Diffusion-weighted imaging of nasopharyngeal carcinoma to predict distant metastases

Our study aimed to identify diffusion-weighted imaging (DWI) parameters obtained from primary nasopharyngeal carcinoma (NPC) at initial presentation, that can predict patients at risk of distant metastases. One hundred and sixty-four patients underwent pretreatment magnetic resonance imaging and DWI. The apparent diffusion coefficient (ADC)_mean, ADC_skewness, and ADC_kurtosis were obtained by histogram analysis. Univariate and multivariate analyses of these ADC parameters together with primary volume (PV), nodal volume (NV), T stage, N stage and presence of locoregional relapse (LRR) were compared between patients with distant metastases (DM+) and patients without distant metastases (DM-) at 5 years using logistic regression. Twenty-eight out of 164 patients (17.1 %) were DM+ (2.5-60 months) and 136/164 patients were DM- (61.2-119.4 months). Compared to DM- patients, the primary tumour of DM+ patients showed significantly lower ADC_skewness (ADC values with the greatest frequency were higher) (p = 0.041), and higher PV (p = 0.022), NV (p < 0.01), T stage (p = 0.023), N stage (p < 0.01) and LRR (p < 0.01). On multivariate analysis the ADC_skewness was no longer significant (p = 0.120) and only NV and LRR were independent predictors for DM+ (p = 0.023 and 0.021, respectively). DWI showed that compared to DM- patients, DM+ patients had a significantly lower primary tumour ADC_skewness, but at initial presentation NV was the only independent predictor of DM.