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

MFI-Net: A multi-resolution fusion input network for retinal vessel segmentation.

PloS one·2021
Same author

Attention-Guided Network with Densely Connected Convolution for Skin Lesion Segmentation.

Sensors (Basel, Switzerland)·2021
Same author

Self-defensive antimicrobial biomaterial surfaces.

Colloids and surfaces. B, Biointerfaces·2020
Same author

Mono-Dispersed Microspheres Locally Assembled on Porous Substrates Formed through a Microemulsion Approach.

Polymers·2020
Same author

Downregulation of MiD49 contributes to tumor growth and metastasis of human pancreatic cancer.

Oncology reports·2020
Same author

Effect of artificial liver support system on short-term prognosis of patients with hepatitis B virus-related acute-on-chronic liver failure.

Artificial organs·2020

Related Experiment Video

Updated: Oct 18, 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

3.0K

Gated Skip-Connection Network with Adaptive Upsampling for Retinal Vessel Segmentation.

Yun Jiang1, Huixia Yao1, Shengxin Tao1

  • 1College of Computer Science and Engineering, Northwest Normal University, Lanzhou 730070, China.

Sensors (Basel, Switzerland)
|September 28, 2021
PubMed
Summary
This summary is machine-generated.

This study introduces GSAU-Net, a novel deep learning method for retinal vessel segmentation. GSAU-Net improves diagnostic accuracy for fundus diseases by enhancing information flow and feature recovery.

Keywords:
adaptive upsamplingdeep convolutional neural workgating mechanismretinal vessel segmentationskip-connection

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

568
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

Related Experiment Videos

Last Updated: Oct 18, 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

3.0K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

568
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

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Computer Vision

Background:

  • Retinal vessel segmentation is crucial for diagnosing fundus diseases.
  • Existing methods face challenges in accurately segmenting fine vascular structures.

Purpose of the Study:

  • To propose an enhanced deep learning network, GSAU-Net, for improved retinal vessel segmentation.
  • To leverage gated skip-connections and adaptive upsampling for better feature propagation and reconstruction.

Main Methods:

  • Developed Gated Skip-Connection Network with Adaptive Upsampling (GSAU-Net).
  • Implemented a novel gated skip-connection in the extension path for encoder-decoder information flow.
  • Utilized adaptive upsampling instead of bilinear interpolation for feature map recovery.

Main Results:

  • GSAU-Net achieved superior performance on DRIVE, CHASE, and STARE datasets.
  • Demonstrated higher accuracy, F-measure (83.13% on DRIVE, 81.40% on CHASE, 84.84% on STARE), and AUCROC compared to DeepVessel, AG-Net, and IterNet.

Conclusions:

  • GSAU-Net offers a significant advancement in automated retinal vessel segmentation.
  • The proposed architecture effectively enhances information transfer and feature reconstruction for improved diagnostic capabilities.