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 Experiment Videos

Performance analysis of different classification algorithms using different feature selection methods on Parkinson's

Ozkan Cigdem1, Hasan Demirel1

  • 1Department of Electrical and Electronics Engineering, Eastern Mediterranean University, Gazimagusa, Mersin 10, Turkey.

Journal of Neuroscience Methods
|September 4, 2018
PubMed
Summary

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

MR Imaging-Based Biomarkers for Strength Prediction: A Statistical Shape and Architecture Modeling of Quadriceps Muscles.

Journal of magnetic resonance imaging : JMRI·2026
Same author

MR-Transformer: A Vision Transformer-based Deep Learning Model for Total Knee Replacement Prediction Using MRI.

Radiology. Artificial intelligence·2025
Same author

Preliminary results of a new endoscopic underlay cartilage tympanoplasty with lateral malleolar flap.

European archives of oto-rhino-laryngology : official journal of the European Federation of Oto-Rhino-Laryngological Societies (EUFOS) : affiliated with the German Society for Oto-Rhino-Laryngology - Head and Neck Surgery·2025
Same author

Estimating time-to-total knee replacement on radiographs and MRI: a multimodal approach using self-supervised deep learning.

Radiology advances·2025
Same author

Artificial intelligence in knee osteoarthritis: A comprehensive review for 2022.

Osteoarthritis imaging·2024
Same author

Deep learning for diagnosis of COVID-19 using 3D CT scans.

Computers in biology and medicine·2021

This study enhances Parkinson

Area of Science:

  • Neuroimaging
  • Medical Diagnostics
  • Machine Learning

Background:

  • Neurodegenerative diseases, including Parkinson's disease (PD), are a significant health concern.
  • Three-dimensional magnetic resonance imaging (3D-MRI) is a key technology for diagnosing neurodegenerative disorders.

Purpose of the Study:

  • To improve the accuracy of Parkinson's disease detection using 3D-MRI data.
  • To evaluate the effectiveness of various feature selection and classification methods for PD diagnosis.

Main Methods:

  • Utilized gray matter (GM) and white matter (WM) tissue maps from 3D-MRI.
  • Implemented source fusion of GM/WM data and decision fusion of multiple classifiers.
  • Employed correlation-based feature selection (CFS) and adaptive Fisher stopping criteria for feature selection.
Keywords:
DARTELDecision fusionFeature selectionParkinson's diseaseSource fusionStructural MRI

Related Experiment Videos

Main Results:

  • Correlation-based feature selection (CFS) outperformed other methods across all classifiers.
  • Support Vector Machine (SVM) showed the best performance among classification algorithms.
  • Fusion of GM and WM datasets significantly improved classification accuracy to 95.00%.

Conclusions:

  • Combining 3D masked GM and WM tissue maps with a decision fusion technique using CFS achieves high accuracy in PD detection.
  • The proposed fusion methodology offers a promising approach for accurate Parkinson's disease diagnosis.