Patch-based convolutional neural networks for automatic landmark detection of 3D facial images in clinical settings.

Journal: European journal of orthodontics
Published Date:

Abstract

BACKGROUND: The facial landmark annotation of 3D facial images is crucial in clinical orthodontics and orthognathic surgeries for accurate diagnosis and treatment planning. While manual landmarking has traditionally been the gold standard, it is labour-intensive and prone to variability.

Authors

  • Bodore Al-Baker
    Orthodontic Department, Hamad Dental Center, Hamad Medical Corporation, Doha, Qatar.
  • Ashraf Ayoub
    Scottish Craniofacial Research Group, Glasgow University Dental Hospital & School, School of Medicine, College of Medical, Veterinary and Life Sciences, University of Glasgow, Glasgow, United Kingdom.
  • Xiangyang Ju
    Medical Devices Unit, Department of Clinical Physics and Bioengineering, National Health Service of Greater Glasgow and Clyde, Glasgow, United Kingdom.
  • Peter Mossey
    Dental Hospital and School, University of Dundee, Dundee, United Kingdom.