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

ObjectivesComputed 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.MethodsA 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.ResultsOf 376 CT scans, 374 (99%) were successfully measured. Segmented airway trees contained a mean of 10 generations and 250 branches. The coefficient of determination (R-2) for the luminal area (LA) ranged from 0.93 at the trachea to 0.68 at the 6(th) generation, decreasing to 0.51 at the 8(th) 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 2-6(th) generations). From the 7(th) generation onwards, there was a sharp decrease in reproducibility and a widening LoA.ConclusionThe 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 6(th) generation.