IMAGE FUSION WITH AUTOMATED COMPENSATION FOR BRAIN DEFORMATION

• US 20140161338A1
• Filed: 12/10/2013
• Published: 06/12/2014
• Est. Priority Date: 12/10/2012
• Status: Active Grant

• Current Assignee: Cleveland Clinic Foundation
• Original Assignee: Cleveland Clinic Foundation
• Inventors: Machado, Andre G.
• Granted Patent: US 9,269,140 B2
• Time in Patent Office: Days
• US Class Current: 382/131
• CPC Class Codes: A61B 2576/026 for the brain
• CPC Class Codes: A61B 5/0042 for the brain
• CPC Class Codes: G06T 2207/10072 Tomographic images
• CPC Class Codes: G06T 2207/10081 Computed x-ray tomography [CT]
• CPC Class Codes: G06T 2207/10088 Magnetic resonance imaging [MRI]
• CPC Class Codes: G06T 2207/20221 Image fusion; Image merging
• CPC Class Codes: G06T 2207/30016 Brain
• CPC Class Codes: G06T 2207/30096 Tumor; Lesion
• CPC Class Codes: G06T 3/14 Transformations for image registration, e.g. adjusting or mapping for alignment of images
• CPC Class Codes: G06T 3/18 Image warping, e.g. rearranging pixels individually
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06T 7/0016 involving temporal comparison
• CPC Class Codes: G06T 7/344 involving models
• CPC Class Codes: G16H 30/40 for processing medical images, e.g. editing

Abstract

A system can include a model to represent a volumetric deformation of a brain corresponding to brain tissue that has been displaced by at least one of disease, surgery or anatomical changes. A fusion engine can perform a coarse and/or fine fusion to align a first image of the brain with respect to a second image of the brain after a region of the brain has been displaced and to employ the deformation model to adjust one or more points on a displacement vector extending through a displaced region of the brain to compensate for spatial deformations that occur between the first and second image of the brain.

Claims

1. A system, comprising:

a model to represent a volumetric deformation of a brain corresponding to brain tissue that has been displaced or shifted by at least one of disease, surgery or anatomical changes; and

a fusion engine to perform a coarse fusion to align a first image of the brain with respect to a second image of the brain after a region of the brain has been displaced and to employ the model to adjust one or more points on a displacement vector extending through a displaced region of the brain to compensate for spatial deformations that occur between the first and second image of the brain.

2. The system of claim 1, further comprising a fiducial marker in the brain image, the fusion engine being programmed to employ the fiducial marker with the volumetric analysis of the model and apply to the brain image to compensate for distortion in the brain image for at least one spatial region of interest selected in response to a user input.

3. The system of claim 2, wherein the fiducial marker is selected in the brain image in response to a user input or an automated system.

4. The system of claim 1, wherein the brain image includes at least one landmark or fiducial marker, the fusion engine is programmed to apply the volumetric analysis of the model and the at least one landmark or fiducial marker to the brain image to compensate further for distortion in the brain image in relation to at least one other image.

5. The system of claim 1, wherein the fusion engine is programmed to fuse or co-register the first image of the brain with the second image of the brain based on the model.

6. The system of claim 5, wherein the model and the fusion engine are employed to fuse or co-register the second image of the brain with a brain atlas to provide an adjusted brain atlas.

7. The system of claim 6, further comprising a vector calculator configured to determine a displacement vector for each pixel or voxel in the second image of the brain and transform each pixel or voxel into a coordinate system of a stereotactic system.

8. The system claim of 7, wherein the fusion engine processes at least one image event that includes at least one of a location of a fiducial marker, a foreign body inserted in the brain, and an anatomical structure after anatomical displacement.

9. The system of claim 8, wherein the image event is correlated or co-registered with a corresponding location in images acquired before the anatomical displacement occurred or after the anatomical displacement has resolved partially or completely.

10. The system claim of 9, wherein the fusion engine compensates for a structural shift that includes a brain shift associated with surgical procedures.

11. The system of claim 1, wherein the fusion engine determines an initial volume for at least one selected anatomic region in a first three-dimensional brain image for a patient and determines another volume for the at least one selected anatomic region in a second three-dimensional brain image for the patient.

12. The system of claim 11, wherein the fusion engine computes shrinkage or growth factors from the first three-dimensional brain image based on a difference between the initial volume and the another volume for the at least one selected anatomic region and generates a mapping between the first and second three-dimensional brain images based on the computed shrinkage or growth factors and at least one volume parameter for the brain to provide feedback that compensates for distortion between the first and second three-dimensional brain images.

13. A method comprising:

determining an initial volume for at least one selected anatomic region in a first three-dimensional brain image for a patient;

determining another volume for the at least one selected anatomic region in a second three-dimensional brain image for the patient;

computing shrinkage or growth factors from the first three-dimensional brain image based on a difference between the initial volume and the another volume for the at least one selected anatomic region; and

generating a mapping between the first and second three-dimensional brain images based on the computed shrinkage or growth factors and at least one volume parameter for the brain that compensates for distortion between the first and second three-dimensional brain images.

14. The method of claim 13, wherein the at least one selected anatomic region comprises at least one of a ventricular region, a subarachnoid region, a cortical region and a subcortical region.

15. The method of claim 13, further comprising utilizing one or more fiducial markers or landmarks to characterize inhomogeneities in anatomy or inhomogenities in a vector of displacement and align images from a digitized atlas and a brain image.

16. A method, comprising:

accessing a first image data of an anatomical feature and second image data of the anatomical feature;

performing a non-rigid alignment between the first image data and the second image data; and

generating a vector field mapping based on the non-rigid alignment to provide displacement data to a user regarding displacement between the first image and the second image data.

17. The method of claim 16, further comprising performing a rigid alignment between the first image data and the second image data to generate a rigidly aligned image.

18. The method of claim 17, wherein the rigid alignment or the non-rigid alignment includes at least one of a normalized mutual information correlation metric, a gradient descent optimization, and a linear interpolation between images.

19. The method of claim 18, wherein the non-rigid registration divides the images into a lattice and iteratively evaluates and optimizes correlation metrics for each cell in the lattice.

20. The method of claim 18, wherein the non-rigid registration employs intermediate results to adjust a continuous nonlinear mapping between the first image data and the second image data which is used to generate the correlation metrics.

21. The method of claim 16, further comprising generating a model which describes how the anatomical feature shifts over time and employing the model to update the vector field mapping over time.

22. The method of claim 16, further comprising determining an initial volume for at least one selected anatomic region in a first three-dimensional brain image for a patient and determining another volume for the at least one selected anatomic region in a second three-dimensional brain image for the patient.

23. The method of claim 22, further comprising computing a shrinkage or growth factors from the first three-dimensional brain image based on a difference between the initial volume and the another volume for the at least one selected anatomic region and generating a mapping between the first and second three-dimensional brain images based on the computed shrinkage or growth factors and at least one volume parameter for the brain to provide feedback that compensates for distortion between the first and second three-dimensional brain images.