Radiomics of the Airway (RadAr): Multi-Scale Airway Phenotyping for Disease Characterization on Routine CT Imaging.

Background: Airway remodeling is a convergent feature across respiratory diseases, yet current quantitative CT tools quantify a small number of prespecified structural abnormalities of the airway tree. Radiomics of the Airway (RadAr) derives interpretable, multi-scale airway measurements from chest CT to characterize airway deformation and discover quantitative imaging biomarkers from routine chest CT. Methods: RadAr extracts over 400 multi-scale, interpretable airway measurements across lobes or generations capturing luminal dimensions, tapering, architectural distortion, and global morphology. It was evaluated in N=1331 patients across four settings: 63-week mortality prediction in fibrotic interstitial lung disease (fILD), COVID-19 severity prediction, structure-function association in progressive pulmonary fibrosis (PPF) and structure-inflammation markers in pediatric cystic fibrosis (CF). Unsupervised clustering was used to identify airway phenotypes across the fILD and COVID-19 cohorts. Results: In fILD, lower-lobe architectural distortion was associated with mortality (balanced accuracy 0·654). In COVID-19, severe disease was independently associated with luminal dilation (AUC 0·719, odds ratio 2·32, p=0·017). In PPF, airway phenotypes correlated with forced vital capacity (ρ=0·83), mid-expiratory flow (ρ=0·87), and Conclusion: RadAr identified interpretable, disease-specific airway phenotypes associated with function and outcomes across restrictive, obstructive, and mixed lung diseases in adult and pediatric settings. These findings establish a framework for discovery and development of quantitative airway biomarkers for patient stratification, disease monitoring, or imaging endpoint development in pulmonary trials.