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

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%