A deep learning approach to permanent tooth germ detection on pediatric panoramic radiographs

다국어 초록 (Multilingual Abstract)

Purpose: The aim of this study was to assess the performance of a deep learning system for permanent tooth germ detection on pediatric panoramic radiographs.
Materials and Methods: In total, 4518 anonymized panoramic radiographs of children between 5 and 13 years of age were collected. YOLOv4, a convolutional neural network (CNN)-based object detection model, was used to automatically detect permanent tooth germs. Panoramic images of children processed in LabelImg were trained and tested in the YOLOv4 algorithm. True-positive, false-positive, and false-negative rates were calculated. A confusion matrix was used to evaluate the performance of the model.
Results: The YOLOv4 model, which detected permanent tooth germs on pediatric panoramic radiographs, provided an average precision value of 94.16% and an F1 value of 0.90, indicating a high level of significance. The average YOLOv4 inference time was 90 ms.
Conclusion: The detection of permanent tooth germs on pediatric panoramic X-rays using a deep learning-based approach may facilitate the early diagnosis of tooth deficiency or supernumerary teeth and help dental practitioners find more accurate treatment options while saving time and effort.

참고문헌 (Reference)

1 Redmon JDS, "You only look once: unified, real-time object detection. arXiv"

2 Bochkovskiy A, "YOLOv4: optimal speed and accuracy of object detection. arXiv"

3 TuzoffDV, "Tooth detection and numbering in panoramic radiographs using convolutional neural networks" 48 : 20180051-, 2019

4 Cordeiro MM, "The effects of periradicular inflamation and infection on a primary tooth and permanent successor" 29 : 193-200, 2005

5 Rallan M, "Surgical management of multiple supernumerary teeth and an impacted maxillary permanent central incisor" 2013

6 Kuwana R, "Performance of deep learning object detection technology in the detection and diagnosis of maxillary sinus lesions on panoramic radiographs" 50 : 20200171-, 2021

7 White SC, "Oral Radiology: principles and interpretation" Elsevier 41-63, 2014

8 Mahdi FP, "Optimization technique combined with deep learning method for teeth recognition in dental panoramic radiographs" 10 : 19261-, 2020

9 Li Z, "Large-scale retrieval for medical image analytics : a comprehensive review" 43 : 66-84, 2018

10 Tzutalin D, "LabelImg" Gifthub

11 Ali S, "Improved YOLOv4for aerial object detection" 1-4, 2021

12 Farman A, "Extraoral and panoramic systems" 44 : 257-272, 2000

13 Orhan K, "Evaluation of artificial intelligence for detecting impacted third molars on cone-beam computed tomography scans" 122 : 333-337, 2021

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

15 Yoshida K, "Depression of the maxillary sinus anterior wall and its influence on panoramic radiography appearance" 46 : 20170126-, 2017

16 Marsillac Mde W, "Dental anomalies in panoramic radiographs of pediatric patients" 61 : e29-33, 2013

17 Murata M, "Deep-learning classification using convolutional neural network for evaluation of maxillary sinusitis on panoramic radiography" 35 : 301-307, 2019

18 Nielsen KB, "Deep learning-based algorithms in screening of diabetic retinopathy : a systematic review of diagnostic performance" 3 : 294-304, 2019

19 Kuwada C, "Deep learning systems for detecting and classifying the presence of impacted supernumerary teeth in the maxillary incisor region on panoramic radiographs" 130 : 464-469, 2020

20 Kim Y, "Deep learning in diagnosis of maxillary sinusitis using conventional radiography" 54 : 7-15, 2019

21 Krois J, "Deep learning for the radiographic detection of periodontal bone loss" 9 : 8495-, 2019

22 Ekert T, "Deep learning for the radiographic detection of apical lesions" 45 : 917-922, 2019

23 Yang H, "Deep learning for automated detection of cyst and tumors of the jaw in panoramic radiographs" 9 : 1839-, 2020

24 Chartrand G, "Deep learning : a primer for radiologists" 37 : 2113-2131, 2017

25 Shin HC, "Deep convolutional neural networks for computer-aided detection : cnn architectures, dataset characteristics and transfer learning" 35 : 1285-1298, 2016

26 Schwendicke F, "Convolutional neural networks for dental image diagnostics : a scoping review" 91 : 103226-, 2019

27 Doi K, "Computer-aided diagnosis in medical imaging : historical review, current status and future potential" 31 : 198-211, 2007

28 Ha EG, "Automatic detection of mesiodens on panoramic radiographs using artificial intelligence" 11 : 23061-, 2021

29 García Rubio V, "Automatic change detection system over unmanned aerial vehicle video sequences based on convolutional neural networks" 19 : 4484-, 2019

30 Ahn Y, "Automated mesiodens classification system using deep learning on panoramic radiographs of children" 11 : 1477-, 2021

31 Vinayahalingam S, "Automated detection of third molars and mandibular nerve by deep learning" 9 : 9007-, 2019

32 최진우, "Assessment of panoramic radiography as a national oral examination tool: review of the literature" 대한영상치의학회 41 (41): 1-6, 2011

33 Kılıc MC, "Artificial intelligence system for automatic deciduous tooth detection and numbering in panoramic radiographs" 50 : 20200172-, 2021

34 Law CS, "Approaching the pediatric dental patient : a review of nonpharmacologic behavior management strategies" 31 : 703-713, 2003

35 Lee JH, "Application of a fully deep convolutional neural network to the automation of tooth segmentation on panoramic radiographs" 129 : 635-642, 2020

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

37 Caliskan S, "A pilot study of a deep learning approach to submerged primary tooth classification and detection" 24 : 1-9, 2021