Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

Clinically grounded retinal representation learning from minimal supervision.

Scientific reports·2026

Same author

Lens Thickness and Refractive Prediction Error After Cataract Surgery Across Age Groups, Including Patients Aged 90 Years or Older.

Korean journal of ophthalmology : KJO·2026

Same author

Clinical Characteristics, Management, and Visual Outcomes of Spontaneous Corneal Perforation: A Single-Center Retrospective Study in South Korea.

Korean journal of ophthalmology : KJO·2026

Same author

Gut microbiota transfer from autoimmune dry eye mice imprints stereotypic B cell receptor repertoires in the lacrimal gland and induces disease.

Frontiers in immunology·2026

Same author

Correction: Clinical variant interpretation comparing two saturation genome editing-based functional studies for <i>BRCA2</i>.

Frontiers in genetics·2026

Same author

Correction to: Whole Genome Sequencing in 25 Families with Suspected Inborn Errors of Immunity: Diagnostic Yield and Clinical Relevance of Genome-wide Analysis.

Journal of clinical immunology·2026

Search research articles

Related Experiment Video

Updated: Jul 1, 2025

Comparing Objective Conjunctival Hyperemia Grading and the Ocular Surface Disease Index Score in Dry Eye Syndrome During COVID-19

Comparing Objective Conjunctival Hyperemia Grading and the Ocular Surface Disease Index Score in Dry Eye Syndrome During COVID-19

Published on: May 25, 2022

Deep learning-based fully automated grading system for dry eye disease severity.

Seonghwan Kim^1,2,3, Daseul Park^4,5, Youmin Shin^4,5

¹Department of Ophthalmology, Seoul National University College of Medicine, Seoul, Korea.

|March 14, 2024

Summary

This summary is machine-generated.

A new deep learning system automates dry eye disease (DED) severity grading using corneal fluorescein staining (CFS) images. This AI tool shows high accuracy, offering potential for objective clinical assessment of DED.

More Related Videos

Intense Pulsed Light for the Treatment of Dry Eye Owing to Meibomian Gland Dysfunction

Intense Pulsed Light for the Treatment of Dry Eye Owing to Meibomian Gland Dysfunction

Published on: April 1, 2019

Establishment of A Mouse Model of Aqueous Deficiency Dry Eye

Establishment of A Mouse Model of Aqueous Deficiency Dry Eye

Published on: November 1, 2024

Related Experiment Videos

Last Updated: Jul 1, 2025

Comparing Objective Conjunctival Hyperemia Grading and the Ocular Surface Disease Index Score in Dry Eye Syndrome During COVID-19

Comparing Objective Conjunctival Hyperemia Grading and the Ocular Surface Disease Index Score in Dry Eye Syndrome During COVID-19

Published on: May 25, 2022

Intense Pulsed Light for the Treatment of Dry Eye Owing to Meibomian Gland Dysfunction

Intense Pulsed Light for the Treatment of Dry Eye Owing to Meibomian Gland Dysfunction

Published on: April 1, 2019

Establishment of A Mouse Model of Aqueous Deficiency Dry Eye

Establishment of A Mouse Model of Aqueous Deficiency Dry Eye

Published on: November 1, 2024

Area of Science:

Ophthalmology
Artificial Intelligence
Medical Imaging

Background:

Dry eye disease (DED) requires objective grading systems for accurate severity assessment.
Current methods for evaluating DED severity can be subjective and time-consuming.

Purpose of the Study:

To develop and validate a fully automated deep learning-based system for assessing DED severity using corneal fluorescein staining (CFS) images.
To evaluate the system's accuracy and potential for clinical application in DED management.

Main Methods:

A deep learning system was developed using 1400 CFS images from DED patients for training and 94 images for external validation.
The system involved corneal segmentation, CFS candidate region classification, and NEI grade estimation via CFS density map generation.
Expert grading using the NEI scale served as the ground truth for system validation.

Main Results:

The automated system achieved high accuracy, with correlation coefficients of 0.868 (internal) and 0.863 (external) compared to expert grading.
The system demonstrated an 88% agreement rate in evaluating disease improvement or deterioration over time.
The corneal segmentation model achieved a Dice coefficient of 0.962, indicating robust performance.

Conclusions:

A fully automated deep learning system can accurately grade DED severity from CFS images.
This AI-driven approach shows significant potential for objective and efficient clinical application in DED assessment.