Detecting Mandible Fractures in CBCT Scans Using a 3-Stage Neural Network.

Autor:	van Nistelrooij N; Department of Oral and Maxillofacial Surgery, Radboud University Medical Center, Nijmegen, The Netherlands.; Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Department of Oral and Maxillofacial Surgery, Berlin, Germany., Schitter S; Department of Oral and Maxillofacial Surgery, Division of Regenerative, Orofacial Medicine, University Medical Center Hamburg-Eppendorf, Hamburg, Germany., van Lierop P; Department of Oral and Maxillofacial Surgery, Radboud University Medical Center, Nijmegen, The Netherlands., Ghoul KE; Department of Oral and Maxillofacial Surgery, Erasmus Medical Center, Rotterdam, The Netherlands., König D; Department of Oral and Maxillofacial Surgery, Division of Regenerative, Orofacial Medicine, University Medical Center Hamburg-Eppendorf, Hamburg, Germany., Hanisch M; Department of Oral and Maxillofacial Surgery, Universitätsklinikum, Münster, Münster, Germany., Tel A; Clinic of Maxillofacial Surgery, Head-Neck and NeuroScience Department University Hospital of Udine, Udine, Italy., Xi T; Department of Oral and Maxillofacial Surgery, Radboud University Medical Center, Nijmegen, The Netherlands., Thiem DGE; Department of Oral and Maxillofacial Surgery, Facial Plastic Surgery, University Medical Centre Mainz, Mainz, Germany., Smeets R; Department of Oral and Maxillofacial Surgery, Division of Regenerative, Orofacial Medicine, University Medical Center Hamburg-Eppendorf, Hamburg, Germany., Dubois L; Department of Oral and Maxillofacial Surgery, Amsterdam UMC, University of Amsterdam, Amsterdam, The Netherlands., Flügge T; Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Department of Oral and Maxillofacial Surgery, Berlin, Germany., van Ginneken B; Diagnostic Image Analysis Group, Radboud University Medical Center, Nijmegen, The Netherlands., Bergé S; Department of Oral and Maxillofacial Surgery, Radboud University Medical Center, Nijmegen, The Netherlands., Vinayahalingam S; Department of Oral and Maxillofacial Surgery, Radboud University Medical Center, Nijmegen, The Netherlands.
Jazyk:	angličtina
Zdroj:	Journal of dental research [J Dent Res] 2024 Jun 24, pp. 220345241256618. Date of Electronic Publication: 2024 Jun 24.
DOI:	10.1177/00220345241256618
Abstrakt:	After nasal bone fractures, fractures of the mandible are the most frequently encountered injuries of the facial skeleton. Accurate identification of fracture locations is critical for effectively managing these injuries. To address this need, JawFracNet, an innovative artificial intelligence method, has been developed to enable automated detection of mandibular fractures in cone-beam computed tomography (CBCT) scans. JawFracNet employs a 3-stage neural network model that processes 3-dimensional patches from a CBCT scan. Stage 1 predicts a segmentation mask of the mandible in a patch, which is subsequently used in stage 2 to predict a segmentation of the fractures and in stage 3 to classify whether the patch contains any fracture. The final output of JawFracNet is the fracture segmentation of the entire scan, obtained by aggregating and unifying voxel-level and patch-level predictions. A total of 164 CBCT scans without mandibular fractures and 171 CBCT scans with mandibular fractures were included in this study. Evaluation of JawFracNet demonstrated a precision of 0.978 and a sensitivity of 0.956 in detecting mandibular fractures. The current study proposes the first benchmark for mandibular fracture detection in CBCT scans. Straightforward replication is promoted by publicly sharing the code and providing access to JawFracNet on grand-challenge.org. Competing Interests: Declaration of Conflicting InterestsThe authors declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article. Shankeeth Vinayahalingam is a co-founder of Ardim BV, a company that develops AI-assisted ultrasound technology for hip dysplasia, and Bram van Ginneken is a co-founder of Thirona BV, a company specializing in AI-assisted lung image analysis.
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu