人工智能辅助口腔内咬翼片与根尖片龋齿诊断的验证研究
本研究评估基于人工智能(Diagnocat)系统在口腔内放射影像上诊断龋齿的可靠性,由两名独立观察者评估323颗选定牙齿的邻面。经过四个阶段比较人工与AI的一致性、灵敏度、特异度及诊断准确率,结论认为该卷积神经网络系统可支持口腔内放射影像的龋齿诊断。
要点
- AI系统与人工观察者间Cohen kappa范围在四个阶段为κ=0.49-1。
- AI诊断灵敏度0.51-0.76、特异度0.88-0.97、准确率0.76-0.86。
- AI系统可作为口腔内放射影像龋齿诊断的辅助支持工具。
核心结论
- Diagnocat卷积神经网络系统可支持口腔内放射影像的龋齿诊断,依据为人与AI观察者间达成共识。
研究设计与样本
- 研究纳入323颗选定牙齿的口腔内放射影像,由两名独立观察者使用基于AI的Diagnocat系统评估邻面。
- 研究分四阶段:第一阶段记录龋损存在与否;4个月后第二阶段由AI辅助的人工观察者评估同一影像;第三阶段由先进卷积神经网络重新评估放射数据;第四阶段排除反映人工分歧的数据。
- 每阶段计算Cohen与Fleiss kappa值,以及Diagnocat的灵敏度、特异度、阳性与阴性预测值和诊断准确率。
主要发现
- 四个阶段中,人工观察者与Diagnocat之间的Cohen kappa值范围为κ=0.66-1、κ=0.58-0.7和κ=0.49-0.7。
- Fleiss kappa值为κ=0.57-0.8。
- 灵敏度、特异度和诊断准确率范围分别为0.51-0.76、0.88-0.97和0.76-0.86。
关键数值与推荐
- Cohen kappa值范围κ=0.66-1、κ=0.58-0.7、κ=0.49-0.7(人工观察者与Diagnocat之间,四个阶段)。
- Fleiss kappa值κ=0.57-0.8。
- 灵敏度0.51-0.76、特异度0.88-0.97、诊断准确率0.76-0.86。
临床怎么用
- 临床可参考该AI系统辅助口腔内放射影像的龋齿诊断,但需注意其灵敏度范围较宽。
- AI结果宜结合人工判读,尤其在人工观察者间存在分歧时。
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: This study aimed to assess the reliability of AI-based system that assists the healthcare processes in the diagnosis of caries on intraoral radiographs. METHODS: The proximal surfaces of the 323 selected teeth on the intraoral radiographs were evaluated by two independent observers using an AI-based (Diagnocat) system. The presence or absence of carious lesions was recorded during Phase 1. After 4 months, the AI-aided human observers evaluated the same radiographs (Phase 2), and the advanced convolutional neural network (CNN) reassessed the radiographic data (Phase 3). Subsequently, data reflecting human disagreements were excluded (Phase 4). For each phase, the Cohen and Fleiss kappa values, as well as the sensitivity, specificity, positive and negative predictive values, and diagnostic accuracy of Diagnocat, were calculated. RESULTS: During the four phases, the range of Cohen kappa values between the human observers and Diagnocat were κ=0.66-1, κ=0.58-0.7, and κ=0.49-0.7. The Fleiss kappa values were κ=0.57-0.8. The sensitivity, specificity and diagnostic accuracy values ranged between 0.51-0.76, 0.88-0.97 and 0.76-0.86, respectively. CONCLUSIONS: The Diagnocat CNN supports the evaluation of intraoral radiographs for caries diagnosis, as determined by consensus between human and AI system observers. CLINICAL SIGNIFICANCE: Our study may aid in the understanding of deep learning-based systems developed for dental imaging modalities for dentists and contribute to expanding the body of results in the field of AI-supported dental radiology..
引用
- Szabó V, Szabó BT, Orhan K, et al. Validation of artificial intelligence application for dental caries diagnosis on intraoral bitewing and periapical radiographs. J Dent. 2024. PMID: 38821394. doi:10.1016/j.jdent.2024.105105
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。