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

Classification of Bones01:18

Classification of Bones

5.1K
The bones of the human skeletal system are of varied shapes, sizes, and functions. They can be classified based on their shape and function into four major classes: long bones, short bones, flat bones, and irregular bones. Some classifications include a fifth type, the sesamoid bones, as a separate class, whereas others categorize them under short bones.
Long and Short Bones
The appendicular skeleton, particularly the upper and lower limbs, is primarily made of long and short bones. The...
5.1K
Classification of Connective Tissues01:30

Classification of Connective Tissues

10.2K
The connective tissues have different properties and functions in the human body. They are broadly categorized into proper, supporting, or fluid connective tissues.
Connective Tissue Proper
Connective tissue proper is the most abundant class of connective tissues. As its name implies, it predominantly connects different tissues in the body. Depending on the cell types, ground substance, viscosity, and fiber types in the ECM, connective tissue proper is further categorized into loose and dense....
10.2K
Assessment of the Mouth01:26

Assessment of the Mouth

141
A thorough mouth assessment, including inspection and palpation of the lips, gums, tongue, tonsils, uvula, and pharynx, is crucial in detecting potential health issues. Diseases ranging from oral cancer to systemic conditions like diabetes could be identified early through careful oral examination. This article provides a detailed guide on conducting a comprehensive mouth assessment.
Mouth Inspection
The inspection begins with visually examining the mouth for symmetry, color, and size.
141
Classification of Epithelial Tissues: Overview01:22

Classification of Epithelial Tissues: Overview

12.8K
Epithelial tissues are classified according to the shape of the cells and the number of cell layers formed. Cell shapes can be squamous (flattened and thin), cuboidal (square-like, as wide as it is tall), or columnar (rectangular, taller than it is wide). Additionally, the nucleus shape helps identify the type of epithelial cells. Squamous cells have flattened disc-shaped nuclei, cuboidal cells have spherical nuclei, and columnar cells have elongated nuclei.
Based on the number of cell layers,...
12.8K
Classification of Epithelial Tissues: Stratified Epithelium01:29

Classification of Epithelial Tissues: Stratified Epithelium

8.8K
Stratified epithelium consists of several stacked layers of cells. They provide the durability to withstand constant physical and chemical attacks. Stratified epithelium is named after the shape of the most apical layer of cells. Stratified squamous epithelium is the most common type found in the human body. In this tissue, the apical cells are squamous, whereas the basal layer contains either columnar or cuboidal cells. The basal cells divide to form new daughter cells, which gradually become...
8.8K
Tooth Anatomy01:21

Tooth Anatomy

374
The human tooth enables us to eat a variety of foods, speak clearly, and even aid in shaping our faces. Teeth are composed of various elements that work together. Here's a detailed look at the anatomy of a human tooth.
The Crown, Neck, and Root
The visible part of the tooth is referred to as the crown. It's covered by enamel, the hardest substance in the human body. The crown is uniquely shaped for each type of tooth, allowing for different functions such as cutting, tearing, or...
374

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Iron-quercetin nanocomplex preconditioning reprograms the mesenchymal stem cell secretome to drive angiogenic, fibroblast and immunoregulatory wound repair.

Regenerative biomaterials·2026
Same author

Prospective feasibility study of a telehealth platform for community-based NCD risk assessment by community health leaders in rural northern Thailand.

SAGE open medicine·2026
Same author

Deep learning versus general dentists: a clinical evaluation of caries diagnostic accuracy on bitewing radiographs.

BMC oral health·2026
Same author

AI-driven differentiation of 2D proximal femur morphometry and hounsfield units for integrated forensic estimation of sex, stature, and age in a modern Thai dry bone sample.

Anatomical science international·2026
Same author

Overexpression of FGFR2 in Mandibular Ameloblastoma Is Potentially Associated with Gene Amplification and Deletion.

International journal of molecular sciences·2026
Same author

Digital and immersive approaches to anatomy education: a pilot comparative study of CI, VR, and hybrid learning in implant planning.

BMC medical education·2026

Related Experiment Video

Updated: Jun 8, 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

6.5K

CrossViT with ECAP: Enhanced deep learning for jaw lesion classification.

Wannakamon Panyarak1, Wattanapong Suttapak2, Phattaranant Mahasantipiya1

  • 1Division of Oral and Maxillofacial Radiology, Department of Oral Biology and Diagnostic Sciences, Faculty of Dentistry, Chiang Mai University, Suthep Road, Suthep Sub-district, Mueang Chiang Mai District, Chiang Mai 50200, Thailand.

International Journal of Medical Informatics
|November 4, 2024
PubMed
Summary

Deep learning models, including CrossViT and ResNet, show improved classification of radiolucent jaw lesions with the Extended Cropping and Padding (ECAP) technique. CrossViT models outperformed ResNets, demonstrating potential for accurate diagnosis.

Keywords:
CrossViTData enhancement techniqueDeep learningDiagnostic imagingPanoramic radiographs

More Related Videos

Induction of Periodontitis via a Combination of Ligature and Lipopolysaccharide Injection in a Rat Model
06:14

Induction of Periodontitis via a Combination of Ligature and Lipopolysaccharide Injection in a Rat Model

Published on: February 17, 2023

3.7K
Systematic Assessment of Mammalian Skull Specimens for Dental and Temporomandibular Joint Pathology
07:26

Systematic Assessment of Mammalian Skull Specimens for Dental and Temporomandibular Joint Pathology

Published on: August 22, 2022

1.3K

Related Experiment Videos

Last Updated: Jun 8, 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

6.5K
Induction of Periodontitis via a Combination of Ligature and Lipopolysaccharide Injection in a Rat Model
06:14

Induction of Periodontitis via a Combination of Ligature and Lipopolysaccharide Injection in a Rat Model

Published on: February 17, 2023

3.7K
Systematic Assessment of Mammalian Skull Specimens for Dental and Temporomandibular Joint Pathology
07:26

Systematic Assessment of Mammalian Skull Specimens for Dental and Temporomandibular Joint Pathology

Published on: August 22, 2022

1.3K

Area of Science:

  • Oral and Maxillofacial Radiology
  • Artificial Intelligence in Medicine
  • Medical Image Analysis

Background:

  • Radiolucent jaw lesions like ameloblastoma (AM), dentigerous cyst (DC), odontogenic keratocyst (OKC), and radicular cyst (RC) present diagnostic challenges due to overlapping radiographic features.
  • Deep learning, specifically multi-scale vision transformers (CrossViT) and Convolutional Neural Networks (ResNets), offers potential for automated image classification.
  • The Extended Cropping and Padding (ECAP) technique, designed to augment training data while preserving context, has not been previously applied to dental radiographic classification.

Purpose of the Study:

  • To evaluate the effectiveness of CrossViT models combined with the ECAP technique for classifying common radiolucent jaw lesions.
  • To compare the performance of CrossViT and ResNet architectures, with and without ECAP, in differentiating between AM, DC, OKC, and RC.
  • To assess the diagnostic performance metrics, including accuracy, precision, recall, F1-score, and AUC, for each model configuration.

Main Methods:

  • A retrospective analysis of 208 radiolucent jaw lesions (AM, DC, OKC, RC) from panoramic radiographs/OPGs with confirmed histological diagnoses.
  • Implementation of horizontal flip and ECAP data augmentation techniques.
  • Training and evaluation of CrossViT-15, CrossViT-18, ResNet-50, ResNet-101, and ResNet-152 models using four-fold cross-validation.

Main Results:

  • CrossViT models consistently outperformed ResNet models in accuracy, precision, recall, and F1-score, irrespective of ECAP application.
  • The ECAP technique generally improved model performance, with a statistically significant increase in F1-score observed for ResNet-152.
  • CrossViT-18 demonstrated the best overall performance, while CrossViT-15 achieved AUCs above 0.80 for all lesion types. Dentigerous cysts had the highest AUCs, and odontogenic keratocysts had the lowest.

Conclusions:

  • The ECAP technique enhances deep learning model performance for radiolucent jaw lesion classification by preserving contextual information.
  • CrossViT models, particularly when augmented with ECAP, show significant promise for accurate and reliable classification of these lesions.
  • This approach is especially valuable for improving the classification of rare lesions where training data may be limited.