Ahn HK, et al. - Researchers used a machine learning approach in patients with non-small cell lung cancer (NSCLC) to evaluate the prognostic value of 2-[¹⁸F]-fluoro-2-deoxy-d-glucose (FDG) positron-emission tomography (PET)-based radiomics. The study sample consisted of 93 patients with stage I–III NSCLC who had combined PET/computed tomography (CT) followed by curative resection. Findings suggested that PET-based radiomics in NSCLC can be measured reliably. PET-based radiomic characteristics are promising imaging biomarkers in NSCLC for tumor recurrence. A radiomic model based on PET with a random forest classifier might help clinicians improve risk stratification.