基于实时的超声成像反馈的管状结构自主式机器人筛选
Autonomous Robotic Screening of Tubular Structures based only on Real-Time Ultrasound Imaging Feedback
摘要:
超声(US)成像被广泛用于周围血管疾病(PVD)的诊断和分期,主要是由于其高可用性和不发射辐射的事实。然而,操作员之间的高变异性和缺乏重复性的US图像采集阻碍了广泛的筛查计划的实施。为了应对这一挑战,我们提出了一种端到端的工作流程,用于仅使用实时的【形】US成像反馈对管状结构进行自动机器人US筛查。我们首先训练一个U-Net,用于从横截面US图像中实时的【形】血管结构分割。然后,我们将检测到的血管结构表示为3D点云,并通过求解约束非线性优化问题来估计目标管状结构的纵轴及其平均半径。迭代先前的过程,US探头被自动对准到垂直于目标管状组织的取向,并基于空间校准在线调整以使跟踪的组织居中。在体模上和在体志愿者肱动脉上对实时的【形】分割结果进行了评价。此外,整个过程在仿真和物理模型中进行了验证。仿真中的平均绝对半径误差和定向误差($\pm$ SD)分别为$1.16\pm0.1~mm$和$2.7\pm3.3^{\circ}$。在凝胶体模上,这些误差为$1.95\pm2.02~mm$和$3.3\pm2.4^{\circ}$。这表明,该方法能够自动筛选具有最佳探头方向(即,垂直于血管)的管状组织,同时能够实时的【形】准确估计平均半径。
英文摘要:
Ultrasound (US) imaging is widely employed for diagnosis and staging of peripheral vascular diseases (PVD), mainly due to its high availability and the fact it does not emit radiation. However, high inter-operator variability and a lack of repeatability of US image acquisition hinder the implementation of extensive screening programs. To address this challenge, we propose an end-to-end workflow for automatic robotic US screening of tubular structures using only the real-time US imaging feedback. We first train a U-Net for real-time segmentation of the vascular structure from cross-sectional US images. Then, we represent the detected vascular structure as a 3D point cloud and use it to estimate the longitudinal axis of the target tubular structure and its mean radius by solving a constrained non-linear optimization problem. Iterating the previous processes, the US probe is automatically aligned to the orientation normal to the target tubular tissue and adjusted online to center the tracked tissue based on the spatial calibration. The real-time segmentation result is evaluated both on a phantom and in-vivo on brachial arteries of volunteers. In addition, the whole process is validated both in simulation and physical phantoms. The mean absolute radius error and orientation error ($\pm$ SD) in the simulation are $1.16\pm0.1~mm$ and $2.7\pm3.3^{\circ}$, respectively. On a gel phantom, these errors are $1.95\pm2.02~mm$ and $3.3\pm2.4^{\circ}$. This shows that the method is able to automatically screen tubular tissues with an optimal probe orientation (i.e. normal to the vessel) and at the same to accurately estimate the mean radius, both in real-time.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。