Artificial intelligence for detecting dental ankylosis in primary molars using panoramic radiographs—a retrospective study

Background: Dental ankylosis is an eruptive abnormality that requires early diagnosis to prevent complications. This study investigated the usability and performance of various deep learning models (including transfer learning, which enhances model performance by utilizing pre-trained networks) for ankylosis detection in dental X-rays. Methods: Classical convolutional neural network (CNN) method, Visual Geometry Group 16-layer (VGG16), Inception V3, and MobileNet V2 deep learning models were used for classification. In total, 268 panoramic radiograph images were diagnosed: 98 as ankylosis cases and 170 as controls, with ages ranging from 4 to 15 years. Various data augmentation techniques were employed. Accuracy, sensitivity, specificity, Area Under Curve (AUC) and F1-Score metrics were assessed to evaluate the performance of the models. Results: The CNN network without pretraining proved insufficient, leading to the adoption of transfer learning. The accuracy, AUC, sensitivity, specificity and F1-Score values of all three models can be used, but the VGG16 and Inception V3 models generally outperformed the MobileNetV2. Based on accuracy and specificity, Inception V3 demonstrated better classification performance, while VGG16 demonstrated a more balanced performance. Conclusions: This study highlights the effectiveness of deep learning models, particularly VGG16, in identifying ankylosis from panoramic radiographs, emphasizing the importance of model selection for improved diagnostic outcomes.

Ankylosis; Artificial intelligence; Deep learning; Transfer learning

[1] Eşian D, Bica CI, Stoica OE, Dako T, Vlasa A, Bud ES, et al. Prevalence and manifestations of dental ankylosis in primary molars using panoramic x-rays: a cross-sectional study. Children. 2022; 9: 188.

[2] Yoon G. Eruption guidance of horizontally impacted permanent first molar with primary retention of primary second molars. Journal of the Korean Academy of Pediatric Dentistry. 2020; 47: 219–227.

[3] Messer LB. Ankylosed primary molars: results and treatment recommendations from an eight-year longitudinal study. Pediatric Dentistry. 1980; 2: 37–47.

[4] Noble J. Diagnosis and management of the infraerupted primary molar. British Dental Journal. 2007; 203: 632–634.

[5] Hua L. To extract or not to extract? Management of infraoccluded second primary molars without successors. British Dental Journal. 2019; 227: 93–98.

[6] Wu Y, Yuan X, Perez KC, Hyman S, Wang L, Pellegrini G, et al. Aberrantly elevated Wnt signaling is responsible for cementum overgrowth and dental ankylosis. Bone. 2019; 122: 176–183.

[7] Ducommun F. Diagnosis of tooth ankylosis using panoramic views, cone beam computed tomography, and histological data: a retrospective observational case series study. European Journal of Orthodontics. 2018; 40: 231–238.

[8] Kurol J. Infraocclusion of primary molars: an epidemiologic and familial study. Community Dentistry and Oral Epidemiology. 1981; 9: 94–102.

[9] Kaya E. Proposing a CNN method for primary and permanent tooth detection and enumeration on pediatric dental radiographs. Journal of Clinical Pediatric Dentistry. 2022; 46: 293–298.

[10] Mine Y, Iwamoto Y, Okazaki S, Nakamura K, Takeda S, Peng TY, et al. Detecting the presence of supernumerary teeth during the early mixed dentition stage using deep learning algorithms: a pilot study. International Journal Paediatric Dentistry. 2022; 32: 678–685.

[11] Liu J. Artificial intelligence-aided detection of ectopic eruption of maxillary first molars based on panoramic radiographs. Journal of Dentistry. 2022; 125: 104239.

[12] Sams CM. Pediatric Panoramic radiography: techniques, artifacts, and interpretation. Radiographics. 2021; 41: 595–608.

[13] Sabbadini GD. A review of pediatric radiology. Journal of the California Dental Association. 2013; 41: 575–581, 584.

[14] Schwendicke F. Artificial intelligence for caries detection: value of data and information. Journal of Dental Research. 2022; 101: 1350–1356.

[15] 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.

[16] Kuwada C, Ariji Y, Fukuda M, Kise Y, Fujita H, Katsumata A, et al. Deep learning systems for detecting and classifying the presence of impacted supernumerary teeth in the maxillary incisor region on panoramic radiographs. Oral Surgery, Oral Medicine, Oral Pathology and Oral Radiology. 2020; 130: 464–469.

[17] 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.

[18] Takeda S. Landmark annotation and mandibular lateral deviation analysis of posteroanterior cephalograms using a convolutional neural network. Journal of Dental Sciences. 2021; 16: 957–963.

[19] Vishwanathaiah S. Artificial intelligence its uses and application in pediatric dentistry: a review. Biomedicines. 2023; 11: 788.

[20] Lee JH. Detection and diagnosis of dental caries using a deep learning-based convolutional neural network algorithm. Journal of Dentistry. 2018; 77: 106–111.

[21] Murata M, Ariji Y, Ohashi Y, Kawai T, Fukuda M, Funakoshi T, et al. Deep-learning classification using convolutional neural network for evaluation of maxillary sinusitis on panoramic radiography. Oral Radiology. 2019; 35: 301–307.

[22] Lee KS, Kwak HJ, Oh JM, Jha N, Kim YJ, Kim W, et al. Automated detection of tmj osteoarthritis based on artificial intelligence. Journal of Dental Research. 2020; 99: 1363–1367.

[23] Askar H, Krois J, Rohrer C, Mertens S, Elhennawy K, Ottolenghi L, et al. Detecting white spot lesions on dental photography using deep learning: a pilot study. Journal of Dentistry. 2021; 107: 103615.

[24] Alevizakos V. Artificial intelligence system for training diagnosis and differentiation with molar incisor hypomineralization (MIH) and similar pathologies. Clinical Oral Investigations. 2022; 26: 6917–6923.

[25] Doufexi A. Tooth ankylosis: etiology, diagnosis and treatment review and case series. European Journal of Dental and Oral Health. 2025; 6: 12–15.

[26] Hadi A. Ankylosed permanent teeth: incidence, etiology and guidelines for clinical management. Medical Dental Research. 2018; 1: 1–11.

[27] Adedigba AP. Performance evaluation of deep learning models on mammogram classification using small dataset. Bioengineering. 2022; 9: 161.

[28] Zhang J. Optimization and performance evaluation of deep learning algorithm in medical image processing. Frontiers in Computing and Intelligent Systems. 2024; 7: 67–71.

[29] Dentsply Sirona. Orthophos XG 3 digital panoramic X-ray for practical diagnostics. 2025. Available at: https://dspconnect.s3.amazonaws.com/Sirona/2Dand3DImaging/OrthophosXG3Brochure.pdf (Accessed: 30 April 2025).

[30] Hussain M, Thaher T, Almourad MB, Mafarja M. Optimizing VGG16 deep learning model with enhanced hunger games search for logo classification. Scientific Reports. 2024; 14: 31759.

[31] Szegedy C. Rethinking the inception architecture for computer vision. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, NV and 27–30 June 2016. Institute of Electrical and Electronics Engineers: Piscataway, NJ. 2016.

[32] Sandler M. Mobilenetv2: inverted residuals and linear bottlenecks. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT and 16 December 2018. Institute of Electrical and Electronics Engineers: Piscataway, NJ. 2018.

[33] Alla SSM. Brain tumor detection using transfer learning in deep learning. Indian Journal of Science and Technology. 2022; 15: 2093–2102.

[34] Aggarwal CC. Classifier performance and evaluation. In Aggarwal CC (ed.) Machine learning for text (pp. 209–234). 1st edn. Springer: Cham. 2018.

[35] Asci E, Kilic M, Celik O, Cantekin K, Bircan HB, Bayrakdar IS, et al. A deep learning approach to automatic tooth caries segmentation in panoramic radiographs of children in primary dentition, mixed dentition, and permanent dentition. Children. 2024; 11: 690.

[36] Schwendicke F. Convolutional neural networks for dental image diagnostics: a scoping review. Journal of Dentistry. 2019; 91: 103226.

[37] Sun XY, Yuan C, Wang XZ, Wang X, Feng XP, Tai BJ, et al. Report of the National investigation of resources for oral health in China. Chinese Journal of Dental Research. 2018; 21: 285–297.

[38] Schwendicke F, Rossi JG, Göstemeyer G, Elhennawy K, Cantu AG, Gaudin R, et al. Cost-effectiveness of artificial intelligence for proximal caries detection. Journal of Dental Research. 2021; 100: 369–376.

[39] Mohammad-Rahimi H, Dianat O, Abbasi R, Zahedrozegar S, Ashkan A, Motamedian SR, et al. Artificial intelligence for detection of external cervical resorption using label-efficient self-supervised learning method. Journal of Endodontics. 2024; 50: 144–153.

[40] Marsillac Mde W. Dental anomalies in panoramic radiographs of pediatric patients. General Dentistry. 2013; 61: 29–33.

[41] Mooney GC, Morgan AG, Rodd HD, North S. Ectopic eruption of first permanent molars: presenting features and associations. European Archives of Paediatric Dentistry. 2007; 8: 153–157.

[42] Noothout JMH, De Vos BD, Wolterink JM, Postma EM, Smeets PAM, Takx RAP, et al. Deep learning-based regression and classification for automatic landmark localization in medical images. IEEE Transactions on Medical Imaging. 2020; 39: 4011–4022.

[43] Hartman H. Exploring the potential of artificial intelligence in paediatric dentistry: a systematic review on deep learning algorithms for dental anomaly detection. International Journal of Paediatric Dentistry. 2024; 34: 639–652.

[44] Ahn Y. Automated mesiodens classification system using deep learning on panoramic radiographs of children. Diagnostics. 2021; 11: 1477.

[45] Martens D. Performance of classification models from a user perspective. Decision Support Systems. 2011; 51: 782–793.

[46] Küçük DB, Imak A, Özçelik STA, Çelebi A, Türkoğlu M, Sengur A, et al. Hybrid CNN-transformer model for accurate impacted tooth detection in panoramic radiographs. Diagnostics. 2025; 15: 244.

[47] Kang S. Diagnostic accuracy of dental caries detection using ensemble techniques in deep learning with intraoral camera images. PLOS ONE. 2024; 19: e0310004.

[48] Mahesh Batra A. A new era of dental care: harnessing artificial intelligence for better diagnosis and treatment. Cureus. 2023; 15: e49319.