Scholarlink

Background <p>Mesiodens is a type of supernumerary tooth in the anterior maxilla with various prevalences. To prevent complications in the future, accurate and precise detection is needed.</p> Objective <p>This study aimed to evaluate and compare YOLOv11-based convolutional neural network (CNN) models for mesiodens detection in pediatric panoramic radiographs using two cloud-based platforms, Roboflow and Ultralytics.</p> Design <p>This study involved 480 pediatric panoramic radiographs, consisting of 240 mesiodens and 240 no mesiodens images, annotated using Roboflow, with a region of interest (ROI) focused on the anterior maxillary area. The dataset was divided into training (70%), validation (20%), and testing (10%) subsets. Model performance was evaluated using mean average precision (mAP), precision, recall, and F1-score.</p> Results <p>The YOLOv11 Accurate model trained on the Roboflow platform achieved the highest validation mAP50 at 99.2% and recall at 100%. However, its performance declined on inference data, where the F1-score was 84.30%. In contrast, the YOLOv11l model trained on the Ultralytics platform showed more stable performance: its validation mAP was 99.3%, precision was 99.11%, and recall was 94.57%, while the inference F1-score was 96.78%, showing robust generalizability and supporting its suitability for clinical practice.</p> Conclusion <p>YOLOv11l demonstrated the most reliable balance between validation and inference performance, suggesting suitability for clinical application. These results highlight the importance of model generalization rather than peak validation metrics. Future studies should therefore evaluate multicenter datasets and broader clinical settings to confirm robustness and applicability in diverse pediatric populations.</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

Generalizability of YOLOv11 models for mesiodens detection in pediatric panoramic radiographs

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年1月28日

查看全文
  • Henri Hartman,
  • Adinara Savero,
  • Tjinta Kaulika Tamim,
  • Farina Pramanik,
  • Saiful Akbar,
  • Denny Nurdin,
  • Arlette Suzy Setiawan

摘要

Background

Mesiodens is a type of supernumerary tooth in the anterior maxilla with various prevalences. To prevent complications in the future, accurate and precise detection is needed.

Objective

This study aimed to evaluate and compare YOLOv11-based convolutional neural network (CNN) models for mesiodens detection in pediatric panoramic radiographs using two cloud-based platforms, Roboflow and Ultralytics.

Design

This study involved 480 pediatric panoramic radiographs, consisting of 240 mesiodens and 240 no mesiodens images, annotated using Roboflow, with a region of interest (ROI) focused on the anterior maxillary area. The dataset was divided into training (70%), validation (20%), and testing (10%) subsets. Model performance was evaluated using mean average precision (mAP), precision, recall, and F1-score.

Results

The YOLOv11 Accurate model trained on the Roboflow platform achieved the highest validation mAP50 at 99.2% and recall at 100%. However, its performance declined on inference data, where the F1-score was 84.30%. In contrast, the YOLOv11l model trained on the Ultralytics platform showed more stable performance: its validation mAP was 99.3%, precision was 99.11%, and recall was 94.57%, while the inference F1-score was 96.78%, showing robust generalizability and supporting its suitability for clinical practice.

Conclusion

YOLOv11l demonstrated the most reliable balance between validation and inference performance, suggesting suitability for clinical application. These results highlight the importance of model generalization rather than peak validation metrics. Future studies should therefore evaluate multicenter datasets and broader clinical settings to confirm robustness and applicability in diverse pediatric populations.