search for




 

Deep learning algorithms for identifying 79 dental implant types
J Dent Rehabil Appl Sci 2022;38(4):196-203
Published online December 31, 2022
© 2022 Korean Academy of Stomatognathic Function and Occlusion.

Hyun-Jun Kong1*, Jin-Yong Yoo2, Sang-Ho Eom2, Jun-Hyeok Lee3

1Department of Prosthodontics, College of Dentistry, Wonkwang University, Iksan, Republic of Korea
2HERIBio Co. Ltd., Seoul, Republic of Korea
3Korea Platform Service Technology Co. Ltd., Daejeon, Republic of Korea
Hyun-Jun Kong
Assistant Professor, Department of Prosthodontics, College of Dentistry, Wonkwang University, 895 Muwang-ro, Iksan, 54538, Republic of Korea
Tel: +82 63 859 2929, Fax: +82 63 857 4002, E-mail: zsfvzsfv@naver.com
Received October 21, 2022; Revised November 7, 2022; Accepted November 9, 2022.
cc It is identical to Creative Commons Non-Commercial License.
Abstract
Purpose: This study aimed to evaluate the accuracy and clinical usability of an identification model using deep learning for 79 dental implant types. Materials and Methods: A total of 45396 implant fixture images were collected through panoramic radiographs of patients who received implant treatment from 2001 to 2020 at 30 dental clinics. The collected implant images were 79 types from 18 manufacturers. EfficientNet and Meta Pseudo Labels algorithms were used. For EfficientNet, EfficientNet-B0 and EfficientNet-B4 were used as submodels. For Meta Pseudo Labels, two models were applied according to the widen factor. Top 1 accuracy was measured for EfficientNet and top 1 and top 5 accuracy for Meta Pseudo Labels were measured. Results: EfficientNet-B0 and EfficientNet-B4 showed top 1 accuracy of 89.4. Meta Pseudo Labels 1 showed top 1 accuracy of 87.96, and Meta pseudo labels 2 with increased widen factor showed 88.35. In Top5 Accuracy, the score of Meta Pseudo Labels 1 was 97.90, which was 0.11% higher than 97.79 of Meta Pseudo Labels 2. Conclusion: All four deep learning algorithms used for implant identification in this study showed close to 90% accuracy. In order to increase the clinical applicability of deep learning for implant identification, it will be necessary to collect a wider amount of data and develop a fine-tuned algorithm for implant identification.
Keywords : dental implants; artificial intelligence; deep learning; convolutional neural networks
Introduction

Since the concept of osseointegration was introduced, dental implants have been considered a successful treatment option for partially or completely edentulous patients.1 It has been reported that dental implants have a high success rate regardless of the type of prosthesis, such as fixed or removable, and their application range and use are gradually increasing.2-4 With the successful introduction of dental implants, numerous types of dental implants are being produced by different manufacturers, and the number continues to grow.5

Although dental implants have a high success rate, various surgical or prosthetic complications exist.6-8 Surgical complications include osseointegration failure and peri-implantitis, and prosthetic complications include fracture of the upper abutment or prosthesis, screw loosening, and screw fracture. When these complications occur, in many cases, the existing abutment and upper prosthesis must be removed, and in particular, when prosthetic complications occur, remake of prosthesis is sometimes necessary. In this case, it is essential for clinicians to accurately identify the type of implant, as there are many manufacturers and each implant is often incompatible.

Radiography is usually used to identify the type of implant.9,10 For this, it was necessary for clinicians to understand the features of the fixture (internal or external hexagonal, thread shape, tapering degree, etc.) shown in radiographs. However, this conventional identification method has important limitations. Since there are so many types of implants currently in use, it is almost impossible for even an experienced clinician to identify the features of all implants. Therefore, it was difficult to accurately identify the type of implant, unless it is an implant that clinicians mainly use or have experience with.

Artificial intelligence, a concept that has recently been widely used throughout society, is one of the subfields of computer science that attempts to implement computer systems to perform tasks that require human learning ability, reasoning ability, and perceptual ability. Deep learning, a field of artificial intelligence, is machine learning based on a multi-layered neural network, and it is a technique to build a high-level abstraction model from a large amount of data.11 Recently, studies to confirm the usefulness of deep learning in the field of dentistry are increasing.12 In particular, studies have been made on implant identification using deep learning image classification.13-16 In these studies, it was reported that a high level of accuracy was achieved when various deep learning algorithms were used for the identification. However, previous studies have a limitation in that they targeted several types of implants. Clinicians are actually exposed to a much wider variety of implants. Considering that the accuracy of the deep learning model decreases as the number of classes increases, it is necessary to confirm whether deep learning can show a high level of accuracy even with more types of implants.

Therefore, in this study, deep learning model was trained on 79 types of implants, and its performance was analyzed to confirm the applicability of deep learning for identification of various types of implants.

Materials and Methods

Data collection

This study was approved by the institutional review board (No.P01-202105-21-009). A total of 45396 implant fixture images were collected through panoramic radiographs of patients who received implant treatment from 2001 to 2020 at 30 dental clinics. Implant images were labeled as one of 79 types of implants from 18 manufacturers according to medical records. The implant manufacturers and systems used in this study are in Table 1.

The manufacturer and system of the implant and the number of images collected for model learning

Manufacturer System Images Manufacturer System Images Manufacturer System Images
Bicon 260-345-305 53 Neobiotech BIS3508A 56 Point Implant POF3008 32
BioHorizons IITSS510D 17 BIS4007A 195 POF3008Q 19
LITSS410D 40 EB310 27 POF3008QNP 111
SLITSS312D 20 EB407 1441 POF4007 269
BIOMET 3i FNT485 402 EB3513A 179 POF4007Q 946
FNT585 104 EB4513A 2867 POF4007QNP 1299
FNT685 53 EBI507 1022 Straumann 21.2408 92
FOS485 49 EBI5010A 128 21.3308 188
OSS410 198 IS33508A 38 21.3508 45
OSS510 48 Nobel Biocare 32114 217 043.054S 215
Biotem ASTFA4011 26 32186 24 043.131S 94
Dentis DS2FM3708S 447 32199 25 Thommen Medical 4.13.243 215
DSFM3708S 279 32200 146 4.13.900 297
DSSOFR5210S 191 32205 367 Zimmer Dental TSVB8 83
Dentium FX3408 1251 32212 403 TSVH8 848
FX3610SW 353 37609 331
FXI3608 118 Osstem Implant AUS3M3508S 507
Dentsply Sirona 26-2431 232 GS2W4511R01 175
24951 6827 GS3S4011R 484
24982 1731 MSD3008S20 24
Dio Implant FTT5015S 18 MSN2508S25 47
SFN3808 1023 MSP25103R 38
SFN3808H 148 MST18104 20
UF(ll)4513S 1701 SS2R4007S18 44
UF(ll)N3315S 706 SS2R4008S28 20
Hi ossen Implant ET3M3508S 438 TS3M3008C 290
IBS Implant 451M4009 104 TS3M3008S 28
551M5007 262 TS3M3508A 4285
MegaGen Implant EF4011P 280 TS3M3508C 3265
IF4010C 51 TS3M3508H 115
TS3M3508S 1572
US3M3508S 1187
US3R411R 71
US4R4007S 3835


Model learning

Regions of interest were cropped and extracted from the panoramic radiographs. Implant images of the maxilla were vertically flipped, and when the fixture was tilted more than 45 degrees, it was manually corrected to be parallel to the vertical axis. Data augmentation was performed on the image to improve the accuracy of the model. For data augmentation, randomly resizing and cropping were performed for each image. Next, the brightness and contrast of the image were randomly changed. Finally, horizontally flipping was performed.

EfficientNet and Meta Pseudo Labels algorithms were used for model learning. EfficientNet is a deep learning architecture and scaling method that uses compound scaling techniques to uniformly scale all dimensions of depth, width, and resolution.17 Meta Pseudo Labels is a semi-supervised learning method that uses a teacher network to generate pseudo labels on unlabeled data to teach a student network. In EfficientNet, 80% of the images were used for training, and 20% were used for validation. In Meta Pseudo Labels, 80% were used for training, of which 20% were fine tuning, 20% were unlabeled, and 60% were labeled. The remaining 20% were used for validation. For EfficientNet, EfficientNet-B0 and EfficientNet-B4 were used as submodels, and for Meta Pseudo Labels, two models were applied according to the widen factor. The settings of the four algorithms used in this study are as follows (Table 2).

EfficientNet and Meta Pseudo Labels algorithms

Algorithm Depth, widen factor Epoch Time (hour)
EfficientNet-B0 - 200 3
EfficientNet-B4 - 300 33
Meta Pseudo Labels 1 28, 2 300,000 32
Meta Pseudo Labels 2 28, 8 300,000 52


Model performance evaluation

The accuracy [(TP +TN) /( TP + FP + FN + TN)] used to evaluate the trained model. TP is a true positive, TN is a true negative, FP is a false positive, and FN is a false negative. According to the default setting of each algorithm, top 1 accuracy was measured in EfficientNet and top 1 and top 5 accuracy in Meta Pseudo Labels were measured. The top 1 accuracy refers to the ratio that the nearest class was predicted and the answer was correct. The top 5 accuracy refers to the ratio in which the five nearest classes were predicted and the answer was in them.

Results

The performances of the trained models are presented in Table 3. EfficientNet-B0 and EfficientNet-B4 showed top 1 accuracy of 89.4. Meta Pseudo Labels 1 showed top 1 accuracy of 87.96, and Meta pseudo labels 2 with increased widen factor showed 88.35. In Top 5 Accuracy, the score of Meta Pseudo Labels 1 was 97.90, which was 0.11% higher than 97.79 of Meta Pseudo Labels 2. Accuracy graphs of train and validation for EfficientNet are shown in Fig. 1. The top 1 accuracy and top 5 accuracy graphs for Metal Pseudo Labels are shown in Fig. 2.

Performance of implant identification models according to algorithm

EfficientNet Meta Pseudo Labels
EfficientNet-B0 EfficientNet-B4 Meta Pseudo Labels 1 Meta Pseudo Labels 2
Top 1 accuracy 89.4 89.4 87.96 88.35
Top 5 accuracy - - 97.90 97.79


Fig. 1. Accuracy and train loss results for EfficientNet-B0 and EfficientNet-B4 algorithms. The value of validation means top 1 accuracy.

Fig. 2. Top 1 and Top 5 accuracy and train loss results of Meta Pseudo Labels algorithms. Meta Pseudo Labels 2 is a setting with an increased widen factor.
Discussion

In this study, we evaluated how accurately the model using deep learning can identify 79 types of implants. According to the study results, the deep learning model identified implants with nearly 90% accuracy, confirming the usefulness of the deep learning model in implant classification.

The clinical importance of the identification of implants has been steadily mentioned since implant treatment became popular. In order to overcome the limitations of the traditionally used radiographic method, various methods have been introduced. Implant Recognition Software is a program that classifies implants according to various characteristics, and when the user selects the characteristics, the type of implant corresponding to the condition is presented.18 There are also commercialized websites that use a similar method to identify implants. However, the disadvantage of this method is that the clinician has to check the characteristics of the implant one by one, which can be difficult, especially for inexperienced clinicians. In contrast, identification of implants using artificial intelligence has the advantage that the accuracy does not depend on the clinician.

In previous studies using deep learning, it was reported that the accuracy of implant identification was between 0.51 and 0.98.13-16 Although this is high accuracy, it has a limitation in that the types of implants to be studied are limited. Therefore, in this study, data were collected from implants from various manufacturers to increase the clinical applicability of the model. The accuracy of this study is somewhat lower than that of previous studies. This is because there are many kinds of classes for model building. In an image classification model using deep learning, it is generally reported that the accuracy decreases as the number of class increases.19 To overcome this, it is necessary to collect a sufficient number of images for each class. In the present study, the minimum number of images obtained per class was 17, which may be insufficient for accurate model training, and this will degrade the overall accuracy of the model. In particular, considering that there are many similar types of implants, it is necessary to have high top 1 accuracy so that the type can be accurately identified in a clinical situation. For this, after classifying implants according to design, more images of implant systems with similar shapes should be collected.

In comparison between algorithms, EfficientNet algorithm showed higher accuracy than Meta Pseudo Labels. According to a study that used various algorithms for implant classification, the Resnet algorithm showed the highest accuracy.16 Algorithms for image classification are very diverse and are being developed at the present time, and research on the strengths and weaknesses of each algorithm continues. Therefore, in order to find the optimal algorithm for classifying implants, it is necessary to train and evaluate models using various algorithms for many types of implants.

Identifying implant images using deep learning is a method of learning the features of each implant type. For this, it is important that the unique features of the implant are clearly revealed on the radiograph. The accuracy of the model can be improved if things like the shape and size of the threads and the taper of the fixtures become clearer. Panoramic radiographs were used in this study. In the case of panoramic radiographs, there is a disadvantage that overlapping of anatomical structures may occur depending on the posture of the patient.20,21 Therefore, to solve these shortcomings, it will be necessary to utilize standardized periapical radiography or computed tomography.

The limitation of this study is that although various types of implant data were collected, it is much less than the types of implants used in clinical practice. In order to use deep learning-based implant identification in actual clinical practice, more extensive data on implants manufactured in Korea and abroad are needed. In addition, the accuracy was lower than that of the previous studies. A sufficient number of images for each type are required, and a process that can analyze the various features of the implant in more detail is needed. Finally, since data were collected from several dental clinics, the contrast, angle, and resolution of radiographs varied, which may have acted as a factor lowering the accuracy of the model.

Conclusion

Deep learning algorithms for identifying 79 dental implant types showed high accuracy close to 90%. It will be necessary to collect a wider amount of data and develop a fine-tuned algorithm for implant identification to increase the clinical applicability.

Acknowledgements

This research was financially supported by the Ministry of Science and ICT of Korea through the Institute of Information and Communications Technology Planning and Evaluation in 2021 (No.20210012430012002, Setting up Big data of dental case and Developing dental implant identification system based on Deep learning technology).

References
  1. Hämmerle CH, Glauser R. Clinical evaluation of dental implant treatment. Periodontol 2000 2004;34:230-9.
    Pubmed CrossRef
  2. Romeo E, Lops D, Margutti E, Ghisolfi M, Chiapasco M, Vogel G. Long-term survival and success of oral implants in the treatment of full and partial arches: a 7-year prospective study with the ITI dental implant system. Int J Oral Maxillofac Implants 2004;19:247-59.
    Pubmed
  3. Grossmann Y, Nissan J, Levin L. Clinical effectiveness of implant-supported removable partial dentures: a review of the literature and retrospective case evaluation. J Oral Maxillofac Surg 2009;67:1941-6.
    Pubmed CrossRef
  4. Simonis P, Dufour T, Tenenbaum H. Long-term implant survival and success: a 10-16-year follow-up of non-submerged dental implants. Clin Oral Implants Res 2010;21:772-7.
    Pubmed CrossRef
  5. Hadj Saïd M, Le Roux MK, Catherine JH, Lan R. Development of an artificial intelligence model to identify a dental implant from a radiograph. Int J Oral Maxillofac Implants 2020;36:1077-82.
    Pubmed CrossRef
  6. Misch K, Wang HL. Implant surgery complications: etiology and treatment. Implant Dent 2008;17:159-68.
    Pubmed CrossRef
  7. Annibali S, Ripari M, LA Monaca G, Tonoli F, Cristalli MP. Local complications in dental implant surgery: prevention and treatment. Oral Implantol 2008;1:21-33.
    Pubmed KoreaMed
  8. Nedir R, Bischof M, Szmukler-Moncler S, Belser UC, Samson J. Prosthetic complications with dental implants: from an up-to-8-year experience in private practice. Int J Oral Maxillofac Implants 2006;21:919-28.
    Pubmed
  9. Sahiwal IG, Woody RD, Benson BW, Guillen GE. Radiographic identification of nonthreaded endosseous dental implants. J Prosthet Dent 2002;87:552-62.
    Pubmed CrossRef
  10. Sewerin I. Identification of dental implants on radiographs. Quintessence Int 1992;23:611-8.
    Pubmed
  11. Chan HP, Samala RK, Hadjiiski LM, Zhou C. Deep learning in medical image analysis. Adv Exp Med Biol 2020;1213:3-21.
    Pubmed KoreaMed CrossRef
  12. Hwang JJ, Jung YH, Cho BH, Heo MS. An overview of deep learning in the field of dentistry. Imaging Sci Dent 2019;49:1-7.
    Pubmed KoreaMed CrossRef
  13. Lee JH, Kim YT, Lee JB, Jeong SN. A performance comparison between automated deep learning and dental professionals in classification of dental implant systems from dental imaging: a multi-center study. Diagnostics 2020;10:910.
    Pubmed KoreaMed CrossRef
  14. Takahashi T, Nozaki K, Gonda T, Mameno T, Wada M, Ikebe K. Identification of dental implants using deep learning-pilot study. Int J Implant Dent 2020;6:53.
    Pubmed KoreaMed CrossRef
  15. Sukegawa S, Yoshii K, Hara T, Yamashita K, Nakano K, Yamamoto N, Nagatsuka H, Furuki Y. Deep neural networks for dental implant system classification. Biomolecules 2020;10:984.
    Pubmed KoreaMed CrossRef
  16. Kim JE, Nam NE, Shim JS, Jung YH, Cho BH, Hwang JJ. Transfer learning via deep neural networks for implant fixture system classification using periapical radiographs. J Clin Med 2020;9:1117.
    Pubmed KoreaMed CrossRef
  17. Tan M, Le QV. Efficientnet: rethinking model scaling for convolutional neural networks. Proc Mach Learn Res 2019;97:6105-14.
  18. Michelinakis G, Sharrock A, Barclay CW. Identification of dental implants through the use of Implant Recognition Software (IRS). Int Dent J 2006;56:203-8.
    Pubmed CrossRef
  19. Zheng Q, Yang M, Tian X, Jiang N, Wang D. A full stage data augmentation method in deep convolutional neural network for natural image classification. Discrete Dyn Nat Soc 2020;1:1-11.
    CrossRef
  20. Truhlar RS, Morris HF, Ochi S. A review of panoramic radiography and its potential use in implant dentistry. Implant Dent 1993;2:122-30.
    Pubmed CrossRef
  21. Kayal RA. Distortion of digital panoramic radiographs used for implant site assessment. J Orthod Sci 2016;5:117-20.
    Pubmed KoreaMed CrossRef


December 2022, 38 (4)
Full Text(PDF) Free

Social Network Service
Services

Cited By Articles
  • CrossRef (0)

Author ORCID Information

Funding Information