Application of deep learning in isolated tooth identification.
Artificial intelligence
Deep learning
Image classification
Image set classification
Tooth identification
Journal
BMC oral health
ISSN: 1472-6831
Titre abrégé: BMC Oral Health
Pays: England
ID NLM: 101088684
Informations de publication
Date de publication:
09 May 2024
09 May 2024
Historique:
received:
18
12
2023
accepted:
18
04
2024
medline:
10
5
2024
pubmed:
10
5
2024
entrez:
9
5
2024
Statut:
epublish
Résumé
Teeth identification has a pivotal role in the dental curriculum and provides one of the important foundations of clinical practice. Accurately identifying teeth is a vital aspect of dental education and clinical practice, but can be challenging due to the anatomical similarities between categories. In this study, we aim to explore the possibility of using a deep learning model to classify isolated tooth by a set of photographs. A collection of 5,100 photographs from 850 isolated human tooth specimens were assembled to serve as the dataset for this study. Each tooth was carefully labeled during the data collection phase through direct observation. We developed a deep learning model that incorporates the state-of-the-art feature extractor and attention mechanism to classify each tooth based on a set of 6 photographs captured from multiple angles. To increase the validity of model evaluation, a voting-based strategy was applied to refine the test set to generate a more reliable label, and the model was evaluated under different types of classification granularities. This deep learning model achieved top-3 accuracies of over 90% in all classification types, with an average AUC of 0.95. The Cohen's Kappa demonstrated good agreement between model prediction and the test set. This deep learning model can achieve performance comparable to that of human experts and has the potential to become a valuable tool for dental education and various applications in accurately identifying isolated tooth.
Sections du résumé
BACKGROUND
BACKGROUND
Teeth identification has a pivotal role in the dental curriculum and provides one of the important foundations of clinical practice. Accurately identifying teeth is a vital aspect of dental education and clinical practice, but can be challenging due to the anatomical similarities between categories. In this study, we aim to explore the possibility of using a deep learning model to classify isolated tooth by a set of photographs.
METHODS
METHODS
A collection of 5,100 photographs from 850 isolated human tooth specimens were assembled to serve as the dataset for this study. Each tooth was carefully labeled during the data collection phase through direct observation. We developed a deep learning model that incorporates the state-of-the-art feature extractor and attention mechanism to classify each tooth based on a set of 6 photographs captured from multiple angles. To increase the validity of model evaluation, a voting-based strategy was applied to refine the test set to generate a more reliable label, and the model was evaluated under different types of classification granularities.
RESULTS
RESULTS
This deep learning model achieved top-3 accuracies of over 90% in all classification types, with an average AUC of 0.95. The Cohen's Kappa demonstrated good agreement between model prediction and the test set.
CONCLUSIONS
CONCLUSIONS
This deep learning model can achieve performance comparable to that of human experts and has the potential to become a valuable tool for dental education and various applications in accurately identifying isolated tooth.
Identifiants
pubmed: 38724912
doi: 10.1186/s12903-024-04274-x
pii: 10.1186/s12903-024-04274-x
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
500Informations de copyright
© 2024. The Author(s).
Références
Kondo S, Morita W, Ohshima H. The biological significance of tooth identification based on developmental and evolutional viewpoints. J Oral Biosci. 2022;64(3):287–302.
doi: 10.1016/j.job.2022.05.004
pubmed: 35598838
Risnes S, Khan Q, Hadler-Olsen E, Sehic A. Tooth identification puzzle: a method of teaching and learning tooth morphology. Eur J Dent Educ. 2019;23(1):62–7.
doi: 10.1111/eje.12403
pubmed: 30369017
Lone M, McKenna JP, Cryan JF, Downer EJ, Toulouse A. A survey of tooth morphology teaching methods employed in the United Kingdom and Ireland. Eur J Dent Educ. 2018;22(3):e438–43.
doi: 10.1111/eje.12322
pubmed: 29334421
Kaul B, Vaid V, Gupta S, Kaul S. Forensic odontological parameters as biometric tool: a review. Int J Clin Pediatr Dent. 2021;14(3):416–19.
doi: 10.5005/jp-journals-10005-1967
pubmed: 34720517
pmcid: 8543982
Petju M, Suteerayongprasert A, Thongpud R, Hassiri K. Importance of dental records for victim identification following the Indian Ocean tsunami disaster in Thailand. Public Health. 2007;121(4):251–7.
doi: 10.1016/j.puhe.2006.12.003
pubmed: 17276465
Yan J, Lou X, Xie L, Yu D, Shen G, Wang Y. Assessment of dental age of children aged 3.5 to 16.9 years using Demirjian’s method: a meta-analysis based on 26 studies. PLoS ONE. 2013;8(12):e84672.
doi: 10.1371/journal.pone.0084672
pubmed: 24367690
pmcid: 3867507
Friedrich RE, Ulbricht C, von Maydell LA, Scheuer HA. Identification of developmental stages of wisdom teeth on orthopantomograms of adolescents and young adults as an aid for forensic-odontological age-estimations: predictive values for the chronological age of 18 years. Arch Kriminol. 2005;216(3–4):73–88.
pubmed: 16274073
Boaz K, Gupta C. Dimorphism in human maxillary and madibular canines in establishment of gender. J Forensic Dent Sci. 2009; 42–4.
Reddy VM, Saxena S, Bansal P. Mandibular canine index as a sex determinant: a study on the population of western Uttar Pradesh. J Oral Maxillofac Pathol. 2008;12(2):56–9.
doi: 10.4103/0973-029X.44577
Choi GPT, Chan HL, Yong R, et al. Tooth morphometry using quasi-conformal theory. Pattern Recognit. 2020;99:107064.
doi: 10.1016/j.patcog.2019.107064
Riaud X. The dental identification of the Egyptian queen Hatshepsut. Int J Sci Res. 2016;2(1):1–3.
Turing AM. Computing Machinery and Intelligence. In: Epstein R, Roberts G, Beber G, editors. Parsing the Turing Test: philosophical and methodological issues in the Quest for the thinking computer. Dordrecht: Springer Netherlands; 2009. pp. 23–65.
doi: 10.1007/978-1-4020-6710-5_3
Yu K, Jia L, Chen Y, Xu W. Deep learning: yesterday, today, and tomorrow. J Comput Res Dev. 2013;50(9):1799–804.
Bianco S, Cadene R, Celona L, Napoletano P. Benchmark analysis of representative deep neural network architectures. IEEE Access. 2018;6:64270–7.
doi: 10.1109/ACCESS.2018.2877890
Hu Z, Cao D, Hu Y, Wang B, Zhang Y, Tang R, et al. Diagnosis of in vivo vertical root fracture using deep learning on cone-beam CT images. BMC Oral Health. 2022;22:382.
doi: 10.1186/s12903-022-02422-9
pubmed: 36064682
pmcid: 9446797
Han Y, Yarlagadda S, Ghosh T, Zhu F, Sazonov E, Delp E. Improving Food Detection for Images from a wearable egocentric camera. Electron Imaging. 2021; 286–1.
Han Y, Lei Y, Shkolnikov V, Label-Free Mammalian Cell Tracking Enhanced by Precomputed Velocity Fields. 21st IEEE International Conference on Machine Learning and, Applications et al. (ICMLA), Nassau, Bahamas, 2022, pp. 353–360.
Cui Z, Li C, Wang W. ToothNet: automatic tooth instance segmentation and identification from cone beam CT images. Proc IEEECVF Conf Comput Vis Pattern Recognit. 2019 Jun 15–20; Long Beach, CA, USA. pp. 6368–6377.
Wang L, Mao J, Hu Y, Sheng W. Tooth identification based on teeth structure feature. Syst Sci Control Eng Taylor Francis. 2020;8(1):521–33.
doi: 10.1080/21642583.2020.1825238
Chung M, Lee J, Park S, Lee M, Lee CE, Lee J, et al. Individual tooth detection and identification from dental panoramic X-ray images via point-wise localization and distance regularization. Artif Intell Med. 2021;111:101996.
doi: 10.1016/j.artmed.2020.101996
pubmed: 33461689
Li Z, Wang SH, Fan RR, Cao G, Zhang YD, Guo T. Teeth category classification via seven-layer deep convolutional neural network with max pooling and global average pooling. Int J Imaging Syst Technol. 2019;29(4):577–83.
doi: 10.1002/ima.22337
Miki Y, Muramatsu C, Hayashi T, Zhou X, Hara T, Katsumata A, Tooth labeling in cone-beam CT using deep convolutional neural network for forensic identification. Med Imaging 2017 Comput-Aided Diagn SPIE;, Orlando et al. Florida, United states. pp. 874–9.
Liu Z, Mao H, Wu CY, Feichtenhofer C, Darrell T, Xie S. A convnet for the 2020s. Proc IEEECVF Conf Comput Vis Pattern Recognit; 2022 Jun 18–24; New Orleans, LA, USA. pp. 11976–11986.
Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN et al. Attention is all you need. Proceedings of the 31st International Conference on Neural Information Processing Systems Red Hook, NY, USA: Curran Associates Inc.; 2017 Dec 4–9; Long Beach, California, USA. pp. 6000–10.
Van der Maaten L, Hinton G. Visualizing data using t-SNE. J Mach Learn Res. 2008;9(11):2579–605.
Landis JR, Koch GG. The measurement of observer agreement for categorical data. Biometrics. 1977;33(1):159–74.
doi: 10.2307/2529310
pubmed: 843571
Obrez A, Briggs C, Buckman J, Goldstein L, Lamb C, Knight WG. Teaching clinically relevant dental anatomy in the dental curriculum: description and assessment of an innovative module. J Dent Educ. 2011;75(6):797–804.
doi: 10.1002/j.0022-0337.2011.75.6.tb05108.x
pubmed: 21642526
Elgreatly A, Mahrous A. Enhancing student learning in dental anatomy by using virtual three-dimensional models. J Prosthodont. 2020;29(3):269–71.
doi: 10.1111/jopr.13152
pubmed: 32065435
Li Y, Ye H, Ye F, Liu Y, Lv L, Zhang P, et al. The current situation and future prospects of simulators in dental education. J Med Internet Res. 2021;23(4):e23635.
doi: 10.2196/23635
pubmed: 33830059
pmcid: 8063092
Lone M, Vagg T, Theocharopoulos A, Cryan JF, Mckenna JP, Downer EJ, et al. Development and assessment of a three-dimensional tooth morphology quiz for dental students. Anat Sci Educ. 2019;12(3):284–99.
doi: 10.1002/ase.1815
pubmed: 30378278
Nance ET, Lanning SK, Gunsolley JC. Dental anatomy carving computer-assisted instruction program: an assessment of student performance and perceptions. J Dent Educ. 2009;73(8):972–9.
doi: 10.1002/j.0022-0337.2009.73.8.tb04786.x
pubmed: 19648568
Thurzo A, Jančovičová V, Hain M, Thurzo M, Novák B, Kosnáčová H, et al. Human remains identification using Micro-CT, Chemometric and AI methods in Forensic Experimental Reconstruction of Dental patterns after concentrated sulphuric acid significant impact. Molecules. 2022;27(13):4035.
doi: 10.3390/molecules27134035
pubmed: 35807281
pmcid: 9268125
Minaee S, Boykov Y, Porikli F, Plaza A, Kehtarnavaz N, Terzopoulos D. Image segmentation using deep learning: a Survey. IEEE Trans Pattern Anal Mach Intell. 2022;44:3523–42.
pubmed: 33596172
Gui J, Sun Z, Wen Y, Tao D, Ye J. A review on generative adversarial networks: algorithms, theory, and applications. IEEE Trans Knowl Data Eng. 2023;35:3313–32.
doi: 10.1109/TKDE.2021.3130191
Bozkurt MH, Karagol S. Jaw and teeth segmentation on the panoramic X-ray images for dental human identification. J Digit Imaging Springer. 2020;33(6):1410–27.
doi: 10.1007/s10278-020-00380-8
Chandrashekar G, AlQarni S, Bumann EE, Lee Y. Collaborative deep learning model for tooth segmentation and identification using panoramic radiographs. Comput Biol Med Elsevier. 2022;148:105829.
doi: 10.1016/j.compbiomed.2022.105829
Jang TJ, Kim KC, Cho HC, Seo JK. A fully automated method for 3D individual tooth identification and segmentation in dental CBCT. IEEE Trans Pattern Anal Mach Intell. 2022;44(10):6562–8.
doi: 10.1109/TPAMI.2021.3086072
pubmed: 34077356
Eliášová H, Dostálová T. 3D multislice and cone-beam computed tomography systems for dental identification. Prague Med Rep. 2017;118(1):14–25.
doi: 10.14712/23362936.2017.2
pubmed: 28364571
Zhao Y, Zhang L, Liu Y, Meng D, Cui Z, Gao C, et al. Two-stream graph convolutional network for intra-oral scanner image segmentation. IEEE Trans Med Imaging IEEE. 2021;41(4):826–35.
doi: 10.1109/TMI.2021.3124217
Ben-Hamadou A, Smaoui O, Chaabouni-Chouayakh H, Rekik A, Pujades S, Boyer E et al. Teeth3DS: a benchmark for teeth segmentation and labeling from intra-oral 3D scans. ArXiv Prepr 2022; 2210.06094.
Miki Y, Muramatsu C, Hayashi T, Zhou X, Hara T, Katsumata A, et al. Classification of teeth in cone-beam CT using deep convolutional neural network. Comput Biol Med. 2017;80:24–9.
doi: 10.1016/j.compbiomed.2016.11.003
pubmed: 27889430