Please use this identifier to cite or link to this item: http://earsiv.odu.edu.tr:8080/xmlui/handle/11489/5224
Title: Deep-learning approach for caries detection and segmentation on dental bitewing radiographs
Authors: Bayrakdar, Ibrahim Sevki
Orhan, Kaan
Akarsu, Serdar
Celik, Ozer
Atasoy, Samet
Pekince, Adem
Yasa, Yasin
Bilgir, Elif
Saglam, Hande
Aslan, Ahmet Faruk
Odabas, Alper
Ordu Üniversitesi
0000-0002-7816-1635
0000-0002-6598-8262
0000-0002-9757-5331
0000-0002-7439-1046
0000-0001-5036-9867
0000-0001-9521-4682
0000-0002-4388-2125
0000-0001-7792-5106
0000-0002-4409-3101
0000-0001-6768-0176
Keywords: Artificial intelligence, Deep learning, Tooth caries, Bitewing radiographs, Dentistry
NEURAL-NETWORK
Issue Date: 2022
Publisher: SPRINGER-NEW YORK
Citation: Bayrakdar, IS., Orhan, K., Akarsu, S., Çelik, Ö., Atasoy, S., Pekince, A., Yasa, Y., Bilgir, E., Saglam, H., Aslan, AF., Odabas, A. (2022). Deep-learning approach for caries detection and segmentation on dental bitewing radiographs. Oral Radiol., 38(4), 468-479. https://doi.org/10.1007/s11282-021-00577-9
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. Methods A total of 621 anonymized bitewing radiographs were used to progress the Artificial Intelligence (AI) system (CranioCatch, Eskisehir, Turkey) for the detection and segmentation of caries lesions. The radiographs were obtained from the Radiology Archive of the Department of Oral and Maxillofacial Radiology of the Faculty of Dentistry of Ordu University. VGG-16 and U-Net implemented with PyTorch models were used for the detection and segmentation of caries lesions, respectively. Results The sensitivity, precision, and F-measure rates for caries detection and caries segmentation were 0.84, 0.81; 0.84, 0.86; and 0.84, 0.84, respectively. Comparing to 5 different experienced observers and AI models on external radiographic dataset, AI models showed superiority to assistant specialists. Conclusion CNN-based AI algorithms can have the potential to detect and segmentation of dental caries accurately and effectively in bitewing radiographs. AI algorithms based on the deep-learning method have the potential to assist clinicians in routine clinical practice for quickly and reliably detecting the tooth caries. The use of these algorithms in clinical practice can provide to important benefit to physicians as a clinical decision support system in dentistry.
Description: WoS Categories: Dentistry, Oral Surgery & Medicine
Web of Science Index: Science Citation Index Expanded (SCI-EXPANDED)
Research Areas: Dentistry, Oral Surgery & Medicine
URI: http://dx.doi.org/10.1007/s11282-021-00577-9
https://www.webofscience.com/wos/woscc/full-record/WOS:000721401600001
http://earsiv.odu.edu.tr:8080/xmlui/handle/11489/5224
ISSN: 0911-6028
1613-9674
Appears in Collections:Ağız, Diş ve Çene Radyolojisi

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.