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

Deciphering the Therapeutic and Preventive Potential of Dietary Tannins in Osteosarcoma: A Multi-Omics Approach Targeting TGFA and Immune Microenvironment Remodeling.

Food science & nutrition·2026
Same author

Development and validation of a simplified dynamic nomogram for preoperative prediction of microvascular invasion in hepatocellular carcinoma.

European journal of gastroenterology & hepatology·2026
Same author

Associations of genetic and non-genetic cardiovascular health metrics with coronary artery disease incidence in cancer survivors.

Scientific reports·2026
Same author

Light Regulation of Anthocyanin Biosynthesis in Plants: From Mechanisms to Applications.

Plant, cell & environment·2026
Same author

Chromosome-level genome assembly of the small-sized Taihang donkey (Equus asinus).

Scientific data·2026
Same author

Letter by Liu and Yao Regarding Article, "Phenotypic Selectivity of Artificial Intelligence-Enhanced Electrocardiography in Cardiovascular Diagnosis and Risk Prediction".

Circulation·2026

Related Experiment Video

Updated: Sep 2, 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

[Infrared Imaging Meibomian Gland Segmentation System Based on Deep Learning].

Hetong Zhang1,2, Kang Yao1,2, Shangshang Ding1,2

  • 1University of Science and Technology of China, Hefei, 230000.

Zhongguo Yi Liao Qi Xie Za Zhi = Chinese Journal of Medical Instrumentation
|August 5, 2022
PubMed
Summary

A new Mobile-U-Net method enhances meibomian gland images for better dry eye diagnosis. This AI approach improves segmentation accuracy, aiding ophthalmologists in recognizing meibomian gland conditions.

Keywords:
U-Netimage enhancementimage segmentationmeibomian glandophthalmology department

More Related Videos

Intense Pulsed Light for the Treatment of Dry Eye Owing to Meibomian Gland Dysfunction
05:00

Intense Pulsed Light for the Treatment of Dry Eye Owing to Meibomian Gland Dysfunction

Published on: April 1, 2019

15.1K
Induction of Ocular Surface Inflammation and Collection of Involved Tissues
06:38

Induction of Ocular Surface Inflammation and Collection of Involved Tissues

Published on: August 4, 2022

2.4K

Related Experiment Videos

Last Updated: Sep 2, 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
Intense Pulsed Light for the Treatment of Dry Eye Owing to Meibomian Gland Dysfunction
05:00

Intense Pulsed Light for the Treatment of Dry Eye Owing to Meibomian Gland Dysfunction

Published on: April 1, 2019

15.1K
Induction of Ocular Surface Inflammation and Collection of Involved Tissues
06:38

Induction of Ocular Surface Inflammation and Collection of Involved Tissues

Published on: August 4, 2022

2.4K

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Dry eye disease diagnosis relies heavily on assessing meibomian gland (MG) structure and function.
  • Current diagnostic tools may lack the precision needed for early or subtle MG abnormalities.
  • Improved imaging techniques are crucial for accurate dry eye assessment.

Purpose of the Study:

  • To develop an automated method for meibomian gland image segmentation and enhancement.
  • To improve the accuracy of dry eye diagnosis by enhancing the visualization of MG structures.
  • To create a tool that assists ophthalmologists in recognizing meibomian gland conditions.

Main Methods:

  • A Mobile-U-Net deep learning network was employed, utilizing MobileNet for the encoder part of U-Net.
  • Feature extraction and fusion techniques were applied within the decoder to guide image segmentation.
  • A large dataset of MG images was collected for training and validation of the semantic segmentation network.
  • Image clarity evaluation indices were used to assess the enhancement effect.

Main Results:

  • The proposed method achieved a stable similarity coefficient of 92.71% for meibomian gland segmentation.
  • The image clarity index demonstrated superior performance compared to existing dry eye detection instruments.
  • The segmentation and enhancement process effectively highlighted meibomian gland regions for diagnostic purposes.

Conclusions:

  • The Mobile-U-Net based method provides accurate segmentation and effective enhancement of meibomian gland images.
  • This AI-driven approach shows significant potential to assist clinicians in diagnosing dry eye disease.
  • The developed technique offers a promising advancement over current instruments for meibomian gland assessment.