Buyuk Cansu, Akkaya Nurullah, Arsan Belde, Unsal Gurkan, Aksoy Secil, Orhan Kaan
Department of Dentomaxillofacial Radiology, Faculty of Dentistry, Istanbul Okan University, 34947 Istanbul, Turkey.
Department of Computer Engineering, Faculty of Engineering, Near East University, 99138 Nicosia, Cyprus.
Diagnostics (Basel). 2022 Aug 20;12(8):2018. doi: 10.3390/diagnostics12082018.
The study aimed to generate a fused deep learning algorithm that detects and classifies the relationship between the mandibular third molar and mandibular canal on orthopantomographs. Radiographs ( = 1880) were randomly selected from the hospital archive. Two dentomaxillofacial radiologists annotated the data via MATLAB and classified them into four groups according to the overlap of the root of the mandibular third molar and mandibular canal. Each radiograph was segmented using a U-Net-like architecture. The segmented images were classified by AlexNet. Accuracy, the weighted intersection over union score, the dice coefficient, specificity, sensitivity, and area under curve metrics were used to quantify the performance of the models. Also, three dental practitioners were asked to classify the same test data, their success rate was assessed using the Intraclass Correlation Coefficient. The segmentation network achieved a global accuracy of 0.99 and a weighted intersection over union score of 0.98, average dice score overall images was 0.91. The classification network achieved an accuracy of 0.80, per class sensitivity of 0.74, 0.83, 0.86, 0.67, per class specificity of 0.92, 0.95, 0.88, 0.96 and AUC score of 0.85. The most successful dental practitioner achieved a success rate of 0.79. The fused segmentation and classification networks produced encouraging results. The final model achieved almost the same classification performance as dental practitioners. Better diagnostic accuracy of the combined artificial intelligence tools may help to improve the prediction of the risk factors, especially for recognizing such anatomical variations.
该研究旨在生成一种融合深度学习算法，用于在全景片上检测并分类下颌第三磨牙与下颌管之间的关系。从医院存档中随机选取了1880张X光片。两名口腔颌面放射科医生通过MATLAB对数据进行标注，并根据下颌第三磨牙牙根与下颌管的重叠情况将其分为四组。每张X光片都使用类似U-Net的架构进行分割。分割后的图像由AlexNet进行分类。使用准确率、加权交并比分数、骰子系数、特异性、敏感性和曲线下面积指标来量化模型的性能。此外，还邀请了三名牙科医生对相同的测试数据进行分类，使用组内相关系数评估他们的成功率。分割网络的全局准确率达到0.99，加权交并比分数为0.98，所有图像的平均骰子分数为0.91。分类网络的准确率为0.80，每类敏感性分别为0.74、0.83、0.86、0.67，每类特异性分别为0.92、0.95、0.88、0.96，曲线下面积分数为0.85。最成功的牙科医生的成功率为0.79。融合的分割和分类网络产生了令人鼓舞的结果。最终模型的分类性能与牙科医生几乎相同。人工智能工具组合更好的诊断准确性可能有助于改善对风险因素的预测，特别是用于识别此类解剖变异。
