Method and system for performing image registration

• US 7,995,864 B2
• Filed: 07/03/2007
• Issued: 08/09/2011
• Est. Priority Date: 07/03/2007
• Status: Active Grant

• Current Assignee: General Electric Company
• Original Assignee: General Electric Company
• Inventors: Ranjan, Sohan Rashmi, Mullick, Rakesh
• Primary Examiner(s): Mehta; Bhavesh M
• Assistant Examiner(s): Koziol; Stephen R
• Application Number:
  US11/772,975
• Publication Number:
  US 20090010540A1
• Time in Patent Office: 1,498 Days
• Field of Search: 382/131, 382/170, 382/294
• US Class Current: 382/294
• CPC Class Codes: G06T 7/38 Registration of image sequences

Abstract

A method for performing image registration is provided. The method comprises obtaining a reference image dataset and a target image dataset and defining an image mask for a region of interest in the reference image dataset. The method further comprises registering a corresponding region of interest in the target image dataset with the image mask, using a similarity metric, wherein the similarity metric is computed based on one or more voxels in the region of interest defined by the image mask.

Claims

1. A method for performing image registration, comprising the steps of:

obtaining a reference image dataset and at least one other target image dataset;

defining an image mask for a region of interest in the reference image dataset;

differently weighting respective sub-regions within the image mask, wherein each sub-region corresponds to a different respective anatomical structure; and

registering a corresponding region of interest in the at least one other target image dataset with the image mask, using a similarity metric, wherein the similarity metric is computed based on one or more voxels in the region of interest defined by the image mask and using the respective weights associated with each voxel.

2. The method of claim 1, wherein the reference image dataset and the at least one other target image dataset is acquired via an imaging system, wherein the imaging system comprises at least one of a computed tomography (CT) imaging system, a positron emission tomography (PET) imaging system, a magnetic resonance (MR) imaging system, an X-ray imaging system, an ultrasound imaging system, or combinations thereof.

3. The method of claim 2, wherein the reference image dataset is acquired via a first imaging modality and the at least one other target image dataset is acquired via a second imaging modality, where the second imaging modality is different from the first imaging modality.

4. The method of claim 2, wherein the reference image dataset and the at least one other target image dataset are acquired via a same imaging modality at different points in time.

5. The method of claim 2, wherein the reference image dataset and the at least one other target image dataset comprise at least one of anatomical information and functional information.

6. The method of claim 5, wherein the reference image dataset comprises anatomical information acquired using a computed tomography (CT) imaging modality and the at least one other target image dataset comprises functional information acquired using a positron emission tomography (PET) imaging modality.

7. The method of claim 1, wherein computing the similarity metric comprises sampling one or more of the voxels in the region of interest defined by the image mask.

8. The method of claim 1, comprising automatically segmenting the region of interest in the reference image dataset to define the image mask.

9. The method of claim 1, comprising automatically registering the reference image dataset using an atlas-based localization technique, to define the image mask.

10. The method of claim 1, comprising permitting a user to define the image mask for the region of interest in the reference image dataset.

11. The method of claim 1, wherein the similarity metric comprises at least one of mutual information (MI), contrast measure, minimizing means-squared error, correlation ratio, ratio image uniformity (RIU), normalized mutual information (NMI), joint histogram, and joint entropy.

12. The method of claim 1, further comprising applying at least one of a rigid transform and a non-rigid transform to register the region of interest in the at least one other target image dataset with the image mask in the reference image dataset.

13. The method of claim 1, further comprising generating a registered image.

14. The method of claim 13, further displaying the registered image to a user.

15. A system, comprising:

at least one imaging system configured to obtain a reference image dataset and at least one other target image dataset; and

a processing module in communication with the at least one imaging system and configured to define an image mask for a region of interest in the reference image dataset, to differently weight respective sub-regions within the image mask, wherein each sub-region corresponds to a different respective anatomical structure, and to register a corresponding region of interest in the at least one other target image dataset with the image mask, using a similarity metric, wherein the similarity metric is computed based on one or more voxels in the region of interest defined by the image mask and using the respective weights associated with each voxel.

16. The system of claim 15, wherein the imaging system comprises at least one of a computed tomography (CT) imaging system, a positron emission tomography (PET) imaging system, a magnetic resonance (MR) imaging system, an X-ray imaging system, an ultrasound imaging system, or combinations thereof.

17. The system of claim 16, wherein the reference image dataset is acquired via a first imaging modality and the at least one other target image dataset is acquired via a second imaging modality, where the second imaging modality is different from the first imaging modality.

18. The system of claim 16, wherein the reference image dataset and the at least one other target image dataset are acquired via the same imaging modality at different points in time.

19. The system of claim 16, wherein the reference image dataset and the at least one other target image dataset comprise at least one of anatomical information and functional information.

20. The system of claim 19, wherein the reference image dataset comprises anatomical information acquired using a computed tomography (CT) imaging modality and the at least one other target image dataset comprises functional information acquired using a positron emission tomography (PET) imaging modality.

21. The system of claim 15, wherein the processing module is configured to automatically segment the region of interest in the reference image dataset to define the image mask.

22. The system of claim 15, wherein the processing module is configured to automatically register the reference image dataset using an atlas-based localization technique, to define the image mask.

23. The system of claim 15, further comprising permitting a user to define the image mask for the region of interest in the reference image dataset.

24. The system of claim 15, wherein the processing module is configured to apply at least one of a rigid transform and a non-rigid transform to register the region of interest in the at least one other target image dataset with the image mask in the reference image dataset.

25. The system of claim 15, wherein the processing module is further configured to generate a registered image.

26. The system of claim 25, wherein the system further comprises a display module configured to display the generated registered image.