Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Modeling Electromagnetic Navigation Systems for Medical Applications using Random Forests and Artificial Neural Networks

Ruoxi Yu, Samuel L. Charreyron, Quentin Boehler, Cameron Weibel, Carmen C. Y. Poon, Bradley J. Nelson

TL;DR

Problem: accurately modeling magnetic fields in electromagnetic navigation systems (eMNS) is challenging due to nonlinear ferromagnetic saturation. Approach: apply random forest (RF) and artificial neural network (ANN) models to predict 3D magnetic fields from position and coil currents, compared against a linear multipole electromagnet method (LMEM) baseline. Findings: RF and ANN outperform LMEM across the workspace, with ANN achieving near-perfect component-wise fits and substantial field-magnitude RMSE reductions; ANN shows the largest gains, including >35 mT improvement in high-current regions (30–35 A). Implications: machine learning offers a practical path to more precise magnetic field maps, enabling improved surgical navigation with eMNS.

Abstract

Electromagnetic Navigation Systems (eMNS) can be used to control a variety of multiscale devices within the human body for remote surgery. Accurate modeling of the magnetic fields generated by the electromagnets of an eMNS is crucial for the precise control of these devices. Existing methods assume a linear behavior of these systems, leading to significant modeling errors within nonlinear regions exhibited at higher magnetic fields. In this paper, we use a random forest (RF) and an artificial neural network (ANN) to model the nonlinear behavior of the magnetic fields generated by an eMNS. Both machine learning methods outperformed the state-of-the-art linear multipole electromagnet method (LMEM). The RF and the ANN model reduced the root mean squared error of the LMEM when predicting the field magnitude by around 40% and 80%, respectively, over the entire current range of the eMNS. At high current regions, especially between 30 and 35 A, the field-magnitude RMSE improvement of the ANN model over the LMEM was over 35 mT. This study demonstrates the feasibility of using machine learning methods to model an eMNS for medical applications, and its ability to account for complex nonlinear behavior at high currents. The use of machine learning thus shows promise for improving surgical procedures that use magnetic navigation.

Modeling Electromagnetic Navigation Systems for Medical Applications using Random Forests and Artificial Neural Networks

TL;DR

Problem: accurately modeling magnetic fields in electromagnetic navigation systems (eMNS) is challenging due to nonlinear ferromagnetic saturation. Approach: apply random forest (RF) and artificial neural network (ANN) models to predict 3D magnetic fields from position and coil currents, compared against a linear multipole electromagnet method (LMEM) baseline. Findings: RF and ANN outperform LMEM across the workspace, with ANN achieving near-perfect component-wise fits and substantial field-magnitude RMSE reductions; ANN shows the largest gains, including >35 mT improvement in high-current regions (30–35 A). Implications: machine learning offers a practical path to more precise magnetic field maps, enabling improved surgical navigation with eMNS.

Abstract

Electromagnetic Navigation Systems (eMNS) can be used to control a variety of multiscale devices within the human body for remote surgery. Accurate modeling of the magnetic fields generated by the electromagnets of an eMNS is crucial for the precise control of these devices. Existing methods assume a linear behavior of these systems, leading to significant modeling errors within nonlinear regions exhibited at higher magnetic fields. In this paper, we use a random forest (RF) and an artificial neural network (ANN) to model the nonlinear behavior of the magnetic fields generated by an eMNS. Both machine learning methods outperformed the state-of-the-art linear multipole electromagnet method (LMEM). The RF and the ANN model reduced the root mean squared error of the LMEM when predicting the field magnitude by around 40% and 80%, respectively, over the entire current range of the eMNS. At high current regions, especially between 30 and 35 A, the field-magnitude RMSE improvement of the ANN model over the LMEM was over 35 mT. This study demonstrates the feasibility of using machine learning methods to model an eMNS for medical applications, and its ability to account for complex nonlinear behavior at high currents. The use of machine learning thus shows promise for improving surgical procedures that use magnetic navigation.

Paper Structure

This paper contains 12 sections, 5 equations, 4 figures, 2 tables.

Table of Contents

  1. INTRODUCTION
  2. MODELING METHODS
  3. Linear Multipole Electromagnet Method (Baseline)
  4. Machine Learning Methods
  5. EXPERIMENTS
  6. Hardware Setup
  7. Data Collection
  8. Model Training
  9. Evaluation Metrics
  10. RESULTS
  11. DISCUSSION
  12. CONCLUSIONS

Figures (4)

  • Figure 1: Data collection setup for an eMNS. A: The CardioMag, an eMNS B: Magnetic sensor array C: Magnetic field measurements with the sensor array for a random current set
  • Figure 2: Prediction performance comparison in the testing dataset stratified by current levels.
  • Figure 3: Spatial prediction error comparison among three models. The maximum $\text{MAPE}_{norm}^\textbf{p}$ across all sensor locations was 33.24% for the LMEM, 29.38% for the RF model and 10.91% for the ANN model.
  • Figure 4: The impact of the training set size on prediction performance.