Ultrasound-Guided Robotic Navigation with Deep Reinforcement Learning
This addresses the problem of precise robotic guidance in medical procedures for clinicians, representing an incremental advance by applying existing RL techniques to a new domain.
The paper tackled robotic navigation using ultrasound images by introducing a reinforcement learning method, achieving an 82.91% success rate in navigating to the sacrum from various starting positions in simulated environments.
In this paper we introduce the first reinforcement learning (RL) based robotic navigation method which utilizes ultrasound (US) images as an input. Our approach combines state-of-the-art RL techniques, specifically deep Q-networks (DQN) with memory buffers and a binary classifier for deciding when to terminate the task. Our method is trained and evaluated on an in-house collected data-set of 34 volunteers and when compared to pure RL and supervised learning (SL) techniques, it performs substantially better, which highlights the suitability of RL navigation for US-guided procedures. When testing our proposed model, we obtained a 82.91% chance of navigating correctly to the sacrum from 165 different starting positions on 5 different unseen simulated environments.