Caries segmentation on tooth X-ray images with a deep network.

Objectives: Deep learning has been a promising technology in many biomedical applications. In this study, a deep network was proposed aiming for caries segmentation on the clinically collected tooth X-ray images.

Methods: The proposed network inherited the skip connection characteristic from the widely used U-shaped network, and creatively adopted vision Transformer, dilated convolution, and feature pyramid fusion methods to enhance the multi-scale and global feature extraction capability. It was then trained on the clinically self-collected and augmented tooth X-ray image dataset, and the dice similarity and pixel classification precision were calculated for the network's performance evaluation.

Results: Experimental results revealed an average dice similarity of 0.7487 and an average pixel classification precision of 0.7443 on the test dataset, which outperformed the compared networks such as UNet, Trans-UNet, and Swin-UNet, demonstrating the remarkable improvement of the proposed network.

Conclusions: This study contributed to the automatic caries segmentation by using a deep network, and highlighted the potential clinical utility value.