目标:尽管人工智能最近有所发展,通过OGS预测上颌骨和下颌骨的手术运动可能比通过正畸治疗预测牙齿运动更困难。使用正颌手术(OGS)患者的术前(T0)和术后(T1)侧位脑图(lat-ceph)和双嵌入模块图卷积神经网络(DEM-GCNN)模型评估手术运动的预测准确性。
方法:使用来自3个机构的599对作为培训,内部验证,内部测试集和其他6个机构的201对被用作外部测试集。DEM-GCNN模型(IEM,学习lat-ceph图像;LTEM,学习标志)被开发用于预测ANS和PNS在上颌骨以及下颌骨的B点和Md1冠的手术运动的数量和方向。比较了由OGS(地面实况)实际移动并由DEM-GCNN模型预测的T1地标坐标与预先存在的基于CNN的Model-C(学习lat-ceph图像)之间的距离。
结果:在内部和外部测试中,DEM-GCNN在所有地标中都没有表现出与地面真实的显著差异(ANS,PNS,B点,Md1crown,所有P>0.05)。当比较每个地标的累积成功检测率时,DEM-GCNN在内部和外部测试中均显示出比Model-C更高的值。在显示预测结果误差分布的小提琴图中,内部和外部测试表明,DEM-GCNN在PNS中具有显著的性能改进,ANS,B点,Md1crown比Model-C.DEM-GCNN显示出明显低于Model-C的预测误差值(单颌手术,B点,Md1crown,所有P<0.005;双颌手术,PNS,ANS,所有P<0.05;B点,Md1crown,所有P<0.005)。
结论:我们开发了一个稳健的OGS规划模型,该模型具有最大化的泛化性,尽管来自9个机构的lat-cephs具有不同的质量。
OBJECTIVE: Despite recent development of AI, prediction of the surgical movement in the maxilla and mandible by OGS might be more difficult than that of tooth movement by orthodontic treatment. To evaluate the prediction accuracy of the surgical movement using pairs of pre-(T0) and post-surgical (T1) lateral cephalograms (lat-ceph) of orthognathic surgery (OGS) patients and dual embedding module-graph convolution neural network (DEM-GCNN) model.
METHODS: 599 pairs from 3 institutions were used as training, internal validation, and internal test sets and 201 pairs from other 6 institutions were used as external test set. DEM-GCNN model (IEM, learning the lat-ceph images; LTEM, learning the landmarks) was developed to predict the amount and direction of surgical movement of ANS and PNS in the maxilla and B-point and Md1crown in the mandible. The distance between T1 landmark coordinates actually moved by OGS (ground truth) and predicted by DEM-GCNN model and pre-existed CNN-based Model-C (learning the lat-ceph images) was compared.
RESULTS: In both internal and external tests, DEM-GCNN did not exhibit significant difference from ground truth in all landmarks (ANS, PNS, B-point, Md1crown, all P > 0.05). When the accumulated successful detection rate for each landmark was compared, DEM-GCNN showed higher values than Model-C in both the internal and external tests. In violin plots exhibiting the error distribution of the prediction results, both internal and external tests showed that DEM-GCNN had significant performance improvement in PNS, ANS, B-point, Md1crown than Model-C. DEM-GCNN showed significantly lower prediction error values than Model-C (one-jaw surgery, B-point, Md1crown, all P < 0.005; two-jaw surgery, PNS, ANS, all P < 0.05; B point, Md1crown, all P < 0.005).
CONCLUSIONS: We developed a robust OGS planning model with maximized generalizability despite diverse qualities of lat-cephs from 9 institutions.