In this letter, we describe a novel framework for planning and executing semi-autonomous tissue retraction in minimally invasive robotic surgery. The approach is aimed at removing tissue flaps or connective tissue from the surgical area autonomously, thus exposing the underlying anatomical structures. First, a deep neural network is used to analyse the endoscopic image and detect candidate tissue flaps obstructing the surgical field. A procedural algorithm for planning and executing the retraction gesture is then developed from extended discussions with clinicians. Experimental validation, carried out on a DaVinci Research Kit, shows an average 25% increase of the visible background after retraction. Another significant contribution of this letter is a dataset containing 1,080 labelled surgical stereo images and the associated depth maps, representing tissue flaps in different scenarios. The work described in this letter is a fundamental step towards the autonomous execution of tissue retraction, and the first example of simultaneous use of deep learning and procedural algorithms. The same framework could be applied to a wide range of autonomous tasks, such as debridement and placement of laparoscopic clips.

中文翻译：

---

机器人辅助微创手术中的自主组织回缩——一项可行性研究

在这封信中，我们描述了一个新的框架，用于在微创机器人手术中规划和执行半自主组织牵开。该方法旨在自主地从手术区域去除组织瓣或结缔组织，从而暴露下面的解剖结构。首先，深度神经网络用于分析内窥镜图像并检测阻碍手术野的候选组织瓣。然后，根据与临床医生的深入讨论，开发出用于规划和执行缩回手势的程序算法。在 DaVinci Research Kit 上进行的实验验证表明，缩回后可见背景平均增加 25%。这封信的另一个重要贡献是一个包含 1,080 个标记手术立体图像和相关深度图的数据集，代表不同情况下的组织瓣。这封信中描述的工作是朝着自主执行组织收缩迈出的重要一步，也是同时使用深度学习和程序算法的第一个例子。相同的框架可以应用于广泛的自主任务，例如清创和放置腹腔镜夹。