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

In vivo evolution of tigecycline resistance in ST540 carbapenem-resistant Acinetobacter baumannii: Mechanisms and global epidemiological perspective.

International journal of antimicrobial agents·2026
Same author

Endogenous Fe-N co-doped biochar for persulfate activation: Synergistic enhancement of persulfate adsorption by porous structure and p-d orbital coupling.

Bioresource technology·2026
Same author

625 mJ, 1 kHz picosecond pulsed laser amplifier based on cascaded zig-zag slabs.

Optics express·2026
Same author

Distribution patterns and ecological networks of pathogenic microorganisms in a tropical urban river: insights from the Mirongo River, Tanzania.

Environmental pollution (Barking, Essex : 1987)·2026
Same author

Comparative between eravacycline and best available therapy in carbapenem-resistant Acinetobacter baumannii HAP/VAP in China: a retrospective real-world multicenter cohort study.

International journal of infectious diseases : IJID : official publication of the International Society for Infectious Diseases·2026
Same author

Environmental Behavior of 2,4,6-Trichlorophenol in the Sediment-Overlying Water System with the Presence of Tubificid Worms.

Toxics·2026

Related Experiment Video

Updated: Jun 14, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

379

ChoroidSeg-ViT: A Transformer Model for Choroid Layer Segmentation Based on a Mixed Attention Feature Enhancement

Zhaolin Lu1, Tao Liu2, Yewen Ni1,3

  • 1The Affiliated Xuzhou Municipal Hospital of Xuzhou Medical University, Xuzhou, Jiangsu, China.

Translational Vision Science & Technology
|September 5, 2024
PubMed
Summary

A novel Vision Transformer model, ChoroidSeg-ViT, precisely segments the choroid layer in optical coherence tomography images, achieving state-of-the-art performance and enabling automated choroidal analysis.

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

2.7K
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

2.3K

Related Experiment Videos

Last Updated: Jun 14, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

379
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

2.7K
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

2.3K

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Accurate segmentation of the choroid layer in optical coherence tomography (OCT) images is crucial for diagnosing and monitoring various eye diseases.
  • Existing segmentation methods may face challenges in precision and automation.

Purpose of the Study:

  • To develop an advanced Vision Transformer (ViT) model, named ChoroidSeg-ViT, for enhanced choroid layer segmentation in OCT images.
  • To improve the precision and automation of choroid layer segmentation using a mixed attention feature enhancement mechanism.

Main Methods:

  • A dataset of 100 OCT B-scan images was utilized, with ground truths meticulously annotated by expert ophthalmologists.
  • An end-to-end ChoroidSeg-ViT model was designed, integrating local-enhanced feature extraction and semantic feature fusion paths.
  • Segmentation performance was evaluated using standard metrics such as mDice, mIoU, and mAcc.

Main Results:

  • ChoroidSeg-ViT demonstrated superior segmentation performance, achieving mDice of 98.31%, mIoU of 96.62%, and mAcc of 98.29%.
  • The proposed model outperformed other deep learning approaches in choroid layer segmentation.
  • Ablation and generalization experiments confirmed the effectiveness of the model's design modules.

Conclusions:

  • A novel Transformer model, ChoroidSeg-ViT, was developed for precise and automatic choroid layer segmentation, achieving state-of-the-art results.
  • The ChoroidSeg-ViT model offers precise and smooth segmentation of choroid layers.
  • This model can serve as a foundation for an automated choroid analysis system, advancing ophthalmological research.