Boosting brain connectome classification accuracy in Alzheimer's disease using higher-order singular value...

Area of Science:

• Neuroimaging
• Biomarkers
• Machine Learning

Background:

• Alzheimer's disease (AD) is a progressive neurodegenerative disorder.
• Early detection of AD and its prodromal stage, mild cognitive impairment (MCI), is critical for timely intervention.
• Identifying reliable brain imaging biomarkers for automated disease staging is an active research area.

Purpose of the Study:

• To propose a novel feature extraction and classification framework for differentiating Alzheimer's disease stages.
• To utilize brain structural networks derived from diffusion MRI.
• To enhance the accuracy of automated AD and MCI detection.

Main Methods:

• Brain structural networks were computed using diffusion MRI data.
• A new feature extraction method based on higher-order singular value decomposition was developed.
• Sparse logistic regression was employed for classification of disease stages.

Main Results:

• The proposed framework demonstrated effectiveness in detecting brain network alterations.
• The method showed promise in classifying different stages of Alzheimer's disease.
• Validation was performed on publicly available data from the Alzheimer's Disease Neuroimaging Initiative.

Conclusions:

• The developed framework offers a promising approach for the automated detection and staging of Alzheimer's disease.
• Brain structural network analysis using diffusion MRI holds potential as a biomarker for AD.
• Further research can refine this method for clinical application in neurodegenerative disease diagnosis.