Systems and methods for contouring a set of medical images

• US 10,599,948 B2
• Filed: 10/16/2017
• Issued: 03/24/2020
• Est. Priority Date: 05/03/2010
• Status: Active Grant

• Current Assignee: MIM Software Incorporated
• Original Assignee: MIM Software Incorporated
• Inventors: Piper, Jonathan William
• Primary Examiner(s): Chu, Randolph I
• Application Number:
  US15/784,857
• Publication Number:
  US 20190012567A1
• Time in Patent Office: 890 Days
• Field of Search: None
• CPC Class Codes: G06T 2207/10072 Tomographic images
• CPC Class Codes: G06T 2207/30004 Biomedical image processing
• CPC Class Codes: G06T 7/12 Edge-based segmentation
• CPC Class Codes: G06T 7/174 involving the use of two or more images
• CPC Class Codes: G06V 10/755 Deformable models or variational models, e.g. snakes or active contours

Abstract

Systems and methods are provided for contouring a set of medical images. Deformation field data is generated between a source image and a target image of the set of medical images. The deformation field data relates structures in the source image to corresponding structures in the target image and is generated in accordance with a deformable registration algorithm. The deformation field data is utilized to generate target contour data associated with the target image from source contour data, associated with the source image, that identifies one or more objects within the source image.

Claims

1. A method for contouring a medical image, comprising:

receiving a plurality of source images, wherein each source image of the plurality of source images is associated with a respective contour identifying one or more features of the source images;

generating deformation data for each source image, of the plurality of source images, to a target image;

generating a plurality of candidate contours for the target image based on the deformation data and respective contours associated with each source image of the plurality of source images; and

generating a target contour for the target image based on the plurality of candidate contours.

2. The method of claim 1, wherein generating the target contour comprises interpolating the target contour by combining the plurality of candidate contours.

3. The method of claim 1, wherein the target contour is an average of the plurality of target contours.

4. The method of claim 1, wherein the medical image is a three-dimensional medical image composed of a set of two-dimensional image slices, and wherein the plurality of source images and the target image are slices from the set of two-dimensional images slices.

5. The method of claim 4, wherein the plurality of source images are non-contiguous slices.

6. The method of claim 4, wherein generating deformation data for each source image to the target image comprises concatenating a series of registrations.

7. The method of claim 6, wherein the series of registrations include one or more image-to-image registrations of images between each source image and the target image in the set of two-dimensional image slices.

8. The method of claim 1, wherein generating deformation data for each source image to the target image comprises directly registering each source image to the target image to generate respective deformation data.

9. The method of claim 1, wherein generating the plurality of candidate contours comprises applying respective deformation data to the respective contour for each source image.

10. A system for contouring a medical image, comprising:

at least one processor; and

a non-transitory, computer-readable storage medium having stored thereon computer-executable instructions, the computer-executable instructions comprising;

an image deformation engine configured to;

receive a plurality of source images each of which is respectively associated with a contour; and

generate deformation data for each source image to a target image; and

a contour transformation engine configured to;

generate a plurality of candidate contours for the target image based on respective deformation data and respective contours associated with each source image; and

generate a target contour for the target image based on the plurality of candidate contours.

11. The system of claim 10, wherein the contour engine is further configured to interpolate the target contour by combining the plurality of candidate contours.

12. The system of claim 10, wherein the target contour is an average of the plurality of target contours.

13. The system of claim 10, wherein the medical image is a three-dimensional medical image composed of a set of two-dimensional image slices, and wherein the plurality of source images and the target image are slices from the set of two-dimensional images slices.

14. The system of claim 13, wherein the image deformation engine is further configured to concatenate a series of registrations to generate deformation data for each source image to the target image.

15. The system of claim 14, wherein the series of registrations include one or more image-to-image registrations of images between each source image and the target image in the set of two-dimensional image slices.

16. The system of claim 10, wherein the image deformation engine is further configured to directly register each source image to the target image to generate respective deformation data.

17. A non-transitory, computer-readable storage medium having stored thereon computer-executable instructions that, when executed by a processor of a computing device, configure the processor to:

generate deformation data for each source image of a plurality of source images to a target image, wherein each source image is associated with a respective contour identifying one or more features of the respective source image;

generate a plurality of candidate contours for the target image based on the deformation data and respective contours associated with each source image of the plurality of source images; and

generate a target contour for the target image based on the plurality of candidate contours.

18. The non-transitory, computer-readable storage medium of claim 17, wherein the computer-executable instructions further configure the processor to interpolate the target contour by combining the plurality of candidate contours.

19. The non-transitory, computer-readable storage medium of claim 17, wherein the computer-executable instructions further configure the processor to generate the target contour as an average of the plurality of target contours.

20. The non-transitory, computer-readable storage medium of claim 17, wherein the computer-executable instructions further configure the processor to apply respective deformation data to the respective contour for each source image to generate the plurality of candidate contours.