DENTAL CARRIES CLASSIFICATION USING YOLO V8
Main Article Content
Keywords
Deep Learning, Caries Detection, Dental X-ray, YOLOv8, Periapical Radiography.
Abstract
This study focuses on the development of a sophisticated caries detection system using deep learning techniques applied to periapical dental X-ray images. By customizing the YOLOv8 architecture, the system was optimized for accurate caries identification. The training process involved intricate customization, including backbone and feature extraction neck integration, and head design. Pre-processing was applied to enhance detection efficiency. Leveraging YOLOv8 elements like the SPPF layer, up-sample layers, and detection modules enabled precise identification of dental caries lesions within X-ray images. The training dataset was meticulously curated with pixel-level annotations by certified dentists to ensure detailed representation. Augmentation techniques like random flipping and rotation were employed to enhance dataset diversity, model generalizability, and standardization. The system's efficacy is validated using a comprehensive suite of metrics: Mean Average Precision (mAP) of 91.8%, F1-score of 92.0%, and recall of 92.6%. This showcases its proficiency in accurately identifying and localizing caries lesions and other relevant dental conditions within X-ray images. The unique aspect of training the network for detecting five classes (cavity, crown, restoration, missing tooth, and root canal treated) on a preliminary basis using a dataset collected from Pakistani patients in Karachi adds a significant dimension to this study. This approach aligns with recent advancements in deep learning algorithms for dental applications, emphasizing the importance of leveraging modern architectures to improve dental diagnostics and aid in accurate diagnoses based on periapical radiographs.
References
2. Schneider S, Taylor GW, Kremer SC. Deep Learning Object Detection Methods for Ecological Camera Trap Data. 2018.
3. Tian Y, Yang G, Wang Z, Li E, Liang Z. Detection of Apple Lesions in Orchards Based on Deep Learning Methods of CycleGAN and YOLOV3-Dense. Journal of Sensors. 2019.
4. Tang X, Xianyue S, He M, Chen B, Deming G, Yanguo Q. Automated Detection of Knee Cystic Lesions on Magnetic Resonance Imaging Using Deep Learning. Frontiers in Medicine. 2022.
5. Ardhianto P, Subiakto RBR, Lin C-Y, Jan YK, Liau B-Y, Tsai JY, et al. A Deep Learning Method for Foot Progression Angle Detection in Plantar Pressure Images. Sensors. 2022.
6. Ünver HM, Ayan E. Skin Lesion Segmentation in Dermoscopic Images With Combination of YOLO and GrabCut Algorithm. Diagnostics. 2019.
7. Suryani D, Shoumi MN, Wakhidah R. Object detection on dental x-ray images using deep learning method. IOP Conference Series: Materials Science and Engineering. 2021;1073(1):012058.
8. Çelik B, Savaştaer EF, Kaya HI, Çelik ME. The role of deep learning for periapical lesion detection on panoramic radiographs. Dentomaxillofacial Radiology. 2023;52(8):20230118.
9. Paidi V, Fleyeh H, Håkansson J, Nyberg RG. Tracking Vehicle Cruising in an Open Parking Lot Using Deep Learning and Kalman Filter. Journal of Advanced Transportation. 2021;2021(1):1812647.
10. Shi R, Liu C, Tao J, Li G, Xiao K, Xie Z, et al., editors. Panoramic Radiographic X-Ray Image Tooth Root Segmentation Based on LeNet-5 Networks. Advanced Machine Learning Technologies and Applications; 2021 2021//; Cham: Springer International Publishing.
11. Görürgöz C, Orhan K, Bayrakdar IS, Çelik Ö, Bilgir E, Odabaş A, et al. Performance of a convolutional neural network algorithm for tooth detection and numbering on periapical radiographs. Dentomaxillofacial Radiology. 2022;51(3):20210246.
12. 이상정. A Deep Learning-based Computer-aided Diagnosis Method for Radiographic Bone Loss and Periodontitis Stage: A Multi-device Study: 서울대학교 대학원; 2021.
13. Martins MV, Baptista L, Luís H, Assunção V, Araújo M-R, Realinho V. Machine Learning in X-ray Diagnosis for Oral Health: A Review of Recent Progress. Computation [Internet]. 2023; 11(6).
14. Moran MBH, Faria M, Giraldi G, Bastos L, Inacio BdS, Conci A, editors. On using convolutional neural networks to classify periodontal bone destruction in periapical radiographs. 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM); 2020 16-19 Dec. 2020.
15. Jang WS, Kim S, Yun PS, Jang HS, Seong YW, Yang HS, et al. Accurate detection for dental implant and peri-implant tissue by transfer learning of faster R-CNN: a diagnostic accuracy study. BMC Oral Health. 2022;22(1):591.
16. Muresan MP, Barbura AR, Nedevschi S, editors. Teeth Detection and Dental Problem Classification in Panoramic X-Ray Images using Deep Learning and Image Processing Techniques. 2020 IEEE 16th International Conference on Intelligent Computer Communication and Processing (ICCP); 2020 3-5 Sept. 2020.
17. Everett MJ, Colston BW, Sathyam US, Silva LBD, Fried D, Featherstone JDB. Noninvasive Diagnosis of Early Caries With Polarization-Sensitive Optical Coherence Tomography (PS-OCT). 1999.
18. Mărginean AC, Mureşanu S, Hedeşiu M, Dioşan L. Teeth Segmentation and Carious Lesions Segmentation in Panoramic X-Ray Images Using CariSeg, a Networks' Ensemble. Heliyon. 2024;10(10):e30836.
19. Lago CMG, López-Gazpio I, Onieva E. Deep Transfer Learning for Interpretable Chest X-Ray Diagnosis. 2021.
20. Reshi AA, Rustam F, Mehmood A, Alhossan A, Alrabiah Z, Ahmad A, et al. An Efficient CNN Model for COVID-19 Disease Detection Based on X-Ray Image Classification. Complexity. 2021.
21. Subramaniam U, Subashini MM, Almakhles D, Karthick A, Manoharan S. An Expert System for COVID-19 Infection Tracking in Lungs Using Image Processing and Deep Learning Techniques. Biomed Research International. 2021.
22. Prados-Privado M, Villalón JG, Martínez-Martínez CH, Ivorra C, Prados-Frutos JC. Dental Caries Diagnosis and Detection Using Neural Networks: A Systematic Review. Journal of Clinical Medicine. 2020.
23. Ren S, He K, Girshick R, Sun J. Faster R-Cnn: Towards Real-Time Object Detection With Region Proposal Networks. Ieee Transactions on Pattern Analysis and Machine Intelligence. 2017.
24. Jin X, Lan W, Chang X. Neural Path Planning With Multi-Scale Feature Fusion Networks. Ieee Access. 2022.
25. Patil S, Kulkarni V, Bhise A. Algorithmic Analysis for Dental Caries Detection Using an Adaptive Neural Network Architecture. Heliyon. 2019.
26. Majanga V, Viriri S. Automatic Blob Detection for Dental Caries. Applied Sciences. 2021.
27. Park J-H, Moon HS, Jung H-I, Hwang J, Choi Y-H, Kim J-E. Deep learning and clustering approaches for dental implant size classification based on periapical radiographs. Scientific Reports. 2023;13(1):16856.
28. Fourure D, Javaid MU, Posocco N, Tihon S, editors. Anomaly Detection: How to Artificially Increase Your F1-Score with a Biased Evaluation Protocol. Machine Learning and Knowledge Discovery in Databases Applied Data Science Track; 2021 2021//; Cham: Springer International Publishing.
29. Padilla R, Netto SL, Silva EABd, editors. A Survey on Performance Metrics for Object-Detection Algorithms. 2020 International Conference on Systems, Signals and Image Processing (IWSSIP); 2020 1-3 July 2020.
30. Erickson BJ, Kitamura F. Magician’s Corner: 9. Performance Metrics for Machine Learning Models. Radiology: Artificial Intelligence. 2021;3(3):e200126.
31. Özbay Y, Kazangirler BY, Özcan C, Pekince A. Detection of the separated endodontic instrument on periapical radiographs using a deep learning-based convolutional neural network algorithm. Australian Endodontic Journal. 2024;50(1):131-9.
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.
Engr. Syed Muhammad Zia Uddin
Department of Telecommunications Engineering, Ned University of Engineering and Technology, Karachi Pakistan
Dr. Muhammad Imran Aslam
Department of Telecommunications Engineering, Ned University of Engineering and Technology, Karachi Pakistan
Dr. Muhammad Moinuddin
Electrical and Computer Engineering Department, King Abdul Aziz University