Systems and methods for modeling neural architecture
Systems and methods are described herein for modeling neural architecture. Regions of interest of a brain of a subject can be identified based on image data characterizing the brain of the subject. the identified regions of interest can be mapped to a connectivity matrix. The connectivity matrix can be a weighted and undirected network. A multivariate transformation can be applied to the connectivity matrix to transform the connectivity matrix into a partial correlation matrix. The multivariate transformation can maintain a positive definite constraint for the connectivity matrix. The partial correlation matrix can be transformed into a neural model indicative of the connectivity matrix.
1. A computer-implemented method comprising:
identifying, by one or more processors, regions of interest of a brain of a subject based on image data characterizing the brain of the subject, wherein the image data comprises one of magnetic resonance imaging (MRI) data, functional magnetic resonance imaging (fMRI) image data, diffusion weighted imaging (DWI) data, diffusion tensor imaging (DTI) data, electromyogram (EMG) data, electroencephalogram (EEG) data, positron emission tomography (PET) data, magnetoencephalography (MEG) data, Electrocorticography (ECoG), ultrasound imaging data, and a combination thereof;
mapping, by the one or more processors, the regions of interest of the image data to a connectivity matrix, wherein the connectivity matrix is a weighted and directed or undirected network;
transforming, by the one or more processors, the connectivity matrix into a biomarker parameter, wherein the biomarker parameter corresponds to a defined statistic;
analyzing, by the one or more processors, the biomarker parameter according to a probability density function of a statistical cognitive model, wherein the probability density function maps a separate population of the biomarker parameter to a cognitive phenomenon; and
generating, by the one or more processors, a probability of the cognitive phenomenon based on the probability density function of the statistical cognitive model, wherein the probability quantifies a severity of the cognitive phenomenon.
2. The computer-implemented method of claim 1 , wherein the biomarker parameter corresponds to a first biomarker parameter, and wherein the statistical cognitive model comprises an additional probability density function that maps a second biomarker parameter to the cognitive phenomena.
3. The computer-implemented method of claim 2 , wherein the first biomarker parameter and the second biomarker parameter are computed, by the one or more processors, based on different atlases such that the statistical cognitive model provides a joint modeling framework.
4. The computer-implemented method of claim 1 , wherein transforming, by the one or more processors, the connectivity matrix into the biomarker parameter is according to a neurological generalized exponential random graph model (neuro-GERGM) algorithm.
5. The computer-implemented method of claim 1 , further comprising administering a treatment for the cognitive phenomenon according to the severity of the cognitive phenomenon.
6. The computer-implemented method of claim 1 , wherein the statistic comprises one of an endogenous statistic, an exogenous statistic, and a combination thereof.
7. A method comprising:
receiving, at one or more processors, image data of a subject;
transforming, at the one or more processors, the image data with a neural modeling engine into a biomarker parameter, wherein the biomarker parameter corresponds to a defined statistic;
analyzing, at the one or more processors, the biomarker parameter with a probability density function of a statistical cognitive model, wherein the probability density function maps a separate population of the biomarker parameter to a cognitive phenomenon;
generating, at the one or more processors, an initial probability of the cognitive phenomenon based on the probability density function of the statistical cognitive model; and
quantifying, at the one or more processors, a severity of the cognitive phenomenon for the subject based upon the initial probability.
8. The method of claim 7 , further comprising administering a treatment for the cognitive phenomenon based on the severity of the cognitive phenomenon.
9. The method of claim 8 , further comprising:
receiving, at the one or more processors, subsequent image data of the subject;
transforming, at the one or more processors, the subsequent image data with the neural modeling engine into a subsequent biomarker parameter, wherein the subsequent biomarker parameter corresponds to a different defined statistic;
generating, at the one or more processors, a subsequent probability of the cognitive phenomenon based on the probability density function of the statistical cognitive model;
comparing, at the one or more processors, the initial probability and the subsequent probability; and
determining, at the one or more processors, an efficacy of the treatment based on a result of the comparison.
10. The method of claim 7 , wherein the neural modeling engine comprises a neurological generalized exponential random graph model (neuro-GERGM) algorithm.
11. The method of claim 7 , wherein the image data comprises one of functional magnetic resonance imaging (fMRI) data, diffusion weighted imaging (DWI) data, diffusion tensor imaging (DTI) data, electromyogram (EMG) data, electroencephalogram (EEG) data, positron emission tomography (PET) data, magnetoencephalography (MEG) data, Electrocorticography (ECoG) data, ultra-sound imaging data, and a combination thereof.
12. The method of claim 7 , wherein the statistic comprises one of an endogenous statistic, an exogenous statistic, and a combination thereof.