A Comprehensive Exploration of Neural Networks for Dental Caries Detection

Abstract

Dental caries, an illness due to bacteria that worsens with time, is the most common cause of tooth loss. This occurs as an outcome of least oral hygiene, which in addition contributes to a variety of dental disorders. Children's dental health will benefit considerably if caries can be detected at an early stage via tele-dentistry technology. Because severe caries causes disease and discomfort, tooth extraction may be necessary. As a result, early detection and diagnosis of these caries are the researchers' priority priorities. Soft computing techniques are commonly employed in dentistry to simplify diagnosis and reduce screening time. The goal of this study is to employ x-ray scanned images to detect dental cavities early on so that treatment can be completed promptly and effectively. As a tele-informatic oral health care system, this classification also applies to tele-dental care. We used a convolution neural network (CNN) deep learning model in the suggested work. We trained several CNN deep learning models. Training and testing were performed on a binary dataset with and without caries photos. The classification precision of CNN models is noted.