Object Detection on Dental X-ray Images Using Region Based Convolutional Neural Networks

EasyChair Preprint 7359

Abstract

In dentistry, Dental X-ray systems help dentists by showing the basic structure of tooth bones to detect various kinds of dental problems. However, depending only on dentists can sometimes impede treatment since identifying things in X-ray pictures requires human effort, experience, and time, which can lead to delays in the process. In image classification, segmentation, object identification, and machine translation, recent improvements in deep learning have been effective. Deep learning may be used in X-ray systems to detect objects. Radiology and pathology have benefited greatly from the use of deep convolutional neural networks, which are a fast growing new area of medical study. Deep learning techniques for the identification of objects in dental X-ray systems are the focus of this study. As part of the study, Deep Neural Network algorithms were evaluated for their ability to identify dental cavities and a root canal on periapical radiographs. An automated detection method for dental caries and root canals in X-rays is presented utilizing Tensor Flow tool packages' faster regions with convolutional neural network characteristics (faster R-CNN).

Keyphrases: Convolutional Neural Network, Dental X-ray Image., Faster R-CNN, deep learning

@booklet{EasyChair:7359,
  author    = {Rakib Hossen and Minhazul Arefin and Mohammed Nasir Uddin},
  title     = {Object Detection on Dental X-ray Images Using Region Based Convolutional Neural Networks},
  howpublished = {EasyChair Preprint 7359},
  year      = {EasyChair, 2022}}