Application of machine learning models in determining the prevalence of apical periodontitis
Main Article Content
Abstract
A cross-sectional descriptive study was conducted on 1,242 patients (29,852 teeth) who underwent panoramic radiography at the Institute of Odonto-Stomatology in 2022. Periapical lesions were detected using a machine learning model and confirmed by two independent dentists. Data were analyzed using SPSS version 26.0 with appropriate statistical tests (Chi-square test and t-test), and statistical significance was set at p < 0.05. The overall prevalence of periapical lesions was 22.49%, increasing with age and reaching the highest level in patients over 60 years (36.15%). Molars exhibited the highest prevalence of periapical lesions (2.14%); however, no statistically significant difference was observed among tooth groups. Among endodontically treated teeth, 36.5% still showed periapical lesions, which were significantly associated with the homogeneity of root canal filling material and the working length (p < 0.001). The machine learning model reduced missed diagnoses, with miss rates among independent dentists ranging from 4.84% to 7.02%, while differences across tooth positions were not statistically significant (p > 0.05).
Article Details
Keywords
Periapical radiolucency, deep learning model, Faster R-CNN, Panoramic radiographs
References
2. Khalighinejad N, Aminoshariae MR, Aminoshariae A, et al. Association between Systemic Diseases and Apical Periodontitis. J Endod. 2016; 42(10): 1427-1434. doi:10.1016/j.joen.2016.07.007.
3. Patel S, Durack C, Abella F, et al. Cone beam computed tomography in Endodontics - a review. Int Endod J. 2015; 48(1): 3-15. doi:10.1111/iej.12270.
4. Ekert T, Krois J, Meinhold L, et al. Quality of root canal fillings and prevalence of apical radiolucencies in a German population: a CBCT analysis. Journal of Endodontics. 2019; 45(7): 917-922.e5. doi:10.1016/j.joen.2019.03.016.
5. Setzer FC, Shi KJ, Zheng Z, et al. Artificial Intelligence for the Computer-aided Detection of Periapical Lesions in Cone-beam Computed Tomographic Images. Journal of Endodontics. 2020; 46(7): 987-993. doi:10.1016/j.joen.2020.03.025.
6. Matijević J, Cizmeković Dadić T, Prpic Mehicic G, et al. Prevalence of apical periodontitis and quality of root canal fillings in population of Zagreb, Croatia: a cross-sectional study. Croat Med J. 2011; 52(6): 679-687. doi:10.3325/cmj.2011.52.679.
7. Bürklein S, Schäfer E, Jöhren HP, et al. Quality of root canal fillings and prevalence of apical radiolucencies in a German population: a CBCT analysis. Clin Oral Invest. 2020; 24(3): 1217-1227. doi:10.1007/s00784-019-02985-y.
8. Ekert T, Krois J, Meinhold L, et al. Deep Learning for the Radiographic Detection of Apical Lesions. Journal of Endodontics. 2019; 45(7): 917-922.e5. doi:10.1016/j.joen.2019.03.016.
9. Litjens G, Kooi T, Bejnordi BE, et al. A survey on deep learning in medical image analysis. Medical Image Analysis. 2017; 42: 60-88. doi:10.1016/j.media.2017.07.005.
10. Moidu NP, Sharma S, Chawla A, et al. Deep learning for categorization of endodontic lesion based on radiographic periapical index scoring system. Clin Oral Invest. 2022; 26(1): 651-658. doi:10.1007/s00784-021-04043-y.
11. G K, Singh N, Yadav R, et al. Comparative analysis of the accuracy of periapical radiography and cone-beam computed tomography for diagnosing complex endodontic pathoses using a gold standard reference - A prospective clinical study. Int Endodontic J. 2021; 54(9): 1448-1461. doi:10.1111/iej.13535.