Parotid Pleomorphic Adenoma and Apparent Diffusion Coefficient: A Novel Clinical Prediction Tool

ABSTRACT Objectives Pleomorphic adenoma (PA) is the most common benign salivary gland tumor. MRI is a non‐invasive diagnostic tool, but its sensitivity and specificity varies. Incorporating diffusion‐weighted imaging (DWI) and quantitative apparent diffusion coefficient (ADC) assessment may enhance preoperative diagnosis. Our primary objective was to determine if including these variables in a clinical tool would enhance the diagnostic utility of MRI. Methods A retrospective study was conducted at Weill Cornell Medical Center, including patients with parotid masses who underwent surgical resection and preoperative MRI (2006–2022). Patient and MRI characteristics, including ADC values, were analyzed to identify predictors of PA. A logistic regression model was developed and internally validated. Results Among 157 patients, 86 (55%) had PA. MRI sensitivity and specificity for PA were 56% and 96%, respectively. Key predictors of PA included higher ADC values ( p < 0.001), T2 hyperintense signal ( p = 0.006), lobulated tumor contour ( p = 0.021), and absence of dumbbell shape ( p = 0.047). The final model achieved a sensitivity of 83% and specificity of 82%, with an area under the curve of 0.87. False negatives were significantly associated with lower ADC values, qualitative diffusion restriction, non‐uniform tumor enhancement pattern, and intermediate/hypointense T2 signal. Conclusion Qualitative MRI features combined with quantitative ADC values offer a non‐invasive, accurate approach for diagnosing PA. The proposed clinical calculator enhances preoperative planning, though external validation is warranted. Level of Evidence: 3.