当前位置: X-MOL 学术Int. J. Intell. Robot. Appl. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Endoscope navigation with SLAM-based registration to computed tomography for transoral surgery
International Journal of Intelligent Robotics and Applications Pub Date : 2020-04-10 , DOI: 10.1007/s41315-020-00127-2
Liang Qiu , Hongliang Ren

Minimally invasive transoral surgery (TROS) aims to reduce the trauma and complications, where transoral examination with an endoscope is a vital step. Close to the critical head-neck-brain anatomical structures, the transoral procedures can be much complicated and pose significant challenges to accurate navigation requirements. Therefore, it is laborious for navigating endoscopic instruments due to the sophisticated anatomy. In this paper, we propose to use visual Simultaneous Localization and Mapping (SLAM) for endoscope navigation in an oral cavity. We create an intra-operative 3D point cloud registered to pre-operative computed tomography (CT) with the aid of semi-dense contour to enhance visualization. Moreover, we have validated our method in the phantom experiment. The corresponding navigation and registration accuracy are presented to validate the proposed approach.

中文翻译:

内窥镜导航与基于SLAM的配准在断层外科手术中的X线断层扫描

微创经口手术(TROS)旨在减少创伤和并发症,而在内窥镜经口检查是至关重要的一步。靠近关键的头颈脑解剖结构,经口手术可能非常复杂,并且对精确的导航要求提出了重大挑战。因此,由于复杂的解剖结构,在导航内窥镜器械方面是费力的。在本文中,我们建议使用视觉同时定位和映射(SLAM)进行口腔内窥镜导航。我们创建了术中3D点云,并借助半密集轮廓增强了术前计算机断层扫描(CT)的可视性。此外,我们已经在幻像实验中验证了我们的方法。
更新日期:2020-04-10
down
wechat
bug