BACKGROUND AND PURPOSE: Epilepsy, a globally prevalent neurological disorder, necessitates precise identification of the epileptogenic zone (EZ) for effective surgical management. While the individual utilities of FDG PET and FMZ PET have been demonstrated, their combined efficacy in localizing the epileptogenic zone remains underexplored. We aim to improve the non-invasive prediction of epileptogenic zone (EZ) in temporal lobe epilepsy (TLE) by combining FDG PET and FMZ PET with statistical feature extraction and machine learning. MATERIALS AND METHODS: This study included 20 drug-resistant unilateral TLE patients (14 mesial TLE, 6 lateral TLE), and two control groups (N=29 for FDG, N=20 for FMZ). EZ of each patient was confirmed by post-surgical pathology, and one-year follow-up, while propagation zone (PZ) and non-involved zone (NIZ) were derived from the epileptogenicity index based on presurgical stereo-encephalography (SEEG) monitoring. Whole brain PET scans were obtained with dual tracers [ RESULTS: FDG SUVR significantly decreased in EZ and PZ compared to NIZ, while FMZ SUVR in EZ significantly differed from PZ. Interaction effects were found between FDG and FMZ in their prediction of epileptogenicity. Fusion of FDG and FMZ provided the best prediction model with an area under the curve (AUC) of 0.86 [0.84-0.87] for EZ vs. NIZ and an AUC of 0.79 [0.77-0.81] for EZ vs. PZ, eliminating 100% false positives in 50% of patients, and ≥80% FPs in 90% patients at patient level. CONCLUSIONS: Combined FDG and FMZ offer a promising avenue for non-invasive localization of the epileptogenic zone in TLE, potentially refining surgical planning. ABBREVIATIONS: AUC = Area under the curve
EI = Epileptogenicity index
EZ = Epileptogenic zone
FMZ = Flumazenil
GABA