A Recurrent Neural Network Approach to Roll Estimation for Needle Steering

TL;DR

This paper introduces an LSTM-based neural network method for real-time needle tip orientation estimation, improving accuracy over traditional model-based observers in steerable needle applications.

Contribution

It presents a novel, model-free, learned approach using LSTM networks for online needle orientation estimation, enhancing steering precision in medical procedures.

Findings

LSTM-based method outperforms Extended Kalman Filter in targeting accuracy.

Successfully integrated into a sliding-mode controller for needle steering.

Validated in gelatin and ex vivo ovine brain tissue.

Abstract

Steerable needles are a promising technology for delivering targeted therapies in the body in a minimally-invasive fashion, as they can curve around anatomical obstacles and hone in on anatomical targets. In order to accurately steer them, controllers must have full knowledge of the needle tip's orientation. However, current sensors either do not provide full orientation information or interfere with the needle's ability to deliver therapy. Further, torsional dynamics can vary and depend on many parameters making steerable needles difficult to accurately model, limiting the effectiveness of traditional observer methods. To overcome these limitations, we propose a model-free, learned-method that leverages LSTM neural networks to estimate the needle tip's orientation online. We validate our method by integrating it into a sliding-mode controller and steering the needle to targets in gelatin and ex vivo ovine brain tissue. We compare our method's performance against an Extended Kalman Filter, a model-based observer, achieving significantly lower targeting errors.