Techniques for example-based affine registration

• US 10,607,108 B2
• Filed: 04/30/2018
• Issued: 03/31/2020
• Est. Priority Date: 04/30/2018
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Wang, Hongzhi, Karargyris, Alexandros
• Primary Examiner(s): Kassa, Yosef
• Application Number:
  US15/966,993
• Publication Number:
  US 20190332890A1
• Time in Patent Office: 701 Days
• CPC Class Codes: G06F 18/214 Generating training patterns; Bootstrap methods, e.g. bagging or boosting
• CPC Class Codes: G06T 3/147 using affine transformations
• CPC Class Codes: G06V 10/242 by image rotation, e.g. by 90 degrees
• CPC Class Codes: G06V 10/26 Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
• CPC Class Codes: G06V 2201/03 Recognition of patterns in medical or anatomical images

Abstract

Example-based affine registration is provided. In various embodiments, a plurality of training images is read. A predetermined affine transform is read for each of the plurality of training images. Each affine transform maps its associated image to a template. Weights are determined for each of the plurality of training images. The weights are determined to minimize a difference between the test image and a weighted linear combination of the training images. An affine transform is determined mapping the test image to the template by computing a weighted linear combination of the affine transforms using the weights.

Claims

1. A method comprising:

reading a plurality of training images;

reading a predetermined affine transform for each of the plurality of training images, each affine transform mapping its associated image to a template;

determining weights for each of the plurality of training images, the weights being determined to minimize a difference between the test image and a weighted linear combination of the training images;

determining an affine transform mapping the test image to the template by computing a weighted linear combination of the affine transforms using the weights.

2. The method of claim 1, wherein determining the weights comprises:

computing a covariance matrix for the training images.

3. The method of claim 2 further comprising:

discarding all training images having negative weights.

4. The method of claim 1, further comprising:

providing the affine transform as an initialization to a second registration algorithm.

5. The method of claim 4, wherein the second registration algorithm is an optimization-based algorithm.

6. The method of claim 5, wherein the optimization-based algorithm comprises Advanced Normalization Tools.

7. The method of claim 4, wherein the second registration algorithm is a deformable registration algorithm.

8. The method of claim 1, wherein the test image is two-dimensional.

9. The method of claim 1, wherein the test image is three-dimensional.

10. A system comprising:

a computing node comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor of the computing node to cause the processor to perform a method comprising;

reading a plurality of training images;

reading a predetermined affine transform for each of the plurality of training images, each affine transform mapping its associated image to a template;

determining weights for each of the plurality of training images, the weights being determined to minimize a difference between the test image and a weighted linear combination of the training images;

determining an affine transform mapping the test image to the template by computing a weighted linear combination of the affine transforms using the weights.

11. The system of claim 10, wherein determining the weights comprises:

computing a covariance matrix for the training images.

12. The system of claim 11, the method further comprising:

discarding all training images having negative weights.

13. The system of claim 10, the method further comprising:

providing the affine transform as an initialization to a second registration algorithm.

14. The system of claim 13, wherein the second registration algorithm is an optimization-based algorithm.

15. The system of claim 14, wherein the optimization-based algorithm comprises Advanced Normalization Tools.

16. The system of claim 13, wherein the second registration algorithm is a deformable registration algorithm.

17. The system of claim 10, wherein the test image is two-dimensional.

18. The system of claim 10, wherein the test image is three-dimensional.

19. A computer program product for affine registration, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to perform a method comprising:

reading a plurality of training images;

reading a predetermined affine transform for each of the plurality of training images, each affine transform mapping its associated image to a template;

determining weights for each of the plurality of training images, the weights being determined to minimize a difference between the test image and a weighted linear combination of the training images;

determining an affine transform mapping the test image to the template by computing a weighted linear combination of the affine transforms using the weights.

20. The computer program product of claim 19, the method further comprising:

providing the affine transform as an initialization to a second registration algorithm.