Related Experiment Video
Updated: Apr 23, 2026
10:50
A Finite Element Approach for Locating the Center of Resistance of Maxillary Teeth
Published on: April 8, 2020
9.1K
Sector Classification of Unerupted Maxillary Canines: A Deep Learning-Based Automated Framework Using Panoramic
Marzio Galdi1, Davide Cannatà1, Flavia Celentano1
1Department of Medicine, Surgery and Dentistry, University of Salerno, Baronissi, SA, Italy.
Orthodontics & Craniofacial Research
|March 3, 2026
Summary
A new deep learning framework automates unerupted maxillary canine (UMC) sector classification. This AI approach shows accuracy comparable to human dentists but with superior reliability in classifying UMC positions.
Area of Science:
- Dentistry
- Artificial Intelligence
- Medical Imaging
Background:
- Accurate sector classification of unerupted maxillary canines (UMCs) is crucial for orthodontic treatment planning.
- Current methods rely on manual interpretation of dental radiographs, which can be subjective and time-consuming.
- Automating this process using artificial intelligence (AI) could improve efficiency and consistency.
Purpose of the Study:
- To develop and evaluate a deep learning-based framework for automated sector classification of UMCs.
- To compare the accuracy and reliability of the AI framework against human dental practitioners.
- To identify the best-performing AI model for UMC sector classification.
Main Methods:
- A dataset of 1528 UMCs from digital panoramic radiographs was utilized.
- Six dental practitioners classified UMCs into three sectors based on Kim's system, with assessments repeated after four weeks.
- Cohen's Kappa statistic was used to assess inter- and intra-examiner agreement.
- Several AI models were trained and tested, with the best model selected based on sensitivity, precision, accuracy, and repeatability.
Main Results:
- Human inter-examiner agreement for UMC sector classification was 0.78, and intra-examiner agreement was 0.85.
- The DenseNet121 model demonstrated the highest performance, achieving an overall accuracy of 76.8% and repeatability of 95.3%.
- The AI framework's accuracy in sector classification was comparable to human performance.
Conclusions:
- The developed deep learning framework offers an automated solution for UMC sector classification.
- The AI approach provides accuracy comparable to human experts.
- The automated system exhibits greater reliability than manual classification by dental practitioners.
Keywords:
artificial intelligencedeep learningimpacted maxillary caninesinterceptive orthodonticsradiologyMore Related Videos
Related Concept Videos
01:18Classification of Bones
14.2K
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...
Long and Short Bones
The appendicular skeleton, particularly the upper and lower limbs, is primarily made of long and short bones. The...
14.2K
01:21Tooth Anatomy
2.7K
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...
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...
2.7K