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 Video

Updated: Jun 13, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

487

Label-Aware Dual Graph Neural Networks for Multi-Label Fundus Image Classification.

Yanbei Liu, Xinwen Peng, Xin Wei

    IEEE Journal of Biomedical and Health Informatics
    |September 10, 2024
    PubMed
    Summary

    This study introduces a new dual graph neural network for multi-label fundus image classification. The model improves diagnosis by considering patient similarities and pathology correlations, outperforming existing methods.

    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

    National trends and disparities in cervical cancer screening among commercially insured Women, 2001-2010.

    Cancer epidemiology, biomarkers & prevention : a publication of the American Association for Cancer Research, cosponsored by the American Society of Preventive Oncology·2014
    Same author

    Persistent medication affordability problems among disabled Medicare beneficiaries after Part D, 2006-2011.

    Medical care·2014
    Same author

    Characterizing topological patterns in amnestic mild cognitive impairment by quantitative water diffusivity.

    Journal of Alzheimer's disease : JAD·2014
    Same author

    Access to affordable medicines after health reform: evidence from two cross-sectional surveys in Shaanxi Province, western China.

    The Lancet. Global health·2014
    Same author

    Increased acyl ghrelin but decreased total ghrelin and unacyl ghrelin in Chinese Han people with impaired fasting glucose combined with impaired glucose tolerance.

    Peptides·2014
    Same author

    [Comparison on surface ultrastructure characteristic and drought resistance of different Trichosanthes kirilowii strains].

    Zhongguo Zhong yao za zhi = Zhongguo zhongyao zazhi = China journal of Chinese materia medica·2014

    Area of Science:

    • Ophthalmology
    • Medical Imaging
    • Artificial Intelligence

    Background:

    • Fundus diseases require early diagnosis for effective treatment.
    • Current deep learning models often overlook subject similarities and pathology correlations.
    • Accurate multi-label classification of fundus images remains a challenge.

    Purpose of the Study:

    • To propose a novel label-aware dual graph neural network for multi-label fundus image classification.
    • To address limitations of existing methods by incorporating inter-subject and inter-pathology relationships.
    • To enhance the accuracy and adaptivity of fundus disease diagnosis.

    Main Methods:

    • Developed a dual graph neural network with population-based and pathology-based modules.
    • Constructed a population graph integrating image and non-image data for patient representation.

    More Related Videos

    Revealing Neural Circuit Topography in Multi-Color
    09:11

    Revealing Neural Circuit Topography in Multi-Color

    Published on: November 14, 2011

    15.0K
    Deep Neural Networks for Image-Based Dietary Assessment
    13:19

    Deep Neural Networks for Image-Based Dietary Assessment

    Published on: March 13, 2021

    9.0K

    Related Experiment Videos

    Last Updated: Jun 13, 2025

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
    03:31

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

    Published on: December 15, 2023

    487
    Revealing Neural Circuit Topography in Multi-Color
    09:11

    Revealing Neural Circuit Topography in Multi-Color

    Published on: November 14, 2011

    15.0K
    Deep Neural Networks for Image-Based Dietary Assessment
    13:19

    Deep Neural Networks for Image-Based Dietary Assessment

    Published on: March 13, 2021

    9.0K
  • Created a pathology graph representing label co-occurrence for classifier score generation.

    • Main Results:

    • The proposed model effectively learns patient representations and pathology correlations.
    • Achieved superior performance compared to state-of-the-art multi-label fundus image classification methods.
    • Demonstrated adaptive recalibration of multi-label outputs.

    Conclusions:

    • The label-aware dual graph neural network offers a significant advancement in multi-label fundus image classification.
    • Integrating population and pathology graphs enhances diagnostic accuracy.
    • This approach provides a more comprehensive analysis of fundus images for disease identification.