Scene graph driven haptic feedback improves precision in robotic eye surgery
Scene Graph-Driven Haptic Feedback for Safety Enhancement in Robotic Ophthalmic Surgery via Physically Simulated iOCT
RoboticsComputer Vision and Pattern Recognition
Summary
Robotic eye surgery is very precise but makes it hard for surgeons to feel what they are doing because they lose the sense of touch. The authors created a system that uses a special way to understand the surgical scene, called a scene graph, by analyzing simulated images from an eye scanner. This system then gives surgeons gentle vibrating feedback so they can better control the needle during surgery. In tests, this feedback helped surgeons align their tools more accurately and use safer movements without taking longer.
What this means in practice
- •For robotic surgery teams: Incorporate scene graph-based haptic feedback to improve precision and safety during delicate eye surgeries.
- •For medical device developers: Design surgical robots with real-time scene graph analysis from imaging to provide context-aware tactile feedback.
Authors
Danial Arbabi, Korab Hoxha, Angelo Henriques, Mirza Imamovic, M. Ali Nasseri
Abstract
Robotic ophthalmic surgery offers high precision but introduces a "sensory gap" by decoupling the surgeon from their instrument, resulting in a loss of tactile feedback. This paper presents a novel haptic feedback system for subretinal injection tasks leveraging Scene Graphs (SG). The system bridges the sensory gap by analyzing a physically simulated intraoperative Optical Coherence Tomography (iOCT) feed to construct a real-time surgical SG. The SG serves as a semantic abstraction layer for the surgical scene, which is then utilized by a deterministic, rule-based engine to generate state-dependent haptic feedback on a robotic input device. The system was evaluated in a user study (N=16) using an anthropomorphic head phantom and a custom-built surgical robot. Results demonstrate that the SG-driven haptic feedback improved surgical precision, reducing needle alignment error by 14% (p = 0.044) and improving System Usability Scale (SUS) scores by 8% (p = 0.015), while maintaining comparable task completion times. A needle trajectory analysis revealed the emergence of a safer "Align-then-Approach" strategy, in which our haptic negative reinforcement prompted users to fine-tune the tool's trajectory before approaching the retinal target. This work suggests that SGs can effectively serve as the direct computational foundation for real-time, safety-enhancing context-aware haptic feedback in robotic microsurgery.