CT texture analysis as predictive factor in metastatic lung adenocarcinoma treated with tyrosine kinase inhibitors (TKIs)

PURPOSE: To assess the predictive and prognostic value of pre-treatment CT texture features in lung adenocarcinoma treated with tyrosine kinase inhibitors (TKI). MATERIALS AND METHODS: Texture analysis was performed using commercially available software (TexRAD Ltd, Cambridge, UK) on pre-treatment contrast-enhanced CT studies from 50 patients with metastatic lung adenocarcinoma treated by TKI. Texture features were quantified on a 5-mm-thick central slice of the primary tumor and were correlated with progression-free and overall survival (PFS and OS) using an internally cross-validated machine learning approach then validated on a bootstrapped sample. RESULTS: Median PFS and OS were 10.5 and 20.7 months, respectively. A noninvasive signature based on five texture parameters predicted 6-month progression with Area Under the Curve (AUC) of 0.8 (95% CI) and 1-year progression with AUC of 0.76. A high-risk group had hazard ratios for progression of 4.63 and 5.78 when divided by median and best cut-off points, respectively. Texture signature did not correlate with OS. Available clinical variables did not correlate with PFS or with OS. CONCLUSION: Texture features seem to be associated with PFS in lung adenocarcinoma treated with TKI