Systems, methods and devices for automated target volume generation

Patent metadata

Field	Value
Publication number	US-10918885-B2
Application number	US-201816144253-A
Country	US
Kind code	B2
Filing date	Sep 27, 2018
Priority date	Sep 27, 2018
Publication date	Feb 16, 2021
Grant date	Feb 16, 2021

Abstract

Systems and method for automatically generating structures, such as target volumes, in a treatment image using structure-guided deformation to propagate the structures from a planning image onto the subsequently acquired treatment image.

First claim

The invention claimed is:

1. A method for generating contours of anatomical structures in an image, comprising:
obtaining a first image including a first set of contour, the first set of contours delineating anatomical structures of a first set, and a second set of contours, the second set of contours delineating anatomical structures of a second set, the first and second set of contours being located at respective first locations in the first image;
obtaining a second image including the anatomical structures of the second set, and generating contours of the anatomical structures of the second set in the second image, the so generated second set of contours in the second image being located at a second location, the second location being different from the first location of the second set of contours from in the first image; and
propagating the first set of contours from the first image to the second image based on image registration that is guided by the second set of contours, the second image containing, after the propagating, the second set of contours and the propagated first set of contours,
wherein the anatomical structures in the second set includes anatomical structures that affect one or more anatomical structures in the first set.

2. The method of claim 1 , wherein the image registration is a deformable image registration.

3. The method of claim 2 , wherein the propagating includes applying a deformable registration algorithm that enables:
creating a first set of contours in the second image;
modifying the first set of contours in the second image based on the second set of contours in the second image;
generating one or more deformation vector fields (DVFs) based on the modifying; and
applying the one or more deformation vector fields (DVFs) to relate the first set of contours from the first image to the second image to generate the first set of contours in the second image.

4. The method of claim 3 , wherein a single deformation vector field (DVF) is used for the propagation.

5. The method of claim 3 , wherein a plurality of deformation vector fields (DVFs) are generated and used for the propagation.

6. The method of claim 3 , wherein the deformable registration algorithm further enables partially rigid deformations of one or more contours within the first set of contours.

7. The method of claim 1 , wherein the first set of contours including contours of one or more target volumes and one or more anatomical structures of interest, and the second set of contours including contours of one or more anatomical influencer structures.

8. The method of claim 7 , wherein the anatomical influencer structures include anatomical structures that influence one of a shape, size, or location of the one or more target volumes.

9. The method of claim 1 , wherein one or more contours of the second set of contours in the second image are generated by manual and/or automatic and/or a combination of manual and automatic delineation.

10. The method of claim 9 , wherein when automatic delineation is used, the method further comprises verifying that the delineation is acceptable.

11. The method of claim 1 , wherein the first image is a planning image, and the second image is a treatment session image.

12. The method of claim 11 , wherein the first and second images are generated from same or different imaging modalities.

13. The method of claim 1 , further comprising performing a treatment session on a subject based on image data of the second image including the first set of contours and the second set of contours.

14. The method of claim 13 , further comprising determining a treatment plan for the treatment session based on the image data of the second image.

15. The method of claim 3 , further comprising using the one or more deformation vector fields (DVFs) to determine radiation dose accumulation.

16. A system including a computer processing device configured to execute a sequence of programmed instructions embodied on a computer-readable storage medium, the execution thereof causing the system to:
obtain a first image including a first set of contours and a second set of contours, the first set of contours delineating anatomical structures of a first set, and the second set of contours delineating anatomical structures of a second set, the first and second set of contours being located at respective first locations in the first image;
obtain a second image including the anatomical structures of the second set, and generating a second set of contours in the second image by delineating the anatomical structure in the second image, the second set of contours being located at a second location in the second image, the second location being different from the first location of the second set of contours in the first image; and
propagate the first set of contours from the first image to the second image based on image registration that is guided by the second set of contours, the second image containing, after the propagating, the second set of contours and the propagating first set of contours,
wherein the anatomical structures in the second set includes anatomical structures that affect one or more anatomical structures in the first set.

17. The system of claim 16 , wherein the image registration is a deformable image registration and the propagating includes applying a deformable registration algorithm that enables:
creating the first set of contours in the second image;
modifying the first set of contours in the second image based on the second set of contours in the second image;
generating one or more deformation vector fields (DVFs) based on the modifying; and
applying the one or more deformation vector fields (DVFs) to relate the first set of contours from the first image onto the second image to generate the first set of contours in the second image.

18. The system of claim 17 , wherein the deformable registration algorithm further enables partially rigid deformations of one or more contours within the first set of contours.

19. The system of claim 17 , wherein the anatomical structures in the first set include one or more target volumes and one or more anatomical structures of interest, and the anatomical structures in the second set include one or more anatomical influencer structures, the influencer structures including anatomical structures that influence one of a shape, size, or location of the one or more target volumes.

20. The system of claim 17 , further comprising performing a treatment session on a subject based on image data of the second image including the first set of contours and the second set of contours and/or determining a treatment plan for a treatment session based on the image data of the second image.

21. A method for automatically generating a target volume in an image, comprising:
obtaining a first image including a contour of the target volume and a contour of an anatomical structure;
obtaining a second image including the contour of the anatomical structure; and
propagating the contour of the target volume from the first image to the second image using a deformable registration algorithm that matches the contour of the anatomical structure in the first image with the contour of the anatomical structure in the second image, the second image thereby containing the contour of the anatomical structure and the propagated contour of the target volume.

Assignees

• Varian Medical Systems Int Ag

Inventors

• Haas Benjamin
• Lessard Marco
• Honegger Jonas
• Coradi Thomas
• Gass Tobias
• MORGAS Tomasz

Classifications

• A61N2005/1055

  using magnetic resonance imaging [MRI] · CPC title

• G06T7/38

  Registration of image sequences · CPC title

• A61B6/03

  Computed tomography [CT] · CPC title

• G06T7/149

  involving deformable models, e.g. active contour models · CPC title

• A61N2005/1061

  using an x-ray imaging system having a separate imaging source · CPC title