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

Hallmark-guided subtypes of hepatocellular carcinoma for the identification of immune-related gene classifiers in the prediction of prognosis, treatment efficacy, and drug candidates.

Frontiers in immunology·2022
Same author

Preparing Sr-containing nano-structures on micro-structured titanium alloy surface fabricated by additively manufacturing to enhance the anti-inflammation and osteogenesis.

Colloids and surfaces. B, Biointerfaces·2022
Same author

Intraoperative Optical Coherence Tomography in Idiopathic Macular Epiretinal Membrane Surgery.

International journal of general medicine·2022
Same author

Specific gut microbiota alterations in essential tremor and its difference from Parkinson's disease.

NPJ Parkinson's disease·2022
Same author

Microplastics in personal care products: Exploring public intention of usage by extending the theory of planned behaviour.

The Science of the total environment·2022
Same author

Inhibition of Dyrk1A Attenuates LPS-Induced Neuroinflammation via the TLR4/NF-κB P65 Signaling Pathway.

Inflammation·2022

Related Experiment Video

Updated: Jul 9, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

406

Automatic segmentation of mandibular canal using transformer based neural networks.

Jinxuan Lv1, Lang Zhang1, Jiajie Xu1

  • 1School of Pharmacy and Bioengineering, Chongqing University of Technology, Chongqing, China.

Frontiers in Bioengineering and Biotechnology
|December 4, 2023
PubMed
Summary

A new automated method accurately segments the mandibular canal for dental surgery. This approach improves precision by focusing on connectivity and fine details, enhancing surgical success rates and patient safety.

Keywords:
CBCTfeature fusionmandibular canalsegmentationtransformer

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

2.8K
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

867

Related Experiment Videos

Last Updated: Jul 9, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

406
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

2.8K
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

867

Area of Science:

  • Medical Imaging
  • Computer-Aided Surgery
  • Biomedical Engineering

Background:

  • Accurate 3D localization of the mandibular canal is critical for successful digitally-assisted dental surgeries.
  • Damage to the mandibular canal during surgery can lead to severe patient complications like pain, numbness, or facial paralysis.
  • Existing segmentation methods struggle with sample imbalance and indistinct boundaries, compromising accuracy.

Purpose of the Study:

  • To develop a fast, stable, and highly precise fully automated segmentation method for the mandibular canal.
  • To overcome challenges of sample imbalance and vague boundaries in current segmentation techniques.
  • To enhance the success rate of dental surgical procedures through improved mandibular canal segmentation.

Main Methods:

  • Utilized a Transformer architecture combined with cl-Dice loss to focus on mandibular canal connectivity.
  • Introduced pixel-level feature fusion to enhance sensitivity to fine structural details.
  • Employed mandibular foramen localization for isolating the maximally connected domain and contrast enhancement for pre-processing.

Main Results:

  • Achieved a Dice score of 0.844, click score of 0.961, IoU of 0.731, and HD95 of 2.947 mm on a public dataset.
  • Demonstrated superior performance metrics compared to existing methods.
  • Validated the efficacy and state-of-the-art performance of the proposed automated segmentation approach.

Conclusions:

  • The proposed automated segmentation approach effectively addresses challenges in mandibular canal segmentation.
  • The method significantly enhances precision and accuracy in identifying the mandibular canal.
  • This advancement holds potential for improving the safety and success of digitally-assisted dental surgeries.