Recently, immune checkpoint inhibitors targeting the programmed death protein 1 (PD-1)/programmed death ligand 1 (PD-L1) axis have become standard of care for patients with advanced non-small cell lung cancer (NSCLC). Tumor immune microenvironment could be classified into four types according to the status of PDL1 expression and CD8+ TIL abundance, while the tumors with tumor microenvironment immune type I (TMIT-I), i.e. with high PD-L1 expression and presence of CD8+ TILs, are more likely to benefit from anti-PD-L1/PD-1 therapies. FDG PET monitors the metabolism of glucose that is actively entrapped as nutrients in neoplastic tissues and tumor-associated activated immune cells. Therefore, FDG PET signals depicting the glucose metabolism are closely related to the characteristics of tumor immune microenvironment. We investigated the correlations between the metabolic parameters (MPs) of dual-time-point FDG PET images and the TMITs in patients with NSCLC, then strived to improve the ability of predicting TMIT-I through FDG PET/CT-based radiomics.