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

Clinical Feasibility and Surgical Outcomes of a 3D-Printed Template-Based PMMA Implant Workflow for Genioplasty.

Journal of clinical medicine·2026
Same author

Correction: Anterolateral thigh free flap using modified turbocharging method: a case report.

Frontiers in surgery·2026
Same author

Advancing nipple volume measurement using Gaussian splatting: Achieving comparable accuracy to current standards.

Journal of plastic, reconstructive & aesthetic surgery : JPRAS·2026
Same author

Iatrogenic lung overinflation resulting in pneumothorax and pneumoperitoneum during oxygen therapy after general anesthesia: A case report.

Medicine·2025
Same author

The Effect of a Collagen-Elastin Implantation on Infraorbital Hallowing in Lower Lid Surgery for Aging Patients.

The Journal of craniofacial surgery·2025
Same author

Outcomes of Reconstructing Lower Lid Defects Using Midface Lifting and Full-Thickness Skin Grafts.

The Journal of craniofacial surgery·2025

Related Experiment Video

Updated: Jul 9, 2025

Classical Short-Delay Eyeblink Conditioning in One-Year-Old Children
07:36

Classical Short-Delay Eyeblink Conditioning in One-Year-Old Children

Published on: September 1, 2018

23.8K

Introduction of Deep Learning-Based Infrared Image Analysis to Marginal Reflex Distance1 Measurement Method to

Bokeun Song1,2, Hyeokjae Kwon1,3, Sunje Kim1

  • 1Department of Plastic and Reconstructive Surgery, Chungnam National University Hospital, Daejeon 35015, Republic of Korea.

Journal of Clinical Medicine
|December 9, 2023
PubMed
Summary

A new deep learning method accurately measures eyelid margin position (MRD1) using IR cameras. This AI approach shows strong agreement with existing methods, offering a reliable clinical tool.

Keywords:
blepharoplastydeep learningeye movement measurementsmachine learning

More Related Videos

Assessing Binocular Central Visual Field and Binocular Eye Movements in a Dichoptic Viewing Condition
07:45

Assessing Binocular Central Visual Field and Binocular Eye Movements in a Dichoptic Viewing Condition

Published on: July 21, 2020

4.5K
Using Retinal Imaging to Study Dementia
09:17

Using Retinal Imaging to Study Dementia

Published on: November 6, 2017

21.7K

Related Experiment Videos

Last Updated: Jul 9, 2025

Classical Short-Delay Eyeblink Conditioning in One-Year-Old Children
07:36

Classical Short-Delay Eyeblink Conditioning in One-Year-Old Children

Published on: September 1, 2018

23.8K
Assessing Binocular Central Visual Field and Binocular Eye Movements in a Dichoptic Viewing Condition
07:45

Assessing Binocular Central Visual Field and Binocular Eye Movements in a Dichoptic Viewing Condition

Published on: July 21, 2020

4.5K
Using Retinal Imaging to Study Dementia
09:17

Using Retinal Imaging to Study Dementia

Published on: November 6, 2017

21.7K

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Marginal reflex distance 1 (MRD1) is a key clinical metric for eyelid margin position relative to the cornea.
  • Manual MRD1 measurement is time-consuming and prone to inter-observer variability.
  • Advancements in AI offer potential for automated and accurate MRD1 assessment.

Purpose of the Study:

  • To introduce and evaluate novel deep learning-based methods for automated MRD1 measurement.
  • To compare the accuracy and agreement of AI-driven MRD1 measurements with traditional methods.

Main Methods:

  • A prospective observational study involving 154 eyes from 77 patients.
  • Development of deep learning algorithms for simultaneous image capture and MRD1 computation.
  • Comparison of measurements from manual penlight, deep learning, RGB ImageJ, and IR ImageJ methods.

Main Results:

  • The deep learning (DL) method showed the strongest agreement with the IR ImageJ method (correlation coefficient 0.822, p < 0.01).
  • Bland-Altman analysis revealed the smallest mean difference (0.0611) and limits of agreement (2.5162) between MRD1_DL and MRD1_IR ImageJ.
  • Mean MRD1 values were 2.64±1.04 mm (manual), 2.85±1.07 mm (DL), 2.78±1.08 mm (RGB), and 3.07±0.95 mm (IR).

Conclusions:

  • A novel MRD1 measurement method utilizing IR cameras and deep learning is statistically significant.
  • This AI-powered approach demonstrates high accuracy and reliability, comparable to established methods.
  • The proposed method is suitable for clinical application, potentially improving efficiency and consistency in MRD1 assessment.