Eichner classification based on panoramic X-ray images using deep learning: A pilot study

Abstract

BACKGROUND: Research using panoramic X-ray images using deep learning has been progressing in recent years. There is a need to propose methods that can classify and predict from image information. OBJECTIVE: In this study, Eichner classification was performed on image processing based on panoramic X-ray images. The Eichner classification was based on the remaining teeth, with the aim of making partial dentures. This classification was based on the condition that the occlusal position was supported by the remaining teeth in the upper and lower jaws. METHODS: Classification models were constructed using two convolutional neural network methods: the sequential and VGG19 models. The accuracy was compared with the accuracy of Eichner classification using the sequential and VGG19 models. RESULTS: Both accuracies were greater than 81%, and they had sufficient functions for the Eichner classification. CONCLUSION: We were able to build a highly accurate prediction model using deep learning scratch sequential model and VGG19. This predictive model will become part of the basic considerations for future AI research in dentistry.