Features of the superficial white matter as biomarkers for the detection of Alzheimer's disease and mild cognitive impairment: A diffusion tensor imaging study

Abstract

Background: With the development of medical imaging and processing tools, accurate diagnosis of diseases has been made possible by intelligent systems. Owing to the remarkable ability of support vector machines (SVMs) for diseases diagnosis, extensive research has been conducted using the SVM algorithm for the classification of Alzheimer's disease (AD) and mild cognitive impairment (MCI).

Objectives: In this study, we applied an automated method to classify patients with AD and MCI and healthy control (HC) subjects based on the diffusion tensor imaging (DTI) features in the superficial white matter (SWM).

Participants: For this purpose, DTI data were downloaded from the Alzheimer's Disease Neuroimaging Initiative (ADNI). This method employed DTI data from 72 subjects: 24 subjects as HC, 24 subjects with MCI, and 24 subjects with AD.

Measure: ments: DTI processing was performed using DSI Studio software and all machine learning analyses were performed using MATLAB software.

Results: The linear kernel of SVM was the best classifier, with an accuracy of 95.8% between the AD and HC groups, followed by the quadratic kernel of SVM with an accuracy of 83.3% between the MCI and HC groups and the Gaussian kernel of SVM with an accuracy of 83.3% between the AD and MCI groups.

Conclusions: Given the importance of diagnosing AD and MCI as well as the role of superficial white matter in the diagnosis of neurodegenerative diseases, in this study, the features of different DTI methods of the SWM are discussed, which could be a useful tool to assist in the diagnosis of AD and MCI.

Keywords: Alzheimer's disease; Diffusion tensor imaging; Mild cognitive impairment; Superficial white matter; Support vector machine.

Figure 1

Steps to extract the parameters from the DTI data.

Figure 2

Overview of the division of the SWM of the brain into the frontal (green), insular (orange), limbic (purple), parietal (pink), temporal (blue), and occipital (yellow) lobes: a) 3D axial view and b) 3D sagittal view.

Figure 3

The process flow chart in our study.

Figure 4

A) The ROC curve followed by the quadratic kernel of SVM for HC-MCI classification. B) The ROC curve followed by the Gaussian kernel of SVM for AD-MCI classification. C) The ROC curve followed by the linear kernel of SVM for AD-HC classification.

Figure 5

The number of selective features of the different methods.

Figure 6

Comparison between the three kernels to find the best kernel in any pair classification.

Figure 7

Example of the complex architecture of the SWM and crossing fiber (The SWM mask is shown in a white background).

Figure 8

An example of the connections between the superficial white matter regions provided by http://mkweb.bcgsc.ca/tableviewer/visualize/.