To investigate the potential benefits of FDG PET radiomic feature maps (RFMs) for target delineation in non-small cell lung cancer (NSCLC) radiotherapy. Methods: Thirty-two NSCLC patients undergoing FDG PET/CT imaging were included. For each patient, nine grey-level co-occurrence matrix (GLCM) RFMs were generated. gross target volume (GTV) and clinical target volume (CTV) were contoured on CT (GTV CT , CTV CT ), PET (GTV PET40 , CTV PET40 ), and RFMs (GTV RFM , CTV RFM ,). Intratumoral heterogeneity areas were segmented as GTV PET50-Boost and radiomic boost target volume (RTV Boost ) on PET and RFMs, respectively. GTV CT in homogenous tumors and GTV PET40 in heterogeneous tumors were considered as GTV gold standard (GTV GS ). One-way analysis of variance was conducted to determine the threshold that finds the best conformity for GTV RFM with GTV GS . Dice similarity coefficient (DSC) and mean absolute percent error (MAPE) were calculated. Linear regression analysis was employed to report the correlations between the gold standard and RFM-derived target volumes. Results: Entropy, contrast, and Haralick correlation (H-correlation) were selected for tumor segmentation. The threshold values of 80%, 50%, and 10% have the best conformity of GTV RFM-entropy , GTV RFM-contrast , and GTV RFM-H-correlation with GTV GS , respectively. The linear regression results showed a positive correlation between GTV GS and GTV RFM-entropy (r = 0.98, p < 0.001), between GTV GS and GTV RFM-contrast (r = 0.93, p < 0.001), and between GTV GS and GTV RFM-H-correlation (r = 0.91, p < 0.001). The average threshold values of 45% and 15% were resulted in the best segmentation matching between CTV RFM-entropy and CTV RFM-contrast with CTV GS , respectively. Moreover, we used RFM to determine RTV Boost in the heterogeneous tumors. Comparison of RTV Boost with GTV PET50-Boost MAPE showed the volume error differences of 31.7%, 36%, and 34.7% in RTV Boost-entropy , RTV Boost-contrast , and RTV Boost-H-correlation , respectively. Conclusions: FDG PET-based radiomics features in NSCLC demonstrated a promising potential for decision support in radiotherapy, helping radiation oncologists delineate tumors and generate accurate segmentation for heterogeneous region of tumors.