Revilla-León Marta, Fernández-Estevan Lucía, Barmak Abdul B, Kois John C, Alonso Pérez-Barquero Jorge
Affiliate Assistant Professor, Graduate Prosthodontics, Department of Restorative Dentistry, School of Dentistry, University of Washington, Seattle, Wash; Faculty and Director, Research and Digital Dentistry, Kois Center, Seattle, Wash; and Adjunct Professor, Department of Prosthodontics, School of Dental Medicine, Tufts University, Boston, Mass.
Professor, Department of Dental Medicine, Faculty of Medicine and Dentistry, University of Valencia, Valencia, Spain.
J Prosthet Dent. 2024 Apr 10. doi: 10.1016/j.prosdent.2024.03.007.
Maxillary and mandibular scans can be articulated in maximum intercuspal position (MIP) by using an artificial intelligence (AI) based program; however, the accuracy of the AI-based program locating the MIP relationship is unknown.
The purpose of the present clinical study was to assess the accuracy of the MIP relationship located by using 4 intraoral scanners (IOSs) and an AI-based program.
Conventional casts of a participant mounted on an articulator in MIP were digitized (T710). Four groups were created based on the IOS used to record a maxillary and mandibular scan of the participant: TRIOS4, iTero, i700, and PrimeScan. Each pair of nonarticulated scans were duplicated 20 times. Three subgroups were created: IOS, AI-articulated, and AI-IOS-corrected subgroups (n=10). In the IOS-subgroup, 10 duplicated scans were articulated in MIP by using a bilateral occlusal record. In the AI-articulated subgroup, the remaining 10 duplicated scans were articulated in MIP by using an AI-based program (BiteFinder). In the AI-IOS-corrected subgroup, the same AI-based program was used to correct the occlusal collisions of the articulated specimens obtained in the IOS-subgroup. A reverse engineering program (Geomagic Wrap) was used to calculate 36 interlandmark measurements on the digitized articulated casts (control) and each articulated specimen. Two-way ANOVA and pairwise multiple comparison Tukey tests were used to analyze trueness (α=.05). The Levene and pairwise multiple comparison Wilcoxon rank tests were used to analyze precision (α=.05).
Significant trueness discrepancies among the groups (P<.001) and subgroups (P<.001) were found, with a significant interaction group×subgroup (P<.001). The Levene test showed significant precision discrepancies among the groups (P<.001) and subgroups (P=.005). The TRIOS4 and iTero groups obtained better trueness and lower precision than the i700 and PrimeScan systems. Additionally, the AI-articulated subgroup showed worse trueness and precision than the IOS and AI-IOS-corrected subgroups. The AI-based program improved the MIP trueness of the scans articulated by using the iTero and PrimeScan systems but reduced the MIP trueness of the articulated scans obtained by using the TRIOS4 and i700.
The trueness and precision of the maxillomandibular relationship was impacted by the IOS system and program used to locate the MIP.
通过使用基于人工智能（AI）的程序，上颌和下颌扫描可以在最大牙尖交错位（MIP）进行咬合；然而，基于AI的程序定位MIP关系的准确性尚不清楚。
本临床研究的目的是评估使用4种口腔内扫描仪（IOS）和基于AI的程序定位的MIP关系的准确性。
将一名参与者在MIP位安装在咬合架上的传统模型进行数字化处理（T710）。根据用于记录参与者上颌和下颌扫描的IOS创建四组：TRIOS4、iTero、i700和PrimeScan。每对未咬合的扫描重复20次。创建三个亚组：IOS亚组、AI咬合亚组和AI-IOS校正亚组（n = 10）。在IOS亚组中，使用双侧咬合记录将10次重复扫描在MIP位进行咬合。在AI咬合亚组中，使用基于AI的程序（BiteFinder）将其余10次重复扫描在MIP位进行咬合。在AI-IOS校正亚组中，使用相同基于AI的程序校正IOS亚组中获得的咬合标本的咬合碰撞情况。使用逆向工程程序（Geomagic Wrap）在数字化的咬合模型（对照）和每个咬合标本上计算36个地标间测量值。使用双向方差分析和两两多重比较Tukey检验分析准确性（α = 0.05）。使用Levene检验和两两多重比较Wilcoxon秩和检验分析精密度（α = 0.05）。
发现各组（P <.001）和亚组（P <.001）之间存在显著的准确性差异，组×亚组存在显著交互作用（P <.001）。Levene检验显示各组（P <.001）和亚组（P = 0.005）之间存在显著的精密度差异。TRIOS4组和iTero组比i700组和PrimeScan系统获得了更好的准确性和更低的精密度。此外，AI咬合亚组比IOS亚组和AI-IOS校正亚组显示出更差的准确性和精密度。基于AI的程序提高了使用iTero和PrimeScan系统进行咬合扫描的MIP准确性，但降低了使用TRIOS4和i700获得的咬合扫描的MIP准确性。
用于定位MIP的IOS系统和程序对上颌下颌关系的准确性和精密度有影响。
