Related Experiment Video
Updated: Sep 7, 2025
Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
Published on: December 15, 2023
The Coupled Representation of Hierarchical Features for Mild Cognitive Impairment and Alzheimer's Disease
Ke Liu1,2, Qing Li1,3, Li Yao1,2
1School of Artificial Intelligence, Beijing Normal University, Beijing, China.
Abstract:
Structural magnetic resonance imaging (MRI) features have played an increasingly crucial role in discriminating patients with Alzheimer's disease (AD) and mild cognitive impairment (MCI) from normal controls (NC). However, the large number of structural MRI studies only extracted low-level neuroimaging features or simply concatenated multitudinous features while ignoring the interregional covariate information. The appropriate representation and integration of multilevel features will be preferable for the precise discrimination in the progression of AD. In this study, we proposed a novel inter-coupled feature representation method and built an integration model considering the two-level (the regions of interest (ROI) level and the network level) coupled features based on structural MRI data. For the intra-coupled interactions about the network-level features, we performed the ROI-level (intra- and inter-) coupled interaction within each network by feature expansion and coupling learning. For the inter-coupled interaction of the network-level features, we measured the coupled relationships among different networks via Canonical correlation analysis. We evaluated the classification performance using coupled feature representations on the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Results showed that the coupled integration model with hierarchical features achieved the optimal classification performance with an accuracy of 90.44% for AD and NC groups, with an accuracy of 87.72% for the MCI converter (MCI-c) and MCI non-converter (MCI-nc) groups. These findings suggested that our two-level coupled interaction representation of hierarchical features has been the effective means for the precise discrimination of MCI-c from MCI-nc groups and, therefore, helpful in the characterization of different AD courses.
Insights
This study introduces a new method using structural MRI data to better distinguish Alzheimer's disease (AD) and mild cognitive impairment (MCI) patients from healthy individuals. The approach effectively identifies individuals likely to progress from MCI to AD.
Area of Science:
- Neuroimaging
- Biomedical Engineering
- Computational Neuroscience
Background:
- Structural magnetic resonance imaging (MRI) is vital for differentiating Alzheimer's disease (AD) and mild cognitive impairment (MCI) from normal controls (NC).
- Existing studies often use limited neuroimaging features or ignore crucial interregional covariate information, hindering precise AD progression discrimination.
- Integrating multilevel features appropriately is key for accurate AD progression assessment.
Purpose of the Study:
- To propose a novel inter-coupled feature representation method for structural MRI data.
- To develop an integration model that considers two-level coupled features (ROI and network levels) for improved AD discrimination.
- To enhance the classification accuracy in distinguishing between different stages of cognitive decline.
Main Methods:
- Proposed a novel inter-coupled feature representation method integrating ROI-level and network-level coupled features from structural MRI.
- Performed ROI-level coupled interaction within networks using feature expansion and coupling learning.
- Measured inter-coupled interactions among networks using Canonical Correlation Analysis (CCA).
Main Results:
- The coupled integration model achieved 90.44% accuracy for AD vs. NC classification.
- The model reached 87.72% accuracy in distinguishing MCI converters (MCI-c) from MCI non-converters (MCI-nc).
- Hierarchical feature representation demonstrated effectiveness in precise discrimination of MCI progression.
Conclusions:
- The proposed two-level coupled interaction representation of hierarchical features is effective for precise discrimination of MCI converters.
- This method aids in characterizing different Alzheimer's disease disease courses.
- The findings highlight the importance of integrated multilevel feature analysis in neuroimaging for neurological disorder diagnosis.
More Related Videos
08:43Application of Granger Causality Analysis of the Directed Functional Connection in Alzheimer's Disease and Mild Cognitive Impairment
Published on: August 7, 2017
12:18A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
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
01:30Dementia
The progression of dementia is generally gradual....
01:17Classification of Illness
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe...