School/Hospital of Stomatology, Zhejiang Chinese Medical University, Hangzhou, Zhejiang, China.
College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, Zhejiang, China.
BMC Oral Health. 2023 Jun 3;23(1):358. doi: 10.1186/s12903-023-03027-6.
Artificial intelligence (AI) has been introduced to interpret the panoramic radiographs (PRs). The aim of this study was to develop an AI framework to diagnose multiple dental diseases on PRs, and to initially evaluate its performance.
The AI framework was developed based on 2 deep convolutional neural networks (CNNs), BDU-Net and nnU-Net. 1996 PRs were used for training. Diagnostic evaluation was performed on a separate evaluation dataset including 282 PRs. Sensitivity, specificity, Youden's index, the area under the curve (AUC), and diagnostic time were calculated. Dentists with 3 different levels of seniority (H: high, M: medium, L: low) diagnosed the same evaluation dataset independently. Mann-Whitney U test and Delong test were conducted for statistical analysis (ɑ=0.05).
Sensitivity, specificity, and Youden's index of the framework for diagnosing 5 diseases were 0.964, 0.996, 0.960 (impacted teeth), 0.953, 0.998, 0.951 (full crowns), 0.871, 0.999, 0.870 (residual roots), 0.885, 0.994, 0.879 (missing teeth), and 0.554, 0.990, 0.544 (caries), respectively. AUC of the framework for the diseases were 0.980 (95%CI: 0.976-0.983, impacted teeth), 0.975 (95%CI: 0.972-0.978, full crowns), and 0.935 (95%CI: 0.929-0.940, residual roots), 0.939 (95%CI: 0.934-0.944, missing teeth), and 0.772 (95%CI: 0.764-0.781, caries), respectively. AUC of the AI framework was comparable to that of all dentists in diagnosing residual roots (p > 0.05), and its AUC values were similar to (p > 0.05) or better than (p < 0.05) that of M-level dentists for diagnosing 5 diseases. But AUC of the framework was statistically lower than some of H-level dentists for diagnosing impacted teeth, missing teeth, and caries (p < 0.05). The mean diagnostic time of the framework was significantly shorter than that of all dentists (p < 0.001).
The AI framework based on BDU-Net and nnU-Net demonstrated high specificity on diagnosing impacted teeth, full crowns, missing teeth, residual roots, and caries with high efficiency. The clinical feasibility of AI framework was preliminary verified since its performance was similar to or even better than the dentists with 3-10 years of experience. However, the AI framework for caries diagnosis should be improved.
人工智能（AI）已被引入用于解读全景 X 光片（PRs）。本研究旨在开发一种用于诊断 PR 上多种牙科疾病的 AI 框架，并初步评估其性能。
AI 框架是基于 2 个深度卷积神经网络（CNNs），BDU-Net 和 nnU-Net 开发的。使用了 1996 张 PR 进行训练。在包括 282 张 PR 的单独评估数据集上进行诊断评估。计算了敏感性、特异性、约登指数、曲线下面积（AUC）和诊断时间。3 位不同级别（H：高，M：中，L：低）的牙医独立诊断相同的评估数据集。采用曼-惠特尼 U 检验和德隆检验进行统计分析（α=0.05）。
该框架诊断 5 种疾病的敏感性、特异性和约登指数分别为 0.964、0.996、0.960（受影响的牙齿）、0.953、0.998、0.951（全冠）、0.871、0.999、0.870（残根）、0.885、0.994、0.879（缺牙）和 0.554、0.990、0.544（龋齿）。该框架诊断这些疾病的 AUC 分别为 0.980（95%CI：0.976-0.983，受影响的牙齿）、0.975（95%CI：0.972-0.978，全冠）和 0.935（95%CI：0.929-0.940，残根）、0.939（95%CI：0.934-0.944，缺牙）和 0.772（95%CI：0.764-0.781，龋齿）。该 AI 框架的 AUC 与所有牙医诊断残根的 AUC 相当（p>0.05），并且其 AUC 值与（p>0.05）或优于（p<0.05）中等级别牙医诊断 5 种疾病的 AUC 值。但是，对于诊断受影响的牙齿、缺牙和龋齿，该框架的 AUC 统计上低于一些 H 级别的牙医（p<0.05）。该框架的平均诊断时间明显短于所有牙医（p<0.001）。
基于 BDU-Net 和 nnU-Net 的 AI 框架在高效诊断受影响的牙齿、全冠、缺牙、残根和龋齿方面表现出高特异性。由于其性能与具有 3-10 年经验的牙医相似甚至更好，因此初步验证了 AI 框架的临床可行性。然而，龋齿诊断的 AI 框架仍需改进。
