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

GRAPH CONVOLUTIONAL NEURAL NETWORKS FOR ALZHEIMER'S DISEASE CLASSIFICATION.

Tzu-An Song1, Samadrita Roy Chowdhury1, Fan Yang1

  • 1Department of Electrical and Computer Engineering, University of Massachusetts Lowell, Lowell, MA.

Proceedings. IEEE International Symposium on Biomedical Imaging
|July 23, 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

Surface substance loss of subsurface bovine enamel lesions after different steps of the resinous infiltration technique: a 3D topography analysis.

Odontology·2011
Same author

Expression of IL-23/Th17 pathway in a murine model of Coxsackie virus B3-induced viral myocarditis.

Virology journal·2011
Same author

Extracellular matrix peptides of Artemia cyst shell participate in protecting encysted embryos from extreme environments.

PloS one·2011
Same author

Therapeutic effect of carboxymethylated and quanternized chitosan on insulin resistance in high-fat-diet-induced rats and 3T3-L1 adipocytes.

Journal of biomaterials science. Polymer edition·2011
Same author

Role of reactive oxygen species in triptolide-induced apoptosis of renal tubular cells and renal injury in rats.

Journal of Huazhong University of Science and Technology. Medical sciences = Hua zhong ke ji da xue xue bao. Yi xue Ying De wen ban = Huazhong keji daxue xuebao. Yixue Yingdewen ban·2011
Same author

Chlorination and ortho-acetoxylation of 2-arylbenzoxazoles.

Organic & biomolecular chemistry·2011

Graph convolutional neural networks (GCNNs) effectively classify Alzheimer's disease (AD) spectrum stages using brain connectivity data. This GCNN approach outperforms traditional methods, improving with disease progression.

Area of Science:

  • Neuroscience
  • Machine Learning
  • Medical Imaging

Background:

  • Convolutional neural networks (CNNs) excel on Euclidean data but struggle with graph-structured data.
  • Brain connectivity studies utilize graph theory to analyze complex brain networks.
  • Alzheimer's disease (AD) is linked to neurodegenerative network dysfunction, necessitating advanced classification tools.

Purpose of the Study:

  • To implement and evaluate a multi-class Graph Convolutional Neural Network (GCNN) classifier.
  • To classify subjects across the Alzheimer's disease (AD) spectrum into four distinct categories.
  • To compare GCNN performance against a Support Vector Machine (SVM) classifier for AD staging.

Main Methods:

  • Utilized structural connectivity graphs derived from diffusion tensor imaging (DTI) data.
Keywords:
Alzheimer’s diseaseGraph CNNclassificationconvolutional neural network

Related Experiment Videos

  • Trained and validated a multi-class GCNN classifier for network-based subject classification.
  • Employed receiver operating characteristic (ROC) curves to assess classifier performance.

    • Main Results:

    • The GCNN classifier demonstrated superior performance compared to the SVM classifier.
    • Performance differences between GCNN and SVM increased with disease progression (from cognitively normal to AD).
    • GCNN showed significant potential for accurate staging and classification of individuals on the AD spectrum.

    Conclusions:

    • GCNNs are a competitive and effective tool for classifying and staging subjects within the Alzheimer's disease spectrum.
    • The study highlights the advantage of GCNNs in handling complex, non-Euclidean brain network data for neurodegenerative disease research.
    • GCNNs offer a promising avenue for improving diagnostic accuracy and understanding disease progression in AD.