System and method for tracking anatomical structures in three dimensional images

• US 20060064007A1
• Filed: 09/01/2005
• Published: 03/23/2006
• Est. Priority Date: 09/02/2004
• Status: Active Grant

• Current Assignee: Siemens Healthcare GMBH (Siemens AG)
• Original Assignee: Siemens Medical Solutions USA Incorporated (Siemens AG)
• Inventors: Zhou, Xiang, Georgescu, Bogdan, Xiao, Jing, Comaniciu, Dorin
• Granted Patent: US 7,555,151 B2
• Time in Patent Office: Days
• US Class Current: 600/416
• CPC Class Codes: A61B 8/08 Detecting organic movements or changes, e.g. tumours, cysts, swellings A61B8/02 - A61B8/06 take precedence
• CPC Class Codes: A61B 8/0883 for diagnosis of the heart
• CPC Class Codes: A61B 8/463 characterised by displaying multiple images or images and diagnostic data on one display composite display in devices for short-range imaging with acoustic waves G01S7/52074
• CPC Class Codes: A61B 8/483 involving the acquisition of a 3D volume of data
• CPC Class Codes: G06T 2200/04 involving 3D image data
• CPC Class Codes: G06T 2200/24 involving graphical user interfaces [GUIs]
• CPC Class Codes: G06T 2207/10136 3D ultrasound image
• CPC Class Codes: G06T 2207/30048 Heart; Cardiac
• CPC Class Codes: G06T 7/0016 involving temporal comparison
• CPC Class Codes: G06T 7/12 Edge-based segmentation
• CPC Class Codes: G06T 7/149 involving deformable models, e.g. active contour models
• CPC Class Codes: G06T 7/246 using feature-based methods, e.g. the tracking of corners or segments
• CPC Class Codes: G06T 7/277 involving stochastic approaches, e.g. using Kalman filters
• CPC Class Codes: G06V 10/245 by locating a pattern; Special marks for positioning
• CPC Class Codes: G06V 2201/031 of internal organs
• CPC Class Codes: Y10S 128/922 including image analysis

Abstract

A system and method for defining and tracking a deformable shape of a candidate anatomical structure wall in a three dimensional (3D) image is disclosed. The shape of the candidate anatomical structure is represented by a plurality of labeled 3D landmark points. At least one 3D landmark point of the deformable shape in an image frame is defined. A 3D cuboid is defined around the detected 3D landmark point. For each landmark point associated with the anatomical structure, its location and location uncertainty matrix is estimated in subsequent frames relative to the reference anatomical structures. A shape model is generated to represent dynamics of the deformable shape in subsequent image frames. The shape model includes statistical information from a training data set of 3D images of representative anatomical structures. The shape model is aligned to the deformable shape of the candidate anatomical structure. The shape model is fused with the deformable shape. A current shape of the candidate anatomical structure is estimated.

Claims

1. A method for defining and tracking a deformable shape of a candidate anatomical structure wall in a three dimensional (3D) image, the shape being represented by a plurality of labeled 3D landmark points, the method comprising the steps of:

defining at least one 3D landmark point of the deformable shape in an image frame;

defining a 3D cuboid around the detected 3D landmark point;

for each landmark point associated with the candidate anatomical structure, computing a location and a location uncertainty matrix;

fusing location estimates computed relative to one or more reference anatomical structures;

generating a shape model to represent dynamics of the deformable shape in subsequent image frames, the shape model comprising statistical information from a training data set of 3D images of representative anatomical structures;

aligning the shape model to the deformable shape of the candidate anatomical structure;

fusing the shape model with the deformable shape; and

estimating a current shape of the candidate anatomical structure.

2. The method of claim 1 wherein the shape model depicts the deformable shape over time.

3. The method of claim 1 wherein localization uncertainties of the plurality of 3D landmark points are represented by covariance matrices.

4. The method of claim 1 wherein the shape model is represented as a single mode or a mixture of multi-normal Gaussian distributions.

5. The method of claim 1 wherein the location uncertainty matrix is transformed with the candidate anatomical structure during the aligning step.

6. The method of claim 1 wherein the shape model is a Gaussian model in space that is generated by concatenating coordinates of the 3D landmark points.

7. The method of claim 1 wherein said location estimation step further comprising the steps of:

matching the 3D landmark points of the candidate anatomical structure to corresponding landmark points of a reference anatomical structure.

8. The method of claim 7 wherein the step of matching 3D landmark points further comprises the step of:

transforming an orientation of the candidate anatomical structure to a same orientation of the reference anatomical structure.

9. The method of claim 8 wherein the transformation includes translation of the image of the candidate anatomical structure.

10. The method of claim 8 wherein the transformation includes rotation of the image of the candidate anatomical structure.

11. The method of claim 8 wherein the transformation includes scaling of the image of the candidate anatomical structure.

12. The method of claim 1 wherein said aligning step takes into account the location uncertainty matrix.

13. The method of claim 12 wherein a weighted least squares formulation is used, where the weighting matrix is determined by the location uncertainty matrix.

14. The method of claim 1 wherein the anatomical structure is a left ventricle.

15. The method of claim 1 wherein the image is a 3D ultrasound image.

16. A system for defining and tracking a deformable shape of a candidate anatomical structure in a three dimensional (3D) image, the shape being represented by a plurality of labeled 3D landmark points, the method comprising the steps of:

means for defining at least one 3D landmark point of the deformable shape in an image frame;

means for defining a 3D cuboid around the detected 3D landmark point;

means for computing a location and a location uncertainty matrix for each 3D landmark point associated with the candidate anatomical structure;

means for fusion location estimates computed relative to one or more reference anatomical structures;

means for generating a shape model to represent dynamics of the deformable shape in subsequent image frames, the shape model comprising statistical information from a training data set of images of representative anatomical structures;

means for aligning the shape model to the deformable shape of the candidate anatomical structure;

means for fusing the shape model with the deformable shape; and

means for estimating a current shape of the candidate anatomical structure.

17. The system of claim 16 wherein the shape model depicts the deformable shape over time.

18. The system of claim 16 wherein localization uncertainties of the plurality of 3D landmark points are represented by covariance matrices.

19. The system of claim 16 wherein the shape model is represented as a single mode or a mixture of multi-normal Gaussian distributions.

20. The system of claim 16 wherein the location uncertainty matrix is transformed with the candidate anatomical structure during the aligning step.

21. The system of claim 16 wherein the shape model is a Gaussian model in space that is generated by concatenating coordinates of the 3D landmark points.

22. The system of claim 16 wherein said means for location estimation further comprises:

means for matching the 3D landmark points of the candidate anatomical structure to corresponding control points of a reference anatomical structure.

23. The system of claim 22 wherein the means for matching 3D landmark points further comprises:

means for transforming an orientation of the candidate anatomical structure to a same orientation of the reference anatomical structure.

24. The system of claim 23 wherein the transformation includes translation of the 3D image of the candidate anatomical structure.

25. The system of claim 23 wherein the transformation includes rotation of the 3D image of the candidate anatomical structure.

26. The system of claim 23 wherein the transformation includes scaling of the 3D image of the candidate anatomical structure.

27. The system of claim 16 wherein said means for aligning takes into account the location uncertainty matrix.

28. The system of claim 27 wherein a weighted least squares formulation is used, where the weighting matrix is determined by the location uncertainty matrix.