PERIAPICAL LESIONS DETECTION USING AN ARTIFICIAL INTELLIGENCE TOOL: A RETROSPECTIVE MULTICENTRIC STUDY OVER PERIAPICAL RADIOGRAPHS
Main Article Content
Keywords
.
Abstract
This study was conducted to design and evaluate an AI tool called Make Sure periapical explorer (MSp) to detect periapical lesions on digital periapical radiographs and to compare its performance with the dentists’. This study was a diagnostic, retrospective, and multi-centric study, with a sample size of 2,200 digital periapical radiographs (with 3,680 periapical lesions). The dataset was split into train, validate, and test datasets; the ratio was 8-1-1. 220 images were randomly allocated to test MSp AI model, and the same images were allocated to test 10 certified dentists. The performance metrics used to test and compare MSp performance and the dentist’s performance included precision, F1 score, recall, and mean average precision (mAP). Kolmogorov-Smirnov test was used to test the normalization of the distributions. The Kruskal-Wallis test was used to determine the significant difference between the mAP, precision, recall, and F1 scores. The statistical significance was set at p < 0.05. MSp achieved a higher performance in all metrics in comparison to the dentists group. There was no statistical difference in the precision metric and recall metric, while there was a statistically significant difference in F1-score and mAP between the two groups. The designed MSp tool proved itself reliable in the detection of periapical lesions in digital periapical radiographs. It also showed a higher performance metrics in detecting periapical lesions when compared to the dentists’ group consensus.
References
1. Schulz, M., von Arx, T., Altermatt, H.J., Bosshardt, D. Histology of Periapical Lesions Obtained During Apical Surgery. J Endod. 35, 634–42 (2009).
2. Fernandes M, Ataide I. Nonsurgical management of periapical lesions. J Conserv Dent. 13, 240 (2010).
3. Croitoru, I.C. et al. Clinical, imagistic and histopathological study of chronic apical periodontitis. Rom J Morphol Embryol. 57, 719-728 (2016).
4. Keser, G., & Pekiner, F. Comparative Evaluation of Periapical Lesions Using Periapical Index Adapted for Panoramic Radiography and Cone Beam Computed Tomography. Clin Exp Health Sci. 8, 50-55 (2017).
5. McCaul, L. K., McHugh, S., & Saunders, W. P. The influence of specialty training and experience on decision making in endodontic diagnosis and treatment planning. Int Endod J. 34, 594–606 (2001).
6. Modi, K., Padmapriya, R., Elango, S., Khandelwal, P., Arul, B., & Natanasabapathy, V. Nonmalignant nonendodontic lesions mimicking periapical lesions of endodontic origin: A systematic review. J Conserv Dent. 25, 214–225 (2022).
7. Vranckx, M. et al. Artificial Intelligence (AI)-Driven Molar Angulation Measurements to Predict Third Molar Eruption on Panoramic Radiographs. Int J Environ Res Public Health. 17:3716 (2020).
8. Hung, K., Yeung, A. W. K., Tanaka, R., & Bornstein, M. M. Current Applications, Opportunities, and Limitations of AI for 3D Imaging in Dental Research and Practice. Int J Environ Res Public Health. 17, 4424 (2020).
9. Zhu, X., Lyu, S., Wang, X., & Zhao, Q. TPH-YOLOv5: Improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios. Proc IEEE Int Conf Comput Vis. 2778–2788 (2021).
10. Pauwels, R. et al. Artificial intelligence for detection of periapical lesions on intraoral radiographs: Comparison between convolutional neural networks and human observers. Oral Surg Oral Med Oral Pathol Oral Radiol. 131, 610–616 (2021).
11. Shah, N., Bansal, N., & Logani, A. Recent advances in imaging technologies in dentistry. World J Radiol. 6, 794–807 (2014).
12. Zaki, H. A. M., Hoffmann, K. R., Hausmann, E., & Scannapieco, F. A. Is Radiologic Assessment of Alveolar Crest Height Useful to Monitor Periodontal Disease Activity? Dent Clin North Am.59:859-72 (2015).
13. Li, C. W. et al. Detection of Dental Apical Lesions Using CNNs on Periapical Radiograph. Sensors (Basel, Switzerland). 21, 7049 (2021).
14. Camps, J., Pommel, L., & Bukiet, F. Evaluation of periapical lesion healing by correction of gray values. J Endod. 30, 762–766 (2004).
15. Fuhrmann, R. A. W., Bücker, A., & Diedrich, P. R. Assessment of alveolar bone loss with high resolution computed tomography. J Periodontal Res. 30, 258–263 (1995).
16. Ahuja, A. S. The impact of artificial intelligence in medicine on the future role of the physician. Peer J. 7, e7702 (2019).
17. Endres, M,G. et al. Development of a Deep Learning Algorithm for Periapical Disease Detection in Dental Radiographs. Diagnostics (Basel). 10:430 (2020).
18. Boreak, N. Effectiveness of Artifcial Intelligence Applications Designed for Endodontic Diagnosis, Decision-making, and Prediction of Prognosis: A Systematic Review. J Contemp Dent Pract. 21, 926–934 (2020).
19. Orhan, K., Bayrakdar, I. S., Ezhov, M., Kravtsov, A., & Özyürek, T. Evaluation of artificial intelligence for detecting periapical pathosis on cone-beam computed tomography scans. Int Endod J. 53, 680–689 (2020).
20. Hamdan, M. H., Tuzova, L., Mol, A., Tawil, P. Z., Tuzoff, D., & Tyndall, D. A. The effect of a deep-learning tool on dentists’ performances in detecting apical radiolucencies on periapical radiographs. Dentomaxillofac Radiol. 51, 20220122 (2022).
2. Fernandes M, Ataide I. Nonsurgical management of periapical lesions. J Conserv Dent. 13, 240 (2010).
3. Croitoru, I.C. et al. Clinical, imagistic and histopathological study of chronic apical periodontitis. Rom J Morphol Embryol. 57, 719-728 (2016).
4. Keser, G., & Pekiner, F. Comparative Evaluation of Periapical Lesions Using Periapical Index Adapted for Panoramic Radiography and Cone Beam Computed Tomography. Clin Exp Health Sci. 8, 50-55 (2017).
5. McCaul, L. K., McHugh, S., & Saunders, W. P. The influence of specialty training and experience on decision making in endodontic diagnosis and treatment planning. Int Endod J. 34, 594–606 (2001).
6. Modi, K., Padmapriya, R., Elango, S., Khandelwal, P., Arul, B., & Natanasabapathy, V. Nonmalignant nonendodontic lesions mimicking periapical lesions of endodontic origin: A systematic review. J Conserv Dent. 25, 214–225 (2022).
7. Vranckx, M. et al. Artificial Intelligence (AI)-Driven Molar Angulation Measurements to Predict Third Molar Eruption on Panoramic Radiographs. Int J Environ Res Public Health. 17:3716 (2020).
8. Hung, K., Yeung, A. W. K., Tanaka, R., & Bornstein, M. M. Current Applications, Opportunities, and Limitations of AI for 3D Imaging in Dental Research and Practice. Int J Environ Res Public Health. 17, 4424 (2020).
9. Zhu, X., Lyu, S., Wang, X., & Zhao, Q. TPH-YOLOv5: Improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios. Proc IEEE Int Conf Comput Vis. 2778–2788 (2021).
10. Pauwels, R. et al. Artificial intelligence for detection of periapical lesions on intraoral radiographs: Comparison between convolutional neural networks and human observers. Oral Surg Oral Med Oral Pathol Oral Radiol. 131, 610–616 (2021).
11. Shah, N., Bansal, N., & Logani, A. Recent advances in imaging technologies in dentistry. World J Radiol. 6, 794–807 (2014).
12. Zaki, H. A. M., Hoffmann, K. R., Hausmann, E., & Scannapieco, F. A. Is Radiologic Assessment of Alveolar Crest Height Useful to Monitor Periodontal Disease Activity? Dent Clin North Am.59:859-72 (2015).
13. Li, C. W. et al. Detection of Dental Apical Lesions Using CNNs on Periapical Radiograph. Sensors (Basel, Switzerland). 21, 7049 (2021).
14. Camps, J., Pommel, L., & Bukiet, F. Evaluation of periapical lesion healing by correction of gray values. J Endod. 30, 762–766 (2004).
15. Fuhrmann, R. A. W., Bücker, A., & Diedrich, P. R. Assessment of alveolar bone loss with high resolution computed tomography. J Periodontal Res. 30, 258–263 (1995).
16. Ahuja, A. S. The impact of artificial intelligence in medicine on the future role of the physician. Peer J. 7, e7702 (2019).
17. Endres, M,G. et al. Development of a Deep Learning Algorithm for Periapical Disease Detection in Dental Radiographs. Diagnostics (Basel). 10:430 (2020).
18. Boreak, N. Effectiveness of Artifcial Intelligence Applications Designed for Endodontic Diagnosis, Decision-making, and Prediction of Prognosis: A Systematic Review. J Contemp Dent Pract. 21, 926–934 (2020).
19. Orhan, K., Bayrakdar, I. S., Ezhov, M., Kravtsov, A., & Özyürek, T. Evaluation of artificial intelligence for detecting periapical pathosis on cone-beam computed tomography scans. Int Endod J. 53, 680–689 (2020).
20. Hamdan, M. H., Tuzova, L., Mol, A., Tawil, P. Z., Tuzoff, D., & Tyndall, D. A. The effect of a deep-learning tool on dentists’ performances in detecting apical radiolucencies on periapical radiographs. Dentomaxillofac Radiol. 51, 20220122 (2022).
Article Sidebar
Published
Jul 24, 2022
Article Details
How to Cite
Abdulbadea Altukroni, Abdullah Alsaeedi, Sakina El-Amri, Omar Ezz El-Deen, Mahmoud Khatiri, Mohammed Alabduh, Turki Jari, Mwaed Ashri, Ahmed Jamaan, & Omar Alshaikh. (2022). PERIAPICAL LESIONS DETECTION USING AN ARTIFICIAL INTELLIGENCE TOOL: A RETROSPECTIVE MULTICENTRIC STUDY OVER PERIAPICAL RADIOGRAPHS. Journal of Population Therapeutics and Clinical Pharmacology, 29(03), 1777-1786. https://doi.org/10.53555/jptcp.v29i03.5607
Section
Articles
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
All articles published in JPTCP are licensed under Copyright Creative Commons Attribution-NonCommercial 4.0 International License.
Author Biographies
Abdulbadea Altukroni
Ministry of Health, Medina, Saudi Arabia
Abdullah Alsaeedi
Taibah University, Medina, Saudi Arabia
Sakina El-Amri
Ministry of Health, Ankara, Turkey
Omar Ezz El-Deen
Ministry of Health, Cairo, Egypt, research-
Mahmoud Khatiri
Ministry of Health, Medina, Saudi Arabia
Mohammed Alabduh
Ministry of Health, Medina, Saudi Arabia
Turki Jari
Ministry of Health, Medina, Saudi Arabia
Mwaed Ashri
Ministry of Health, Medina, Saudi Arabia
Ahmed Jamaan
Ministry of Health, Medina, Saudi Arabia
Omar Alshaikh
Ministry of Health, Medina, Saudi Arabia
How to Cite
Abdulbadea Altukroni, Abdullah Alsaeedi, Sakina El-Amri, Omar Ezz El-Deen, Mahmoud Khatiri, Mohammed Alabduh, Turki Jari, Mwaed Ashri, Ahmed Jamaan, & Omar Alshaikh. (2022). PERIAPICAL LESIONS DETECTION USING AN ARTIFICIAL INTELLIGENCE TOOL: A RETROSPECTIVE MULTICENTRIC STUDY OVER PERIAPICAL RADIOGRAPHS. Journal of Population Therapeutics and Clinical Pharmacology, 29(03), 1777-1786. https://doi.org/10.53555/jptcp.v29i03.5607