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: Dec 12, 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

3.2K

DoFE: Domain-Oriented Feature Embedding for Generalizable Fundus Image Segmentation on Unseen Datasets.

Shujun Wang, Lequan Yu, Kang Li

    IEEE Transactions on Medical Imaging
    |August 11, 2020
    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

    A retrieval-augmented framework enabling VLM spatial awareness for object-centric robot manipulation.

    Science robotics·2026
    Same author

    HandBooster+: Boosting 3D Hand-Mesh Reconstruction From Data Synthesis to Progressive Multi-Hypothesis Aggregation.

    IEEE transactions on pattern analysis and machine intelligence·2025
    Same author

    Visualization-Driven Illumination for Density Plots.

    IEEE transactions on visualization and computer graphics·2024
    Same author

    Video Instance Shadow Detection Under the Sun and Sky.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2024
    Same author

    DreamStone: Image as a Stepping Stone for Text-Guided 3D Shape Generation.

    IEEE transactions on pattern analysis and machine intelligence·2023
    Same author

    Kine-Appendage: Enhancing Freehand VR Interaction Through Transformations of Virtual Appendages.

    IEEE transactions on visualization and computer graphics·2023

    This study introduces a new Domain-oriented Feature Embedding (DoFE) framework to enhance deep learning models for fundus image segmentation. DoFE improves generalization to new datasets by leveraging knowledge from multiple sources.

    Area of Science:

    • Ophthalmology
    • Medical Imaging
    • Computer Science

    Background:

    • Deep convolutional neural networks (CNNs) excel at fundus image segmentation but struggle with variations across different data sources.
    • Distribution discrepancies between training and testing datasets lead to poor generalization and overfitting in CNNs.
    • Clinical fundus images exhibit appearance variations due to factors like scanner vendors and image quality.

    Purpose of the Study:

    • To develop a novel framework, Domain-oriented Feature Embedding (DoFE), to enhance the generalization ability of CNNs for fundus image segmentation on unseen target domains.
    • To leverage knowledge from multiple source domains to improve the robustness of deep learning models against domain shifts.
    • To create more discriminative semantic features by dynamically enriching image features with domain prior knowledge.

    More Related Videos

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    685

    Related Experiment Videos

    Last Updated: Dec 12, 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

    3.2K
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    685

    Main Methods:

    • Introduced a Domain Knowledge Pool to learn and store prior information from multiple source domains.
    • Augmented original image features with domain-oriented aggregated features, guided by input image similarity to source domains.
    • Designed a domain code prediction branch and an attention-guided mechanism for dynamic feature fusion.

    Main Results:

    • The DoFE framework demonstrated satisfying segmentation results on unseen fundus image datasets.
    • Achieved superior performance compared to existing domain generalization and network regularization methods.
    • Successfully improved generalization for optic cup/disc and vessel segmentation tasks.

    Conclusions:

    • The proposed DoFE framework effectively enhances the generalization ability of CNNs for fundus image segmentation.
    • Dynamic feature enrichment using multi-source domain knowledge is a promising approach to address domain shift challenges.
    • DoFE offers a robust solution for reliable medical image analysis across diverse clinical settings.