Medical image processing apparatus and method

• US 10,445,891 B2
• Filed: 11/03/2017
• Issued: 10/15/2019
• Est. Priority Date: 11/03/2017
• Status: Active Grant

• Current Assignee: Canon Medical Systems Corporation (Canon Inc.)
• Original Assignee: Canon Medical Systems Corporation (Canon Inc.)
• Inventors: Wyeth, Daniel Lee Catherwood
• Primary Examiner(s): Thirugnanam, Gandhi
• Application Number:
  US15/802,675
• Publication Number:
  US 20190139238A1
• Time in Patent Office: 711 Days
• CPC Class Codes: A61B 5/055 involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
• CPC Class Codes: A61B 6/032 Transmission computed tomography [CT]
• CPC Class Codes: A61B 6/037 Emission tomography
• CPC Class Codes: A61B 6/4085 Cone-beams
• 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: A61B 8/5238 for combining image data of patient, e.g. merging several images from different acquisition modes into one image for image registration algorithms G06T7/30
• CPC Class Codes: G06T 2207/10081 Computed x-ray tomography [CT]
• CPC Class Codes: G06T 2207/30008 Bone
• CPC Class Codes: G06T 3/02 Affine transformations for image registration G06T3/147; for image mosaicing G06T3/4038
• CPC Class Codes: G06T 3/10 Selection of transformation methods according to the characteristics of the input images
• CPC Class Codes: G06T 7/33 using feature-based methods
• CPC Class Codes: G06T 7/337 involving reference images or patches
• CPC Class Codes: G06T 7/35 using statistical methods
• CPC Class Codes: G06T 7/37 using transform domain methods
• CPC Class Codes: G06T 7/74 involving reference images or patches

Abstract

An apparatus comprises processing circuitry configured to: obtain medical imaging data that is representative of an anatomical region of a subject, the anatomical region comprising at least one anatomical feature of interest; obtain a template that is representative of a desired view of the at least one anatomical feature of interest; register the medical imaging data and reference anatomical data to obtain a distribution of registration probability with respect to at least one registration parameter; and perform a selection process comprising: obtaining a plurality of transforms, each having an associated registration; for each of the plurality of transforms: generating a respective view of the at least one anatomical feature of interest based on said transform; and determining a template matching probability that represents a similarity of the generated view to the template; and selecting at least one of the transforms and/or at least one of the views based on a combination of at least one of the registration probabilities with at least one of the template matching probabilities.

Claims

1. An apparatus comprising processing circuitry configured to:

obtain medical imaging data that is representative of an anatomical region of a subject, the anatomical region comprising at least one anatomical feature of interest;

obtain a template that is representative of a desired view of the at least one anatomical feature of interest;

register the medical imaging data and reference anatomical data to obtain a distribution of registration probability with respect to at least one registration parameter; and

perform a selection process comprising;

obtaining a plurality of transforms, each having an associated registration probability;

for each of the plurality of transforms;

generating a respective view of the at least one anatomical feature of interest based on said transform; and

determining a template matching probability that represents a similarity of the generated view to the template; and

selecting at least one of the transforms and/or at least one of the views based on a combination of at least one of the registration probabilities with at least one of the template matching probabilities.

2. An apparatus according to claim 1, further comprising a display device, wherein the processing circuitry is further configured to display the selected at least one view on the display device.

3. An apparatus according to claim 1, wherein the selection process comprises obtaining the plurality of transforms based on the distribution of registration probability.

4. An apparatus according to claim 1, wherein the obtaining of the plurality of registrations comprises selecting a transform having a highest registration probability, and adjusting at least one registration parameter of the selected transform to obtain further registrations.

5. An apparatus according to claim 1, wherein selecting at least one of the registrations and/or at least one of the views based on a combination of at least one of the registration probabilities and at least one of the template matching probabilities comprises selecting the at least one of the registrations and/or at least one of the views based on a joint probability for each of the plurality of registrations.

6. An apparatus according to claim 1, wherein the processing circuitry is further configured to perform a plurality of iterations of the selection process.

7. An apparatus according to claim 6, wherein each iteration of the selection process comprises:

obtaining a plurality of further transforms based on at least one transform and/or view selected in the previous iteration;

for each of the plurality of further transforms;

generating a respective view of the at least one anatomical feature of interest based on said further transform; and

determining a template matching probability that represents a similarity of the generated view to the template; and

selecting at least one of the plurality of further transforms and/or at least one of the views generated from the further transforms based on a combination of at least one of the registration probabilities for the further transforms with at least one of the template matching probabilities for the further transforms.

8. An apparatus according to claim 6, wherein processing circuitry is configured to perform the iterations of the selection process until a convergence condition is met.

9. An apparatus according to claim 1, wherein the distribution of registration probabilities is used to guide a search over candidate transforms.

10. An apparatus according to claim 9, wherein the search over candidate transforms comprises a gradient descent search.

11. An apparatus according to claim 1, wherein each respective view of the at least one anatomical feature comprises a respective oblique reformat.

12. An apparatus according to claim 1, wherein each transform comprises an affine transform.

13. An apparatus according to claim 1, wherein at least some of the transforms each comprise anisotropic scaling.

14. An apparatus according to claim 1, the registering of the medical imaging data and the reference anatomical data comprising mapping a plurality of landmarks in the medical imaging data with corresponding reference landmarks in the reference anatomical data.

15. An apparatus according to claim 1, wherein the reference anatomical data comprises at least one of:

atlas data, virtual anatomy data.

16. An apparatus according to claim 1, wherein, for each transform, the determining of the template matching probability for said transform comprises obtaining a distance map of the respective view by locating at least one edge within the view image and determining, for each of a plurality of pixels in the view, a distance to the at least one edge, and comparing the distance map of the respective view with a distance map of the template.

17. An apparatus according to claim 1, wherein the at least one anatomical feature of interest comprises a joint.

18. An apparatus according to claim 17, wherein the joint comprises at least one of a knee, a shoulder, an elbow, a wrist, an ankle, a hip joint.

19. An apparatus according to claim 1, wherein the medical imaging data comprises at least one of CT data, cone-beam CT data, MR data, X-ray data, ultrasound data, PET data or SPECT data.

20. A method comprising:

obtaining medical imaging data that is representative of an anatomical region of a subject, the anatomical region comprising at least one anatomical feature of interest;

obtaining a template that is representative of a desired view of the at least one anatomical feature of interest;

registering the medical imaging data and reference anatomical data to obtain a distribution of registration probability with respect to at least one registration parameter; and

performing a selection process comprising;

obtaining a plurality of transforms, each having an associated registration probability;

for each of the plurality of registrations;

generating a respective view of the at least one anatomical feature of interest based on said transform; and

determining a template matching probability that represents a similarity of the generated view to the template; and

selecting at least one of the transforms and/or at least one of the views based on a combination of at least one of the registration probabilities with at least one of the template matching probabilities.