Methods and apparatus for detecting injury using multiple types of magnetic resonance imaging data

1. A computerized system, for evaluating an impact of injury to brain networks or regions, the computerized system comprising:

at least one computer processor; and

at least one computer-readable medium encoded with a plurality of instructions that, when executed by the at least one computer processor, perform a method of evaluating an impact of injury to one or more brain networks or regions, the method comprising:

receiving magnetic resonance imaging (MRI) data of a brain of an individual, wherein the MRI data includes a first volumetric dataset recorded using first imaging parameters and a second volumetric dataset recorded using second imaging parameters;

normalizing first MRI data based on the first volumetric dataset to produce normalized first MRI data;

normalizing second MRI data based on the second volumetric dataset to produce normalized second MRI data,

combining, on a voxel-by-voxel basis, the normalized first MRI data and the normalized second MRI data to produce a volumetric injury map;

performing a structural-functional analysis of one or more brain networks or regions by refining the volumetric injury map using a volumetric eloquence map that specifies eloquent brain tissue within the one or more brain networks or regions to determine an impact of injury within the one or more brain networks; and

displaying a visualization of the determined impact of injury within the one or more brain networks or regions,

wherein normalizing the first MRI data and normalizing the second MRI data comprises using one or more of internal normalization, regional internal normalization and swapped regional internal normalization.

2. The computerized system of claim 1 , wherein the method further comprises:

thresholding the normalized first MRI data to produce thresholded normalized first MRI data; and

thresholding the normalized second MRI data to produce thresholded normalized second MRI data,

wherein combining the normalized first MRI data and the normalized second MRI data is performed using the thresholded normalized first MRI data and the thresholded normalized second MRI data.

3. The computerized system of claim 2 , wherein thresholding the normalized first MRI data comprises including in the thresholded normalized first MRI data only values that fall within two standard deviations from a mean value of the normalized first MRI data.

4. The computerized system of claim 2 , wherein the method further comprises:

selecting a threshold value based, at least in part, on a type of MRI scan used to collect the first volumetric dataset and/or a neurological disease of the individual, and

wherein thresholding the normalized first MRI data comprises applying the selected threshold value to the normalized first MRI data to produce the thresholded normalized first MRI data.

5. The computerized system of claim 1 , wherein combining on a voxel-by-voxel basis, the normalized first MRI data and the normalized second MRI data to produce a volumetric injury map comprises:

generating, for each voxel, a weighted combination of the normalized first MRI data and the normalized second MRI data.

6. The computerized system of claim 5 , wherein the method further comprises:

selecting a first weighting factor based on a type of MRI scan used to collect the first volumetric dataset;

selecting a second weighting factor based on a type of MRI scan used to collect the second volumetric dataset, and

wherein generating a weighted combination of the normalized first MRI data and the normalized second MRI data comprises combining the normalized first MRI data weighted by the first weighting factor and the normalized second MRI data weighted by the second weighting factor.

7. The computerized system of claim 6 , wherein the first weighting factor and/or the second weighting factor are further selected based on a neurological disease of the individual.

8. The computerized system of claim 5 , wherein generating a weighted combination of the normalized first MRI data and the normalized second MRI data for each voxel is based, at least in part, on a value of one or more other voxels in the normalized first MRI data and/or the normalized second MRI data.

9. The computerized system of claim 8 , wherein the one or more other voxels include at least one voxel that neighbors the voxel for which the weighted combination is being generated.

10. The computerized system of claim 5 , wherein generating a weighted combination of the normalized first MRI data and the normalized second MRI data for each voxel is based, at least in part, on a tissue type associated with the voxel.

11. The computerized system of claim 10 , wherein the method further comprises:

applying a first weighting factor when the tissue type associated with the voxel is white matter; and

applying a second weighting factor when the tissue type associated with the voxel is grey matter.

12. A computerized system for evaluating an impact of injury to brain networks or regions, the system comprising:

at least one computer processor; and

at least one computer-readable medium encoded with a plurality of instructions that, when executed by the at least one computer processor, perform a method of evaluating an impact of injury to one or more brain networks or regions, the method comprising:

receiving magnetic resonance imaging (MRI) data of a brain of an individual, wherein the MRI data includes a first volumetric dataset recorded using first imaging parameters and a second volumetric dataset recorded using second imaging parameters;

combining, on a voxel-by-voxel basis, first MRI data based on the first volumetric dataset and second MRI data based on the second volumetric dataset to produce a volumetric injury map;

performing a structural-functional analysis of one or more brain networks or regions by refining the volumetric injury map using a volumetric eloquence map that specifies eloquent brain tissue within the one or more brain networks or regions to determine an impact of injury within the one or more brain networks; and

displaying a visualization of the determined impact of injury within the one or more brain networks or regions,

wherein performing a structural-functional analysis of one or more brain networks or regions by refining the volumetric injury map using a volumetric eloquence map comprises:

combining, on a voxel-by-voxel basis, the volumetric injury map and the volumetric eloquence map to produce an injury mask.

13. The computerized system of claim 12 , wherein combining, on a voxel-by-voxel basis, the first MRI data and the second MRI data to produce a volumetric injury map and combining, on a voxel-by-voxel basis, the volumetric injury map and the volumetric eloquence map are merged into a single step.

14. The computerized system of claim 12 , wherein performing a structural-functional analysis of one or more brain networks or regions further comprises:

comparing the injury mask to a library of masks; and

determining the impact of the injury based on the comparison of the injury mask to the library of masks.

15. The computerized system of claim 14 , wherein

each mask in the library of masks indicates grey matter nodes and white matter tracts for a structural-functional unit in the brain, and

determining the impact of the injury based on the comparison of the injury mask to the library of masks is further based on a spatial overlap between voxels in the injury mask and a structural-functional unit for a particular mask in the library of masks.