Learn about the flu shot, COVID-19 vaccine, and our masking policy »
New to MyHealth?
Manage Your Care From Anywhere.
Access your health information from any device with MyHealth. You can message your clinic, view lab results, schedule an appointment, and pay your bill.
ALREADY HAVE AN ACCESS CODE?
DON'T HAVE AN ACCESS CODE?
NEED MORE DETAILS?
MyHealth for Mobile
Get the iPhone MyHealth app »
Get the Android MyHealth app »
Abstract
Background. The revolutions in AI hold tremendous capacity to augment human achievements in surgery, but robust integration of deep learning algorithms with high-fidelity surgical simulation remains a challenge. We present a novel application of reinforcement learning (RL) for automating surgical maneuvers in a graphical simulation.Methods. In the Unity3D game engine, the Machine Learning-Agents package was integrated with the NVIDIA FleX particle simulator for developing autonomously behaving RL-trained scissors. Proximal Policy Optimization (PPO) was used to reward movements and desired behavior such as movement along desired trajectory and optimized cutting maneuvers along the deformable tissue-like object. Constant and proportional reward functions were tested, and TensorFlow analytics was used to informed hyperparameter tuning and evaluate performance.Results. RL-trained scissors reliably manipulated the rendered tissue that was simulated with soft-tissue properties. A desirable trajectory of the autonomously behaving scissors was achieved along 1 axis. Proportional rewards performed better compared to constant rewards. Cumulative reward and PPO metrics did not consistently improve across RL-trained scissors in the setting for movement across 2 axes (horizontal and depth).Conclusion. Game engines hold promising potential for the design and implementation of RL-based solutions to simulated surgical subtasks. Task completion was sufficiently achieved in one-dimensional movement in simulations with and without tissue-rendering. Further work is needed to optimize network architecture and parameter tuning for increasing complexity.
View details for DOI 10.1177/15533506221095298
View details for PubMedID 35503302