Unique cardiovascular measurements for human identification

• US 9,031,288 B2
• Filed: 04/18/2012
• Issued: 05/12/2015
• Est. Priority Date: 04/18/2012
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Codella, Noel C., Connell, Jonathan, Leiguang, Gong, Natsev, Apostol I., Ratha, Nalini
• Primary Examiner(s): Chu, Randolph I
• Assistant Examiner(s): BLOOM, NATHAN J
• Application Number:
  US13/449,720
• Publication Number:
  US 20130279764A1
• Time in Patent Office: 1,119 Days
• Field of Search: None
• US Class Current: 382/115
• CPC Class Codes: A61B 2576/023 for the heart
• CPC Class Codes: A61B 5/055 involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
• CPC Class Codes: A61B 5/1171 based on the shapes or appearances of their bodies or parts thereof
• CPC Class Codes: G06V 40/10 Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
• CPC Class Codes: G06V 40/15 Biometric patterns based on physiological signals, e.g. heartbeat, blood flow

Abstract

A method, an apparatus and an article of manufacture for generating a cardiovascular measurement for individual identification. The method includes acquiring at least one depiction of cardiac anatomy from an individual, extracting at least one quantified representation of cardiac anatomy from the at least one depiction, defining at least one comparison technique between the at least one quantified representation of cardiac anatomy and at least one additional quantified representation of cardiac anatomy, and identifying the individual based on the at least one defined comparison technique.

Claims

1. A method for generating a cardiovascular measurement for individual identification, wherein the method comprises:

acquiring multiple imaging modality signals pertaining to cardiac anatomy of a given individual, wherein the cardiac anatomy comprises a left ventricle of a heart;

extracting multiple quantified representation of cardiac anatomy from the a multiple imaging modality signals, wherein the multiple quantified representations comprise (i) a quantified representation of an endocardial lumen of the left ventricle, (ii) a quantified representation of a myocardial wall of the left ventricle, and (iii) a quantified representation of papillary muscles of the left ventricle;

determining a pattern of cardiac anatomy associated with the given individual based on (i) the quantified representation of the endocardial lumen of the left ventricle, (ii) the quantified representation of the myocardial wall of the left ventricle, and (iii) the quantified representation of the papillary muscles of the left ventricle;

defining at least one comparison technique between the pattern of cardiac anatomy associated with the given individual and at least one additional pattern of cardiac anatomy; and

identifying the given individual based on the at least one defined comparison technique.

2. The method of claim 1, wherein the multiple imaging modality signals comprises a transverse slice of the left ventricle.

3. The method of claim 1, wherein an imaging modality signal comprises a digital image.

4. The method of claim 1, wherein the multiple imaging modality signals pertaining to cardiac anatomy is acquired during end diastolic phase.

5. The method of claim 1, wherein acquiring the multiple imaging modality signals pertaining to cardiac anatomy comprises acquiring the multiple imaging modality signals pertaining to cardiac anatomy via at least one anatomical imaging modality including one of magnetic resonance imaging (MRI), computed tomography (CT), two-dimensional (2D) echo/ultrasound, three-dimensional (3D) echo/ultrasound, positron emission tomography (PET) or a combination thereof.

6. The method of claim 1, wherein identifying the given individual comprises defining a similarity measure between the pattern of cardiac anatomy associated with the given individual and at least one additional pattern of cardiac anatomy to produce at least one score.

7. The method of claim 6, wherein the pattern of cardiac anatomy associated with the given individual is a plurality of images for the given individual, and wherein said comparing comprises computing a score between pairs of images from individuals, and generating a final comparison score which is a function of two or more pair scores.

8. The method of claim 6, wherein identifying the given individual based on the defined similarity measure is based on a similarity measure threshold.

9. The method of claim 8, wherein the similarity measure threshold is different for different individuals.

10. The method of claim 1, wherein said defining at least one comparison technique comprises geometric aligning and warping of the representations to be compared.

11. The method of claim 1, wherein said defining at least one comparison technique is based on a pixel-wise difference of one or more selected anatomical structures in a representation.

12. The method of claim 1, wherein said defining at least one comparison technique is based on identifying individual papillary fibers and determining a correspondence between fibers in two representations.

13. The method of claim 1, wherein said extracting comprises using a segmentation technique.

14. The method of claim 1, wherein the at least one comparison technique comprises implementing an algorithm that analyzes left ventricle anatomical structures including at least one of endocardium, myocardium, and papillary muscles.

15. The method of claim 1, wherein identifying the given individual based on the at least one defined comparison technique comprises:

defining two or more similarity measures between the pattern of cardiac anatomy associated with the given individual and at least one additional pattern of cardiac anatomy; and

combining the two or more similarity measures to produce at least one score.

16. An article of manufacture comprising a non-transitory computer readable storage medium having computer readable instructions tangibly embodied thereon which, when implemented, cause a computer to carry out a plurality of method steps comprising:

acquiring multiple imaging modality signals pertaining to cardiac anatomy of a given individual, wherein the cardiac anatomy comprises a left ventricle of a heart;

extracting multiple quantified representation of cardiac anatomy from the multiple imaging modality signals, wherein the multiple quantified representations comprise (i) a quantified representation of an endocardial lumen of the left ventricle, (ii) a quantified representation of a myocardial wall of the left ventricle, and (iii) a quantified representation of papillary muscles of the left ventricle;

determining a pattern of cardiac anatomy associated with the given individual based on (i) the quantified representation of the endocardial lumen of the left ventricle, (ii) the quantified representation of the myocardial wall of the left ventricle, and (iii) the quantified representation of the papillary muscles of the left ventricle;

defining at least one comparison technique between the pattern of cardiac anatomy associated with the given individual and at least one additional pattern of cardiac anatomy; and

identifying the given individual based on the at least one defined comparison technique.

17. The article of manufacture of claim 16, wherein said identifying the given individual based on the at least one defined comparison technique comprises defining a similarity measure between the pattern of cardiac anatomy associated with the given individual and at least one additional pattern of cardiac anatomy to produce at least one score.

18. The article of manufacture of claim 17, wherein comparing the pattern of cardiac anatomy associated with the given individual and at least one additional pattern of cardiac anatomy includes geometric aligning and warping of the representations to be compared.

19. The article of manufacture of claim 17, wherein comparing the pattern of cardiac anatomy associated with the given individual and at least one additional pattern of cardiac anatomy comprises identifying individual papillary fibers and determining a correspondence between fibers in two representations.

20. A system for generating a cardiovascular measurement for individual identification, comprising:

at least one distinct software module, each distinct software module being embodied on a tangible computer-readable medium;

a memory; and

at least one processor coupled to the memory and operative for;

acquiring multiple imaging modality signals pertaining to cardiac anatomy of a given individual, wherein the cardiac anatomy comprises a left ventricle of a heart;

extracting multiple quantified representation of cardiac anatomy from the multiple imaging modality signals, wherein the multiple quantified representations comprise (i) a quantified representation of an endocardial lumen of the left ventricle, (ii) a quantified representation of a myocardial wall of the left ventricle, and (iii) a quantified representation of papillary muscles of the left ventricle;

determining a pattern of cardiac anatomy associated with the given individual based on (i) the quantified representation of the endocardial lumen of the left ventricle, (ii) the quantified representation of the myocardial wall of the left ventricle, and (iii) the quantified representation of the papillary muscles of the left ventricle;

defining at least one comparison technique between the pattern of cardiac anatomy associated with the given individual and at least one additional pattern of cardiac anatomy; and

identifying the given individual based on the at least one defined comparison technique.

21. The system of claim 20, wherein the at least one processor is further operative for acquiring the multiple imaging modality signals pertaining to cardiac anatomy via at least one anatomical imaging modality including one of magnetic resonance imaging (MRI), computed tomography (CT), two-dimensional (2D) echo/ultrasound, three-dimensional (3D) echo/ultrasound, positron emission tomography (PET) or a combination thereof.

22. The system of claim 21, wherein the at least one processor is further operative for defining a similarity measure between the pattern of cardiac anatomy associated with the given individual and at least one additional quantified pattern of cardiac anatomy to produce at least one score.

23. The system of claim 22, wherein the at least one processor is further operative for geometric aligning and warping of the representations to be compared.

24. The system of claim 22, wherein the at least one processor is further operative for identifying individual papillary fibers and determining a correspondence between fibers in two representations.