Diagnosis of Proximal Caries on Radiograph by Designing System Based on Machine Learning Techniques
Main Article Content
Keywords
Dental Caries, Dental Radiography, Machine Learning Techniques
Abstract
Background: Dental Caries are one of the most common dental diseases around the world and diagnosis it is a challenging task. If the caries is caught early, it can be treated.
Objective: This study aim to designing system based on machine learning techniques for diagnosis of proximal caries.
Patients and methods: This paper applied machine learning techniques on X-rays for 200 teeth which collected in the dental clinics of the college of dentistry in university of Thi_Qar to diagnosing the stages of surface caries . In order to remove the noise and corrupted pixels we used the Gaussian blur filter then segmented the image by K means clustering technique to extract the region of interest
Then we used Grey Level Co Concurrent Matrix (GLCM) algorithm for feature extraction. Features extracted by GLCM inputs into Naive Bayes classifier (NBC).
Results: Our proposed approach of detecting and classifying dental caries achieve the results of 96%,97% ,98%,98% for F1,recall ,precision and Accuracy values, respectively.
Conclusions: The experimental results indicate that dental caries could be detected accurately by this diagnostic system. The key benefits of the suggested approach are its ease of use, quick computation, and simplicity of implementation.
References
2. Casalegno F, et al.(2019): Caries detection with near-infrared transillumination using deep learning. Journal of dental research, 98(11): p. 1227-1233.
3. Claus, et al.(2012): Dental x‐rays and risk of meningioma. Cancer. 118(18): p. 4530-4537.
4. Pauwels R (2021): A brief introduction to concepts and applications of artificial intelligence in dental imaging. Oral Radiology, 37(1): p. 153-160.
5. Dhanachandra K, Manglem, and Chanu J (2015): Image segmentation using K-means clustering algorithm and subtractive clustering algorithm. Procedia Computer Science, 54: p. 764-771.
6. Ahmed S, et al.(2017): Identification and volume estimation of dental caries using CT image. in 2017 IEEE International Conference on
Telecommunications and Photonics( ICTP). IEEE.
7. Jusman Y, et al.(2020): Analysis of features extraction performance to differentiate of dental caries types using gray level co-occurrence matrix algorithm. in 2020 10th IEEE International Conference on Control System, Computing and Engineering (ICCSCE). IEEE.
8. Navarro K, et al (2019): Detecting smooth surface dental caries in frontal teeth using image processing. in Proceedings of the 2019 3rd High Performance Computing and Cluster Technologies Conference. 2019.
9. Verma D, et al)2020): Anomaly detection in panoramic dental x-rays using a hybrid Deep Learning and Machine Learning approach. in 2020 IEEE REGION 10 CONFERENCE (TENCON). IEEE.
10. Jusman Y, et al.(2022): Caries Level Classification using K-Nearest Neighbor, Support Vector Machine, and Decision Tree using Zernike Moment Invariant Features. in 2022 International Conference on Data Science and Its Applications (ICoDSA). IEEE.
11. Estai M, et al.(2022):Evaluation of a deep learning system for automatic detection of proximal surface dental caries on bitewing radiographs. Oral Surgery, Oral Medicine, Oral Pathology and Oral Radiology.
12. Geetha V, and Aprameya K (2019): Dental Caries Diagnosis in X-ray Images using KNN Classifier. Indian Journal of Science and Technology, 2 .019 :12p. 4.
13. Haghanifar A, Majdabadi M, and Ko B and Paxnet(2020): Dental caries detection in panoramic x-ray using ensemble transfer learning and capsule classifier. arXiv preprint arXiv:2012.13666.
14. ALbahbah, El-Bakry H, and Abd-Elgahany S(2016):Detection of caries in panoramic dental X-ray images using back-propagation neural network. International Journal of Electronics Communication and Computer Engineering, 7(5): p. 250
Article Sidebar
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
All articles published in JPTCP are licensed under Copyright Creative Commons Attribution-NonCommercial 4.0 International License.