Deep Learning Estimation of Small Airways Disease from Inspiratory Chest CT is Associated with FEV1Decline in COPD

Abstract

ABSTRACTRationaleQuantifying 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 (fSADTLC).ObjectivesTo evaluate an AI model for estimating fSADTLCand study its clinical associations in chronic obstructive pulmonary disease (COPD).MethodsWe analyzed 2513 participants from the SubPopulations and InteRmediate Outcome Measures in COPD Study (SPIROMICS). Using a subset (n= 1055), we developed a generative model to produce virtual expiratory CTs for estimating fSADTLCin the remaining 1458 SPIROMICS participants. We compared fSADTLCwith dual volume, parametric response mapping fSADPRM. We investigated univariate and multivariable associations of fSADTLCwith FEV1, FEV1/FVC, six-minute walk distance (6MWD), St. George’s Respiratory Questionnaire (SGRQ), and FEV1decline. The results were validated in a subset (n= 458) from COPDGene study. Multivariable models were adjusted for age, race, sex, BMI, baseline FEV1, smoking pack years, smoking status, and percent emphysema.Measurements and Main ResultsInspiratory fSADTLCwas highly correlated with fSADPRMin SPIROMICS (Pearson’s R = 0.895) and COPDGene (R = 0.897) cohorts. In SPIROMICS, fSADTLCwas associated with FEV1(L) (adj.β = −0.034,P< 0.001), FEV1/FVC (adj.β = −0.008,P< 0.001), SGRQ (adj.β = 0.243,P< 0.001), and FEV1decline (mL / year) (adj.β = −1.156,P< 0.001). fSADTLCwas also associated with FEV1(L) (adj.β = −0.032,P< 0.001), FEV1/FVC (adj.β = −0.007,P< 0.001), SGRQ (adj.β = 0.190,P= 0.02), and FEV1decline (mL / year) (adj.β = - 0.866,P= 0.001) in COPDGene. We found fSADTLCto be more repeatable than fSADPRMwith intraclass correlation of 0.99 (95% CI: 0.98, 0.99) vs. 0.83 (95% CI: 0.76, 0.88).ConclusionsInspiratory fSADTLCcaptures small airways disease as reliably as fSADPRMand is associated with FEV1decline.Funding SourceThis work was supported by NHLBI grants R01 HL142625, U01 HL089897 and U01 HL089856, by NIH contract 75N92023D00011, and by a grant from The Roy J. Carver Charitable Trust (19-5154). The COPDGene study (NCT00608764) has also been supported by the COPD Foundation through contributions made to an Industry Advisory Committee that has included AstraZeneca, Bayer Pharmaceuticals, Boehringer-Ingelheim, Genentech, GlaxoSmithKline, Novartis, Pfizer, and Sunovion.