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

Depth Perception and Spatial Vision

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

Predicting worsening visual field via masked dual stage attention recurrent neural network.

Scientific reports·2026

Same author

Predicting 10-Year Diabetes Risk Through Physiological Acceleration: A Longitudinal Deep Learning Ensemble Approach.

Diagnostics (Basel, Switzerland)·2026

Same author

Tegoprazan and the risk of end-stage kidney disease progression: a nationwide Korean study.

Kidney research and clinical practice·2026

Same author

Deep learning-based prediction of 24-2 visual field from fundus photographs in glaucoma.

Graefe's archive for clinical and experimental ophthalmology = Albrecht von Graefes Archiv fur klinische und experimentelle Ophthalmologie·2026

Same author

A novel disposition index without insulin is an earlier and sensitive predictor of type 2 diabetes than current diagnostic criteria.

Diabetes research and clinical practice·2026

Same author

Effects of axial malrotation on posterior tibial slope measurement: a digitally reconstructed radiograph study enabling automated quality assessment.

Knee surgery & related research·2026

Search research articles

Related Experiment Video

Updated: Dec 10, 2025

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

Prediction of visual field from swept-source optical coherence tomography using deep learning algorithms.

Keunheung Park^1,2, Jinmi Kim³, Sangyoon Kim⁴

¹Department of Ophthalmology, Pusan National University College of Medicine, Busan, South Korea.

Graefe'S Archive for Clinical and Experimental Ophthalmology = Albrecht Von Graefes Archiv Fur Klinische Und Experimentelle Ophthalmologie

|August 27, 2020

Summary

Deep learning models accurately predict visual fields (VF) from OCT scans. Inception-ResNet-v2 demonstrated superior performance, offering a potential alternative for patients unable to complete traditional VF testing.

Keywords:

Deep learning Inception Swept-source optical coherence tomography Visual field

More Related Videos

Multimodal Volumetric Retinal Imaging by Oblique Scanning Laser Ophthalmoscopy oSLO and Optical Coherence Tomography OCT

Multimodal Volumetric Retinal Imaging by Oblique Scanning Laser Ophthalmoscopy oSLO and Optical Coherence Tomography OCT

Published on: August 4, 2018

Using Optical Coherence Tomography and Optokinetic Response As Structural and Functional Visual System Readouts in Mice and Rats

Using Optical Coherence Tomography and Optokinetic Response As Structural and Functional Visual System Readouts in Mice and Rats

Published on: January 10, 2019

Related Experiment Videos

Last Updated: Dec 10, 2025

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

Multimodal Volumetric Retinal Imaging by Oblique Scanning Laser Ophthalmoscopy oSLO and Optical Coherence Tomography OCT

Multimodal Volumetric Retinal Imaging by Oblique Scanning Laser Ophthalmoscopy oSLO and Optical Coherence Tomography OCT

Published on: August 4, 2018

Using Optical Coherence Tomography and Optokinetic Response As Structural and Functional Visual System Readouts in Mice and Rats

Using Optical Coherence Tomography and Optokinetic Response As Structural and Functional Visual System Readouts in Mice and Rats

Published on: January 10, 2019

Area of Science:

Ophthalmology
Medical Imaging
Artificial Intelligence

Background:

Visual field (VF) testing is crucial for diagnosing and monitoring glaucoma.
Wide-angle swept-source optical coherence tomography (SS-OCT) provides detailed retinal imaging.
Predicting VF from SS-OCT could offer an alternative for patients unable to perform standard VF tests.

Purpose of the Study:

To develop and evaluate deep learning models for predicting visual fields (VF) using SS-OCT data.
To compare the performance of three Google Inception architectures (Inception-ResNet-v2, Inception-v3, Inception-v4) for VF prediction.
To assess the impact of glaucoma severity and specific retinal sectors on prediction accuracy.

Main Methods:

Three deep learning models based on Inception-ResNet-v2, Inception-v3, and Inception-v4 architectures were trained.
Models predicted 24-2 VF from macular ganglion cell-inner plexiform layer and peripapillary retinal nerve fibre layer maps from SS-OCT.
Prediction performance was quantified using root mean square error (RMSE) and compared across models, glaucoma severities, and Garway-Heath sectors.

Main Results:

Inception-ResNet-v2 achieved the lowest global prediction error (RMSE) of 4.44 ± 2.09 dB, significantly outperforming Inception-v3 and Inception-v4 (P < 0.001).
Prediction error increased significantly with glaucoma progression, reaching up to 7.79 dB for Inception-v4.
The nasal sector showed the lowest prediction error, followed by the superotemporal sector.

Conclusions:

The Inception-ResNet-v2 deep learning model demonstrated the best performance in predicting visual fields from SS-OCT data.
Prediction accuracy is influenced by glaucoma severity, with higher errors in advanced stages.
This AI-driven approach holds promise for clinical applications, especially for patients who cannot undergo conventional visual field testing.