Quantitative CT Imaging Biomarkers of Interstitial Lung Disease Are Associated with Survival in Non–Small Cell Lung Cancer

Background Interstitial lung disease (ILD) is a clinically important but often under-recognized comorbidity in patients with non–small cell lung cancer (NSCLC). Although ILD has been associated with adverse outcomes, objective and reproducible imaging biomarkers for prognostic assessment remain limited. This study aimed to evaluate the prognostic value of quantitative CT-derived ILD features in NSCLC. Methods In this retrospective cohort study, 324 patients with pathologically confirmed NSCLC and coexisting ILD were included. Automated CT-based segmentation was applied to quantify tumor volume and ILD-related components, including ground-glass opacity, emphysema, honeycombing, and fibrosis. Fibrosis was defined as the sum of reticulation, traction bronchiectasis, and honeycombing, with honeycombing analyzed as an independent subtype. Visual assessment was independently performed by two experienced radiologists. Cox proportional hazards regression was used to identify prognostic factors for overall survival (OS). Prognostic models were constructed using clinical variables, quantitative CT features, and their combinations. Results In multivariable Cox analysis, both honeycombing volume and total fibrosis volume were independently associated with poorer OS after adjustment for clinical covariates. Prognostic models incorporating quantitative CT features demonstrated improved discrimination compared with clinical variables alone. The combined model integrating clinical variables, quantitative CT features, and radiologists’ visual assessment achieved the best overall performance. Conclusions Quantitative CT imaging biomarkers of ILD are independently associated with survival in patients with NSCLC. Integrating objective imaging-derived ILD features with clinical evaluation may improve risk stratification and support individualized management in this patient population.