Abstract：
BACKGROUND: Quantitative evaluation of facial aesthetics is an important but also time-consuming procedure in orthognathic surgery, while existing 2D beauty-scoring models are mainly used for entertainment with less clinical impact.
METHODS: A deep-learning-based 3D evaluation model DeepBeauty3D was designed and trained using 133 patients\' CT images. The customised image preprocessing module extracted the skeleton, soft tissue, and personal physical information from raw DICOM data, and the predicting network module employed 3-input-2-output convolution neural networks (CNN) to receive the aforementioned data and output aesthetic scores automatically.
RESULTS: Experiment results showed that this model predicted the skeleton and soft tissue score with 0.231 ± 0.218 (4.62%) and 0.100 ± 0.344 (2.00%) accuracy in 11.203 ± 2.824 s from raw CT images.
CONCLUSIONS: This study provided an end-to-end solution using real clinical data based on 3D CNN to quantitatively evaluate facial aesthetics by considering three anatomical factors simultaneously, showing promising potential in reducing workload and bridging the surgeon-patient aesthetics perspective gap.
METHODS: A deep-learning-based 3D evaluation model DeepBeauty3D was designed and trained using 133 patients\' CT images. The customised image preprocessing module extracted the skeleton, soft tissue, and personal physical information from raw DICOM data, and the predicting network module employed 3-input-2-output convolution neural networks (CNN) to receive the aforementioned data and output aesthetic scores automatically.
RESULTS: Experiment results showed that this model predicted the skeleton and soft tissue score with 0.231 ± 0.218 (4.62%) and 0.100 ± 0.344 (2.00%) accuracy in 11.203 ± 2.824 s from raw CT images.
CONCLUSIONS: This study provided an end-to-end solution using real clinical data based on 3D CNN to quantitatively evaluate facial aesthetics by considering three anatomical factors simultaneously, showing promising potential in reducing workload and bridging the surgeon-patient aesthetics perspective gap.
摘要：
背景：在正颌手术中，面部美学的定量评估是一项重要但耗时的程序，而现有的2D美容评分模型主要用于娱乐，临床影响较小。
方法：设计了基于深度学习的3D评估模型DeepBeauty3D，并使用133名患者的CT图像进行了训练。定制的图像预处理模块提取骨架，软组织,和来自原始DICOM数据的个人身体信息，预测网络模块采用3输入2输出卷积神经网络（CNN）来接收上述数据并自动输出美学评分。
结果：实验结果表明，该模型在11.203±2.824s内预测骨骼和软组织评分的准确率为0.231±0.218（4.62%）和0.100±0.344（2.00%）。
结论：这项研究提供了一种端到端的解决方案，该解决方案使用基于3DCNN的真实临床数据，通过同时考虑三个解剖因素来定量评估面部美学，在减少工作量和弥合外科医生与患者的美学观点差距方面显示出有希望的潜力。
方法：设计了基于深度学习的3D评估模型DeepBeauty3D，并使用133名患者的CT图像进行了训练。定制的图像预处理模块提取骨架，软组织,和来自原始DICOM数据的个人身体信息，预测网络模块采用3输入2输出卷积神经网络（CNN）来接收上述数据并自动输出美学评分。
结果：实验结果表明，该模型在11.203±2.824s内预测骨骼和软组织评分的准确率为0.231±0.218（4.62%）和0.100±0.344（2.00%）。
结论：这项研究提供了一种端到端的解决方案，该解决方案使用基于3DCNN的真实临床数据，通过同时考虑三个解剖因素来定量评估面部美学，在减少工作量和弥合外科医生与患者的美学观点差距方面显示出有希望的潜力。
