Machine learning-based approaches for disease and material detection in dental x-ray images

Recently, rapid developments in computer software and hardware technology, along with the development of the digital world and communication, have led to the popularity of the concept of the internet of things. Technological advances also have a major impact, especially in areas such as object classification, object detection, and pattern recognition. This Ph.D. thesis study deals with the detection of disease and material by using deep learning methods in dental x-ray images. Today, dental health is an important issue in the field of medicine and accurate analysis of dental x-ray images is of great importance for correct diagnosis and treatment. The thesis study takes a step forward in using deep learning methods in dental x-ray images, which have the potential to help dentists make more accurate and faster decisions in the diagnosis and treatment processes. In the current studies in the literature, it has been observed that there is a lack of sufficient and original data sets that can be used in this field. Therefore, as a part of the thesis study, an original data set was created by examining it with the help of a specialist dentist. This original data set forms the basis of the thesis and is evaluated on the accuracy and performance of the proposed deep learning-based algorithms. In addition, these original methods were compared with current models to analyze the success of these proposed methods. The results obtained contribute to the development of more reliable and effective methods for the detection of disease and material in dental x-ray images by eliminating the deficiency in the literature, that the proposed methods are effective.