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: Oct 20, 2025

Retinal Vascular Reactivity as Assessed by Optical Coherence Tomography Angiography
07:23

Retinal Vascular Reactivity as Assessed by Optical Coherence Tomography Angiography

Published on: March 26, 2020

8.4K

Genetic U-Net: Automatically Designed Deep Networks for Retinal Vessel Segmentation Using a Genetic Algorithm.

Jiahong Wei, Guijie Zhu, Zhun Fan

    IEEE Transactions on Medical Imaging
    |September 10, 2021
    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

    Circulating tumor DNA and prognosis in gastric cancer patients undergoing surgery: meta-analysis and trial sequential analysis.

    Frontiers in oncology·2026
    Same author

    Exploring the Mechanisms of <i>Hydrangea macrophylla</i> Adapting to Low Light-Induced Ornamental Whitening Through Physiological, Transcriptional, and Metabolomic Analyses.

    Genes·2026
    Same author

    Recent Advances (2023-2025) of Capillary Electrophoresis-Mass Spectrometry (CE-MS) for Top-Down Proteomics.

    Mass spectrometry reviews·2026
    Same author

    Evolution of anammox granular sludge performance during long-term preservation: Insights from double exponential kinetics.

    Bioresource technology·2026
    Same author

    TXNDC5 in POAG: Promoting Extracellular Matrix Protein Accumulation and Raising Intraocular Pressure.

    Investigative ophthalmology & visual science·2026
    Same author

    Spatiotemporal dynamics of seizure networks: Progressive posterior hippocampal recruitment in mesial temporal lobe epilepsy.

    Epilepsia·2026
    Same journal

    MUST: Multi-style virtual staining with incomplete pairs.

    IEEE transactions on medical imaging·2026
    Same journal

    BrainCL: Transformer-Based Brain Network Contrastive Learning with Multi-Order Topology and Salience Masking.

    IEEE transactions on medical imaging·2026
    Same journal

    LLM-enhanced Neuron Segmentation and Reconstruction in Complex Mouse Brain Images.

    IEEE transactions on medical imaging·2026
    Same journal

    Matrixed-Spectrum Decomposition Accelerated Linear Boltzmann Transport Equation Solver for Fast Scatter Correction in Multi-Spectral CT.

    IEEE transactions on medical imaging·2026
    Same journal

    The Ritz Adjoint Method for MRI Pulse Design.

    IEEE transactions on medical imaging·2026
    Same journal

    Physiology-guided Self-supervised Learning for Simultaneous Dual-Tracer PET Separation.

    IEEE transactions on medical imaging·2026
    See all related articles

    Genetic U-Net automatically designs convolutional neural networks (CNNs) for retinal vessel segmentation. This approach yields superior performance with significantly fewer parameters than manual designs, improving efficiency and accuracy.

    Area of Science:

    • Ophthalmology
    • Computer Science
    • Artificial Intelligence

    Background:

    • Hand-designed Convolutional Neural Networks (CNNs) show promise in retinal vessel segmentation but struggle with complex images.
    • Existing CNNs often have numerous parameters, leading to overfitting and high computational costs.
    • Manual CNN design is labor-intensive and requires specialized expertise.

    Purpose of the Study:

    • To propose an automated method, Genetic U-Net, for designing efficient U-shaped CNNs for retinal vessel segmentation.
    • To address limitations of manual CNN design, including parameter count, computational complexity, and development time.
    • To achieve superior segmentation performance with a reduced number of architecture-based parameters.

    Main Methods:

    • Devised a condensed yet flexible search space based on a U-shaped encoder-decoder architecture.

    More Related Videos

    Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
    05:56

    Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

    Published on: April 14, 2023

    2.8K
    Isolation of Murine Retinal Endothelial Cells for Next-Generation Sequencing
    09:59

    Isolation of Murine Retinal Endothelial Cells for Next-Generation Sequencing

    Published on: October 11, 2021

    3.3K

    Related Experiment Videos

    Last Updated: Oct 20, 2025

    Retinal Vascular Reactivity as Assessed by Optical Coherence Tomography Angiography
    07:23

    Retinal Vascular Reactivity as Assessed by Optical Coherence Tomography Angiography

    Published on: March 26, 2020

    8.4K
    Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
    05:56

    Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

    Published on: April 14, 2023

    2.8K
    Isolation of Murine Retinal Endothelial Cells for Next-Generation Sequencing
    09:59

    Isolation of Murine Retinal Endothelial Cells for Next-Generation Sequencing

    Published on: October 11, 2021

    3.3K
  • Employed an improved genetic algorithm to search for optimal network architectures within the defined space.
  • Investigated the correlation between network architecture and parameter efficiency for improved segmentation.

    • Main Results:

    • The Genetic U-Net achieved superior retinal vessel segmentation performance compared to existing methods.
    • The generated U-shaped CNN architecture utilized less than 1% of the parameters of the original U-Net.
    • The proposed method demonstrated significantly fewer parameters than other state-of-the-art models.
    • Identified effective network operations and patterns contributing to enhanced segmentation outcomes.

    Conclusions:

    • Genetic U-Net offers an effective automated approach for designing high-performance, parameter-efficient CNNs for retinal vessel segmentation.
    • This method overcomes the constraints of manual design, reducing computational complexity and development time.
    • The findings provide insights into designing superior network architectures for medical image analysis.