# US 10,311,373 B2 · Subject-specific assessment of neurological disorders with biochemical propagation mechanisms > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,311,373 B2 - Document ID: US10311373B2 - Status: Granted - Kind: B2 - Application number: 14/688,148 - Filed: 2015-04-16 - Published: 2016-10-20 - Granted: 2019-06-04 - Earliest claimed: 2015-04-16 - Assignees: Siemens Healthcare GmbH - Applicants: Siemens Healthcare GmbH - Inventors: Saikiran Rapaka; Hasan Ertan Cetingul; Francisco Pereira; Dorin Comaniciu; Alma Gregory Sorensen - Web page: https://patentgrep.com/patent/US10311373B2 ## CPC - G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems - A61B 5/0042: {for the brain} - A61B 5/055: involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging - A61B 5/37: Intracranial electroencephalography [IC-EEG], e.g. electrocorticography [ECoG] - A61B 5/372: Analysis of electroencephalograms - A61B 5/384: Recording apparatus or displays specially adapted therefor - G06N 20/00: Machine learning - G16H 50/50: for simulation or modelling of medical disorders - A61B 5/4094: {Diagnosing or monitoring seizure diseases, e.g. epilepsy} - A61B 5/72: {Signal processing specially adapted for physiological signals or for diagnostic purposes} - A61B 5/7264: {Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems} - A61B 5/7278: {Artificial waveform generation or derivation, e.g. synthesizing signals from measured signals} - A61B 2576/026: for the brain - G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA - A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract A method for subject-specific assessment of neurological disorders, the method includes receiving 3D image data representative of a subject's brain and identifying subject-specific anatomical structures in the 3D image data. A subject-specific model for electrical dynamics is created based on the 3D image data and the subject-specific anatomical structures and one or more functional indicators of neurological disorder are computed using the subject-specific model for electrical dynamics. ## Claims ### Claim 1 A method for subject-specific assessment of neurological disorders, the method comprising: receiving 3D image data representative of a subject's brain, wherein the 3D image data comprises (i) structural data representative of structures in the subject's brain and (ii) diffusion data representative of diffusion of fluid through the subject's brain; identifying subject-specific anatomical structures using the structural data; identifying a plurality of subject-specific anatomical connections in the subject's brain using the diffusion data; using the 3D image data to perform surface based analysis of the subject's brain, yielding a flattened representation of the subject's brain; imposing a grid on the flattened representation of the subject's brain using the subject-specific anatomical structures, wherein the grid comprises a plurality of grid nodes and a plurality of edges connecting the grid nodes; weighing the edges of the grid based on the subject-specific anatomical connections, thereby yielding a weighted grid; creating a subject-specific model for electrical dynamics based on the weighted grid, wherein the subject-specific model for electrical dynamics utilizes one or more Lattice Boltzmann methods; computing, by a parallel processing platform, one or more functional indicators of neurological disorder using the subject-specific model for electrical dynamics, wherein the Lattice Boltzmann methods are used to parallelize at least a portion of computations performed by the subject-specific model across a plurality of processors included in the parallel processing platform. ### Claim 2 (depends on 1) The method of claim 1, wherein the subject-specific anatomical structures are identified by a process comprising: applying a machine learning process to segment the subject's brain into a plurality of brain segments, wherein the subject-specific anatomical structures comprises the plurality of brain segments. ### Claim 3 (depends on 1) The method of claim 1, wherein the surface based analysis comprises: generating a surface mesh of the subject's brain; inflating the surface mesh to yield an inflated mesh; flattening the inflated mesh to yield the flattened representation of the subject's brain. ### Claim 4 (depends on 1) The method of claim 1, further comprising: receiving electrical sensing data representative of the subject's brain, wherein the subject-specific model for electrical dynamics is created using the electrical sensing data. ### Claim 5 (depends on 4) The method of claim 4, wherein the subject-specific model for electrical dynamics is created by a process comprising: creating an initial version of the subject-specific model for electrical dynamics based on the 3D image data and the subject-specific anatomical structures; and refining the initial version of the subject-specific model for electrical dynamics using the electrical sensing data to yield the subject-specific model for electrical dynamics. ### Claim 6 (depends on 4) The method of claim 4, wherein the electrical sensing data comprises electroencephalography (EEG) data. ### Claim 7 (depends on 4) The method of claim 4, wherein the electrical sensing data comprises electrocorticography (ECoG) data. ### Claim 8 A method for subject-specific assessment of neurological disorders, the method comprising: receiving 3D image data representative of a subject's brain, wherein the 3D image data comprises (i) structural data representative of structures in the subject's brain and (ii) diffusion data representative of diffusion of fluid through the subject's brain; identifying subject-specific anatomical structures in the 3D image data; identifying a plurality of subject-specific anatomical connections in the subject's brain using the diffusion data; generating a surface mesh of the subject's brain based on the 3D image data; applying an inflation process to the surface mesh to yield an inflated mesh; applying a flattening process to the inflated mesh to yield the flattened representation of the subject's brain; imposing a grid on the flattened representation of the subject's brain using the subject-specific anatomical structures, wherein the grid comprises a plurality of grid nodes and a plurality of edges connecting the grid nodes; weighing the edges of the grid based on the subject-specific anatomical connections, thereby yielding a weighted grid; generating a subject-specific model for electrical dynamics using the weighted grid, wherein the subject-specific model for electrical dynamics utilizes one or more Lattice Boltzmann methods; dividing the grid into a plurality of blocks; using a parallel computing platform to compute one or more functional indicators of neurological disorder by executing multiple copies of the subject-specific model for electrical dynamics in parallel, wherein each respective copy corresponds to one of the plurality of blocks. ### Claim 9 (depends on 8) The method of claim 8, further comprising: receiving electrical sensing data representative of the subject's brain, generating an initial version of the subject-specific model for electrical dynamics based on the 3D image data and the subject-specific anatomical structures; and refining the initial version of the subject-specific model for electrical dynamics using the electrical sensing data to yield the subject-specific model for electrical dynamics. ### Claim 10 (depends on 8) The method of claim 8, wherein the subject-specific anatomical structures are identified by a process comprising: applying a machine learning process to segment the subject's brain into a plurality of brain segments, identifying diffusion data included in the 3D image data, the diffusion data information representative of diffusion of fluid through the subject's brain; and identifying a plurality of anatomical connections in the subject's brain using the diffusion data, wherein the subject-specific anatomical structures further comprise the plurality of brain segments and the plurality of anatomical connections. ### Claim 11 A system for calculating electrical wave propagation across a subject's brain, the system comprising: one or more imaging devices configured to acquire 3D image data representative of a subject's brain, wherein the 3D image data comprises (i) structural data representative of structures in the subject's brain and (ii) diffusion data representative of diffusion of fluid through the subject's brain; a modeling computing system operably coupled to the imaging devices and configured to use a plurality of processors to simulate electrical dynamics across the subject's brain, the processors performing the modeling computing system comprising system memory storing instructions, which instructions are configures to perform a method comprising: identifying subject-specific anatomical structures in the 3D image data, identifying a plurality of subject-specific anatomical connections in the subject's brain using the diffusion data, using the 3D image data to perform surface based analysis of the subject's brain, yielding a flattened representation of the subject's brain, imposing a grid on the flattened representation of the subject's brain using the subject-specific anatomical structures and the subject-specific anatomical connections, wherein the grid comprises a plurality of grid nodes and a plurality of edges connecting the grid nodes, weighing the edges of the grid based on the subject-specific anatomical connections, thereby yielding a weighted grid; creating a subject-specific model for electrical dynamics based on the weighted grid, wherein the subject-specific model for electrical dynamics utilizes one or more Lattice Boltzmann methods, and calculating electrical wave propagation from an initial spreading point using the subject-specific model for electrical dynamics, wherein the Lattice Boltzmann methods are used to parallelize at least a portion of computations performed by the subject-specific model across the processors. ### Claim 12 (depends on 11) The system of claim 11, wherein at least one of the imaging devices is a Magnetic Resonance Imaging (MM) device. ### Claim 13 (depends on 11) The system of claim 11, further comprising: an electrical sensing data acquisition device configured to acquire electrical sensing data representative of the subject's brain. ### Claim 14 (depends on 13) The system of claim 13, wherein the processors are further configured to: create an initial version of the subject-specific model for electrical dynamics based on the 3D image data and the subject-specific anatomical structures; and refine the initial version of the subject-specific model for electrical dynamics using the electrical sensing data. ### Claim 15 (depends on 13) The system of claim 13, wherein the electrical sensing data acquisition device comprises an electroencephalography (EEG) acquisition device. ### Claim 16 (depends on 13) The system of claim 13, wherein the electrical sensing data acquisition device comprises an electrocorticography (ECoG) acquisition device. ### Claim 17 (depends on 13) The system of claim 13, wherein the modeling computing system comprises one or more graphical processing units (GPUs) configured to parallelize execution of operations corresponding to the simulation of electrical dynamics across the subject's brain. ### Claim 18 (depends on 11) The system of claim 11, further comprising: a display configured to present a visualization of the electrical wave propagation from the initial spreading point. ### Claim 19 (depends on 18) The system of claim 18, wherein the display is further configured to present a graphical user interface which allows user interaction with the visualization of the electrical wave propagation from the initial spreading point.