Deep-learning approach for caries detection and segmentation on dental bitewing radiographs.

Journal: Oral radiology
Published Date: Nov 22, 2021

Abstract

OBJECTIVES: The aim of this study is to recommend an automatic caries detection and segmentation model based on the Convolutional Neural Network (CNN) algorithms in dental bitewing radiographs using VGG-16 and U-Net architecture and evaluate the clinical performance of the model comparing to human observer.

Authors

  • İbrahim Şevki Bayrakdar
    Department of Oral Diagnosis and Radiology, Faculty of Dentistry, Eskişehir Osmangazi University, Eskişehir, Turkey.
  • Kaan Orhan
    Department of Dentomaxillofacial Radiology, Faculty of Dentistry, Dentomaxillofacial Radiologist, Ankara University, Ankara, Turkey.
  • Serdar Akarsu
    Department of Restorative Dentistry, Faculty of Dentistry, Ordu University, Ordu, Turkey.
  • Özer Çelik
    Department of Mathematics and Computer, Faculty of Science and Letters, Eskişehir Osmangazi University, Eskişehir, Turkey.
  • Samet Atasoy
    Department of Restorative Dentistry, Faculty of Dentistry, Ordu University, Ordu, Turkey.
  • Adem Pekince
    Department of Oral and Maxillofacial Radiology, Faculty of Dentistry, Karabuk University, Karabuk, Turkey.
  • Yasin Yasa
    Department of Oral and Maxillofacial Radiology, Faculty of Dentistry, Ordu University, Ordu, Turkey.
  • Elif Bilgir
    Department of Oral and Maxillofacial Radiology, Faculty of Dentistry, Eskisehir Osmangazi University, Eskisehir, Turkey.
  • Hande Sağlam
    Department of Oral and Maxillofacial Radiology, Faculty of Dentistry, Eskisehir Osmangazi University, Eskişehir, Turkey.
  • Ahmet Faruk Aslan
    Department of Mathematics and Computer Science, Faculty of Science, Eskisehir Osmangazi University, Eskisehir, Turkey.
  • Alper Odabaş
    Department of Mathematics and Computer Science, Faculty of Science, Eskisehir Osmangazi University, Eskisehir, Turkey.

Keywords

External Resources

Popular Topics
Recent Journals