Deep Learning for Midfacial Fracture Detection in CT Images.

Journal: Studies in health technology and informatics
Published Date: Jan 25, 2024

Abstract

This study deploys the deep learning-based object detection algorithms to detect midfacial fractures in computed tomography (CT) images. The object detection models were created using faster R-CNN and RetinaNet from 2,000 CT images. The best detection model, faster R-CNN, yielded an average precision of 0.79 and an area under the curve (AUC) of 0.80. In conclusion, faster R-CNN model has good potential for detecting midfacial fractures in CT images.

Authors

  • Kritsasith Warin
    Division of Oral and Maxillofacial Surgery, Faculty of Dentistry, Thammasat University, Pathum Thani, Thailand.
  • Sothana Vicharueang
    StoreMesh, Thailand Science Park, Pathum Thani, Thailand.
  • Patcharapon Jantana
    StoreMesh, Thailand Science Park, Pathum Thani, Thailand.
  • Wasit Limprasert
    College of Interdisciplinary Studies, Thammasat University, Patum Thani, Thailand.
  • Bhornsawan Thanathornwong
    Faculty of Dentistry, Srinakharinwirot University, Bangkok, Thailand.
  • Siriwan Suebnukarn
    Faculty of Dentistry, Thammasat University, Pathum Thani, Thailand.

Keywords

External Resources

Popular Topics
Recent Journals