Implant Thread Shape Classification by Placement Site from Dental Panoramic Images Using Deep Neural Networks
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Purpose: In this study, we aimed to classify an implant system by comparing the types of implant thread shapes shown on radiographs using various Convolutional Neural Networks (CNNs), particularly Xception, InceptionV3, ResNet50V2, and ResNet101V2. The accuracy of the CNN based on the implant site was compared. Materials and Methods: A total of 1000 radiographic images, consisting of eight types of implants, were preprocessed by resizing and CLAHE filtering, and then augmented. CNNs were trained and validated for implant thread shape prediction. Grad-CAM was used to visualize class activation maps (CAM) on the implant threads shown within the radiographic image. Results: Averaged over 10 validation folds, each model achieved an AUC of over 0.96: AUC of 0.961 (95% CI 0.952–0.970) with Xception, 0.973 (95% CI 0.966-0.980) with InceptionV3, 0.980 (95% CI 0.974-0.988) with ResNet50V2, and 0.983 (95% CI 0.975-0.992) with ResNet101V2. Accuracy was higher in the posterior region than in the anterior area in all four models. Most CAMs highlighted the implant surface where the threads were present; however, some showed responses in other areas. Conclusion: The CNN models accurately classified implants in all areas of the oral cavity according to the thread shape, using radiographic images.
Abstract
Purpose: In this study, we aimed to classify an implant system by comparing the types of implant thread shapes shown on radiographs using various Convolutional Neural Networks (CNNs), particularly Xception, InceptionV3, ResNet50V2, and ResNet101V2. The accuracy of the CNN based on the implant site was compared. Materials and Methods: A total of 1000 radiographic images, consisting of eight types of implants, were preprocessed by resizing and CLAHE filtering, and then augmented. CNNs were trained and validated for implant thread shape prediction. Grad-CAM was used to visualize class activation maps (CAM) on the implant threads shown within the radiographic image. Results: Averaged over 10 validation folds, each model achieved an AUC of over 0.96: AUC of 0.961 (95% CI 0.952–0.970) with Xception, 0.973 (95% CI 0.966-0.980) with InceptionV3, 0.980 (95% CI 0.974-0.988) with ResNet50V2, and 0.983 (95% CI 0.975-0.992) with ResNet101V2. Accuracy was higher in the posterior region than in the anterior area in all four models. Most CAMs highlighted the implant surface where the threads were present; however, some showed responses in other areas. Conclusion: The CNN models accurately classified implants in all areas of the oral cavity according to the thread shape, using radiographic images.
참고문헌 (24)
- Adell R, "A long-term follow-up study of osseointegrated implants in the treatment of totally edentulous jaws", Int J Oral Maxillofac Implants, 5, pp.347~359 (1990)
- Jung RE, "Systematic review of the survival rate and the incidence of biological, technical, and aesthetic complications of single crowns on implants reported in longitudinal studies with a mean follow-up of 5 years", Clin Oral Implants Res, 23, pp.2~21 (2012)
- Jokstad A, "Systematic review of clinical and patient-reported outcomes following oral rehabilitation on dental implants with a tapered compared to a non-tapered implant design", Clin Oral Implants Res, 29, pp.41~54 (2018)
- Steigenga JT, "Dental implant design and its relationship to long-term implant success", Implant Dent, 12, pp.306~317 (2003)
- Hwang JJ, "An overview of deep learning in the field of dentistry", Imaging Sci Dent, 49, pp.1~7 (2019)
- Shan T, "Application of artificial intelligence in dentistry", J Dent Res, 100, pp.232~244 (2021)
- Lim HK, "Application of artificial intelligence in identification of dental implants system : literature review", J Dent Implant Res, 39, pp.48~52 (2020)
- Manikyamba YJB, "Implant thread designs : An overview", Trends Prosthodont Dent Implantol, 8, pp.11~19 (2017)
- Rodriguez JD, "Sensitivity analysis of k-fold cross validation in prediction error estimation", IEEE Trans Pattern Anal Mach Intell, 32, pp.569~575 (2009)
- Zhou B, "Learning deep features for discriminative localization", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.2921~2929 (2016)
- Kim JE, "Transfer learning via deep neural networks for implant fixture system classification using periapical radiographs", J Clin Med, 9, pp.1117~ (2020)
- Sukegawa S, "Deep neural networks for dental implant system classification", Biomolecules, 10, pp.984~ (2020)
- Montani S, "Artificial intelligence in clinical decision support : a focused literature survey", Yearb Med Inform, 28, pp.120~127 (2019)
- Magrabi F, "Artificial Intelligence in Clinical Decision Support : Challenges for Evaluating AI and Practical Implications : A Position Paper from the IMIA Technology Assessment & Quality Development in Health Informatics Working Group and the EFMI Working Group for Assessment of Health Information Systems", Yearb Med Inform, 28, pp.128~134 (2019)
- He K, "Rethinking imagenet pre-training", Proceedings of the IEEE International Conference on Computer Vision, pp.4918~4927 (2019)
- "Keras Applications", ~
- Sunny S, "A smart tele-cytology point-of-care platform for oral cancer screening", PLoS ONE, 14, pp.e0224885~ (2019)
- Shin HC, "Deep convolutional neural networks for computer-aided detection : CNN architectures, dataset characteristics and transfer learning", IEEE Trans Med Imaging, 35, pp.1285~1298 (2016)
- Attia SJ, "Enhancement of chest X-ray Images for diagnosis purposes", J Nat Sci Res, 6, pp.43~46 (2016)
- Jadoon MM, "Three-class mammogram classification based on descriptive CNN features", Biomed Res Int, 2017, pp.3640901~ (2017)
- Al-Wahadni A, "Dentists’ most common practices when selecting an implant system", J Prosthodont, 27, pp.250~259 (2018)
- Zarch SH, "Evaluation of the accuracy of panoramic radiography in linear measurements of the jaws", Iran J Radiol, 8, pp.97~102 (2011)