PDF(Pubmed)
Abstract：
OBJECTIVE: To examine the patterns of pretreatment facial soft tissue shape in orthodontic cases with premolar extraction using artificial intelligence (AI) and to investigate the corresponding changes.
METHODS: One hundred and fifty-two patients who underwent orthodontic treatment with premolar extraction were enrolled. Lateral cephalograms were obtained before and after the treatment. For each record, the outlines of the nose-lip-chin profile and corresponding 21 cephalometric variables were extracted. The AI method classified pretreatment records into three subject groups based on the feature variables extracted from the outline. Dentoskeletal and soft tissue facial form changes observed after treatment were compared statistically (P < 0.05) between the groups using ANOVA. Multivariate regression models were used for each group.
RESULTS: Group 1 (n = 59) was characterized by Class II high-angle retrognathic mandible with an incompetent lip, group 2 (n = 55) by Class I malocclusion with retruded and thin lips, and group 3 (n = 38) by Class I malocclusion with an everted superior lip before treatment. The ratios of anteroposterior soft tissue to hard tissue movements in Group 1 were 56% (r = 0.64) and 83% (r = 0.75) for the superior and inferior lips, respectively, whereas those in Group 2 were 49% (r = 0.78) and 91% (r = 0.80), and 40% (r = 0.54) and 79% (r = 0.70), respectively, in Group 3.
CONCLUSIONS: The modes of facial form changes differed depending on the pre-treatment profile patterns classified by the AI. This indicates that the determination of the pre-treatment profile pattern can help in the selection of soft tissue to hard tissue movement ratios, which helps estimate the post-treatment facial profile with a moderate to high correlation.
METHODS: One hundred and fifty-two patients who underwent orthodontic treatment with premolar extraction were enrolled. Lateral cephalograms were obtained before and after the treatment. For each record, the outlines of the nose-lip-chin profile and corresponding 21 cephalometric variables were extracted. The AI method classified pretreatment records into three subject groups based on the feature variables extracted from the outline. Dentoskeletal and soft tissue facial form changes observed after treatment were compared statistically (P < 0.05) between the groups using ANOVA. Multivariate regression models were used for each group.
RESULTS: Group 1 (n = 59) was characterized by Class II high-angle retrognathic mandible with an incompetent lip, group 2 (n = 55) by Class I malocclusion with retruded and thin lips, and group 3 (n = 38) by Class I malocclusion with an everted superior lip before treatment. The ratios of anteroposterior soft tissue to hard tissue movements in Group 1 were 56% (r = 0.64) and 83% (r = 0.75) for the superior and inferior lips, respectively, whereas those in Group 2 were 49% (r = 0.78) and 91% (r = 0.80), and 40% (r = 0.54) and 79% (r = 0.70), respectively, in Group 3.
CONCLUSIONS: The modes of facial form changes differed depending on the pre-treatment profile patterns classified by the AI. This indicates that the determination of the pre-treatment profile pattern can help in the selection of soft tissue to hard tissue movement ratios, which helps estimate the post-treatment facial profile with a moderate to high correlation.
摘要：
目的：使用人工智能（AI）检查正畸患者前磨牙拔除前的面部软组织形态，并研究其相应的变化。
方法：纳入了一百五十二例接受前磨牙拔除正畸治疗的患者。在治疗前后获得侧位头颅图。对于每个记录，提取了鼻-唇-下巴轮廓和相应的21个头颅测量变量。AI方法根据从大纲中提取的特征变量将预处理记录分为三个主题组。采用方差分析,观察两组治疗后牙骨及软组织面部形态变化,差异有统计学意义(P<0.05)。各组采用多因素回归模型。
结果：第1组（n=59）的特征是II类高角度下颌骨下颌骨，嘴唇不称职，第2组（n=55）通过I类错牙合，嘴唇下垂和薄，和第3组（n=38），在治疗前使用上唇外翻的I类错牙合。第一组上唇和下唇前后软组织与硬组织运动的比率分别为56％（r=0.64）和83％（r=0.75），分别,而第二组分别为49%(r=0.78)和91%(r=0.80)，40%(r=0.54)和79%(r=0.70)，分别,在第3组。
结论：面部形态变化的模式取决于AI分类的治疗前轮廓模式。这表明治疗前轮廓图案的确定可以帮助选择软组织与硬组织的运动比，这有助于估计治疗后的面部轮廓具有中等到高度的相关性。
方法：纳入了一百五十二例接受前磨牙拔除正畸治疗的患者。在治疗前后获得侧位头颅图。对于每个记录，提取了鼻-唇-下巴轮廓和相应的21个头颅测量变量。AI方法根据从大纲中提取的特征变量将预处理记录分为三个主题组。采用方差分析,观察两组治疗后牙骨及软组织面部形态变化,差异有统计学意义(P<0.05)。各组采用多因素回归模型。
结果：第1组（n=59）的特征是II类高角度下颌骨下颌骨，嘴唇不称职，第2组（n=55）通过I类错牙合，嘴唇下垂和薄，和第3组（n=38），在治疗前使用上唇外翻的I类错牙合。第一组上唇和下唇前后软组织与硬组织运动的比率分别为56％（r=0.64）和83％（r=0.75），分别,而第二组分别为49%(r=0.78)和91%(r=0.80)，40%(r=0.54)和79%(r=0.70)，分别,在第3组。
结论：面部形态变化的模式取决于AI分类的治疗前轮廓模式。这表明治疗前轮廓图案的确定可以帮助选择软组织与硬组织的运动比，这有助于估计治疗后的面部轮廓具有中等到高度的相关性。
