School of Mechanical Engineering and Automation, Fuzhou University, Fuzhou, China.
Fujian Engineering Research Center of Joint Intelligent Medical Engineering, Fuzhou, China.
Int J Med Robot. 2023 Aug;19(4):e2523. doi: 10.1002/rcs.2523. Epub 2023 May 27.
BACKGROUND: The existing augmented reality (AR) dental implant surgery navigation system usually uses markers to complete image guidance. However, markers often affect dentists' operations and make patients uncomfortable. METHODS: To solve the problems caused by markers, this paper proposes an effective marker-less image guidance method. After initialisation is completed by contour matching, the corresponding relationship is obtained by matching the feature points between the current frame and the preloaded initial frame. The camera pose is estimated by solving the Perspective-n-Point problem. RESULTS: The registration error of AR images is 0.731 ± 0.144 mm. The planting errors are 1.174 ± 0.241 mm at the neck, 1.433 ± 0.389 mm at the apex and 5.566 ± 2.102° for the angle. The maximum error and standard deviation meet the clinical requirements. CONCLUSIONS: We demonstrate that the proposed method can accurately guide dentists to perform dental implant surgery.
背景:现有的增强现实(AR)牙科种植手术导航系统通常使用标记物来完成图像引导。然而,标记物通常会影响牙医的操作并使患者感到不适。
方法:为了解决标记物带来的问题,本文提出了一种有效的无标记图像引导方法。通过轮廓匹配完成初始化后,通过匹配当前帧和预加载初始帧之间的特征点来获得对应关系。通过求解 Perspective-n-Point 问题来估计相机姿态。
结果:AR 图像的配准误差为 0.731±0.144mm。颈部种植误差为 1.174±0.241mm,根尖种植误差为 1.433±0.389mm,角度误差为 5.566±2.102°。最大误差和标准差满足临床要求。
结论:我们证明了所提出的方法可以准确地指导牙医进行牙科种植手术。
Int J Oral Maxillofac Implants. 2018
Int J Med Robot. 2022-2
Int J Comput Assist Radiol Surg. 2019-3-1
Comput Biol Med. 2023-3
Int J Comput Assist Radiol Surg. 2020-6-5
Int J Comput Assist Radiol Surg. 2021-7