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

Lower Eyelid Fat Pad Transfer and Upper Eyelid Blepharoplasty for Simultaneous Correction of Tear Trough and Sunken Upper Eyelid Deformities.

Aesthetic plastic surgery·2026
Same author

FOSL1-mediated super-enhancer facilitates pathological scarring.

Cell reports·2026
Same author

Adipose precursor cell-derived clusterin promotes homeostasis in subcutaneous adipose tissue.

Stem cell reports·2026
Same author

From Posttraumatic Lipoma to Hemangioma: 2 Foreign Bodies' 4-decade Unnoticed Presence.

Plastic and reconstructive surgery. Global open·2026
Same author

MOF-Ag Nanozyme for <i>Fusobacterium nucleatum</i> Eradication and Enhanced Nanocatalytic Therapy of Colorectal Cancer.

International journal of nanomedicine·2026
Same author

Mitochondrial dynamics in skin health and disease: energy, aging, and therapeutic perspectives.

Burns & trauma·2026

Related Experiment Video

Updated: Jun 29, 2025

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans
10:23

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

Published on: September 8, 2023

2.7K

Automated anatomical landmark detection on 3D facial images using U-NET-based deep learning algorithm.

Yuming Chong1,2, Fengzhou Du1,2, Xuda Ma1,2

  • 1Department of Plastic and Aesthetic Surgery, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China.

Quantitative Imaging in Medicine and Surgery
|March 28, 2024
PubMed
Summary

A novel deep learning algorithm automates facial landmark detection on 3D models, significantly improving the efficiency of 3D facial anthropometry. This advancement addresses the time-consuming manual process, offering accurate results for various patient groups.

Keywords:
3-dimensional imaging (3D imaging)algorithmautomated landmark detectiondeep learning

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
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.5K

Related Experiment Videos

Last Updated: Jun 29, 2025

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans
10:23

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

Published on: September 8, 2023

2.7K
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
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.5K

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Artificial Intelligence

Background:

  • 3D photogrammetry is increasingly popular in surgery for facial anthropometry.
  • Manual landmark localization in 3D photogrammetry is time-consuming.
  • Automated methods are needed to improve the efficiency of 3D facial analysis.

Purpose of the Study:

  • To develop a deep learning algorithm for automated anatomical landmark detection on 3D facial models.
  • To overcome the limitations of manual landmark localization in 3D photogrammetry.
  • To enhance the accuracy and efficiency of 3D facial image analysis.

Main Methods:

  • A U-NET-based deep learning algorithm was developed, stacking two U-NETs.
  • The algorithm utilized 3x3 convolution kernels and ReLU activation functions.
  • 200 3D images from healthy, acromegaly, and localized scleroderma patients were used for training and testing.

Main Results:

  • The algorithm achieved an average Normalized Mean Error (NME) of 1.4 mm in healthy cases.
  • Percentage of Correct Key Points (PCK) reached 90% at a 2 mm threshold in healthy cases.
  • Average NME was 2.8 mm for acromegaly and 2.2 mm for localized scleroderma patients.

Conclusions:

  • A deep learning algorithm for automated facial landmark detection on 3D images was successfully developed.
  • The algorithm demonstrated accurate landmark detection across three distinct participant groups.
  • This innovation improves the efficiency and accuracy of 3D facial image analysis in clinical settings.