System for rapid and accurate quantitative assessment of traumatic brain injury

• US 9,256,951 B2
• Filed: 11/17/2010
• Issued: 02/09/2016
• Est. Priority Date: 12/10/2009
• Status: Active Grant

• Current Assignee: The Trustees of Dartmounth College (Dartmouth College), Koninklijke Philips Electronics N.V. (Koninklijke Philips N.V.)
• Original Assignee: Koninklijke Philips N.V.
• Inventors: Zagorchev, Lyubomir Georgiev, Morre, Elizabeth Anne, Garlinghouse, Matthew A., Roth, Robert M., McAllister, Thomas W., Kneser, Reinhard, Geller, Dieter, Peters, Jochen, Weese, Juergen, Qian, Yuechen
• Primary Examiner(s): Ma, Tize
• Application Number:
  US13/514,713
• Publication Number:
  US 20120327075A1
• Time in Patent Office: 1,910 Days
• Field of Search: 345/419
• US Class Current: 1/1
• CPC Class Codes: G06T 2200/24 involving graphical user interfaces [GUIs]
• CPC Class Codes: G06T 2207/10081 Computed x-ray tomography [CT]
• CPC Class Codes: G06T 2207/30016 Brain
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06T 7/149 involving deformable models, e.g. active contour models

Abstract

A system and method for automatic segmentation, performed by selecting a deformable model of an anatomical structure of interest imaged in a volumetric image, the deformable model formed of a plurality of polygons including vertices and edges, displaying the deformable model on a display, detecting a feature point of the anatomical structure of interest corresponding to each of the plurality of polygons and adapting the deformable model by moving each of the vertices toward the corresponding feature points until the deformable model morphs to a boundary of the anatomical structure of interest, forming a segmentation of the anatomical structure of interest.

Claims

1. A method for automatic segmentation, comprising:

selecting a deformable model of an anatomical structure of interest imaged in a volumetric image, the deformable model formed of a plurality of polygons including vertices and edges;

displaying the deformable model on a display;

detecting a plurality of feature points of the anatomical structure of interest, each of the plurality of feature points corresponding to each of the plurality of polygons; and

adapting the deformable model by moving each of the polygons toward the corresponding feature point by moving the vertices of each polygon toward a boundary of the anatomical structure of interest, forming a segmentation of the anatomical structure of interest;

wherein at least a portion of the anatomical structure of interest is a normally symmetrical structure, and the method includes;

determining deviations from a mean vertex value relative to a mid-sagittal plane of the normally symmetrical structure to determine abnormality, and

displaying the deviations to show a deformation in the normally symmetrical structure.

2. The method of claim 1, wherein the deformable model is selected from a database of structures stored in a memory.

3. The method of claim 1, wherein the feature points lie substantially along the boundary of the anatomical structure of interest.

4. The method of claim 1, further comprising receiving a user input via a graphical user interface, the user input selecting an option in regard to segmentation.

5. The method of claim 4, further comprising generating a response to the user input.

6. The method of claim 4, wherein the user input includes selection of one of:

calculating a volume of the segmentation and determining a curvature at a selected point.

7. The method of claim 1, wherein the anatomical structure of interest is a brain region.

8. The method of claim 1, wherein different deviations are displayed in different colors.

9. A system, comprising:

a processor selecting a deformable model of an anatomical structure of interest imaged in a volumetric image, the deformable model formed of a plurality of polygons including vertices and edges; and

a display displaying the deformable model,

wherein the processor;

detects a plurality of feature points of the anatomical structure of interest, each of the plurality of feature points corresponding to each of the plurality of polygons,

deforms the deformable model by moving each of the polygons toward the corresponding feature point by moving the vertices of each polygon toward a boundary of the anatomical structure of interest, forming a segmentation of the anatomical structure of interest,

wherein at least a portion of the anatomical structure of interest is a normally symmetrical structure, and the processor;

determines deviations from a mean vertex value relative to a mid-sagittal plane of the normally symmetrical structure to determine abnormality

the deviations to show a deformation in the normally symmetrical structure.

10. The system of claim 9, further comprising:

a memory storing a database of structures from which the deformable model is selected.

11. The system of claim 9, wherein the feature points lie substantially along the boundary of the anatomical structure of interest.

12. The system of claim 9, further comprising:

a graphical user interface receiving a user input selecting an option in regard to segmentation.

13. The system of claim 12, wherein the processor generates a response to the user input.

14. The system of claim 12, wherein the user input includes selection of one of:

calculating a volume of the segmentation and determining a curvature at a selected point.

15. The system of claim 9, wherein the anatomical structure of interest is a brain region.

16. The system of claim 9, wherein the display displays different deviations in different colors.

17. A non-transient computer-readable storage medium including a set of instructions executable by a processor that cause the processor to:

select a deformable model of an anatomical structure of interest imaged in a volumetric image, the deformable model formed of a plurality of polygons including vertices and edges;

display the deformable member on a display;

detect a feature point of the anatomical structure of interest corresponding to each of the plurality of polygons; and

adapt the deformable model by moving each of the polygons toward the corresponding feature point by moving the vertices of each polygon toward a boundary of the anatomical structure of interest, forming a segmentation of the anatomical structure of interest;

wherein at least a portion of the anatomical structure of interest is a normally symmetrical structure, and the instructions cause the processor to;

determine deviations from a mean vertex value relative to a mid-sagittal plane of the normally symmetrical structure to determine abnormality,

the deviations to show a deformation in the normally symmetrical structure.

18. The medium of claim 17, wherein the anatomical structure of interest is a brain region.

19. The medium of claim 17, wherein different deviations are displayed in different colors.

20. The medium of claim 17, wherein the deformable model is selected from a database of structures stored in a memory.