Design of an Intelligent Detection System for Dental Health Status Based on Improved YOLOv8

DOI: https://doi.org/10.62517/jike.202604132

Author(s)

Zhengju Guo, Yu Pu, Ting Huang, Jiarui Luo, Shengni Fu, Guangyan Wang*

Affiliation(s)

School of Information Engineering, Tianjin University of Commerce, Tianjin, China *Corresponding Author

Abstract

To address the issues of low efficiency and high error rates associated with traditional manual diagnosis in oral health examinations, this paper proposes a real-time dental health detection system based on an improved YOLOv8 algorithm. By integrating the SE attention mechanism to enhance the recognition capability for subtle lesions and optimizing the CIoU loss function to improve localization accuracy, the system is trained and validated on a constructed dataset comprising nearly 3,000 multi-modal oral images. The proposed system achieves an average precision (AP) of 84.26% for ulcers and a detection accuracy of 63.64% for caries in oral endoscopic images. For dental panoramic radiographs, the system enables accurate localization of metallic restorations, and the detection results exhibit strong robustness under complex backgrounds. This system provides a viable technical solution for the intelligent screening and computer-aided diagnosis of dental diseases.

Keywords

Dental Health Detection; YOLOv8 Algorithm; Deep Learning; Dental Medical Imaging; Object Detection

References

[1]M. Lin, L. Zou, R. Gao and R. Peng, "Research on visual image processing based on YOLO algorithm," 2025 2nd International Conference on Digital Image Processing and Computer Applications (DIPCA), Xi'an, China, 2025, pp. 10-14. [2]L. Hu, "An Improved YOLOv5 Algorithm of Target Recognition,"2023 IEEE 2nd International Conference on Electrical Engineering, Big Data and Algorithms (EEBDA), Changchun, China, 2023, pp.1373-1377. [3]Li F, Sun H, Wang F, et al. Lightweight optimization of YOLOv8m for robotic vision-based snack cucumber sorting and palletizing. Journal of Agriculture and Food Research, 2025, 23102248-102248. [4]G. -H. Li, T. -C. Hsung, W. -K. Ling, W. Yu-Hang Lam, G. Pelekos and C. McGrath, "Automatic Site-Specific Multiple Level Gum Disease Detection Based on Deep Neural Network," 2021 15th International Symposium on Medical Information and Communication Technology (ISMICT), Xiamen, China, 2021, pp. 201-205. [5]Qi S, Fu Y, Zhang Q, et al. Localisation and classification of multi-stage caries on CBCT images with a 3D convolutional neural network. Clinical Oral Investigations, 2025, 29: 246. [6]Atni M H M, Rosdy M N M M N, Tajudin M A A M, et al. Development and evaluation of a multi-model stacking approach for caries risk assessment in adults using supervised machine learning. British Dental Journal, 2025, (prepublish):1-7. [7]Lin W C, Chiang C P. Artificial intelligence measurement of multi-layer tooth structures using semantic segmentation and computer vision. Journal of Dental Sciences, 2024, 20(1): 723-725. [8]Ghorbani M, Nozari S, Nekooei M, et al. Artificial Intelligence for Root Canal Segmentation on Radiographic Images: A Scoping Review. Research Square, 2025-03-19. [9]Edik M, Çelebi F, Çukurluoğlu A. Deeplearningbased detection of openapex teeth on panoramic radiographs using YOLO models. Oral radiology, 2025: 1-11. [10]Mendes C A, Quintanilha P B D, Pessoa P C A, et al. Automated Tooth Detection and Numbering in Panoramic Radiographs Using YOLO. Procedia Computer Science, 2025, 2561318-1325. [11]Mao Z, Li X, Hu S, et al. A GPU accelerated mixed-precision Smoothed Particle Hydrodynamics framework with cell-based relative coordinates. Engineering Analysis with Boundary Elements, 2024, 161113-125. [12]Zhuo Y, Kirkpatrick A W, Couperus K, et al. The Trauma THOMPSON Challenge Report MICCAI 2023. Lecture Notes in Computer Science, 2025: 61-71. [13]Ronneberger O, Fischer P, Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation. Medical Image Computing and Computer-Assisted Intervention. MICCAI 2015. Springer International Publishing, 2015: 234-241. [14]Liu J, Zhang H, Chen J, et al. Automated detection and segmentation of dental caries using a novel cascaded learning approach. Biomedical Signal Processing and Control, 2025, 96: 106498. [15]Yeh J-Y, Wu S-Y. Probability-Based Two-Stage CNN for Pulmonary Embolism Detection in Computed Tomography Pulmonary Angiography. International Journal on Engineering, Science and Technology, 2023, 4(4): 344–367.. [16]Casalegno F, Newton T, Daher R, et al. Caries detection with near -infrared transillumination using deep learning. J Dent Res, 2019, 98(11): 1227-1233.24 [17]Goodfellow I, Pouget-Abadie J, Mirza M, et al. Generative adversarial nets. Advances in neural information processing systems, MIT Press, 2014, 27: 2672 - 2680.