A Validation Employing Convolutional Neural Network for the Radiographic Detection of Absence or Presence of Teeth.

María Prados-Privado,Carlos Ivorra,Carlos Hugo Martínez-Martínez,Antonio Blázquez Torres,Javier García Villalón

doi:10.3390/jcm10061186

Abstract

Dental radiography plays an important role in clinical diagnosis, treatment and making decisions. In recent years, efforts have been made on developing techniques to detect objects in images. The aim of this study was to detect the absence or presence of teeth using an effective convolutional neural network, which reduces calculation times and has success rates greater than 95%. A total of 8000 dental panoramic images were collected. Each image and each tooth was categorized, independently and manually, by two experts with more than three years of experience in general dentistry. The neural network used consists of two main layers: object detection and classification, which is the support of the previous one. A Matterport Mask RCNN was employed in the object detection. A ResNet (Atrous Convolution) was employed in the classification layer. The neural model achieved a total loss of 0.76% (accuracy of 99.24%). The architecture used in the present study returned an almost perfect accuracy in detecting teeth on images from different devices and different pathologies and ages.

Highlights

A very important element in any field of medicine and, in particular, of dentistry, is to have good clinical diagnosis with which it is possible to make decisions about how the treatment will be executed [1]
Sometimes misdiagnosis may occur due to several dentist factors such as fatigue, emotions and low experience levels, but these situations can be reduced thanks to the use of tools based on artificial intelligence to interpret dental X-ray images [4]
The neural network used consists of two main layers: object detection and classificaThe neural network used consists of two main layers: object detection and classification, which is the support of the previous one

Summary

Introduction

A very important element in any field of medicine and, in particular, of dentistry, is to have good clinical diagnosis with which it is possible to make decisions about how the treatment will be executed [1]. An important role in clinical diagnosis, treatment and surgery is played by dental radiography since it can be used to find bone loss, cavities and hidden dental structures among others [2,3]. Dental images can be classified as intraoral or extraoral images. Panoramic X-ray images are extraoral radiographs that are used to detect dental problems in the jaw and the maxilla. Periapical images or bitewing images are an example of intraoral radiographies with which it is possible to get details of certain area of mouth [2,5]

Objectives

Methods

Results

Discussion

Conclusion