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

Adjuvant-Enabled Halving of Florpyrauxifen-Benzyl Dose Maintains Paddy Weed Control and Enhances Soil Health and Rice Yield.

Plants (Basel, Switzerland)·2026
Same author

A resveratrol derivative RVX-208 inhibits PD-1/PD-L1 to restrain non-small cell lung cancer as an immunotherapy.

Biochemical pharmacology·2026
Same author

Effects of endogenous walnut pellicle polyphenols on the structure and functional properties of walnut meal isolate proteins.

Food chemistry: X·2026
Same author

Corrigendum to "Microenvironment-responsive hydrogels for spatiotemporal delivery of epigallocatechin gallate and BMP-2 to promote osteoporotic bone defect repair" [Mater. Today Bio Volume 35 (2025) 102290].

Materials today. Bio·2026
Same author

A Novel Denoising Method for Mud Continuous-Wave Signals Based on Selective Ensemble Strategy with Particle Swarm Optimization.

Sensors (Basel, Switzerland)·2025
Same author

Up-regulation of Ifi27l2a expression in bone marrow monocytes contributes to glucocorticoid-induced bone loss.

Communications biology·2025

Related Experiment Video

Updated: Jul 1, 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

2.7K

PKSEA-Net: A prior knowledge supervised edge-aware multi-task network for retinal arteriolar morphometry.

Chongjun Huang1, Zhuoran Wang1, Guohui Yuan1

  • 1School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, 611731, China; Yangtze Delta Region Institute (Quzhou), University of Electronic Science and Technology of China, Quzhou, Zhejiang 324000, China.

Computers in Biology and Medicine
|March 10, 2024
PubMed
Summary
This summary is machine-generated.

PKSEA-Net enhances retinal vessel segmentation in fundus images by improving edge detection. This novel method offers precise boundary delineation for better cardiovascular and cerebrovascular disease insights.

Keywords:
Edge awareMulti-task learningPrior knowledge supervisionRetinal arteriolar morphometryVision transformer

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

399
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

2.4K

Related Experiment Videos

Last Updated: Jul 1, 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

2.7K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

399
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

2.4K

Area of Science:

  • Ophthalmology and Medical Imaging
  • Artificial Intelligence in Medicine
  • Biomedical Engineering

Background:

  • Retinal fundus images provide non-invasive insights into cardiovascular and cerebrovascular health via retinal vessel analysis.
  • Retinal arteriolar morphometry is crucial for patient screening but faces challenges due to image noise and blurred vessel boundaries.
  • Accurate segmentation of retinal vessels is essential for reliable diagnostic interpretation.

Purpose of the Study:

  • To introduce PKSEA-Net, a novel deep learning methodology for enhanced retinal vessel segmentation in fundus images.
  • To improve the perception of edge information in retinal images for more accurate vessel boundary delineation.
  • To establish a new benchmark dataset, Retinal Cross-Sectional Vessel (RCSV), for evaluating retinal vessel segmentation algorithms.

Main Methods:

  • PKSEA-Net utilizes the PVT-v2 architecture as an encoder.
  • A novel decoder architecture incorporates an Edge-Aware Block (EAB) and a Pyramid Feature Fusion Module (PFFM).
  • The EAB block uses prior knowledge, enhanced Full Width at Half Maximum (FWHM) algorithm, and gradient maps for supervision, while PFFM integrates multi-scale features via attention fusion.

Main Results:

  • PKSEA-Net demonstrated superior performance in retinal vessel segmentation compared to state-of-the-art networks.
  • The method achieved precise boundary delineation, outperforming existing approaches.
  • The newly collected RCSV dataset served as a valuable benchmark for comparative evaluations.

Conclusions:

  • PKSEA-Net represents a state-of-the-art approach for accurate retinal vessel segmentation.
  • The enhanced edge perception and feature fusion capabilities of PKSEA-Net address key limitations in current methods.
  • This advancement holds significant potential for improving the diagnosis and monitoring of systemic diseases through retinal imaging.