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

Integrating basal and reserve salivary function defines clinically anchored functional phenotypes and contextualises salivary end points in Sjögren's disease.

RMD open·2026
Same author

Artificial Intelligence-Assisted Screening for Patients With Diabetic Retinopathy and Age-Related Macular Degeneration in Family Medicine and Geriatric and Gerontology Care: Protocol for a Pragmatic Randomized Clinical Trial.

JMIR research protocols·2026
Same author

Association between probiotic prescriptions and the incidence of primary open-angle glaucoma in patients with documented dry eye.

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

Association of Tirzepatide versus Glucagon-Like Peptide-1 Receptor Agonists with Incident Glaucoma in Patients with Type 2 Diabetes: A Retrospective Cohort Study.

Ophthalmology science·2026
Same author

GLP-1 Receptor Agonists and Age-related Macular Degeneration Risk in Diabetes or Non-diabetic Obesity: A Retrospective Cohort Study.

The American journal of medicine·2026
Same author

Comparative efficacy of single and double povidone-iodine soaking protocols combined with draping sequence in donor cornea disinfection.

Indian journal of ophthalmology·2026

Related Experiment Video

Updated: Dec 5, 2025

Corneal Confocal Microscopy: A Novel Non-invasive Technique to Quantify Small Fibre Pathology in Peripheral Neuropathies
11:29

Corneal Confocal Microscopy: A Novel Non-invasive Technique to Quantify Small Fibre Pathology in Peripheral Neuropathies

Published on: January 3, 2011

27.1K

Keratoconus Screening Based on Deep Learning Approach of Corneal Topography.

Bo-I Kuo1,2, Wen-Yi Chang3, Tai-Shan Liao4

  • 1Department of Ophthalmology, National Taiwan University Hospital, Taipei, Taiwan.

Translational Vision Science & Technology
|October 16, 2020
PubMed
Summary
This summary is machine-generated.

Deep learning algorithms accurately detect keratoconus using corneal topography, aiding ophthalmologists in early screening. Visualization methods confirm the models focus on key diagnostic areas for improved clinical explainability.

Keywords:
convolutional neuronal networkcorneal topographydeep learningkeratoconus

More Related Videos

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

1.9K
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

3.2K

Related Experiment Videos

Last Updated: Dec 5, 2025

Corneal Confocal Microscopy: A Novel Non-invasive Technique to Quantify Small Fibre Pathology in Peripheral Neuropathies
11:29

Corneal Confocal Microscopy: A Novel Non-invasive Technique to Quantify Small Fibre Pathology in Peripheral Neuropathies

Published on: January 3, 2011

27.1K
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

1.9K
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

3.2K

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Keratoconus is a progressive corneal ectasia.
  • Early detection is crucial for effective management.
  • Corneal topography is a key diagnostic tool.

Purpose of the Study:

  • Develop and compare deep learning algorithms for keratoconus detection.
  • Utilize corneal topography data for diagnosis.
  • Validate algorithms using visualization methods.

Main Methods:

  • Retrospective collection of corneal topographies (keratoconus, normal astigmatism).
  • Training and testing of three convolutional neural network (CNN) models.
  • Analysis of model performance using sensitivity, specificity, and ROC curves.
  • Visualization of pixel-wise discriminative features and heat maps.

Main Results:

  • CNN models demonstrated high accuracy (sensitivity/specificity > 0.90).
  • ResNet152 model achieved an area under the ROC curve of 0.995.
  • Visualization confirmed models focused on diagnostic clues (gradient differences).
  • Subclinical keratoconus was accurately predicted.

Conclusions:

  • Deep learning models show high accuracy for keratoconus screening.
  • Visualization enhances clinical explainability of AI in ophthalmology.
  • These models can assist ophthalmologists in diagnosing keratoconus.