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: Jun 6, 2025

Retinal Vascular Reactivity as Assessed by Optical Coherence Tomography Angiography
07:23

Retinal Vascular Reactivity as Assessed by Optical Coherence Tomography Angiography

Published on: March 26, 2020

7.1K

Retinal Vessel Plexus Differentiation Based on OCT Angiography Using Deep Learning.

Jamie L Shaffer1,2, Luis De Sisternes3, Anand E Rajesh1,2

  • 1Department of Ophthalmology, UW Medicine, Seattle, Washington.

Ophthalmology Science
|December 3, 2024
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

Automated Deep Learning Quantification of Avascular Area and Intravitreal Neovascularization in Retinal Flatmounts of Rodent Oxygen-Induced Retinopathy Models.

Translational vision science & technology·2026
Same author

Uses and Abuses of Big Data in Ophthalmology Research.

Ophthalmology·2026
Same author

Traumatic brain injury and late-life Alzheimer's disease neuropathology: Quantitative investigation in the Adult Changes in Thought study.

Journal of Alzheimer's disease : JAD·2026
Same author

Quantitative Swept-Source Optical Coherence Tomography Angiography Indicators of Neurovascular Dysfunction in Alzheimer Disease.

JAMA ophthalmology·2026
Same author

Age-related macular degeneration severity and risk of Alzheimer's disease in older adults in a prospective, community-based cohort study.

Alzheimer's & dementia (Amsterdam, Netherlands)·2026
Same author

Mobile-Based Artificial Intelligence and Ocular Surface Malignancies.

JAMA ophthalmology·2026
Same journal

Split-Spectrum Amplitude-Decorrelation Optoretinography Detects Impaired Photoreceptor Function in Age-Related Macular Degeneration.

Ophthalmology science·2026
Same journal

Genome-Wide Association Study for Glucocorticoid-Induced Ocular Hypertension.

Ophthalmology science·2026
Same journal

Assessing Polypoidal Choroidal Vasculopathy-Related OCT Features in the TENAYA and LUCERNE Trials.

Ophthalmology science·2026
Same journal

Quantitative Analysis of Choroidal Thickness and Blood Flow in Thyroid-Associated Ophthalmopathy Using Ultra-Widefield Swept-Source OCT Angiography.

Ophthalmology science·2026
Same journal

Epiretinal Membrane Is Associated with Acquired Vitelliform Lesion Morphometrics in Intermediate Age-Related Macular Degeneration.

Ophthalmology science·2026
Same journal

Multisource Machine Learning Model for Detecting Referral-Warranted Retinopathy of Prematurity.

Ophthalmology science·2026
See all related articles
This summary is machine-generated.

This study demonstrates deep learning can segment retinal vascular plexuses using only OCT angiography (OCTA) data, eliminating the need for structural OCT images. Synthetic 2-class images significantly improved segmentation performance.

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Optical Coherence Tomography Angiography (OCTA) is crucial for visualizing retinal vasculature.
  • Traditional methods rely on structural Optical Coherence Tomography (OCT) for differentiating vascular plexuses.
  • Vascular plexuses do not always align with retinal layers, posing segmentation challenges.

Purpose of the Study:

  • To develop a deep learning model for segmenting superficial, deep, and avascular plexuses from OCTA images.
  • To achieve segmentation without relying on structural OCT input or predefined segmentation boundaries.
  • To assess the efficacy of using OCTA data alone for plexus segmentation.

Main Methods:

  • A U-Net based deep learning model was trained and evaluated on 235 OCTA cubes (705 images) from 33 patients.
Keywords:
Deep learningOCT angiographyRetinal vascular plexusRetinal vasculature

More Related Videos

Monitoring Dynamic Growth of Retinal Vessels in Oxygen-Induced Retinopathy Mouse Model
10:32

Monitoring Dynamic Growth of Retinal Vessels in Oxygen-Induced Retinopathy Mouse Model

Published on: April 2, 2021

3.4K
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

2.1K

Related Experiment Videos

Last Updated: Jun 6, 2025

Retinal Vascular Reactivity as Assessed by Optical Coherence Tomography Angiography
07:23

Retinal Vascular Reactivity as Assessed by Optical Coherence Tomography Angiography

Published on: March 26, 2020

7.1K
Monitoring Dynamic Growth of Retinal Vessels in Oxygen-Induced Retinopathy Mouse Model
10:32

Monitoring Dynamic Growth of Retinal Vessels in Oxygen-Induced Retinopathy Mouse Model

Published on: April 2, 2021

3.4K
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

2.1K
  • Weakly labeled images were augmented, and synthetic 2-class images were created to enhance training.
  • The model's generalization was tested on multiclass thin slabs from OCTA volumes.

    • Main Results:

    • The model achieved high Dice scores (>0.82) on single-class images and significantly improved (>0.95) with synthetic 2-class images.
    • The model successfully performed plexus labeling on multiclass slab data, demonstrating generalization.
    • OCTA data alone proved effective for segmenting retinal vascular plexuses.

    Conclusions:

    • Deep learning models can segment superficial, deep, and avascular retinal plexuses using OCTA data exclusively.
    • Reliance on structural OCT layer segmentations as boundaries is not necessary for accurate plexus segmentation.
    • The use of synthetic 2-class images offers a significant performance improvement in OCTA-based segmentation.