Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

Three-dimensional CT imaging features of impacted first permanent molars and their correlation with prognosis.

Oral radiology·2026

Same author

Caries is a gradient, not a boundary: Detection rather than segmentation is the appropriate deep learning approach.

Imaging science in dentistry·2026

Same author

A novel cross-attentive network for classifying cervical metastatic lymph nodes on B- and D-mode ultrasound images in oral squamous cell carcinoma.

Dento maxillo facial radiology·2025

Same author

Development of 10 principles of radiation protection in oral and maxillofacial radiology.

Imaging science in dentistry·2025

Same author

Assessment of vertical magnification ratios in digital panoramic radiography using phantoms: evaluation of DICOM metadata and calibration consistency.

Dento maxillo facial radiology·2025

Same author

Diagnostic performance of quantitative parameters derived from twin-beam dual-energy CT for differentiating benign and malignant salivary gland tumors of the palate.

Dento maxillo facial radiology·2025

Same journal

Does adding ultrasonography to clinical-psychosocial measures improve discrimination for temporomandibular disorders?

Imaging science in dentistry·2026

Same journal

Three-dimensional analysis of condylar displacement after orthognathic surgery in patients with facial asymmetry.

Imaging science in dentistry·2026

Same journal

Deep learning-driven super-resolution for cone-beam computed tomography: An <i>ex vivo</i> proof-of-concept study using artificially degraded micro-computed tomography data.

Imaging science in dentistry·2026

Same journal

Evaluation of artifacts in cone-beam computed tomography from different intraradicular pins and cementation materials using different exposure protocols.

Imaging science in dentistry·2026

Same journal

Contribution of cone-beam computed tomography to the evaluation of lesions resulting from multiple myeloma and to the early diagnosis of the disease: A scoping review.

Imaging science in dentistry·2026

Same journal

Radiotherapy-induced alterations in trabecular microarchitecture and bone mass of the mandibular condylar process: A retrospective analysis using fractal dimension and pixel intensity on digital panoramic radiographs.

Imaging science in dentistry·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Aug 15, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Deep learning-based apical lesion segmentation from panoramic radiographs.

Il-Seok Song¹, Hak-Kyun Shin², Ju-Hee Kang¹

¹Department of Oral and Maxillofacial Radiology and Dental Research Institute, School of Dentistry, Seoul National University, Seoul, Korea.

Imaging Science in Dentistry

|January 6, 2023

Summary

This summary is machine-generated.

This study demonstrates that a deep convolutional neural network (CNN) effectively segments apical lesions in dental panoramic radiographs. The artificial intelligence approach shows high performance in detecting these early-stage disease indicators.

Keywords:

Artificial Intelligence Deep Learning Periapical Periodontitis Radiography, Panoramic

More Related Videos

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

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

Published on: August 5, 2021

Guided Endodontics: Three-Dimensional Planning and Template-Aided Preparation of Endodontic Access Cavities

Guided Endodontics: Three-Dimensional Planning and Template-Aided Preparation of Endodontic Access Cavities

Published on: May 24, 2022

Related Experiment Videos

Last Updated: Aug 15, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

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

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

Published on: August 5, 2021

Guided Endodontics: Three-Dimensional Planning and Template-Aided Preparation of Endodontic Access Cavities

Guided Endodontics: Three-Dimensional Planning and Template-Aided Preparation of Endodontic Access Cavities

Published on: May 24, 2022

Area of Science:

Artificial Intelligence in Dentistry
Medical Imaging Analysis
Deep Learning Applications

Background:

Convolutional neural networks (CNNs) are advanced artificial intelligence (AI) tools increasingly utilized in medical and dental research.
CNNs offer effective diagnostic capabilities for early disease detection.

Purpose of the Study:

To assess the performance of a deep CNN algorithm for segmenting apical lesions in panoramic radiographs.
To evaluate the utility of AI in identifying early-stage dental pathologies.

Main Methods:

A dataset of 1000 panoramic images with apical lesions was divided into training (80%), validation (10%), and testing (10%) sets.
The deep CNN algorithm, specifically U-Net, was employed for lesion segmentation.
Performance was measured using precision, recall, and F1-score at various intersection over union (IoU) thresholds.

Main Results:

The deep CNN successfully segmented 147 out of 180 apical lesions in the test set (IoU threshold of 0.3).
The F1-scores achieved were 0.828 (IoU 0.3), 0.815 (IoU 0.4), and 0.742 (IoU 0.5), indicating high performance.
The U-Net based CNN demonstrated significant accuracy in apical lesion detection.

Conclusions:

Deep learning, particularly using CNNs like U-Net, shows significant potential for segmenting apical lesions.
This AI-driven approach offers a promising tool for the early and accurate detection of apical periodontitis from panoramic radiographs.