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

AI-Powered Mobile App for Nuclear Cataract Detection.

Sensors (Basel, Switzerland)·2025
Same author

Biometric Technologies Based on Optical Coherence Tomography.

Sensors (Basel, Switzerland)·2023
Same author

Segmentation of Preretinal Space in Optical Coherence Tomography Images Using Deep Neural Networks.

Sensors (Basel, Switzerland)·2021
See all related articles

Related Experiment Video

Updated: Aug 8, 2025

Retinal Vascular Reactivity as Assessed by Optical Coherence Tomography Angiography
07:23

Retinal Vascular Reactivity as Assessed by Optical Coherence Tomography Angiography

Published on: March 26, 2020

7.6K

Neural Networks Application for Accurate Retina Vessel Segmentation from OCT Fundus Reconstruction.

Tomasz Marciniak1, Agnieszka Stankiewicz1, Przemyslaw Zaradzki1

  • 1Division of Electronic Systems and Signal Processing, Institute of Automatic Control and Robotics, Poznan University of Technology, 60-965 Poznan, Poland.

Sensors (Basel, Switzerland)
|February 28, 2023
PubMed
Summary

This study explores using neural networks for retinal vessel segmentation from 3D OCT scans. Researchers achieved high accuracy (98%) in segmenting retinal blood vessels, even from lower-quality OCT-derived images.

Keywords:
UNetbiometricsconvolutional neural networksfundus reconstructionoptical coherence tomographyretina vessel segmentation

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

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

Published on: November 30, 2022

2.8K
Quantification of Vascular Parameters in Whole Mount Retinas of Mice with Non-Proliferative and Proliferative Retinopathies
12:28

Quantification of Vascular Parameters in Whole Mount Retinas of Mice with Non-Proliferative and Proliferative Retinopathies

Published on: March 12, 2022

3.7K

Related Experiment Videos

Last Updated: Aug 8, 2025

Retinal Vascular Reactivity as Assessed by Optical Coherence Tomography Angiography
07:23

Retinal Vascular Reactivity as Assessed by Optical Coherence Tomography Angiography

Published on: March 26, 2020

7.6K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

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

Published on: November 30, 2022

2.8K
Quantification of Vascular Parameters in Whole Mount Retinas of Mice with Non-Proliferative and Proliferative Retinopathies
12:28

Quantification of Vascular Parameters in Whole Mount Retinas of Mice with Non-Proliferative and Proliferative Retinopathies

Published on: March 12, 2022

3.7K

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Retinal vessel segmentation is crucial for diagnosing eye diseases.
  • Current methods primarily use color fundus photographs.
  • 3D Optical Coherence Tomography (OCT) offers alternative imaging but presents reconstruction challenges.

Purpose of the Study:

  • To evaluate neural network performance for retinal vessel segmentation using fundus images reconstructed from 3D OCT data.
  • To compare different neural network architectures for this task.
  • To assess the feasibility of OCT-derived fundus images for vessel segmentation.

Main Methods:

  • Five neural network architectures were investigated.
  • Fundus images were reconstructed from 3D OCT B-scans, with three reconstruction variants proposed.
  • Performance was evaluated on a custom dataset of 24 3D OCT scans with manual annotations.
  • A 6-fold cross-validation strategy was employed.

Main Results:

  • High segmentation accuracy, up to 98%, was achieved.
  • Neural networks demonstrated effectiveness in segmenting retinal vessels from OCT-based reconstructions.
  • The quality of fundus image reconstruction significantly impacts segmentation performance.

Conclusions:

  • Neural networks show significant promise for retinal vessel segmentation using OCT-derived fundus images.
  • Proper reconstruction of OCT data is essential for accurate vessel segmentation.
  • This approach offers a potential alternative to traditional fundus photography for retinal imaging analysis.