0.001) than CS after 3 years, and after 4 years. In multivariate analyses, smoking status independently predicted TD, LA, and WP at baseline, at 3 years and 4 years (p < 0.01-0.001), with stronger impact than pack years.

CONCLUSIONS

Bronchial dimensions depend on the smoking status. Smoking-induced airway remodeling can be partially reversible after smoking cessation even in long-term heavy smokers. Therefore, QCT-based airway metrics in clinical trials should consider the current smoking status besides pack years.

KEY POINTS

• Airway lumen and diameter are decreased in active smokers compared to ex-smokers, and there is a trend towards increased airway wall thickness in active smokers. • Smoking-related airway changes improve within 2 years after smoking cessation. • Smoking status is an independent predictor of airway dimensions.

Comparison of low- and ultralow-dose computed tomography protocols for quantitative lung and airway assessment

PURPOSE

Quantitative computed tomography (CT) measures are increasingly being developed and used to characterize lung disease. With recent advances in CT technologies, we sought to evaluate the quantitative accuracy of lung imaging at low- and ultralow-radiation doses with the use of iterative reconstruction (IR), tube current modulation (TCM), and spectral shaping.

METHODS

We investigated the effect of five independent CT protocols reconstructed with IR on quantitative airway measures and global lung measures using an in vivo large animal model as a human subject surrogate. A control protocol was chosen (NIH-SPIROMICS + TCM) and five independent protocols investigating TCM, low- and ultralow-radiation dose, and spectral shaping. For all scans, quantitative global parenchymal measurements (mean, median and standard deviation of the parenchymal HU, along with measures of emphysema) and global airway measurements (number of segmented airways and pi10) were generated. In addition, selected individual airway measurements (minor and major inner diameter, wall thickness, inner and outer area, inner and outer perimeter, wall area fraction, and inner equivalent circle diameter) were evaluated. Comparisons were made between control and target protocols using difference and repeatability measures.

RESULTS

Estimated CT volume dose index (CTDIvol) across all protocols ranged from 7.32 mGy to 0.32 mGy. Low- and ultralow-dose protocols required more manual editing and resolved fewer airway branches; yet, comparable pi10 whole lung measures were observed across all protocols. Similar trends in acquired parenchymal and airway measurements were observed across all protocols, with increased measurement differences using the ultralow-dose protocols. However, for small airways (1.9 ± 0.2 mm) and medium airways (5.7 ± 0.4 mm), the measurement differences across all protocols were comparable to the control protocol repeatability across breath holds. Diameters, wall thickness, wall area fraction, and equivalent diameter had smaller measurement differences than area and perimeter measurements.

CONCLUSIONS

In conclusion, the use of IR with low- and ultralow-dose CT protocols with CT volume dose indices down to 0.32 mGy maintains selected quantitative parenchymal and airway measurements relevant to pulmonary disease characterization.