Diffusion Kurtosis Imaging and Radiomics in Diffuse Axonal Injury

Abstract

This study aimed to assess the feasibility of radiomic features derived from diffusion kurtosis imaging (DK MRI) in identifying microstructural brain damage in diffuse axonal injury (DAI) and predicting its outcome. We hypothesized that radiomic features, computed from parametric DK MRI maps, may differ between healthy individuals and those with trauma, and may be related to DAI outcomes. The study included 31 DAI patients and 12 healthy volunteers. A total of 342,300 radiomic features were calculated (2282 features for each combination of 10 parametric DK maps with 15 regions of interest). Our findings suggest that the set of radiomic features effectively distinguishes between healthy and damaged brain tissues, and can predict DAI outcome. A broad spectrum of radiomic parameters based on DK MRI data showed high diagnostic and prognostic potential in DAI, presenting advantages beyond the traditionally used average values for the regions of interest on parametric DK MRI maps.