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 authorSame journalSame Topic

Proto-clinical optoretinography dependence on temporal and spatial resolution.

Biomedical optics express·2026
Same author

Adoption of artificial intelligence in drug review across the lifecycle: Transformation of regulatory decision-making.

Regulatory toxicology and pharmacology : RTP·2026
Same author

Environmental drivers of influenza A and B: causal analysis and forecasting.

BMC public health·2026
Same author

Histology correlated adaptive optics polarisation sensitive optical coherence tomography.

Biomedical optics express·2026
Same author

Validation and application of automated CT analysis to musculoskeletal profiling in MVC occupants.

Traffic injury prevention·2026
Same author

Exploring Spatial Distribution of Intrinsic Oxide Trap by Decoupling Channel Thickness Effects in Amorphous IGZO TFTs.

ACS applied materials & interfaces·2026

Related Experiment Video

Updated: Dec 6, 2025

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

3.2K

Semi-supervised deep learning based 3D analysis of the peripapillary region.

Morgan Heisler1, Mahadev Bhalla2, Julian Lo1

  • 1Simon Fraser University, Department of Engineering Science, 8888 University Drive, Burnaby, BC, V5A 1S6, Canada.

Biomedical Optics Express
|October 5, 2020
PubMed
Summary

This study introduces a novel deep learning method for segmenting optic nerve head structures in OCT scans, improving glaucoma diagnosis by utilizing unlabeled data for enhanced accuracy in analyzing retinal nerve fiber layer and Bruch's membrane opening.

More Related Videos

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

3.4K
Exploring Deep Space - Uncovering the Anatomy of Periventricular Structures to Reveal the Lateral Ventricles of the Human Brain
17:13

Exploring Deep Space - Uncovering the Anatomy of Periventricular Structures to Reveal the Lateral Ventricles of the Human Brain

Published on: October 22, 2017

17.5K

Related Experiment Videos

Last Updated: Dec 6, 2025

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

3.2K
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

3.4K
Exploring Deep Space - Uncovering the Anatomy of Periventricular Structures to Reveal the Lateral Ventricles of the Human Brain
17:13

Exploring Deep Space - Uncovering the Anatomy of Periventricular Structures to Reveal the Lateral Ventricles of the Human Brain

Published on: October 22, 2017

17.5K

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Optical coherence tomography (OCT) is crucial for glaucoma evaluation, primarily via circumpapillary scans.
  • Three-dimensional OCT volumes offer deeper analysis of the optic nerve head (ONH), a key site for initial glaucomatous damage.
  • Automated segmentation of peripapillary layers and Bruch's membrane opening (BMO) in OCT is challenging due to anatomical variations and data requirements.

Purpose of the Study:

  • To evaluate a semi-supervised adversarial deep learning method for segmenting peripapillary retinal layers in OCT B-scans.
  • To leverage unlabeled data to improve segmentation performance.
  • To automatically segment the BMO using a Faster R-CNN architecture for 3D morphometric analysis.

Main Methods:

  • Implemented a semi-supervised adversarial deep learning approach for retinal layer segmentation.
  • Utilized generative adversarial networks (GANs) to incorporate unlabeled OCT data.
  • Employed a Faster R-CNN architecture for automated Bruch's membrane opening (BMO) segmentation.
  • Performed 3D morphometric analysis on control and glaucomatous ONH volumes.

Main Results:

  • The semi-supervised adversarial deep learning method demonstrated improved segmentation performance for peripapillary retinal layers.
  • The use of unlabeled data enhanced the accuracy of OCT-based segmentation.
  • Automated BMO segmentation was successfully achieved using the Faster R-CNN architecture.
  • The developed methods enabled detailed 3D morphometric analysis of the optic nerve head.

Conclusions:

  • Semi-supervised adversarial deep learning effectively segments peripapillary retinal layers in OCT B-scans, utilizing unlabeled data.
  • The integration of GANs and Faster R-CNN offers a robust approach for automated BMO segmentation.
  • The proposed methods show significant potential for clinical utility in the 3D morphometric analysis of glaucomatous optic nerve heads.