Radiomics of the Airway (RadAr): Multi-Scale Airway Phenotyping for Disease Characterization on Routine CT Imaging
- 1Emory University
Abstract
BackgroundAirway 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.
MethodsRadAr 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.
ResultsIn fILD, lower-lobe architectural distortion was associated with mortality (balanced accuracy 0{middle dot}654). In COVID-19, severe disease was independently associated with luminal dilation (AUC 0{middle dot}719, odds ratio 2{middle dot}32, p=0{middle dot}017). In PPF, airway phenotypes correlated with forced vital capacity ({rho}=0{middle dot}83), mid-expiratory flow ({rho}=0{middle dot}87), and {superscript 1}{superscript 2}Xe MRI alveolar gas exchange impairment ({rho}=0{middle dot}70). In pediatric CF, reduced tapering and increased cylindricity were associated with prior exacerbations and bronchoalveolar lavage neutrophilia ({rho}=-0{middle dot}64 to -0{middle dot}78). Five phenotypes were identified from extensive, tapered airway trees to sparse, dilated, thick-walled, tortuous trees, with increasing COVID-19 severity and fILD mortality across this spectrum.
ConclusionRadAr 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.
Related
- Multimodal Retinal Imaging for Systemic Microvascular Phenotyping: Chronic Kidney Disease as a Translational Reference Model
- Leukocyte-to-HDL Ratios for Symptomatic Phenotyping in Heart Failure: Head-to-Head Comparison of Routine Inflammatory Indices and Benchmarking Against NT-proBNP
- Routine cine cardiovascular magnetic resonance for clinical phenotyping and serial assessment of heart failure with preserved ejection fraction: a retrospective single-center clinical analysis
- Artificial Intelligence in Oncologic Imaging: Deep Learning, Radiomics, and Clinical Integration for Precision Cancer Diagnosis
- Magnetic resonance imaging-based radiomics for predicting P53-mutated hepatocellular carcinoma: intratumoral and peritumoral analysis
BibTeX
@misc{mutha2026radiomics,
title = {{Radiomics of the Airway (RadAr): Multi-Scale Airway Phenotyping for Disease Characterization on Routine CT Imaging}},
author = {P. Mutha and J. Lee and G. L. Silva and B. Dreihuys and Z. Healy and D. Mummy and B. Kaul and S. Ram and R. Tirouvanziam and L. Guglani and A. Madabhushi},
howpublished = {medRxiv},
year = {2026},
month = jul,
doi = {10.64898/2026.07.19.26358441},
url = {https://www.medrxiv.org/content/10.64898/2026.07.19.26358441v2},
note = {CC BY-NC},
}
RIS
TY - UNPB
TI - Radiomics of the Airway (RadAr): Multi-Scale Airway Phenotyping for Disease Characterization on Routine CT Imaging
AU - P. Mutha
AU - J. Lee
AU - G. L. Silva
AU - B. Dreihuys
AU - Z. Healy
AU - D. Mummy
AU - B. Kaul
AU - S. Ram
AU - R. Tirouvanziam
AU - L. Guglani
AU - A. Madabhushi
PY - 2026
DA - 2026/07/19
PB - medRxiv
DO - 10.64898/2026.07.19.26358441
UR - https://www.medrxiv.org/content/10.64898/2026.07.19.26358441v2
AB - BackgroundAirway 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. MethodsRadAr 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. ResultsIn fILD, lower-lobe architectural distortion was associated with mortality (balanced accuracy 0{middle dot}654). In COVID-19, severe disease was independently associated with luminal dilation (AUC 0{middle dot}719, odds ratio 2{middle dot}32, p=0{middle dot}017). In PPF, airway phenotypes correlated with forced vital capacity ({rho}=0{middle dot}83), mid-expiratory flow ({rho}=0{middle dot}87), and {superscript 1}{superscript 2}Xe MRI alveolar gas exchange impairment ({rho}=0{middle dot}70). In pediatric CF, reduced tapering and increased cylindricity were associated with prior exacerbations and bronchoalveolar lavage neutrophilia ({rho}=-0{middle dot}64 to -0{middle dot}78). Five phenotypes were identified from extensive, tapered airway trees to sparse, dilated, thick-walled, tortuous trees, with increasing COVID-19 severity and fILD mortality across this spectrum. ConclusionRadAr 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.
ER -