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

Interface-Defect-Morphology Multivariable Engineering of Two-Dimensional BiOBr Nanosheets on TiO<sub>2</sub> Nanotube Arrays for ppb-Level NO<sub>2</sub> Detection at Room Temperature.

ACS sensors·2026
Same author

Correction to "Accelerating Carrier Transfer in Dual p-n Heterojunctions by Mo-N Coupling to Gain an Ultrahigh-Sensitive NO<sub>2</sub> Sensing at Room Temperature for Asthma Diagnosis".

ACS sensors·2025
Same author

On-Site Generation of Coreactant on a Solid-State Electrochemiluminescence Electrode for Label-Free Detection of Enterohemorrhagic <i>Escherichia coli</i> in Raw Meat Samples.

Analytical chemistry·2025
Same author

Stabilizing Ti(III) Species in Black TiO<sub>2</sub> via a Phosphate Capping Layer for Sub-Parts-per-Billion-Level NO<sub>2</sub> Detection at Room Temperature.

ACS sensors·2025
Same author

Accelerating Carrier Transfer in Dual p-n Heterojunctions by Mo-N Coupling to Gain an Ultrahigh-Sensitive NO<sub>2</sub> Sensing at Room Temperature for Asthma Diagnosis.

ACS sensors·2025
Same author

Integrating Vacancies and Defect Levels in Heterojunctions to Synergistically Enhance the Performance of H<sub>2</sub>S Chemiresistors for Periodontitis Diagnosis.

ACS sensors·2025

Related Experiment Video

Updated: Oct 25, 2025

Full-Field Optical Coherence Microscopy for Histology-Like Analysis of Stromal Features in Corneal Grafts
07:51

Full-Field Optical Coherence Microscopy for Histology-Like Analysis of Stromal Features in Corneal Grafts

Published on: October 21, 2022

1.8K

[Classification Model of Corneal Opacity Based on Digital Image Features].

Peng Luo1, Jilong Zheng2, Peng Zhou1

  • 1Department of Biomedical Engineering, China Medical University, Shenyang, 110122.

Zhongguo Yi Liao Qi Xie Za Zhi = Chinese Journal of Medical Instrumentation
|August 7, 2021
PubMed
Summary

This study developed a support vector machine (SVM) model to objectively classify corneal opacity using digital image features. The model achieved a high F1 score, demonstrating its effectiveness in quantifying opacity levels.

Keywords:
SVMcorneal opacityfeature extractionfeature selection

More Related Videos

A Porcine Corneal Endothelial Organ Culture Model Using Split Corneal Buttons
08:36

A Porcine Corneal Endothelial Organ Culture Model Using Split Corneal Buttons

Published on: October 6, 2019

7.3K
Author Spotlight: Establishing a Practical and Cost-Effective Protocol for Corneal Sensitivity Testing in Clinical Settings
04:00

Author Spotlight: Establishing a Practical and Cost-Effective Protocol for Corneal Sensitivity Testing in Clinical Settings

Published on: August 2, 2024

2.6K

Related Experiment Videos

Last Updated: Oct 25, 2025

Full-Field Optical Coherence Microscopy for Histology-Like Analysis of Stromal Features in Corneal Grafts
07:51

Full-Field Optical Coherence Microscopy for Histology-Like Analysis of Stromal Features in Corneal Grafts

Published on: October 21, 2022

1.8K
A Porcine Corneal Endothelial Organ Culture Model Using Split Corneal Buttons
08:36

A Porcine Corneal Endothelial Organ Culture Model Using Split Corneal Buttons

Published on: October 6, 2019

7.3K
Author Spotlight: Establishing a Practical and Cost-Effective Protocol for Corneal Sensitivity Testing in Clinical Settings
04:00

Author Spotlight: Establishing a Practical and Cost-Effective Protocol for Corneal Sensitivity Testing in Clinical Settings

Published on: August 2, 2024

2.6K

Area of Science:

  • Veterinary Ophthalmology
  • Biomedical Image Analysis
  • Machine Learning in Medicine

Background:

  • Corneal opacity is a significant issue in animal health, often requiring subjective assessment.
  • Objective quantification methods are needed for accurate diagnosis and treatment monitoring.
  • Digital imaging offers potential for automated analysis of corneal conditions.

Purpose of the Study:

  • To develop and validate a multi-classification support vector machine (SVM) model for objective quantification of corneal opacity.
  • To explore the utility of digital image features for classifying the severity of corneal opacity.
  • To establish a reliable method for assessing corneal opacity in veterinary diagnostics.

Main Methods:

  • Collection of digital cornea images from deceased pigs.
  • Extraction of relevant color and texture features from the images.
  • Development of a multi-classification SVM model, optimized using SVM-Recursive Feature Elimination (SVM-RFE) and cross-validation.
  • Evaluation of model performance using precision, sensitivity, and F1 scores.

Main Results:

  • The developed SVM model successfully classified degrees of corneal opacity.
  • The highest F1 score achieved was 0.9744, indicating high accuracy.
  • An optimal feature subset comprising 126 features was identified for model optimization.

Conclusions:

  • The SVM multi-classification model provides an effective and objective method for classifying corneal opacity.
  • Digital image analysis combined with machine learning can accurately assess corneal opacity.
  • This approach holds promise for improving diagnostic accuracy in veterinary ophthalmology.