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

Research Progress on Anti-Inflammatory Adipokine SFRP5-Mediated Lipid Metabolism and Its Potential Role in Neural Development.

Immunity, inflammation and disease·2026
Same author

Multicentre Pixel-Level Tear Meniscus Segmentation Dataset with Multimodal Imaging for Dry Eye Diagnosis.

Scientific data·2025
Same author

Effective automatic classification methods via deep learning for multi-type infectious keratitis diagnosis.

Graefe's archive for clinical and experimental ophthalmology = Albrecht von Graefes Archiv fur klinische und experimentelle Ophthalmologie·2025
Same author

TransDualSegNet: transformer dual segment network for retinal vasculature segmentation in OCT.

Quantitative imaging in medicine and surgery·2025
Same author

Research Progress in Artificial Intelligence for Central Serous Chorioretinopathy: A Systematic Review.

Ophthalmology and therapy·2025
Same author

Artificial intelligence-assisted tear meniscus height measurement: a multicenter study.

Quantitative imaging in medicine and surgery·2025

Related Experiment Video

Updated: Aug 20, 2025

Optimization of the Retinal Vein Occlusion Mouse Model to Limit Variability
07:23

Optimization of the Retinal Vein Occlusion Mouse Model to Limit Variability

Published on: August 6, 2021

2.8K

Hypermixed Convolutional Neural Network for Retinal Vein Occlusion Classification.

Guanghua Zhang1,2, Bin Sun3, Zhaoxia Zhang3

  • 1Department of Intelligence and Automation, Taiyuan University, Taiyuan 030000, China.

Disease Markers
|November 21, 2022
PubMed
Summary
This summary is machine-generated.

This study introduces a novel VGG-CAM network for automated diagnosis of retinal vein occlusion (RVO). The AI model accurately classifies RVO types and detects lesions in retinal images, aiding treatment strategies.

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

2.9K
In Vivo Multimodal Imaging and Analysis of Mouse Laser-Induced Choroidal Neovascularization Model
09:56

In Vivo Multimodal Imaging and Analysis of Mouse Laser-Induced Choroidal Neovascularization Model

Published on: January 21, 2018

9.3K

Related Experiment Videos

Last Updated: Aug 20, 2025

Optimization of the Retinal Vein Occlusion Mouse Model to Limit Variability
07:23

Optimization of the Retinal Vein Occlusion Mouse Model to Limit Variability

Published on: August 6, 2021

2.8K
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

2.9K
In Vivo Multimodal Imaging and Analysis of Mouse Laser-Induced Choroidal Neovascularization Model
09:56

In Vivo Multimodal Imaging and Analysis of Mouse Laser-Induced Choroidal Neovascularization Model

Published on: January 21, 2018

9.3K

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Retinal vein occlusion (RVO) is a prevalent vascular disease causing vision loss.
  • Accurate and timely diagnosis of RVO, classified as CRVO or BRVO, is crucial for effective treatment.
  • Automated diagnostic methods for differentiating RVO types are limited, presenting a clinical challenge.

Purpose of the Study:

  • To develop and validate a novel deep learning model for automated classification of Central Retinal Vein Occlusion (CRVO) and Branch Retinal Vein Occlusion (BRVO).
  • To implement an unsupervised learning method for detecting lesion areas associated with RVO in retinal fundus images.
  • To assess the potential of the proposed model in supporting research on RVO and cerebrovascular diseases.

Main Methods:

  • Development of a hypermixed convolutional neural network (CNN) model, termed VGG-CAM.
  • Utilizing a dataset of retinal fundus images labeled by senior ophthalmologists.
  • Employing unsupervised learning for lesion area detection within the VGG-CAM framework.

Main Results:

  • The VGG-CAM network demonstrated high accuracy in classifying the two main types of RVO (CRVO and BRVO).
  • The model successfully identified and localized lesion areas indicative of RVO using unsupervised learning.
  • Validation confirmed the network's capability in disease classification and lesion detection.

Conclusions:

  • The proposed VGG-CAM network offers a promising tool for the automated diagnosis and lesion detection in RVO.
  • This AI-driven approach can potentially enhance clinical workflows and optimize RVO treatment strategies.
  • Further research can explore the association between RVO and cerebrovascular diseases using this validated model.