The role of imaging in the surveillance of patients with node-positive advanced-stage head and neck cancer is unclear, and whether patients should undergo a planned neck dissection following primary chemoradiation treatment is controversial. In a prospective, randomized, controlled trial, investigators assessed the noninferiority of PET–CT-guided surveillance to planned neck dissection in patients with stage N2 or N3 nodal disease. At a median follow up of 36 months, PET–CT resulted in fewer neck dissections than planned surgery (54 versus 221). Moreover, the hazard ratio for death slightly favoured PET–CT-guided surveillance, and indicated noninferiority of surveillance compared with planned neck dissection. Survival was similar among patients who underwent PET–CT-guided surveillance and those who had a planned neck dissection; however, surveillance resulted in considerably fewer operations and was more cost-effective, with a saving of UK£1,492 per patient over the course of the trial.