NEUROPSYCHOLOGICAL SPATIOTEMPORAL PATTERN RECOGNITION

• US 20090297000A1
• Filed: 05/27/2007
• Published: 12/03/2009
• Est. Priority Date: 05/25/2006
• Status: Active Grant

• Current Assignee: ElMindA, Ltd.
• Original Assignee: ElMindA, Ltd.
• Inventors: Geva, Amir B., Shahaf, Goded
• Granted Patent: US 8,320,649 B2
• Time in Patent Office: Days
• US Class Current: 382/128
• CPC Class Codes: A61B 5/245 specially adapted for magnetoencephalographic [MEG] signals
• CPC Class Codes: A61B 5/374 Detecting the frequency distribution of signals, e.g. detecting delta, theta, alpha, beta or gamma waves
• CPC Class Codes: A61B 5/7246 using correlation, e.g. template matching or determination of similarity
• CPC Class Codes: A61B 5/7275 Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
• CPC Class Codes: G06F 17/18 for evaluating statistical data , e.g. average values, frequency distributions, probability functions, regression analysis forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04
• CPC Class Codes: G06F 18/2323 based on graph theory, e.g. minimum spanning trees [MST] or graph cuts
• CPC Class Codes: G06F 2218/14 by matching peak patterns
• CPC Class Codes: G16H 50/50 for simulation or modelling of medical disorders
• CPC Class Codes: G16Z 99/00 Subject matter not provided for in other main groups of this subclass

Abstract

Systems and methods for identifying and analyzing neuropsychological flow patterns, include creating a knowledge base of neuropsychological flow patterns. The knowledge base is formed by obtaining signals from multiple research groups for particular behavioral processes, localizing sources of activity participating in the particular behavioral processes, identifying sets of patterns of brain activity for the behavioral processes and neuropsychologically analyzing the localized sources and the identified patterns for each of the research groups. The neuropsychological analysis includes identifying all possible pathways for the identified sets of patterns, ranking the possible pathways based on likelihood for the particular behavioral process and reducing the number of ranked possible pathways based on additional constraints. A system for comparison of obtained signals from an individual to the created knowledge base is provided. These obtained signals are then used to further update the existing knowledge base.

Claims

1. A method for establishing a knowledge base of neuropsychological flow patterns, the method comprising:

obtaining signals from multiple subjects from one or more research groups for a particular behavioral process, wherein said signals comprise EEG signals;

determining source localization participating in said particular behavioral process for said research groups according to said signals;

identifying sets of patterns of brain activity for said behavioral process for said research groups;

neuropsychologically analyzing said source localization and said identified patterns for each of said research groups, said neuropsychologically analyzing comprising;

identifying a plurality of possible pathways for said identified sets of patterns;

ranking said possible pathways based on likelihood for said particular behavioral process; and

reducing the number of ranked possible pathways based on one or more additional constraints;

creating a set of flow patterns from said neuropsychologically analyzed sources and patterns, for each of said research groups; and

creating a knowledge base of said flow patterns, wherein said knowledge base is then used as a constraint for said reducing.

2. The method of claim 1, wherein said source localization is done prior to said identifying sets of patterns of brain activity for said behavioral process.

3. The method of claim 1, wherein said identifying sets of patterns of brain activity for said behavioral process is done prior to said source localization.

4. The method of claim 1, wherein said identifying sets of patterns is done using a counting method or method of calculating statistical significances of pairs.

6. The method of claim 1, wherein said constraints comprise one or more temporal constraints or one or more constraints obtained from published literature.

8. The method of claim 1, wherein said creating a set of flow patterns is done using a region matrix.

9. The method of claim 1, further comprising using said knowledge base to aid in said determining said source localization or identifying.

11. The method of claim 1, wherein said obtaining said signals from multiple subjects comprises administering one or more stimuli to said subjects.

12. The method of claim 1, wherein said behavioral process comprises spontaneous activity or a pathological process.

14. The method of claim 1, wherein said neuropsychologically analyzing said source localization and said identified patterns comprises arranging localized sources in a time series for analysis.

15. The method of claim 14, wherein said time series is analyzed to determine one or more of filtered waveforms, wavelets, or markers of wave amplitudes.

16. The method of claim 15, wherein said neuropsychologically analyzing said source localization and said identified patterns further comprises analyzing waveforms of varying frequencies and amplitudes over time for each electrode of said EEG.

17. The method of claim 16, wherein said analyzing said waveforms further comprises performing frequency separation into a plurality of bands and peaks.

18. The method of claim 17, wherein said neuropsychologically analyzing said source localization and said identified patterns further comprises relating said identified patterns to one or more of a behavioral function, pathology or one or more behavioral sub-functions.

5. (canceled)

7. (canceled)

10. (canceled)

13. (canceled)

19. A system for neuropsychological brain activity analysis, the system comprising:

a signal collector for collecting EEG signals from a testing subject;

a processor, said processor comprising a pattern generator for generating patterns based on said collected signals, a neuropsychological analyzer for translating said generated patterns into neuropsychologically accurate pathways for particular tasks, flow pattern knowledge base having previously determined neuropsychological pathways, and a pattern comparator for comparing said collected signals to said flow pattern knowledge base; and

an output module for presenting results of said comparison.

20. The system of claim 19, wherein said signal collector comprises electrodes configured to be placed on a testing subject.

21. The system of claim 20, wherein said pattern comparator includes a parser.

22. The system of claim 21, wherein said parser is configured to match patterns for a cognitive behavior or a particular task.

24. The system of claim 19, wherein said output module comprises a workstation including a feedback loop provider configured to receive results from said pattern comparator and to provide a stimulus to the testing subject based on said received results.

25. The system of claim 24, wherein said feedback loop provider provides stimuli comprising one or more of neurofeedback or peripheral feedback.

26. The system of claim 25, wherein said stimuli comprise multi-sensory feedback.

27. The system of claim 25, wherein said feedback loop provider provides said stimuli for diagnosing or treating the testing subject.

23. (canceled)

28. (canceled)

29. A knowledge base of flow patterns comprised of at least one set of flow patterns corresponding to a neuropsychological behavior, said set of flow patterns established based on identification and neuropsychological analysis of patterns of brain activity from multiple subjects during performance of said neuropsychological behavior and wherein said at least one set is comparable to a flow pattern obtained from an individual subject, and wherein said knowledge base is adapted for additional neuropsychological analysis.

30. The knowledge base of claim 29, wherein said neuropsychological analysis includes identification of possible pathways for said identified patterns of brain activity and reduction of the number of said identified possible pathways based on neuropsychological constraints.

31. The knowledge base of claim 30, wherein said at least one set of flow patterns includes multiple sets of flow patterns, each of said multiple sets corresponding to different neuropsychological behaviors.

32. The knowledge base of claim 31, wherein at least one of said multiple sets corresponds to a control group of subjects.

33. The knowledge base of claim 29, wherein said signals are obtained from an EEG or a method including one or more of fMRI, PET, optical imaging or MEG.

35. A method for analyzing signals from a brain of a subject, comprising:

obtaining said signals from the brain of the subject;

determining a pattern for said signals;

comparing said pattern to a plurality of patterns in the knowledge base of claim 29; and

identifying a similar pattern from the knowledge base.

36. The method of claim 35, wherein said determining said pattern for said signals comprises:

determining source localization for said signals to form localized sources;

arranging said signals for said localized sources in a time series; and

determining at least one temporal relationship between said localized sources.

37. The method of claim 36, wherein a plurality of temporal relationships is determined and wherein said determining said pattern further comprises combining one or more temporal relationships to form said pattern.

38. The method of claim 37, wherein said combining said one or more temporal relationships is performed at least partially according to one or more patterns from the knowledge base.

39. The method of claim 35, wherein said signals are obtained from an EEG or a method including one or more fMRI, PET, optical imaging or MEG.

34. (canceled)

40. (canceled)

41. A method for analyzing signals from a brain of a subject, comprising:

obtaining signals according to a method selected from the group consisting of EEG, fMRI, PET, optical imaging or MEG;

determining source localization for said signals to form a plurality of localized sources;

arranging said localized sources into a time series; and

analyzing said time series to form a pattern by combining said localized sources into a flow pattern according to a probability calculation.

42. The method of claim 41, wherein said obtaining said signals comprises presenting the subject with stimuli and wherein said probability calculation is determined according to at least one previously obtained pattern with said stimuli.