Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Oct;38(4):468-479.
doi: 10.1007/s11282-021-00577-9. Epub 2021 Nov 22.

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

Ibrahim Sevki Bayrakdar  1   2 , Kaan Orhan  3   4 , Serdar Akarsu  5 , Özer Çelik  5   4 , Samet Atasoy  6 , Adem Pekince  7 , Yasin Yasa  8 , Elif Bilgir  9 , Hande Sağlam  9 , Ahmet Faruk Aslan  5 , Alper Odabaş  5
Affiliations

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

Ibrahim Sevki Bayrakdar et al. Oral Radiol. 2022 Oct.

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.

Keywords: Artificial intelligence; Bitewing radiographs; Deep learning; Dentistry; Tooth caries.

PubMed Disclaimer

Comment in

References

    1. Frencken JE, Sharma P, Stenhouse L, Green D, Laverty D, Dietrich T. Global epidemiology of dental caries and severe periodontitis—a comprehensive review. J Clin Periodontol. 2017;44(Suppl 18):S94-s105.
    1. Stookey GK, Jackson RD, Zandona AG, Analoui M. Dental caries diagnosis. Dent Clin North Am. 1999;43:665-77 vi.
    1. Hellén-Halme K, Petersson GH. Influence of education level and experience on detection of approximal caries in digital dental radiographs. An in vitro study. Swed Dent J. 2010;34:63–9.
    1. Hosny A, Parmar C, Quackenbush J, Schwartz LH, Aerts H. Artificial intelligence in radiology. Nat Rev Cancer. 2018;18:500–10.
    1. Leite AF, Van Gerven A, Willems H, Beznik T, Lahoud P, Gaêta-Araujo H, et al. Artificial intelligence-driven novel tool for tooth detection and segmentation on panoramic radiographs. Clin Oral Invest. 2020. https://doi.org/10.1007/s00784-020-03544-6 . - DOI

Publication types

LinkOut - more resources