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

Authors

• Maxime Gillot, University of Michigan, Ann Arbor
• Baptiste Baquero, University of Michigan, Ann Arbor
• Celia Le, University of Michigan, Ann Arbor
• Romain Deleat-Besson, University of Michigan, Ann Arbor
• Jonas Bianchi, University of the PacificFollow
• Antonio Ruellas, University of Michigan, Ann Arbor
• Marcela Gurgel, University of Michigan, Ann Arbor
• Marilia Yatabe, University of Michigan, Ann Arbor
• Najla Al Turkestani, University of Michigan, Ann Arbor
• Kayvan Najarian, University of Michigan, Ann Arbor
• Reza Soroushmehr, University of Michigan, Ann Arbor
• Steve Pieper, Isomics
• Ron Kikinis, Harvard Medical School
• Beatriz Paniagua, Kitware, Inc.
• Jonathan Gryak, University of Michigan, Ann Arbor
• Marcos Ioshida, University of Michigan, Ann Arbor
• Camila Massaro, University of Michigan, Ann Arbor
• Liliane Gomes, University of Michigan, Ann Arbor
• Heesoo Oh, University of the PacificFollow
• Karine Evangelista, University of Michigan, Ann Arbor
• Cauby Maia Chaves Junior, University of Ceará
• Daniela Garib, Universidade de São Paulo

Document Type

Article

Publication Title

PloS One

Department

Orthodontics

ISSN

19326203

Volume

17

Issue

10

DOI

10.1371/journal.pone.0275033

First Page

1

Last Page

12

Publication Date

10-12-2022

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.

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Recommended Citation

Gillot, Maxime; Baquero, Baptiste; Le, Celia; Deleat-Besson, Romain; Bianchi, Jonas; Ruellas, Antonio; Gurgel, Marcela; Yatabe, Marilia; Al Turkestani, Najla; Najarian, Kayvan; Soroushmehr, Reza; Pieper, Steve; Kikinis, Ron; Paniagua, Beatriz; Gryak, Jonathan; Ioshida, Marcos; Massaro, Camila; Gomes, Liliane; Oh, Heesoo; Evangelista, Karine; Chaves Junior, Cauby Maia; and Garib, Daniela, "Automatic multi-anatomical skull structure segmentation of cone-beam computed tomography scans using 3D UNETR" (2022). Pacific Faculty Work. 229.
https://scholarlycommons.pacific.edu/all-faculty/229