METHOD FOR EDITING 3D IMAGE SEGMENTATION MAPS

• US 20090279756A1
• Filed: 12/22/2008
• Published: 11/12/2009
• Est. Priority Date: 05/06/2008
• Status: Active Grant

• Current Assignee: Philips Healthcare Informatics Incorporated (Koninklijke Philips N.V.)
• Original Assignee: CareStream Health Incorporated
• Inventors: Ray, Lawrence A., Simon, Richard A., Gindele, Edward B.
• Granted Patent: US 8,077,948 B2
• Time in Patent Office: Days
• US Class Current: 382/128
• CPC Class Codes: G06T 19/00 Manipulating 3D models or images for computer graphics
• CPC Class Codes: G06T 2207/10081 Computed x-ray tomography [CT]
• CPC Class Codes: G06T 2207/20101 Interactive definition of point of interest, landmark or seed
• CPC Class Codes: G06T 2207/30064 Lung nodule
• CPC Class Codes: G06T 2219/008 Cut plane or projection plane definition
• CPC Class Codes: G06T 7/11 Region-based segmentation

Abstract

A digital image editing method includes receiving a three-dimensional volume image of an anatomical object of interest, wherein the volume image is characterized by first and second mutually exclusive segmentation classes. The method also includes deriving a two-dimensional slice image from the volume image, selecting a single point on the slice image within the second segmentation class, and defining a plane in response to the selection of the single point, the plane dividing the second segmentation class into a target portion corresponding to the object and a remainder portion.

Claims

1. A digital image editing method, comprising:

receiving a three-dimensional volume image of an anatomical object of interest, wherein the volume image is characterized by first and second mutually exclusive segmentation classes;

deriving a two-dimensional slice image from the volume image;

selecting a single point on the slice image within the second segmentation class; and

defining a plane in response to the selection of the single point, the plane dividing the second segmentation class into a target portion corresponding to the object and a remainder portion.

2. The method of claim 1, wherein the first segmentation class corresponds to at least one of a parenchyma, a vessel, and a chest wall, and the second segmentation class corresponds to a lesion.

3. The method of claim 1, wherein the target portion corresponds to a lesion, and the remainder portion corresponds to at least one of a parenchyma, a vessel, and a chest wall.

4. The method of claim 1, wherein the single point lies within the plate.

5. The method of claim 1, further including creating a three-dimensional rendering of the target and remainder portions connected at the first plane.

6. The method of claim 5, further including rendering the remainder portion transparent such that only the target portion is displayed in the three-dimensional rendering.

7. The method of claim 1, further including defining an additional plane in response to the selection of the single point, wherein the plane and the additional plane each define a cross section of the object thereon.

8. The method of claim 7, further including calculating a characteristic of each of the defined cross sections, and choosing one of the plane and the additional plane based on the calculated characteristics.

9. The method of claim 8, wherein choosing one of the plane and the additional plane comprises selecting a plane that defines a minimum cross sectional area of a contiguous portion of the object and that passes through the single point.

10. The method of claim 8, wherein the calculated characteristic is an area of the defined cross section.

11. A digital image editing method, comprising:

viewing a two-dimensional slice image of an anatomical object of interest corresponding to a three-dimensional volume image of the object, wherein the volume image is characterized by first and second mutually exclusive segmentation classes;

selecting a single point on the slice image within the second segmentation class;

forming a plurality of planes in response to the selection of the single point, each plane of the plurality of planes passing through the single point and defining a cross section of the object thereon;

calculating a characteristic of each cross section defined by the plurality of planes;

selecting a plane of the plurality of planes based on the calculated characteristics; and

classifying the second segmentation class along the selected plane.

12. The method of claim 11, wherein calculating a characteristic of each cross section comprises calculating an area of a contiguous portion of each cross section defined by the plurality of planes.

13. The method of claim 11, wherein selecting a plane of the plurality of planes comprises selecting a plane defining a minimum cross sectional area of a contiguous portion of the object.

14. The method of claim 11, wherein the first segmentation class corresponds to at least one of a parenchyma, a vessel, and a chest wall, and the second segmentation class corresponds to a lesion.

15. The method of claim 11, further including forming a three-dimensional rendering of the object comprising a target portion and a remainder portion connected by the selected plane.

16. The method of claim 15, further including rendering the remainder portion transparent such that only the target portion is displayed in the three-dimensional rendering.

17. A digital image editing method, comprising:

receiving a three-dimensional volume image of an anatomical object of interest, wherein the volume image is characterized by first and second mutually exclusive segmentation classes;

deriving a three-dimensional view from the volume image;

selecting a single point on the three-dimensional view within the second segmentation class; and

defining a plane in response to the selection of the single point, the plane dividing the second segmentation class into a target portion corresponding to the object and a remainder portion.

18. The method of claim 17, wherein the first segmentation class corresponds to a parenchyma and the second segmentation class corresponds to a lesion connected to one of a vessel and a chest wall.

19. The method of claim 17, further including identifying an additional point on the three-dimensional view, the single point and the additional point both being disposed on the plane.

20. The method of claim 19, wherein the additional point lies along a line of sight vector passing through the single point.