Method, storage medium, and system for analyzing image sequences of periodic physiological activities

Patent metadata

Field	Value
Publication number	US-10980502-B2
Application number	US-201916689048-A
Country	US
Kind code	B2
Filing date	Nov 19, 2019
Priority date	Jan 8, 2018
Publication date	Apr 20, 2021
Grant date	Apr 20, 2021

Abstract

The present disclosure relates to a method, storage medium, and system for analyzing an image sequence of a periodic physiological activity. In one implementation, the method includes receiving the image sequence acquired by an imaging device, the image sequence having a plurality of frames, and identifying a feature point in a first frame. The method further includes determining motion vectors for the feature point in the frames of the image sequence. Each motion vector for the feature point is determined based on respective locations of corresponding feature points in frames adjacent to the first frame. The method also includes determining a motion magnitude profile based on the determined motion vectors and determining a phase of each frame in the image sequence based on the motion magnitude profile.

First claim

What is claimed is:

1. A computer-implemented method for analyzing an image sequence of a periodic physiological activity, the method comprising:
receiving the image sequence acquired by an imaging device, the image sequence having a plurality of frames;
identifying a feature point in a first frame;
determining motion vectors for the feature point in the frames of the image sequence, wherein each motion vector for the feature point is determined based on respective locations of corresponding feature points in frames adjacent to the first frame;
determining a motion magnitude profile based on the determined motion vectors; and
determining a phase of each frame in the image sequence based on the motion magnitude profile.

2. The method of claim 1 , wherein identifying the feature point further comprises identifying an observed object in the first frame.

3. The method of claim 1 , wherein determining the motion vector for each feature point comprises calculating a displacement between the respective locations of the corresponding feature points in the two adjacent frames.

4. The method of claim 1 , wherein the motion vector for each feature point is determined using an optical flow estimation.

5. The method of claim 1 , wherein the motion vector for each feature point is determined using a patch matching method.

6. The method of claim 1 , wherein identifying the corresponding feature point in a second frame adjacent to the first frame further comprises:
identifying a searching region in the second frame defined with respect to the location of feature point in the first frame;
selecting candidate feature points within the searching region;
calculating correlation coefficients between the feature point in the first frame and the candidate feature points; and
identifying the candidate feature point with the largest correlation coefficient as the corresponding feature point in the second frame.

7. The method of claim 1 , wherein determining the motion magnitude profile further includes calculating global motion magnitudes for the plurality of frames; and integrating the global motion magnitudes to provide a global motion magnitude profile.

8. The method of claim 1 , wherein determining the phase of each frame comprises:
determining a global motion magnitude profile by integrating global motion magnitudes for the plurality of frames;
determining a global displacement for the frame; and
determining a corresponding position of the global displacement on the global motion magnitude profile.

9. The method of claim 1 , wherein the periodic physiological activity includes a cardiac activity or a respiratory activity.

10. A system for performing analysis on an image sequence of periodic physiological activity, comprising:
a processor; and
a memory storing computer-executable instructions that, when executed by the processor, cause the processor to:
receive the image sequence acquired by an imaging device, the image sequence having a plurality of frames;
identify a feature point in a first frame;
determine motion vectors for the feature point in the frames of the image sequence, wherein each motion vector for the feature point is determined based on respective locations of corresponding feature points in frames adjacent to the first frame;
determine a motion magnitude profile based on the determined motion vectors; and
determine a phase of each frame in the image sequence based on the motion magnitude profile.

11. The system of claim 10 , wherein identifying the feature point further comprises identifying an observed object in the first frame.

12. The system of claim 10 , wherein the instructions cause the processor to determine the motion vector for each feature point by calculating a displacement between the respective locations of the corresponding feature points in the two adjacent frames.

13. The system of claim 10 , wherein the instructions cause the processor to identify the corresponding feature point in a second frame adjacent to the first frame by:
identifying a searching region in the second frame defined with respect to the location of feature point in the first frame;
selecting candidate feature points within the searching region;
calculating correlation coefficients between the feature point in the first frame and the candidate feature points; and
identifying the candidate feature point with the largest correlation coefficient as the corresponding feature point in the second frame.

14. The system of claim 10 , wherein the instructions cause the processor to determine the motion magnitude profile by calculating global motion magnitudes for the plurality of frames and integrating the global motion magnitudes to provide a global motion magnitude profile.

15. The system of claim 10 , wherein the instructions when executed by the processor further cause the processor to: mark the determined phases on corresponding frames, and store, in the memory, the frames marked with the phases.

16. The system of claim 15 , wherein the memory is in communication with a medical database storing at least one of the image sequence and the frames marked with the phases.

17. The system of claim 15 , further comprising: a display configured to display the frames marked with the phases.

18. A non-transitory computer-readable storage medium, with computer-executable instructions stored thereon, wherein the instructions, when executed by a processor, cause the processor to perform a method for analyzing an image sequence of a periodic physiological activity, the method comprising:
receiving the image sequence acquired by an imaging device, the image sequence having a plurality of frames;
identifying a feature point in a first frame;
determining motion vectors for the feature point in the frames of the image sequence, wherein each motion vector for the feature point is determined based on respective locations of corresponding feature points in frames adjacent to the first frame;
determining a motion magnitude profile based on the determined motion vectors; and
determining a phase of each frame in the image sequence based on the motion magnitude profile.

19. The non-transitory computer-readable storage medium of claim 18 , wherein identifying the feature point further comprises identifying an observed object in the first frame.

20. The non-transitory computer-readable storage medium of claim 18 , wherein identifying the corresponding feature point in a second frame adjacent to the first frame further comprises:
identifying a searching region in the second frame defined with respect to the location of feature point in the first frame;
selecting candidate feature points within the searching region;
calculating correlation coefficients between the feature point in the first frame and the candidate feature points; and
identifying the candidate feature point with the largest correlation coefficient as the corresponding feature point in the second frame.

Assignees

• Shenzhen Keya Medical Tech Corporation

Inventors

• Song Qi
• Zhi Ying Xuan
• Liu Xiaoxiao
• Liu Shubao
• Yin Youbing
• Li Yuwei
• Cao Kunlin

Classifications

• G06T7/20

  Analysis of motion (motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51) · CPC title

• G06T2207/10081

  Computed x-ray tomography [CT] · CPC title

• A61B6/5217

  extracting a diagnostic or physiological parameter from medical diagnostic data · CPC title

• G06T2207/30101

  Blood vessel; Artery; Vein; Vascular · CPC title

• G06T2207/30048

  Heart; Cardiac · CPC title