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: Jan 14, 2026

Optimization of the Retinal Vein Occlusion Mouse Model to Limit Variability
07:23

Optimization of the Retinal Vein Occlusion Mouse Model to Limit Variability

Published on: August 6, 2021

3.2K

Deep learning based retinal hard exudates quantification of optical coherence tomography.

Chang Ki Yoon1, Hyung Woo Lee2, Hyun Woong Kim3

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

International Journal of Retina and Vitreous
|October 17, 2025
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

Clinical and Molecular Features of <i>CNGA1</i>-Associated Retinitis Pigmentosa in an East Asian Cohort: Insights for Gene Therapy Trials.

Ophthalmology science·2026
Same author

Clinically grounded retinal representation learning from minimal supervision.

Scientific reports·2026
Same author

Intraocular Lens Positional Instability and Refractive Prediction Error after Cataract Surgery in Eyes with Retinitis Pigmentosa: A Comparative Study.

Korean journal of ophthalmology : KJO·2026
Same author

Impact of gestational diabetes on future diabetic retinopathy and microvascular complications: a nationwide cohort study.

BMC medicine·2026
Same author

Gas-Lesion Contact and Postural Compliance After Vitrectomy With Tamponade: A Continuous Monitoring and 3D Quantitative Analysis.

Translational vision science & technology·2026
Same author

Clinical and genetic characteristics of RPE65-associated inherited retinal degeneration in Koreans.

Scientific reports·2026

A deep learning model accurately segments retinal hard exudates in optical coherence tomography scans. This advanced method provides detailed 3D structural information for improved visualization and quantification.

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Retinal hard exudates (HE) are indicators of various retinal diseases.
  • Accurate segmentation of HE is crucial for diagnosis and monitoring.
  • Current imaging methods may lack detailed structural information.

Purpose of the Study:

  • To develop a deep learning (DL) model for segmenting retinal hard exudates (HE) from optical coherence tomography (OCT) scans.
  • To evaluate the model's accuracy in segmentation and volumetric prediction.
  • To compare the model's visualization capabilities with traditional imaging techniques.

Main Methods:

  • A modified U-Net architecture was employed for HE segmentation on OCT B-scans.
  • The model was trained on 1,811 OCT scans from patients with diabetic retinopathy or branch retinal vein occlusion.
Keywords:
Deep learningOptical coherence tomographyRetinal hard exudateVolume

More Related Videos

Doppler Optical Coherence Tomography of Retinal Circulation
10:46

Doppler Optical Coherence Tomography of Retinal Circulation

Published on: September 18, 2012

19.2K
In Vivo Vascular Injury Readouts in Mouse Retina to Promote Reproducibility
07:35

In Vivo Vascular Injury Readouts in Mouse Retina to Promote Reproducibility

Published on: April 21, 2022

2.6K

Related Experiment Videos

Last Updated: Jan 14, 2026

Optimization of the Retinal Vein Occlusion Mouse Model to Limit Variability
07:23

Optimization of the Retinal Vein Occlusion Mouse Model to Limit Variability

Published on: August 6, 2021

3.2K
Doppler Optical Coherence Tomography of Retinal Circulation
10:46

Doppler Optical Coherence Tomography of Retinal Circulation

Published on: September 18, 2012

19.2K
In Vivo Vascular Injury Readouts in Mouse Retina to Promote Reproducibility
07:35

In Vivo Vascular Injury Readouts in Mouse Retina to Promote Reproducibility

Published on: April 21, 2022

2.6K
  • Performance was assessed using Dice coefficient and accuracy; predictions were compared to manual measurements.

    • Main Results:

    • The DL model achieved a Dice coefficient of 0.721 and 99.9% accuracy on the test set.
    • Moderate correlations were found between predicted and manually measured HE volume and area (R=0.589, R=0.618).
    • The generated 2D projected image offered superior structural detail compared to fundus photographs.

    Conclusions:

    • The developed DL model accurately segments retinal HE from OCT scans.
    • It provides volumetric data with enhanced horizontal and vertical structural information.
    • This approach improves visualization and quantification compared to traditional 2D imaging.