Journal of Korean Dental Science

Korean Academy of Dental Science (대한치의학회)
권호 표지
DOI QR코드

DOI QR Code

Deep Learning-Based Diagnosis of Medication-Related Osteonecrosis of the Jaw Using Panoramic Radiographs and Clinical Data: Pilot Study

  • Hye-Min Jeong (Department of Artificial Intelligence Convergence, Ewha Womans University) ;
  • Hyun Hwang (Department of Dental Hygiene, Graduate School of Medical Sciences, Ewha Womans University) ;
  • Se-hyang Kim (Department of Dental Hygiene, Graduate School of Medical Sciences, Ewha Womans University) ;
  • Heon-Young Kim (Department of Oral and Maxillofacial Surgery, Research Center for Intractable Osteonecrosis of the Jaw, Ewha Womans University College of Medicine) ;
  • Jung-Hyun Park (Department of Oral and Maxillofacial Surgery, Research Center for Intractable Osteonecrosis of the Jaw, Ewha Womans University College of Medicine) ;
  • Sun-Jong Kim (Department of Oral and Maxillofacial Surgery, Research Center for Intractable Osteonecrosis of the Jaw, Ewha Womans University College of Medicine) ;
  • Minji Kim (Department of Orthodontics, School of Medicine, Ewha Womans University) ;
  • Yuncheol Kang (School of Business, Ewha Womans University) ;
  • Jin-Woo Kim (Department of Oral and Maxillofacial Surgery, Research Center for Intractable Osteonecrosis of the Jaw, Ewha Womans University College of Medicine)
  • Received : 2025.11.10
  • Accepted : 2025.12.10
  • Published : 2025.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

Purpose: This study aimed to develop and evaluate a multimodal deep learning model that integrates panoramic radiographs and clinical data to improve the diagnosis of medication-related osteonecrosis of the jaw (MRONJ). Materials and Methods: The study included 705 panoramic radiographs (401 MRONJ and 304 Normal) collected from Ewha Womans University Mokdong and Seoul Hospitals. Radiographs were paired with patient information, including age, sex, body mass index (BMI), type of medication, duration, route of administration, dosage, and dental risk factors. Two deep learning models were compared: a ResNet-50 model using panoramic radiographs alone and the Modified ResNet-50 model incorporating both image and clinical features. Model performance was evaluated using accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC). Lesion localization and feature importance were analyzed using Gradient-weighted Class Activation Mapping (Grad-CAM) and SHapley Additive exPlanations (SHAP). Result: Significant differences in clinical characteristics were observed between the groups; the MRONJ group was older (74.5±10.0 vs. 68.6±12.7 years, P<0.01) and had a higher proportion of females (92.5% vs. 82.2%, P<0.01). In model performance, the Modified ResNet-50 model outperformed the PR-only model. Specifically, the Modified ResNet-50 model achieved an accuracy of 75.0%, a recall of 84.3%, and an AUC of 0.843, whereas the PR-only model showed lower performance with an accuracy of 72.1%, a recall of 81.4%, and an AUC of 0.720. SHAP analysis identified prolonged medication use and specific drug types (e.g., zoledronate, P<0.01) as influential predictors. Conclusion: The proposed multimodal deep learning framework demonstrated improved diagnostic performance and interpretability compared to radiograph-only models. This approach may serve as a practical and explainable AI-assisted tool for MRONJ diagnosis in routine dental practice.

Keywords

Acknowledgement

This research was supported by a grant from the Korea Health Technology R&D Project through the Korea Health Industry Development Institute (KHIDI), funded by the Ministry of Health & Welfare, Republic of Korea (grant number: RS2023-KH134688).

References

  1. Ruggiero SL, Dodson TB, Fantasia J, Goodday R, Aghaloo T, Mehrotra B, O'Ryan F. American Association of Oral and Maxillofacial Surgeons position paper on medication-related osteonecrosis of the jaw - 2014 update. J Oral Maxillofac Surg. 2014;72:1938-56. https://doi.org/10.1016/j.joms.2014.04.031
  2. Campisi G, Mauceri R, Bertoldo F, Bettini G, Biasotto M, Colella G, Consolo U, Di Fede O, Favia G, Fusco V, Gabriele M, Lo Casto A, Lo Muzio L, Marcianò A, Mascitti M, Meleti M, Mignogna MD, Oteri G, Panzarella V, Romeo U, Santarelli A, Vescovi P, Marchetti C, Bedogni A. Medication-related osteonecrosis of jaws (MRONJ) prevention and diagnosis: Italian consensus update 2020. Int J Environ Res Public Health. 2020;17: 5998. https://doi.org/10.3390/ijerph17165998
  3. Arce K, Assael LA, Weissman JL, Markiewicz MR. Imaging findings in bisphosphonate-related osteonecrosis of jaws. J Oral Maxillofac Surg. 2009;67(5 Suppl):75-84. https://doi.org/10.1016/j.joms.2008.12.002
  4. Leite AF, Ogata Fdos S, de Melo NS, Figueiredo PT. Imaging findings of bisphosphonate-related osteonecrosis of the jaws: A critical review of the quantitative studies. Int J Dent. 2014;2014:784348. https://doi.org/10.1155/2014/784348
  5. Kawahara M, Kuroshima S, Sawase T. Clinical considerations for medication-related osteonecrosis of the jaw: A comprehensive literature review. Int J Implant Dent. 2021;7:47. https://doi.org/10.1186/s40729-021-00323-0
  6. Schiodt M, Otto S, Fedele S, Bedogni A, Nicolatou-Galitis O, Guggenberger R, Herlofson BB, Ristow O, Kofod T. Workshop of European task force on medication-related osteonecrosis of the jaw - Current challenges. Oral Dis. 2019;25:1815-21. https://doi.org/10.1111/odi.v25.7
  7. Ruggiero SL, Dodson TB, Aghaloo T, Carlson ER, Ward BB, Kademani D. American Association of Oral and Maxillofacial Surgeons' position paper on medication-related osteonecrosis of the jaws - 2022 update. J Oral Maxillofac Surg. 2022;80:920-43. https://doi.org/10.1016/j.joms.2022.02.008
  8. Moreno-Rabié C, Gaêta-Araujo H, Oliveira-Santos C, Politis C, Jacobs R. Early imaging signs of the use of antiresorptive medication and MRONJ: A systematic review. Clin Oral Investig. 2020;24:2973-89. https://doi.org/10.1007/s00784-020-03423-0
  9. American Dental Association Council on Scientific Affairs. The use of dental radiographs: update and recommendations. J Am Dent Assoc. 2006;137:1304-12. https://doi.org/10.14219/jada.archive.2006.0393
  10. Ahlqwist M, Halling A, Hollender L. Rotational panoramic radiography in epidemiological studies of dental health: Comparison between panoramic radiographs and intraoral full mouth surveys. Swed Dent J. 1986;10:73-84.
  11. Lecomber AR, Yoneyama Y, Lovelock DJ, Hosoi T, Adams AM. Comparison of patient dose from imaging protocols for dental implant planning using conventional radiography and computed tomography. Dentomaxillofac Radiol. 2001;30:255-9. https://doi.org/10.1038/sj/dmfr/4600627
  12. Stockmann P, Hinkmann FM, Lell MM, Fenner M, Vairaktaris E, Neukam FW, Nkenke E. Panoramic radiograph, computed tomography or magnetic resonance imaging. Which imaging technique should be preferred in bisphosphonate-associated osteonecrosis of the jaw? Clin Oral Investig. 2010;14:311-7. https://doi.org/10.1007/s00784-009-0293-1
  13. Bianchi SD, Scoletta M, Cassione FB, Migliaretti G, Mozzati M. Computerized tomographic findings in bisphosphonate-associated osteonecrosis of the jaw in patients with cancer. Oral Surg Oral Med Oral Pathol Oral Radiol Endod. 2007;104:249-58. https://doi.org/10.1016/j.tripleo.2007.01.040
  14. Liu X, Faes L, Kale AU, Wagner SK, Fu DJ, Bruynseels A, Mahendiran T, Moraes G, Shamdas M, Kern C, Ledsam JR, Schmid MK, Balaskas K, Topol EJ, Bachmann LM, Keane PA, Denniston AK. A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: a systematic review and meta-analysis. Lancet Digit Health. 2019;1:e271-97. https://doi.org/10.1016/S2589-7500(19)30123-2
  15. Sharma N, Jain V, Mishra A. An analysis of convolutional neural networks for image classification. Procedia Comput Sci. 2018;132:377-84. https://doi.org/10.1016/j.procs.2018.05.198
  16. Sarvamangala DR, Kulkarni RV. Convolutional neural networks in medical image understanding: A survey. Evol Intell. 2022;15:1-22. https://doi.org/10.1007/s12065-020-00540-3
  17. Prajapati SA, Nagaraj R, Mitra S. Classification of dental diseases using CNN and transfer learning. 2017 5th International Symposium on Computational and Business Intelligence (ISCBI): Dubai; 2017. p. 70-4.
  18. Alotaibi G, Awawdeh M, Farook FF, Aljohani M, Aldhafiri RM, Aldhoayan M. Artificial intelligence (AI) diagnostic tools: Utilizing a convolutional neural network (CNN) to assess periodontal bone level radiographically- a retrospective study. BMC Oral Health. 2022;22:399. https://doi.org/10.1186/s12903-022-02436-3
  19. Jubair F, Al-karadsheh O, Malamos D, Al Mahdi S, Saad Y, Hassona Y. A novel lightweight deep convolutional neural network for early detection of oral cancer. Oral Dis. 2022;28:1123-30. https://doi.org/10.1111/odi.v28.4
  20. Jeyaraj PR, Samuel Nadar ER. Computer-assisted medical image classification for early diagnosis of oral cancer employing deep learning algorithm. J Cancer Res Clin Oncol. 2019;145:829-37. https://doi.org/10.1007/s00432-018-02834-7
  21. Baseri Saadi S, Moreno-Rabié C, van den Wyngaert T, Jacobs R. Convolutional neural network for automated classification of osteonecrosis and related mandibular trabecular patterns. Bone Rep. 2022;17:101632. https://doi.org/10.1016/j.bonr.2022.101632
  22. Devindi GAI, Dissanayake DMDR, Liyanage SN, Francis FBAH, Pavithya MBD, Piyarathne NS, Hettiarachchi PVKS, Rasnayaka RMSGK, Jayasinghe RD, Ragel RG, Nawinne I. Multimodal deep convolutional neural network pipeline for AI-assisted early detection of oral cancer. IEEE Access. 2024;12:124375-90.
  23. Acosta JN, Falcone GJ, Rajpurkar P, Topol EJ. Multimodal biomedical AI. Nat Med. 2022;28:1773-84. https://doi.org/10.1038/s41591-022-01981-2
  24. Lee YH, Jeon S, Won JH, Auh QS, Noh YK. Automatic detection and visualization of temporomandibular joint effusion with deep neural network. Sci Rep. 2024; 14:18865. https://doi.org/10.1038/s41598-024-69848-9
  25. Kwon O, Yong TH, Kang SR, Kim JE, Huh KH, Heo MS, Lee SS, Choi SC, Yi WJ. Automatic diagnosis for cysts and tumors of both jaws on panoramic radiographs using a deep convolution neural network. Dentomaxillofac Radiol. 2020;49:20200185. https://doi.org/10.1259/dmfr.20200185
  26. Sivasundaram S, Pandian C. Performance analysis of classification and segmentation of cysts in panoramic dental images using convolutional neural network architecture. Int J Imaging Syst Technol. 2021;31:2214-25. https://doi.org/10.1002/ima.v31.4
  27. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. Proc IEEE Conf Comput Vis Pattern Recognit. 2016;770-8.
  28. Park J, Woo S, Lee JY, Kweon IS. A simple and lightweight attention module for convolutional neural networks. Int J Comput Vis. 2020;128:783-98. https://doi.org/10.1007/s11263-019-01283-0
  29. Santurkar S, Tsipras D, Ilyas A, Madry A. How does batch normalization help optimization? Adv Neural Inf Process Syst. 2018;31:2483-93.
  30. Dubey SR, Singh SK, Chaudhuri BB. Activation functions in deep learning: A comprehensive survey and benchmark. Neurocomputing. 2022;503:92-108. https://doi.org/10.1016/j.neucom.2022.06.111
  31. Nohara Y, Matsumoto K, Soejima H, Nakashima N. Explanation of machine learning models using shapley additive explanation and application for real data in hospital. Comput Methods Programs Biomed. 2022;214:106584. https://doi.org/10.1016/j.cmpb.2021.106584
  32. Tan M, Le QV. Eff icientNet: Rethinking model scaling for convolutional neural networks. arXiv. 2020;1905.11946.
  33. Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv. 2015;1409.1556.
  34. Morita K, Hasegawa T, Takeda D, Akashi M, Wakabayashi T. Preoperative osteonecrosis region detection using contrastive learning and SVM. J Jpn Soc Fuzzy Theory Intell Informatics. 2024;36:616-22. https://doi.org/10.3156/jsoft.36.2_616
  35. Kwack DW, Park SM. Prediction of medication-related osteonecrosis of the jaw (MRONJ) using automated machine learning in patients with osteoporosis associated with dental extraction and implantation: A retrospective study. J Korean Assoc Oral Maxillofac Surg. 2023;49:135-41. https://doi.org/10.5125/jkaoms.2023.49.3.135
  36. Choi SG, Lee EY, Lee OJ, Kim S, Kang JY, Lim JS. Prediction models for early diagnosis of actinomycotic osteomyelitis of the jaw using machine learning techniques: A preliminary study. BMC Oral Health. 2022;22:164. https://doi.org/10.1186/s12903-022-02201-6
  37. Jamshidi A, Moztarzadeh O, Baghalipour N, Najdaghi S, Davani DN, Jamshidi M, Hauer L. Using machine learning techniques for diagnosing and analysing medication-related osteonecrosis of the jaw (MRONJ). Res Sq. 2024. doi.org/10.21203/rs.3.rs-4098010/v1.
  38. Harvey LA. Case-control studies: An efficient study design. Spinal Cord. 2019;57:1-2. https://doi.org/10.1038/s41393-018-0234-4
  39. Tenny S, Kerndt CC, Hoffman MR. Case control studies. In: StatPearls. Treasure Island: StatPearls Publishing; 2024.
  40. Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP. SMOTE: Synthetic minority over-sampling technique. J Artif Intell Res. 2002;16:321-57. https://doi.org/10.1613/jair.953