EFFICIENT USER INTERACTION WITH POLYGONAL MESHES FOR MEDICAL IMAGE SEGMENTATION

• US 20090310835A1
• Filed: 07/02/2007
• Published: 12/17/2009
• Est. Priority Date: 07/17/2006
• Status: Active Grant

• Current Assignee: Koninklijke Philips Electronics N.V. (Koninklijke Philips N.V.), University Health Network
• Original Assignee: Koninklijke Philips Electronics N.V. (Koninklijke Philips N.V.)
• Inventors: Dawson, Laura A., Kaus, Michael R.
• Granted Patent: US 8,660,325 B2
• Time in Patent Office: Days
• US Class Current: 382/128
• CPC Class Codes: G06T 17/20 Finite element generation, e.g. wire-frame surface description, tesselation
• CPC Class Codes: G06T 2207/10072 Tomographic images
• CPC Class Codes: G06T 2207/30012 Spine; Backbone
• CPC Class Codes: G06T 2207/30096 Tumor; Lesion
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06T 7/12 Edge-based segmentation
• CPC Class Codes: G06T 7/149 involving deformable models, e.g. active contour models

Abstract

An apparatus for delineating a structure of interest includes: a plane selection interface (32, 70) for selecting a contouring plane of selectable orientation in a three-dimensional image or map (80); a contouring interface (32, 72) for defining a contour in the selected contour plane; and a mesh constructor (74, 76) configured to construct a three-dimensional polygonal mesh (90) delineating the structure of interest in the three-dimensional image or map. The mesh constructor positions constrained vertices (102, Vc) on or near a plurality of non-coplanar delineation contours (84, Ccor, Cobl) defined using the contouring interface.

Claims

1. A method of delineating a structure of interest in a three-dimensional image or map, the method comprising:

defining at least two contours delineating the structure of interest, the at least two contours lying in at least two different contouring planes that are different and non-parallel respective to each other; and

fitting a three-dimensional polygonal mesh while respecting the defined contours as constraints on vertices of the polygonal mesh.

2. The method as set forth in claim 1, further including:

identifying a sub-set of vertices of the three-dimensional polygonal mesh as constrained vertices to be positioned at or near the defined contours.

3. The method as set forth in claim 2, wherein the identifying includes:

identifying the sub-set of vertices based on minimum vertex distance from the at least two contours.

4. The method as set forth in claim 3, wherein the fitting is an iterative deformation process, and the identifying is repeated for each iteration of the deforming.

5. The method as set forth in claim 4, wherein the sub-set of vertices identified as constrained vertices changes between at least two successive iterations of the iterative deforming process.

6. The method as set forth in claim 3, wherein the minimum distance used for the selecting is defined by a Euclidean distance transform.

7. The method as set forth in claim 3, wherein the fitting employs an energy or force minimization deformation process, and the selected constraints on the constrained vertices respective to the at least two contours include:

incorporating a constraint energy or force term for each constrained vertex, the constraint energy or force term being dependent upon the minimum vertex distance from the at least two contours.

8. The method as set forth in claim 7, wherein the energy or force minimization deformation process further includes contrast-based energy or force terms derived from contrast delineating at least a portion of the structure of interest in the three-dimensional image or map.

9. The method as set forth in claim 8, wherein the energy or force minimization deformation process further includes deformation energy or force terms derived from an extent of deformation of the three-dimensional polygonal mesh from a default mesh configuration.

10. The method as set forth in claim 3, wherein the fitting includes:

projecting each constrained vertex onto a nearest of the at least two contours.

11. The method as set forth in claim 2, wherein the fitting includes:

minimizing a combination of force or energy terms including at least (i) constraint force or energy terms related to minimum distances of the constrained vertices from the at least two contours and (ii) deformation energy or force terms related to deviation of the three-dimensional polygonal mesh from a default mesh configuration.

12. The method as set forth in claim 1, wherein the defining comprises:

selecting the at least two different contouring planes from the group of planes consisting of sagittal, coronal, and axial planes.

13. The method as set forth in claim 1, wherein the defining comprises:

selecting the at least two different contouring planes including at least one oblique plane not belonging to the group of planes consisting of sagittal, coronal, and axial planes.

14. An apparatus comprising:

a plane selection interface for selecting a contouring plane of selectable orientation in a three-dimensional image or map;

a contouring interface for defining a contour in the selected contour plane; and

a mesh constructor configured to construct a three-dimensional polygonal mesh delineating a structure of interest in the three-dimensional image or map, the mesh constructor positioning constrained vertices on or near a plurality of non-coplanar delineation contours defined using the contouring interface.

15. The apparatus as set forth in claim 14, wherein the mesh constructor positions the constrained vertices on the non-coplanar delineation contours.

16. The apparatus as set forth in claim 14, wherein the mesh constructor includes:

a mesh optimizer that deforms the three-dimensional polygonal mesh with the deforming biased to position each constrained vertex on or near a closest non-coplanar delineation contour.

17. The apparatus as set forth in claim 14, further including:

a pointing device; and

a display;

the pointing device and the display being components of each of the plane selection interface and the contouring interface.

18. The apparatus as set forth in claim 14, further including:

a planning processor configured to plan a radiotherapy session based on the three-dimensional image or map and the constructed three-dimensional polygonal mesh delineating the structure of interest in the three-dimensional image or map.

19. The apparatus as set forth in claim 18, further including:

a radiotherapy system for performing the planned radiotherapy session.

20. The apparatus as set forth in claim 14, wherein the plane selection interface is configured to enable manual selecting of an axial, sagittal, or coronal contouring plane, and the contouring interface is configured to enable manual defining of a contour in said axial, sagittal, or coronal contouring plane.

21. The apparatus as set forth in claim 20, wherein the plane selection interface is further configured to enable manual selecting of an oblique contouring plane that is not an axial, sagittal, or coronal plane, and the contouring interface is configured to enable manual defining of a contour in said oblique contouring plane.

22. An apparatus operative in conjunction with an adaptive treatment process, the apparatus comprising:

a segmenting processor configured to delineate a structure, the segmenting processor including (i) a contouring interface configured to define structure-delineating contours in at least two different, non-parallel contouring planes, and (ii) a mesh constructor for constructing a three-dimensional polygonal mesh using a mesh deformation process constrained at least by the defined structure-delineating contours; and

a planning processor configured to identify parameters for adaptive treatment of a subject based on delineation via the segmenting processor of at least one structure of interest in a three-dimensional image or map of the subject.

23. The apparatus as set forth in claim 22, wherein the planning processor includes:

an inverse planning processor for determining beamlet parameters for delivering a selected radiation profile to the subject; and

a conversion processor for converting the beamlet parameters into control parameters for an intensity modulated radiotherapy system.

24. The apparatus as set forth in claim 23, further including:

said intensity modulated radiotherapy system configured to deliver radiation to the subject in accordance with said control parameters.

25. The apparatus as set forth in claim 22, wherein the segmenting processor and the planning processor are configured to be reapplied for subsequent adaptive treatment sessions to adjust the parameters for adaptive treatment between sessions.