Treffer: Deploying a novel deep learning framework for segmentation of specific anatomical structures on cone-beam CT.
Original Publication: Gifu, Japan : Japanese Society of Dental Radiology,
Steinklein J, Nguyen V. Dental anatomy pathology encountered on routine CT of the head neck. Am J Roentgenol. 2013;201(6):W843–53. (PMID: 10.2214/AJR.12.9616)
Rafai N, Lemos M, Kennes LN, Hawari A, Gerhardt-Szép S, Classen-Linke I. Anatomy meets dentistry! Linking anatomy and clinical practice in the preclinical dental curriculum. BMC Med Educ. 2016;16:1–10. (PMID: 10.1186/s12909-016-0825-8)
Boeddinghaus R, Whyte A. Trends in maxillofacial imaging. Clin Radiol. 2018;73(1):4–18. (PMID: 10.1016/j.crad.2017.02.01528341434)
Protection R. Evidence-based guidelines on cone beam CT for dental and maxillofacial radiology. European Commission; 2012.
Angelopoulos C. Cone beam tomographic imaging anatomy of the maxillofacial region. Dent Clin N Am. 2008;52(4):731–52. (PMID: 10.1016/j.cden.2008.07.00218805226)
Suomalainen A, Pakbaznejad Esmaeili E, Robinson S. Dentomaxillofacial imaging with panoramic views and cone beam CT. Insights Imaging. 2015;6:1–16. (PMID: 10.1007/s13244-014-0379-4255758684330237)
Hosny A, Parmar C, Quackenbush J, Schwartz LH, Aerts HJ. Artificial intelligence in radiology. Nat Rev Cancer. 2018;18(8):500–10. (PMID: 10.1038/s41568-018-0016-5297771756268174)
Heo M-S, Kim J-E, Hwang J-J, Han S-S, Kim J-S, Yi W-J, Park I-W. Artificial intelligence in oral and maxillofacial radiology: what is currently possible? Dentomaxillofac Radiol. 2021;50(3):20200375. (PMID: 10.1259/dmfr.2020037533197209)
Jaskari J, Sahlsten J, Järnstedt J, Mehtonen H, Karhu K, Sundqvist O, Hietanen A, Varjonen V, Mattila V, Kaski K. Deep learning method for mandibular canal segmentation in dental cone beam computed tomography volumes. Sci Rep. 2020;10(1):5842. (PMID: 10.1038/s41598-020-62321-3322459897125134)
Keser G, Bayrakdar IS, Pekiner FN, Çelik Ö, Orhan K. A deep learning approach for masseter muscle segmentation on ultrasonography. J Ultrasonogr. 2022;22(91):e204–8. (PMID: 10.15557/JoU.2022.0034)
Hung KF, Ai QYH, Leung YY, Yeung AWK. Potential and impact of artificial intelligence algorithms in dento-maxillofacial radiology. Clin Oral Invest. 2022;26(9):5535–55. (PMID: 10.1007/s00784-022-04477-y)
Singh NK, Raza K. Progress in deep learning-based dental and maxillofacial image analysis: a systematic review. Expert Syst Appl. 2022;199: 116968. (PMID: 10.1016/j.eswa.2022.116968)
Görürgöz C, Orhan K, Bayrakdar IS, Çelik Ö, Bilgir E, Odabaş A, Aslan AF, Jagtap R. Performance of a convolutional neural network algorithm for tooth detection and numbering on periapical radiographs. Dentomaxillofac Radiol. 2022;51(3):20210246. (PMID: 10.1259/dmfr.2021024634623893)
Önder M, Evli C, Türk E, Kazan O, Bayrakdar İŞ, Çelik Ö, Costa ALF, Gomes JPP, Ogawa CM, Jagtap R. Deep-learning-based automatic segmentation of parotid gland on computed tomography images. Diagnostics. 2023;13(4):581. (PMID: 10.3390/diagnostics13040581368320699955422)
Sobiesk JL, Munakomi S. Anatomy, head and neck, nasal cavity. 2019.
Choi H, Jeon KJ, Kim YH, Ha E-G, Lee C, Han S-S. Deep learning-based fully automatic segmentation of the maxillary sinus on cone-beam computed tomographic images. Sci Rep. 2022;12(1):14009. (PMID: 10.1038/s41598-022-18436-w359780869385721)
Morgan N, Van Gerven A, Smolders A, de Faria Vasconcelos K, Willems H, Jacobs R. Convolutional neural network for automatic maxillary sinus segmentation on cone-beam computed tomographic images. Sci Rep. 2022;12(1):7523. (PMID: 10.1038/s41598-022-11483-3355258579079060)
Bayrakdar IS, Elfayome NS, Hussien RA, Gulsen IT, Kuran A, Gunes I, Al-Badr A, Celik O, Orhan K. Artificial intelligence system for automatic maxillary sinus segmentation on cone beam computed tomography images. Dentomaxillofac Radiol. 2024;53(4):256–66. (PMID: 10.1093/dmfr/twae0123850296311056744)
Orhan K, Shamshiev M, Ezhov M, Plaksin A, Kurbanova A, Ünsal G, Gusarev M, Golitsyna M, Aksoy S, Mısırlı M. AI-based automatic segmentation of craniomaxillofacial anatomy from CBCT scans for automatic detection of pharyngeal airway evaluations in OSA patients. Sci Rep. 2022;12(1):11863. (PMID: 10.1038/s41598-022-15920-1358314519279304)
Sin Ç, Akkaya N, Aksoy S, Orhan K, Öz U. A deep learning algorithm proposal to automatic pharyngeal airway detection and segmentation on CBCT images. Orthod Craniofac Res. 2021;24:117–23. (PMID: 10.1111/ocr.1248033619828)
Laura CO, Hartwig K, Distergoft A, Hoffmann T, Scheckenbach K, Brüsseler M, Wesarg S. Automatic segmentation of the structures in the nasal cavity and the ethmoidal sinus for the quantification of nasal septal deviations. In: Medical imaging 2021: computer-aided diagnosis. Spie; 2021.
Oliveira-Santos C, Capelozza ALÁ, Dezzoti MSG, Fischer CM, Poleti ML, Rubira-Bullen IRF. Visibility of the mandibular canal on CBCT crosssectional images. J Appl Oral Sci. 2011;19:240–3. (PMID: 10.1590/S1678-77572011000300011216257404234336)
Lahoud P, Diels S, Niclaes L, Van Aelst S, Willems H, Van Gerven A, Quirynen M, Jacobs R. Development and validation of a novel artificial intelligence driven tool for accurate mandibular canal segmentation on CBCT. J Dent. 2022;116: 103891. (PMID: 10.1016/j.jdent.2021.10389134780873)
Thakur AR, Burde K, Guttal K, Naikmasur VG. Anatomy and morphology of the nasopalatine canal using cone-beam computed tomography. Imaging Sci Dent. 2013;43(4):273–81. (PMID: 10.5624/isd.2013.43.4.273243800673873316)
Kwak GH, Kwak E-J, Song JM, Park HR, Jung Y-H, Cho B-H, Hui P, Hwang JJ. Automatic mandibular canal detection using a deep convolutional neural network. Sci Rep. 2020;10(1):5711. (PMID: 10.1038/s41598-020-62586-8322358827109125)
Oliveira-Santos N, Jacobs R, Picoli FF, Lahoud P, Niclaes L, Groppo FC. Automated segmentation of the mandibular canal and its anterior loop by deep learning. Sci Rep. 2023;13(1):10819. (PMID: 10.1038/s41598-023-37798-33740278410319881)
Dasanayaka C, Dharmasena B, Bandara WR, Dissanayake MB, Jayasinghe R. Segmentation of mental foramen in dental panoramic tomography using deep learning. In: 2019 14th conference on industrial and information systems (ICIIS). 2019.
Kats L, Vered M, Blumer S, Kats E. Neural network detection and segmentation of mental foramen in panoramic imaging. J Clin Pediatr Dent. 2020;44(3):168–73. (PMID: 10.17796/1053-4625-44.3.632552450)
Raza H, Ali M, Singh VK, Wahjuningrum A, Sarig R, Chaurasia A. Segmentation of mental foramen in orthopantomographs: a deep learning approach. 2024. arXiv:2408.04763 .
Weitere Informationen
Aim: Cone-beam computed tomography (CBCT) imaging plays a crucial role in dentistry, with automatic prediction of anatomical structures on CBCT images potentially enhancing diagnostic and planning procedures. This study aims to predict anatomical structures automatically on CBCT images using a deep learning algorithm.
Materials and Methods: CBCT images from 70 patients were analyzed. Anatomical structures were annotated using a regional segmentation tool within an annotation software by two dentomaxillofacial radiologists. Each volumetric dataset comprised 405 slices, with relevant anatomical structures marked in each slice. Seventy DICOM images were converted to Nifti format, with seven reserved for testing and the remaining sixty-three used for training. The training utilized nnUNetv2 with an initial learning rate of 0.01, decreasing by 0.00001 at each epoch, and was conducted for 1000 epochs. Statistical analysis included accuracy, Dice score, precision, and recall results.
Results: The segmentation model achieved an accuracy of 0.99 for nasal fossa, maxillary sinus, nasopalatine canal, mandibular canal, foramen mentale, and foramen mandible, with corresponding Dice scores of 0.85, 0.98, 0.79, 0.73, 0.78, and 0.74, respectively. Precision values ranged from 0.73 to 0.98. Maxillary sinus segmentation exhibited the highest performance, while mandibular canal segmentation showed the lowest performance.
Conclusion: The results demonstrate high accuracy and precision across most structures, with varying Dice scores indicating the consistency of segmentation. Overall, our segmentation model exhibits robust performance in delineating anatomical features in CBCT images, promising potential applications in dental diagnostics and treatment planning.
(© 2025. The Author(s) under exclusive licence to Japanese Society for Oral and Maxillofacial Radiology.)
Declarations. Conflict of interest: The authors declare no financial or non-financial conflicts of interest relevant to this study. Ethical approval: This study was conducted in accordance with the principles outlined in the 1964 Helsinki Declaration concerning medical research ethics. The research received approval from the non-interventional Clinical Research Ethical Committee of Eskisehir Osmangazi University approved the study protocol (decision no. 04.10.2022/22). Informed consent: Informed consent was not required for this study, as all imaging data were fully anonymized prior to analysis. The study design ensures that no identifiable information about participants is retained, thereby adhering to ethical standards and privacy regulations.