System and method for monitoring health status of a gradient coil

Patent metadata

Field	Value
Publication number	US-11269749-B2
Application number	US-201815974323-A
Country	US
Kind code	B2
Filing date	May 8, 2018
Priority date	May 8, 2018
Publication date	Mar 8, 2022
Grant date	Mar 8, 2022

Abstract

A system for monitoring a health status of a gradient coil disposed in a magnetic resonance imaging system is provided. The system includes one or more sensors and a controller. The one or more sensors are operative to obtain one or more parameter readings of the gradient coil, wherein the one or more parameter readings include at least one of an acoustic measurement and a back electromotive force measurement. The controller is in electronic communication with the one or more sensors and operative to generate the health status based on at least one of the acoustic measurement and the back electromotive force measurement.

First claim

What is claimed is:

1. A system for monitoring a health status of a gradient coil disposed in a magnetic resonance imaging system, the system comprising:
one or more sensors operative to obtain a parameter reading of the gradient coil, wherein the parameter reading includes at least one of an acoustic measurement and a back electromotive force measurement; and
a controller in electronic communication with the one or more sensors and operative to:
feed a training dataset to a neural network, wherein the training dataset includes a plurality of pairings each comprising of the parameter reading and a known health status of the gradient coil;
train the neural network in a supervised manner on the training dataset such that, for one or more of the pairings, the neural network generates the health status that substantially matches the known health status.

2. A method for monitoring a health status of a gradient coil in a magnetic resonance imaging system, the method comprising:
obtaining a parameter reading of the gradient coil via one or more sensors, wherein the parameter reading includes at least one of an acoustic measurement and a back electromotive force measurement;
feeding a training dataset to a neural network, wherein the training dataset includes a plurality of pairings each comprising of the parameter reading and a known health status of the gradient coil;
training the neural network in a supervised manner on the training dataset such that, for one or more of the pairings, the neural network generates the health status that substantially matches the known health status; and
outputting one or more weights of the neural network after the neural network has been trained.

3. The system of claim 1 , wherein the controller is further operative to trigger an alarm when the health status exceeds a threshold.

4. The system of claim 1 , wherein the controller is further operative to prevent excitation of the gradient coil when the health status exceeds a threshold.

5. The system of claim 1 , wherein the one or more sensors include a microphone disposed proximate to the gradient coil and operative to obtain the acoustic measurement.

6. The system of claim 1 , wherein the one or more sensors includes a voltmeter operative to obtain the back electromotive force measurement.

7. The system of claim 6 , wherein the voltmeter is disposed within a gradient amplifier that drives the gradient coil.

8. The system of claim 7 , wherein the controller is operative to obtain the back electromotive force measurement via the voltmeter after the gradient amplifier has removed an excitation current from the gradient coil.

9. The system of claim 1 , wherein the the parameter reading further includes at least one of an impedance measurement, an inductance measurement, a resistance measurement, a strain measurement, a temperature measurement, an acceleration measurement, a B 0 drift measurement, and a terminal block torque measurement.

10. The system of claim 1 , wherein the controller is further operative to predict a time period when the health status will exceed a threshold.

11. The system of claim 1 , wherein the neural network is trained on a dataset that corresponds to one or more pulse sequences of one or more magnetic resonance imaging systems.

12. The method of claim 2 further comprising:
triggering, via the controller, an alarm when the health status exceeds a threshold.

13. The method of claim 2 further comprising:
preventing, via the controller, excitation of the gradient coil when the health status exceeds a threshold.

14. The method of claim 2 , wherein obtaining the parameter reading of the gradient coil via one or more sensors comprises:
obtaining the acoustic measurement via a microphone disposed proximate to the gradient coil.

15. The method of claim 2 , wherein obtaining the parameter reading of the gradient coil via one or more sensors comprises:
obtaining the back electromotive force measurement via a voltmeter disposed in a gradient amplifier that drives the gradient coil.

16. The method of claim 2 further comprising:
predicting, via the controller, a time period when the health status will exceed a threshold.

17. A method of training a neural network, the method comprising:
feeding a training dataset to the neural network, wherein the training dataset includes a plurality of pairings each comprising of a parameter reading and a known health status of a gradient coil, wherein the parameter reading is at least one of an acoustic measurement and a back electromotive force measurement;
training the neural network in a supervised manner on the training dataset such that, for one or more of the pairings, the neural network generates a health status that substantially matches the known health status; and
outputting, after the neural network has been trained, one or more weights of the neural network.

Assignees

• Gen Electric

Inventors

• Citirik Erman
• Astary Garrett
• Mathieu Jean-Baptiste
• Seeber Derek
• Reganti Namratha

Classifications

• G06N3/08

  Learning methods · CPC title

• G06N3/09

  Supervised learning · CPC title

• G06N3/0499

  Feedforward networks · CPC title

• G01R33/0385

  in relation with magnetic force measurements (magnetic force microscopes G01Q60/50) · CPC title

• G01R33/385 Primary

  using gradient magnetic field coils · CPC title