Zhang Yuchen, Xu Yifei, Zhao Jiamin, Du Tianjing, Li Dongning, Zhao Xinyan, Wang Jinxiu, Li Chen, Tu Junbo, Qi Kun
Key Laboratory of Shaanxi Province for Craniofacial Precision Medicine Research, College of Stomatology, Xi'an Jiaotong University, 98 XiWu Road, Xi'an 710004, China.
Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering, School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an 710049, China.
Diagnostics (Basel). 2023 May 25;13(11):1853. doi: 10.3390/diagnostics13111853.
Three-dimensional facial soft tissue landmark prediction is an important tool in dentistry, for which several methods have been developed in recent years, including a deep learning algorithm which relies on converting 3D models into 2D maps, which results in the loss of information and precision.
This study proposes a neural network architecture capable of directly predicting landmarks from a 3D facial soft tissue model. Firstly, the range of each organ is obtained by an object detection network. Secondly, the prediction networks obtain landmarks from the 3D models of different organs.
The mean error of this method in local experiments is 2.62±2.39, which is lower than that in other machine learning algorithms or geometric information algorithms. Additionally, over 72% of the mean error of test data falls within ±2.5 mm, and 100% falls within 3 mm. Moreover, this method can predict 32 landmarks, which is higher than any other machine learning-based algorithm.
According to the results, the proposed method can precisely predict a large number of 3D facial soft tissue landmarks, which gives the feasibility of directly using 3D models for prediction.
三维面部软组织标志点预测是牙科领域的一项重要工具，近年来已开发出多种方法，其中包括一种深度学习算法，该算法依赖于将三维模型转换为二维地图，这会导致信息和精度的损失。
本研究提出了一种能够直接从三维面部软组织模型预测标志点的神经网络架构。首先，通过目标检测网络获取每个器官的范围。其次，预测网络从不同器官的三维模型中获取标志点。
该方法在局部实验中的平均误差为2.62±2.39，低于其他机器学习算法或几何信息算法。此外，测试数据平均误差的72%以上落在±2.5毫米范围内，100%落在3毫米范围内。而且，该方法可以预测32个标志点，高于任何其他基于机器学习的算法。
根据结果，所提出的方法可以精确预测大量三维面部软组织标志点，这为直接使用三维模型进行预测提供了可行性。
