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

Erbium-doped fiber polarizer via femtosecond laser inscription for ultrafast fiber lasers.

Optics letters·2026
Same author

Immunological characteristics of children with autism spectrum disorder and comorbid atopic dermatitis.

Frontiers in pediatrics·2026
Same author

Aminopeptides ameliorate long COVID symptoms in immunocompromised rheumatic patients through immune reconstitution.

International immunopharmacology·2026
Same author

Proteoliposomes containing ATPase as microreactors to mimic microbial metabolism for bioenergy synthesis.

Journal of colloid and interface science·2026
Same author

Deep-learning-based beam position estimation with a photon-counting camera in free-space optical communications.

Optics express·2025
Same author

Deep learning-based identification of periodontal infrabony defects with regenerative potential: A multicenter retrospective study.

Journal of periodontology·2025

Related Experiment Video

Updated: Dec 25, 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

3.3K

Optic Disc and Cup Image Segmentation Utilizing Contour-Based Transformation and Sequence Labeling Networks.

Zhe Xie1,2, Tonghui Ling1, Yuanyuan Yang1

  • 1Laboratory for Medical Imaging Informatics, Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai, 200083, China.

Journal of Medical Systems
|March 21, 2020
PubMed
Summary

This study introduces a novel coarse-to-fine approach for segmenting optic disc and optic cup, improving glaucoma diagnosis. The method achieves state-of-the-art results, outperforming ophthalmologists in accuracy.

Keywords:
Convolutional neural networksFundus imageGlaucoma screeningOptic disc segmentationSequence labelingViterbi decoding

More Related Videos

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.5K
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

43.3K

Related Experiment Videos

Last Updated: Dec 25, 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

3.3K
Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.5K
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

43.3K

Area of Science:

  • Ophthalmology and Medical Imaging
  • Computer Vision and Machine Learning

Background:

  • Accurate optic disc (OD) and optic cup (OC) segmentation are crucial for diagnosing optic nerve head abnormalities like glaucoma.
  • Current pixel classification methods struggle with spatial relations and imbalanced data, leading to noise and biased models.

Purpose of the Study:

  • To develop an improved method for OD and OC segmentation addressing limitations of existing approaches.
  • To enhance the accuracy of glaucoma screening through precise optic nerve head analysis.

Main Methods:

  • A coarse-to-fine segmentation strategy using U-Net for initial boundary detection.
  • A novel SU-Net combined with the Viterbi algorithm for sequence labeling-based boundary decoding.
  • Geometric parameter-based data augmentation to improve model generalization and reduce overfitting.

Main Results:

  • Achieved state-of-the-art performance on two datasets for both OD and OC segmentation.
  • Outperformed ophthalmologists in agreement on the MESSIDOR dataset for OD and OC segmentation.
  • Demonstrated superior glaucoma screening performance with the lowest cup-to-disc ratio (CDR) error and highest area under the ROC curve (AUC) on the Drishti-GS dataset.

Conclusions:

  • The proposed coarse-to-fine segmentation method effectively models spatial relations and handles data imbalance for accurate OD and OC segmentation.
  • This approach offers a significant advancement in automated glaucoma screening and diagnosis.