ObjectiveTo evaluate the accuracy of diffusion‐weighted magnetic resonance imaging (DWI‐MRI) in diagnosing persistent/recurrent head and neck squamous cell carcinomas (HNSCCs) after primary chemoradiotherapy (CRT).Data SourcesScopus, PubMed/MEDLINE, and Cochrane Library databases were searched for relevant publications until April 18, 2023.Review MethodsA systematic review and meta‐analysis was performed according to the Preferred Reporting Items for Systematic Reviews and Meta‐analyses of Diagnostic Test Accuracy statement. The search was conducted independently by 2 investigators. Methodological quality of included studies was assessed using the Quality Assessment of Diagnostic Studies‐2 questionnaire. Extracted data were used to calculate the pooled DWI‐MRI sensitivity, specificity, diagnostic odds ratio, and positive and negative likelihood ratio.ResultsA total of 618 patients from 10 studies were included for calculation of diagnostic accuracy parameters. At the level of the primary tumor, the pooled sensitivity and specificity were, respectively, 0.96 (95% confidence interval [CI]: 0.89‐1.00) and 0.81 (95% CI: 0.54‐0.98) in the case of qualitative analysis, and, respectively, 0.79 (95% CI: 0.66‐0.89) and 0.88 (95% CI: 0.77‐0.96) for quantitative analysis. At the level of the neck, the pooled sensitivity and specificity were, respectively, 0.87 (95% CI: 0.75‐0.95) and 0.84 (95% CI: 0.74‐0.93) when images were analyzed qualitatively, and 0.79 (95% CI: 0.60‐0.94) and 0.90 (95% CI: 0.82‐0.97) when analyzed quantitatively.ConclusionDWI‐MRI showed high diagnostic accuracy and should be considered if persistent/recurrent HNSCCs is suspected after primary CRT. No significant differences were found between qualitative and quantitative imaging assessment.