Methods and tools for analyzing brain images
Methods and systems for analyzing a medical image of a subject's brain are disclosed. Analysis of a medical image of a subject's brain for predictive and diagnostic determination of neurodegenerative disease state. The method comprises parcellating the grey matter in the image of the brain and determining the size of each region to generate an initial pattern of the disease process; applying a diffusion kernel to obtain an output vector; and predicting future changes to the brain based on the output vector. Another method of analyzing a medical image of a subject's brain includes solving for eigen-modes of a connectivity matrix, projecting the eigen-modes onto the initial disease state to produce an output product and diagnosing a disease or lack thereof based on a comparison of the output product to one or more reference standards.
1. A method for analyzing a subject's brain, the method comprising:
parcellating, by a computing device, grey matter in a medical image of the subject's brain to produce an initial disease state;
applying, by the computing device, a diffusion kernel to the initial disease state to produce an output vector; and
predicting future changes to the subject's brain based on the output vector.
2. The method of claim 1 , wherein the medical image comprises a tomographic diffusion weighted image.
3. The method of claim 1 , wherein the medical image is produced by MRI, CT, or PET.
4. The method of claim 1 , wherein the diffusion kernel is generated based on the medical image of the subject's brain.
5. The method of claim 1 , wherein the diffusion kernel is derived from a connectivity matrix that corresponds to the subject's brain.
6. The method of claim 1 , further comprising:
administering a medical intervention;
parcellating, by a computing device, grey matter in a second medical image of the subject's brain to produce a second disease state;
applying, by the computing device, a diffusion kernel to the second disease state to produce a second output vector;
predicting future changes to the subject's brain based on the second output vector; and
comparing predicted future changes to the subject's brain to predicted future changes to the subject's brain based on the second output vector.
7. The method of claim 1 , further comprising:
parcellating, by a computing device, grey matter in a second medical image of a second subject's brain to produce an initial disease state of the second subject;
applying, by the computing device, a diffusion kernel to the initial disease state of the second subject to produce a second output vector;
predicting future changes to the second subject's brain based on the second output vector; and
stratifying the subject and the second subject based on a comparison of the output vector and the second output vector.
8. A non-transitory computer-readable medium having instructions stored thereon that, upon execution by a computing device, cause the computing device to perform operations comprising:
parcellating grey matter in a medical image of a subject's brain to produce an initial disease state;
applying a diffusion kernel to the medical image to produce an output vector; and
predicting future changes to the subject's brain based on the output vector.
9. The non-transitory computer-readable medium of claim 8 , wherein the operations further comprise reporting the future changes to the subject's brain by displaying representations of the future changes to the subject's brain.
10. A system for analyzing a subject's brain, comprising:
a memory; and
one or more processors coupled to the memory, wherein the one or more processors are configured to:
parcellate grey matter in a medical image of the subject's brain to produce an initial disease state;
apply a diffusion kernel to the medical image to produce an output vector; and
predict future changes to the subject's brain based on the output vector.
11. The system of claim 10 , wherein the one or more processors are further configured to report the future changes to the subject's brain by displaying representations of the future changes to the subject's brain.