biostudies-literatureGillot MAmerican Association of Orthodontists FoundationNational Institute of Dental and Craniofacial ResearchUniversity of the Pacifice0275033https://www.ebi.ac.uk/biostudies/studies/S-EPMC9555672biostudies-literatureUnknown17(10)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 rPloS oneAutomatic multi-anatomical skull structure segmentation of cone-beam computed tomography scans using 3D UNETR.PMC9555672Grabber Family Teaching and Research AwardResearch Enhancement Award Activity 141024450Oh HPrieto JCGillot MGomes LCosta FDeleat-Besson RAl Turkestani NLe CGurgel MPaniagua BIoshida MPieper SGryak JNajarian KRuellas AKikinis RSoroushmehr RBaquero BBenavides EFillion-Robin JCJoshi HGarib DBianchi JMassaro CSoki FChaves Junior CMEvangelista KYatabe MCevidanes LfalseAutomatic multi-anatomical skull structure segmentation of cone-beam computed tomography scans using 3D UNETR.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 r2022-01-01T00:00:00Z20222025-04-18T19:02:36.246Z2025-04-07T06:44:26.212ZS-EPMC95556723622333010.1371/journal.pone.0275033