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

Thermoresponsive Nanoparticles Hijack Neutrophils In Vivo to In Situ Construct Biohybrids for Enhanced Cancer and Infection Therapy.

ACS nano·2026
Same author

Image segmentation of track bolts based on improved YOLO model.

Scientific reports·2026
Same author

Programmed oral delivery of peptide therapeutics for multiorgan targeting in metabolic disorders of hyperglycemia and hyperuricemia.

Science advances·2026
Same author

pH/enzyme dual-responsive nanoparticles hitchhike neutrophils to enhance bacteria-induced acute lung infection treatment.

International journal of pharmaceutics·2026
Same author

Physics-guided resampling and asymmetric fusion for ultra-high-frequency bolt-loosening detection.

Scientific reports·2026
Same author

PEGylated Cu-doped WS<sub>2</sub> hybrid nanosheets for targeted multimodal cancer therapy.

Microsystems & nanoengineering·2026

Related Experiment Video

Updated: Jun 15, 2025

A Novel Approach to Monitoring Graft Neovascularization in the Human Gingiva
07:51

A Novel Approach to Monitoring Graft Neovascularization in the Human Gingiva

Published on: January 12, 2019

6.7K

Deep learning based approach: automated gingival inflammation grading model using gingival removal strategy.

Chang Wen1,2, Xueying Bai1, Jiaxin Yang1

  • 1State Key Laboratory of Oral & Maxillofacial Reconstruction and Regeneration, Key Laboratory of Oral Biomedicine Ministry of Education, Hubei Key Laboratory of Stomatology, School & Hospital of Stomatology, Wuhan University, #237 Luoyu Road, Hongshan District, Wuhan, China.

Scientific Reports
|August 26, 2024
PubMed
Summary
This summary is machine-generated.

A new deep learning model accurately assesses gingival inflammation using advanced feature extraction. This AI tool enhances periodontitis diagnosis by precisely grading inflammation severity from images.

Keywords:
Auxiliary diagnosisDeep learningGingival inflammationIntra-oral photo imagePeriodontal disease

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

1.7K
Three-dimensional Inflammatory Human Tissue Equivalents of Gingiva
08:43

Three-dimensional Inflammatory Human Tissue Equivalents of Gingiva

Published on: April 3, 2018

9.8K

Related Experiment Videos

Last Updated: Jun 15, 2025

A Novel Approach to Monitoring Graft Neovascularization in the Human Gingiva
07:51

A Novel Approach to Monitoring Graft Neovascularization in the Human Gingiva

Published on: January 12, 2019

6.7K
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
Three-dimensional Inflammatory Human Tissue Equivalents of Gingiva
08:43

Three-dimensional Inflammatory Human Tissue Equivalents of Gingiva

Published on: April 3, 2018

9.8K

Area of Science:

  • Periodontology and Dental Imaging
  • Artificial Intelligence in Healthcare
  • Computer Vision for Medical Diagnosis

Background:

  • Gingival inflammation grading is crucial for periodontitis assessment.
  • Current methods for evaluating gingival inflammation can be subjective and time-consuming.
  • Objective and automated assessment tools are needed to improve diagnostic accuracy and efficiency.

Purpose of the Study:

  • To develop a deep learning (DL) network for automatic gingival inflammation assessment.
  • To implement a novel feature extraction method for enhanced DL model performance.
  • To evaluate the accuracy and sensitivity of the proposed DL model in identifying and grading gingival inflammation.

Main Methods:

  • Utilized T-distributed Stochastic Neighbor Embedding (t-SNE) for dimensionality reduction.
  • Developed a convolutional neural network (CNN) model based on DenseNet for gingival inflammation identification.
  • Implemented a novel teeth removal algorithm and Grad-CAM++ encoder for computer visual attention analysis.

Main Results:

  • Achieved a mean Intersection over Union (MIoU) of 0.727 ± 0.117 for gingivitis identification.
  • Obtained accuracy rates ranging from 73.68% to 79.22% for five inflammatory degrees.
  • Demonstrated significant increases in attention ratios towards gingival tissue (overall 51.82% to 78.21%) using Grad-CAM++.

Conclusions:

  • The proposed DL model with novel feature extraction offers high accuracy and sensitivity for gingival inflammation assessment.
  • The automated system provides objective grading of gingival inflammation, aiding in periodontitis diagnosis.
  • This AI-driven approach has the potential to improve clinical workflows and patient outcomes in periodontology.