The prognostic value of 18F-FDG PET-derived whole-body feature in patients with lung adenocarcinoma treated with EGFR-targeted therapy.

Abstract

Objective: To evaluate the prognostic values of ¹⁸F-FDG PET-derived whole-body imaging features in patients with metastatic lung adenocarcinoma treated with EGFR-targeted therapies.

Methods: We retrospectively analyzed 249 patients with lung adenocarcinoma who underwent pre-treatment ¹⁸F-FDG PET and were treated with EGFR-targeted agents. The patients were divided into analog (n = 150) and digital (n = 99) PET cohorts. Whole-body and primary tumor respiratory-stable imaging features were extracted. The prognostic values of the study variables for progression-free (PFS) and overall survival (OS) were assessed using univariate and multivariate Cox regression analyses across the analog and digital PET cohorts.

Results: Total sphericity and primary tumor inverse difference normalized were independent predictors of both PFS and OS. The total metabolic tumor volume was another independent predictor of OS. Combined models integrating these imaging biomarkers with clinical variables outperformed the traditional staging system (c-indices for PFS: 0.649 versus 0.550 for analog and 0.668 versus 0.583 for digital PET cohorts; for OS: 0.694 versus 0.562 for analog and 0.728 versus 0.579 for digital PET cohorts). Our models showed consistent predictive values across subgroups based on sex, EGFR mutation subtype, and clinical stage.

Conclusions: Our results indicate that models integrating whole-body ¹⁸F-FDG PET features with traditional variables can enhance survival prediction and may support personalized treatment strategies for patients with lung adenocarcinoma treated with EGFR-targeted therapies.