Deep learning segmentation of mandible with lower dentition from cone beam CT
Oral Radiology · 2025
DOI: 10.1007/s11282-024-00770-6 ↗Kurz gefasst
Fachartikel in der Zeitschrift Oral Radiology, 2025. Verfasst von Daniel C Kargilis und 6 weiteren Autor:innen. Beteiligte Einrichtung: University of Pennsylvania, 1 Founders Pavilion, 3400 Spruce Street, Philadelphia, PA, 19104-4283, USA. dkargil1@jh.edu. Hauptthemen laut MEDLINE: Cone-Beam Computed Tomography, Deep Learning, Mandible. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 42 Literaturangaben.
Abstract (Originalsprache)
OBJECTIVES: This study aimed to train a 3D U-Net convolutional neural network (CNN) for mandible and lower dentition segmentation from cone-beam computed tomography (CBCT) scans. METHODS: In an ambispective cross-sectional design, CBCT scans from two hospitals (2009-2019 and 2021-2022) constituted an internal dataset and external validation set, respectively. Manual segmentation informed CNN training, and evaluations employed Dice similarity coefficient (DSC) for volumetric accuracy. A blinded oral maxillofacial surgeon performed qualitative grading of CBCT scans and object meshes. Statistical analyses included independent t-tests and ANOVA tests to compare DSC across patient subgroups of gender, race, body mass index (BMI), test dataset used, age, and degree of metal artifact. Tests were powered for a minimum detectable difference in DSC of 0.025, with alpha of 0.05 and power level of 0.8. RESULTS: 648 CBCT scans from 490 patients were included in the study. The CNN achieved high accuracy (average DSC: 0.945 internal, 0.940 external). No DSC differences were observed between test set used, gender, BMI, and race. Significant differences in DSC were identified based on age group and the degree of metal artifact. The majority (80%) of object meshes produced by both manual and automatic segmentation were rated as acceptable or higher quality. CONCLUSION: We developed a model for automatic mandible and lower dentition segmentation from CBCT scans in a demographically diverse cohort including a high degree of metal artifacts. The model demonstrated good accuracy on internal and external test sets, with majority acceptable quality from a clinical grader.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- University of Pennsylvania, 1 Founders Pavilion, 3400 Spruce Street, Philadelphia, PA, 19104-4283, USA. dkargil1@jh.edu.
- Johns Hopkins University, Baltimore, USA. dkargil1@jh.edu.
- University of Pennsylvania, 1 Founders Pavilion, 3400 Spruce Street, Philadelphia, PA, 19104-4283, USA.
ORCID-Profile: Daniel C Kargilis
Zitieren
APA
Kargilis, D. C., Xu, W., Reddy, S., Ramesh, S. S. K., Wang, S., Le, A. D., & Rajapakse, C. S. (2025). Deep learning segmentation of mandible with lower dentition from cone beam CT. Oral Radiology. https://doi.org/10.1007/s11282-024-00770-6
Vancouver
Kargilis DC, Xu W, Reddy S, Ramesh SSK, Wang S, Le AD, et al. Deep learning segmentation of mandible with lower dentition from cone beam CT. Oral Radiology. 2025. doi:10.1007/s11282-024-00770-6
BibTeX
@article{Kargilis2025,
author = {Kargilis, Daniel C and Xu, Winnie and Reddy, Samir and Ramesh, Shilpa Shree Kuduva and Wang, Steven and Le, Anh D and Rajapakse, Chamith S},
title = {Deep learning segmentation of mandible with lower dentition from cone beam CT},
journal = {Oral Radiology},
year = {2025},
doi = {10.1007/s11282-024-00770-6}
}
EUVIMED