Methods and apparatus for using brain imaging to predict performance
Methods and apparatus for predicting performance of an individual on a task, the method comprises receiving brain imaging data for the individual, wherein the brain imaging data comprises structural brain data, determining values for at least one characteristic of the structural brain data within regions of interest defined for a population of individuals having different performance levels, and predicting based on the determined values, a performance potential of the individual.
1. A computerized system for identifying brain regions that predict differences in task performance, 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, the method comprising:
receiving brain imaging data for each of a plurality of individuals in a reference cohort, wherein the brain imaging data comprises structural brain data characterizing a static state of a brain and physiological brain data characterizing a dynamic state of the brain;
receiving functional skill data for each of the plurality of individuals in the reference cohort, wherein the functional skill data indicates a performance score for each of the plurality of individuals on one or more tasks;
determining, based, at least in part, on at least one first characteristic of the structural brain data, at least one second characteristic of the physiological brain data, and the functional skill data, brain regions associated with differences in performance on the one or more tasks; and
outputting the determined brain regions as a set of predictive regions of interest.
2. The computerized system of claim 1 , wherein the method further comprises defining a set of brain regions and connections between the brain regions as a structural functional unit, and wherein
determining the brain regions associated with differences in performance on the one or more tasks comprises identifying within the brain regions of the structural functional unit, brain regions associated with differences in performance on the one or more tasks.
3. The computerized system of claim 2 wherein determining the brain regions associated with differences in performance on the one or more tasks comprises:
for each voxel of a brain region of the structural functional unit, determining a value indicating how well the brain data for the voxel characterizes differences in performance on the one or more tasks.
4. The computerized system of claim 3 , wherein determining a value indicating how well the brain data for the voxel characterizes difference in performance on the one or more tasks comprises:
defining a first group of individuals in the reference cohort who performed well on the one or more tasks;
defining a second group of individuals in the reference cohort who performed poorly on the one or more tasks; and
performing, for the voxel, a numerical comparison between brain data for the first group of individuals and brain data for the second group of individuals to determine the value indicating how well the brain data for the voxel characterizes differences in performance on the one or more tasks.
5. The computerized system of claim 4 , wherein the method further comprises:
performing a local transformation using a neighborhood of voxels around the voxel to determine a first value for the at least one first characteristic of the structural brain data and a second value for the at least one second characteristic of the physiological brain data, and
wherein performing, for the voxel, a numerical comparison between brain data for the first group of individuals and brain data for the second group of individuals comprises performing a first numerical comparison based on the first value and a second numerical comparison based on the second value.
6. A computer-implemented method for identifying brain regions that predict differences in task performance, the method comprising:
receiving brain imaging data for each of a plurality of individuals in a reference cohort, wherein the brain imaging data comprises structural brain data characterizing a static state of a brain and physiological brain data characterizing a dynamic state of the brain;
receiving functional skill data for each of the plurality of individuals in the reference cohort, wherein the functional skill data indicates a performance score for each of the plurality of individuals on one or more tasks;
determining, based, at least in part, on at least one first characteristic of the structural brain data, at least one second characteristic of the physiological brain data, and the functional skill data, brain regions associated with differences in performance on the one or more tasks; and
outputting the determined brain regions as a set of predictive regions of interest.
7. The computer-implemented method of claim 6 , further comprising:
defining a set of brain regions and connections between the brain regions as a structural functional unit, wherein
determining the brain regions associated with differences in performance on the one or more tasks comprises identifying within the brain regions of the structural functional unit, brain regions associated with differences in performance on the one or more tasks.
8. The computer-implemented method of claim 7 wherein determining the brain regions associated with differences in performance on the one or more tasks comprises:
for each voxel of a brain region of the structural functional unit, determining a value indicating how well the brain data for the voxel characterizes differences in performance on the one or more tasks.
9. The computer-implemented method of claim 8 , wherein determining a value indicating how well the brain data for the voxel characterizes difference in performance on the one or more tasks comprises:
defining a first group of individuals in the reference cohort who performed well on the one or more tasks;
defining a second group of individuals in the reference cohort who performed poorly on the one or more tasks; and
performing, for the voxel, a numerical comparison between brain data for the first group of individuals and brain data for the second group of individuals to determine the value indicating how well the brain data for the voxel characterizes differences in performance on the one or more tasks.
10. The computer-implemented method of claim 9 , further comprising:
performing a local transformation using a neighborhood of voxels around the voxel to determine a first value for the at least one first characteristic of the structural brain data and a second value for the at least one second characteristic of the physiological brain data, and
wherein performing, for the voxel, a numerical comparison between brain data for the first group of individuals and brain data for the second group of individuals comprises performing a first numerical comparison based on the first value and a second numerical comparison based on the second value.