Deep Learning Estimation of Small Airways Disease from Inspiratory Chest CT: Clinical Validation, Repeatability, and Associations with Adverse Clinical Outcomes in COPD.

RATIONALE

Quantifying functional small airways disease (fSAD) requires additional expiratory computed tomography (CT) scan, limiting clinical applicability. Artificial intelligence (AI) could enable fSAD quantification from chest CT scan at total lung capacity (TLC) alone (fSAD).

OBJECTIVES

To evaluate an AI model for estimating fSAD, compare it with dual-volume parametric response mapping fSAD (fSAD), and assess its clinical associations and repeatability in chronic obstructive pulmonary disease (COPD).

METHODS

We analyzed 2513 participants from the SubPopulations and InteRmediate Outcome Measures in COPD Study (SPIROMICS). Using a randomly sampled subset ( = 1055), we developed a generative model to produce virtual expiratory CTs for estimating fSAD in the remaining 1458 SPIROMICS participants. We compared fSAD with dual volume, parametric response mapping fSAD. We investigated univariate and multivariable associations of fSAD with FEV, FEV/FVC, six-minute walk distance (6MWD), St. George's Respiratory Questionnaire (SGRQ), and FEV decline. The results were validated in a subset ( = 458) from COPDGene study. Multivariable models were adjusted for age, race, sex, BMI, baseline FEV, smoking pack years, smoking status, and percent emphysema.

MEASUREMENTS AND MAIN RESULTS

Inspiratory fSAD showed a strong correlation with fSAD in both SPIROMICS (Pearson's R = 0.895) and COPDGene (R = 0.897) cohorts. Higher fSAD levels were significantly associated with lower lung function, including lower postbronchodilator FEV (L) and FEV/FVC ratio, and poorer quality of life reflected by higher total SGRQ scores, independent of percent CT emphysema. In SPIROMICS, individuals with higher fSAD experienced an annual decline in FEV of 1.156 mL (relative decrease; 95% CI: 0.613, 1.699; < 0.001) per year for every 1% increase in fSAD. The rate of decline in COPDGene was slightly lower at 0.866 mL / year (relative decrease; 95% CI: 0.345, 1.386; < 0.001) for percent increase in fSAD. Inspiratory fSAD demonstrated greater consistency between repeated measurements with a higher intraclass correlation coefficient (ICC) of 0.99 (95% CI: 0.98, 0.99) compared to fSAD [ICC: 0.83 (95% CI: 0.76, 0.88)].

CONCLUSIONS

Small airways disease can be reliably assessed from a single inspiratory CT scan using generative AI, eliminating the need for an additional expiratory CT scan. fSAD estimation from inspiratory CT correlates strongly with fSAD, demonstrates a significant association with FEV decline, and offers greater repeatability.