A deep learning model for multiclass tooth segmentation on cone-beam computed tomography scans.

Journal: American journal of orthodontics and dentofacial orthopedics : official publication of the American Association of Orthodontists, its constituent societies, and the American Board of Orthodontics
Published Date:

Abstract

INTRODUCTION: Machine learning, a common artificial intelligence technology in medical image analysis, enables computers to learn statistical patterns from pairs of data and annotated labels. Supervised learning in machine learning allows the computer to predict how a specific anatomic structure should be segmented in new patients. This study aimed to develop and validate a deep learning algorithm that automatically creates 3-dimensional surface models of human teeth from a cone-beam computed tomography scan.

Authors

  • Tarek ElShebiny
    Department of Orthodontics, Case Western Reserve University School of Dental Medicine, Cleveland, Ohio.
  • Dina Abdelrauof
    Research and Development Division, Intixel Co, Cairo, Egypt.
  • Mustafa Elattar
    Medical Imaging and Image Processing, Center of Informatics Science, Nile University, Sheikh Zayed City , Egypt.
  • Melih Motro
    Department of Orthodontics and Dentofacial Orthopedics, Boston University Goldman School of Dentistry, Boston, Massachusetts.
  • Jean Marc Retrouvey
    Department of Molecular Genetics, Baylor College of Medicine, Houston, Tex.
  • Mostafa El-Dawlatly
    Department of Orthodontics, Faculty of Dentistry, Cairo University, 11 El-Saraya Street, Manial, Cairo, Egypt.
  • Yehia Mostafa
    Department of Orthodontics, Future University, Cairo, Egypt.
  • Anwar Alhazmi
    Department of Preventive Dental Science, Jazan University, College of Dentistry, Jazan, Saudi Arabia.
  • Juan Martin Palomo
    Department of Orthodontics, School of Dental Medicine, Case Western Reserve University, Cleveland, Ohio, USA.