Wang Raokaijuan, Cheng Fangyuan, Dai Guangsheng, Zhang Jiayu, Fan Chengmin, Yu Jinghong, Li Juan, Jiang Fulin
Department of Orthodontics, West China School of Stomatology, Sichuan University, Chengdu, 610041, China.
Chengdu Boltzmann Intelligence Technology Co., Ltd, Chengdu, 610095, China.
BMC Oral Health. 2025 Jul 21;25(1):1230. doi: 10.1186/s12903-025-06356-w.
PXseg, a novel approach for tooth segmentation, numbering and abnormal morphology detection in panoramic X-ray (PX), was designed and promoted through optimizing annotation and applying pre-training.
Derived from multicenter, ctPXs generated from cone beam computed tomography (CBCT) with accurate 3D labels were utilized for pre-training, while conventional PXs (cPXs) with 2D labels were input for training. Visual and statistical analyses were conducted using the internal dataset to assess segmentation and numbering performances of PXseg and compared with the model without ctPX pre-training, while the accuracy of PXseg detecting abnormal teeth was evaluated using the external dataset consisting of cPXs with complex dental diseases. Besides, a diagnostic testing was performed to contrast diagnostic efficiency with and without PXseg's assistance.
The DSC and F1-score of PXseg in tooth segmentation reached 0.882 and 0.902, which increased by 4.6% and 4.0% compared to the model without pre-training. For tooth numbering, the F1-score of PXseg reached 0.943 and increased by 2.2%. Based on the promotion in segmentation, the accuracy of abnormal tooth morphology detection exceeded 0.957 and was 4.3% higher. A website was constructed to assist in PX interpretation, and the diagnostic efficiency was greatly enhanced with the assistance of PXseg.
The application of accurate labels in ctPX increased the pre-training weight of PXseg and improved the training effect, achieving promotions in tooth segmentation, numbering and abnormal morphology detection. Rapid and accurate results provided by PXseg streamlined the workflow of PX diagnosis, possessing significant clinical application prospect.
设计并推广了PXseg，这是一种用于全景X线片（PX）中牙齿分割、编号及异常形态检测的新方法，通过优化标注和应用预训练来实现。
利用来自多中心的、由锥束计算机断层扫描（CBCT）生成的带有精确三维标签的ctPXs进行预训练，同时将带有二维标签的传统PXs（cPXs）输入进行训练。使用内部数据集进行视觉和统计分析，以评估PXseg的分割和编号性能，并与未进行ctPX预训练的模型进行比较，同时使用由患有复杂牙病的cPXs组成的外部数据集评估PXseg检测异常牙齿的准确性。此外，进行了诊断测试，以对比有无PXseg辅助时的诊断效率。
PXseg在牙齿分割中的DSC和F1分数分别达到0.882和0.902，与未预训练的模型相比分别提高了4.6%和4.0%。对于牙齿编号，PXseg的F1分数达到0.943，提高了2.2%。基于分割方面的提升，异常牙齿形态检测的准确率超过0.957，提高了4.3%。构建了一个网站来辅助PX解读，在PXseg的辅助下诊断效率大大提高。
在ctPX中应用精确标签增加了PXseg的预训练权重，提高了训练效果，在牙齿分割编号及异常形态检测方面均有提升。PXseg提供的快速准确结果简化了PX诊断工作流程，具有显著的临床应用前景。
