Correlation study between DKI and conventional DWI in brain and head and neck tumors.

Purpose: To investigate the relationship between the Diffusion Kurtosis Imaging (DKI) parameters and conventional metrics provided by Diffusion-weighted imaging (DWI) in patients affected by Brain or Head and Neck (HN) cancer.
Methods: Ten patients affected by brain tumor and nine patients with HN tumor underwent a pre-treatment MR examination at 3 T. The largest tumor section was manually contoured by two expert neuroradiologists. The apparent diffusion coefficient (D _app ) and apparent diffusional kurtosis (K _app ) parameters were determined at the voxel level by using the DKI model, and compared to the apparent diffusion coefficient (ADC) and the tissue diffusion coefficient (D _mono ) obtained from mono-exponential fitting methods. The Akaike Information Criteria (AIC) was calculated to assess the quality of the fitting methods. Cross-correlations between all the variables were assessed using the Spearman rank test.
Results: Increased K _app values were found in each lesion. All parameters were strongly related, in particular an inverse relationship emerged between median values of K _app and D _app /D _mono /ADC in both patient groups, while D _app showed positive correlations with D _mono and ADC. From the analysis at the voxel level, significant inverse associations were found between K _app and D _mono within the lesions, while a weak or moderate association emerged between K _app and ADC or D _app .
Conclusions: A significant association between the apparent diffusional kurtosis K _app and the tissue diffusion coefficient D _mono emerged for both brain and HN tumors at 3 T, suggesting that both variables may consistently reflect deeper insight into the microstructural characteristics of tumors.
(Copyright © 2017 Elsevier Inc. All rights reserved.)