Related Experiment Video
Updated: Mar 24, 2026
14:27
Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
Published on: June 26, 2013
16.5K
Cross-View Neuroimage Pattern Analysis in Alzheimer's Disease Staging
Sidong Liu1, Weidong Cai1, Sonia Pujol2
1The Biomedical and Multimedia Information Technology Research Group, School of Information Technologies, The University of Sydney Sydney, NSW, Australia.
Frontiers in Aging Neuroscience
|March 5, 2016
Summary
This study introduces a novel framework for staging Alzheimer's disease (AD) using multiple neuroimaging biomarkers. Combining different imaging data types significantly improves early detection and classification of neurological disorders.
Area of Science:
- Neuroscience and Medical Imaging
- Biomarker Discovery and Application
Background:
- Early staging of pre-symptomatic and prodromal neurological disorders, like Alzheimer's disease (AD), is critical for dementia prevention and optimizing disease-modifying therapies.
- Neuroimaging biomarkers are increasingly utilized for early AD detection and predicting conversion from mild cognitive impairment (MCI) and normal control (NC) to AD.
- While multi-view neuroimaging biomarkers show promise for improved AD staging, the mechanisms of synergy and optimal utilization remain unclear.
Purpose of the Study:
- To propose and evaluate a cross-view pattern analysis framework for investigating the synergy between different neuroimaging biomarkers in AD staging.
- To quantitatively analyze nine types of biomarkers from FDG-PET and T1-MRI for classifying AD, MCI, and NC subjects.
- To understand how to preserve or maximize the performance of multi-view neuroimaging biomarkers in AD staging.
Main Methods:
- Development of a cross-view pattern analysis framework to explore synergy among neuroimaging biomarkers.
- Quantitative analysis of nine distinct biomarkers derived from FDG-PET and T1-MRI.
- Evaluation of biomarker performance in classifying subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI) baseline cohort into AD, MCI, and NC groups.
Main Results:
- The analyzed neuroimaging biomarkers effectively depict AD pathology from diverse perspectives, revealing distinct patterns associated with disease progression.
- Biomarkers were successfully separated into clusters, with each cluster representing a specific pathological aspect.
- Inter-cluster features consistently outperformed intra-cluster features in AD staging, indicating synergistic benefits of combining diverse biomarker patterns.
Conclusions:
- The proposed cross-view pattern analysis framework effectively investigates and leverages the synergy between multi-view neuroimaging biomarkers for improved AD staging.
- Combining complementary neuroimaging biomarkers offers enhanced performance in early detection and classification of Alzheimer's disease and related cognitive states.
- Future research should focus on optimizing the integration of multi-view biomarkers to maximize their potential in clinical applications for neurological disorders.
