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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Proactive Support, Not Pressure: Responding to "Stop Pressuring Pharmacy Residents to be Licensed by July 1st".

American journal of pharmaceutical education·2026
Same author

Towards controllable video synthesis of routine and rare OR events.

International journal of computer assisted radiology and surgery·2026
Same author

CT-override: endoscopic updates to preoperative anatomical models during ablative surgery.

International journal of computer assisted radiology and surgery·2026
Same author

Detecting dataset bias in medical AI using a generalized and modality agnostic auditing approach.

NPJ digital medicine·2026
Same author

Investigating robot control policy learning for autonomous x-ray-guided spine procedures.

International journal of computer assisted radiology and surgery·2026
Same author

An analysis of two approaches to residency preparation and their effect on residency match results.

Currents in pharmacy teaching & learning·2026

Related Experiment Video

Updated: Aug 4, 2025

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping
07:11

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping

Published on: December 8, 2023

1.6K

Predicting Visual Field Worsening with Longitudinal OCT Data Using a Gated Transformer Network.

Kaihua Hou1, Chris Bradley2, Patrick Herbert2

  • 1Johns Hopkins University, Baltimore, Maryland.

Ophthalmology
|April 1, 2023
PubMed
Summary

A new Gated Transformer Network (GTN) model accurately identifies visual field (VF) worsening in glaucoma using OCT scans. This AI approach may streamline tracking functional decline with less demanding structural testing.

Keywords:
Artificial intelligenceDeep learningGlaucomaOCTVisual field

More Related Videos

Assessing Early Stage Open-Angle Glaucoma in Patients by Isolated-Check Visual Evoked Potential
07:11

Assessing Early Stage Open-Angle Glaucoma in Patients by Isolated-Check Visual Evoked Potential

Published on: May 25, 2020

6.4K
Translaminar Autonomous System Model for the Modulation of Intraocular and Intracranial Pressure in Human Donor Posterior Segments
08:55

Translaminar Autonomous System Model for the Modulation of Intraocular and Intracranial Pressure in Human Donor Posterior Segments

Published on: April 24, 2020

3.1K

Related Experiment Videos

Last Updated: Aug 4, 2025

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping
07:11

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping

Published on: December 8, 2023

1.6K
Assessing Early Stage Open-Angle Glaucoma in Patients by Isolated-Check Visual Evoked Potential
07:11

Assessing Early Stage Open-Angle Glaucoma in Patients by Isolated-Check Visual Evoked Potential

Published on: May 25, 2020

6.4K
Translaminar Autonomous System Model for the Modulation of Intraocular and Intracranial Pressure in Human Donor Posterior Segments
08:55

Translaminar Autonomous System Model for the Modulation of Intraocular and Intracranial Pressure in Human Donor Posterior Segments

Published on: April 24, 2020

3.1K

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Glaucoma is a progressive optic neuropathy characterized by visual field (VF) loss.
  • Accurate and timely detection of VF worsening is crucial for managing glaucoma and preventing vision loss.
  • Current methods for detecting VF worsening can be time-consuming and may not always capture subtle changes effectively.

Purpose of the Study:

  • To develop and evaluate a Gated Transformer Network (GTN) for identifying visual field (VF) worsening using longitudinal Optical Coherence Tomography (OCT) data.
  • To assess the performance of the GTN across various definitions of VF worsening and different glaucoma severity stages at baseline.
  • To compare the GTN's performance against traditional non-deep learning models.

Main Methods:

  • A retrospective longitudinal cohort study included 4211 eyes from 2666 patients with at least 5 reliable VF results and 1 OCT scan per year.
  • Seven reference standards for VF worsening were established, including trend-based and event-based methods, culminating in a "majority of 6" (M6) algorithm.
  • Seven GTNs were trained using serial OCT scans to predict VF worsening, and their performance was compared to linear mixed-effects models (MEMs) and naive Bayes classifiers (NBCs).

Main Results:

  • The GTN achieved a high Area Under the Curve (AUC) of 0.97 when trained with the M6 algorithm for identifying VF worsening.
  • GTNs trained with other reference standards showed AUCs ranging from 0.78 to 0.89.
  • All seven GTNs significantly outperformed corresponding MEMs and NBCs, although performance decreased in eyes with more severe baseline glaucoma.

Conclusions:

  • Gated Transformer Network models trained on OCT data demonstrate significant potential for identifying visual field worsening in glaucoma patients.
  • The GTN offers a promising, less onerous method for tracking functional glaucoma progression compared to traditional structural testing.
  • Further validation is recommended before clinical implementation to optimize the tracking of functional worsening in glaucoma.