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

Surgical Margin Affects the Long-Term Prognosis of Patients With Hepatocellular Carcinoma Undergoing Radical Hepatectomy Followed by Adjuvant TACE.

The oncologist·2023
Same author

The factors influencing postoperative efficacy of anterior clinoidal meningioma treatment and an analysis of best-suited surgical strategies.

Frontiers in neurology·2023
Same author

Repurposing fluphenazine to suppress melanoma brain, lung and bone metastasis by inducing G0/G1 cell cycle arrest and apoptosis and disrupting autophagic flux.

Clinical & experimental metastasis·2023
Same author

AATSN: Anatomy Aware Tumor Segmentation Network for PET-CT volumes and images using a lightweight fusion-attention mechanism.

Computers in biology and medicine·2023
Same author

Deep-learning based quantification model for hip bone marrow edema and synovitis in patients with spondyloarthritis based on magnetic resonance images.

Frontiers in physiology·2023
Same author

Reproductive outcomes of women with moderate to severe intrauterine adhesions after transcervical resection of adhesion: A systematic review and meta-analysis.

Medicine·2023

Related Experiment Video

Updated: Aug 3, 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

2.8K

Reconstruction-Driven Dynamic Refinement Based Unsupervised Domain Adaptation for Joint Optic Disc and Cup

Ziyang Chen, Yongsheng Pan, Yong Xia

    IEEE Journal of Biomedical and Health Informatics
    |April 12, 2023
    PubMed
    Summary
    This summary is machine-generated.

    A new method, RDR-Net, improves optic disc and optic cup segmentation for glaucoma screening by addressing variations in fundus images. This unsupervised domain adaptation technique enhances model generalization across different healthcare settings.

    More Related Videos

    Using Retinal Imaging to Study Dementia
    09:17

    Using Retinal Imaging to Study Dementia

    Published on: November 6, 2017

    21.7K
    Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping
    07:11

    Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping

    Published on: December 8, 2023

    1.6K

    Related Experiment Videos

    Last Updated: Aug 3, 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

    2.8K
    Using Retinal Imaging to Study Dementia
    09:17

    Using Retinal Imaging to Study Dementia

    Published on: November 6, 2017

    21.7K
    Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping
    07:11

    Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping

    Published on: December 8, 2023

    1.6K

    Area of Science:

    • Ophthalmology
    • Medical Imaging
    • Computer Vision

    Background:

    • Glaucoma is a leading cause of irreversible blindness worldwide.
    • Accurate segmentation of the optic disc (OD) and optic cup (OC) in fundus images is vital for glaucoma screening.
    • Deep learning models face challenges in OD/OC segmentation due to domain shift caused by variations in image tone, contrast, and brightness across different healthcare centers.

    Purpose of the Study:

    • To propose a novel unsupervised domain adaptation (UDA) method, RDR-Net, to address the domain shift issue in OD/OC segmentation.
    • To improve the generalization ability of deep learning models for glaucoma screening across diverse fundus image datasets.
    • To develop a robust method for segmenting optic disc and optic cup that performs well even with variations in image acquisition.

    Main Methods:

    • Proposed Reconstruction-driven Dynamic Refinement Network (RDR-Net), a UDA method featuring a dual-path segmentation backbone for simultaneous edge detection and region prediction.
    • Implemented a Reconstruction Alignment (RA) module using a variational auto-encoder (VAE) for self-supervised image reconstruction and style-consistency to retain domain-invariant information.
    • Introduced a Low-level Feature Refinement (LFR) module with input-specific dynamic convolutions to suppress domain-variant information and a Prediction-Map Alignment (PMA) module using entropy-driven adversarial learning for boundary and region consistency.

    Main Results:

    • RDR-Net demonstrated superior performance compared to state-of-the-art methods on four public fundus image datasets.
    • The proposed method showed significant improvements in both segmentation accuracy and generalization ability.
    • Evaluation confirmed the effectiveness of RA, LFR, and PMA modules in alleviating the domain gap.

    Conclusions:

    • RDR-Net effectively addresses the domain shift problem in OD/OC segmentation for glaucoma screening.
    • The proposed UDA method offers enhanced generalization capabilities, making it suitable for deployment in diverse clinical settings.
    • RDR-Net represents a significant advancement in automated glaucoma screening through improved fundus image analysis.