Image segmentation of impacted mesiodens using deep learning

This study aimed to evaluate the performance of deep learning algorithms for the classification and segmentation of impacted mesiodens in pediatric panoramic radiographs. A total of 850 panoramic radiographs of pediatric patients (aged 3–9 years) was included in this study. The U-Net semantic segmentation algorithm was applied for the detection and segmentation of mesiodens in the upper anterior region. For enhancement of the algorithm, pre-trained ResNet models were applied to the encoding path. The segmentation performance of the algorithm was tested using the Jaccard index and Dice coefficient. The diagnostic accuracy, precision, recall, F1-score and time to diagnosis of the algorithms were compared with those of human expert groups using the test dataset. Cohen’s kappa statistics were compared between the model and human groups. The segmentation model exhibited a high Jaccard index and Dice coefficient (>90%). In mesiodens diagnosis, the trained model achieved 91–92% accuracy and a 94–95% F1-score, which were comparable with human expert group results (96%). The diagnostic duration of the deep learning model was 7.5 seconds, which was significantly faster in mesiodens detection compared to human groups. The agreement between the deep learning model and human experts is moderate (Cohen’s kappa = 0.767). The proposed deep learning algorithm showed good segmentation performance and approached the performance of human experts in the diagnosis of mesiodens, with a significantly faster diagnosis time.

Artificial intelligence; Mesiodens; Deep learning; U-Net; Semantic segmentation; Panoramic radiography

[1] Perschbacher S. Interpretation of panoramic radiographs. Australian Dental Journal. 2012; 57: 40–45.

[2] Leite AF, Gerven AV, Willems H, Beznik T, Lahoud P, Gaêta-Araujo H, et al. Artificial intelligence-driven novel tool for tooth detection and segmentation on panoramic radiographs. Clinical Oral Investigations. 2021; 25: 2257–2267.

[3] Asaumi J, Hisatomi M, Yanagi Y, Unetsubo T, Maki Y, Matsuzaki H, et al. Evaluation of panoramic radiographs taken at the initial visit at a department of paediatric dentistry. Dentomaxillofacial Radiology. 2008; 37: 340–343.

[4] Omer RS, Anthonappa RP, King NM. Determination of the optimum time for surgical removal of unerupted anterior supernumerary teeth. Pediatric Dentistry. 2010; 32: 14–20.

[5] Rajab LD, Hamdan MAM. Supernumerary teeth: review of the literature and a survey of 152 cases. International Journal of Paediatric Dentistry. 2002; 12: 244–254.

[6] Ata-Ali F, Ata-Ali J, Penarrocha-Oltra D, Penarrocha-Diago M. Prevalence, etiology, diagnosis, treatment and complications of supernumerary teeth. Journal of Clinical and Experimental Dentistry. 2014; 6: e414–e418.

[7] Asaumi J, Shibata Y, Yanagi Y, Hisatomi M, Matsuzaki H, Konouchi H, et al. Radiographic examination of mesiodens and their associated complications. Dentomaxillofacial Radiology. 2004; 33: 125–127.

[8] Kim SG, Lee SH. Mesiodens: a clinical and radiographic study. Journal of Dentistry for Children. 2003; 70: 58–60.

[9] Mukhopadhyay S. Mesiodens: a clinical and radiographic study in children. Journal of Indian Society of Pedodontics and Preventive Dentistry. 2011; 29: 34–38.

[10] Ayers E, Kennedy D, Wiebe C. Clinical recommendations for management of mesiodens and unerupted permanent maxillary central incisors. European Archives of Paediatric Dentistry. 2014; 15: 421–428.

[11] Shen D, Wu G, Suk H. Deep learning in medical image analysis. Annual Review of Biomedical Engineering. 2017; 19: 221–248.

[12] Esteva A, Chou K, Yeung S, Naik N, Madani A, Mottaghi A, et al. Deep learning-enabled medical computer vision. npj Digital Medicine. 2021; 4: 5.

[13] Wang J, Zhu H, Wang S, Zhang Y. A review of deep learning on medical image analysis. Mobile Networks and Applications. 2021; 26: 351–380.

[14] Bayraktar Y, Ayan E. Diagnosis of interproximal caries lesions with deep convolutional neural network in digital bitewing radiographs. Clinical Oral Investigations. 2022; 26: 623–632.

[15] Cejudo JE, Chaurasia A, Feldberg B, Krois J, Schwendicke F. Classification of dental radiographs using deep learning. Journal of Clinical Medicine. 2021; 10: 1496.

[16] Cantu AG, Gehrung S, Krois J, Chaurasia A, Rossi JG, Gaudin R, et al. Detecting caries lesions of different radiographic extension on bitewings using deep learning. Journal of Dentistry. 2020; 100: 103425.

[17] Lee JH, Jeong SN. Efficacy of deep convolutional neural network algorithm for the identification and classification of dental implant systems, using panoramic and periapical radiographs: a pilot study. Medicine. 2020; 99: e20787.

[18] Lee S, Oh SI, Jo J, Kang S, Shin Y, Park JW. Deep learning for early dental caries detection in bitewing radiographs. Scientific Reports. 2021; 11: 16807.

[19] Wang P, Chen P, Yuan Y, Liu D, Huang Z, Hou X, et al. Understanding convolution for semantic segmentation. 2018 IEEE Winter Conference on Applications of Computer Vision. IEEE: Lake Tahoe. 2018.

[20] Jiang F, Grigorev A, Rho S, Tian Z, Fu Y, Jifara W, et al. Medical image semantic segmentation based on deep learning. Neural Computing and Applications. 2018; 29: 1257–1265.

[21] Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation. Lecture Notes in Computer Science. 2015; 1: 234–241.

[22] Du G, Cao X, Liang J, Chen X, Zhan Y. Medical image segmentation based on U-Net: a review. Journal of Imaging Science & Technology. 2020; 64: 1–12.

[23] Jaccard P. The distribution of the flora in the alpine zone. New Phytologist. 1912; 11: 37–50.

[24] Sorenson T. A method of establishing groups of equal amplitude in plant sociology based on similarity of species content, and its application to analysis of vegetation on Danish commons. Kongelige Danske Videnskabernes Selskab, Biologiske Skrifter. 1948; 5: 1–34.

[25] Howard J, Gugger S. Fastai: a layered API for deep learning. Information. 2020; 11: 108.

[26] Landis JR, Koch GG. The measurement of observer agreement for categorical data. Biometrics. 1977; 33: 159–174.

[27] Matteson SR, Lupton CR, Morrison WS. Effect of panoramic focal trough topography on radiographic imaging of supernumerary teeth in the anterior region. Journal of Oral and Maxillofacial Surgery. 1982; 40: 318–319.

[28] Itaya S, Oka K, Kagawa T, Oosaka Y, Ishii K, Kato Y, et al. Diagnosis and management of mesiodens based on the investigation of its position using cone-beam computed tomography. Pediatric Dental Journal. 2016; 26: 60–66.

[29] Ahn Y, Hwang JJ, Jung YH, Jeong T, Shin J. Automated mesiodens classification system using deep learning on panoramic radiographs of children. Diagnostics. 2021; 11: 1477.

[30] Kim J, Hwang JJ, Jeong T, Cho B, Shin J. Deep learning-based identification of mesiodens using automatic maxillary anterior region estimation in panoramic radiography of children. Dentomaxillofacial Radiology. 2022; 51: 20210528.

[31] Ha EG, Jeon KJ, Kim YH, Kim JY, Han SS. Automatic detection of mesiodens on panoramic radiographs using artificial intelligence. Scientific Reports. 2021; 11: 23061.

[32] Arora S, Tripathy SK, Gupta R, Srivastava R. Exploiting multimodal CNN architecture for automated teeth segmentation on dental panoramic X-ray images. Proceedings of the Institution of Mechanical Engineers, Part H: Journal of Engineering in Medicine. 2023; 237: 395–405.

[33] Lee J, Han S, Kim YH, Lee C, Kim I. Application of a fully deep convolutional neural network to the automation of tooth segmentation on panoramic radiographs. Oral Surgery, Oral Medicine, Oral Pathology and Oral Radiology. 2020; 129: 635–642.

[34] Bayrakdar IS, Orhan K, Akarsu S, Çelik Ö, Atasoy S, Pekince A, et al. Deep-learning approach for caries detection and segmentation on dental bitewing radiographs. Oral Radiology. 2022; 38: 468–479.

[35] Ying S, Wang B, Zhu H, Liu W, Huang F. Caries segmentation on tooth X-ray images with a deep network. Journal of Dentistry. 2022; 119: 104076.

[36] Vinayahalingam S, Xi T, Bergé S, Maal T, de Jong G. Automated detection of third molars and mandibular nerve by deep learning. Scientific Reports. 2019; 9: 9007.

[37] Oztekin F, Katar O, Sadak F, Aydogan M, Yildirim TT, Plawiak P, et al. Automatic semantic segmentation for dental restorations in panoramic radiography images using U-Net model. International Journal of Imaging Systems and Technology. 2022; 32: 1990–2001.

[38] Zhu H, Yu H, Zhang F, Cao Z, Wu F, Zhu F. Automatic segmentation and detection of ectopic eruption of first permanent molars on panoramic radiographs based on nnU-Net. International Journal of Paediatric Dentistry. 2022; 32: 785–792.