Background: In patients with non-small cell lung cancer (NSCLC), interstitial lung abnormalities (ILA) have been linked to mortality and can be identified on computed tomography (CT) scans. In the present study we aimed to evaluate the predictive value of automatically quantified ILA based on the Fleischner Society definition in patients with stage I NSCLC.
Methods: We retrospectively reviewed 948 patients with pathological stage I NSCLC who underwent pulmonary resection between April 2009 and October 2022. A commercially available deep learning-based automated quantification program for ILA was used to evaluate the preoperative CT data. The Fleischner Society definition, quantitative results, and interdisciplinary discussion led to the division of patients into normal and ILA groups. The sum of the fibrotic and nonfibrotic ILA components constituted the total ILA component and more than 5%.
Results: Of the 948 patients with stage I NSCLC, 99 (10.4%) patients had ILA. Shorter overall survival and recurrence-free survival was associated with the presence of ILA. After controlling for confounding variables, the presence of ILA remained significant for increased risk of death (hazard ratio [HR] = 3.09; 95% confidence interval [CI]: 1.91-5.00; p < 0.001) and the presence of ILA remained significant for increased recurrence (HR = 1.96; 95% CI: 1.16-3.30; p = 0.012).
Conclusions: The automated CT quantification of ILA, based on the Fleischner Society definition, was significantly linked to poorer survival and recurrence in patients with stage I NSCLC.
Keywords: computed tomography; deep learning; interstitial lung abnormality; lung cancer.
© 2024 The Authors. Thoracic Cancer published by John Wiley & Sons Australia, Ltd.