Systems, devices, and methods for detecting false movements for motion correction during a medical imaging scan

• US 9,943,247 B2
• Filed: 07/28/2016
• Issued: 04/17/2018
• Est. Priority Date: 07/28/2015
• Status: Expired due to Fees

• Current Assignee: Queen's Medical Center, University of Hawai'i
• Original Assignee: Queen's Medical Center, University of Hawai'i
• Inventors: Ernst, Thomas Michael, Keating, Brian, Singh, Aditya, Zaitsev, Maxim, Herbst, Michael
• Primary Examiner(s): Do, Anh H
• Application Number:
  US15/222,811
• Publication Number:
  US 20170032538A1
• Time in Patent Office: 628 Days
• Field of Search: 382103, 382104, 382155, 382203, 345156, 345168, 37524001, 37524009, 701 45, 715863
• CPC Class Codes: A61B 5/055 involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
• CPC Class Codes: A61B 5/1121 Determining geometric values, e.g. centre of rotation or angular range of movement
• CPC Class Codes: A61B 5/1127 using markers
• CPC Class Codes: A61B 5/682 Mouth, e.g., oral cavity; tongue; Lips; Teeth
• CPC Class Codes: A61B 5/7207 of noise induced by motion artifacts
• CPC Class Codes: A61B 5/7267 involving training the classification device
• CPC Class Codes: G06F 18/214 Generating training patterns; Bootstrap methods, e.g. bagging or boosting
• CPC Class Codes: G06F 18/2415 based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
• CPC Class Codes: G06F 18/253 of extracted features
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/10088 Magnetic resonance imaging [MRI]
• CPC Class Codes: G06T 2207/20081 Training; Learning
• CPC Class Codes: G06T 2207/20084 Artificial neural networks [ANN]
• CPC Class Codes: G06T 2207/30004 Biomedical image processing
• CPC Class Codes: G06T 2207/30204 Marker
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06T 7/246 using feature-based methods, e.g. the tracking of corners or segments
• CPC Class Codes: G06T 7/248 involving reference images or patches
• CPC Class Codes: G06V 10/806 of extracted features
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients

Abstract

The systems, methods, and devices described herein generally relate to achieving accurate and robust motion correction by detecting and accounting for false movements in motion correction systems used in conjunction with medical imaging and/or therapeutic systems. In other words, in some embodiments of the systems, methods, and devices described herein can be configured to detect false movements for motion correction during a medical imaging scan and/or therapeutic procedure, and thereby ensure that such false movements are not accounted for in the motion correction process. Upon detection of false movements, the imaging or therapeutic system can be configured to transiently suppress and/or subsequently repeat acquisitions.

Claims

1. A computer-implemented method for determining false motion tracked by a motion correction system during a medical imaging scan, the method comprising:

obtaining tracking data, wherein the tracking data reflects motion of a subject of the medical imaging scan or a portion thereof;

determining by a false motion discriminator a likelihood of the obtained tracking data reflecting false motion, wherein the false motion is not reflective of true motion of the subject of the medical imaging scan or the portion thereof; and

generating by the false motion discriminator a confidence level of the determined likelihood of the obtained tracking data reflecting false motion, wherein the motion correction system is configured to adjust output based on the confidence level,

wherein the false motion discriminator comprises a computer processor and an electronic storage medium.

2. The computer-implemented method of claim 1, wherein the likelihood of the obtained tracking data reflecting false motion is based on at least one of velocity, acceleration, center of rotation, and axis of rotation of the motion of the subject.

3. The computer-implemented method of claim 1, wherein the likelihood of the obtained tracking data reflecting false motion is based on machine learning.

4. A false motion classifier system for determining false motion tracked by a motion correction system during a medical imaging scan, the false motion classifier system comprising:

a first false motion discriminator configured to determine a center of rotation of a detected motion and further determine a first confidence level based on the center of rotation of the detected motion, wherein the first confidence level is indicative of the detected motion being true or false;

a second false motion discriminator configured to determine a velocity of the detected motion and further determine a second confidence level based on the velocity of the detected motion, wherein the second confidence level is indicative of the detected motion being true or false; and

a combination module configured to combine the first and second confidence levels to generate an output indicative of the detected motion being true or false, wherein an output indicative of the detected motion being false causes the motion correction system not to apply one or more motion correction processes to the detected motion.

5. The false motion classifier system of claim 4 further comprising a third false motion discriminator configured to determine a third confidence level indicative of the detected motion being true or false based on machine learning.

6. The false motion classifier system of claim 4 further comprising a differential motion discriminator configured to determine a third confidence level indicative of the detected motion being true or false based on relative motion of two or more motion trackers used by the motion correction system.

7. The false motion classifier system of claim 4 further comprising one or more external discriminators configured to determine one or more external confidence levels indicative of the detected motion being true or false.

8. The false motion classifier system of claim 7, wherein the one or more external discriminators are configured to determine the one or more external confidence levels based on at least one or more of noise and video tracking.

9. The false motion classifier system of claim 4, wherein the output is binary.

10. A motion correction system for detecting and correcting motion by a subject during a medical imaging scan, the motion correction system comprising:

one or more markers placed on one or more portions of the subject;

one or more detectors configured to track motion of the one or more markers; and

a tracking quality classifier for determining false motion of the one or more markers, wherein the tracking quality classifier system comprises one or more false motion discriminators,

wherein determination by the tracking quality classifier that a false motion of the one or more markers occurred causes the motion correction system not to apply one or more motion correction processes to the false motion.

11. The motion correction system of claim 10, wherein the one or more false motion discriminators are configured to determine false motion of the one or more markers based on at least one or more of velocity, rotational center, and machine learning.

12. The motion correction system of claim 10, wherein the tracking quality classifier further comprises one or more external discriminators.

13. The motion correction system of claim 10, further comprising a scanner control module configured to control a scanner for the medical imaging scan not to utilize acquired data during the false motion.

14. The motion correction system of claim 10, further comprising a scanner control module configured to control a scanner for the medical imaging scan to repeat acquisitions of data initially acquired during the false motion.