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 Experiment Videos

Deep Learning and Radiomics Assessment for Highly Myopic Glaucoma Detection Based on Fundus Photography.

Man Luo1,2,3, Wenjing Han4, Lingjing Hu4

  • 1Center on Frontiers of Computing Studies, School of Computer Science, Institute for Artificial Intelligence, Peking University, Beijing, China.

Ophthalmology Science
|July 12, 2026
PubMed
Summary

Related Concept Videos

Glaucoma: Overview01:25

Glaucoma: Overview

Glaucoma is an eye condition characterized by increased intraocular pressure that damages the retina and optic nerve, leading to irreversible blindness if left untreated. The human eye has various components, including the cornea, iris, pupil, lens, and optic nerve. Aqueous humor is secreted by the epithelium of the ciliary body in the posterior chamber and flows through the trabecular meshwork and canal of Schlemm, maintaining normal intraocular pressure. The trabecular meshwork and the canal...

You might also read

Related Articles

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

Sort by
Same author

Natural History and Influence on Long-term Outcomes of Isolated Type II Endoleak after Endovascular Aneurysm Repair: A 10-year Experience at a Single Center.

Reviews in cardiovascular medicine·2022
Same author

Reply to Editor.

Annals of diagnostic pathology·2022
Same author

Microbial transformations by sulfur bacteria can recover value from phosphogypsum: A global problem and a possible solution.

Biotechnology advances·2022
Same author

AAV-delivered suppressor tRNA overcomes a nonsense mutation in mice.

Nature·2022
Same author

Surface plasmon enhancement in different spatial distributions of nanowires and two-dimensional materials.

Physical chemistry chemical physics : PCCP·2022
Same author

Zero-Field Splitting Calculations by Multiconfiguration Pair-Density Functional Theory.

Journal of chemical theory and computation·2022

This study integrated radiomics and deep learning to identify unique features in fundus images for diagnosing highly myopic glaucoma (HMG). The developed models demonstrated high accuracy in distinguishing HMG from high myopia and primary open-angle glaucoma.

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Glaucoma in highly myopic eyes presents diagnostic challenges.
  • Accurate differentiation of highly myopic glaucoma (HMG) from other conditions is crucial for effective management.
  • Current diagnostic methods may not fully capture the subtle anatomical changes in HMG.

Purpose of the Study:

  • To investigate spatially distinctive features in fundus photographs of highly myopic glaucoma (HMG) using radiomics and deep learning.
  • To develop a quantitative classification model for HMG based on integrated imaging biomarkers.
  • To correlate identified radiomic features with anatomical characteristics in the optic nerve region.

Main Methods:

  • Utilized a dataset of 2000 fundus images for semi-automated optic disc segmentation with U-Net.
Keywords:
Deep learningFundus photographyHighly myopic glaucomaRadiomics

Related Experiment Videos

  • Extracted 414 radiomics features from 5 regions of interest around the optic disc.
  • Trained and validated classification models using random forest and support vector machine algorithms, comparing radiomics, clinical, and combined approaches.

    • Main Results:

    • The radiomics model achieved high accuracy in detecting HMG versus high myopia (0.97) and HMG versus primary open-angle glaucoma (0.85) in external validation.
    • Top radiomics features, including intensity and textural features, showed strong diagnostic capability (AUROC up to 0.984) and were independent of glaucoma progression.
    • The developed models outperformed traditional clinical models in differentiating HMG.

    Conclusions:

    • The integration of U-Net and radiomics effectively delineates spatial biomarkers for HMG.
    • A quantitative classification model correlated with anatomical features was established for HMG diagnosis.
    • This approach offers a promising tool for improving the diagnosis of highly myopic glaucoma.