IP Library Granted Patent US 7,668,354
Granted Patent B2
US 7,668,354 · App. 11/372,783 · Granted Feb 23, 2010

System and method for tracking and classifying the left ventricle of the heart using cine-delayed enhancement magnetic resonance

View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 7,668,354
App. No.
11/372,783
Granted
Feb 23, 2010
Kind
B2
Abstract

A system and method for tracking and classifying the left ventricle of the heart using cine-delayed enhancement magnetic resonance (Cine-DEMR) are provided. The method for tracking the left ventricle comprises: delineating myocardial borders of the left ventricle in an image of a first phase of a cardiac cycle of the heart; registering the image of the first phase with an image of a second phase of the cardiac cycle; copying the myocardial borders from the first phase onto the second phase; fitting the myocardial borders of the first phase to myocardial borders of the second phase; and refining the myocardial borders of the second phase.

Claims (48)

1. A method for tracking a left ventricle of a heart using cine-delayed enhancement magnetic resonance (Cine-DEMR), comprising:

delineating myocardial borders of the left ventricle in an image of a first phase of a cardiac cycle of the heart;

registering the image of the first phase with an image of a second phase of the cardiac cycle;

copying the myocardial borders from the first phase onto the second phase;

fitting the myocardial borders of the first phase to myocardial borders of the second phase; and

refining the myocardial borders of the second phase;

wherein the myocardial borders of the second phase are refined by matching radial intensity profiles of the second phase with radial intensity profiles of the first phase.

2. The method of claim 1 , wherein the myocardial borders are manually drawn onto the image of the first phase, the image of the first phase is a first image of a cine-DEMR image sequence.

3. The method of claim 2 , wherein the image of the second phase is a second image of the cine-DEMR image sequence.

4. The method of claim 1 , wherein the myocardial borders represent an endocardium and an epicardium.

5. The method of claim 1 , wherein the myocardial borders are fit by performing an affine transformation.

6. The method of claim 1 , further comprising:

classifying viable tissue from non-viable tissue.

7. The method of claim 6 , wherein the viable and non-viable tissues are classified by using a trained support vector machine.

8. The method of claim 1 , further comprising:

registering the image of the first phase with an image of a third phase of the cardiac cycle;

copying the myocardial borders from the first phase onto the third phase;

fitting the myocardial borders of the first phase to myocardial borders of the third phase; and

refining the myocardial borders of the third phase.

9. A system for tracking a left ventricle of a heart using cine-delayed enhancement magnetic resonance (Cine-DEMR), comprising:

a memory device for storing a program;

a processor in communication with the memory device, the processor operative with the program to:

delineate myocardial borders of the left ventricle in an image of a first phase of a cardiac cycle of the heart;

register the image of the first phase with an image of a second phase of the cardiac cycle;

copy the myocardial borders from the first phase onto the second phase;

fit the myocardial borders of the first phase to myocardial borders of the second phase; and

refine the myocardial borders of the second phase;

wherein—the myocardial borders of the second phase are refined by matching radial intensity profiles of the second phase with radial intensity profiles of the first phase.

10. The system of claim 9 , wherein the myocardial borders are manually drawn onto the image of the first phase, the image of the first phase is a first image of a cine-DEMR image sequence.

11. The system of claim 10 , wherein the image of the second phase is a second image of the cine-DEMR image sequence.

12. The system of claim 10 , wherein the cine-DEMR image sequence is acquired using an MR scanner.

13. The system of claim 9 , wherein the myocardial borders represent an endocardium and an epicardium.

14. The system of claim 9 , wherein the myocardial borders are fit by performing an affine transformation.

15. The system of claim 9 , wherein the processor is further operative with the program code to:

classify viable tissue from non-viable tissue.

16. The system of claim 15 , wherein the viable and non-viable tissues are classified by using a trained support vector machine.

17. The system of claim 9 , wherein the processor is further operative with the program code to:

register the image of the first phase with an image of a third phase of the cardiac cycle;

copy the myocardial borders from the first phase onto the third phase;

fit the myocardial borders of the first phase to myocardial borders of the third phase; and

refine the myocardial borders of the third phase.

18. A method for tracking and classifying a left ventricle of a heart using a cine-delayed enhancement magnetic resonance (Cine-DEMR) image sequence of a cardiac cycle of the heart, comprising:

delineating contours of the left ventricle in an image of a first phase of the cardiac cycle, wherein the contours represent an endocardium and an epicardium;

registering the image of the first phase with an image of a second phase of the cardiac cycle;

copying the contours from the first phase onto the second phase;

fitting the contours of the first phase to contours of the second phase by performing an affine transformation;

refining the contours of the second phase by matching radial intensity profiles of the second phase with radial intensity profiles of the first phase; and

classifying live tissue from dead tissue by using a trained support vector machine.

Assignments (3)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 17, 2007
From: SIEMENS CORPORATE RESEARCH, INC.
To: SIEMENS MEDICAL SOLUTIONS USA, INC.
Reel/Frame 019309/0669 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 22, 2006
From: DIKICI, ENGIN; O'DONNELL, THOMAS
To: SIEMENS CORPORATE RESEARCH, INC.
Reel/Frame 017827/0557 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 22, 2006
From: SETSER, RANDOLPH M.; WHITE, RICHARD D.
To: THE CLEVELAND CLINIC FOUNDATION
Reel/Frame 017827/0832 →