Purpose : The purpose of this study was to evaluate the diagnostic accuracy of [18F]FDG PET in the diagnosis of recurrent head and neck cancer after the completion of surgery and radiotherapy in patients with head and neck cancers. Materials and Methods: In fifty-nine patients with head and neck cancers, whole body [18F]FDG PET studies were performed. According to the different therapeutic modalities, patients were divided into four groups (Group I; pre-treatment, Group II; surgery, Group III; radiotherapy, Group IV; both surgery and radiotherapy). [18F]FDG PET images were compared with clinical, CT and histopathologic findings. Results: For detection of metastatic lymph nodes in 14 patients of pre-treatment group (group I), the sensitivity and specificity of PET were 100% (10/10) and 75% (3/4), and those of CT were 80% (8/10) and 100% (4/4). For detection of recurrence in 45 patients of post-treatment group, overall sensitivity and specificity of PET were 96.2% (25/26) and 78.9% (15/19) [(100% and 75% in group II, 80% and 50% in group III, and 100% and 100% in group IV)] without significant difference from pre-treatment group (P>0.1). In detecting recurrence, the sensitivity and specificity of [18F]FDG PET were 90.9% (10/11) and 20% (1/5) in 16 patients who underwent [18F]FDG PET within 2 months after the completion of treatment. The specificity of these patients was significantly lower than that of 29 patients (100% of sensitivity and specificity) who underwent [18F]FDG PET 2 months after treatment (P<0.05). Conclusion: [18F]FDG PET is an accurate diagnostic modality for the detection of recurrence in head and neck cancer. Post-therapy [18F]FDG PET should be obtained at least 2 months after the completion of surgery or radiotherapy.