人工智能在上颌磨牙根尖片中检测可临床疏通MB2根管
本研究开发并验证深度学习模型,用于在上颌第一和第二磨牙术前根尖片中检测可临床疏通的MB2根管,并与临床医生比较。共收集1504张由牙髓专科医生治疗的术前根尖片,使用六种预训练监督卷积神经网络和三种自监督模型进行五折交叉验证微调。ResNet-18在测试集上准确率最高达66.0%(95%CI 63.0-68.9),人类专家准确率为53.6%至61.4%,最优AI模型与人类专家准确率无显著差异(p>0.05)。
要点
- 深度学习模型在根尖片上检测可疏通MB2根管的准确率与牙髓专家相似。
- ResNet-18测试集准确率66.0%(95%CI 63.0-68.9),人类专家为53.6%至61.4%。
- AI在上颌第一磨牙及无全冠修复的牙齿上表现更好。
核心结论
- 深度学习模型在识别上颌第一和第二磨牙根尖片中可临床疏通的MB2根管方面与临床专家表现相似。
研究设计与样本
- 收集1504张上颌第一和第二磨牙术前根尖片,均由牙髓专科医生治疗,并附有无可临床疏通MB2根管的临床数据。
- 采用五折交叉验证微调六种预训练监督卷积神经网络(ResNet-18、ResNet-50、ResNeXt-101、VGG-16、DenseNet-121和MobileNetV2)和三种自监督模型(DINO、SimCLR和BYOL)。
- 在保留测试集上评估模型性能,指标包括准确率、精确率、灵敏度、特异度和F1分数及95%置信区间。
- 三名独立临床医生(一名牙髓专科医生、一名牙髓住院医师和一名口腔颌面放射科医生)也评估了测试集。
主要发现
- 交叉验证中ResNet-50平均准确率最高(67.6%),DINO在自监督模型中表现最佳(62.8%)。
- ResNet-18、ResNet-50、ResNeXt-101、DenseNet-121和DINO显著优于BYOL(p<0.01),最优模型间无显著差异。
- 测试集上ResNet-18准确率最高,为66.0%(95%CI 63.0-68.9),人类专家准确率范围为53.6%至61.4%。
- 分层分析显示AI模型在上颌第一磨牙和无全冠修复的牙齿上性能普遍更好。
- 最优AI模型与人类专家准确率无显著差异(p>0.05)。
临床怎么用
- AI可辅助临床医生评估牙髓病例难度,尤其是在识别可临床疏通的MB2根管方面。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
AIM: Artificial intelligence (AI) has the potential to aid clinicians in assessing case difficulty in endodontics. The objectives of this study were to develop and validate deep learning models for the detection of clinically negotiable MB2 canals in periapical images of maxillary first and second molars, and to compare the performance of AI models with that of human clinicians. METHODOLOGY: A total of 1504 pre-operative periapical images of maxillary first and second molars that were treated by endodontic specialists were collected with clinical data as to the presence or absence of a clinically negotiable MB2 canal. Six pretrained supervised convolutional neural networks (ResNet-18, ResNet-50, ResNeXt-101, VGG-16, DenseNet-121 and MobileNetV2) and three self-supervised models (DINO, SimCLR and BYOL) were fine-tuned using fivefold cross-validation. Model performance was evaluated on a hold-out test set using accuracy, precision, sensitivity, specificity, and F1-score with 95% confidence intervals. Three independent clinicians (an endodontist, an endodontic resident, and an oral and maxillofacial radiologist) also assessed the test set. RESULTS: In cross-validation, ResNet-50 achieved the highest mean accuracy (67.6%), while DINO was the top-performing self-supervised model (62.8%). ResNet-18, ResNet-50, ResNeXt-101, DenseNet-121 and DINO significantly outperformed BYOL (p < 0.01), while no significant differences were observed among the top-performing models. ResNet-18 achieved the highest accuracy at 66.0% (95% CI, 63.0-68.9) on the test set while human expert accuracy ranged from 53.6% to 61.4%. Stratified analysis showed a general trend for improved AI model performance in maxillary first molars and in teeth without full-crown restorations. There was no significant difference in the accuracy of the top-performing AI model and human experts (p > 0.05). CONCLUSION: Deep learning models performed similarly to clinician experts in identifying clinically negotiable MB2 canals in periapical images of maxillary first and second molars. These findings support the potential role of AI in endodontic case difficulty assessment.
引用
- Ourang SA, Sohrabniya F, Sadr S, et al. Artificial Intelligence in the Detection of Clinically Negotiable Second Mesio-Buccal Canals in Periapical Images of Maxillary Molars. Int Endod J. 2025. PMID: 41254435. doi:10.1111/iej.70065
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。