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

Early Prostate-Specific Antigen Dynamics as Predictors of Treatment Response and Survival Outcomes in Patients with Castration-Resistant Prostate Cancer and Bone Metastases Undergoing Radium-223 Therapy.

The world journal of men's health·2026
Same author

Revisiting p53 Immunohistochemical Staining and Its Prognostic Implications in Advanced EGFR-Mutated Lung Adenocarcinoma.

Cancers·2025
Same author

Prevalence and clinical impact of JAK2-CHIP: Association with Parkinsonism and hematologic changes in a population cohort.

Journal of the Formosan Medical Association = Taiwan yi zhi·2025
Same author

Design and Validation of a Deep Learning Model for Renal Stone Detection and Segmentation on Kidney-Ureter-Bladder Images.

Bioengineering (Basel, Switzerland)·2023
Same author

Lightweight Authentication Mechanism for Industrial IoT Environment Combining Elliptic Curve Cryptography and Trusted Token.

Sensors (Basel, Switzerland)·2023
Same author

Mutation-Driven S100A8 Overexpression Confers Aberrant Phenotypes in Type 1 <i>CALR</i>-Mutated MPN.

International journal of molecular sciences·2023

Related Experiment Video

Updated: Jul 25, 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

2.8K

Retinal Vascular Image Segmentation Using Improved UNet Based on Residual Module.

Ko-Wei Huang1, Yao-Ren Yang1, Zih-Hao Huang1

  • 1Department of Electrical Engineering, National Kaohsiung University of Science and Technology, Kaohsiung 80778, Taiwan.

Bioengineering (Basel, Switzerland)
|June 28, 2023
PubMed
Summary

This study introduces an improved U-Net deep learning model for accurate retinal blood vessel segmentation in medical images. The AI model enhances diagnostic efficiency and outperforms existing methods on benchmark datasets.

Keywords:
deep learningmedical imageneural networkretinal vessel segmentation

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

2.5K
Efficient and Consistent Generation of Retinal Pigment Epithelium/Choroid Flatmounts from Human Eyes for Histological Analysis
07:59

Efficient and Consistent Generation of Retinal Pigment Epithelium/Choroid Flatmounts from Human Eyes for Histological Analysis

Published on: October 28, 2022

2.8K

Related Experiment Videos

Last Updated: Jul 25, 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

2.8K
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

2.5K
Efficient and Consistent Generation of Retinal Pigment Epithelium/Choroid Flatmounts from Human Eyes for Histological Analysis
07:59

Efficient and Consistent Generation of Retinal Pigment Epithelium/Choroid Flatmounts from Human Eyes for Histological Analysis

Published on: October 28, 2022

2.8K

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Deep learning in clinical diagnosis and medical imaging analysis is rapidly advancing.
  • Traditional medical image evaluation relies on individual clinician expertise, which can be time-consuming and subjective.
  • Artificial intelligence (AI) offers a trend towards automated analysis and diagnostic assistance for efficient medical information evaluation.

Purpose of the Study:

  • To propose a novel machine learning architecture for accurate retinal blood vessel segmentation.
  • To enhance feature extraction and combine multi-scale information for improved segmentation performance.

Main Methods:

  • Development of an improved U-Net neural network model incorporating a residual module for effective feature extraction.
  • Implementation of a full-scale skip connection to integrate low-level details with high-level features across different scales.
  • Experimental evaluation on benchmark datasets (DRIVE and ROSE) to assess segmentation accuracy.

Main Results:

  • The proposed model achieved accurate segmentation of retinal blood vessel images.
  • The method demonstrated superior performance compared to existing models like U-Net, ResUNet, U-Net3+, ResUNet++, and CaraNet on DRIVE and ROSE datasets.

Conclusions:

  • The enhanced U-Net architecture provides accurate and efficient retinal blood vessel segmentation.
  • This AI-driven approach supports clinicians in medical image evaluation, improving diagnostic efficiency.