Towards Autonomous Retinal Microsurgery Using RGB-D Images
Ji Woong Kim*, Shuwen Wei*, Peiyao Zhang*,
Peter L. Gehlbach, Jin U. Kang, Iulian Iordachita, Marin Kobilarov
Johns Hopkins University
Ji Woong Kim*, Shuwen Wei*, Peiyao Zhang*,
Peter L. Gehlbach, Jin U. Kang, Iulian Iordachita, Marin Kobilarov
Johns Hopkins University
Retinal surgery is a challenging procedure requiring precise manipulation of soft tissues, often at the scale of tens-of-micrometers. Its difficulty has motivated the development of robotic assistance platforms to enable precise motion, and more recently, novel sensors such as microscope integrated optical coherence tomography (OCT) for RGB-D view of the surgical workspace. The combination of these devices opens new possibilities for task autonomy such as for subretinal injection (SI), a procedure that involves precise needle insertion into the retina for targeted drug delivery. Motivated by this opportunity, we develop a framework for autonomous needle navigation in SI. We develop a system which enables the surgeon to specify waypoint goals in the microscope and OCT views, and the system autonomously navigates the needle into the desired subretinal space. Our system is enabled by a novel scheme that integrates OCT and microscope images in real-time, various CNNs that automatically segment the surgical tool and retinal tissue boundaries, and model predictive control that generates optimal trajectories while respecting kinematic constraints to ensure patient safety. We validate our system by demonstrating 30 successful SI trials on pig eyes. Preliminary comparisons to a human operator in robot-assisted mode highlight the enhanced safety of our system.Â