Related Experiment Video
Updated: May 2, 2026
05:33
Three-Dimensional Shape Modeling and Analysis of Brain Structures
Published on: November 14, 2019
6.6K
MULTIMODAL CLASSIFICATION OF DEMENTIA USING FUNCTIONAL DATA, ANATOMICAL FEATURES AND 3D INVARIANT SHAPE DESCRIPTORS
Arthur Mikhno1, Pablo Martinez Nuevo2, Davangere P Devanand3
1Department of Biomedical Engineering, Columbia University.
Summary
This study introduces 3D Zernike moments from MRI scans to classify Alzheimer's disease (AD) and Mild Cognitive Impairment (MCI). Combining Zernike features with PET scans significantly improves diagnostic accuracy for these neurodegenerative conditions.
Area of Science:
- Neuroimaging
- Medical Diagnostics
- Biomedical Engineering
Background:
- Alzheimer's disease (AD) and Mild Cognitive Impairment (MCI) classification is crucial for timely intervention.
- Existing classification frameworks can be improved by integrating multimodal data.
- Advanced feature extraction from neuroimaging is needed for enhanced diagnostic accuracy.
Purpose of the Study:
- To develop and evaluate a novel multimodality classification framework for AD and MCI.
- To introduce invariant shape descriptors based on 3D Zernike moments applied to the hippocampus.
- To compare the performance of Zernike features against traditional volumetric MRI and PET imaging.
Main Methods:
- Utilized Magnetic Resonance Imaging (MRI) and Positron Emission Tomography (PET) data.
- Extracted features including 3D Zernike moments (hippocampal shape descriptors) and traditional volumetric measures from MRI.
- Incorporated PET data from fluorodeoxyglucose (FDG) and Pittsburg compound B (PIB) radioligands.
Main Results:
- 3D Zernike moments significantly outperformed volumetric MRI for CTR/AD (90.7% vs 71.6%), CTR/MCI (76.2% vs 60.0%), and MCI/AD (84.3% vs 65.5%) classification.
- Zernike features demonstrated comparable and complementary performance to PET imaging.
- Combining Zernike and PET features achieved optimal classification accuracy, with CTR/AD reaching 98.8% accuracy, 99.5% specificity, and 98.1% sensitivity.
Conclusions:
- 3D Zernike moments represent a powerful new MRI-based feature for classifying AD and MCI.
- Multimodal approaches integrating advanced MRI features with PET imaging enhance diagnostic performance.
- This framework offers a promising avenue for improved early detection and differential diagnosis of neurodegenerative conditions.
Related Concept Videos
01:22Dementia l: Introduction
35
Dementia is an acquired, progressive syndrome characterized by a decline in multiple cognitive domains severe enough to impair daily functioning and reduce independence. Although memory loss is a central feature, the diagnosis requires additional deficits involving language, executive function, visuospatial skills, judgment, calculation, or abstract reasoning. These cognitive impairments reflect underlying neurodegenerative or vascular processes that gradually disrupt neuronal networks...
35
01:30Dementia
687
Dementia is a collective term for cognitive disorders primarily affecting memory, thinking, and reasoning. It is not a specific disease but a syndrome, with Alzheimer's disease being the most common cause, accounting for approximately 60-80% of cases. Other types include vascular dementia, Lewy body dementia, and frontotemporal dementia. Dementia affects millions worldwide, particularly older adults, though it is not a normal part of aging.
The progression of dementia is generally gradual....
The progression of dementia is generally gradual....
687