Deep Learning Estimation of Small Airway Disease from Inspiratory Chest Computed Tomography: Clinical Validation, Repeatability, and Associations with Adverse Clinical Outcomes in Chronic Obstructive Pulmonary Disease.
Authors
Affiliations (15)
Affiliations (15)
- The Roy J. Carver Department of Biomedical Engineering, University of Iowa, Iowa City, Iowa.
- Center for Lung Analytics and Imaging Research, Division of Pulmonary, Allergy and Critical Care Medicine, University of Alabama at Birmingham, Birmingham, Alabama.
- Division of Pulmonary, Critical Care and Occupational Medicine, Department of Internal Medicine, and.
- Division of Pulmonary and Critical Care Medicine and.
- Department of Epidemiology, Mailman School of Public Health, Columbia University, New York, New York.
- Department of Physiology, David Geffen School of Medicine at UCLA, Los Angeles, California.
- Department of Radiology, University of Michigan, Ann Arbor, Michigan.
- Division of Pulmonary and Critical Care Medicine, University of Michigan Health System, Ann Arbor, Michigan.
- Department of Medicine, Johns Hopkins School of Medicine, Baltimore, Maryland.
- Breathe Chicago Center, University of Illinois at Chicago, Chicago, Illinois.
- Department of Radiology, University of Illinois College of Medicine at Chicago, Chicago, Illinois.
- University of Massachusetts Chan Medical School, Worcester, Massachusetts.
- Wake Forest University School of Medicine, Winston-Salem, North Carolina; and.
- Division of Respiratory, Critical Care and Occupational Pulmonary Medicine, University of Utah, Salt Lake City, Utah.
- Department of Radiology, University of Iowa Roy J. and Lucille A. Carver College of Medicine, Iowa City, Iowa.
Abstract
<b>Rationale:</b> Quantifying functional small airway disease (fSAD) requires additional expiratory computed tomography (CT) scans, limiting clinical applicability. Artificial intelligence (AI) could enable fSAD quantification from chest CT scans at total lung capacity (TLC) alone (fSAD<sup>TLC</sup>). <b>Objectives:</b> To evaluate an AI model for estimating fSAD<sup>TLC</sup>, compare it with dual-volume parametric response mapping fSAD (fSAD<sup>PRM</sup>), and assess its clinical associations and repeatability in chronic obstructive pulmonary disease (COPD). <b>Methods:</b> We analyzed 2,513 participants from SPIROMICS (the Subpopulations and Intermediate Outcome Measures in COPD Study). Using a randomly sampled subset (<i>n</i> = 1,055), we developed a generative model to produce virtual expiratory CT scans for estimating fSAD<sup>TLC</sup> in the remaining 1,458 SPIROMICS participants. We compared fSAD<sup>TLC</sup> with dual-volume fSAD<sup>PRM</sup>. We investigated univariate and multivariable associations of fSAD<sup>TLC</sup> with FEV<sub>1</sub>, FEV<sub>1</sub>/FVC ratio, 6-minute-walk distance, St. George's Respiratory Questionnaire score, and FEV<sub>1</sub> decline. The results were validated in a subset of patients from the COPDGene (Genetic Epidemiology of COPD) study (<i>n</i> = 458). Multivariable models were adjusted for age, race, sex, body mass index, baseline FEV<sub>1</sub>, smoking pack-years, smoking status, and percent emphysema. <b>Measurements and Main Results:</b> Inspiratory fSAD<sup>TLC</sup> showed a strong correlation with fSAD<sup>PRM</sup> in SPIROMICS (Pearson's <i>R</i> = 0.895) and COPDGene (<i>R</i> = 0.897) cohorts. Higher fSAD<sup>TLC</sup> levels were significantly associated with lower lung function, including lower postbronchodilator FEV<sub>1</sub> (in liters) and FEV<sub>1</sub>/FVC ratio, and poorer quality of life reflected by higher total St. George's Respiratory Questionnaire scores independent of percent CT emphysema. In SPIROMICS, individuals with higher fSAD<sup>TLC</sup> experienced an annual decline in FEV<sub>1</sub> of 1.156 ml (relative decrease; 95% confidence interval [CI], 0.613-1.699; <i>P</i> < 0.001) per year for every 1% increase in fSAD<sup>TLC</sup>. The rate of decline in the COPDGene cohort was slightly lower at 0.866 ml/yr (relative decrease; 95% CI, 0.345-1.386; <i>P</i> < 0.001) per 1% increase in fSAD<sup>TLC</sup>. Inspiratory fSAD<sup>TLC</sup> demonstrated greater consistency between repeated measurements, with a higher intraclass correlation coefficient of 0.99 (95% CI, 0.98-0.99) compared with fSAD<sup>PRM</sup> (0.83; 95% CI, 0.76-0.88). <b>Conclusions:</b> Small airway 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<sup>PRM</sup>, demonstrates a significant association with FEV<sub>1</sub> decline, and offers greater repeatability.