Characterize the non-Gaussian diffusion property of cerebrospinal fluid using Diffusion Kurtosis Imaging and explore its diagnostic efficacy for Alzheimer's disease

TL;DR

This study uses diffusion kurtosis imaging to characterize non-Gaussian diffusion in cerebrospinal fluid, revealing potential diagnostic markers for Alzheimer's disease with high accuracy.

Contribution

It demonstrates the application of DKI to differentiate AD patients from healthy controls and develops a highly accurate SVM-based prediction model.

Findings

Significant differences in CSF diffusion properties between AD and controls

High diagnostic accuracy with AUC of 0.96-1.00

Prediction accuracy of 87.1%-90.0%

Abstract

Differentiating Alzheimer's disease (AD) patients from healthy controls (HCs) remains a challenge. The changes of protein level in cerebrospinal fluid (CSF) of AD patients have been reported in the literature. Macromolecules will hinder the movement of water in CSF and lead to non-Gaussian diffusion. Diffusion kurtosis imaging (DKI) is a commonly used technique for quantifying non-Gaussian diffusivity. In this study, we used DKI to evaluate the non-Gaussian diffusion of CSF in AD patients and HC. Between-group difference was explored. In addition, we have built a prediction model using cross-validation Support Vector Machines (SVM), and achieved excellent performance. The validated area under the receiver operating characteristic curve(AUC) is in the range of 0.96-1.00, and the correct prediction is in the range of 87.1% - 90.0%.