Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Vision

Vision

Vision is the result of light being detected and transduced into neural signals by the retina of the eye. This information is then further analyzed and interpreted by the brain. First, light enters the front of the eye and is focused by the cornea and lens onto the retina—a thin sheet of neural tissue lining the back of the eye. Because of refraction through the convex lens of the eye, images are projected onto the retina upside-down and reversed.

You might also read

Related Articles

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

Sort by

Same author

Neuroretinal Layer Thinning on OCT Imaging and Hemoglobin A1c in Youth With Type 1 Diabetes.

JAMA ophthalmology·2026

Same author

Artificial intelligence-based retinal imaging for brain health assessment: a scoping review.

The Lancet. Digital health·2026

Same author

Multi-scale Radiomic Fingerprint: Quantifying Spatial Changes in Biology.

Journal of imaging informatics in medicine·2026

Same author

American Radium Society (ARS) Appropriate Use Criteria (AUC) for Low-Dose Radiotherapy for Treatment of Osteoarthritis.

American journal of clinical oncology·2026

Same author

Centering the marginalized: AI-driven strategies for advancing health equity in rare disease care.

Patterns (New York, N.Y.)·2026

Same author

Global approval and certification of ophthalmic AI devices: A comparative regulatory perspective.

Asia-Pacific journal of ophthalmology (Philadelphia, Pa.)·2026

Search research articles

Related Experiment Video

Updated: Jul 8, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

Vision transformers: The next frontier for deep learning-based ophthalmic image analysis.

Jo-Hsuan Wu¹, Neslihan D Koseoglu², Craig Jones^2,3,4

¹Department of Ophthalmology, Shiley Eye Institute and Viterbi Family, University of California, San Diego, La Jolla, CA, USA.

Saudi Journal of Ophthalmology : Official Journal of the Saudi Ophthalmological Society

|December 11, 2023

Summary

Vision transformers (ViTs) show strong performance in ophthalmic image analysis for diabetic retinopathy and glaucoma detection. While potentially superior to convolutional neural networks (CNNs), their widespread adoption faces challenges due to higher data requirements.

Keywords:

Color fundus photographs deep learning ophthalmic image analysis optical coherence tomography vision transformers

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Related Experiment Videos

Last Updated: Jul 8, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Area of Science:

Ophthalmology
Medical Imaging
Artificial Intelligence
Deep Learning

Background:

Deep learning, particularly convolutional neural networks (CNNs), is the standard for ophthalmic image analysis.
Vision transformers (ViTs) are emerging as a powerful alternative, potentially surpassing CNN capabilities.
The comparative performance and adoption of ViTs in ophthalmology require focused investigation.

Purpose of the Study:

To review studies applying ViT-based models to ophthalmic image analysis.
To assess the performance of ViTs in tasks like diabetic retinopathy grading and glaucoma detection.
To compare ViT performance against traditional CNN approaches in this domain.

Main Methods:

Systematic literature search of PubMed and Google Scholar databases.
Inclusion of original investigations published up to March 2023.
Focus on studies utilizing ViT models for color fundus photographs and optical coherence tomography (OCT) image analysis.

Main Results:

ViT-based models demonstrated robust performance in grading diabetic retinopathy and detecting glaucoma.
Some studies indicated ViT superiority over CNNs in specific ophthalmic image analysis contexts.
ViTs generally require more extensive training data compared to CNNs, posing a potential adoption barrier.

Conclusions:

ViT models show significant promise for advancing ophthalmic image analysis, offering competitive or superior performance.
The clinical adoption of ViTs may be moderated by their data-intensive training requirements.
Further research is needed to fully understand the long-term impact and integration of ViTs in ophthalmic diagnostics.