Towards Autonomous Eye Surgery by Combining Deep Imitation Learning with Optimal Control
This work addresses the challenge of precise and safe tool manipulation in eye surgery, offering potential to improve surgical outcomes by reducing errors compared to human capabilities, though it is incremental as it builds on existing imitation learning and control methods.
The paper tackles the problem of automating tool navigation in retinal microsurgery by predicting goal positions on the retina and generating optimal, safe trajectories, achieving errors of 0.089mm and 0.118mm in simulation and phantom experiments, which are below human tremor levels.
During retinal microsurgery, precise manipulation of the delicate retinal tissue is required for positive surgical outcome. However, accurate manipulation and navigation of surgical tools remain difficult due to a constrained workspace and the top-down view during the surgery, which limits the surgeon's ability to estimate depth. To alleviate such difficulty, we propose to automate the tool-navigation task by learning to predict relative goal position on the retinal surface from the current tool-tip position. Given an estimated target on the retina, we generate an optimal trajectory leading to the predicted goal while imposing safety-related physical constraints aimed to minimize tissue damage. As an extended task, we generate goal predictions to various points across the retina to localize eye geometry and further generate safe trajectories within the estimated confines. Through experiments in both simulation and with several eye phantoms, we demonstrate that our framework can permit navigation to various points on the retina within 0.089mm and 0.118mm in xy error which is less than the human's surgeon mean tremor at the tool-tip of 0.180mm. All safety constraints were fulfilled and the algorithm was robust to previously unseen eyes as well as unseen objects in the scene. Live video demonstration is available here: https://youtu.be/n5j5jCCelXk