Frenkel Elisabeth, Neumayr Julia, Schwarzmaier Julia, Kessler Andreas, Ammar Nour, Schwendicke Falk, Kühnisch Jan, Dujic Helena
Department of Conservative Dentistry and Periodontology, University Hospital, Ludwig-Maximilians University of Munich, 80336 Munich, Germany.
Department of Prosthetic Dentistry, Faculty of Medicine, Center for Dental Medicine, Medical Center-University of Freiburg, University of Freiburg, 79106 Freiburg, Germany.
Diagnostics (Basel). 2024 Oct 14;14(20):2281. doi: 10.3390/diagnostics14202281.
This ex vivo diagnostic study aimed to externally validate a freely accessible AI-based model for caries detection, classification, localisation and segmentation using an independent image dataset. It was hypothesised that there would be no difference in diagnostic performance compared to previously published internal validation data.
For the independent dataset, 718 dental images representing different stages of carious ( = 535) and noncarious teeth ( = 183) were retrieved from the internet. All photographs were evaluated by the dental team (reference standard) and the AI-based model (test method). Diagnostic performance was statistically determined using cross-tabulations to calculate accuracy (ACC), sensitivity (SE), specificity (SP) and area under the curve (AUC).
An overall ACC of 92.0% was achieved for caries detection, with an ACC of 85.5-95.6%, SE of 42.9-93.3%, SP of 82.1-99.4% and AUC of 0.702-0.909 for the classification of caries. Furthermore, 97.0% of the cases were accurately localised. Fully and partially correct segmentation was achieved in 52.9% and 44.1% of the cases, respectively.
The validated AI-based model showed promising diagnostic performance in detecting and classifying caries using an independent image dataset. Future studies are needed to investigate the validity, reliability and practicability of AI-based models using dental photographs from different image sources and/or patient groups.
这项体外诊断研究旨在使用独立图像数据集对外验证一个可免费获取的基于人工智能的龋齿检测、分类、定位和分割模型。研究假设是，与之前发表的内部验证数据相比，该模型的诊断性能不会有差异。
对于独立数据集，从互联网上检索了718张代表龋齿（n = 535）和非龋齿（n = 183）不同阶段的牙科图像。所有照片均由牙科团队（参考标准）和基于人工智能的模型（测试方法）进行评估。使用交叉表统计确定诊断性能，以计算准确率（ACC）、灵敏度（SE）、特异度（SP）和曲线下面积（AUC）。
龋齿检测的总体准确率为92.0%，龋齿分类的准确率为85.5 - 95.6%，灵敏度为42.9 - 93.3%，特异度为82.1 - 99.4%，曲线下面积为0.702 - 0.909。此外，97.0%的病例定位准确。分别有52.9%和44.1%的病例实现了完全和部分正确分割。
经过验证的基于人工智能的模型在使用独立图像数据集检测和分类龋齿方面表现出了有前景的诊断性能。未来需要开展研究，使用来自不同图像来源和/或患者群体的牙科照片，调查基于人工智能的模型的有效性、可靠性和实用性。
