Research Article
Open Access
Dental Classes Classification using TEYOLOv8 Network
1
Department of Electronics and Communication Engineering, Tirumala Institute of Technology and Sciences, Narasaraopet 522549, India
2
Department of Electronics and Communication Engineering, Tirumala Engineering College, Narasaraopet 522601, India
* Corresponding Author:
Pavan Sandula,
[email protected]
Volume 1, Issue 1
2026
Received: 13 September 2025
Accepted: 16 September 2025
Published: 08 November 2025
You have full access to this open access article
·
CC BY 4.0 License
Article Information
Published in
Frontiers in Biomedical Signal Processing
Volume/Issue
Volume 1, Issue 1, 2026
Pages
37-48
Abstract
Accurate and automated detection of dental anatomy is essential for diagnosis and treatment planning. This study proposes a Transformer-Embedded YOLOv8 (TEYOLOv8) network to improve detection and classification of seven dental classes. The model enhances localization and segmentation accuracy by embedding an attentive transformer mechanism into the YOLOv8 framework. The TEYOLOv8 architecture integrates data augmentation, feature localization, segmentation, and classification. It employs C2f (Cross-Stage Partial Focus) convolutional blocks to preserve partial segmentation features and introduces a C2fAttn (Cross-Stage Feature Attention) module to capture fine-grained spatial details such as shape and position, addressing feature dissimilarity and loss. The model was trained and evaluated on a custom dental dataset with metrics including mean Average Precision (mAP), precision, and recall. Experimental results demonstrate that TEYOLOv8 achieves superior performance, with precision of 0.954, recall of 0.973, [email protected] of 0.981, and [email protected]:0.95 of 0.794. The integration of the attention mechanism substantially improves feature representation and segmentation quality, enabling precise localization and classification of complex dental structures. Clinical Significance: The TEYOLOv8 model provides an efficient and accurate tool for dental image analysis, supporting precise identification of dental classes. It has strong potential to streamline clinical workflows, improve diagnostic accuracy, and enhance patient outcomes.
Graphical Abstract
Keywords
attention mechanism
classification
cross-stage feature attention
mean average Precision (mAP)
YOLOv8
Data Availability Statement
Data will be made available on request.
Funding
This work was supported without any funding.
Conflicts of Interest
The authors declare no conflicts of interest.
Ethical Approval and Consent to Participate
Not applicable.
References
- MUHAMAD, D. A. H. (2016). Dental and Oral Health. Sciences, 14(4), 124-130.
[Google Scholar] - Liu, X., Faes, L., Kale, A. U., Wagner, S. K., Fu, D. J., Bruynseels, A., ... & Denniston, A. K. (2019). A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: a systematic review and meta-analysis. The lancet digital health, 1(6), e271-e297.
[CrossRef] [Google Scholar] - Rozylo-Kalinowska, I. (2020). Introduction to Dental Radiography and Radiology. In Imaging Techniques in Dental Radiology: Acquisition, Anatomic Analysis and Interpretation of Radiographic Images (pp. 1-5). Cham: Springer International Publishing.
[CrossRef] [Google Scholar] - Tsuneki, M. (2022). Deep learning models in medical image analysis. Journal of Oral Biosciences, 64(3), 312-320.
[CrossRef] [Google Scholar] - Schwendicke, F., Golla, T., Dreher, M., & Krois, J. (2019). Convolutional neural networks for dental image diagnostics: A scoping review. Journal of dentistry, 91, 103226.
[CrossRef] [Google Scholar] - Fang, W., Wang, L., & Ren, P. (2019). Tinier-YOLO: A real-time object detection method for constrained environments. Ieee Access, 8, 1935-1944.
[CrossRef] [Google Scholar] - Ganguly, A., & Ruby, A. U. (2023). Evaluating CNN architectures using attention mechanisms: Convolutional Block Attention Module, Squeeze, and Excitation for image classification on CIFAR10 dataset.
[Google Scholar] - Chien, C. T., Ju, R. Y., Chou, K. Y., Xieerke, E., & Chiang, J. S. (2025). YOLOv8-AM: YOLOv8 Based on Effective Attention Mechanisms for Pediatric Wrist Fracture Detection. IEEE Access.
[CrossRef] [Google Scholar] - Ghafoor, A., Moon, S. Y., & Lee, B. (2023). Multiclass Segmentation Using Teeth Attention Modules for Dental X-Ray Images. IEEE Access, 11, 123891-123903.
[CrossRef] [Google Scholar] - Razaghi, M., Komleh, H. E., Dehghani, F., & Shahidi, Z. (2024, March). Innovative diagnosis of dental diseases using YOLO V8 deep learning model. In 2024 13th Iranian/3rd International Machine Vision and Image Processing Conference (MVIP) (pp. 1-5). IEEE.
[CrossRef] [Google Scholar] - Sukegawa, S., Yoshii, K., Hara, T., Tanaka, F., Yamashita, K., Kagaya, T., ... & Furuki, Y. (2022). Is attention branch network effective in classifying dental implants from panoramic radiograph images by deep learning?. PLoS One, 17(7), e0269016.
[CrossRef] [Google Scholar] - George, J., Hemanth, T. S., Raju, J., Mattapallil, J. G., & Naveen, N. (2023, August). Dental radiography analysis and diagnosis using YOLOv8. In 2023 9th International Conference on Smart Computing and Communications (ICSCC) (pp. 102-107). IEEE.
[CrossRef] [Google Scholar] - Rischen, R. J., Breuning, K. H., Bronkhorst, E. M., & Kuijpers-Jagtman, A. M. (2013). Records needed for orthodontic diagnosis and treatment planning: a systematic review. PLoS one, 8(11), e74186.
[CrossRef] [Google Scholar] - Davila, K., Setlur, S., Doermann, D., Kota, B. U., & Govindaraju, V. (2020). Chart mining: A survey of methods for automated chart analysis. IEEE transactions on pattern analysis and machine intelligence, 43(11), 3799-3819.
[CrossRef] [Google Scholar] - Kong, M., He, Q., & Li, L. (2018). AI assisted clinical diagnosis & treatment, and development strategy. Strategic Study of Chinese Academy of Engineering, 20(2), 86-91.
[Google Scholar] - Wang, H., Diao, K., Wu, L., Li, X., Zhou, X., & Liu, X. (2024, December). An Automatic Tooth Position and Dental Disease Detection Algorithm Based on YOLOv8. In 2024 10th International Conference on Computer and Communications (ICCC) (pp. 2058-2062). IEEE.
[CrossRef] [Google Scholar] - Akdoğan, S., Öziç, M. Ü., & Tassoker, M. (2025). Development of an AI-Supported clinical tool for assessing mandibular third molar tooth extraction difficulty using panoramic radiographs and YOLO11 Sub-Models. Diagnostics, 15(4), 462.
[CrossRef] [Google Scholar]
Cite This Article
APA Style
Chilaka, V. K., Sandula, P., & Thati, J. (2025). Dental Classes Classification using TEYOLOv8 Network. Frontiers in Biomedical Signal Processing, 1(1), 37–48. https://doi.org/10.62762/FBSP.2025.431958
Export Citation
RIS Format
Compatible with EndNote, Zotero, Mendeley, and other reference managers
TY - JOUR AU - Chilaka, Victor Kumar AU - Sandula, Pavan AU - Thati, Jagadeesh PY - 2025 DA - 2025/11/08 TI - Dental Classes Classification using TEYOLOv8 Network JO - Frontiers in Biomedical Signal Processing T2 - Frontiers in Biomedical Signal Processing JF - Frontiers in Biomedical Signal Processing VL - 1 IS - 1 SP - 37 EP - 48 DO - 10.62762/FBSP.2025.431958 UR - https://www.icck.org/article/abs/FBSP.2025.431958 KW - attention mechanism KW - classification KW - cross-stage feature attention KW - mean average Precision (mAP) KW - YOLOv8 AB - Accurate and automated detection of dental anatomy is essential for diagnosis and treatment planning. This study proposes a Transformer-Embedded YOLOv8 (TEYOLOv8) network to improve detection and classification of seven dental classes. The model enhances localization and segmentation accuracy by embedding an attentive transformer mechanism into the YOLOv8 framework. The TEYOLOv8 architecture integrates data augmentation, feature localization, segmentation, and classification. It employs C2f (Cross-Stage Partial Focus) convolutional blocks to preserve partial segmentation features and introduces a C2fAttn (Cross-Stage Feature Attention) module to capture fine-grained spatial details such as shape and position, addressing feature dissimilarity and loss. The model was trained and evaluated on a custom dental dataset with metrics including mean Average Precision (mAP), precision, and recall. Experimental results demonstrate that TEYOLOv8 achieves superior performance, with precision of 0.954, recall of 0.973, [email protected] of 0.981, and [email protected]:0.95 of 0.794. The integration of the attention mechanism substantially improves feature representation and segmentation quality, enabling precise localization and classification of complex dental structures. Clinical Significance: The TEYOLOv8 model provides an efficient and accurate tool for dental image analysis, supporting precise identification of dental classes. It has strong potential to streamline clinical workflows, improve diagnostic accuracy, and enhance patient outcomes. SN - 3071-2912 PB - Institute of Central Computation and Knowledge LA - English ER -
BibTeX Format
Compatible with LaTeX, BibTeX, and other reference managers
@article{Chilaka2025Dental,
author = {Victor Kumar Chilaka and Pavan Sandula and Jagadeesh Thati},
title = {Dental Classes Classification using TEYOLOv8 Network},
journal = {Frontiers in Biomedical Signal Processing},
year = {2025},
volume = {1},
number = {1},
pages = {37-48},
doi = {10.62762/FBSP.2025.431958},
url = {https://www.icck.org/article/abs/FBSP.2025.431958},
abstract = {Accurate and automated detection of dental anatomy is essential for diagnosis and treatment planning. This study proposes a Transformer-Embedded YOLOv8 (TEYOLOv8) network to improve detection and classification of seven dental classes. The model enhances localization and segmentation accuracy by embedding an attentive transformer mechanism into the YOLOv8 framework. The TEYOLOv8 architecture integrates data augmentation, feature localization, segmentation, and classification. It employs C2f (Cross-Stage Partial Focus) convolutional blocks to preserve partial segmentation features and introduces a C2fAttn (Cross-Stage Feature Attention) module to capture fine-grained spatial details such as shape and position, addressing feature dissimilarity and loss. The model was trained and evaluated on a custom dental dataset with metrics including mean Average Precision (mAP), precision, and recall. Experimental results demonstrate that TEYOLOv8 achieves superior performance, with precision of 0.954, recall of 0.973, [email protected] of 0.981, and [email protected]:0.95 of 0.794. The integration of the attention mechanism substantially improves feature representation and segmentation quality, enabling precise localization and classification of complex dental structures. Clinical Significance: The TEYOLOv8 model provides an efficient and accurate tool for dental image analysis, supporting precise identification of dental classes. It has strong potential to streamline clinical workflows, improve diagnostic accuracy, and enhance patient outcomes.},
keywords = {attention mechanism, classification, cross-stage feature attention, mean average Precision (mAP), YOLOv8},
issn = {3071-2912},
publisher = {Institute of Central Computation and Knowledge}
}
Article Metrics
Publisher's Note
ICCK stays neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and Permissions
Copyright © 2025 by the Author(s). Published by Institute of Central Computation and Knowledge. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/), which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made.
Preserved at
Portico
Portico
Scan to read this article