46 patients with a newly diagnosed, histologically verified glioma that was visually classified as [18F]FET-negative were included. Tumor volumes were defined using routine T2/FLAIR MRI data and applied to extract information from dynamic [18F]FET PET data, i.e. early and late tu-mor-to-background (TBR5-15, TBR20-40) images and time-to-peak (TTP) images. Radiomic features of healthy background were calculated from the tumor volume-of-interest mirrored to the con-tralateral hemisphere. Differences between tumor and healthy tissue features were compared us-ing Wilcoxon test. Additionally, the ability to distinguish tumor from healthy tissue was assessed using logistic regression. 5 % of features derived from TBR20-40 images were significantly differ-ent; 16 % of features derived from TBR5-15 images and 69 % of features derived from TTP images. The high number of significantly different features derived from TTP images was even found in isometabolic gliomas (after exclusion of photopenic gliomas) with visually normal [18F]FET up-take in static images. However, the differences did not reach satisfactory predictability for ma-chine learning based identification of tumor tissue. In conclusion, radiomic features derived from dynamic [18F]FET PET data may extract additional information even in [18F]FET-negative glio-mas, which should be investigated in larger cohorts and correlated with histological and out-come features in future studies.