Submit Manuscript
Edit a Special Issue
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 - request pending PB - Institute of Central Computation and Knowledge LA - English ER -
@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 = {request pending},
publisher = {Institute of Central Computation and Knowledge}
}
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. 
Frontiers in Biomedical Signal Processing
ISSN: request pending (Online) | ISSN: request pending (Print)
Email: [email protected]
Portico
All published articles are preserved here permanently:
https://www.portico.org/publishers/icck/