Neurophysiological monitoring for prospective motion gating in radiological imaging

Patent metadata

Field	Value
Publication number	US-2016000383-A1
Application number	US-201414767691-A
Country	US
Kind code	A1
Filing date	Mar 12, 2014
Priority date	Mar 20, 2013
Publication date	Jan 7, 2016
Grant date	—

Abstract

A system, method and non-transitory computer-readable storage medium for monitoring motion during medical imaging. The monitoring of the motion includes initiating an acquisition of image data, measuring physiological signals of a patient, generating a prediction signal by integrating the physiological signals, determining whether patient motion is likely to occur based on the prediction signal and modifying the acquisition of image data, if it is predicted that patient motion is likely to occur.

First claim

1 . A method for monitoring motion during medical imaging, comprising:
initiating an acquisition of image data; measuring physiological signals of a patient; generating a prediction signal by integrating the physiological signals; determining whether patient motion is likely to occur based on the prediction signal; and modifying the acquisition of image data, if it is predicted that patient motion is likely to occur.

2 . The method of claim 1 , further comprising:
extracting a study information for a requested medical image to determine a motion tolerance indicator indicating a tolerated range of motion of the patient.

3 . The method of claim 2 , wherein the study information includes one of body part, modality, protocol, resolution and view.

4 . The method of claim 1 , wherein the physiological signals are integrated over time by one of (i) averaging over a period preceding a prediction, (ii) determining a minimum, maximum or median, and (iii) calculating a standard deviation.

5 . The method of claim 1 , wherein the physiological signals are integrated across signal types via a mathematical function.

6 . The method of claim 5 , further comprising:
a machine learning algorithm defining the mathematical function, wherein the machine learning algorithm is trained with one of (i) prior patient data including known signal values and occurrence or non-occurrence of subsequent patient motion within a fixed or adaptive time frame and (ii) current patient data acquired during previous imaging sessions, wherein the machine learning algorithm is at least one of an artificial neural network, a support vector machine, a Bayesian network, a decision tree, a linear discriminant and a nearest-neighbor classifier.

7 . The method of claim 1 , further comprising
initiating a mental focus device attracting a focus of the patient.

8 . The method of claim 1 , wherein determining whether patient motion is likely to occur includes determining whether the prediction signal exceeds a threshold value.

9 . The method of claim 1 , wherein modifying the acquisition of image data includes one of (i) ceasing the acquisition of image data, (ii) ceasing a flow of electricity to an x-ray tube and (iii) shifting the acquisition of data to a less motion sensitive area of the patient.

10 . The method of claim 1 , further comprising:
restarting the acquisition of image data to an original state upon receipt of a restart signal, wherein the restart signal is based on one of a fixed timer, a manual intervention by a user and a sensor observation indicating that the patient has returned to an original position.

11 . A system for monitoring motion during medical imaging, comprising:
a monitoring system measuring physiological signals of a patient; and a processor initiating an acquisition of image data, generating a prediction signal by integrating the physiological signals, determining whether patient motion is likely to occur based on the prediction signal and modifying the acquisition of image data, if it is predicted that patient motion is likely to occur.

12 . The system of claim 1 , wherein the processor extracts a study information for a requested medical image to determine a motion tolerance indicator indicating a tolerated range of motion of the patient.

13 . (canceled)

14 . (canceled)

15 . (canceled)

16 . (canceled)

17 . The system of claim 11 , further comprising:
a mental focus device attracting a focus of the patient.

18 . The system of claim 11 , wherein the processor determines whether patient motion is likely to occur by determining whether the prediction signal exceeds a threshold value.

19 . (canceled)

20 . (canceled)

21 . A non-transitory computer-readable storage medium including a set of instructions executable by a processor, the set of instructions operable to:
initiate an acquisition of image data; measure physiological signals of a patient; generate a prediction signal by integrating the physiological signals; determine whether patient motion is likely to occur based on the prediction signal; and modify the acquisition of image data, if it is predicted that patient motion is likely to occur.

Assignees

• Koninkl Philips Nv

Inventors

• Lee Michael Chun-Chieh
• Manzke Robert
• Qian Yuechen
• Cohen-Solal Eric

Classifications

• A61B6/541

  involving acquisition triggered by a physiological signal · CPC title

• G16H30/40

  for processing medical images, e.g. editing · CPC title

• G01R33/5673

  Gating or triggering based on a physiological signal other than an MR signal, e.g. ECG gating or motion monitoring using optical systems for monitoring the motion of a fiducial marker · CPC title

• A61B5/7267

  involving training the classification device · CPC title

• A61B5/11 Primary

  Measuring movement of the entire body or parts thereof, e.g. head or hand tremor or mobility of a limb {(A61B5/1038 takes precedence; motion detection to correct for motion artifacts in physiological signals A61B5/721)} · CPC title