An Explainable Deep Learning Model to Prediction Dental Caries Using Panoramic Radiograph Images

Abstract

Dental caries is the most frequent dental health issue in the general population. Dental caries can result in extreme pain or infections, lowering people’s quality of life. Applying machine learning models to automatically identify dental caries can lead to earlier treatment. However, physicians frequently find the model results unsatisfactory due to a lack of explainability. Our study attempts to address this issue with an explainable deep learning model for detecting dental caries. We tested three prominent pre-trained models, EfficientNet-B0, DenseNet-121, and ResNet-50, to determine which is best for the caries detection task. These models take panoramic images as the input, producing a caries–non-caries classification result and a heat map, which visualizes areas of interest on the tooth. The model performance was evaluated using whole panoramic images of 562 subjects. All three models produced remarkably similar results. However, the ResNet-50 model exhibited a slightly better performance when compared to EfficientNet-B0 and DenseNet-121. This model obtained an accuracy of 92.00%, a sensitivity of 87.33%, and an F1-score of 91.61%. Visual inspection showed us that the heat maps were also located in the areas with caries. The proposed explainable deep learning model diagnosed dental caries with high accuracy and reliability. The heat maps help to explain the classification results by indicating a region of suspected caries on the teeth. Dentists could use these heat maps to validate the classification results and reduce misclassification.

Teeth segmentation and carious lesions segmentation in panoramic X-ray images using CariSeg, a networks' ensemble

“…In the same year, Oztekin et al [21] introduced a model that is given a panoramic X-ray as an input produces a classification for each tooth as healthy or not. It also produces a heat map as an output, which is meant to indicate the cavities inside the image.…”

Deep learning architectures in dental diagnostics: a systematic comparison of techniques for accurate prediction of dental disease through x-ray imaging

“…To find the most effective model for the caries identification position, Oztekin et al . (2023) investigated three distinct models that include EfficientNet-B0, ResNet-50 and DenseNet-121.…”

Designing Interpretable ML System to Enhance Trustworthy AI in Healthcare: A Systematic Review of the Last Decade to A Proposed Robust Framework

“…SMOTE, introduced by [64], is an oversampling technique that relies on k-nearest neighbors to generate synthetic samples. For instance, in [65] data augmentation method has been applied to prevent the negative effects of the small number of dental images for detecting caries. Moreover, Autoencoders (AE) techniques can be used to generate artificial data, such as this study: an AI framework for Early diagnosis of coronary artery disease, applying SMOTE, autoencoders and CNN, and they achieved higher accuracy after using data augmentation method [66].…”