VGG-16 딥러닝 알고리즘을 활용한 우식치아와 건전치아 분류 = Evaluation of VGG-16 deep learning algorithm for dental caries classification

다국어 초록 (Multilingual Abstract)

Objectives: Diagnosis of dental caries is based on the dentist’s observation and subjective judgment; therefore, a reliable and objective approach for diagnosing caries is required. Intraoral camera images combined with deep learning technology can be a useful tool to diagnose caries. This study aimed to evaluate the accuracy of the VGG-16 convolutional neural network (CNN) model in detecting dental caries in intraoral camera images.
Methods: Images were obtained from the Internet and websites using keywords linked to teeth and dental caries. The 670 images that were obtained were categorized by an investigator as either sound (404 sound teeth) or dental caries (266 dental caries), and used in this study. The training and test datasets were divided in the ratio of 7:3 and a four-fold cross validation was performed. The Tensorflow-based Python package Keras was used to train and validate the CNN model. Accuracy, Kappa value, sensitivity, specificity, positive predictive value, negative predictive value, ROC (receiver operating characteristic) curve and AUC (area under curve) values were calculated for the test datasets.
Results: The accuracy of the VGG-16 deep learning model for the four datasets, through random sampling, was between 0.77 and 0.81, with 0.81 being the highest. The Kappa value was 0.51- 0.60, indicating moderate agreement. The resulting positive predictive values were 0.77-0.82 and negative predictive values were 0.80-0.85. Sensitivity, specificity, and AUC values were 0.66-0.74, 0.81-0.88, and 0.88-0.91, respectively.
Conclusions: The VGG-16 CNN model showed good discriminatory performance in detecting dental caries in intraoral camera images. The deep learning model can be beneficial in monitoring dental caries in the population.

참고문헌 (Reference)

1 강민제, "딥러닝을 위한 경사하강법 비교" 한국산학기술학회 21 (21): 189-194, 2020

2 송경두, "딥러닝 알고리즘 개발과정을 통해 본 영상의학분야에서 딥러닝의 최신 경향" 대한영상의학회 80 (80): 202-212, 2019

3 Gimenez T, "Visual inspection for caries detection : a systematic review and meta-analysis" 94 : 895-904, 2015

4 Gimenez T, "Visual inspection for caries detection : a systematic review and meta-analysis" 94 : 895-904, 2015

5 Simonyan K, "Very deep convolutional networks for large-scale image recognition"

6 Kim BM, "Trend of image classification technology based on deep learning" 35 (35): 8-14, 2018

7 Ismail AI, "The International Caries Detection and Assessment System(ICDAS) : an integrated system for measuring dental caries" 35 (35): 170-178, 2007

8 Bader JD, "Systematic reviews of selected dental caries diagnostic and management methods" 65 (65): 960-968, 2021

9 Kim SJ, "Reliability evaluation of dental caries detection using deep learning" Seoul National University 2019

10 Petersen PE, "Oral health surveys:basic methods" World Health Organization 2013

11 Choe Gh, "Latest Research Trends in Convolutional Neural Networks" 36 (36): 25-31, 2018

12 Alassaad SS, "Incomplete cusp fractures : Early diagnosis and communication with patients using fiber-optic transillumination and intraoral photography" 59 : 132-135, 2011

13 Krizhevsky A, "Imagenet classification with deep convolutional neural networks" 25 : 1097-1105, 2012

14 Deng J, "ImageNet: A large-scale hierarchical image database" 248-255, 2009

15 Szegedy C, "Going deeper with convolutions" 1-9, 2015

16 Lee KS, "Evaluation of transfer learning with deep convolutional neural networks for screening osteoporosis in dental panoramic radiographs" 9 (9): 392-, 2020

17 Obrochta JC, "Efficient & Effective Use of the Intraoral Camera"

18 National Institutes of Health, "Diagnosis and management of dental caries throughout life" 18 (18): 1-23, 2001

19 Khanagar SB, "Developments, application, and performance of artificial intelligence in dentistry-a systematic review" 16 (16): 508-522, 2021

20 Lee JH, "Detection and diagnosis of dental caries using a deep learning-based convolutional neural network algorithm" 77 : 106-111, 2018

21 Fejerskov O, "Dental Caries: the Disease and Its Clinical Management" Wiley Blackwell 7-10, 2015

22 Fejerskov O, "Dental Caries: the Disease and Its Clinical Management" Wiley Blackwell 11-20, 2015

23 Fejerskov O, "Dental Caries: the Disease and Its Clinical Management" Wiley Blackwell 173-190, 2015

24 Schwendicke F, "Deep learning for caries lesion detection in near-infrared light transillumination images : A pilot study" 92 : 103260-, 2020

25 Boye U, "Comparison of an intra-oral photographic caries assessment with an established visual caries assessment method for use in dental epidemiological studies of children" 41 : 526-533, 2013

26 Pitts NB, "Clinical diagnosis of dental caries : a European perspective" 65 (65): 972-978, 2001

27 Prajapati SA, "Classification of dental diseases using CNN and transfer learning" 70-74, 2017

28 Pretty IA, "Caries detection and diagnosis : novel technologies" 34 (34): 727-739, 2006

29 Gook KH, "Artificial intelligence technology and examples of industrial application" 20 : 5-27, 2019

30 Babu A, "Artificial Intelligence in dentistry:Concepts, Applications and Research Challenges" 297-, 2021

31 황재준, "An overview of deep learning in the field of dentistry" 대한영상치의학회 49 (49): 1-7, 2019

32 Devito KL, "An artificial multilayer perceptron neural network for diagnosis of proximal dental caries" 106 : 879-884, 2008

33 홍준용, "AI 의료영상 분석의 개요 및 연구 현황에 대한 고찰" 대한방사선과학회 43 (43): 195-208, 2020

34 Ministry of Health & Welfare, "2018 Korean National Oral Health Survey" Ministry of Health & Welfare 382-, 2019