Automated quantification of airway wall thickness on chest CT using retina U-Nets – Performance evaluation and application to a large cohort of chest CTs of COPD patients

•An AI algorithm pipeline allows for automated measurement of airway wall thickness on CT.•Walls of airway generations 3–8 were significantly thicker in COPD patients compared to controls.•A classifier combining average airway wall thickness with an emphysema score was successfully differentiated CTs of COPD patients from CTs of controls.•Airway wall thickness could complement the CT emphysema scoring (%LAV-950) in lung disease in the future. Airway wall thickening is a consequence of chronic inflammatory processes and usually only qualitatively described in CT radiology reports. The purpose of this study is to automatically quantify airway wall thickness in multiple airway generations and assess the diagnostic potential of this parameter in a large cohort of patients with Chronic Obstructive Pulmonary Disease (COPD). This retrospective, single-center study included a series of unenhanced chest CTs. Inclusion criteria were the mentioning of an explicit COPD GOLD stage in the written radiology report and time period (01/2019–12/2021). A control group included chest CTs with completely unremarkable lungs according to the report. The DICOM images of all cases (axial orientation; slice-thickness: 1 mm; soft-tissue kernel) were processed by an AI algorithm pipeline consisting of (A) a 3D-U-Net for det detection and tracing of the bronchial tree centerlines (B) extraction of image patches perpendicular to the centerlines of the bronchi, and (C) a 2D U-Net for segmentation of airway walls on those patches. The performance of centerline detection and wall segmentation was assessed. The imaging parameter average wall thickness was calculated for bronchus generations 3–8 (AWT3-8) across the lungs. Mean AWT3-8 was compared between five groups (control, COPD Gold I-IV) using non-parametric statistics. Furthermore, the established emphysema score %LAV-950 was calculated and used to classify scans (normal vs. COPD) alone and in combination with AWT3-8. A total of 575 chest CTs were processed. Algorithm performance was very good (airway centerline detection sensitivity: 86.9%; airway wall segmentation Dice score: 0.86). AWT3-8 was statistically significantly greater in COPD patients compared to controls (2.03 vs. 1.87 mm, p