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: Jun 3, 2026

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

A deep learning approach for keratoconus detection using spatio-temporal features from corneal imaging.

Arkadiusz Syta1, Tomasz Chorągiewicz2, Jakub Gęca3

  • 1Faculty of Mathematics and Information Technology, Department of Technical Computer Science, Lublin University of Technology, Nadbystrzycka 38, Lublin, 20-618, Poland. a.syta@pollub.pl.

Scientific Reports
|June 1, 2026
PubMed

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

Tea tree oil action on human corneal epithelial cells biological activity.

Graefe's archive for clinical and experimental ophthalmology = Albrecht von Graefes Archiv fur klinische und experimentelle Ophthalmologie·2026
Same author

Keratoconus molecular alterations revealed by Fourier-transform infrared spectroscopy.

Experimental eye research·2026
Same author

PMMA-based composite bone cements with zirconium oxide fillers of different granulations: structural optimization and biofunctional potential.

Frontiers in bioengineering and biotechnology·2026
Same author

Vascular Changes in the Macula and Peripapillary Regions Using Optical Coherence Tomography Angiography in Migraine with Aura and Migraine Without Aura.

Journal of clinical medicine·2026
Same author

Nanocarrier-Based Ocular Drug Delivery Systems for Retinal Diseases: Therapeutic Potential.

Life (Basel, Switzerland)·2026
Same author

Stabilization strategies as a factor modifying the chemical profile and valorization potential of grape pomace from temperate-climate cultivars.

Bioresource technology·2026
Summary

This study introduces a deep learning model for early keratoconus detection using corneal imaging. The AI achieved high accuracy in distinguishing healthy eyes from keratoconus cases.

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Keratoconus is a progressive corneal disease requiring early detection to prevent vision loss.
  • Accurate diagnosis is crucial for timely intervention and management of keratoconus.
  • Current diagnostic methods may benefit from advanced computational tools.

Purpose of the Study:

  • To develop and evaluate a deep learning model for classifying healthy versus keratoconic eyes.
  • To utilize dynamic corneal imaging data from the CORVIS system for keratoconus detection.
  • To assess the model's performance and generalization capabilities.

Main Methods:

  • A hybrid Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) architecture was employed.
  • The model combined an InceptionV3 network for spatial features and an LSTM module for temporal patterns.
Keywords:
BiomechanicsCNN-RNNCorneaDeep learningFuzzy logicKeratoconus

Related Experiment Videos

Last Updated: Jun 3, 2026

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

  • A 10-fold stratified cross-validation at the patient level ensured robust evaluation and prevented data leakage.

    • Main Results:

    • The deep learning model achieved an average accuracy, precision, recall, and F1-score of approximately 0.90.
    • The model demonstrated strong generalization performance with minimal variance across cross-validation folds.
    • High effectiveness was observed in classifying both healthy and keratoconic eyes, with slight variability in healthy eye classification.

    Conclusions:

    • The proposed deep learning model shows significant promise as a tool for keratoconus screening.
    • The method effectively distinguishes between healthy and keratoconic corneas using dynamic imaging data.
    • Further external dataset validation is recommended before clinical implementation.