Dental Cavity Detection Using Vision Transformer

DOI

10.2991/978-94-6239-693-7_25How to use a DOI?

Keywords

Medical image analysis; Dental X-ray Image; Vision Transformer; Deep Learning; Image Classification

Abstract

Dental disease is considered to be one of the biggest healthcare issues worldwide, and the most widely distributed chronic infection known today. The identification of dental issues via image assessment early on can help dentists develop better treatment plans and manage more severe health issues sooner. Although many AI models, most notably CNN (Convolutional Neural Network) models, have been found to work well for assessing images of dental X-rays, AI models are frequently plagued by the challenges of applying such models directly in actual clinical environments. One of the major downsides to the use of CNN models is that these models assess a small and localised area of the dental radiograph at a time, thereby losing the connection between distant portions of the dental radiographs. To remedy this limitation, this research introduced a new Vision Transformer model focused on dental image categorisation. Testing of this model was conducted on a broad sample of dental radiographs, representing a diverse patient group, to validate the reliability of the model for a variety of patients with different types of dental pathology. Findings validate that the Architecture developed for Vision Transformer (ViT) meets or exceeds the accuracy and consistency of conventional deep learning approaches. In particular, the model exhibits far greater success at detecting early stage cavities compared to conventional software. Research demonstrates that the absence of traditional convolutional component permits the model to concentrate more accurately upon the individualized features of dental caries (cavity) detection and such serves to furnish a more accurate instrument for dentists to quickly make an informed decision in their routine practice.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - N. Vijayendra
AU  - M. Dinesh
AU  - K. Seethalakshmi
AU  - A. Bhagyalakshmi
AU  - R. Panneerselvi
PY  - 2026
DA  - 2026/06/16
TI  - Dental Cavity Detection Using Vision Transformer
BT  - Proceedings of the International Conference on Intelligent Systems for a Sustainable Future (ISSF 2026)
PB  - Atlantis Press
SP  - 243
EP  - 249
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6239-693-7_25
DO  - 10.2991/978-94-6239-693-7_25
ID  - Vijayendra2026
ER  -