SavedAdd your journal

Journals / Dicle Dental Journal / 2026 / Volume: 27 Issue: 2

A deep learning approach to automatic caries segmentation in dental periapical radiographs

Selin Yeşiltepe(ADNAN MENDERES ÜNİVERSİTESİ)0000-0002-6857-1411
Özge Çeliksöz(OSMANGAZİ ÜNİVERSİTESİ)0000-0002-4879-3631
Semih Tanrıverdi(İSTANBUL GELİŞİM ÜNİVERSİTESİ, DİŞ HEKİMLİĞİ FAKÜLTESİ)0009-0004-0486-1315
Şuayip Burak Duman(İNÖNÜ ÜNİVERSİTESİ)0000-0003-2552-0187
İbrahim Şevki Bayrakdar(OSMANGAZİ ÜNİVERSİTESİ)0000-0001-5036-9867
Ali Syed(Case Western Reserve University)0000-0001-8051-0964
Özer Çelik(OSMANGAZİ ÜNİVERSİTESİ)0000-0002-4409-3101
Kaan Orhan(ANKARA ÜNİVERSİTESİ, DİŞ HEKİMLİĞİ FAKÜLTESİ)0000-0001-6768-0176
Pages
—
Publication Date
2026-08-31
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

When probable caries lesions are detected, this technique can help with clinical decision-making, which has a direct impact on practice workflow and clinical service efficiency.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Aims: This study aims to design and train a convolutional neural networks (CNN) -based deep learning model to detect caries in periapical radiographs and evaluate its diagnostic performance.
📊
Key Findings & Data:Methods: A total of 1,613 artifact-free periapical radiographs included in the study.
💡
Conclusion & Impact:When probable caries lesions are detected, this technique can help with clinical decision-making, which has a direct impact on practice workflow and clinical service efficiency.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:artificial intelligence · dental caries · periapical radiography

Abstract

Aims: This study aims to design and train a convolutional neural networks (CNN) -based deep learning model to detect caries in periapical radiographs and evaluate its diagnostic performance. Methods: A total of 1,613 artifact-free periapical radiographs included in the study. Three observers provided ground truth annotations for each label on periapical images using the XXX Labeling Tool (XXX, XXX). Polygonal boundaries were drawn around all caries lesions on periapical radiographs. Automatic caries segmentation models (XX, XX, XX) were designed in periapical radiographs using PyTorch implemented U-Net architecture. Model performance was assessed using sensitivity, precision, and F1 score metrics. Results: True positive, false positive and false negative were 114, 18 and 17, respectively. The sensitivity, precision, and F1-measure values of artificial intelligence (AI) model for caries segmentation in internal test data set were found as 0.8924, 0.8867, and 0.8895, respectively and in external test data set were found as 0.7358, 0.8298, 0.7800, respectively. Findings support the potential role of AI as a decision support tool, particularly in situations where observer variability or limited expertise may influence diagnostic outcomes. Conclusion: This CNN-based model developed in this study demonstrated promising ability to diagnosing interproximal caries lesions on digital periapical radiographs. When probable caries lesions are detected, this technique can help with clinical decision-making, which has a direct impact on practice workflow and clinical service efficiency.

Özet

Amaç: Bu çalışmanın amacı, periapikal radyograflarda çürüklerin otomatik olarak tespit edilmesi ve segmentasyonu için konvolüsyonel sinir ağları (CNN) tabanlı bir derin öğrenme modeli tasarlamak ve eğitmek ve tanısal performansını değerlendirmektir. Yöntemler: Çalışmaya toplam 1.613 adet artefaktsız periapikal radyograf dahil edilmiştir. Gerçek referans anotasyonları, üç bağımsız gözlemci tarafından XXX Etiketleme Aracı (XXX, XXX) kullanılarak sağlanmıştır. Periapikal görüntüler üzerindeki tüm çürük lezyonlarının etrafına çokgen sınırlar manuel olarak çizilmiştir. PyTorch ortamında uygulanmış U-Net mimarisi kullanılarak otomatik çürük segmentasyonu modelleri (XX, XX, XX) geliştirilmiştir. Model performansı duyarlılık, kesinlik (precision) ve F1-skoru metrikleri kullanılarak değerlendirilmiştir. Bulgular: Doğru pozitif, yanlış pozitif ve yanlış negatif sayıları sırasıyla 114, 18 ve 17 olarak bulunmuştur. Yapay zekâ modelinin çürük segmentasyonu için iç test veri setindeki duyarlılık, kesinlik ve F1-skoru değerleri sırasıyla 0,8924, 0,8867 ve 0,8895; dış test veri setinde ise sırasıyla 0,7358, 0,8298 ve 0,7800 olarak saptanmıştır. Bu bulgular, özellikle gözlemci değişkenliğinin veya sınırlı uzmanlığın tanısal sonuçları etkileyebileceği durumlarda, yapay zekânın klinik karar destek aracı olarak potansiyel bir rolü olduğunu göstermektedir. Sonuç: Bu çalışmada geliştirilen CNN tabanlı model, dijital periapikal radyograflarda interproksimal çürük lezyonlarının tespiti ve segmentasyonunda umut verici bir başarı göstermiştir. Olası çürük lezyonları belirlendiğinde, bu yaklaşım klinik karar verme sürecine yardımcı olabilir ve iş akışı verimliliği ile genel klinik hizmet sunumunu iyileştirebilir.

🔖

Cite This Article

Yeşiltepe, S., Çeliksöz, Ö., Tanrıverdi, S., Duman, Ş. B., Bayrakdar, İ. Ş., Syed, A., Çelik, Ö., Orhan, K. (2026). A deep learning approach to automatic caries segmentation in dental periapical radiographs. Dicle Dental Journal, Volume: 27 Issue: 2. https://ajindex.com/articles/1643243

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (37)

  1. Kassebaum NJ, Bernabé E, Dahiya M, Bhandari B, Murray CJ, Marcenes W. Global burden of untreated caries: a systematic review and meta-regression. J Dent Res. 2015;94(5):650–658.
  2. Schwendicke F, Tzschoppe M, Paris S. Radiographic caries detection: a systematic review and meta-analysis. J Dent. 2015;43:924–933.
  3. Fejerskov O, Kidd EAM. Dental caries: the disease and its clinical management. Hoboken, NJ: John Wiley. 2009.
  4. Chan M, Dadul T, Langlais R, Russell D, Ahmad M. Accuracy of extraoral bite-wing radiography in detecting proximal caries and crestal bone loss. J Am Dent Assoc. 2018;149(1):51-58.
  5. Vandenberghe B, Jacobs R, Bosmans H. Modern dental imaging: a review of the current technology and clinical applications in dental practice. Eur Radiol. 2010;20(11):2637-2655.
  6. Chartrand G, Cheng PM, Vorontsov E, et al. Deep learning: a primer for radiologists. Radiographics. 2017;37:2113-2131.
  7. Lee JG, Jun S, Cho YW, et al. Deep learning in medical imaging: general overview. Korean J Radiol. 2017;18(4):570-584.
  8. Choy G, Khalilzadeh O, Michalski M, et al. Current applications and future impact of machine learning in radiology. Radiology. 2018;288(2):318-328.
  9. Yates EJ, Yates LC, Harvey H. Machine learning "red dot": open-source, cloud, deep convolutional neural networks in chest radiograph binary normality classification. Clin Radiol. 2018;73(9):827-831.
  10. Hosny A, Parmar C, Quackenbush J, Schwartz LH, Aerts HJWL. Artificial intelligence in radiology. Nat Rev Cancer. 2018;18(8):500-510.
  11. Dratsch T, Caldeira L, Maintz D, Dos Santos DP. Artificial intelligence abstracts from the European Congress of Radiology: analysis of topics and compliance with the STARD for abstracts checklist. Insights Imaging. 2020;11(1):59.
  12. Hiraiwa T, Ariji Y, Fukuda M, et al. A deep-learning artificial intelligence system for assessment of root morphology of the mandibular first molar on panoramic radiography. Dentomaxillofac Radiol. 2019;48(3):20180218.
  13. Ariji Y, Yanashita Y, Kutsuna S, et al. Automatic detection and classification of radiolucent lesions in the mandible on panoramic radiographs using a deep learning object detection technique. Oral Surg Oral Med Oral Pathol Oral Radiol. 2019;128(4):424-430.
  14. Lee JH, Kim DH, Jeong SN. Diagnosis of cystic lesions using panoramic and cone beam computed tomographic images based on deep learning neural network. Oral Dis. 2020;26(1):152-158.
  15. Ekert T, Krois J, Meinhold L, et al. Deep learning for the radiographic detection of apical lesions. J Endod. 2019;45(7):917-922.e5.
  16. Orhan K, Bayrakdar IS, Ezhov M, Kravtsov A, Özyürek T. Evaluation of artificial intelligence for detecting periapical pathosis on cone-beam computed tomography scans. Int Endod J. 2020;53(5):680-689.
  17. Lee JH, Kim DH, Jeong SN, Choi SH. Diagnosis and prediction of periodontally compromised teeth using a deep learning-based convolutional neural network algorithm. J Periodontal Implant Sci. 2018;48(2):114-123.
  18. Krois J, Ekert T, Meinhold L, et al. Deep learning for the radiographic detection of periodontal bone loss. Sci Rep. 2019;9(1):8495.
  19. Fukuda M, Inamoto K, Shibata N, et al. Evaluation of an artificial intelligence system for detecting vertical root fracture on panoramic radiography. Oral Radiol. 2020;36(4):337-343.
  20. Devito KL, de Souza Barbosa F, Felippe Filho WN. An artificial multilayer perceptron neural network for diagnosis of proximal dental caries. Oral Surg Oral Med Oral Pathol Oral Radiol Endod. 2008;106(6):879-884.
  21. Valizadeh S, Goodini M, Ehsani S, Mohseni H, Azimi F, Bakhshandeh H. Designing of a computer software for detection of approximal caries in posterior teeth. Iran J Radiol. 2015;12(4):e16242.
  22. Schwendicke F, Elhennawy K, Paris S, Friebertshuser P, Krois J. Deep learning for caries lesion detection in near-infrared light transillumination images: a pilot study. J Dent. 2020;92:103260.
  23. Zhang X, Liang Y, Li W, et al. Development and evaluation of deep learning for screening dental caries from oral photographs. Oral Dis. 2022;28(1):173-181.
  24. Cantu AG, Gehrung S, Krois J, et al. Detecting caries lesions of different radiographic extension on bitewings using deep learning. J Dent. 2020;100:103425.
  25. Lee JH, Kim DH, Jeong SN, Choi SH. Detection and diagnosis of dental caries using a deep learning-based convolutional neural network algorithm. J Dent. 2018;77:106-111.
  26. Soffer S, Ben-Cohen A, Shimon O, Amitai MM, Greenspan H, Klang E. Convolutional neural networks for radiologic images: a radiologist's guide. Radiology. 2019;290(3):590-606.
  27. Hung K, Montalvao C, Tanaka R, Kawai T, Bornstein MM. The use and performance of artificial intelligence applications in dental and maxillofacial radiology: a systematic review. Dentomaxillofac Radiol. 2020;49(1):20190107.
  28. Litjens G, Kooi T, Bejnordi BE, et al. A survey on deep learning in medical image analysis. Med Image Anal. 2017;42:60-88.
  29. Li Z, Zhang X, Müller H, Zhang S. Large-scale retrieval for medical image analytics: a comprehensive review. Med Image Anal. 2018;43:66-84.
  30. Xue Y, Zhang R, Deng Y, Chen K, Jiang T. A preliminary examination of the diagnostic value of deep learning in hip osteoarthritis. PLoS One. 2017;12:e0178992.
  31. Gyftopoulos S, Lin D, Knoll F, Doshi AM, Rodrigues TC, Recht MP. Artificial intelligence in musculoskeletal imaging: current status and future directions. AJR Am J Roentgenol. 2019;213(3):506–513.
  32. Xue Y, Chen S, Qin J, Liu Y, Huang B, Chen H. Application of deep learning in automated analysis of molecular images in cancer: a survey. Contrast Media Mol Imaging. 2017;2017:1-10.
  33. Schwendicke F, Golla T, Dreher M, Krois J. Convolutional neural networks for dental image diagnostics: a scoping review. J Dent. 2019;91:103226.
  34. Bayrakdar IS, Orhan K, Akarsu S, et al. Deep-learning approach for caries detection and segmentation on dental bitewing radiographs. Oral Radiol. 2022;38(4):468-479.
  35. Bayraktar Y, Ayan E. Diagnosis of interproximal caries lesions with deep convolutional neural network in digital bitewing radiographs. Clin Oral Investig. 2022;26(1):623-632.
  36. Asci E, Kilic M, Celik O, et al. A deep learning approach to automatic tooth caries segmentation in panoramic radiographs of children in primary dentition, mixed dentition, and permanent dentition. Children (Basel). 2024;11(6),690.
  37. Liu J, Zhang H, Chen J, et al. Automated detection and segmentation of dental caries using a novel cascaded learning approach. Biomed Signal Process Control. 2025;102:107344.