Journal of the korean academy of Pediatric Dentistry (대한소아치과학회지)

Korean Academy of Pediatric Dentistry (대한소아치과학회)
권호 표지
DOI QR코드

DOI QR Code

Detection of Proximal Caries Lesions with Deep Learning Algorithm

심층학습 알고리즘을 활용한 인접면 우식 탐지

  • Hyuntae, Kim (Department of Pediatric Dentistry, School of Dentistry, Seoul National University) ;
  • Ji-Soo, Song (Department of Pediatric Dentistry, School of Dentistry, Seoul National University) ;
  • Teo Jeon, Shin (Department of Pediatric Dentistry, School of Dentistry, Seoul National University) ;
  • Hong-Keun, Hyun (Department of Pediatric Dentistry, School of Dentistry, Seoul National University) ;
  • Jung-Wook, Kim (Department of Pediatric Dentistry, School of Dentistry, Seoul National University) ;
  • Ki-Taeg, Jang (Department of Pediatric Dentistry, School of Dentistry, Seoul National University) ;
  • Young-Jae, Kim (Department of Pediatric Dentistry, School of Dentistry, Seoul National University)
  • 김현태 (서울대학교 치의학대학원 소아치과학교실) ;
  • 송지수 (서울대학교 치의학대학원 소아치과학교실) ;
  • 신터전 (서울대학교 치의학대학원 소아치과학교실) ;
  • 현홍근 (서울대학교 치의학대학원 소아치과학교실) ;
  • 김정욱 (서울대학교 치의학대학원 소아치과학교실) ;
  • 장기택 (서울대학교 치의학대학원 소아치과학교실) ;
  • 김영재 (서울대학교 치의학대학원 소아치과학교실)
  • Received : 2021.10.17
  • Accepted : 2021.11.28
  • Published : 2022.05.31
Download PDF
⟨ Previous Next ⟩

Abstract

This study aimed to evaluate the effectiveness of deep convolutional neural networks (CNNs) for diagnosis of interproximal caries in pediatric intraoral radiographs. A total of 500 intraoral radiographic images of first and second primary molars were used for the study. A CNN model (Resnet 50) was applied for the detection of proximal caries. The diagnostic accuracy, sensitivity, specificity, receiver operating characteristic (ROC) curve, and area under ROC curve (AUC) were calculated on the test dataset. The diagnostic accuracy was 0.84, sensitivity was 0.74, and specificity was 0.94. The trained CNN algorithm achieved AUC of 0.86. The diagnostic CNN model for pediatric intraoral radiographs showed good performance with high accuracy. Deep learning can assist dentists in diagnosis of proximal caries lesions in pediatric intraoral radiographs.

이번 연구는 소아의 인접면 우식을 진단하는데 있어 사용하고 있는 구내방사선 사진에서 심층학습(deep learning) 알고리즘을 활용하여 치아우식을 진단하는 모델의 성능을 평가하고자 하였다. 제1유구치와 제2유구치 사이의 인접면이 포함된 500개의 구내방사선 사진을 대상으로 연구를 시행하였다. 치아우식을 진단하는 모델의 학습에는 Resnet50 기반의 인공신경망 모델을 사용하였다. 평가자료군에서 진단모델의 정확도, 민감도, 특이도를 구하고, ROC 곡선을 얻어 AUC 값을 바탕으로 분류 모델의 성능을 평가하였다. 학습 모델의 정확도는 0.84, 민감도는 0.74, 특이도는 0.94로 나타났으며 AUC는 0.86으로 나타났다. 인공신경망을 기반으로 하는 소아의 구내방사선 사진에서의 인접면 우식의 진단 모델은 비교적 높은 정확도를 보여주었다. 심층학습 모델은 구내방사선 사진상에서 인접면 우식을 진단하는데 있어 향후 치과의사를 보조하는 진단 도구로서 활용될 수 있을 것이다.

Keywords

References

  1. Pitts NB, Zero DT, Ismail A, et al. : Dental caries. Nat Rev Dis Primers, 3:17030, 2017. 
  2. Featherstone JD : The science and practice of caries prevention. J Am Dent Assoc, 131:887-899, 2000.  https://doi.org/10.14219/jada.archive.2000.0307
  3. Sheiham A : Dental caries affects body weight, growth and quality of life in pre-school children. Br Dent J, 201:625-626, 2006.  https://doi.org/10.1038/sj.bdj.4814259
  4. Selwitz RH, Ismail AI, Pitts NB : Dental caries. Lancet, 369:51-59, 2007.  https://doi.org/10.1016/S0140-6736(07)60031-2
  5. Eli I, Weiss EI, Kaffe I, et al. : Interpretation of bitewing radiographs. Part 1. Evaluation of the presence of approximal lesions. J Dent, 24:379-383, 1996.  https://doi.org/10.1016/0300-5712(95)00111-5
  6. Weiss EI, Tzohar A, Eli I, et al. : Interpretation of bitewing radiographs. Part 2. Evaluation of the size of approximal lesions and need for treatment. J Dent, 24:385-388, 1996.  https://doi.org/10.1016/0300-5712(95)00112-3
  7. Akkaya N, Kansu O, Arslan U, et al. : Comparing the accuracy of panoramic and intraoral radiography in the diagnosis of proximal caries. Dentomaxillofac Radiol, 35:170-174, 2006.  https://doi.org/10.1259/dmfr/26750940
  8. Schwendicke F, Tzschoppe M, Paris S : Radiographic caries detection: A systematic review and meta-analysis. J Dent, 43:924-933, 2015.  https://doi.org/10.1016/j.jdent.2015.02.009
  9. Chan HP, Hadjiiski LM, Samala RK : Computer-aided diagnosis in the era of deep learning. Med Phys, 47:218-227, 2020. 
  10. Russel S, Norvig P : Artificial intelligence: a modern approach, 4th ed. Pearson, Hoboken, 1-5, 2021. 
  11. LeCun Y, Bengio Y, Hinton G : Deep learning. Nature, 521:436-444, 2015.  https://doi.org/10.1038/nature14539
  12. Rusk N : Deep learning. Nature Methods, 13:35-35, 2016.  https://doi.org/10.1038/nmeth.3707
  13. Albawi S, Mohammed TA, Al-Zawi S : Understanding of a convolutional neural network. 2017 International Conference on Engineering and Technology (ICET), 2017:21-23, 2017. 
  14. Zaremba W, Sutskever I, Vinyals O : Recurrent neural network regularization. ArXiv, abs:1409.2329, 2014. 
  15. Howard J, Gugger S : Fastai: A Layered API for Deep Learning. Information, 11:108, 2020. 
  16. Paszke A, Gross S, Chintala S, et al. : Pytorch: An imperative style, high-performance deep learning library. Adv Neural Inf Process Syst, 32:8026-8037, 2019. 
  17. Schneiderman A, Elbaum M, Driller J, et al. : Assessment of dental caries with Digital Imaging Fiber-Optic Translllumination (DIFOTI): in vitro study. Caries Res, 31:103-110, 1997.  https://doi.org/10.1159/000262384
  18. Lussi A, Hibst R, Paulus R : DIAGNOdent: An optical method for caries detection. J Dent Res, 83:80-83, 2004.  https://doi.org/10.1177/154405910408301s16
  19. Caliskan Yanikoglu F, Ozturk F, Stookey GK, et al. : Detection of natural white spot caries lesions by an ultrasonic system. Caries Res, 34:225-232, 2000.  https://doi.org/10.1159/000016595
  20. 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, 77:106-111, 2018.  https://doi.org/10.1016/j.jdent.2018.07.015
  21. Cantu AG, Gehrung S, Schwendicke, F, et al. : Detecting caries lesions of different radiographic extension on bitewings using deep learning. J Dent, 100:103425, 2020. 
  22. Bayraktar Y, Ayan E : Diagnosis of interproximal caries lesions with deep convolutional neural network in digital bitewing radiographs. Clin Oral Investig, 26:623-632, 2022.  https://doi.org/10.1007/s00784-021-04040-1
  23. Lee S, Oh SI, Park JW, et al. : Deep learning for early dental caries detection in bitewing radiographs. Sci Rep, 11:16807, 2021. 
  24. Kamburoglu K, Kolsuz E, Ozen T, et al. : Proximal caries detection accuracy using intraoral bitewing radiography, extraoral bitewing radiography and panoramic radiography. Dentomaxillofac Radiol, 41:450-459, 2012.  https://doi.org/10.1259/dmfr/30526171
  25. Muller MP, Tomlinson G, Gold WL, et al. : Can routine laboratory tests discriminate between severe acute respiratory syndrome and other causes of community-acquired pneumonia?. Clin Infect Dis, 40:1079-1086, 2005.  https://doi.org/10.1086/428577
  26. Krois J, Garcia Cantu A, Schwendicke, F, et al. : Generalizability of deep learning models for dental image analysis. Sci Rep, 11:6102, 2021.