Supervised Autonomous Bimanual Suction and Cauterization for Bleeding Control in Low Grade Splenic Trauma
Authors: Francis Fan, Mackenzie A Eagleson, Yvonne Zhang, Hongting Pan, Lujia Yang, Ethan Kilmer, Jiawei Ge, Nural Yilmaz, Avinash Dhimal, Ahmed Ghazi, Jeffrey Jopling, Laura Connolly, Axel Krieger
Organizations: Laboratory of Computational Sensing and Robotics (LCSR), Johns Hopkins University, Baltimore, MD 21218, USA · Department of Surgery, Johns Hopkins Medicine, Baltimore, MD 21287, USA · Brady Urological Institute, Johns Hopkins University, Baltimore, MD 21287, USA
Uncontrolled hemorrhage remains a leading cause of preventable trauma mortality. Timely intervention is not always available, making autonomous systems that can aid in bleeding control a promising alternative. Given the safety-critical nature of the task, supervised autonomy, in which the system executes the technical steps while a human retains oversight, represents a necessary intermediate step toward this goal. In this work, we present a supervised autonomous bimanual robotic framework for injury cauterization (eletrosurgical coagulation) in low-grade splenic trauma. The system integrates real-time bleeding segmentation, markerless tool keypoint tracking, and deep tool-tissue contact detection to coordinate two robotic arms for synchronized suction and cauterization. Evaluated on a novel, cannulated ex vivo splenic hemorrhage model, the system achieved an average bleeding surface cauterization coverage of 82.9% across seven distinct injuries. This work demonstrates the feasibility of using a supervised autonomous bimanual system to deliver targeted coagulation across an injury site.
Figures & tables
Fig. 1: Supervised autonomous bimanual suction and cauterization for bleeding control. Images progress in time from top to bottom. Top: Blood pooling from a simulated splenic injury. Middle: Autonomous suction clearing blood from the injury site. Bottom: Autonomous cauterization covering the injury surface to initiate bleeding control.
Fig. 2: System diagram: Left: Cannulated vessels in the ex vivo splenic hemorrhage model. Middle: Experimental setup including suction pump, robotic tools, and perfusion system. The splenic hemorrhage model is outlined in green; robotic instrument positions are highlighted in yellow and pink. Right, top: Close-up of the yellow-outlined tool, a custom-designed robotic suction tool fitted to ProGrasp forceps. Right, bottom: Close-up of the pink-outlined tool, a cautery hook instrument used for wound coagulation.
Fig. 3: Overview of the supervised autonomous bimanual suction and cauterization workflow. The bleeding segmentation model is run on a laparoscopic image to produce a bleeding segmentation mask, from which the injury location is derived. The positions of both robotic tools (suction and cautery) are extracted from the image using a markerless tool-tracking framework based on keypoint detection. This tracking information is used to crop the image to a smaller region of interest for input to the tool–tissue contact detection model. The robotic tools are moved to the injury location via visual servoing, lowered until contact is detected, and then used to execute an autonomous Cartesian trajectory along the wound length.
Fig. 4: Images of injuries before and after suction and cauterization. Top row: Injury before any intervention. Middle row: Injury after cauterization. Bottom row: Overlap between the injury mask and the cauterized surface area.
Injury
Grade
Depth
Length
Coverage
(mm)
(mm)
(%)
1
I
10
7.4
98.69
2
I
10
7.8
98.74
3
I
10
8.4
67.89
4
I
10
5.2
67.85
5
I
10
10.0
100
TABLE I: Results of supervised autonomous bimanual suction and cautery. Column 1 is the injury ID, corresponding to Figure 4 . Columns 2 - 4 represent the extend of the injury (grade, length). Column 5 is the percentage of bleeding surface area cauterized.
Objective: To demonstrate and evaluate THERMO, a thermal-velocity optimization algorithm for autonomous electrosurgery, in ex vivo porcine tissue using the UR10e-based ASTR system. Methods: Thermography for Electrosurgical Rate Modulation via Optimization (ThERMO), a closed-loop algorithm that uses real-time thermal imaging data to minimize thermal injury while ensuring accurate cut margins, was tested on ex vivo porcine tissue. Histological analysis was performed to detect thermal injury extent at a cellular level, and 3D photogrammetric measurement was used to verify margin accuracy. ThERMO's performance was compared against two previously used fixed velocity methods. Results: ThERMO outperformed both fixed velocity comparison methods without requiring data-driven training or iterative tuning, reducing thermal injury by up to 52%, improving cut accuracy by up to 59%, and maintaining task completion speed. Conclusions: Closed-loop thermal feedback via ThERMO improves autonomous robotic electrosurgery by simultaneously reducing thermal injury and improving margin accuracy, reinforcing its value over fixed velocity approaches for tumor resection applications. Significance: This work advances autonomous robotic tumor resection by demonstrating that real-time closed-loop thermal feedback control can substantially reduce collateral tissue damage and improve surgical margin accuracy.
Naveed D. Riaziat, Jiawei Ge, Ethan Kilmer +6
Laboratory for Computational Sensing and Robotics, Johns Hopkins University, Baltimore, Maryland · Department of Pathology, Johns Hopkins Hospital, Baltimore, Maryland
Autonomous soft-tissue cancer surgery has been limited to interventions on organ surfaces, because current systems cannot perceive and adapt to anatomy once it deforms or is cut. We introduce the first vision-guided autonomous system capable of performing complete tumor resections for partial nephrectomy. Our system integrates conditional occupancy networks, trained entirely in a physics-based simulation, that infer full 3-D anatomy (tumor, margin tissue, and kidney) from single-view partial point clouds. These occupancy networks maintain intraoperative tracking even as tissue is cut and deformed, enabling adaptive planning and execution. The surgical platform combines a depth camera for capturing surface point clouds, dual robotic arms for electrosurgical cutting and vacuum-based tissue manipulation, and an autonomous control strategy for tumor resection. In patient-derived hydrogel phantoms under an open partial nephrectomy setting, the robot performed eight consecutive autonomous tumor resections comprising 77 electrosurgical cuts, with all cuts achieving negative surgical margins and 1.61 ± 0.48 mm mean absolute margin error. This work demonstrates, for the first time, a foundation for supervised autonomous closed-loop, imaging-driven, margin-negative tumor removal in phantoms.
Ethan Kilmer, Pit Henrich, Jiawei Ge +13
Laboratory of Computational Sensing and Robotics (LCSR), Johns Hopkins University, Baltimore, MD 21218, USA · Department Artificial Intelligence in Biomedical Engineering (AIBE), Friedrich-Alexander University Erlangen-Nürnberg (FAU), 91052 Erlangen, Germany · Brady Urological Institute, Johns Hopkins University, Baltimore, MD 21287, USA +1
Augmented dexterity has the potential to reduce the fatigue experienced by surgeons during repetitive surgical tasks. In this paper, we propose the first AGentic RObotics framework for SUrgical VIscoelastic DEbridement (AGRO-SUVIDE), the repeated removal of small fragments attached to a viscoelastic substrate. Leveraging the self-improving and coding capability of agents, AGRO-SUVIDE adopts a modular framework. Specifically, the demonstration analysis module automatically identifies recurring skills from a single expert demonstration, using both visual and kinematic information. The construction module then builds each skill, either as a procedural model-based skill the agent codes against a scaffolded library or as a model-free policy-based skill. At runtime, the monitoring module composes the skills into a loop-style graph sized to the number of fragments it observes, then verifies pre- and post-conditions of each skill to decide whether to advance or retry. We evaluate AGRO-SUVIDE through 340 physical trials on the da Vinci Research Kit (dVRK). AGRO-SUVIDE achieves an average single-fragment removal success rate of 85%, completing consecutive three-fragment removal at 60% and at 95% with one human intervention. It further generalizes to unseen five-fragment scenarios with an average success rate of 80% for single-fragment removal. Project page: https://surgical-robotics.github.io/AGRO-SUVIDE/
Shutong Jin, Ziyang Chen, Preethi Satish +4
Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, CA 94720, USA. · Department of Robotics, Perception and Learning, KTH Royal Institute of Technology, Stockholm, SE 10044, Sweden. · Intuitive Surgical, Sunnyvale, CA 94086, USA.