Related Experiment Video
Updated: Nov 21, 2025
Application of Granger Causality Analysis of the Directed Functional Connection in Alzheimer's Disease and Mild Cognitive Impairment
Published on: August 7, 2017
Multiclass classification of patients during different stages of Alzheimer's disease using fMRI time-series
Hessam Ahmadi1, Emad Fatemizadeh2, Ali Motie-Nasrabadi3
1Department of Biomedical Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran.
Abstract:
Alzheimer's Disease (AD) begins several years before the symptoms develop. It starts with Mild Cognitive Impairment (MCI) which can be separated into Early MCI and Late MCI (EMCI and LMCI). Functional connectivity analysis and classification are done among the different stages of illness with Functional Magnetic Resonance Imaging (fMRI). In this study, in addition to the four stages including healthy, EMCI, LMCI, and AD, the patients have been tracked for a year. Indeed, the classification has been done among 7 groups to analyze the functional connectivity changes in one year in different stages. After generating the functional connectivity graphs for eliminating the weak links, three different sparsification methods were used. In addition to simple thresholding, spectral sparsification based on effective resistance and sparse autoencoder were performed in order to analyze the effect of sparsification routine on classification results. Also, instead of extracting common features, the correlation matrices were reshaped to a correlation vector and used as a feature vector to enter the classifier. Since the correlation matrix is symmetric, in another analysis half of the feature vector was used, moreover, the Genetic Algorithm (GA) also utilized for feature vector dimension reduction. The non-linear SVM classifier with a polynomial kernel applied. The results showed that the autoencoder sparsification method had the greatest discrimination power with the accuracy of 98.35% for classification when the feature vector was the full correlation matrix.
Insights
This study used functional MRI to analyze brain connectivity changes in Alzheimer's Disease (AD) and Mild Cognitive Impairment (MCI). Sparse autoencoder methods achieved 98.35% accuracy in classifying these neurodegenerative disease stages.
Area of Science:
- Neuroimaging
- Machine Learning
- Neurology
Background:
- Alzheimer's Disease (AD) progression begins years before symptom onset, with stages including Mild Cognitive Impairment (MCI), Early MCI (EMCI), and Late MCI (LMCI).
- Functional connectivity analysis using fMRI is crucial for understanding brain network alterations in neurodegenerative diseases.
- Tracking patients over a year allows for analysis of functional connectivity changes across disease stages.
Purpose of the Study:
- To classify different stages of Alzheimer's Disease (AD) and Mild Cognitive Impairment (MCI) using functional MRI data.
- To evaluate the impact of various sparsification methods on classification accuracy.
- To investigate functional connectivity changes over one year in healthy individuals and patients with MCI and AD.
Main Methods:
- Functional connectivity graphs were generated from fMRI data for healthy individuals and patients across four stages (EMCI, LMCI, AD).
- Three sparsification techniques were applied: simple thresholding, spectral sparsification, and sparse autoencoder.
- Correlation matrices were converted to feature vectors, with analyses including using half the vector and Genetic Algorithm (GA) for dimension reduction. A non-linear SVM classifier with a polynomial kernel was used.
Main Results:
- The sparse autoencoder sparsification method demonstrated the highest classification performance.
- An accuracy of 98.35% was achieved using the sparse autoencoder with the full correlation matrix as the feature vector.
- Different sparsification methods and feature vector manipulations influenced classification outcomes.
Conclusions:
- Sparse autoencoder-based sparsification is a highly effective method for discriminating between stages of Alzheimer's Disease and Mild Cognitive Impairment.
- Functional connectivity analysis via fMRI, coupled with advanced machine learning techniques, holds significant potential for early diagnosis and monitoring of AD.
- The study highlights the importance of selecting appropriate feature extraction and dimensionality reduction techniques for optimal classification performance in neurodegenerative disease research.
More Related Videos
Related Concept Videos
01:26Alzheimer's Disease: Overview
The clinical diagnosis of AD hinges on the presence of memory and other cognitive impairments. Biomarkers, such as changes in Aβ...
01:22Alzheimer's Disease: Treatment