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

Parkinson's Disease Detection Using Isosurfaces-Based Features and Convolutional Neural Networks.

Andrés Ortiz1, Jorge Munilla1, Manuel Martínez-Ibañez1

  • 1Department of Communications Engineering, Universidad de Málaga, Malaga, Spain.

Frontiers in Neuroinformatics
|July 18, 2019
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

Starch and tuber traits of diploid potato lines B26 and B100 and their hybrids.

BMC plant biology·2026
Same author

Evaluation of Explainable Artificial Intelligence in IoT Intrusion Detection Systems Under DeepFool Adversarial Conditions.

Sensors (Basel, Switzerland)·2026
Same author

Kolmogorov-Arnold Networks for Sensor Data Processing: A Comprehensive Survey of Architectures, Applications, and Open Challenges.

Sensors (Basel, Switzerland)·2026
Same author

Continuous glucose monitoring trajectories in patients with acute coronary syndrome.

Cardiovascular diabetology·2026
Same author

PhysioMotion Artifact: A task-driven EEG dataset with point-wise motion artifact annotations.

Scientific data·2026
Same author

Multimodal brain tumor segmentation and classification based on optimized DeepLabV3 + and fused fire module with self-attention.

European journal of medical research·2026

This study introduces isosurfaces to simplify 3D brain images for Parkinson's disease diagnosis using Convolutional Neural Networks (CNNs). This approach significantly improves classification accuracy and reduces computational load for computer-aided diagnosis systems.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Neurology

Background:

  • Computer-aided diagnosis (CAD) systems aid Parkinson's disease (PD) detection through brain imaging.
  • Convolutional Neural Networks (CNNs) show promise for PD pattern recognition in neuroimaging.
  • High dimensionality of 3D brain images complicates CNN architectures, potentially degrading performance due to overfitting.

Purpose of the Study:

  • To propose isosurfaces as a method for reducing data complexity in 3D brain images for PD diagnosis.
  • To evaluate the effectiveness of isosurfaces in conjunction with CNNs for classifying DaTScan images.
  • To enhance the efficiency and accuracy of automated PD detection systems.

Main Methods:

  • Utilized isosurfaces to extract salient information from 3D brain images, reducing data volume.
Keywords:
Parkinson's diseasecomputer-aided diagnosisconvolutional neural networksdeep learningisosurfaces

Related Experiment Videos

  • Implemented classification using two established CNN architectures: LeNet and AlexNet.
  • Trained and tested the models on DaTScan images for Parkinson's disease classification.

    • Main Results:

    • Achieved an average classification accuracy of 95.1% for Parkinson's disease detection.
    • Obtained an Area Under the Curve (AUC) of 97% in the classification task.
    • Demonstrated classification performance comparable to or better than recent state-of-the-art systems.

    Conclusions:

    • Isosurface computation effectively reduces input data complexity for CNN-based PD diagnosis.
    • The proposed method achieves high classification accuracy with a significantly reduced computational burden.
    • This approach offers a promising strategy for improving computer-aided diagnosis of Parkinson's disease.