[论文解读] Robotic Navigation Autonomy for Subretinal Injection via Intelligent Real-Time Virtual iOCT Volume Slicing

Shervin Dehghani, Michael Sommersperger+7 more|PubMed|Jan 17, 2023

Retinal and Macular Surgery参考文献 37被引用 5

一句话总结

本文提出了一种用于自主机器人视网膜下注射的端到端框架，通过实时处理术中光学相干断层扫描（iOCT）体积数据实现。通过引入智能虚拟B扫描——基于卷积神经网络（CNN）、与器械对齐的二维切片——该方法实现了快速的三维器械位姿估计与在线配准，在离体猪眼模型中实现了亚30 μm的靶向精度。

ABSTRACT

In the last decade, various robotic platforms have been introduced that could support delicate retinal surgeries. Concurrently, to provide semantic understanding of the surgical area, recent advances have enabled microscope-integrated intraoperative Optical Coherent Tomography (iOCT) with high-resolution 3D imaging at near video rate. The combination of robotics and semantic understanding enables task autonomy in robotic retinal surgery, such as for subretinal injection. This procedure requires precise needle insertion for best treatment outcomes. However, merging robotic systems with iOCT introduces new challenges. These include, but are not limited to high demands on data processing rates and dynamic registration of these systems during the procedure. In this work, we propose a framework for autonomous robotic navigation for subretinal injection, based on intelligent real-time processing of iOCT volumes. Our method consists of an instrument pose estimation method, an online registration between the robotic and the iOCT system, and trajectory planning tailored for navigation to an injection target. We also introduce <i>intelligent virtual B-scans</i>, a volume slicing approach for rapid instrument pose estimation, which is enabled by Convolutional Neural Networks (CNNs). Our experiments on ex-vivo porcine eyes demonstrate the precision and repeatability of the method. Finally, we discuss identified challenges in this work and suggest potential solutions to further the development of such systems.

研究动机与目标

• 通过术中光学相干断层扫描（iOCT）成像，实现用于视网膜下注射的实时、自主机器人导航。
• 解决机器人器械与iOCT体积之间高数据吞吐量和动态系统配准的挑战。
• 通过生成与器械对齐的虚拟B扫描，降低3D iOCT处理的复杂度，实现高效的位姿估计。
• 将外科医生参与控制与自动化轨迹规划及执行相结合。
• 在真实手术条件下，于离体猪眼模型中展示系统的精度与可重复性。

提出的方法

• 提出一种外科医生参与的流程，将机器人控制与iOCT体积采集及实时处理相结合。
• 引入“智能虚拟B扫描”——从3D iOCT体积中自动选取、与器械对齐的2D切片，以简化3D位姿估计。
• 采用卷积神经网络（CNN）实现实时处理虚拟B扫描中的器械与组织结构的2D分割。
• 通过fiducial标记与器械位姿反馈，实现机器人系统与iOCT体积之间的在线配准。
• 基于实时器械位姿与目标点选择执行轨迹规划，初始实验中仅采用平移运动。
• 执行过程中采用固定速度的机器人运动轨迹，未来可扩展为动态速度调节。

Figure 1: Overview of the proposed system, consisting of an iOCT Microscope (a), which is used for volume acquisition and data transmission to the computation unit (b). A following step enables the surgeon can choose a target point for applying an injection. All the necessary computations are applie

实验结果

研究问题

• RQ1 实时处理体积化iOCT数据是否能够实现准确且可重复的机器人导航用于视网膜下注射？
• RQ2 如何通过动态选取的虚拟B扫描的2D处理，高效近似实现3D器械位姿估计？
• RQ3 在智能虚拟B扫描与在线配准引导下，机器人系统的可实现靶向精度是多少？
• RQ4 组织形变如何影响导航性能？实时数据采集在维持精度方面起到什么作用？
• RQ5 iOCT与机器人系统的集成是否足够稳健且高效，可实现眼科手术的临床部署？

主要发现

• 系统在导航至视网膜下空间目标时，平均靶向误差为24±5 μm，表现出高精度。
• 在导航至视网膜内目标时，平均误差为32±4 μm，表明在更深层视网膜组织中精度略有下降。
• 各次试验的误差分布显示性能一致，绝大多数针尖落在目标点30 μm以内。
• 在空气中进行的实验误差低于离体组织中的实验，表明组织形变与器械-组织相互作用会影响精度。
• 智能虚拟B扫描显著降低了计算复杂度，即使在高iOCT数据速率下仍能实现实时处理。
• 该框架可适配弯曲器械，并可在未来工作中扩展支持RCM基旋转与动态速度控制。

Figure 2: The proposed workflow follows volume processing and visualization (a), planning (b) and execution (c) stages.