Method, system and storage medium which includes instructions for analyzing anatomical structures

• US 20060025673A1
• Filed: 07/18/2005
• Published: 02/02/2006
• Est. Priority Date: 07/16/2004
• Status: Active Grant

• Current Assignee: New York University
• Original Assignee: New York University
• Inventors: Tsui, Wai-Hon, Mosconi, Lisa, Rusinek, Henry, De Leon, Mony J.
• Granted Patent: US 7,787,671 B2
• Time in Patent Office: Days
• US Class Current: 600/410
• CPC Class Codes: G06T 2207/10088 Magnetic resonance imaging [MRI]
• CPC Class Codes: G06T 2207/10104 Positron emission tomography [PET]
• CPC Class Codes: G06T 2207/20104 Interactive definition of region of interest [ROI]
• CPC Class Codes: G06T 2207/30016 Brain
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06T 7/12 Edge-based segmentation
• CPC Class Codes: G06T 7/143 involving probabilistic approaches, e.g. Markov random field [MRF] modelling
• CPC Class Codes: G06T 7/97 Determining parameters from multiple pictures depth or shape recovery from multiple images G06T7/55; stereo camera calibration G06T7/85

Abstract

A method, system and storage arrangement are provided for effectuating an evaluation and analysis of anatomical structures, and creating and/or modifying images associated therewith. In particular, at least two images associated with the anatomical structure can be normalized so as to produce normalized image. A normalized set of regions of interest can be obtained based on the normalized images. Each of the normalized set of regions of interest may be analyzed to provide analysis data. Further, the anatomical structure mask may be created and/or modified based on the analysis data. Another embodiment provides for rating and analyzing anatomical structures.

Claims

1. A method for at least one of creating or modifying an anatomical structure mask, comprising:

normalizing at least two images associated with the anatomical structure so as to produce normalized images;

obtaining a normalized set of regions of interest based on the normalized images;

analyzing each of the normalized set of regions of interest to provide analysis data; and

at least one of creating or modifying the anatomical structure mask based on the analysis data.

2. The method of claim 1, wherein the analyzing step comprises:

determining a percentage of overlap region for each of the normalized set of regions of interest; and

selectively iterating each of the normalized regions of interest through the first normalized set of regions of interest.

3. The method of claim 2, further comprising:

determining an optimal ratio of sensitivity to specificity for the normalized set of regions of interest; and

modifying the anatomical structure mask to account for the optimal ratio.

4. The method of claim 1, further comprising:

selecting a patient set;

generating the at least two images associated with the anatomical structure, each of the first set of images corresponding to a unique one of the patient set;

determining at least two regions of interest, each of the at least two regions of interest corresponding to a unique one of the at least two images and containing an image of the anatomical structure;

wherein

each of the normalized set of regions of interest correspond to a unique one of the at least two regions of interest.

5. The method of claim 1, wherein the anatomical structure is a brain.

6. The method of claim 5, wherein each of the normalized set of regions of interest includes a hippocampus.

7. The method of claim 5, wherein each of the normalized set of regions of interest includes an amygdala.

8. The method of claim 1, further comprising:

generating a template from each of the normalized images;

wherein the operation of obtaining a normalized set of regions of interest based on the normalized images comprises;

registering each of the normalized images to the template to create a set of registered images; and

extracting the normalized set of regions of interest from each of the registered images.

9. The method of claim 1, wherein the anatomical structure mask comprises a mask of an average anatomical structure.

10. The method of claim 9, wherein the mask of an average anatomical structure is derived from the at least two images.

11. The method of claim 1, wherein the at least two images are magnetic resonance images.

12. The method of claim 1, wherein the at least two images are positron-emission tomography images.

13. The method of claim 1, further comprising:

obtaining at least a third image;

registering the third image to one of the first or second images;

obtaining a region of interest corresponding to the third image; and

applying the anatomical structure mask to the region of interest corresponding to the third image.

14. The method of claim 13, further comprising normalizing the third image to a template.

15. The method of claim 14, wherein:

the at least two images are a first image type; and

the third image is a second image type.

16. The method of claim 15, wherein

the first image type is a magnetic resonance image;

and

the second image type is a positron-emission topography scan.

17. A system for at least one of creating or modifying an anatomical structure mask, comprising:

a processing arrangement which, when executing a software program, is capable of;

normalizing at least two images associated with the anatomical structure so as to produce normalized images;

obtaining a normalized set of regions of interest based on the normalized images;

analyzing each of the normalized set of regions of interest to provide analysis data; and

at least one of creating or modifying the anatomical structure mask based on the analysis data.

18. A storage medium comprising computer readable instructions which is provided for at least one of creating or modifying an anatomical structure mask, wherein, when a processing arrangement executes the instructions, the processing arrangement is configured to

normalize at least two images associated with the anatomical structure so as to produce normalized images;

obtain a normalized set of regions of interest based on the normalized images;

analyze each of the normalized set of regions of interest to provide analysis data; and

at least one of create or modify the anatomical structure mask based on the analysis data.

19. A method for classifying at least one image associated with at least one anatomical structure, comprising:

generating the least one image from the at least one anatomical structure;

selecting an axial plane intersecting the anatomical structure;

separating the at least one image approximately along the axial plane to produce a separated image; and

classifying the separated image according to a scale.

20. The method of claim 19, wherein the axial plane is a negative-angle axial plane.

21. The method of claim 19, wherein the axial plane is a pathological angle axial plane.

22. The method of claim 19, wherein the step of classifying the image according to a scale comprises visually classifying the image according to a scale.

23. The method of claim 22, wherein the scale comprises a system for rating a metabolism of the anatomical structure.

24. The method of claim 19, further comprising:

selecting a second axial plane intersecting the anatomical structure; and

separating the at least one image approximately along the second axial plane to produce a second separated image.

25. The method of claim 24, wherein the step of classifying the separated image according to a scale comprises:

classifying one of the separated image and the second separated image according to a scale.

26. The method of claim 25, further comprising evaluating a health of the anatomical structure in response to classifying the image.

27. The method of claim 19, wherein the anatomical structure is the brain.

28. The method of claim 19, wherein the operations are executed by a computer.

29. A system for at least one of creating or modifying an anatomical structure mask, comprising:

a processing arrangement which, when executing a software program, is capable of;

generating the least one image from the at least one anatomical structure;

selecting an axial plane intersecting the anatomical structure;

separating the at least one image approximately along the axial plane to produce a separated image; and

classifying the separated image according to a scale.

30. A storage medium comprising computer readable instructions which is provided for at least one of creating or modifying an anatomical structure mask, wherein, when a processing arrangement executes the instructions, the processing arrangement is configured to:

generate the least one image from the at least one anatomical structure;

select an axial plane intersecting the anatomical structure;

separate the at least one image approximately along the axial plane to produce a separated image; and

classify the separated image according to a scale.

31. A model for an anatomical structure, comprising:

data associated with an averaged region of interest that bounded within the anatomical structure, the averaged region of interest being associated with at least two images, each of the at least two images including a corresponding region of interest.

32. The model of claim 31, wherein the averaged region of interest is derived from the at least two images by:

selectively iterating the at least two images; and

determining an optimal ratio of sensitivity to specificity for the corresponding regions of interest.