Method of processing fluoroscopy images

Patent metadata

Field	Value
Publication number	US-10813611-B2
Application number	US-201916259127-A
Country	US
Kind code	B2
Filing date	Jan 28, 2019
Priority date	Jan 30, 2018
Publication date	Oct 27, 2020
Grant date	Oct 27, 2020

Abstract

A method of extracting mechanical activation of the left ventricle from a sequence of contrasted X-ray fluoroscopy images is provided. The method includes: processing the image sequence to perform segmentation of the coronary veins; annotating branches of the segmented coronary veins; tracking the positions of the annotations throughout the fluoroscopy image sequence; computing the principle components of the motion of the annotations from the tracked positions; projecting the motion of the annotations to the axis corresponding to a first principle component; and analyzing the resulting motion curves to identify a latest activating region of the left ventricle.

First claim

The invention claimed is:

1. A method of extracting mechanical activation of a left ventricle from an image sequence of contrasted X-ray fluoroscopy images, the method comprising:
processing the image sequence to perform a segmentation of coronary veins within the fluoroscopy images;
annotating branches of the segmented coronary veins;
tracking positions of the annotations throughout the image sequence;
computing principle components of a motion of the annotations from the tracked positions;
projecting the motion of the annotations to an axis corresponding to a first principle component;
analyzing resulting motion curves to identify a latest activating region of the left ventricle; and
identifying a primary motion curve associated with a main vein of a coronary sinus.

2. The method of claim 1 , wherein a position of an annotation is noted in an initial image of the image sequence, and
wherein the motion of an annotation is tracked by determining the position of the annotation from the initial image in remaining images of the image sequence.

3. The method of claim 1 , further comprising:
identifying minima in the motion curves; and
measuring a relative delay between the minima, wherein the delay of a motion curve minimum is measured relative to a corresponding minimum of the primary motion curve.

4. The method according to claim 3 , further comprising:
identifying a motion curve with a largest relative delay; and
identifying a corresponding annotated branch of the coronary veins to identify a late-activating region of the left ventricle.

5. The method of claim 1 , wherein the annotating of the branches comprises placing a label on a respective branch in a segmented and/or skeletonized layer superposed on an image of the image sequence.

6. The method of claim 5 , wherein a label is placed at a vein bifurcation.

7. The method of claim 1 , wherein at least two annotations are tracked in the image sequence.

8. The method of claim 1 , wherein the image sequence is obtained at a frame rate of at least 7.5 frames per second, at a resolution of at least 130 ms, or a combination thereof.

9. The method of claim 1 , wherein the image sequence comprises images obtained over at least one complete cardiac cycle.

10. An image processing arrangement for extracting left ventricle mechanical activation information from an image sequence of contrasted X-ray fluoroscopy images, the image processing arrangement comprising:
a control unit configured to:
perform a segmentation of coronary veins;
annotate branches of the segmented coronary veins;
track positions of the annotations in the image sequence;
compute principle components of motion of the annotated branches;
provide motion curves of the annotations representing the computed principle components; and
identify a primary motion curve associated with a main vein of a coronary sinus.

11. The image processing arrangement of claim 10 , wherein the control unit is configured to automatically identify a branch of the coronary veins and to place an annotation accordingly.

12. The image processing arrangement of claim 10 , wherein the control unit is configured to replicate the annotations in a plurality of images of the image sequence.

13. The image processing arrangement of claim 10 , wherein the image processing arrangement is configured to allow manual image annotation.

14. A non-transitory computer program product comprising a computer program configured to be directly loadable into a memory of a control unit of an image processing arrangement and which comprises program elements, wherein, when the computer program is executed by the control unit of the image processing arrangement, causes the control unit to:
segment coronary veins within an image sequence of contrasted X-ray fluoroscopy images;
annotate branches of the segmented coronary veins;
track positions of the annotations throughout the image sequence;
compute principle components of a motion of the annotations from the tracked positions;
project the motion of the annotations to an axis corresponding to a first principle component;
analyze resulting motion curves to identify a latest activating region of a left ventricle; and
identify a primary motion curve associated with a main vein of a coronary sinus.

Assignees

• Siemens Healthcare Gmbh

Inventors

• Toth Daniel
• Mountney Peter
• Kurzendorfer Tanja
• Rinaldi Christopher A
• Rhode Kawal

Classifications

• G06T7/0012 Primary

  Biomedical image inspection · CPC title

• G06V2201/031

  of internal organs · CPC title

• G06T2207/10121

  Fluoroscopy · CPC title

• A61N1/3627

  for treating a mechanical deficiency of the heart, e.g. congestive heart failure or cardiomyopathy · CPC title

• G06T2207/30048

  Heart; Cardiac · CPC title