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 Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

From Image to Pixels: Towards Fine-Grained Medical Vision-Language Models.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

Synergistic Tuning of Heterovalent States and Oxygen-Vacancy Defect Engineering in Hydrophilic W-Doped Sb<sub>2</sub>OS<sub>2</sub> for Enhanced Nitrogen Photoreduction to Ammonia.

ACS applied materials & interfaces·2024
Same author

Knowledge, attitudes, and practices of adolescent depression among parents of children diagnosed with depression in Ningbo City, eastern China.

Frontiers in public health·2024
Same author

Measurement plane of the cross-sectional area of the masseter muscle in patients with skeletal Class III malocclusion: An artificial intelligence model.

American journal of orthodontics and dentofacial orthopedics : official publication of the American Association of Orthodontists, its constituent societies, and the American Board of Orthodontics·2024
Same author

Changes in masseter muscle morphology after surgical-orthodontic treatment in patients with skeletal Class III malocclusion with mandibular asymmetry: The automatic masseter muscle segmentation model.

American journal of orthodontics and dentofacial orthopedics : official publication of the American Association of Orthodontists, its constituent societies, and the American Board of Orthodontics·2024
Same author

HC-Net: A hybrid convolutional network for non-human primate brain extraction.

Frontiers in computational neuroscience·2023

Related Experiment Video

Updated: Nov 6, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.1K

Robust Collaborative Learning of Patch-Level and Image-Level Annotations for Diabetic Retinopathy Grading From Fundus

Yehui Yang, Fangxin Shang, Binghong Wu

    IEEE Transactions on Cybernetics
    |May 7, 2021
    PubMed
    Summary

    This study introduces a new framework for grading diabetic retinopathy (DR) using fundus images. It improves accuracy by combining lesion and image information, outperforming current methods and human experts.

    More Related Videos

    Quantification of Diabetes-induced Adherent Leukocytes in Retinal Vasculature
    05:54

    Quantification of Diabetes-induced Adherent Leukocytes in Retinal Vasculature

    Published on: January 24, 2025

    474
    Using Retinal Imaging to Study Dementia
    09:17

    Using Retinal Imaging to Study Dementia

    Published on: November 6, 2017

    21.9K

    Related Experiment Videos

    Last Updated: Nov 6, 2025

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
    04:48

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

    Published on: November 30, 2022

    3.1K
    Quantification of Diabetes-induced Adherent Leukocytes in Retinal Vasculature
    05:54

    Quantification of Diabetes-induced Adherent Leukocytes in Retinal Vasculature

    Published on: January 24, 2025

    474
    Using Retinal Imaging to Study Dementia
    09:17

    Using Retinal Imaging to Study Dementia

    Published on: November 6, 2017

    21.9K

    Area of Science:

    • Ophthalmology
    • Medical Imaging
    • Artificial Intelligence

    Background:

    • Diabetic retinopathy (DR) grading from fundus images is crucial for patient care.
    • Current deep learning models often overlook lesion-specific details, limiting DR grading accuracy.
    • Integrating diverse data sources can enhance diagnostic capabilities.

    Purpose of the Study:

    • To develop a robust framework for diabetic retinopathy severity grading.
    • To leverage both patch-level and image-level annotations for improved feature extraction.
    • To enhance the discriminative power of algorithms for DR detection.

    Main Methods:

    • A novel framework utilizing collaborative patch-level and image-level annotations.
    • End-to-end optimization enabling bidirectional information exchange between lesion and grade data.
    • Development of a system capable of exploiting fine-grained lesion characteristics.

    Main Results:

    • The proposed framework demonstrated superior performance compared to state-of-the-art algorithms and experienced ophthalmologists.
    • The algorithm exhibited robustness across datasets with varying distributions and image quality.
    • Ablation studies confirmed the effectiveness and necessity of individual framework components.

    Conclusions:

    • The developed framework offers a more accurate and robust approach to diabetic retinopathy grading.
    • Integrating multi-level annotations significantly enhances feature discriminability for DR assessment.
    • The publicly available code and annotations facilitate further research and clinical application.