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

Weighted knowledge distillation for semi-supervised segmentation of maxillary sinus in panoramic X-ray images.

Scientific reports·2026
Same author

High-strength and high-modulus silicon monoxide for high-energy-density and fast-charging lithium-ion batteries.

Nature communications·2026
Same author

Giant Complex Odontoma Occurring Independently Within the Maxillary Sinus.

The Journal of craniofacial surgery·2025
Same author

Implant in the Area of Cemento-osseous Dysplasia: Secondary Infection After Osseointegration and Loading.

The Journal of craniofacial surgery·2024
Same author

Attention-guided jaw bone lesion diagnosis in panoramic radiography using minimal labeling effort.

Scientific reports·2024
Same author

Resolving the non-uniformity in the feature space of age estimation: A deep learning model based on feature clusters of panoramic images.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2024

Related Experiment Video

Updated: Sep 6, 2025

A Postoperative Evaluation Guideline for Computer-Assisted Reconstruction of the Mandible
10:42

A Postoperative Evaluation Guideline for Computer-Assisted Reconstruction of the Mandible

Published on: January 28, 2020

6.6K

Three-Dimensional Postoperative Results Prediction for Orthognathic Surgery through Deep Learning-Based Alignment

Seung Hyun Jeong1, Min Woo Woo1,2, Dong Sun Shin3

  • 1Advanced Mechatronics R&D Group, Korea Institute of Industrial Technology (KITECH), Gyeongsan 38408, Korea.

Journal of Personalized Medicine
|June 24, 2022
PubMed
Summary

Deep neural networks can now predict orthognathic surgery outcomes using 3D skull data, eliminating the need for traditional, time-consuming measurements. This AI-driven approach simplifies predicting postoperative results for dentofacial dysmorphosis.

Keywords:
CT X-raydeep learningdentofacial deformitiesorthognathic surgery

More Related Videos

Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures
09:10

Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures

Published on: August 5, 2021

1.9K
Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
05:49

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Published on: February 23, 2024

978

Related Experiment Videos

Last Updated: Sep 6, 2025

A Postoperative Evaluation Guideline for Computer-Assisted Reconstruction of the Mandible
10:42

A Postoperative Evaluation Guideline for Computer-Assisted Reconstruction of the Mandible

Published on: January 28, 2020

6.6K
Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures
09:10

Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures

Published on: August 5, 2021

1.9K
Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
05:49

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Published on: February 23, 2024

978

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Medicine
  • Craniofacial Surgery

Background:

  • Traditional dentofacial dysmorphosis diagnosis relies on manual measurements (points, planes, angles), which are time-consuming and practitioner-dependent.
  • Predicting postoperative outcomes in orthognathic surgery is crucial for treatment planning and patient satisfaction.

Purpose of the Study:

  • To develop and evaluate a deep neural network model for predicting postoperative results of orthognathic surgery.
  • To assess the model's performance without using traditional reference points, planes, and angles.

Main Methods:

  • Utilized 3D point cloud data from 269 patients' skulls.
  • Employed a two-stage deep learning approach: segmentation network for skull division and alignment network for predicting 3D transformation parameters.
  • Calculated ground truth transformation parameters using iterative closest points (ICP).
  • Compared PointNet, PointNet++, and PointConv as feature extractors and designed a novel loss function.

Main Results:

  • Achieved high accuracy (0.9998), mIoU (0.9994), and DC (0.9998) for segmenting the skull into upper and lower parts.
  • Attained high metrics for segmenting the lower skull into five parts (accuracy: 0.9949, mIoU: 0.9900, DC: 0.9949).
  • Demonstrated low mean absolute errors for key facial structures: maxilla (0.765mm transverse, 1.455mm AP, 1.392mm vertical), mandible (1.069mm transverse, 1.831mm AP, 1.375mm vertical), and chin (1.913mm transverse, 2.340mm AP, 1.257mm vertical).

Conclusions:

  • Deep neural networks can accurately predict postoperative orthognathic surgery results using 3D computed tomography (CT) point cloud data.
  • This AI-based method offers a faster and potentially more objective alternative to traditional diagnostic techniques.
  • The proposed model simplifies the prediction of surgical outcomes, aiding in treatment planning for dentofacial dysmorphosis.