The objective of the study was to evaluate the impact of 18F-fluorodeoxyglucose positron emission tomography/computed tomography (PET/CT) imaging on nodal staging for head and neck cancers. This was a retrospectively analyzed single institution study. The study population consisted of 36 patients with head and neck cancers who were evaluated with PET/CT and went on to neck dissection. All of them had clinically and radiographically negative neck (N-0) and each patient underwent PET/CT imaging before undergoing selective neck dissection for N-0 disease. Tissues were submitted for histopathologic examination and were oriented for the pathologist to permit correlation between the histopathologic findings and the imaging results. The sizes of the lymph nodes and the maximum standardized uptake values (SUVmax) measured from PET/CT images were compared with the histopathologic findings. All primary tumors were visualized with PET/CT. On histopathological examination, 19 patients had positive and 17 patients had negative lymph nodes. Receiver operating characteristic analyses were used to predict the optimal corrected SUVmax cutoffs; the optimal value was 2.95 for respective outcomes of lymph node involvement. This cutoff value yielded 84.2 % sensitivity and 76.5 % specificity for nodal-level staging. PET/CT proved to be accurate in 27 (75 %) patients and inaccurate in 9 (25 %) patients. PET/CT was a valuable tool to assess nodal stage of head and neck cancers, and should be considered before surgical treatment.