Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Gaussian Connectivity-Driven EEG Imaging for Deep Learning-Based Motor Imagery Classification.

Sensors (Basel, Switzerland)·2026
Same author

Takens-Based Kernel Transfer Entropy Connectivity Network for Motor Imagery Classification.

Sensors (Basel, Switzerland)·2025
Same author

CrowdAttention: An Attention Based Framework to Classify Crowdsourced Data in Medical Scenarios.

Sensors (Basel, Switzerland)·2025
Same author

Integrating Cacao Physicochemical-Sensory Profiles via Gaussian Processes Crowd Learning and Localized Annotator Trustworthiness.

Foods (Basel, Switzerland)·2025
Same author

EEG-Based Music Emotion Prediction Using Supervised Feature Extraction for MIDI Generation.

Sensors (Basel, Switzerland)·2025
Same author

Therapeutic Hypothermia and Its Role in Preserving Brain Volume in Term Neonates with Perinatal Asphyxia.

Journal of clinical medicine·2024

Related Experiment Video

Updated: Feb 24, 2026

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.9K

Enhanced Data Representation by Kernel Metric Learning for Dementia Diagnosis.

David Cárdenas-Peña1, Diego Collazos-Huertas1, German Castellanos-Dominguez1

  • 1Signal Processing and Recognition Group, Universidad Nacional de ColombiaManizales, Colombia.

Frontiers in Neuroscience
|August 12, 2017
PubMed
Summary

This study introduces a new kernel framework for metric learning to improve early Alzheimer's disease (AD) diagnosis using MRI scans. The method enhances classification accuracy, aiding in better patient outcomes and distinguishing between AD, mild cognitive impairment, and healthy individuals.

Keywords:
ADNIcentered kernel alignmentcomputer-aided diagnosismagnetic resonance imagingmetric learning

More Related Videos

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

16.4K
Basics of Multivariate Analysis in Neuroimaging Data
06:35

Basics of Multivariate Analysis in Neuroimaging Data

Published on: July 24, 2010

17.4K

Related Experiment Videos

Last Updated: Feb 24, 2026

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.9K
Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

16.4K
Basics of Multivariate Analysis in Neuroimaging Data
06:35

Basics of Multivariate Analysis in Neuroimaging Data

Published on: July 24, 2010

17.4K

Area of Science:

  • Medical Imaging and Diagnostics
  • Machine Learning in Healthcare
  • Neurodegenerative Disease Research

Background:

  • Alzheimer's disease (AD) is the most prevalent form of dementia globally, necessitating early detection for effective treatment and improved patient quality of life.
  • Computer-aided diagnosis tools utilizing Magnetic Resonance Imaging (MRI) show promise in differentiating between AD, mild cognitive impairment (MCI), and healthy controls.
  • Existing diagnostic approaches require performance enhancement to improve classification accuracy for neurological conditions.

Purpose of the Study:

  • To propose and evaluate a novel kernel framework for metric learning designed to enhance the performance of dementia diagnosis systems.
  • To improve the discrimination capabilities between three neurological classes: AD, MCI, and healthy controls.
  • To boost the accuracy and reliability of computer-aided diagnosis for neurodegenerative diseases.

Main Methods:

  • A kernel framework for metric learning was developed, focusing on maximizing the center kernel alignment function to create more discriminative feature spaces.
  • The framework was evaluated on the Alzheimer's Disease Neuroimaging Initiative (ADNI) database, using structural MRI data from 286 AD patients, 379 MCI patients, and 231 healthy controls.
  • Three supervised classification machines (k-nn, SVM, NNs) were employed for both multi-class and bi-class classification, with data split into 70% for tuning and 30% for blind testing. FreeSurfer software extracted 310 morphological measurements from each MRI scan.

Main Results:

  • The proposed supervised metric learning framework significantly improved the performance of baseline classifiers in both multi-class and bi-class scenarios.
  • In the multi-class setting, the best performance achieved was 60.1% accuracy with a 1-layered neural network.
  • High average performance exceeding 90% was obtained for the healthy control (HC) versus AD classification task, demonstrating enhanced class separability and balanced performance across classes.

Conclusions:

  • The developed metric learning framework effectively enhances classifier performance by creating feature spaces with improved class separability.
  • This approach leads to more balanced diagnostic performance, increasing sensitivity for pathological groups (AD, MCI) and specificity for healthy controls.
  • The findings suggest a valuable advancement for computer-aided diagnosis tools in identifying dementia, contributing to better clinical decision-making.