Expiration CT Gas Trapping Measures with Texture-Based Radiomics Improves Association with Lung Function and Lung Function Decline in COPD.

Rationale And Objectives: Several methods quantify gas-trapping on expiration computed tomography (CT) images, but they do not consider the spatial relationship of voxels. The objective of this study was to determine if the addition of expiration CT texture-based radiomics features to existing gas-trapping measurements improves model performance for lung function, lung function decline, COPD classification and visual gas-trapping.

Materials And Methods: CanCOLD participants performed spirometry, plethysmography and CT chest imaging at full-inspiration/expiration with radiologist-assessed gas-trapping. Quantitative CT measurements were performed: low attenuation areas≤-856HU (LAA), ratio of expiratory-to-inspiratory mean lung attenuation (E/I MLA), and difference between expiratory-inspiratory lung volumes between -856 and -950 HU (RVC). Texture-based radiomics analysis generated 95 features; LASSO regression coefficients were summed to create a representative variable (RadScore). Multivariable linear regression models determined associations for baseline RV/TLC, FEV/FVC, FEV, FEF, and 6-year ΔFEV, with established CT gas-trapping and RadScore. Binary logistic regression determined associations for COPD classification and visual gas-trapping.

Results: 1111 participants were investigated (n=234 never-smokers, n=325 at-risk, n=314 mild COPD, n=238 moderate-severe COPD). In separate models for baseline RV/TLC, FEV/FVC, FEV, and FEF, ΔFEV, COPD classification and visual gas-trapping, all CT gas-trapping and CT RadScore measurements were independently significant (p<0.05). When CT gas-trapping and CT RadScore were included in the same model, all model performance metrics improved significantly (p<0.05).

Conclusion: CT measures extracted from full-expiratory images that quantify the distribution, not just extent, of gas-trapping provide important information related to lung function and lung function decline in COPD.

Summary Statement: Full-expiratory CT texture-based radiomics improves model performance when used in combination with conventional gas-trapping measurements for lung function and lung function decline, COPD classification and presence of visual gas-trapping.