Han Mengqi, Du Shaoyi, Ge Yuyan, Zhang Dong, Chi Yuting, Long Hong, Yang Jing, Yang Yang, Xin Jingmin, Chen Teng, Zheng Nanning, Guo Yu-Cheng
Key Laboratory of Shaanxi Province for Craniofacial Precision Medicine Research, College of Stomatology, Xi'an Jiaotong University, 98 XiWu Road, Xi'an, 710004, Shaanxi, People's Republic of China.
Department of Orthodontics, College of Stomatology, Xi'an Jiaotong University, 98 XiWu Road, Xi'an, 710004, Shaanxi, People's Republic of China.
Int J Legal Med. 2022 May;136(3):821-831. doi: 10.1007/s00414-022-02796-z. Epub 2022 Feb 14.
Age estimation can aid in forensic medicine applications, diagnosis, and treatment planning for orthodontics and pediatrics. Existing dental age estimation methods rely heavily on specialized knowledge and are highly subjective, wasting time, and energy, which can be perfectly solved by machine learning techniques. As the key factor affecting the performance of machine learning models, there are usually two methods for feature extraction: human interference and autonomous extraction without human interference. However, previous studies have rarely applied these two methods for feature extraction in the same image analysis task. Herein, we present two types of convolutional neural networks (CNNs) for dental age estimation. One is an automated dental stage evaluation model (ADSE model) based on specified manually defined features, and the other is an automated end-to-end dental age estimation model (ADAE model), which autonomously extracts potential features for dental age estimation. Although the mean absolute error (MAE) of the ADSE model for stage classification is 0.17 stages, its accuracy in dental age estimation is unsatisfactory, with the MAE (1.63 years) being only 0.04 years lower than the manual dental age estimation method (MDAE model). However, the MAE of the ADAE model is 0.83 years, being reduced by half that of the MDAE model. The results show that fully automated feature extraction in a deep learning model without human interference performs better in dental age estimation, prominently increasing the accuracy and objectivity. This indicates that without human interference, machine learning may perform better in the application of medical imaging.
年龄估计有助于法医学应用、正畸学和儿科学的诊断及治疗规划。现有的牙龄估计方法严重依赖专业知识，主观性强，耗费时间和精力，而机器学习技术可完美解决这些问题。作为影响机器学习模型性能的关键因素，特征提取通常有两种方法：人工干预和无人为干预的自主提取。然而，以往研究很少在同一图像分析任务中应用这两种特征提取方法。在此，我们提出两种用于牙龄估计的卷积神经网络（CNN）。一种是基于特定手动定义特征的自动牙龄阶段评估模型（ADSE模型），另一种是自动端到端牙龄估计模型（ADAE模型），它能自主提取用于牙龄估计的潜在特征。尽管ADSE模型用于阶段分类的平均绝对误差（MAE）为0.17个阶段，但其牙龄估计的准确性并不理想，MAE（1.63岁）仅比手动牙龄估计方法（MDAE模型）低0.04岁。然而，ADAE模型的MAE为0.83岁，比MDAE模型降低了一半。结果表明，深度学习模型中无人为干预的全自动特征提取在牙龄估计中表现更好，显著提高了准确性和客观性。这表明在无人为干预的情况下，机器学习在医学成像应用中可能表现更佳。
