Reference Areas Selection Affects Registration of AI-Segmented Mandibles Acquired With CBCT
DOI:
https://doi.org/10.5566/ias.3289Keywords:
Cone-beam computed tomography, deep learning, dental models, Partial Denture, Computer assisted image processing, Three-dimensional imagingAbstract
Precise registration of sequential 3D datasets is crucial for accurate dimensional analysis. Utilizing the Local Best-Fit (LBF) algorithm and stable Registration Reference Areas (RRAs) facilitates the accurate alignment of 3D surface models. Currently, Cone-beam Computed Tomography (CBCT) and Deep Learning (DL) algorithms are at the forefront for segmenting CBCT scans to monitor morphological changes in the residual alveolar ridge. This study compares the effectiveness of different RRAs in registration sequential 3D surface models of partially edentulous mandibles. DL-assisted software segmented two sequential CBCTs (T0 and T1) from 10 patients, producing sequential 3D mandibular models. These models were aligned using three distinct RRAs: (i) WHOLE, encompassing the entire surface model; (ii) MND_BODY, covering the mandibular body while excluding the unstable alveolar ridge; and (iii) SPIN_FOR, incorporating stable RRAs (mental foramina and mental spine). An innovative method assessed registration accuracy by generating centroids from cross-sectional outlines of the mandibular nerve canals at the anterior third (A), medial third (B), and posterior third (C) of the posterior edentulous areas. The distance between centroids at T0 and T1 quantified registration accuracy. The MND_BODY group exhibited superior accuracy, whereas the SPIN_FOR group showed the least, with accuracy decreasing from A to C, suggesting rotational misalignments. When selecting RRAs, both stability and spatial distribution must be taken into account. For optimal alignment, sequential 3D surface models should use RRAs that are both stable and widely distributed.
References
Ahmad R, Abu-Hassan MI, Li Q, Swain M V. 2013. Three dimensional quantification of mandibular bone remodeling using standard tessellation language registration based superimposition. Clin Oral Implants Res. 24(11):1273–79.
Besl PJ, McKay ND. 1992. A method for registration of 3-D shapes. IEEE Trans Pattern Anal Mach Intell. 14(2):239–56.
Cui Z, Fang Y, Mei L, Zhang B, Yu B, Liu J, Jiang C, Sun Y, Ma L, Huang J, et al. 2022. A fully automatic AI system for tooth and alveolar bone segmentation from cone-beam CT images. Nat Commun. 13(1).
Friot-Giroux L, Peyrin F, Maxim V. 2022. Iterative tomographic reconstruction with TV prior for low-dose CBCT dental imaging. Phys Med Biol. 67(20).
Garikano X, Amezua X, Iturrate M, Solaberrieta E. 2024. Evaluation of repeatability of different alignment methods to obtain digital interocclusal records: An in vitro study. J Prosthet Dent. 131(4):709–17.
Häner ST, Kanavakis G, Matthey F, Gkantidis N. 2020. Voxel-based superimposition of serial craniofacial CBCTs: Reliability, reproducibility and segmentation effect on hard-tissue outcomes. Orthod Craniofac Res. 23(1):92–101.
Hodson TO. 2022. Root-mean-square error (RMSE) or mean absolute error (MAE): when to use them or not. Geosci Model Dev. 15(14):5481–87.
Joda T, Gallucci GO, Wismeijer D, Zitzmann NU. 2019. Augmented and virtual reality in dental medicine: A systematic review. Comput Biol Med. 108:93–100.
Koerich L, Burns D, Weissheimer A, Claus JDP. 2016. Three-dimensional maxillary and mandibular regional superimposition using cone beam computed tomography: a validation study. Int J Oral Maxillofac Surg. 45(5):662–69.
Kondo T, Kanayama K, Egusa H, Nishimura I. 2023. Current perspectives of residual ridge resorption: Pathological activation of oral barrier osteoclasts. J Prosthodont Res. 67(1):12–22.
Kuralt M, Fidler A. 2021. Assessment of reference areas for superimposition of serial 3D models of patients with advanced periodontitis for volumetric soft tissue evaluation. J Clin Periodontol. 48(6):765–73.
Kuralt M, Gašperšič R, Fidler A. 2020. 3D computer-aided treatment planning in periodontology: A novel approach for evaluation and visualization of soft tissue thickness. Journal of Esthetic and Restorative Dentistry. 32(5):457–62.
Kuralt M, Selmani Bukleta M, Kuhar M, Fidler A. 2019. Bone and soft tissue changes associated with a removable partial denture. A novel method with a fusion of CBCT and optical 3D images. Comput Biol Med. 108:78–84.
Kuralt M, Selmani Bukleta M, Kuhar M, Fidler A. 2022. A NOVEL DIGITAL METHOD FOR EVALUATION OF MUCOSA THICKNESS CHANGES IN TIME: CHANGES ASSOCIATED WITH A REMOVABLE PARTIAL DENTURE. Image Analysis & Stereology. 41:181–91.
Lahoud P, Diels S, Niclaes L, Van Aelst S, Willems H, Van Gerven A, Quirynen M, Jacobs R. 2022. Development and validation of a novel artificial intelligence driven tool for accurate mandibular canal segmentation on CBCT. J Dent. 116:103891.
Li P, Wang R, Wang Y, Tao W. 2020. Evaluation of the ICP Algorithm in 3D Point Cloud Registration. IEEE Access. 8:68030–68048.
Liu X, Faes L, Kale AU, Wagner SK, Fu DJ, Bruynseels A, Mahendiran T, Moraes G, Shamdas M, Kern C, et al. 2019. A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: a systematic review and meta-analysis. Lancet Digit Health. 1(6):e271–97.
Ma J, Schneider L, Lapuschkin S, Achtibat R, Duchrau M, Krois J, Schwendicke F, Samek W. 2022. Towards Trustworthy AI in Dentistry. J Dent Res. 101(11):1263–68.
Mangano C, Luongo F, Migliario M, Mortellaro C, Mangano FG. 2018. Combining intraoral scans, cone beam computed tomography and face scans: The virtual patient. Journal of Craniofacial Surgery. 29(8):2241–46.
Mohammad-Rahimi H, Rokhshad R, Bencharit S, Krois J, Schwendicke F. 2023. Deep learning: A primer for dentists and dental researchers. J Dent. 130:104430.
Nguyen KCT, Duong DQ, Almeida FT, Major PW, Kaipatur NR, Pham TT, Lou EHM, Noga M, Punithakumar K, Le LH. 2020. Alveolar Bone Segmentation in Intraoral Ultrasonographs with Machine Learning. J Dent Res. 99(9):1054–61.
Nguyen T, Cevidanes L, Franchi L, Ruellas A, Jackson T. 2018. Three-dimensional mandibular regional superimposition in growing patients. American Journal of Orthodontics and Dentofacial Orthopedics. 153(5):747–54.
De Oliveira Ruellas AC, Yatabe MS, Souki BQ, Benavides E, Nguyen T, Luiz RR, Franchi L, Cevidanes LHS. 2016. 3D mandibular superimposition: Comparison of regions of reference for voxel-based registration. PLoS One. 11(6).
Oliveira-Santos N, Jacobs R, Picoli FF, Lahoud P, Niclaes L, Groppo FC. 2023. Automated segmentation of the mandibular canal and its anterior loop by deep learning. Sci Rep. 13(1):10819.
O’Toole S, Osnes C, Bartlett D, Keeling A. 2019. Investigation into the accuracy and measurement methods of sequential 3D dental scan alignment. Dental Materials. 35(3):495–500.
Ponce-Garcia C, Ruellas ACDO, Cevidanes LHS, Flores-Mir C, Carey JP, Lagravere-Vich M. 2020. Measurement error and reliability of three available 3D superimposition methods in growing patients. Head Face Med. 16(1).
Preda F, Morgan N, Van Gerven A, Nogueira-Reis F, Smolders A, Wang X, Nomidis S, Shaheen E, Willems H, Jacobs R. 2022a. Deep convolutional neural network-based automated segmentation of the maxillofacial complex from cone-beam computed tomography:A validation study. J Dent. 124.
Preda F, Morgan N, Van Gerven A, Nogueira-Reis F, Smolders A, Wang X, Nomidis S, Shaheen E, Willems H, Jacobs R. 2022b. Deep convolutional neural network-based automated segmentation of the maxillofacial complex from cone-beam computed tomography:A validation study. J Dent. 124:104238.
Revilla-León M, Gohil A, Barmak AB, Zandinejad A, Raigrodski AJ, Alonso Pérez-Barquero J. 2022. Best-Fit Algorithm Influences on Virtual Casts’ Alignment Discrepancies. Journal of Prosthodontics.
Revilla-León M, Pérez-Barquero JA, Barmak BA, Agustín-Panadero R, Fernández-Estevan L, Att W. 2021. Facial scanning accuracy depending on the alignment algorithm and digitized surface area location: An in vitro study. J Dent. 110.
Rischke R, Schneider L, Müller K, Samek W, Schwendicke F, Krois J. 2022. Federated Learning in Dentistry: Chances and Challenges. J Dent Res. 101(11):1269–73.
Schneider L, Arsiwala-Scheppach L, Krois J, Meyer-Lueckel H, Bressem KK, Niehues SM, Schwendicke F. 2022. Benchmarking Deep Learning Models for Tooth Structure Segmentation. J Dent Res. 101(11):1343–49.
Schwendicke F, Krois J. 2022. Data Dentistry: How Data Are Changing Clinical Care and Research. J Dent Res. 101(1):21–29.
Schwendicke F, Samek W, Krois J. 2020. Artificial Intelligence in Dentistry: Chances and Challenges. J Dent Res. 99(7):769–74.
Schwendicke F, Singh T, Lee JH, Gaudin R, Chaurasia A, Wiegand T, Uribe S, Krois J. 2021. Artificial intelligence in dental research: Checklist for authors, reviewers, readers. J Dent. 107.
Shaheen E, Leite A, Alqahtani KA, Smolders A, Van Gerven A, Willems H, Jacobs R. 2021. A novel deep learning system for multi-class tooth segmentation and classification on cone beam computed tomography. A validation study: Deep learning for teeth segmentation and classification. J Dent. 115.
Song P. 2015. Local voxelizer: A shape descriptor for surface registration. Comput Vis Media (Beijing). 1(4):279–89.
Spencer KR. 2018. Implant based rehabilitation options for the atrophic edentulous jaw. Aust Dent J. 63:S100–07.
Stucki S, Gkantidis N. 2020a. Assessment of techniques used for superimposition of maxillary and mandibular 3D surface models to evaluate tooth movement: A systematic review. Eur J Orthod. 42(5):559–70.
Stucki S, Gkantidis N. 2020b. Assessment of techniques used for superimposition of maxillary and mandibular 3D surface models to evaluate tooth movement: A systematic review. Eur J Orthod. 42(5):559–70.
Tallgren A. 1972. The continuing reduction of the residual alveolar ridges in complete denture wearers: A mixed-longitudinal study covering 25 years. J Prosthet Dent. 27(2):120–32.
Tan M, Cui Z, Zhong T, Fang Y, Zhang Y, Shen D. 2024. A progressive framework for tooth and substructure segmentation from cone-beam CT images. Comput Biol Med. 169:107839.
Verhelst PJ, Smolders A, Beznik T, Meewis J, Vandemeulebroucke A, Shaheen E, Van Gerven A, Willems H, Politis C, Jacobs R. 2021. Layered deep learning for automatic mandibular segmentation in cone-beam computed tomography. J Dent. 114.
Wang H, Minnema J, Batenburg KJ, Forouzanfar T, Hu FJ, Wu G. 2021. Multiclass CBCT Image Segmentation for Orthodontics with Deep Learning. J Dent Res. 100(9):943–49.
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Klemen Leopold, Aleš Fidler, Manushaqe Selmani Bukleta, Milan Kuhar
This work is licensed under a Creative Commons Attribution 4.0 International License.
