Department of Oral and Cranio-Maxillofacial Surgery, Shanghai Ninth People's Hospital, College of Stomatology, Shanghai Jiao Tong University School of Medicine, Shanghai, 200011, China.
National Center for Stomatology & National Clinical Research Center for Oral Diseases, Shanghai, 200011, China.
BMC Oral Health. 2023 Mar 18;23(1):161. doi: 10.1186/s12903-023-02844-z.
Preoperative planning of orthognathic surgery is indispensable for achieving ideal surgical outcome regarding the occlusion and jaws' position. However, orthognathic surgery planning is sophisticated and highly experience-dependent, which requires comprehensive consideration of facial morphology and occlusal function. This study aimed to investigate a robust and automatic method based on deep learning to predict reposition vectors of jawbones in orthognathic surgery plan.
A regression neural network named VSP transformer was developed based on Transformer architecture. Firstly, 3D cephalometric analysis was employed to quantify skeletal-facial morphology as input features. Next, input features were weighted using pretrained results to minimize bias resulted from multicollinearity. Through encoder-decoder blocks, ten landmark-based reposition vectors of jawbones were predicted. Permutation importance (PI) method was used to calculate contributions of each feature to final prediction to reveal interpretability of the proposed model.
VSP transformer model was developed with 383 samples and clinically tested with 49 prospectively collected samples. Our proposed model outperformed other four classic regression models in prediction accuracy. Mean absolute errors (MAE) of prediction were 1.41 mm in validation set and 1.34 mm in clinical test set. The interpretability results of the model were highly consistent with clinical knowledge and experience.
The developed model can predict reposition vectors of orthognathic surgery plan with high accuracy and good clinically practical-effectiveness. Moreover, the model was proved reliable because of its good interpretability.
正颌手术的术前规划对于实现咬合和颌骨位置的理想手术效果至关重要。然而，正颌手术规划复杂且高度依赖经验，需要综合考虑面部形态和咬合功能。本研究旨在探索一种基于深度学习的稳健、自动的方法，以预测正颌手术计划中颌骨的复位向量。
基于 Transformer 架构开发了一种名为 VSP transformer 的回归神经网络。首先，使用 3D 头影测量分析来量化骨骼-面部形态作为输入特征。接下来，使用预先训练的结果对输入特征进行加权，以最小化多线性相关性导致的偏差。通过编码器-解码器块，预测了十个基于标志点的颌骨复位向量。使用置换重要性（PI）方法计算每个特征对最终预测的贡献，以揭示所提出模型的可解释性。
VSP transformer 模型是使用 383 个样本开发的，并在 49 个前瞻性收集的样本中进行了临床测试。与其他四个经典回归模型相比，我们提出的模型在预测精度方面表现更好。验证集的平均绝对误差（MAE）为 1.41mm，临床测试集的 MAE 为 1.34mm。模型的可解释性结果与临床知识和经验高度一致。
所开发的模型可以以高精度和良好的临床实用性预测正颌手术计划的复位向量。此外，由于其良好的可解释性，该模型被证明是可靠的。
