A Novel Approach to Dental X-Ray Analysis: Using Vision Transformers for Detecting Caries

Wasan Mueti  Hadi; Zahraa K.  Al-Sendi; Manar Hamza  Bashaa; Ghosoon k.  munahy; Noor Abbas  Khudhair

doi:10.30572/2018/KJE/170222

Authors

Wasan Mueti Hadi Department of Computer Science, College of Computer Science and Information Technology, University of Kerbala, Iraq
Zahraa K. Al-Sendi Department of Computer Science, College of Computer Science and Information Technology, University of Kerbala, Iraq
Manar Hamza Bashaa Department of Information Technology, College of Computer Science and Information Technology, University of Kerbala, Kerbala, Iraq
Ghosoon k. munahy Department of Information Technology, College of Computer Science and Information Technology, University of Kerbala, Kerbala, Iraq
Noor Abbas Khudhair University of Al_Ameed College of Dentistry, Kerbala, Iraq

DOI:

https://doi.org/10.30572/2018/KJE/170222

Keywords:

Vision Transformers, Medical Image Analysis, Caries Detection, Deep Learning in Dentistry, Self-Supervised Learning

Abstract

All age groups are affected by oral diseases that are common worldwide. The dentist relies on Dental radiographs were used to explore the characteristics of oral diseases. Dental X-ray image segmentation and analysis pose significant challenges compared with other medical images. This secondary challenge makes dental radiography challenging. Because dental images are captured at a lower resolution, the segmentation of a tooth and its related complications can be unreliable because they are not resolvable. Dental X-ray Image Segmentation (DXIS) is one of the most fundamental and important steps in obtaining relevant information concerning oral diseases. In dentistry, DXIS is an important step in obtaining many different pathologies of gingival tissues. The next proposed methodology uses Vision Transformers (ViTs) to identify dental caries from dental X-ray images. In contrast to traditional CNN-based approaches, this approach uses attention mechanisms to dissect each patch of the image in more detail and yields more accurate results with earlier detection of caries. The results showed that ViTs are better than CNN, the proposed performance accuracy reached 95% compared to the accuracy of the convolutional neural network, which reached 86%

Downloads

Download data is not yet available.

References

Abbosh, Y.M., Ali, S.M., Ali, D.M. and Alhummada, I.A.(2025). “Keratoconus detection using deep learning”. Kufa Journal of Engineering, 16(2).

Azad, R., Kazerouni, A., Heidari, M., Aghdam, E.K., Molaei, A., Jia, Y., Jose, A., et al. (2024), “Advances in medical image analysis with vision transformers: a comprehensive review”, Medical Image Analysis, Elsevier, Vol. 91, p. 103000, doi: 10.1016/j.media.2023.103000.

Felsch, M., Meyer, O., Schlickenrieder, A., Engels, P., Schönewolf, J., Zöllner, F., Heinrich-Weltzien, R., et al. (2023), “Detection and localization of caries and hypomineralization on dental photographs with a vision transformer model”, NPJ Digital Medicine, Nature Publishing Group UK London, Vol. 6 No. 1, p. 198.

Gao, N., Li, Y., Liang, R., Chen, P., Tang, J. and Liu, T. (2023), “Btcn: Bridging the gap between pre-trained and downstream models for endoscopic caries detection”, 2023 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), IEEE, pp. 857–862, doi: 10.1109/BIBM58861.2023.10385358.

Hashim, A.A. and Mazinani, M.( 2025). “Detection of keratoconus disease depending on corneal topography using deep learning”. Kufa Journal of Engineering, 16(1).

Hasnain, M.A., Ali, Z., Maqbool, M.S. and Aziz, M. (2024), “X-ray Image Analysis for Dental Disease: A Deep Learning Approach Using EfficientNets”, VFAST Transactions on Software Engineering, Vol. 12 No. 3 SE-Articles, pp. 147–165, doi: 10.21015/vtse.v12i3.1912.

Hossain, M.S., Rahman, M.M., Syeed, M.M.M., Hannan, U.H., Uddin, M.F. and Mumu, S.B. (2023), “Cavit: Early stage dental caries detection from smartphone-image using vision transformer”, 2023 4th International Conference on Artificial Intelligence, Robotics and Control (AIRC), IEEE, pp. 9–14, doi: 10.1109/AIRC57904.2023.10303012.

https://github.com/wasanhadi/My-dataset/tree/main

Jiang, H., Zhang, P., Che, C. and Jin, B. (2021), “Rdfnet: A fast caries detection method incorporating transformer mechanism”, Computational and Mathematical Methods in Medicine, Wiley Online Library, Vol. 2021 No. 1, p. 9773917.

Li, P., Gao, C., Lian, C. and Meng, D. (2024), “Spatial Prior-Guided Bi-Directional Cross-Attention Transformers for Tooth Instance Segmentation”, IEEE Transactions on Medical Imaging, IEEE, doi: 10.1109/TMI.2024.3406015.

Liu, W., Zhou, X., Durrani, S. and Popovski, P. (2017), “A novel receiver design with joint coherent and non-coherent processing”, IEEE Transactions on Communications, IEEE, Vol. 65 No. 8, pp. 3479–3493.

Mail-Sharifa, E. (2025), “From Image to Insight: Using Vision Transformers to Revolutionize Dental Caries Assessment in Radiographic Imaging”, SEEJPH, Vol. XXVI No. S2, pp. 494–501.

Mittal, P., Sharma, B. and Yadav, D.P.(2024). “Comparative analysis between CNN and ViT using brain MRI dataset”. In: 2024 Eighth International Conference on Parallel, Distributed and Grid Computing (PDGC), December 2024, pp.290–295. IEEE.

Mohammed, H.A., Kareem, S.W. and Mohammed, A.S. (2022). “A comparative evaluation of deep learning methods in digital image classification”. Kufa Journal of Engineering, 13(4).

Sun, C. and Chen, H. (2022), “An attention-based transformer model for dental caries detection”, International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2022), Vol. 12256, SPIE, pp. 673–679, doi: 10.1117/12.2635362.

Ying, S., Huang, F., Shen, X., Liu, W. and He, F. (2024), “Performance comparison of multifarious deep networks on caries detection with tooth X-ray images”, Journal of Dentistry, Elsevier, Vol. 144, p. 104970, doi: 10.1016/j.jdent.2024.104970.

Ying, S., Wang, B., Zhu, H., Liu, W. and Huang, F. (2022), “Caries segmentation on tooth X-ray images with a deep network”, Journal of Dentistry, Elsevier, Vol. 119, p. 104076, doi: 10.1016/j.jdent.2022.104076.

Yoon, K., Jeong, H.-M., Kim, J.-W., Park, J.-H. and Choi, J. (2024), “AI-based dental caries and tooth number detection in intraoral photos: Model development and performance evaluation”, Journal of Dentistry, Elsevier, Vol. 141, p. 104821, doi: 10.1016/j.jdent.2023.104821.

Zhang, X., Guo, E., Liu, X., Zhao, H., Yang, J., Li, W., Wu, W., et al. (2025), “Enhancing furcation involvement classification on panoramic radiographs with vision transformers”, BMC Oral Health, Springer, Vol. 25 No. 1, p. 153, doi: 10.1186/s12903-025-05431-6.

Zhou, X., Yu, G., Yin, Q., Yang, J., Sun, J., Lv, S. and Shi, Q. (2023), “Tooth type enhanced transformer for children caries diagnosis on dental panoramic radiographs”, Diagnostics, MDPI, Vol. 13 No. 4, p. 689.

Zhu, H., Cao, Z., Lian, L., Ye, G., Gao, H. and Wu, J. (2023), “CariesNet: a deep learning approach for segmentation of multi-stage caries lesion from oral panoramic X-ray image”, Neural Computing and Applications, Springer, pp. 1–9.