Automatic quantitative analysis of pulmonary vascular morphology in CT images

Abstract

PurposeVascular 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.MethodsThe 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.ResultsIn 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.ConclusionIn 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.

Measuring pulmonary function in COPD using quantitative chest computed tomography analysis

“…Comorbidities, affecting the health status of the patient and thereby possibly influencing the LVR selection, may also be detectable. For instance, due to the relatively high contrast between pulmonary parenchyma and pulmonary vessels, the vessels can be segmented out of the lung [85]. The segmented vessels could provide useful information on pulmonary hypertension [86,87], as pulmonary hypertension involves vascular remodelling [88,89].…”

Vascular remodeling of the small pulmonary arteries and measures of vascular pruning on computed tomography

“…The results of our study, which found that CT-based pruning was associated with thickening of the walls of the small pulmonary vessels and a resulting loss in luminal cross- We are aware of only one other study to examine the relationship between volumetric CT measures of the pulmonary vasculature and histologic changes in the pulmonary arterioles, with the Rahaghi study being the other 11 . While not directly relevant to histologic changes, Zhai and colleagues also found that CT-based methods of quantifying pulmonary vascular morphology were able to accurately capture pulmonary vessels using a 3D-printed vascular phantom which included vessels as small as 0.2mm (200µm) in diameter 31 . Our study's strengths include a relatively large cohort size, which is one of the largest to investigate the correlations of radiographic and histologic pulmonary vascular morphology.…”

Compromised Lung Volume and Hemostatic Abnormalities in COVID-19 Pneumonia: Results from an Observational Study on 510 Consecutive Patients

“…The usefulness of quantifying the volume of the compromised lung from a simple unenhanced chest CT performed upon admission resides in the fact that this method can identify minimal changes in voxel units that may not be visible to the unaided eye. Many studies have reported its use in research on interstitial lung diseases, pulmonary sarcoidosis, and pulmonary vascular diseases [17][18][19].…”