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

Multi-Layer Multi-View Classification for Alzheimer's Disease Diagnosis.

Changqing Zhang1,2, Ehsan Adeli3, Tao Zhou1

  • 1Department of Radiology and BRIC, University of North Carolina at Chapel Hill, North Carolina, USA.

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence
|November 13, 2018
PubMed
Summary
This summary is machine-generated.

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

Single-immunocyte transcriptomics reveal the role of natural killer cell-dependent exogenous antigen presentation in ankylosing spondylitis severity.

Experimental & molecular medicine·2026
Same author

Cartilage organoids bridging bench to bedside: A steroid-free strategy for early osteoarthritis repair.

Materials today. Bio·2026
Same author

Esterified-pectin-coupled polar stiffening controls grass stomatal opening.

Nature plants·2026
Same author

Expression of concern: 3D-printed magnetic Fe<sub>3</sub>O<sub>4</sub>/MBG/PCL composite scaffolds with multifunctionality of bone regeneration, local anticancer drug delivery and hyperthermia.

Journal of materials chemistry. B·2026
Same author

Differential organ-specific toxicity profiling of BDE-209 and its derivative DBDPE in zebrafish.

Environmental pollution (Barking, Essex : 1987)·2026
Same author

Human peripheral osteoclast-precursor-development patterns reveal the significance of RPS17-dependent ribosome synthesis to Ankylosing Spondylitis lesions.

Bone research·2025

This study introduces a new Multi-Layer Multi-View Classification (ML-MVC) method for diagnosing Alzheimer's Disease (AD) using neuroimaging and genetics data. The approach effectively handles complex correlations and data from multiple sources to improve diagnostic accuracy.

Area of Science:

  • Neuroscience
  • Medical Imaging
  • Genetics
  • Machine Learning

Background:

  • Alzheimer's Disease (AD) diagnosis faces challenges with traditional methods using multi-source data.
  • Linear models are often ineffective due to complex correlations between imaging features and diagnostic labels.
  • Exploiting data complementarity from various sources (neuroimaging, genetics) is crucial for accurate AD diagnosis.

Purpose of the Study:

  • To propose a novel Multi-Layer Multi-View Classification (ML-MVC) method for Alzheimer's Disease diagnosis.
  • To address the limitations of traditional classification on multi-source neuroimaging and genetics data.
  • To effectively capture high-order complementarity and nonlinear correlations among different data views.

Main Methods:

Related Experiment Videos

  • Developed a Multi-Layer Multi-View Classification (ML-MVC) approach.
  • Constructed a latent representation to explore complex feature-label correlations.
  • Employed low-rank tensor regularization to capture high-order complementarity among data views.
  • Utilized the Alternating Direction Method of Multipliers (ADMM) for optimization.

Main Results:

  • The ML-MVC method effectively explores nonlinear correlations and complementarity among different data views.
  • The proposed approach demonstrated improved classification accuracy for Alzheimer's Disease diagnosis.
  • Validation was performed using datasets from the Alzheimer's Disease Neuroimaging Initiative (ADNI).

Conclusions:

  • The novel ML-MVC method offers an effective solution for Alzheimer's Disease diagnosis using multi-source data.
  • The approach successfully addresses challenges related to complex correlations and data complementarity.
  • The findings highlight the potential of advanced multi-view learning in neurodegenerative disease diagnostics.