Fried Inbar, Hoelscher Janine, Akulian Jason A, Pizer Stephen, Alterovitz Ron
I. Fried, J. Hoelscher, S. Pizer, and R. Alterovitz are with the Department of Computer Science, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA.
I. Fried is also with the Medical Scientist Training Program, University of North Carolina School of Medicine, Chapel Hill, NC, 27599, USA.
Rep U S. 2023 Oct;2023:6593-6600. doi: 10.1109/iros55552.2023.10342115. Epub 2023 Dec 13.
Bronchoscopy is currently the least invasive method for definitively diagnosing lung cancer, which kills more people in the United States than any other form of cancer. Successfully diagnosing suspicious lung nodules requires accurate localization of the bronchoscope relative to a planned biopsy site in the airways. This task is challenging because the lung deforms intraoperatively due to respiratory motion, the airways lack photometric features, and the anatomy's appearance is repetitive. In this paper, we introduce a real-time camera-based method for accurately localizing a bronchoscope with respect to a planned needle insertion pose. Our approach uses deep learning and accounts for deformations and overcomes limitations of global pose estimation by estimating pose relative to anatomical landmarks. Specifically, our learned model considers airway bifurcations along the airway wall as landmarks because they are distinct geometric features that do not vary significantly with respiratory motion. We evaluate our method in a simulated dataset of lungs undergoing respiratory motion. The results show that our method generalizes across patients and localizes the bronchoscope with accuracy sufficient to access the smallest clinically-relevant nodules across all levels of respiratory deformation, even in challenging distal airways. Our method could enable physicians to perform more accurate biopsies and serve as a key building block toward accurate autonomous robotic bronchoscopy.
支气管镜检查是目前确诊肺癌的侵入性最小的方法，在美国，肺癌致死人数超过其他任何癌症。成功诊断可疑肺结节需要将支气管镜相对于气道中计划活检部位进行精确的定位。这项任务具有挑战性，因为术中肺部会因呼吸运动而变形，气道缺乏光度特征，且解剖结构外观具有重复性。在本文中，我们介绍了一种基于摄像头的实时方法，用于相对于计划的针插入姿势精确地定位支气管镜。我们的方法使用深度学习，通过估计相对于解剖标志的姿势来考虑变形并克服全局姿势估计的局限性。具体而言，我们的学习模型将气道壁上的气道分支视为标志，因为它们是独特的几何特征，不会随呼吸运动而显著变化。我们在模拟的肺部呼吸运动数据集中评估了我们的方法。结果表明，我们的方法可推广到不同患者，并能精确地定位支气管镜，足以在所有呼吸变形水平下触及临床上最小的相关结节，即使在具有挑战性的远端气道中也是如此。我们的方法可以使医生进行更精确的活检，并成为实现精确自主机器人支气管镜检查的关键组成部分。
