Deep learning and clustering approaches for dental implant size classification based on periapical radiographs

Abstract

This study investigated two artificial intelligence (AI) methods for automatically classifying dental implant diameter and length based on periapical radiographs. The first method, deep learning (DL), involved utilizing the pre-trained VGG16 model and adjusting the fine-tuning degree to analyze image data obtained from periapical radiographs. The second method, clustering analysis, was accomplished by analyzing the implant-specific feature vector derived from three key points coordinates of the dental implant using the k-means++ algorithm and adjusting the weight of the feature vector. DL and clustering model classified dental implant size into nine groups. The performance metrics of AI models were accuracy, sensitivity, specificity, F1-score, positive predictive value, negative predictive value, and area under the receiver operating characteristic curve (AUC-ROC). The final DL model yielded performances above 0.994, 0.950, 0.994, 0.974, 0.952, 0.994, and 0.975, respectively, and the final clustering model yielded performances above 0.983, 0.900, 0.988, 0.923, 0.909, 0.988, and 0.947, respectively. When comparing the AI model before tuning and the final AI model, statistically significant performance improvements were observed in six out of nine groups for DL models and four out of nine groups for clustering models based on AUC-ROC. Two AI models showed reliable classification performances. For clinical applications, AI models require validation on various multicenter data.

Figure 1

A schematic description of deep learning and clustering approaches: (a) data acquisition and data splitting for deep learning and clustering; (b) comparing of deep learning and clustering process.

Figure 2

Results for implant size classification using deep learning and clustering approaches: (a) relationship between the fine-tuning degree and deep learning model accuracy; (b) relationship between the weight of the feature vector and clustering model accuracy; (c) confusion matrix of the final DL model result; (d) confusion matrix of the final clustering model result.

Figure 3

Bone level implant images and their Grad-CAM of the final deep learning model, described with true label, predicted label, and softmax value.

Figure 4

Scatter plot of the clustering analysis: (a) scatter plot of the feature vectors for clustering; (b) scatter plot of the final clustering model with the color code and representation of centroids of clusters (yellow circles).

Figure 5

Grad-CAM images for different fine-tuning degrees and training epochs in deep learning approach.

Figure 6

Six cases of the pre-trained VGG16 model by adjusting the fine-tuning degree.

Figure 7

Key point selection and feature extraction for clustering.