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

Ecosystem functions and network complexity do not increase linearly with restoration levels on China's loess plateau.

Journal of environmental management·2026
Same author

Augmented Reality Navigation-Assisted Laparoscopic Hepatectomy: A Retrospective Comparison of Anatomical and Non-anatomical Resection.

Clinical Medicine Insights. Oncology·2026
Same author

Correspondence-free local-to-global liver deformation correction via implicit neural representation and biomechanical model.

International journal of computer assisted radiology and surgery·2026
Same author

Association of Postpartum Depression With Phenotypic Biological Aging and Aging-Related Diseases in Midlife Women.

The journal of obstetrics and gynaecology research·2026
Same author

Liver point cloud registration via multi-feature fusion and hyperbolic embedding for augmented reality surgical navigation.

Computer methods and programs in biomedicine·2026
Same author

Novel Psychiatric Disorders Following Mild Traumatic Brain Injury in the Second Year of the Adolescent Brain Cognitive Development Study.

Journal of neurotrauma·2026

Related Experiment Video

Updated: Sep 8, 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

2.9K

Real-time corneal image segmentation for cataract surgery based on detection framework.

Xueyi Shi1, Dexun Zhang1, Shenwen Liang2

  • 1School of Life and Environmental Sciences, Guilin University of Electronic Technology, Guilin, China.

International Journal of Computer Assisted Radiology and Surgery
|September 5, 2025
PubMed
Summary
This summary is machine-generated.

EllipseNet offers fast and accurate real-time corneal segmentation for cataract surgery, significantly reducing the annotation effort required for deep learning models. This innovation improves clinical applicability.

Keywords:
Anchor-freeCataract surgeryCorneal segmentationDeep learningObject detection

More Related Videos

Author Spotlight: Unraveling the Molecular Mechanisms in PCO and Fibrosis Following Cataract Surgery
05:19

Author Spotlight: Unraveling the Molecular Mechanisms in PCO and Fibrosis Following Cataract Surgery

Published on: December 1, 2023

1.2K
Full-Field Optical Coherence Microscopy for Histology-Like Analysis of Stromal Features in Corneal Grafts
07:51

Full-Field Optical Coherence Microscopy for Histology-Like Analysis of Stromal Features in Corneal Grafts

Published on: October 21, 2022

1.7K

Related Experiment Videos

Last Updated: Sep 8, 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

2.9K
Author Spotlight: Unraveling the Molecular Mechanisms in PCO and Fibrosis Following Cataract Surgery
05:19

Author Spotlight: Unraveling the Molecular Mechanisms in PCO and Fibrosis Following Cataract Surgery

Published on: December 1, 2023

1.2K
Full-Field Optical Coherence Microscopy for Histology-Like Analysis of Stromal Features in Corneal Grafts
07:51

Full-Field Optical Coherence Microscopy for Histology-Like Analysis of Stromal Features in Corneal Grafts

Published on: October 21, 2022

1.7K

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Computer Vision

Background:

  • Cataract surgery is a common global procedure.
  • Accurate, real-time segmentation of the cornea and surgical instruments is crucial for intraoperative guidance and surgical education.
  • Current deep learning segmentation methods often require time-consuming pixel-level annotations, hindering practical use.

Purpose of the Study:

  • To introduce EllipseNet, an efficient framework for real-time corneal segmentation in cataract surgery.
  • To develop a method that reduces the annotation workload compared to traditional pixel-level annotation techniques.
  • To enable faster and more precise corneal segmentation for clinical applications.

Main Methods:

  • Developed EllipseNet, an anchor-free framework using ellipse-based modeling for corneal segmentation.
  • Utilized the Hourglass network for feature extraction.
  • Employed simple rectangular bounding box annotations, enabling autonomous inference of elliptical parameters for precise corneal shape matching.

Main Results:

  • Achieved real-time performance, segmenting images within 42 ms.
  • Attained a high Dice accuracy of 95.81%.
  • Demonstrated segmentation speeds nearly three times faster than state-of-the-art models while maintaining comparable accuracy.

Conclusions:

  • EllipseNet provides rapid, accurate, and real-time corneal segmentation, significantly decreasing annotation workload.
  • The framework simplifies the segmentation pipeline, thereby lowering the barrier for clinical adoption.
  • Publicly available source code facilitates further research and development.