Scholarlink

Introduction <p>This study aimed to validate an artificial intelligence (AI)-based automated image analysis for three-dimensional (3D) characterization of impacted canine position. In addition, it compared clinical treatment plans developed using conventional orthodontic records versus with the aid of the AI-generated diagnostic report.</p> Methods <p>A sample of 228 cone-beam computed tomography (CBCT) scans for patients with impacted maxillary canines was retrospectively collected. AI models were used to automatically orient scans and identify anatomical landmarks to quantify impaction severity. The accuracy of the AI approach was validated by comparing its assessments with manual measurements performed by expert clinicians. Clinical applicability was assessed by comparing diagnoses made by clinicians using conventional records to those made using AI-based diagnostic system.</p> Results <p>A total of 316 impacted canines were assessed, with 20.9% classified as buccal, 31.3% as bicortical, and 47.8% as palatal. The AI-based diagnostic system accurately identified the position of impacted canines, achieving a mean detection success rate of 96.2%. Palatally impacted canines tend to have the crown closer to the midpalatal plane, reduced vertical distance to the occlusal plane, and greater pitch and roll angles compared to bicortically and buccally impacted canines (P&lt;0.001). Overlap with adjacent teeth was the primary contributor to the AI-generated severity index (81.11%). The AI-based diagnostic system report significantly influenced clinicians' decisions, particularly patient education (72.31%) and biomechanics (51.15%).</p> Conclusions <p>The AI-based diagnostic system accurately characterized impacted canine position and severity, demonstrating the effectiveness of AI in enhancing diagnosis for impacted canine.</p> Clinical relevance <p>The automated diagnostic report provides objective measurements that enhance clinicians’ understanding of impaction complexity, improve patient communication, and support more informed biomechanical and treatment-planning decisions.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

AI-Assisted 3D diagnosis of impacted maxillary canines: A validation study

  • 期刊论文

  • 发表日期：

    2025年11月12日

查看全文
  • Sara Tinawi,
  • Rodrigo Teixeira,
  • Aron Aliaga-Del Castillo,
  • Erika Benavides,
  • Fabiana Soki,
  • Antonio Carlos De Oliveira Ruellas,
  • Brent Larson,
  • Luis Enersto Arriola Guillén,
  • Yalil Augusto Rodríguez-Cárdenas,
  • Gustavo Armando Ruíz-Mora,
  • Jonas Bianchi,
  • Marcela Gurgel,
  • Felicia Miranda,
  • Dylan Keener,
  • Maxime Gillot,
  • Luc Anchling,
  • Jeanne Claret,
  • Christopher Roberts,
  • Laurie McClatchey McNamara,
  • Mary Barkley,
  • Eric Hannapel,
  • Maria Pinzon,
  • Thomas Gebeck,
  • Nicholas Shirey,
  • Claudia Mattos,
  • Gregory Hummon,
  • Lucia Cevidanes

摘要

Introduction

This study aimed to validate an artificial intelligence (AI)-based automated image analysis for three-dimensional (3D) characterization of impacted canine position. In addition, it compared clinical treatment plans developed using conventional orthodontic records versus with the aid of the AI-generated diagnostic report.

Methods

A sample of 228 cone-beam computed tomography (CBCT) scans for patients with impacted maxillary canines was retrospectively collected. AI models were used to automatically orient scans and identify anatomical landmarks to quantify impaction severity. The accuracy of the AI approach was validated by comparing its assessments with manual measurements performed by expert clinicians. Clinical applicability was assessed by comparing diagnoses made by clinicians using conventional records to those made using AI-based diagnostic system.

Results

A total of 316 impacted canines were assessed, with 20.9% classified as buccal, 31.3% as bicortical, and 47.8% as palatal. The AI-based diagnostic system accurately identified the position of impacted canines, achieving a mean detection success rate of 96.2%. Palatally impacted canines tend to have the crown closer to the midpalatal plane, reduced vertical distance to the occlusal plane, and greater pitch and roll angles compared to bicortically and buccally impacted canines (P<0.001). Overlap with adjacent teeth was the primary contributor to the AI-generated severity index (81.11%). The AI-based diagnostic system report significantly influenced clinicians' decisions, particularly patient education (72.31%) and biomechanics (51.15%).

Conclusions

The AI-based diagnostic system accurately characterized impacted canine position and severity, demonstrating the effectiveness of AI in enhancing diagnosis for impacted canine.

Clinical relevance

The automated diagnostic report provides objective measurements that enhance clinicians’ understanding of impaction complexity, improve patient communication, and support more informed biomechanical and treatment-planning decisions.