Detecting Pulp Stones with Automatic Deep Learning in Bitewing Radiographs: A Pilot Study of Artificial Intelligence

Abstract

Purpose: This study aims to examine the diagnostic performance of detecting pulp stones with a deep learning model on bite-wing radiographs. Material and Methods: 2203 radiographs were scanned retrospectively. 1745 pulp stones were marked on 1269 bite-wing radiographs with the CranioCatch labeling program (CranioCatch, Eskişehir, Turkey) in patients over 16 years old after the consensus of two experts of Maxillofacial Radiologists. This dataset was divided into 3 grou as training (n = 1017 (1396 labels), validation (n = 126 (174 labels)) and test (n = 126) (175 labels) sets, respectively. The deep learning model was developed using Mask R-CNN architecture. A confusion matrix was used to evaluate the success of the model. Results: The results of precision, sensitivity, and F1 obtained using the Mask R-CNN architecture in the test dataset were found to be 0.9115, 0.8879, and 0.8995, respectively. Discussion- Conclusion: Deep learning algorithms can detect pulp stones. With this, clinicians can use software systems based on artificial intelligence as a diagnostic support system. Mask R-CNN architecture can be used for pulp stone detection with approximately 90% sensitivity. The larger data sets increase the accuracy of deep learning systems. More studies are needed to increase the success rates of deep learning models.

Keywords

• artificial intelligence
• Bitewing radiography
• deep learning
• pulp stone

References

1. (1) Üçok, M. (2013). Diş Pulpasında Meydana Gelen Kalsifikasyonlar . Journal of Istanbul University Faculty of Dentistry , 13 (2) , 167-188 . Retrieved from https://dergipark.org.tr/en/pub/jiufd/issue/8929/111344
2. (2) Langeland, K., Rodrigues, H., & Dowden, W. (1974). Periodontal disease, bacteria, and pulpal histopathology. Oral Surgery, Oral Medicine, Oral Pathology, 37(2), 257-270, DOI: 10.1016/0030-4220(74)90421-6
3. (3) Goga, R., Chandler, N. P., & Oginni, A. O. (2008). Pulp stones: a review. International Endodontic Journal, 41(6), 457-468. DOI: 10.1111/j.1365-2591.2008.01374.x
4. (4) Deva, V., Mogoantă, L., Manolea, H., Pancă, O. A., Vătu, M., & Vătăman, M. (2006). Radiological and microscopic aspects of the denticles. Rom J Morphol Embryol, 47(3), 263-268.
5. (5) Nayak, M., Kumar, J., & Prasad, L. K. (2010). A radiographic correlation between systemic disorders and pulp stones. Indian Journal of Dental Research, 21(3), 369., DOI: 10.4103/0970-9290.70806
6. (6) Bauss, O., Neter, D., & Rahman, A. (2008). Prevalence of pulp calcifications in patients with Marfan syndrome. Oral Surgery, Oral Medicine, Oral Pathology, Oral Radiology, and Endodontology, 106(6), e56-e61., DOI: 10.1016/j.tripleo.2008.06.029
7. (7) Tamse, A., Kaffe, I., Littner, M. M., & Shani, R. (1982). Statistical evaluation of radiologic survey of pulp stones. Journal of Endodontics, 8(10), 455-458., DOI: 10.1016/S0099-2399(82)80150-7
8. (8) Gulsahi, A., Cebeci, A. I., & Özden, S. (2009). A radiographic assessment of the prevalence of pulp stones in a group of Turkish dental patients. International endodontic journal, 42(8), 735-739., DOI: 10.1111/j.1365-2591.2009.01580.x

9. (9) Moss-Salentijn, L., & Hendricks-Klyvert, M. (1988). Calcified structures in human dental pulps. Journal of Endodontics, 14(4), 184-189., DOI: 10.1016/S0099-2399(88)80262-0
10. (10) Hung, K., Montalvao, C., Tanaka, R., Kawai, T., & Bornstein, M. M. (2020). The use and performance of artificial intelligence applications in dental and maxillofacial radiology: A systematic review. Dentomaxillofacial Radiology, 49(1), 20190107., DOI: 10.1259/dmfr.20190107
11. (11) Kaur, P., Singh, G., & Kaur, P. (2018). A review of denoising medical images using machine learning approaches. Current medical imaging, 14(5), 675-685., DOI: 10.2174/1573405613666170428154156
12. (12) Ali, R. B., Ejbali, R., & Zaied, M. (2016, August). Detection and classification of dental caries in x-ray images using deep neural networks. In International conference on software engineering advances (ICSEA),
13. (13) Pauwels, R. (2021). A brief introduction to concepts and applications of artificial intelligence in dental imaging. Oral Radiology, 37(1), 153-160., DOI: 10.1007/s11282-020-00468-5
14. (14) Turkal, M., Tan, E., Uzgur, R., Hamidi, M., Colak, H., & Uzgur, Z. (2013). Incidence and distribution of pulp stones found in radiographic dental examination of adult Turkish dental patients. Annals of medical and health sciences research, 3(4), 572-576., DOI: 10.4103/2141-9248.122115
15. (15) Orhan, K., Bayrakdar, I. S., Ezhov, M., Kravtsov, A., & Özyürek, T. A. H. A. (2020). Evaluation of artificial intelligence for detecting periapical pathosis on cone‐beam computed tomography scans. International endodontic journal, 53(5), 680-689., DOI: 10.1111/iej.13265
16. (16) El-Damanhoury, H. M., Fakhruddin, K. S., & Awad, M. A. (2014). Effectiveness of teaching International Caries Detection and Assessment System II and its e-learning program to freshman dental students on occlusal caries detection. European journal of dentistry, 8(04), 493-497., DOI: 10.4103/1305-7456.143631
17. (17) Selmi, A., Syed, L., & Abdulkareem, B. (2021, November). Pulp Stone Detection Using Deep Learning Techniques. In EAI International Conference on IoT Technologies for HealthCare (pp. 113-124). Springer, Cham.