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 4, 2026

Using Retinal Imaging to Study Dementia
09:17

Using Retinal Imaging to Study Dementia

Published on: November 6, 2017

Automated Optic Disc Tilt Classification in Fundus Photographs Using Segmentation and the Elliptical Ratio: External

Chae Yeon Lim1,2,3,4, Jaeryung Kim5, Joonhyoung Kim5

  • 1Department of Medical Device Management and Research, Samsung Advanced Institute for Health Sciences and Technology (SAIHST), Sungkyunkwan University, Seoul, Republic of Korea.

JMIR Formative Research
|July 2, 2026
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

Aquaporin-1 sustains lymphangiogenic responses in hyperosmotic inflammatory microenvironments.

The Journal of experimental medicine·2026
Same author

Beyond the lung: recognizing incidental breast lesions on chest computed tomography.

Translational cancer research·2026
Same author

Chemotherapy-driven intestinal dysbiosis and indole-3-propionic acid rewire myelopoiesis to promote a metastasis-refractory state.

Nature communications·2025
Same author

Optic neuritis and risk of heart failure and atrial fibrillation: A nationwide cohort study.

PNAS nexus·2025
Same author

The relationship between glycaemic status and the risk of third, fourth and sixth cranial nerve palsy: a nationwide population-based study (2009-2018).

Eye (London, England)·2025
Same author

Predicting Short-Term Outcome of COVID-19 Pneumonia Using Deep Learning-Based Automatic Detection Algorithm Analysis of Serial Chest Radiographs.

Bioengineering (Basel, Switzerland)·2025
Same journal

Technology-Enhanced Peer Support for Depression in Older Adults: Single-Arm Mixed Methods Feasibility Study.

JMIR formative research·2026
Same journal

AI-Assisted Clinical Data Abstraction From Electronic Health Records: Retrospective Concordance Study.

JMIR formative research·2026
Same journal

Structured Large Language Model Workflows for Motivational Interviewing in Health Behavior Change: Proof-of-Concept Study.

JMIR formative research·2026
Same journal

Mining Association Rules From a Multimodal Dataset of a Digital Therapeutics Application for Sleep Improvement Through a Healthy Lifestyle: Quantitative Study.

JMIR formative research·2026
Same journal

Construct Validation of a Remote Brain Health Assessment Battery to Evaluate Vocational Aptitude and Factors Associated With Cognitive Resilience in the Military: Observational Trial.

JMIR formative research·2026
Same journal

Identifying Behavior Change Techniques for Digital Interventions Addressing Alcohol and Tobacco Co-Use: Findings From a Delphi Consensus Study.

JMIR formative research·2026
See all related articles
This summary is machine-generated.

This study presents an AI pipeline for accurate optic disc tilt detection in eye images, improving diagnostic reliability for myopia-related conditions. The system offers objective analysis, enhancing clinical interpretation and AI-based assessments.

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Optic disc tilt is a common morphological change in myopic eyes.
  • It complicates the interpretation of fundus images and AI-based analyses.
  • Accurate detection is crucial for reliable diagnosis and avoiding misinterpretation.

Purpose of the Study:

  • To develop and validate an end-to-end AI pipeline for optic disc segmentation and tilt classification.
  • To provide an objective alternative to manual segmentation and subjective clinical assessments.
  • To enhance diagnostic reliability in color fundus photographs (CFPs).

Main Methods:

  • A nnU-Net-based model was trained on the SMDG dataset for optic disc segmentation.
  • External validation was performed on the Samsung Medical Center (SMC) dataset.
Keywords:
AIartificial intelligencecomputer-assisted diagnosisdigital healthfundus photographymyopiaophthalmic image analysisophthalmologistsoptic discoptic disc tiltretinal imagingsegmentationtelemedicine

More Related Videos

Quantitative Fundus Autofluorescence for the Evaluation of Retinal Diseases
07:22

Quantitative Fundus Autofluorescence for the Evaluation of Retinal Diseases

Published on: March 11, 2016

Related Experiment Videos

Last Updated: Jul 4, 2026

Using Retinal Imaging to Study Dementia
09:17

Using Retinal Imaging to Study Dementia

Published on: November 6, 2017

Quantitative Fundus Autofluorescence for the Evaluation of Retinal Diseases
07:22

Quantitative Fundus Autofluorescence for the Evaluation of Retinal Diseases

Published on: March 11, 2016

  • Tilt classification used the ratio of long-to-short axis diameters (≥1.3).
  • Performance was evaluated using Dice similarity coefficient, intersection over union, pixel accuracy, and clinical acceptance rates.

    • Main Results:

    • The AI pipeline achieved high segmentation performance (Dice: 0.956-0.961) on the SMDG dataset.
    • Clinical acceptance rates on the SMC dataset were high (98.61%-98.86%).
    • Optic disc tilt was detected in 7.5% of images, with varying rates across conditions like edema and glaucoma.

    Conclusions:

    • The developed AI pipeline offers objective and reproducible optic disc tilt detection in CFPs.
    • It demonstrates strong generalizability to clinical images.
    • The pipeline supports tilt-aware AI diagnostics and scalable screening for myopia-related conditions, with future improvements for edema-related cases.