人工智能预测龋齿去腐露髓:深度学习图像数据与标准牙科X线片的比较
研究用292张术前咬翼片构建多路径神经网络预测露髓概率,并让25名牙科学生在四种信息条件下进行预测。AI模型F1分数0.71显著优于所有学生组(P<0.001);学生获得AI预测后F1分数仅从0.58/0.59升至0.61,差异边缘显著(P=0.054)。结论认为AI性能优越但学生获益有限,需更可解释的AI预测及学习曲线。
要点
- AI模型预测露髓F1分数0.71,显著优于牙科学生各组(P<0.001)。
- 学生获得AI预测后F1仅从0.58/0.59升至0.61,差异边缘显著(P=0.054)。
- AI辅助对学生预测能力的提升有限,需更可解释的AI与学习曲线。
核心结论
- AI模型预测露髓性能显著优于所有学生组,但学生获得AI预测后仅轻微获益。
- AI技术有前景,但需更可解释的预测及学习曲线。
研究设计与样本
- 使用292张术前咬翼片,构建基于ResNet-50的CNN与基于牙髓-病变距离的神经网络融合模型。
- 25名牙科学生参与试验,分四组:仅X线、X线+临床数据、X线+AI、X线+临床数据+AI。
主要发现
- AI模型F1分数0.71,显著优于所有学生组(P<0.001)。
- 学生X线+AI组和X线+临床数据+AI组F1均为0.61,略高于仅X线组0.58和X线+临床数据组0.59,P=0.054。
关键数值与推荐
- AI模型F1分数0.71(P<0.001 vs 学生组)。
- 学生F1:仅X线0.58,X线+临床数据0.59,X线+AI 0.61,X线+临床数据+AI 0.61,P=0.054。
临床怎么用
- AI可辅助预测龋齿去腐前露髓风险,但学生使用AI预测的增益有限。
- 临床引入AI需配合可解释性提升与学习曲线培训。
局限性
- AI预测对学生帮助仅轻微,可能限制其教学与临床辅助价值。
- 需更可解释的AI预测及学习曲线。
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
OBJECTIVES: The objective was to examine the effect of giving Artificial Intelligence (AI)-based radiographic information versus standard radiographic and clinical information to dental students on their pulp exposure prediction ability. METHODS: 292 preoperative bitewing radiographs from patients previously treated were used. A multi-path neural network was implemented. The first path was a convolutional neural network (CNN) based on ResNet-50 architecture. The second path was a neural network trained on the distance between the pulp and lesion extracted from X-ray segmentations. Both paths merged and were followed by fully connected layers that predicted the probability of pulp exposure. A trial concerning the prediction of pulp exposure based on radiographic input and information on age and pain was conducted, involving 25 dental students. The data displayed was divided into 4 groups (G): GX-ray, GX-ray+clinical data, GX-ray+AI, GX-ray+clinical data+AI. RESULTS: The results showed that AI surpassed the performance of students in all groups with an F1-score of 0.71 (P < 0.001). The students' F1-score in GX-ray+AI and GX-ray+clinical data+AI with model prediction (0.61 and 0.61 respectively) was slightly higher than the F1-score in GX-ray and GX-ray+clinical data (0.58 and 0.59 respectively) with a borderline statistical significance of P = 0.054. CONCLUSIONS: Although the AI model had much better performance than all groups, the participants when given AI prediction, benefited only 'slightly'. AI technology seems promising, but more explainable AI predictions along with a 'learning curve' are warranted.
引用
- Ramezanzade S, Dascalu TL, Ibragimov B, et al. Prediction of pulp exposure before caries excavation using artificial intelligence: Deep learning-based image data versus standard dental radiographs. J Dent. 2023. PMID: 37778496. doi:10.1016/j.jdent.2023.104732
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。