Methodologies linking patterns from multi-modality datasets
First Claim
Patent Images
1. A method comprising:
- acquiring a plurality of datasets (Di, i=1-I) from each of a plurality of objects (On, n=1-N);
finding a linkage between Di and Dj, where Di and Dj 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 (On, n=1-N).
1 Assignment
0 Petitions
Accused Products
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.
-
Citations
32 Claims
-
1. A method comprising:
-
acquiring a plurality of datasets (Di, i=1-I) from each of a plurality of objects (On, n=1-N);
finding a linkage between Di and Dj, where Di and Dj 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 (On, n=1-N). - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10)
-
-
11. A method comprising:
- .
acquiring dual FDG-PET (PETn) and MRI (MRIn) datasets upon each of a plurality of human subjects (On, 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. - View Dependent Claims (12, 13, 14, 15)
- .
-
16. A method comprising:
- .
acquiring, at each of a plurality of tj (time=tj, j=1-2), a plurality of datasets (Dij, i=1-I, j=1,
2) for each of a plurality of objects (On, n=1-N);
administering a treatment to each of the objects On between t1 and t2;
finding a linkage between Di 1 j and Di2 j at tj, where Di1 j and Di2 j are not the same modality;
reducing the linkage at tj 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 (On, n=1-N). - View Dependent Claims (17, 18, 19, 20, 21, 22, 23, 24)
- .
-
25. A method comprising:
- .
acquiring, at each of a plurality of tj (time=tj, j=1-2), a dual FDG-PET and MRI dataset (PETnj and MRInj, j=1,
2) upon each of a plurality of human subjects (On, n=1-N);
administering a putative therapy to slow an aspect of brain aging on each of the human subjects On between t1 and t2;
finding a linkage between the FDG-PET and MRI dataset at tj, 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 tj 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 (On, n=1-N). - View Dependent Claims (26, 27, 28, 30, 31, 32)
- .
-
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.
Specification