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

Editorial: Biomechanical and cognitive pattern assessment in human-machine collaborative tasks for industrial robotics.

Frontiers in neurorobotics·2026
Same author

Standalone RFID Access Control System with Data-Integrity Verification Capabilities.

Sensors (Basel, Switzerland)·2026
Same author

A privacy-centric microservice framework for secure FHIR-based integration of heterogeneous medical data.

International journal of medical informatics·2026
Same author

Artificial intelligence-assisted diagnosis and subtype differentiation of infectious keratitis.

Eye (London, England)·2026
Same author

Quantitative imaging for assessing uveitis activity: A comprehensive review.

Survey of ophthalmology·2026
Same author

Reply.

Ophthalmology science·2026

Related Experiment Video

Updated: Oct 9, 2025

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.8K

A Hybrid Deep Learning Construct for Detecting Keratoconus From Corneal Maps.

Ali H Al-Timemy1,2, Zahraa M Mosa3, Zaid Alyasseri4,5

  • 1Biomedical Engineering Department, Al-Khwarizmi College of Engineering, University of Baghdad, Baghdad, Iraq.

Translational Vision Science & Technology
|December 16, 2021
PubMed
Summary
This summary is machine-generated.

A new hybrid deep learning model accurately detects keratoconus (KCN) using corneal topographic maps. This AI approach offers a fast and efficient method for identifying KCN in clinical settings.

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

3.0K
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: Oct 9, 2025

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.8K
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

3.0K
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

Area of Science:

  • Ophthalmology
  • Artificial Intelligence
  • Medical Imaging

Background:

  • Keratoconus (KCN) is a progressive eye condition affecting corneal shape.
  • Accurate and early detection of KCN is crucial for effective management.
  • Current diagnostic methods can be invasive or require specialized expertise.

Purpose of the Study:

  • To develop and evaluate a hybrid deep learning model for keratoconus detection.
  • To assess the accuracy of the model using corneal topographic maps.
  • To establish a time-efficient and computationally inexpensive KCN detection framework.

Main Methods:

  • Collected 3794 corneal images from 280 subjects for model development.
  • Utilized seven deep learning models based on various corneal topographic parameters.
  • Validated the hybrid model on an independent dataset of 1050 images from 85 subjects.
  • Evaluated model performance using AUC, confusion matrices, accuracy, and F1 score.

Main Results:

  • The hybrid deep learning model demonstrated high accuracy in detecting KCN.
  • AUC values reached 0.99 for two-class and 0.93 for three-class KCN detection on the development set.
  • The model successfully differentiated between normal, suspected, and confirmed KCN cases.

Conclusions:

  • A hybrid deep learning model can accurately detect keratoconus from corneal topographic maps.
  • The developed model offers a time-efficient framework with low computational complexity.
  • Deep learning shows significant potential for KCN detection in research and clinical practice.