Impact Factor 2.635 | CiteScore 2.99
More on impact ›

Original Research ARTICLE Provisionally accepted The full-text will be published soon. Notify me

Front. Neurol. | doi: 10.3389/fneur.2019.01097

Machine learning based framework for differential diagnosis between vascular dementia and Alzheimer's disease using structural MRI features

  • 1Department of Radiology, First Affiliated Hospital of Chongqing Medical University, China
  • 2Department of Neurology, First Affiliated Hospital of Chongqing Medical University, China

Background and objective: Vascular dementia (VaD) and Alzheimer's disease (AD) could be characterized by the same syndrome of dementia. This study aims to assess whether multi-parameter features derived from structural MRI can serve as the informative biomarker for differential diagnosis of VaD and AD using machine learning.
Methods: A total of 93 patients imaged with brain MRI including 58 AD and 35 VaD confirmed by two chief physicians were recruited in this study from June 2013 to July 2019. Automated brain tissue segmentation was performed by AccuBrain tool to extract multi-parameter volumetric measurements from different brain regions. Firstly, totally 62 structural MRI biomarkers were addressed to select significantly different features between VaD and AD for dimensionality reduction. Then, least absolute shrinkage and selection operator (LASSO) was further used to construct a feature set that is fed into a support vector machine (SVM) classifier. To ensure the unbiased evaluation of model performance, a comparative study of classification models was implemented by using different machine learning algorithms in order to determine which performs best in the application of differential diagnosis between VaD and AD. The diagnostic performance of the classification models was evaluated by the quantitative metrics derived from receiver operating characteristic curve (ROC).
Results: The experimental results demonstrate that SVM with RBF model achieved an encouraging performance with sensitivity (SEN), specificity (SPE) and accuracy (ACC) values of 82.65%, 87.17% and 84.35% (AUC=0.861, 95% CI = 0.820-0.902) for the differential diagnosis between VaD and AD. The experimental results demonstrate that the proposed model achieved an encouraging performance.
Conclusions: The proposed computer-aided diagnosis method highlights the potential of combing structural MRI and machine learning to support clinical decision making in distinction of VaD vs. AD.

Keywords: structural MRI, VaD and AD, SVM - Support vector machine, machine learning, Computer-Aided Diagnosis (CAD)

Received: 06 Mar 2019; Accepted: 30 Sep 2019.

Copyright: © 2019 Zheng, Guo, Zhang, Wu, Li and Lv. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

* Correspondence: MD, PhD. Fajin Lv, First Affiliated Hospital of Chongqing Medical University, Department of Neurology, Chongqing, China,