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: Sep 11, 2025

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

2.8K

Individualized Estimation of Baseline Retinal Nerve Fiber Layer Thickness Using Conditional Variational Autoencoder.

Ou Tan1, Keke Liu1,2, Aiyin Chen1

  • 1Casey Eye Institute, Oregon Health & Science University, Portland, Oregon.

Ophthalmology Science
|August 13, 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

Semaglutide and Neovascular Age-Related Macular Degeneration Among Adults with Type 2 Diabetes: An OHDSI Network Study.

Ophthalmology·2026
Same author

Topical Brimonidine Is Associated With Trabeculectomy Failure in Glaucoma Patients.

American journal of ophthalmology·2026
Same author

Semaglutide and diabetic retinopathy: an OHDSI network study.

BMJ open diabetes research & care·2025
Same author

Mitomycin C in Ahmed Glaucoma Valve Implant Affects Surgical Outcomes.

Bioengineering (Basel, Switzerland)·2025
Same author

Reduced Ocular Surface Inflammation in SMILE Patients: The Beneficial Outcome of 0.1% Ciclosporin Cationic Emulsion Treatment.

Clinical ophthalmology (Auckland, N.Z.)·2025
Same author

Development and Evaluation of a Computable Phenotype for Normal Tension Glaucoma.

Ophthalmology science·2025
Same journal

Tropomyosin-Related Kinase Receptor Type B Agonism in Geographic Atrophy-The Translational Challenges from Preclinical Data to a First-in-Human Trial.

Ophthalmology science·2026
Same journal

Disease and Participant-Related Correlates of Genetic Testing Completion for Hereditary Eye Disorders in a Cohort of over 1400 Patients.

Ophthalmology science·2026
Same journal

Nationwide Multicenter Survey of Severe Complications of Strabismus Surgery in Japan: Japanese Strabismus Surgery Study.

Ophthalmology science·2026
Same journal

Pathways to Patchy Atrophy in High Myopia: Precursor Patterns, Structural Characteristics, and Long-Term Outcomes.

Ophthalmology science·2026
Same journal

Sleep Pattern and Structural Damage in Older Adults with Glaucoma: A United States and China Study.

Ophthalmology science·2026
Same journal

Machine Learning-Based Prediction of Long-Term Intraocular Pressure Fluctuations in Open-Angle Glaucoma.

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

Generative deep learning models create personalized nerve fiber layer thickness profiles. This AI approach improves accuracy in detecting thinning, especially in myopic eyes.

Area of Science:

  • Ophthalmology
  • Artificial Intelligence
  • Medical Imaging

Background:

  • Nerve fiber layer thickness (NFLT) is crucial for diagnosing glaucoma.
  • Accurate NFLT assessment requires individualized reference profiles.
  • Current methods may lack precision, particularly in myopic eyes.

Purpose of the Study:

  • To develop generative deep learning (DL) models for estimating individualized baseline nerve fiber layer thickness (NFLT) profiles.
  • To incorporate individual ocular characteristics, including vascular patterns, into NFLT estimations.
  • To improve the accuracy of NFLT assessment and detection of thinning.

Main Methods:

  • A cross-sectional study utilizing data from the Hong Kong FAMILY and Casey Eye Institute (CEI) cohorts.
  • Generative DL models were trained to reconstruct individualized NFLT using spectral-domain OCT data, vascular patterns, axial length, refractive error, and demographics.
Keywords:
Conditional variational autoencoderGlaucomaNerve fiber layer thicknessOCT

More Related Videos

Using Retinal Imaging to Study Dementia
09:17

Using Retinal Imaging to Study Dementia

Published on: November 6, 2017

21.8K
In Vivo Multimodal Imaging and Analysis of Mouse Laser-Induced Choroidal Neovascularization Model
09:56

In Vivo Multimodal Imaging and Analysis of Mouse Laser-Induced Choroidal Neovascularization Model

Published on: January 21, 2018

9.3K

Related Experiment Videos

Last Updated: Sep 11, 2025

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

2.8K
Using Retinal Imaging to Study Dementia
09:17

Using Retinal Imaging to Study Dementia

Published on: November 6, 2017

21.8K
In Vivo Multimodal Imaging and Analysis of Mouse Laser-Induced Choroidal Neovascularization Model
09:56

In Vivo Multimodal Imaging and Analysis of Mouse Laser-Induced Choroidal Neovascularization Model

Published on: January 21, 2018

9.3K
  • Models were compared against population means and multiple linear regression (MLR) using fivefold cross-validation.

    • Main Results:

    • DL models significantly reduced prediction error for overall and quadrant NFLT compared to population means and MLR.
    • The models decreased the false-positive rate of identifying abnormal NFLT thinning in myopic groups (from 13.0%-27.0% to 6.3%-9.4%).
    • Prediction error reductions were independently validated using CEI cohort data.

    Conclusions:

    • Generative DL models can construct individualized NFLT baseline profiles using OCT-derived vascular patterns.
    • These AI-driven individualized baselines reduce NFLT prediction error in healthy eyes.
    • This approach shows potential for improving the accuracy of detecting abnormal NFLT thinning, particularly in myopic individuals.