Context-Aware Depth and Pose Estimation for Bronchoscopic Navigation

作     者：Shen, Mali Gu, Yun Liu, Ning Yang, Guang-Zhong 

作者机构：Imperial Coll London Hamlyn Ctr Robot Surg London SW7 2AZ England 

出 版 物：《IEEE ROBOTICS AND AUTOMATION LETTERS》 (IEEE Robot. Autom.)

年 卷 期：2019年第4卷第2期

页      面：732-739页

核心收录：

学科分类：0808[工学-电气工程] 08[工学] 0811[工学-控制科学与工程] 

基　　金：Engineering and Physical Sciences Research Council (EPSRC), U.K. [EP/N019318/1] Chinese Scholarship Council (CSC) EPSRC [EP/J021199/1, EP/N019318/1, EP/P012779/1] Funding Source: UKRI 

主　　题：Visual learning visual-based navigation computer vision for medical robotics deep learning in robotics and automation 

摘      要：Endobronchial intervention is increasingly used as a minimally invasive means of lung intervention. Vision-based localization approaches are often sensitive to image artifacts in bronchoscopic videos. In this letter, a robust navigation system based on a context-aware depth recovery approach for monocular video images is presented. To handle the artifacts, a conditional generative adversarial learning framework is proposed for reliable depth recovery. The accuracy of depth estimation and camera localization is validated on an in vivo dataset. Both quantitative and qualitative results demonstrate that the depth recovered with the proposed method preserves better structural information of airway lumens in the presence of image artifacts, and the improved camera localization accuracy demonstrates its clinical potential for bronchoscopic navigation.