{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Gillot M"],"funding":["American Association of Orthodontists Foundation","National Institute of Dental and Craniofacial Research","University of the Pacific"],"pagination":["e0275033"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC9555672"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["17(10)"],"pubmed_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 r"],"journal":["PloS one"],"pubmed_title":["Automatic multi-anatomical skull structure segmentation of cone-beam computed tomography scans using 3D UNETR."],"pmcid":["PMC9555672"],"funding_grant_id":["Grabber Family Teaching and Research Award","Research Enhancement Award Activity 141","024450"],"pubmed_authors":["Oh H","Prieto JC","Gillot M","Gomes L","Costa F","Deleat-Besson R","Al Turkestani N","Le C","Gurgel M","Paniagua B","Ioshida M","Pieper S","Gryak J","Najarian K","Ruellas A","Kikinis R","Soroushmehr R","Baquero B","Benavides E","Fillion-Robin JC","Joshi H","Garib D","Bianchi J","Massaro C","Soki F","Chaves Junior CM","Evangelista K","Yatabe M","Cevidanes L"],"additional_accession":[]},"is_claimable":false,"name":"Automatic multi-anatomical skull structure segmentation of cone-beam computed tomography scans using 3D UNETR.","description":"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 r","dates":{"release":"2022-01-01T00:00:00Z","publication":"2022","modification":"2025-04-18T19:02:36.246Z","creation":"2025-04-07T06:44:26.212Z"},"accession":"S-EPMC9555672","cross_references":{"pubmed":["36223330"],"doi":["10.1371/journal.pone.0275033"]}}