Automatic multi-anatomical skull structure segmentation of cone-beam computed tomography scans using 3D UNETR
Maxime Gillot, Baptiste Baquero, Celia Le, Romain Deleat‐Besson, Jonas Bianchi, Antônio Carlos de Oliveira Ruellas, Marcela Gurgel, Marília Yatabe, Najla Al Turkestani, Kayvan Najarian, S. M. Reza Soroushmehr, Steve Pieper, Ron Kikinis, Beatriz Paniagua, Jonathan Gryak, Marcos Ioshida, Camila Massaro, Liliane Gomes, Heesoo Oh, Karine Evangelista, Cauby Maia Chaves, Daniela Gamba Garib, Fábio Wildson Gurgel Costa, Erika Benavides, Fabiana N. Soki, Jean‐Christophe Fillion‐Robin, Hina Joshi, Lucía Cevidanes, Juan Carlos Prieto
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.