van Nistelrooij Niels, Chaves Eduardo Trota, Cenci Maximiliano Sergio, Cao Lingyun, Loomans Bas A C, Xi Tong, El Ghoul Khalid, Romero Vitor Henrique Digmayer, Lima Giana Silveira, Flügge Tabea, van Ginneken Bram, Huysmans Marie-Charlotte, Vinayahalingam Shankeeth, Mendes Fausto Medeiros
Department of Oral and Maxillofacial Surgery, Radboud University Medical Center, Nijmegen, The Netherlands.
Department of Oral and Maxillofacial Surgery, Charité - Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt Universität zu Berlin, Berlin, Germany.
Caries Res. 2025;59(3):163-173. doi: 10.1159/000542289. Epub 2024 Oct 29.
Despite the notable progress in developing artificial intelligence-based tools for caries detection in bitewings, limited research has addressed the detection and staging of secondary caries. Therefore, we aimed to develop a convolutional neural network (CNN)-based algorithm for these purposes using a novel approach for determining lesion severity.
We used a dataset from a Dutch dental practice-based research network containing 2,612 restored teeth in 413 bitewings from 383 patients aged 15-88 years and trained the Mask R-CNN architecture with a Swin Transformer backbone. Two-stage training fine-tuned caries detection accuracy and severity assessment. Annotations of caries around restorations were made by two evaluators and checked by two other experts. Aggregated accuracy metrics (mean ± standard deviation - SD) in detecting teeth with secondary caries were calculated considering two thresholds: detecting all lesions and dentine lesions. The correlation between the lesion severity scores obtained with the algorithm and the annotators' consensus was determined using the Pearson correlation coefficient and Bland-Altman plots.
Our refined algorithm showed high specificity in detecting all lesions (0.966 ± 0.025) and dentine lesions (0.964 ± 0.019). Sensitivity values were lower: 0.737 ± 0.079 for all lesions and 0.808 ± 0.083 for dentine lesions. The areas under ROC curves (SD) were 0.940 (0.025) for all lesions and 0.946 (0.023) for dentine lesions. The correlation coefficient for severity scores was 0.802.
We developed an improved algorithm to support clinicians in detecting and staging secondary caries in bitewing, incorporating an innovative approach for annotation, considering the lesion severity as a continuous outcome.
尽管在开发基于人工智能的咬翼片龋齿检测工具方面取得了显著进展，但针对继发龋的检测和分期的研究仍然有限。因此，我们旨在使用一种确定病变严重程度的新方法，开发一种基于卷积神经网络（CNN）的算法来实现这些目的。
我们使用了来自荷兰基于牙科实践的研究网络的数据集，该数据集包含383名年龄在15 - 88岁患者的413张咬翼片中的2612颗修复牙齿，并使用带有Swin Transformer主干的Mask R-CNN架构进行训练。两阶段训练对龋齿检测准确性和严重程度评估进行了微调。修复体周围龋齿的注释由两名评估人员完成，并由另外两名专家进行检查。考虑两个阈值计算检测继发龋牙齿的综合准确性指标（平均值±标准差 - SD）：检测所有病变和牙本质病变。使用Pearson相关系数和布兰德-奥特曼图确定算法获得的病变严重程度评分与注释者共识之间的相关性。
我们改进后的算法在检测所有病变（0.966±0.025）和牙本质病变（0.964±0.019）方面显示出高特异性。敏感性值较低：所有病变为0.737±0.079，牙本质病变为0.808±0.083。所有病变的ROC曲线下面积（SD）为0.940（0.025），牙本质病变为0.946（0.023）。严重程度评分的相关系数为0.802。
我们开发了一种改进算法，以支持临床医生检测和分期咬翼片中的继发龋，纳入了一种创新的注释方法，将病变严重程度视为连续结果。
