USE OF COLLECTION OF PLANS TO DEVELOP NEW OPTIMIZATION OBJECTIVES

• US 20120280135A1
• Filed: 11/18/2010
• Published: 11/08/2012
• Est. Priority Date: 12/16/2009
• Status: Active Grant

• Current Assignee: Koninklijke Philips N.V.
• Original Assignee: Koninklijke Philips Electronics N.V. (Koninklijke Philips N.V.)
• Inventors: Bal, Matthieu
• Granted Patent: US 9,076,222 B2
• Time in Patent Office: Days
• US Class Current: 250/395
• CPC Class Codes: A61B 5/0036 including treatment, e.g., using an implantable medical device, ablating, ventilating
• CPC Class Codes: A61B 5/004 adapted for image acquisition of a particular organ or body part A61B5/0082 takes precedence; arrangements for optical scanning A61B5/0062
• CPC Class Codes: A61B 6/52 Devices using data or image processing specially adapted for radiation diagnosis
• CPC Class Codes: A61B 6/5211 involving processing of medical diagnostic data
• CPC Class Codes: A61B 6/5229 combining image data of a patient, e.g. combining a functional image with an anatomical image
• CPC Class Codes: A61N 5/103 Treatment planning systems
• CPC Class Codes: A61N 5/1039 using functional images, e.g. PET or MRI
• CPC Class Codes: G06T 2207/10072 Tomographic images
• CPC Class Codes: G06T 2207/30096 Tumor; Lesion
• CPC Class Codes: G06T 7/12 Edge-based segmentation

Abstract

A radiation therapy system includes a diagnostic image scanner (12) which acquires a multidimensional dataset of a subject that is reconstructed into at least one image representation of an object of interest. An image processing apparatus (72), of radiation therapy system, includes a segmentation unit (74) which identifies a surface contour of the object of interest, or other critical structures. A masking unit (82) determines a non-constant margin, based on the identified surface contour and appends the determined non-constant margin to the identified surface contour. The non-constant margin is based on at least one of anisotropic motion, surface morphology, positional uncertainty, proximity to other organs, and probability of dose distribution. A planning processor (70) generates a radiation therapy plan which limits the delivery of therapeutic radiation to anatomy associated with the surface contour and appended non-constant margin. A radiation delivery system (40) delivers therapeutic radiation according to the generated plan.

Claims

1. A method for image segmentation of anatomical features, comprising:

identifying a surface contour of at least one object of interest from a multi-dimensional data set; and

determining a non-constant margin based on the identified surface contour, the non-constant contour being appended to the identified surface contour.

2. The method according to claim 1, wherein the non-constant margin is determined based on anisotropic surface motion of the object of interest.

3. The method according to claim 1, wherein the non-constant margin is determined based surface morphology of the object of interest.

4. The method according to claim 1, further including:

identifying a surface model based on the surface contour; and

determining the non-constant margin based on the surface model.

5. The method according to claim 4, wherein the surface model includes a plurality of surface elements which define a surface of the surface model, each surface element describes a width and a weight factor of a portion of the non-constant margin corresponding to that surface element.

6. The method according to claim 4, wherein the step identifies a surface model further comprising:

matching an surface model to the surface contour of the at least one object of interest; and

adapting a surface of the surface model to correspond to the geometry of the surface contour of the at least one object of interest.

7. The method according to claim 6, wherein matching the surface model to the surface contour of the at least one object of interest is based on at least one of position, morphology, motion, or functionality of the object of interest.

8. A method for radiation therapy, comprising:

acquiring a multidimensional dataset of a subject;

reconstructing the multidimensional dataset into at least one image representation of at least one anatomical feature of the subject;

segmenting the image representation according to the method of claim 1;

generating a radiation therapy plan according to the segmented image representation, the radiation plan limits the delivery of therapeutic radiation to within the identified surface contour of the anatomical feature and the appended non-constant margin; and

delivering therapeutic radiation according to the generated radiation therapy plan.

9. A computer readable medium carrying a computer program which controls a processor to perform the method of claim 1.

10. A radiation therapy system, comprising:

a diagnostic imaging scanner;

a radiation delivery system; and

a radiation therapy planning processor programmed to perform the method according to claim 1.

11. An image processing apparatus, comprising:

a segmentation unit which identifies a surface contour of at least one object of interest from a multi-dimensional data set; and

a masking unit which determines a non-constant margin based on the identified surface contour and appends the determined non-constant margin to the identified surface contour.

12. The image processing apparatus according to claim 11, further comprising:

an identification unit which identifies a surface model, selected from a surface model database, based on the identified surface contour.

13. The image processing apparatus according to claim 11, wherein the non-constant margin is based on at least one of anisotropic motion, surface morphology, positional uncertainty, proximity to other organs, and probability of dose distribution.

14. The image processing apparatus according to claim 12, wherein the surface model includes a plurality of surface elements which define a surface of the surface model, each surface element describes a width and a weight factor of a portion of the non-constant margin corresponding to that surface element.

15. The image processing apparatus according to claim 12, further including:

a deformation unit which matches the surface model to the surface contour of the at least one object of interest and adapts a surface of the surface model to correspond to the geometry of the surface contour of the at least one object of interest.

16. The image processing apparatus according to claim 15, wherein matching the surface model to the surface contour of the at least one object of interest is based on at least one of position, morphology, motion, or functionality of the object of interest.

17. The image processing apparatus according to claim 14, wherein the surface model is a surface mesh model and each surface element is a polygonal mesh element.

18. A radiation therapy system, comprising:

an image scanner which acquires a multidimensional dataset of a subject and generates at least one image representation of an object of interest from the multidimensional dataset; and

an image processing apparatus according to claim 11.

19. The radiation therapy system according to claim 18, further including:

a planning processor which generates a radiation therapy plan according to the segmented image representation, the radiation plan limits the delivery of therapeutic radiation to within the identified surface contour of the anatomical feature and the appended non-constant margin; and

a radiation delivery system which delivers therapeutic radiation according to the generated radiation therapy plan.