混合牙列全景影像C2f-CBAM儿童牙病检测方法

焦总政; 杨帅康; 王少辉; Minpo Jung

doi:10.70693/cjst.v2i3.2029

Authors

焦总政韩国灵山大学
杨帅康韩国灵山大学
王少辉韩国灵山大学
Minpo Jung 韩国灵山大学

DOI:

https://doi.org/10.70693/cjst.v2i3.2029

Keywords:

儿童牙科全景影像；混合牙列；YOLOv8；C2f-CBAM；目标检测；辅助筛查

Abstract

针对儿童混合牙列期牙科全景 X 光片中背景结构复杂、病灶尺寸微小且纹理特征模糊等问题，本文提出一种基于 C2f-CBAM 嵌入式 YOLOv8 的儿童牙病自动检测方法。该方法在 YOLOv8 主干网络的 C2f 模块中嵌入卷积块注意力模块，通过通道注意力与空间注意力联合建模，引导网络关注牙体硬组织脱矿、牙髓钙化和修复体边缘等局部病灶特征。实验采用 Kaggle 平台公开发布的儿童牙科全景 X 光数据集，包含 849 张 0~12 岁儿童全景影像及 14 类牙科疾病或异常标注。补充实验结果表明，C2f-CBAM YOLOv8 在 mAP50 为 88.27%、mAP50-95 为 67.19% 的条件下保持 32.0 FPS 的推理速度。与 baseline_c2f 相比，C2f-CBAM 整体精度略有下降，说明注意力模块在该数据集上并未带来全面指标提升；但与 Faster R-CNN 相比，所提模型在 mAP50、mAP50-95 和实时推理效率方面具有明显优势。研究结果表明，C2f-CBAM YOLOv8 更适合作为儿童混合牙列全景片的辅助筛查模型，为后续口腔影像智能分析系统提供了实验参考。

References

[1] World Health Organization. Global oral health status report: towards universal health coverage for oral health by 2030[R]. Geneva: World Health Organization, 2022.

[2] Zhang Y, Ye F, Chen L, et al. Children’s dental panoramic radiographs dataset for caries segmentation and dental disease detection[J]. Scientific Data, 2023, 10: 380.

[3] Beser B, Reis T, Berber M N, et al. YOLO-V5 based deep learning approach for tooth detection and segmentation on pediatric panoramic radiographs in mixed dentition[J]. BMC Medical Imaging, 2024, 24: 1-12.

[4] Ren S, He K, Girshick R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks[C]//Advances in Neural Information Processing Systems. 2015: 91-99.

[5] Wang C Y, Bochkovskiy A, Liao H Y M. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2023: 7464-7475.

[6] Jocher G, Chaurasia A, Qiu J. YOLO by Ultralytics, version 8.0.0[CP/OL]. 2023 [2026-05-25]. https://github.com/ultralytics/ultralytics.

[7] Tuzoff D V, Tuzova L N, Bornstein M M, et al. Tooth detection and numbering in panoramic radiographs using convolutional neural networks[J]. Dentomaxillofacial Radiology, 2019, 48(4): 20180051.

[8] Lian H, Li L, Wang T, et al. Multiscale attention-based convolutional neural network for caries detection in dental panoramic radiographs[J]. IEEE Transactions on Medical Imaging, 2021, 40(12): 3662-3675.

[9] Bayati M, Alizadeh Savareh B, Ahmadinejad H, et al. Advanced AI-driven detection of interproximal caries in bitewing radiographs using YOLOv8[J]. Scientific Reports, 2025, 15: 1-12.

[10] Pornprasertsuk-Damrongsri S, Vachmanus S, Papasratorn D, et al. Clinical application of deep learning for enhanced multistage caries detection in dental radiographs[J]. BMC Oral Health, 2025, 25: 1-12.

[11] Vinayahalingam S, Kempers S, Limon L, et al. Classification of caries in third molars on panoramic radiographs using deep learning[J]. Scientific Reports, 2021, 11: 12609.

[12] Chen Y, Du H, Yun Z, et al. Automatic detection of prominent dental diseases using dental X-ray images: A survey[J]. IEEE Access, 2021, 9: 165567-165586.

[13] Majanga V, Viriri S. A survey of dental caries segmentation and detection techniques[J]. Scientific World Journal, 2022: 8415705.

[14] Peker R B, Kurtoglu C O. Evaluation of the performance of a YOLOv10-based deep learning model for tooth detection and numbering on panoramic radiographs[J]. Diagnostics, 2025, 15: 1-15.

[15] Hu J, Shen L, Sun G. Squeeze-and-excitation networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018: 7132-7141.

[16] Hou Q, Zhou D, Feng J. Coordinate attention for efficient mobile network design[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2021: 13713-13722.

[17] Woo S, Park J, Lee J Y, et al. CBAM: Convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision. 2018: 3-19.

[18] Zuiderveld K. Contrast limited adaptive histogram equalization[M]//Heckbert P S. Graphics Gems IV. San Diego: Academic Press Professional, 1994: 474-485.

[19] Wanmugui. Children’s dental panoramic x-ray datase t[DB/OL]. Kaggle. [2026-05-25]. https://www.kaggle.com/datasets/wanmugui/childrens-dental-panoramic-x-ray-dataset