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 10, 2026

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

Image-Quality-Aware Multimodal Artificial Intelligence for Automated Structured OCT Report Generation in Glaucoma

Jalil Jalili1,2, Yashraj Gavhane1,3, Evan Walker1,2

  • 1Division of Ophthalmology Informatics and Data Science, Viterbi Family Department of Ophthalmology, Shiley Eye Institute, University of California San Diego, La Jolla, California.

Ophthalmology Science
|July 9, 2026
PubMed
Summary

Related Concept Videos

Glaucoma: Overview01:25

Glaucoma: Overview

Glaucoma is an eye condition characterized by increased intraocular pressure that damages the retina and optic nerve, leading to irreversible blindness if left untreated. The human eye has various components, including the cornea, iris, pupil, lens, and optic nerve. Aqueous humor is secreted by the epithelium of the ciliary body in the posterior chamber and flows through the trabecular meshwork and canal of Schlemm, maintaining normal intraocular pressure. The trabecular meshwork and the canal...

You might also read

Related Articles

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

Sort by
Same author

Differential Impact of Intraocular Pressure Lowering on Glaucoma Progression in African and European Descent Individuals.

American journal of ophthalmology·2026
Same author

Nicotinamide Supplementation and Primary Open-Angle Glaucoma in Patients With Ocular Hypertension.

JAMA ophthalmology·2026
Same author

Dataset documentation for responsible AI: analysis of suitability and usage for health datasets.

NPJ digital medicine·2026
Same author

Association of Deep Optic Nerve Head Structural Remodeling with Choroidal Microvasculature Dropout in Glaucoma with and without Myopia.

American journal of ophthalmology·2026
Same author

Glaucomatous Remodeling of the Lamina Cribrosa: Association With Visual Field Progression.

Investigative ophthalmology & visual science·2026
Same author

A Comparative Analysis of Visual Field Test Results Using Tablet-Based and Table-Mounted Devices in a Telemedicine Program Set in Underserved Areas.

Translational vision science & technology·2026

A new multimodal large language model (MM-LLM) accurately screens optic nerve head (ONH) OCT scans for quality and detects glaucoma. It also generates detailed reports on retinal nerve fiber layer (RNFL) thinning, aiding clinical decisions.

Area of Science:

  • Ophthalmology
  • Artificial Intelligence
  • Medical Imaging Analysis

Background:

  • Optic nerve head (ONH) and retinal nerve fiber layer (RNFL) assessments are crucial for glaucoma diagnosis.
  • Automated analysis of OCT scans can improve efficiency and accuracy in clinical practice.

Purpose of the Study:

  • Develop an explainable multimodal large language model (MM-LLM) for ONH OCT scan quality screening.
  • Generate structured clinical reports including glaucoma diagnosis and sector-wise RNFL thinning assessments.

Main Methods:

  • A retrospective cohort study utilized longitudinal data from two large glaucoma studies.
  • An MM-LLM (Llama 3.2 Vision-Instruct) was fine-tuned on 43,849 Spectralis OCT scans.
  • The model was evaluated on quality assessment, glaucoma detection, and RNFL thinning classification.
Keywords:
Clinical report generationGlaucoma detectionMultimodal large language modelQuality triageRetinal nerve fiber layer

Related Experiment Videos

Last Updated: Jul 10, 2026

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

Main Results:

  • The MM-LLM achieved 0.90 accuracy for quality triage and 0.86 accuracy for glaucoma detection.
  • RNFL thinning prediction accuracy ranged from 0.83 to 0.94 across seven anatomical sectors.
  • Text generation quality showed strong alignment with reference reports (e.g., BERTScore-F1: 0.99).

Conclusions:

  • The fine-tuned MM-LLM accurately analyzes OCT images, identifies quality issues, and detects glaucoma.
  • The model provides valuable sectoral RNFL thinning descriptions for clinical decision support.
  • Further validation is needed, but the approach shows potential as a scalable tool.