Deep learning for early dental caries detection in bitewing radiographs

Abstract

The early detection of initial dental caries enables preventive treatment, and bitewing radiography is a good diagnostic tool for posterior initial caries. In medical imaging, the utilization of deep learning with convolutional neural networks (CNNs) to process various types of images has been actively researched, with promising performance. In this study, we developed a CNN model using a U-shaped deep CNN (U-Net) for caries detection on bitewing radiographs and investigated whether this model can improve clinicians' performance. The research complied with relevant ethical regulations. In total, 304 bitewing radiographs were used to train the CNN model and 50 radiographs for performance evaluation. The diagnostic performance of the CNN model on the total test dataset was as follows: precision, 63.29%; recall, 65.02%; and F1-score, 64.14%, showing quite accurate performance. When three dentists detected caries using the results of the CNN model as reference data, the overall diagnostic performance of all three clinicians significantly improved, as shown by an increased sensitivity ratio (D1, 85.34%; D1', 92.15%; D2, 85.86%; D2', 93.72%; D3, 69.11%; D3', 79.06%; p < 0.05). These increases were especially significant (p < 0.05) in the initial and moderate caries subgroups. The deep learning model may help clinicians to diagnose dental caries more accurately.

Figure 1

Example of the analysis of dental structures and caries tagging. The observers drew lines for the segmentation of dental structures (enamel, dentin, pulp, metal restoration, tooth-color restorations, gutta percha) and dental caries on the bitewing radiographs. *No software was used to generate the image. The picture used in Figure is a file printed using the source code that we implemented ourselves.

Figure 2

Flowchart of the detection of dental caries in the deep learning model, showing two models: the U-Net for caries segmentation (U-CS), and the U-Net for structure segmentation (U-SS). *No software was used to generate the image. The picture used in Figure is a file printed using the source code that we implemented ourselves.

Figure 3

Comparison of diagnostic performance (sensitivity) between three dentists (before and after revision) and the deep learning model. Mean ± standard deviation, CNN convolutional neural network, CI confidence intervals. *The significance level was set at alpha = 0.05 in the post hoc analysis. Statistical analyses were performed using SAS (version 9.4, SAS Inc., Cary, NC, USA), GEEs were used.