Zhao Taotao, Ni Ming, Xia Shunxing, Jiao Yuehao, He Yating
College of Information Engineering, Sichuan Agricultural University, Ya'an 625014, China.
Nan Fang Yi Ke Da Xue Xue Bao. 2025 Aug 20;45(8):1791-1799. doi: 10.12122/j.issn.1673-4254.2025.08.23.
We propose a YOLOv11-TDSP model for improving the accuracy of dental abnormality detection on panoramic oral X-ray images.
The SHSA single-head attention mechanism was integrated with C2PSA in the backbone layer to construct a new C2PSA_SHSA attention mechanism. The computational redundancy was reduced by applying single-head attention to some input channels to enhance the efficiency and detection accuracy of the model. A small object detection layer was then introduced into the head layer to correct the easily missed and false detections of small objects. Two rounds of structured pruning were implemented to reduce the number of model parameters, avoid overfitting, and improve the average precision. Before training, data augmentation techniques such as brightness enhancement and gamma contrast adjustment were employed to enhance the generalization ability of the model.
The experiment results showed that the optimized YOLOv11-TDSP model achieved an accuracy of 94.5%, a recall rate of 92.3%, and an average precision of 95.8% for detecting dental abnormalities. Compared with the baseline model YOLOv11n, these metrics were improved by 6.9%, 7.4%, and 5.6%, respectively. The number of parameters and computational cost of the YOLOv11-TDSP model were only 12% and 13% of those of the high-precision YOLOv11x model, respectively.
The lightweight YOLOv11-TDSP model is capable of highly accurate identification of various dental diseases on panoramic oral X-ray images.
我们提出一种YOLOv11 - TDSP模型，以提高全景口腔X光图像上牙齿异常检测的准确性。
将SHSA单头注意力机制与骨干层中的C2PSA相结合，构建新的C2PSA_SHSA注意力机制。通过对一些输入通道应用单头注意力来减少计算冗余，以提高模型的效率和检测准确性。然后在头部层引入小目标检测层，以纠正小目标容易漏检和误检的问题。实施两轮结构化剪枝以减少模型参数数量，避免过拟合，并提高平均精度。在训练前，采用亮度增强和伽马对比度调整等数据增强技术来提高模型的泛化能力。
实验结果表明，优化后的YOLOv11 - TDSP模型在检测牙齿异常方面的准确率达到94.5%，召回率为92.3%，平均精度为95.8%。与基线模型YOLOv11n相比，这些指标分别提高了6.9%、7.4%和5.6%。YOLOv11 - TDSP模型的参数数量和计算成本分别仅为高精度YOLOv11x模型的12%和13%。
轻量级的YOLOv11 - TDSP模型能够在全景口腔X光图像上高精度地识别各种牙齿疾病。
