Does a computational vascular morphometry approach based on scale-space particles track vascular remodeling in CT scans of patients with COPD?
A novel computational vascular morphometry approach using scale-space particles can automatically extract lung vasculature and track vascular remodeling in COPD patients using CT scans.
We present a fully automatic computational vascular morphometry (CVM) approach for the clinical assessment of pulmonary vascular disease (PVD). The approach is based on the automatic extraction of the lung intraparenchymal vasculature using scale-space particles. Based on the detected features, we developed a set of image-based biomarkers for the assessment of the disease using the vessel radii estimation provided by the particle's scale. The biomarkers are based on the interrelation between vessel cross-section area and blood volume. We validate our vascular extraction method using simulated data with different complexity and we present results in 2,500 CT scans with different degrees of chronic obstructive pulmonary disease (COPD) severity. Results indicate that our CVM pipeline may track vascular remodeling present in COPD and it can be used in further clinical studies to assess the involvement of PVD in patient populations.
Estépar et al. (Tue,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: