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

Glutathione-related redox imbalance and cognitive impairment in drug-naïve, first-episode schizophrenia: a focus on GSSG.

Schizophrenia (Heidelberg, Germany)·2026
Same author

Dynamic changes in In vitro rumen fermentation, nutrient degradation, and microbial communities of fermentation inoculant-treated licorice stem and leaf silage under different dry matter contents.

PloS one·2026
Same author

Effectiveness of the dual teachers-three rings-four dimensions teaching model in cultivating nursing students' comprehensive competence: A quasi-experimental study.

Nurse education today·2026
Same author

The Impact of Localized Muscle Fatigue on Multi-Joint Biomechanical Strategies During Stair Ascent.

Life (Basel, Switzerland)·2026
Same author

Association of anhedonia with brain-derived neurotrophic factor and oxidative stress in bipolar disorder.

BMC psychiatry·2026
Same author

Risk factors for severe <i>Chlamydia pneumoniae</i> pneumonia in children: a retrospective case-control study.

Frontiers in pediatrics·2026

Related Experiment Video

Updated: May 10, 2025

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

2.3K

Tooth segmentation on multimodal images using adapted segment anything model.

Peijuan Wang1,2, Hanjie Gu1,2, Yuliang Sun3

  • 1College of Information Science and Technology, Zhejiang Shuren University, Hangzhou, 310015, China.

Scientific Reports
|April 22, 2025
PubMed
Summary

A new method, Tooth-ASAM, adapts the Segment Anything Model (SAM) for precise tooth segmentation. This advanced technique improves digital dentistry workflows for orthodontics and surgery.

Keywords:
DentistryMultimodal imagesSegment Anything ModelTooth segmentation

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

2.6K
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

1.7K

Related Experiment Videos

Last Updated: May 10, 2025

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

2.3K
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

2.6K
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

1.7K

Area of Science:

  • Dentistry
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Increasing patient numbers and digital transformation in dentistry necessitate accurate tooth segmentation for various applications.
  • Current methods may lack precision for complex digital dental workflows like orthodontics, implant surgery, and prosthodontics.

Purpose of the Study:

  • To adapt the Segment Anything Model (SAM) for high-performance tooth segmentation.
  • To introduce a novel method, Tooth-ASAM, for precise segmentation of teeth from multimodal dental images.

Main Methods:

  • Developed an adapter-based image encoder and mask decoder to tailor SAM for tooth segmentation.
  • Evaluated the Tooth-ASAM method on diverse datasets including Cone Beam Computed Tomography (CBCT), panoramic X-rays, and micro-camera images.

Main Results:

  • Tooth-ASAM demonstrated remarkable performance across all four evaluated datasets, outperforming state-of-the-art methods.
  • Achieved excellent results in key segmentation metrics such as Dice coefficient, IoU, HD95, and ASSD.
  • Delivered perceptually more accurate segmentation results compared to existing techniques.

Conclusions:

  • Precise tooth segmentation is achievable using SAM with an effective adaptation training strategy.
  • The Tooth-ASAM method shows significant potential for clinical applications in digital dentistry, including orthodontics, oral implant surgery, and prosthodontics.