Hybrid ConvViT model for classification of dental radiography images

Öz

Dental radiography is used as an important diagnostic tool in the field of dentistry. Dental radiography provides detailed visualization of teeth, jaws and surrounding structures. Dental radiographs are manually interpreted by dentists for diagnosis and treatment purposes. Artificial intelligence methods are successfully applied to automate various image-related processes such as diagnosis and classification. In this study, a hybrid ConvViT model was developed to detect caries, fillings, impacted teeth, implants and normal teeth from dental radiography images. ConvViT combined the advantages of CNN and ViT architectures and provided more successful classification of dental radiography images. ConvViT was compared with popular pre-trained deep learning models such as ResNet-50, VGG-16, EfficientNetB0, and DenseNet201. Experimental results showed that ConvViT outperformed the compared models with 95% accuracy, 95% precision, 94% recall and 94% F-score. ConvViT makes a significant contribution to the development of artificial intelligence-based automatic diagnosis systems in the field of dentistry by effectively modeling both local and long-range features thanks to its hybrid structure.

Anahtar Kelimeler

• Dental radiography
• CNN
• ViT
• pre-trained models
• deep learning

Dental radyografi görüntülerinin sınıflandırılmasına yönelik hibrit ConvViT modeli

Öz

Dental radyografi, diş hekimliği alanında önemli bir tanı aracı olarak kullanılmaktadır. Dental radyografi, dişlerin, çenenin ve bu dili çevreleyen yapıların ayrıntılı bir şekilde görüntülenmesini sağlar. Diş radyografileri, teşhis ve tedavi amacıyla diş hekimleri tarafından manuel olarak yorumlanmaktadır. Yapay zekâ yöntemleri, tanı ve sınıflandırma gibi görüntülerle ilgili çeşitli süreçleri otomatikleştirmek amacıyla başarılı bir şekilde uygulanmaktadır. Bu çalışmada, dental radyografi görüntülerinden çürük, dolgu, gömülü diş, implant ve normal diş durumlarını tespit etmek amacıyla hibrit ConvViT modeli geliştirilmiştir. ConvViT, CNN ve ViT mimarilerinin avantajlarını bir araya getirerek dental radyografi görüntülerinin daha başarılı bir şekilde sınıflandırılmasını sağlamıştır. ConvViT, ResNet-50, VGG-16, EfficientNetB0 ve DenseNet201 gibi popüler önceden eğitilmiş derin öğrenme modelleriyle karşılaştırılmıştır. Deneysel sonuçlar, ConvViT'in %95 doğruluk, %95 kesinlik, %94 duyarlılık ve %94 F-skor ile karşılaştırılan modellere göre daha başarılı olduğunu göstermiştir. ConvViT, hibrit yapısı sayesinde hem yerel hem de uzun menzilli özellikleri etkili bir şekilde modelleyerek diş hekimliği alanında yapay zekâ tabanlı otomatik teşhis sistemlerinin geliştirilmesine önemli bir katkı sunmaktadır.

Anahtar Kelimeler

• Dental radyografi
• CNN
• ViT
• önceden eğitilmiş modeller
• derin öğrenme

Kaynakça

1. 1. Yazdanian, M., Karami, S., Tahmasebi, E., Alam, M., Abbasi, K., Rahbar, M., Yazdanian, A., Dental radiographic/digital radiography technology along with biological agents in human identification, Scanning, 2022 (1), 2022.
2. 2. Rahi, D., Abbassi, S., Tajbakhsh, N. A., systematic Review on Epidemiologic Study on Radiolucent lesions in Patients Referred to Radiology Departments, Eurasian Journal of Chemical, Medicinal and Petroleum Research, 3 (3), 1016-1035, 2024.
3. 3. Kumar, A., Bhadauria, H. S., Singh, A., Descriptive analysis of dental X-ray images using various practical methods: A review, PeerJ Computer Science, 7, 2021.
4. 4. Rahi, D., Abbassi, S., Tajbakhsh, N., Evaluation of Root Canal Morphology of Mandibular Bone Using Radiological Imaged a Systematic Review, Eurasian Journal of Chemical, Medicinal and Petroleum Research, 3 (3), 993-1015, 2024.
5. 5. Samuel, S. Dental X-rays: Learn about the various types of dental x-rays, including bitewing, periapical, occlusal, panoramic and digital imaging, Oral Health, 18 (2), 2024.
6. 6. Schüler, I. M., Hennig, C. L., Buschek, R., Scherbaum, R., Jacobs, C., Scheithauer, M., Mentzel, H. J., Radiation exposure and frequency of dental, bitewing and occlusal radiographs in children and adolescents, Journal of Personalized Medicine, 13 (4), 2023.
7. 7. Tomášik, J., Zsoldos, M., Oravcová, Ľ., Lifková, M., Pavleová, G., Strunga, M., Thurzo, A., AI and Face-Driven Orthodontics: A Scoping Review of Digital Advances in Diagnosis and Treatment Planning, AI, 5 (1), 158-176, 2024.
8. 8. Flügge, T., Gross, C., Ludwig, U., Schmitz, J., Nahles, S., Heiland, M., Nelson, K., Dental MRI-only a future vision or standard of care? A literature review on current indications and applications of MRI in dentistry, Dentomaxillofacial Radiology, 52 (4), 2023.

9. 9. Çelik, B., Çelik, M. E., Automated detection of dental restorations using deep learning on panoramic radiographs, Dentomaxillofacial Radiology, 51 (8), 2022.
10. 10. Almalki, Y. E., Din, A. I., Ramzan, M., Irfan, M., Aamir, K. M., Almalki, A., Rahman, S., Deep learning models for classification of dental diseases using orthopantomography X-ray OPG images, Sensors, 22 (19), 2022.
11. 11. Shon, H. S., Kong, V., Park, J. S., Jang, W., Cha, E. J., Kim, S. Y., Kim, K. A., Deep learning model for classifying periodontitis stages on dental panoramic radiography, Applied Sciences, 12 (17), 2022.
12. 12. Aljabri, M., Aljameel, S. S., Min-Allah, N., Alhuthayfi, J., Alghamdi, L., Alduhailan, N., Al Turki, W., Canine impaction classification from panoramic dental radiographic images using deep learning models, Informatics in Medicine Unlocked, 30, 2022.
13. 13. Okazaki, S., Mine, Y., Iwamoto, Y., Urabe, S., Mitsuhata, C., Nomura, R., Murayama, T., Analysis of the feasibility of using deep learning for multiclass classification of dental anomalies on panoramic radiographs, Dental Materials Journal, 41 (6), 889-895, 2022.
14. 14. Lin, Y. C., Chen, M. C., Chen, C. H., Chen, M. H., Liu, K. Y., Chang, C. C., Fully automated film mounting in dental radiography: a deep learning model, BMC Medical Imaging, 23 (1), 2023.
15. 15. Oztekin, F., Katar, O., Sadak, F., Yildirim, M., Cakar, H., Aydogan, M., Acharya, U. R., An explainable deep learning model to prediction dental caries using panoramic radiograph images, Diagnostics, 13 (2), 2023.
16. 16. Park, J. H., Moon, H. S., Jung, H. I., Hwang, J., Choi, Y. H., & Kim, J. E., Deep learning and clustering approaches for dental implant size classification based on periapical radiographs, Scientific reports, 13 (1), 2023.
17. 17. Chen, I. D. S., Yang, C. M., Chen, M. J., Chen, M. C., Weng, R. M., Yeh, C. H., Deep learning-based recognition of periodontitis and dental caries in dental x-ray images, Bioengineering, 10 (8), 2023.
18. 18. Yilmaz, S., Tasyurek, M., Amuk, M., Celik, M., Canger, E. M., Developing deep learning methods for classification of teeth in dental panoramic radiography. Oral Surgery, Oral Medicine, Oral Pathology and Oral Radiology, 138 (1), 118-127, 2024.
19. 19. Mahdie Rahmati. Segmented Dental Radiography. Kaggle. https://www.kaggle.com/datasets/mahdierahmati/segmented-dental-radiography/data. Yayın tarihi. Ağustos 10, 2024. Erişim tarihi. Ağustos 28, 2024.
20. 20. Üzülmez S., Çifçi M.A., Early diagnosis of lung cancer using deep learning and uncertainty measures, Journal of the Faculty of Engineering and Architecture of Gazi University, 39 (1), 385-400, 2023.
21. 21. Bangare, S., Rajankar, H., Patil, P., Nakum, K., Paraskar, G., Pneumonia detection and classification using CNN and VGG-16. International Journal of Advanced Research in Science, Communication and Technology, 12, 771-779, 2022.
22. 22. Mesran, M., Yahya, S. R., Nugroho, F., Windarto, A. P., Investigating the Impact of ReLU and Sigmoid Activation Functions on Animal Classification Using CNN Models, Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), 8 (1), 111-118, 2024.
23. 23. Mogan, J. N., Lee, C. P., Lim, K. M., Muthu, K. S., VGG-16-MLP: gait recognition with fine-tuned VGG-16 and multilayer perceptron, Applied Sciences, 12 (15), 2022.
24. 24. Karahanlı G., Taşkın C., Determining the growth stages of sunflower plants using deep learning methods, Journal of the Faculty of Engineering and Architecture of Gazi University, 39 (3), 1455-1472, 2024.
25. 25. Aktaş A., Demir Ö., Doğan B., Tactile paving surface detection with deep learning methods, Journal of the Faculty of Engineering and Architecture of Gazi University, 35 (3), 1685-1700, 2020.
26. 26. Yogeswararao, G., Naresh, V., Malmathanraj, R., Palanisamy, P., An efficient densely connected convolutional neural network for identification of plant diseases, Multimedia Tools and Applications, 81 (23), 32791-32816, 2022.
27. 27. Islam, M. M., Talukder, M. A., Uddin, M. A., Akhter, A., Khalid, M., Brainnet: precision brain tumor classification with optimized efficientnet architecture. International Journal of Intelligent Systems, 2024 (1), 2024.
28. 28. Salati M., Askerzade İ., Bostancı G.E., Convolutional neural network models using metaheuristic based feature selection method for intrusion detection, Journal of the Faculty of Engineering and Architecture of Gazi University, 40 (1), 179-188, 2025.
29. 29. Gupta, N., Garg, H., Agarwal, R., A robust framework for glaucoma detection using CLAHE and EfficientNet, The Visual Computer, 1-14, 2022.
30. 30. Talukder, M. A., Layek, M. A., Kazi, M., Uddin, M. A., Aryal, S., Empowering covid-19 detection: Optimizing performance through fine-tuned efficientnet deep learning architecture, Computers in Biology and Medicine, 168, 2024.
31. 31. Narin A., İşler Y., Detection of new coronavirus disease from chest x-ray images using pre-trained convolutional neural networks, Journal of the Faculty of Engineering and Architecture of Gazi University, 36 (4), 2095-2108, 2021.
32. 32. Usanmaz K., Güney S., Real time classification of traffic sign with deep learning methods, Journal of the Faculty of Engineering and Architecture of Gazi University, 40 (2), 1311-1324, 2025.
33. 33. Alt, T., Schrader, K., Augustin, M., Peter, P., Weickert, J., Connections between numerical algorithms for PDEs and neural networks, Journal of Mathematical Imaging and Vision, 65 (1), 185-208, 2023.
34. 34. Weng, O., Marcano, G., Loncar, V., Khodamoradi, A., Sheybani, N., Meza, A., Kastner, R., Tailor: Altering skip connections for resource-efficient inference, ACM Transactions on Reconfigurable Technology and Systems, 17 (1), 1-23, 2024.
35. 35. Xu, W., Fu, Y. L., Zhu, D., ResNet and its application to medical image processing: Research progress and challenges, Computer Methods and Programs in Biomedicine, 240, 2023.
36. 36. Dawod, R. G., Dobre, C., ResNet interpretation methods applied to the classification of foliar diseases in sunflower, Journal of Agriculture and Food Research, 9, 2022.
37. 37. Ding, Y., Jia, M., Convolutional transformer: An enhanced attention mechanism architecture for remaining useful life estimation of bearings, IEEE Transactions on Instrumentation and Measurement, 71, 1-10, 2022.
38. 38. Yu, L., Xiang, W., Fang, J., Chen, Y. P. P., Chi, L., ex-vit: A novel explainable vision transformer for weakly supervised semantic segmentation, Pattern Recognition, 142, 2023.
39. 39. Liu, S., Wang, W., Deng, L., Xu, H., Cnn-trans model: A parallel dual-branch network for fundus image classification, Biomedical Signal Processing and Control, 96, 2024.
40. 40. Lin, M., Li, G., Xu, S., Hao, Y., Zhang, S., Decoupling foreground and background with Siamese ViT networks for weakly-supervised semantic segmentation, Neurocomputing, 128540, 2024.
41. 41. Lv, P., Wu, W., Zhong, Y., Du, F., Zhang, L., SCViT: A spatial-channel feature preserving vision transformer for remote sensing image scene classification, IEEE Transactions on Geoscience and Remote Sensing, 60, 1-12, 2022.
42. 42. Soydaner, D., Attention mechanism in neural networks: where it comes and where it goes. Neural Computing and Applications, 34 (16), 13371-13385, 2022.
43. 43. Kara, A., Multi-scale deep neural network approach with attention mechanism for remaining useful life estimation, Computers & Industrial Engineering, 169, 2022.