Preliminary Study on Automatic Localization and Multiplanar Reconstruction of CBCT Images of Bilateral Temporomandibular Joints

doi:10.13701/j.cnki.kqyxyj.2025.03.005

Abstract

Abstract: Objective: To develop an algorithm for automatic localization and multiplanar reconstruction of temporomandibular joint (TMJ) on cone beam computed tomography (CBCT) images and to verify its accuracy and stability. Methods: In this study, the algorithm development included: (1) the maxillary and mandibular boundary lines were obtained with maximum density projection (MIP) on CBCT images; (2) the dental arch control points line was obtained with axial MIP and branch points deletion; (3) the endpoints on both sides of the dental arch line were the center points of the bilateral temporomandibular joints, and the sagittal and coronal reconstruction images of the temporomandibular joints were obtained with average intensity projection (AIP). Totally 190 CBCT image data from 3 different CBCT brands in our hospital were selected and imported into the developed software for automatic localization and multiplanar reconstruction of bilateral TMJs. Scoring were performed by 2 oral and dento-maxillofacial radiologists, the scoring was based on the results of automatic localization of condyle with maximum diameter, automatic sagittal and cortical reconstruction of bilateral TMJs respectively (0-4 scores). After 3 months, 30 CBCT images were randomly selected and imported into the software again for automatic localization and reconstruction, and the stability of the software was evaluated. Results: The algorithm developed in this study was able to automatic localize and reconstruct bilateral TMJs. The mean scores of automatic localizations and multiplanar reconstruction of bilateral TMJs were 3.33, 3.13, and 3.51 for 3 different CBCT devices’ images, respectively. There were no significant differences among them (P>0.05). And the algorithm showed perfect stability (Kappa=1). Conclusion: The algorithm based on maximum density projection and mean density projection could be used for automatic localization and multiplanar reconstruction of TMJs on different brands of CBCT images.

Key words: temporomandibular joint, cone-beam CT, automatic localization, automatic multiplanar reconstruction

XIE Xin, WANG Chengtao, PAN Xiao, DONG Qi, CHEN Ying, ZHANG Wentao, LIN Zitong. Preliminary Study on Automatic Localization and Multiplanar Reconstruction of CBCT Images of Bilateral Temporomandibular Joints[J]. Journal of Oral Science Research, 2025, 41(3): 200-206.

References

[1] Wang YH, Ma RH, Li JJ, et al. Diagnostic efficacy of CBCT, MRI and CBCT-MRI fused images in determining anterior disc displacement and bone changes of temporomandibular joint[J].Dentomaxillofac Radiol, 2022, 51(2):20210286.
[2] Chen Y, Li L, Li Y, et al. Comprehensive positional and morphological assessments of the temporomandibular joint in adolescents with skeletal Class Ⅲ malocclusion: a retrospective CBCT study[J].BMC Oral Health, 2023, 23(1): 78.
[3] Görürgöz C, içen M, Kurt MH, et al. Degenerative changes of the mandibular condyle in relation to the temporomandibular joint space, gender and age: A multicenter CBCT study[J].Dent Med Probl, 2023, 60(1): 127-135.
[4] Yu W, Jeon HH, Kim S, et al. Correlation between TMJ space alteration and disc displacement: A retrospective CBCT and MRI study[J].Diagnostics (Basel), 2023, 14(1):44.
[5] 傅开元,胡敏,余强,等.颞下颌关节紊乱病锥形束CT检查规范及诊断标准的专家共识[J].中华口腔医学杂志,2020,55(9): 613-616.
[6] Yap AU, Lei J, Zhang XH, et al. TMJ degenerative joint disease: relationships between CBCT findings, clinical symptoms, and signs[J].Acta Odontol Scand, 2023, 81(7): 562-568.
[7] Fischer J, Augdal TA, Angenete O, et al. In children and adolescents with temporomandibular disorder assembled with juvenile idiopathic arthritis-no association were found between pain and TMJ deformities using CBCT[J].BMC Oral Health, 2021, 21(1): 518.
[8] 韩生伟,韩伟.人工智能技术在口腔医学领域的应用进展[J].口腔医学研究,2020,36(6): 519-522.
[9] Yilmaz E, Kayikcioglu T, Kayipmaz S. Computer-aided diagnosis of periapical cyst and keratocystic odontogenic tumor on cone beam computed tomography[J].Comput Methods Programs Biomed, 2017, 146: 91-100.
[10] Sunny S, Baby A, James BL, et al. A smart tele-cytology point-of-care platform for oral cancer screening[J].PLoS One, 2019, 14(11): e0224885.
[11] Setzer FC, Shi KJ, Zhang Z, et al. Artificial intelligence for the computer-aided detection of periapical lesions in cone-beam computed tomographic images[J].J Endod, 2020, 46(7): 987-993.
[12] Amasya H, Yildirim D, Aydogan T, et al. Cervical vertebral maturation assessment on lateral cephalometric radiographs using artificial intelligence: comparison of machine learning classifier models[J].Dentomaxillofac Radiol, 2020, 49(5): 20190441.
[13] Vinayahalingam S, Berends B, Baan F, et al. Deep learning for automated segmentation of the temporomandibular joint[J].J Dent, 2023, 132: 104475.
[14] Kim YH, Shin JY, Lee A, et al. Automated cortical thickness measurement of the mandibular condyle head on CBCT images using a deep learning method[J].Sci Rep, 2021, 11(1):14852.
[15] Talaat WM, Shetty S, Al Bayatti S, et al. An artificial intelligence model for the radiographic diagnosis of osteoarthritis of the temporomandibular joint[J].Sci Rep, 2023, 13(1): 15972.
[16] Kazimierczak W, Kędziora K, Janiszewska-Olszowska J, et al. Noise-optimized CBCT imaging of temporomandibular joints-The impact of AI on image quality[J].J Clin Med, 2024, 13(5):1502.
[17] Bueno MR, Estrela C, Granjeiro JM, et al. Cone-beam computed tomography cinematic rendering: clinical, teaching and research applications[J].Braz Oral Res, 2021, 35: e024.