Diffusion kurtosis imaging and conventional diffusion weighted imaging to assess electrochemotherapy response in locally advanced pancreatic cancer

Background. The aim of the study was to evaluate diagnostic performance of functional parameters derived by conventional mono-exponential approach of diffusion weighted imaging (DWI) and by diffusion kurtosis imaging (DKI) in the assessment of pancreatic tumours treated with electrochemotherapy (ECT). Patients and methods. Twenty-one consecutive patients with locally advanced pancreatic adenocarcinoma subjected to ECT were enrolled in a clinical approved trial. Among twenty-one enrolled patients, 13/21 (61.9%) patients were subjected to MRI before and after ECT. DWI was performed with a 1.5 T scanner; a free breathing axial single shot echo planar DWI pulse sequence parameters were acquired using seven b value = 0, 50, 100, 150, 400, 800, 1000 s/ mm(2). Apparent diffusion coefficient by conventional mono-exponential approach and mean of diffusion coefficient (MD) and mean of dffusional kurtosis (MK) by DKI approach were derived from DWI. Receiver operating characteristic (ROC) analysis was performed and sensitivity, specificity, positive and negative predictive value were calculated. Results. Among investigated diffusion parameters, only the MD derived by DKI showed a significant variation of values between pre and post treatment (p = 0.02 at Wilcoxon test) and a significant statistically difference for percentage change between responders and not responders (p = 0.01 at Kruskal Wallis test). MD had a good diagnostic performance with a sensitivity of 80%, a specificity of 100% and area under ROC of 0.933. Conclusions. MD derived by DKI allows identifying responders and not responders patients subject to ECT treatment. MD had higher diagnostic performance to assess ECT response compared to conventional DWI derived parameters.