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

PEPNet: a two-stage point cloud framework with hierarchical embedding and antigen-antibody interaction modeling for epitope prediction.

Briefings in bioinformatics·2026
Same author

Artificial intelligence-based personalized treatment strategies for unresectable hepatocellular carcinoma: integrating HSP90α for prognosis and survival prediction.

NPJ digital medicine·2025
Same author

3D digital space analysis for leveling the curve of Spee.

BMC oral health·2025
Same author

Deep Unfolding Segmentation Network for Under-Sampled Magnetic Resonance Images.

IEEE journal of biomedical and health informatics·2025
Same author

Study on the correlation between soundscape perception and pro-environmental behaviors in Grand Canal National Cultural Park based on the expert perspective.

Scientific reports·2025
Same author

3D necroprinting: Leveraging biotic material as the nozzle for 3D printing.

Science advances·2025

Related Experiment Video

Updated: Jul 31, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

458

FEGNet: A Feedback Enhancement Gate Network for Automatic Polyp Segmentation.

Qunchao Jin, Hongyu Hou, Guixu Zhang

    IEEE Journal of Biomedical and Health Informatics
    |May 1, 2023
    PubMed
    Summary
    This summary is machine-generated.

    A new Feedback Enhancement Gate Network (FEGNet) improves automatic polyp segmentation for colonoscopies. This AI model enhances polyp detection, aiding in colorectal cancer prevention by accurately identifying polyps.

    More Related Videos

    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
    Two Algorithms for High-throughput and Multi-parametric Quantification of Drosophila Neuromuscular Junction Morphology
    12:29

    Two Algorithms for High-throughput and Multi-parametric Quantification of Drosophila Neuromuscular Junction Morphology

    Published on: May 3, 2017

    10.7K

    Related Experiment Videos

    Last Updated: Jul 31, 2025

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

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    458
    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
    Two Algorithms for High-throughput and Multi-parametric Quantification of Drosophila Neuromuscular Junction Morphology
    12:29

    Two Algorithms for High-throughput and Multi-parametric Quantification of Drosophila Neuromuscular Junction Morphology

    Published on: May 3, 2017

    10.7K

    Area of Science:

    • Medical Imaging
    • Artificial Intelligence
    • Gastroenterology

    Background:

    • Colorectal cancer (CRC) prevention relies on detecting colorectal polyps during colonoscopy.
    • Automatic polyp segmentation is crucial for precise polyp localization but challenging due to polyp variability and ambiguous boundaries.
    • Existing methods struggle with the diverse shapes, sizes, textures, and ill-defined edges of polyps.

    Purpose of the Study:

    • To introduce a novel U-shaped model, the Feedback Enhancement Gate Network (FEGNet), for accurate automatic polyp segmentation.
    • To address the challenges posed by polyp appearance variability and boundary ambiguity in colonoscopic images.
    • To improve the precision and reliability of polyp detection in colonoscopy through advanced AI techniques.

    Main Methods:

    • Proposed a U-shaped architecture named Feedback Enhancement Gate Network (FEGNet).
    • Introduced a Recurrent Gate Module (RGM) with a feedback mechanism for refining attention maps without extra parameters.
    • Incorporated a Feature Aggregation Attention Gate (FAAG) for context and feedback aggregation and a Multi-Scale Module (MSM) for multi-scale feature capture.
    • Developed an edge extraction module to guide early feature training using polyp boundary information.

    Main Results:

    • FEGNet demonstrated superior performance in polyp segmentation compared to state-of-the-art models.
    • Quantitative and qualitative evaluations confirmed the effectiveness of FEGNet across five diverse colonoscopy datasets.
    • The proposed RGM and edge extraction module significantly contributed to improved segmentation accuracy.

    Conclusions:

    • FEGNet offers a robust solution for accurate polyp segmentation in colonoscopy.
    • The model's ability to handle polyp variability and ambiguous boundaries enhances diagnostic support.
    • FEGNet shows significant potential for improving colorectal cancer screening and early detection through automated analysis.