Accuracy of tooth segmentation algorithm based on deep learning

doi:10.19439/j.sjos.2024.04.002

Abstract

Abstract: PURPOSE: The established automatic AI tooth segmentation algorithm was used to achieve rapid and automatic tooth segmentation from CBCT images. The three-dimensional data obtained by oral scanning of real isolated teeth were used as the gold standard to verify the accuracy of the algorithm. METHODS: Thirty sets of CBCT data and corresponding 59 isolated teeth were collected from Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine. The three-dimensional tooth data in CBCT images were segmented by the algorithm. The digital information obtained by scanning the extracted teeth after processing was used as the gold standard. In order to compare the difference between the segmentation results and the scanning results of the algorithm. The Dice coefficient(Dice), sensitivity (Sen) and average symmetric surface distance (ASSD) were selected to evaluate the segmentation accuracy of the algorithm. The intra-class correlation coefficient(ICC) was used to evaluate the differences in length, area, and volume between the single tooth obtained by the AI system and the digital isolated tooth. Due to the existence of CBCT with different resolution, ANOVA was used to analyze the differences between groups with different resolution, and SNK method was used to compare them between two groups. SPSS 25.0 software package was used to analyze the data. RESULTS: After comparing the segmentation results with the in vitro dental scanning results, the average Dice value was (94.7±1.88)%, the average Sen was (95.8±2.02)%, and the average ASSD was (0.49±0.12) mm. By comparing the length, area and volume of a single tooth obtained by the digital isolated tooth and the AI system, the ICC values of the intra-group correlation coefficients were 0.734, 0.719 and 0.885, respectively. The single tooth divided by the AI system has a good consistency with the digital model in evaluating the length, area and volume, but the segmentation results were still different from the real situation in terms of specific values. The smaller the voxel of CBCT, the higher the resolution, the better the segmentation results. CONCLUSIONS: The CBCT tooth segmentation algorithm established in this study can accurately achieve the tooth segmentation of the whole dentition in CBCT at all resolutions. The improvement of CBCT resolution ratio can make the algorithm more accurate. Compared with the current segmentation algorithms, our algorithm has better performance. Compared with the real situation, there are still some differences, and the algorithm needs to be further improved and verified.

Key words: Artificial intelligence, Cone-beam CT, Tooth Segmentation, Accuracy

CLC Number:

R781.05

ZHANG Bo-jun, CUI Zhi-ming, LIU Zhi-xu, CHEN Si-yue, GU Kai-jun, LI Si-tong, WU Yan-qi, SHEN Ding-gang, ZHU Min. Accuracy of tooth segmentation algorithm based on deep learning[J]. Shanghai Journal of Stomatology, 2024, 33(4): 339-344.

References

[1] 巩汉顺, 徐伟, 徐寿平, 等. 不同扫描条件下CBCT影像质量及其HU值长期稳定性分析[J].中国医疗器械杂志, 2016, 40(2): 86-89, 94.
[2] Chung M, Lee M, Hong J, et al.Pose-aware instance segmentation framework from cone beam CT images for tooth segmentation[J]. Comput Biol Med, 2020, 120: 103720.
[3] Cui Z, Li C, Wang W.ToothNet: automatic tooth instance segmentation and identification from cone beam CT images[C]. Proc IEEE/CVF Conf Comput Vis Pattern Recognit(CVPR), 2019: 6361-6370.
[4] 赵一姣, 王斯维, 刘怡, 等. 基于影像学牙周膜解剖特征快速提取活体牙三维牙根形态的方法[J]. 北京大学学报(医学版), 2017, 49(1): 54-59.
[5] Lee RJ, Pi S, Park J, et al.Accuracy and reliability of the expected root position setup methodology to evaluate root position during orthodontic treatment[J]. Am J Orthod Dentofacial Orthop, 2018, 154(4): 583-595.
[6] Gao H, Chae O.Individual tooth segmentation from CT images using level set method with shape and intensity prior[J]. Pattern Recognit, 2010, 43(7): 2406-2417.
[7] Gan Y, Xia Z, Xiong J, et al.Tooth and alveolar bone segmentation from dental computed tomography images[J]. IEEE J Biomed Health Inform, 2017, 22(1): 196-204.
[8] Evain T, Ripoche X, Atif J, et al.Semi-automatic teeth segmentation in cone-beam computed tomography by graph-cut with statistical shape priors[C]. 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017), 2017: 1197-1200.
[9] Jang TJ, Kim KC, Cho HC, et al.A fully automated method for 3D individual tooth identification and segmentation in dental CBCT[J]. IEEE Trans Pattern Anal Mach Intell, 2022, 44(10): 6562-6568.
[10] Chen Y, Du H, Yun Z, et al.Automatic segmentation of individual tooth in dental CBCT images from tooth surface map by a multi-task FCN[J]. IEEE Access, 2020, 8: 97296-97309.
[11] Wu X, Chen H, Huang Y, et al.Center-sensitive and boundary-aware tooth instance segmentation and classification from cone-beam CT[C]. 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI), 2020: 939-942.
[12] Yang Y, Xie R, Jia W, et al.Accurate and automatic tooth image segmentation model with deep convolutional neural networks and level set method[J]. Neurocomputing, 2021, 419: 108-125.
[13] Cui Z, Zhang B, Lian C, et al.Hierarchical morphology-guided tooth instance segmentation from CBCT images[C]. Information Processing in Medical Imaging: 27th International Conference, 2021: 150-162.
[14] Cui Z, Fang Y, Mei L, et al.A fully automatic AI system for tooth and alveolar bone segmentation from cone-beam CT images[J]. Nat Commun, 2022, 13(1): 2096.
[15] Róth I, Czigola A, Fehér D, et al.Digital intraoral scanner devices: a validation study based on common evaluation criteria[J]. BMC Oral Health, 2022, 22(1): 140-156.
[16] Chiu A, Chen YW, Hayashi J, et al.Accuracy of CAD/CAM digital impressions with different intraoral scanner parameters[J]. Sensors(Basel), 2020, 20(4): 1157-1166.
[17] Christopoulou I, Kaklamanos EG, Makrygiannakis MA, et al.Intraoral scanners in orthodontics: a critical review[J]. Int J Environ Res Public Health, 2022, 19(3): 1407-1418.
[18] Kihara H, Hatakeyama W, Komine F, et al.Accuracy and practicality of intraoral scanner in dentistry: a literature review[J]. J Prosthodont Res, 2020, 64(2): 109-113.
[19] Tomita Y, Uechi J, Konno M, et al.Accuracy of digital models generated by conventional impression/plaster-model methods and intraoral scanning[J]. Dent Mater J, 2018, 37(4): 628-633.
[20] Gavounelis NA, Gogola CC, Halazonetis DJ.The effect of scanning strategy on intraoral scanner's accuracy[J]. Dent J, 2022, 10(7): 123-133.
[21] 林翔, 傅裕杰, 任根强, 等. U-Net神经网络分割锥形束CT影像中下颌磨牙牙体与牙髓腔及其准确性验证[J]. 上海口腔医学, 2022, 31(5): 454-459.
[22] Abramson Z, Susarla SM, Lawler M, et al.Three-dimensional computed tomographic airway analysis of patients with obstructive sleep apnea treated by maxillomandibular advancement[J]. J Oral Maxillofac Surg, 2011, 69(3): 677-686.
[23] Honey OB, Scarfe WC, Hilgers MJ, et al.Accuracy of cone-beam computed tomography imaging of the temporomandibular joint: comparisons with panoramic radiology and linear tomography[J]. Am J Orthod Dentofacial Orthop, 2007, 132(4): 429-438.
[24] Schubert M, Proff P, Kirschneck C.Improved eruption path quantification and treatment time prognosis in alignment of impacted maxillary canines using CBCT imaging[J]. Eur J Orthod, 2018, 40(6): 597-607.
[25] 程涛. 口腔正畸治疗中牙根吸收的研究进展[J]. 临床口腔医学杂志, 2016, 32(1) : 59-61.
[26] Pei Y, Ai X, Zha H, et al.3D exemplar-based random walks for tooth segmentation from cone-beam computed tomography images[J]. Med Phys, 2016, 43(9): 5040-5050.
[27] Lahoud P, EzEldeen M, Beznik T, et al. Artificial intelligence for fast and accurate 3-dimensional tooth segmentation on cone-beam computed tomography[J]. J Endod, 2021, 47(5): 827-835.
[28] Ayidh Alqahtani K, Jacobs R, Smolders A, et al.Deep convolutional neural network-based automated segmentation and classification of teeth with orthodontic brackets on cone-beam computed-tomographic images: a validation study[J]. Eur J Orthod, 2023, 45(2): 169-174.