Optimizing Dental Implant Identification using Deep Learning Leveraging Artificial Data

Abstract

Abstract This study aims to evaluate the potential enhancement in implant classification performance achieved by incorporating artificially generated images of commercially available products into a deep learning process of dental implant classification using panoramic X-ray images. To supplement an existing dataset of 7,946 in vivo dental implant images, a three-dimensional scanner was employed to create an implant surface model. Subsequently, it was used to generate two-dimensional X-ray images, which were compiled with original images to create a comprehensive dataset. Image classification of 10 types of implants was performed using ResNet50 under the following dataset conditions: (A) images of implants in vivo, (B) artificial implant images without background adjustments, and (C) implant images with background adjustments, derived from in vivo images. The classification accuracy for the three datasets is as follows: A registered at 0.8888; B, 0.903, and C, 0.9146. Notably, dataset C demonstrated the highest performance and had the most optimal feature distribution. In the context of deep learning classifiers for dental implants using panoramic X-ray images, incorporating artificially generated X-ray images—designed to mirror the appearance of human body implants—proved to be the most beneficial in enhancing the performance of the classification model.