Automatic multi-anatomical skull structure segmentation of cone-beam computed tomography scans using 3D UNETR.

Journal: PloS one
PMID: 36223330

Abstract

The segmentation of medical and dental images is a fundamental step in automated clinical decision support systems. It supports the entire clinical workflow from diagnosis, therapy planning, intervention, and follow-up. In this paper, we propose a novel tool to accurately process a full-face segmentation in about 5 minutes that would otherwise require an average of 7h of manual work by experienced clinicians. This work focuses on the integration of the state-of-the-art UNEt TRansformers (UNETR) of the Medical Open Network for Artificial Intelligence (MONAI) framework. We trained and tested our models using 618 de-identified Cone-Beam Computed Tomography (CBCT) volumetric images of the head acquired with several parameters from different centers for a generalized clinical application. Our results on a 5-fold cross-validation showed high accuracy and robustness with a Dice score up to 0.962±0.02. Our code is available on our public GitHub repository.

Authors

  • Maxime Gillot
    Department of Orthodontics and Pediatric Dentistry, University of Michigan, 1011 North University Avenue, Ann Arbor, MI 48109, USA.
  • Baptiste Baquero
    Department of Orthodontics and Pediatric Dentistry, University of Michigan, 1011 North University Avenue, Ann Arbor, MI 48109, USA.
  • Celia Le
    University of Michigan, Ann Arbor, MI 48109, USA.
  • Romain Deleat-Besson
    University of Michigan, Ann Arbor, MI 48109, USA.
  • Jonas Bianchi
    University of Michigan, Ann Arbor, MI, USA.
  • Antonio Ruellas
    Federal University of Rio de Janeiro, Rio de Janeiro, Brazil.
  • Marcela Gurgel
    University of Michigan, Ann Arbor, MI, USA.
  • Marilia Yatabe
    University of Michigan, Ann Arbor, MI, USA.
  • Najla Al Turkestani
    University of Michigan, Ann Arbor, MI, USA.
  • Kayvan Najarian
  • Reza Soroushmehr
    Department of Computational Medicine and Bioinformatics, University of Michigan, 100 Washtenaw Avenue, Ann Arbor, MI 48109, USA.
  • Steve Pieper
    Isomics Inc., Cambridge, MA, USA.
  • Ron Kikinis
    Department of Radiology, Brigham and Women's Hospital and Harvard Medical School, Boston, MA, United States.
  • Beatriz Paniagua
    Kitware Inc., Carrboro, NC, USA.
  • Jonathan Gryak
  • Marcos Ioshida
    Department for Orthodontics and Pediatric Dentistry, University of Michigan, Ann Arbor, MI, USA.
  • Camila Massaro
  • Liliane Gomes
    Department for Orthodontics and Pediatric Dentistry, University of Michigan, Ann Arbor, MI, USA.
  • Heesoo Oh
  • Karine Evangelista
  • Cauby Maia Chaves Junior
    University of Ceara, Fortaleza, Brazil.
  • Daniela Garib
  • Fabio Costa
  • Erika Benavides
    University of Michigan, Department of Periodontics and Oral Medicine, School of Dentistry, Ann Arbor, MI, 48109, USA.
  • Fabiana Soki
    University of Michigan, Department of Periodontics and Oral Medicine, School of Dentistry, Ann Arbor, MI, 48109, USA.
  • Jean-Christophe Fillion-Robin
  • Hina Joshi
    University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, United States of America.
  • Lucia Cevidanes
    University of Michigan, Ann Arbor, MI, USA.
  • Juan Carlos Prieto
    University of North Carolina, Chapel Hill, USA.

Keywords

External Resources

Popular Topics
Recent Journals