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 13, 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

Fairness-aware deep learning for predicting visual field loss from optical coherence tomography.

Shreeya Pandey1, Leila Gheisi1, Yu Huang2

  • 1University of Louisiana at Lafayette, School of Computing and Informatics, Lafayette, Louisiana, United States.

Journal of Medical Imaging (Bellingham, Wash.)
|July 12, 2026
PubMed
Summary

Related Concept Videos

Depth Perception and Spatial Vision01:15

Depth Perception and Spatial Vision

Depth perception is the ability to perceive objects three-dimensionally. It relies on two types of cues: binocular and monocular. Binocular cues depend on the combination of images from both eyes and how the eyes work together. Since the eyes are in slightly different positions, each eye captures a slightly different image. This disparity between images, known as binocular disparity, helps the brain interpret depth. When the brain compares these images, it determines the distance to an object.

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Advances in biomechanical modeling of lumbar spine diseases and tumors: gaps, opportunities, and AI integration.

Frontiers in bioengineering and biotechnology·2026
Same author

Biomechanical analysis of lumbar oblique manipulation for lumbar disc herniation with different protrusion subtypes.

Mechanobiology in medicine·2026
Same author

A Review of Finite Element Analysis in Spine Surgery Decision-Making.

Journal of clinical medicine·2026
Same author

A Review of Synthetic Bone Grafts in Lumbar Interbody Fusion.

Bioengineering (Basel, Switzerland)·2026
Same author

The "Spine Intelligence" Era: AI, simulations and LLMs advancing precision spine care.

European spine journal : official publication of the European Spine Society, the European Spinal Deformity Society, and the European Section of the Cervical Spine Research Society·2026
Same author

A Review of Motion-Preserving Cervical Spinal Implants and Fusion Constructs.

Bioengineering (Basel, Switzerland)·2026

This study introduces a fairness-aware deep learning model using 3D OCT scans to predict visual field loss in glaucoma. The model improves prediction accuracy and reduces racial disparities in performance.

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Standard automated perimetry for glaucoma visual field loss is subjective and time-consuming.
  • Optical coherence tomography (OCT) offers fast, reproducible structural measurements.
  • OCT imaging presents an opportunity to estimate functional visual field loss.

Purpose of the Study:

  • To develop and evaluate a fairness-aware deep learning framework for predicting visual field loss from 3D OCT.
  • To jointly improve predictive accuracy and demographic equity in visual field prediction.
  • To integrate an adaptive fairness feedback (AFF) mechanism with 3D OCT modeling.

Main Methods:

  • A 3D ResNet-18 model was trained on 3300 paired OCT-VF samples.
  • The model incorporated demographic embeddings and an AFF mechanism for dynamic learning rate adjustment.
Keywords:
deep learningdemographic equityfairnessglaucomaoptical coherence tomographyvisual field prediction

Related Experiment Videos

Last Updated: Jul 13, 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

  • Performance was evaluated using metrics like MAE, RMSE, R², and subgroup disparity analysis.

    • Main Results:

    • The fairness-aware model achieved RMSE of 5.21 dB, MAE of 3.32 dB, and R² of 0.56.
    • The model reduced worst-group MAE from 3.90 to 3.53 dB and MAE disparity by 37% across racial subgroups.
    • Overall prediction accuracy was simultaneously improved while reducing performance disparities.

    Conclusions:

    • Fairness-aware volumetric modeling with AFF enhances OCT-based visual field prediction accuracy.
    • The approach effectively reduces racial performance disparities in glaucoma assessment.
    • Caution is advised for ethnicity-based results due to small subgroup sizes.