Related Experiment Video
Updated: Jan 6, 2026
05:49
Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
Published on: February 23, 2024
1.3K
AI-Assisted 3D diagnosis of impacted maxillary canines: A validation study
Sara Tinawi1, Rodrigo Teixeira2, Aron Aliaga-Del Castillo1
1Department of Orthodontics and Pediatric Dentistry, School of Dentistry, University of Michigan, Ann Arbor, MI, USA.
Clinical Oral Investigations
|November 12, 2025
Summary
An artificial intelligence (AI) system accurately identifies impacted canine position and severity using 3D imaging. This AI diagnostic tool enhances clinical decisions, improving patient education and treatment planning for impacted canines.
Area of Science:
- Dentistry
- Artificial Intelligence
- Medical Imaging
Background:
- Impacted maxillary canines require accurate 3D characterization for effective treatment.
- Conventional orthodontic records can be time-consuming for assessing impaction severity.
Purpose of the Study:
- To validate an AI-based automated image analysis for 3D characterization of impacted canine position.
- To compare clinical treatment plans using conventional records versus AI-assisted diagnosis.
Main Methods:
- Retrospective analysis of 228 cone-beam computed tomography (CBCT) scans.
- AI models automatically oriented scans and identified landmarks for impaction severity quantification.
- AI accuracy was validated against manual measurements by expert clinicians.
Main Results:
- AI achieved a 96.2% detection success rate for impacted canines.
- Palatally impacted canines showed distinct positional and angular characteristics (P<0.001).
- AI significantly influenced clinicians' decisions in patient education (72.31%) and biomechanics (51.15%).
Conclusions:
- AI-based diagnostic systems accurately characterize impacted canine position and severity.
- AI enhances diagnosis, providing objective measurements for complex impactions.
- AI improves patient communication and supports informed treatment planning.
