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 Experiment Video

Updated: Jul 26, 2025

The Corneal Micropocket Assay: A Model of Angiogenesis in the Mouse Eye
11:49

The Corneal Micropocket Assay: A Model of Angiogenesis in the Mouse Eye

Published on: August 16, 2014

16.9K

Detecting the corneal neovascularisation area using artificial intelligence.

Burak Mergen1,2, Tarek Safi3, Matthias Nadig4

  • 1Department of Ophthalmology, Saarland University Medical Center (UKS), Homburg, Saarland, Germany burakmergen@gmail.com.

The British Journal of Ophthalmology
|June 20, 2023
PubMed
Summary

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

Dysregulated Intraocular Pressure in Acanthamoeba Keratitis: Clinical Associations, Therapy, and Prognosis.

Microorganisms·2026
Same author

Machine Learning-Based Prediction of Long-Term Intraocular Pressure Fluctuations in Open-Angle Glaucoma.

Ophthalmology science·2026
Same author

Long-term impact of scleral contact lens use on endothelial cell density in patients with moderate to advanced keratoconus.

BMC ophthalmology·2026
Same author

Excimer Laser-assisted Deep Anterior Lamellar Keratoplasty (Excimer-DALK).

Klinische Monatsblatter fur Augenheilkunde·2026
Same author

[Adjuvant Crosslinking to Improve Graft Survival after High-Risk Keratoplasty - A Case Series from the CrossCornealVision Study].

Klinische Monatsblatter fur Augenheilkunde·2026
Same author

In Vitro Analysis of Gene and Protein Expression in Primary Limbal Epithelial Cells Exposed to Differentiation-Inducing Medium.

Biology·2026
Same journal

Novel technique for treating extraocular muscle adherence after fracture repair.

The British journal of ophthalmology·2026
Same journal

Safe use of fluorinated gases in vitreoretinal surgery: learning from patient safety incidents with expert panel recommendations from the British and Eire Association of Vitreoretinal Surgeons (BEAVRS).

The British journal of ophthalmology·2026
Same journal

Fast progressors in Asian normal-tension glaucoma: 10 years and beyond in a longitudinal cohort.

The British journal of ophthalmology·2026
Same journal

Identifying patients with poor visual outcomes after primary rhegmatogenous retinal detachment surgery using machine learning.

The British journal of ophthalmology·2026
Same journal

Incidence of bilateral disease and choroidal neovascularisation in punctate inner choroiditis.

The British journal of ophthalmology·2026
Same journal

Reference map of multimodal vision deficits in intermediate age-related macular degeneration: contrast sensitivity and low-contrast visual acuity.

The British journal of ophthalmology·2026
See all related articles
This summary is machine-generated.

An artificial intelligence tool accurately quantifies corneal neovascularisation (CoNV) areas from slit-lamp images. This AI-powered analysis shows high accuracy, suggesting its potential for clinical use in CoNV assessment.

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Corneal neovascularisation (CoNV) poses a significant challenge in ophthalmology.
  • Accurate quantification of CoNV is crucial for effective treatment monitoring.
  • Manual assessment of CoNV can be time-consuming and subjective.

Purpose of the Study:

  • To develop and evaluate an AI-based image analysis tool for measuring corneal neovascularisation.
  • To automate the quantification of CoNV area from slit-lamp images.
  • To assess the performance of the AI tool against manual measurements.

Main Methods:

  • Deep learning (U-Net) model trained on manually annotated slit-lamp images of CoNV.
  • Sixfold cross-validation used for performance evaluation.
Keywords:
CorneaDiagnostic tests/InvestigationImagingNeovascularisationOcular surface

More Related Videos

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

9.2K
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

1.7K

Related Experiment Videos

Last Updated: Jul 26, 2025

The Corneal Micropocket Assay: A Model of Angiogenesis in the Mouse Eye
11:49

The Corneal Micropocket Assay: A Model of Angiogenesis in the Mouse Eye

Published on: August 16, 2014

16.9K
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

9.2K
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

1.7K
  • Intersection over union (IoU) metric employed to assess accuracy.

    • Main Results:

    • The AI tool achieved high IoU scores for total corneal area (90.0%-95.5%) and non-vascularised area (76.6%-82.2%).
    • High specificity was observed for detecting both total corneal area (96.4%-98.6%) and non-vascularised area (96.6%-98.0%).
    • The algorithm demonstrated strong performance in segmenting and detecting CoNV.

    Conclusions:

    • The AI tool exhibits high accuracy in quantifying CoNV areas compared to ophthalmologist measurements.
    • The developed automated tool shows promise for clinical application in CoNV assessment.
    • AI-powered image analysis can provide objective and efficient CoNV quantification.