Methodologies linking patterns from multi-modality datasets

• US 20060074290A1
• Filed: 10/03/2005
• Published: 04/06/2006
• Est. Priority Date: 10/04/2004
• Status: Active Grant

• Current Assignee: Banner Health
• Original Assignee: Banner Health
• Inventors: Reiman, Eric M., Chen, Kewei
• Granted Patent: US 9,471,978 B2
• Time in Patent Office: Days
• US Class Current: 600/407
• CPC Class Codes: A61B 5/00 Measuring for diagnostic purposes radiation diagnosis A61B6/00; diagnosis by ultrasonic, sonic or infrasonic waves A61B8/00; Identification of persons
• CPC Class Codes: A61B 5/165 Evaluating the state of mind, e.g. depression, anxiety
• 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 2207/30096 Tumor; Lesion
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• 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
• CPC Class Codes: G16H 15/00 ICT specially adapted for medical reports, e.g. generation or transmission thereof
• CPC Class Codes: G16H 20/10 relating to drugs or medications, e.g. for ensuring correct administration to patients
• CPC Class Codes: G16H 30/40 for processing medical images, e.g. editing
• CPC Class Codes: G16H 70/20 relating to practices or guidelines

Abstract

A method is disclosed to acquire imaging and non-imaging datasets from like objects. A linkage is found using a partial least squares (PLS) technique between imaging and non-imaging datasets. The linkage is then reduced to an expression of a single numerical assessment. The single numerical assessment is then used as an objective, quantified assessment of the differences and similarities between the objects. The data each dataset can be aspects of performance, physical characteristics, or measurements of appearance.

Claims

1. A method comprising:

acquiring a plurality of datasets (D_i, i=1-I) from each of a plurality of objects (O_n, n=1-N);

finding a linkage between D_i and D_j, where D_i and D_j are not the same modality;

reducing the linkage to an expression of a single numerical assessment; and

use the single numerical assessment as an objective, quantified assessment of the differences and similarities between objects (O_n, n=1-N).

2. The method as defined in claim 1, wherein the data in the plurality of datasets (D_i, i=1-I) is acquired by either by an imaging modality or a non-imaging modality.

3. The method as defined in claim 2, wherein the imaging modality is selected from the group consisting of:

ultrasound;

a PET, single photon emission tomography radiotracer, or other nuclear medicine procedure;

structural, functional, perfusion-weighted, or diffusion-weighted MRI;

x-ray computed tomography;

magnetic resonance spectroscopy measurements of N-acetyl aspartic acid, myoinositol, and other chemical compounds;

electroencephalography, quantitative electroencephalography, event-related potentials, and other electrophysiological procedures;

magnetoencephalography;

a medical imaging measurement procedure; and

a non-medical imaging measurement procedure.

4. The method as defined in claim 2, wherein the non-imaging modality is selected from the group consisting of:

a set of biochemical measurements;

a set of molecular measurements;

a set of genetic measurements

a set of transcriptomic measurements;

a set of proteomic measurements;

a set of cognitive measurements or clinical ratings;

a set of behavioral measurements; and

a set of measurements from a non-medical non-imaging modality.

5. The method as defined in claim 1, wherein O_n is selected from the group consisting of an article of manufacture, a human body tissue, a human body fluid;

a mammal or portion thereof, and a plant or portion thereof.

6. The method as defined in claim 1, wherein the data in each dataset O_n is an index set selected from the group consisting of aspects of performance, physical characteristics, and measurements of appearance.

7. The method as defined in claim 1, wherein the linkage between D_i and D_j is found using partial least squares (PLS).

8. The method as defined in claim 7, wherein the PLS is selected from the group consisting of Dual Block (DB) PLS and Multi-block (MB) PLS.

9. The method as defined in claim 1, wherein the linkage between D_i and D_j is found using either inter-SEM or inter-ICA.

10. A computer readable medium comprising instructions that, when executed by a computer, perform the method as defined in claim 1.

11. A method comprising:

.

acquiring dual FDG-PET (PET_n) and MRI (MRI_n) datasets upon each of a plurality of human subjects (O_n, n=1-N);

finding a linkage between FDG-PET and MRI, where FDG-PET and MRI are pooled datasets from all of the human subjects;

reducing the linkage between FDG-PET and MRI to an expression of a single numerical assessment; and

using the single numerical assessment as an objective, quantified assessment of the differences and similarities between the human subjects.

12. The method as defined in claim 11, wherein:

the human subjects (O_n, n=1-N) are divided into group; and

the single numerical assessment is used as an objective, quantified assessment of the differences and similarities between each said group of the human subjects.

13. The method as defined in claim 11, wherein the linkage between FDG-PET and MRI is found using partial least squares (PLS).

14. The method as defined in claim 13, wherein the PLS is selected from the group consisting of Dual Block (DB) PLS and Multi-block (MB) PLS.

15. A computer readable medium comprising instruction that, when executed by a computer, perform the method as defined in claim 11.

16. A method comprising:

.

acquiring, at each of a plurality of t_j (time=t_j, j=1-2), a plurality of datasets (D_i^j, i=1-I, j=1,

     2) for each of a plurality of objects (O_n, n=1-N);

administering a treatment to each of the objects O_n between t₁ and t₂;

finding a linkage between D_i1^j and D_i2^j at t_j, where D_i1^j and D_i2^j are not the same modality;

reducing the linkage at t_j to an expression of a single numerical assessment; and

using the single numerical assessment to assess the treatment effect, from time t₁ to time t₂, upon the objects (O_n, n=1-N).

17. The method as defined in claim 16, wherein the linkage is found using partial least squares (PLS).

18. The method as defined in claim 17, wherein the PLS is selected from the group consisting of Dual Block (DB) PLS and Multi-block (MB) PLS.

19. The method as defined in claim 16, wherein the data in the plurality of datasets (D_i^j, i=1-I, j=1, 2) is acquired by either by an imaging modality or a non-imaging modality.

20. The method as defined in claim 19, wherein the imaging modality is selected from the group consisting of:

ultrasound;

different PET and single photon emission tomography radiotracer methods;

structural, functional, perfusion-weighted, or diffusion-weighted MRI;

x-ray computed tomography;

magnetic resonance spectroscopy measurements of N-acetyl aspartic acid, myoinositol, and other chemical compounds;

electroencephalography, quantitative electroencephalography, event-related potentials, and other electrophysiological procedures; and

magnetoencephalography.

21. The method as defined in claim 19, wherein the non-imaging modality is selected from the group consisting of:

biochemical measurements;

molecular measurements;

transcriptomic measurements;

proteomic measurements;

cognitive measurements; and

behavior measurements.

22. The method as defined in claim 16, wherein On is selected from the group consisting of an article of manufacture, a mammal, a human body tissue, and a human body fluid.

23. The method as defined in claim 16, wherein the data in each dataset O_n is an index set selected from the group consisting of aspects of performance, physical characteristics, and measurements of appearance.

24. A computer readable medium comprising instructions that, when executed by a computer, perform the method as defined in claim 16.

25. A method comprising:

.

acquiring, at each of a plurality of t_j (time=t_j, j=1-2), a dual FDG-PET and MRI dataset (PET_n^j and MRI_n^j, j=1,

     2) upon each of a plurality of human subjects (O_n, n=1-N);

administering a putative therapy to slow an aspect of brain aging on each of the human subjects O_n between t₁ and t₂;

finding a linkage between the FDG-PET and MRI dataset at t_j, where FDG-PET and MRI are pooled datasets from all of the human subjects;

reducing the indices of linkage between FDG-PET and MRI at t_j to an expression of a single numerical assessment; and

using the single numerical assessment to assess the treatment effect, from time t₁ to time t₂, upon the human subjects (O_n, n=1-N).

26. The method as defined in claim 25, wherein:

the human subjects (O_n, n=1-N) are divided into sub-sets; and

the single numerical assessment is used as an objective, quantified assessment of the differences and similarities between each said sub-set of the human subjects.

27. The method as defined in claim 25, wherein:

the human subjects (O_n, n=1-N) are divided into sub-sets; and

the single numerical assessment is used as an objective, quantified assessment of the differences and similarities between the human subjects;

to whom the treatment to slow the aging process was administered; and

to whom the treatment to slow the aging process was not administered.

28. The method as defined in claim 25, wherein the linkage between FDG-PET and MRI is found using partial least squares (PLS).

30. The method as defined in claim 25, wherein the putative therapy to slow an aspect of brain aging is selected from the group consisting of a pharmacological prescription, an over-the-counter medication, an immunization therapy, a biological therapeutic, a dietary supplement, a dietary change, a physical exercise, a mental exercise, a lifestyle change intended to promote healthy living, a lifestyle change intended to promote healthy mental function, a lifestyle change intended to decrease a risk of cardiovascular disease, and a combination of the foregoing.

31. The method as defined in claim 25, wherein:

the human subjects (O_n, n=1-N) are divided into group; and

the single numerical assessment is used as an objective, quantified assessment of

the differences and similarities between each said group of the human subjects.

32. A computer readable medium comprising instructions that, when executed by a computer, perform the method as defined in claim 25.

29. The method as defined in Claim28, wherein the PLS is selected from the group consisting of Dual Block (DB) PLS and Multi-block (MB) PLS.