Autonomous Robotic Suction to Clear the Surgical Field for Hemostasis using Image-based Blood Flow Detection

Autonomous robotic surgery has seen significant progression over the last\ndecade with the aims of reducing surgeon fatigue, improving procedural\nconsistency, and perhaps one day take over surgery itself. However, automation\nhas not been applied to the critical surgical task of controlling tissue and\nblood vessel bleeding--known as hemostasis. The task of hemostasis covers a\nspectrum of bleeding sources and a range of blood velocity, trajectory, and\nvolume. In an extreme case, an un-controlled blood vessel fills the surgical\nfield with flowing blood. In this work, we present the first, automated\nsolution for hemostasis through development of a novel probabilistic blood flow\ndetection algorithm and a trajectory generation technique that guides\nautonomous suction tools towards pooling blood. The blood flow detection\nalgorithm is tested in both simulated scenes and in a real-life trauma scenario\ninvolving a hemorrhage that occurred during thyroidectomy. The complete\nsolution is tested in a physical lab setting with the da Vinci Research Kit\n(dVRK) and a simulated surgical cavity for blood to flow through. The results\nshow that our automated solution has accurate detection, a fast reaction time,\nand effective removal of the flowing blood. Therefore, the proposed methods are\npowerful tools to clearing the surgical field which can be followed by either a\nsurgeon or future robotic automation developments to close the vessel rupture.\n