Neurophysiological data analysis using spatiotemporal parcellation

• US 10,136,830 B2
• Filed: 11/13/2013
• Issued: 11/27/2018
• Est. Priority Date: 11/13/2012
• Status: Active Grant

• Current Assignee: ElMindA, Ltd.
• Original Assignee: ElMindA, Ltd.
• Inventors: Geva, Amir B., Stern, Yaki, Reches, Amit
• Primary Examiner(s): JANG, CHRISTIAN YONGKYUN
• Application Number:
  US14/442,407
• Publication Number:
  US 20160038049A1
• Time in Patent Office: 1,840 Days
• CPC Class Codes: A61B 5/0036 including treatment, e.g., using an implantable medical device, ablating, ventilating
• CPC Class Codes: A61B 5/0042 for the brain
• CPC Class Codes: A61B 5/0515 Magnetic particle imaging
• CPC Class Codes: A61B 5/0522 Magnetic induction tomography
• CPC Class Codes: A61B 5/055 involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
• CPC Class Codes: A61B 5/165 Evaluating the state of mind, e.g. depression, anxiety
• 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 5/377 using evoked responses
• CPC Class Codes: A61B 5/4064 Evaluating the brain A61B5/031, A61B5/369, A61B5/14553 take precedence
• CPC Class Codes: A61B 5/4076 Diagnosing or monitoring particular conditions of the nervous system A61B5/4821, A61B5/4824 take precedence
• CPC Class Codes: A61B 5/7246 using correlation, e.g. template matching or determination of similarity
• CPC Class Codes: A61B 5/7267 involving training the classification device
• 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: A61B 5/7282 Event detection, e.g. detecting unique waveforms indicative of a medical condition A61B5/4094, A61B5/4818, A61B5/349, A61B5/0823 take precedence
• CPC Class Codes: A61N 1/36135 using physiological parameters
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06T 11/206 Drawing of charts or graphs
• CPC Class Codes: G06T 2207/30016 Brain
• 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

A method of analyzing neurophysiological data recorded from a subject is disclosed. The method comprises identifying activity-related features in the data, and parceling the data according to the activity-related features to define a plurality of capsules, each representing a spatiotemporal activity region in the brain. The method further comprises comparing at least some of the defined capsules to at least one reference capsule, and estimating a brain function of the subject based on the comparison.

Claims

1. A method of analyzing neurophysiological data recorded from a brain of a subject, the method comprising:

recording the neurophysiological data by a plurality of measuring devices respectively placed at a plurality of different locations on the scalp of the subject,

operating a data processor for;

identifying activity-related features in the data;

parceling the data according to said activity-related features to define a plurality of capsules, each representing a spatiotemporal activity region in the brain and corresponding to an extremum of the data and a spatiotemporal neighborhood defined as a spatial region in which said extremum is located and a time-interval during which said extremum occurs, wherein a size of said neighborhood is determined based on a property of said extremum;

storing said capsules in a memory;

comparing at least some of said defined capsules to at least one reference capsule;

estimating a brain function of the subject based on said comparison and;

generating on a display an output indicative of said brain function.

2. The method according to claim 1, wherein said comparison comprises calculating, for each of said at least some of said defined capsules, a statistical score of a spatiotemporal vector corresponding to said capsule using multidimensional statistical distribution describing a respective database capsule.

3. The method according to claim 2, wherein each entry of said database is also associated with a weight, and the method further comprises weighing said statistical score using said weight.

4. The method according to claim 2, further comprising calculating a correlation between said capsule and a respective database capsule.

5. The method according to claim 1, wherein said comparison is executed irrespective of any inter-capsule relation.

6. The method according to claim 5, wherein said inter-capsule relation comprises at least one of spatial proximity between two defined capsules, temporal proximity between two defined capsules, spectral proximity between two defined capsules, and energetic proximity between two defined capsules.

7. The method according to claim 1, further comprising determining inter-capsule relations among said capsules, and constructing a capsule network pattern responsively to said inter-capsule relations, wherein said database comprises database capsule network patterns, and where said comparison comprises comparing said constructed pattern to said database pattern.

8. The method according to claim 1, wherein said at least one reference capsule comprises an annotated database capsule stored in a database having a plurality of entries, and the method further comprises accessing said database.

9. The method according to claim 1, wherein said at least one reference capsule comprises a baseline capsule defined using neurophysiological data acquired from the same subject at a different time, and the method comprises comparing the variation of said capsule relative to said baseline capsule, to a previously stored variation of a first capsule annotated as normal and a second capsule also annotated as normal.

10. The method according to claim 1, wherein said at least one reference capsule comprises a capsule defined using neurophysiological data acquired form a different subject.

11. The method according to claim 1, further comprising:

constructing a brain network activity (BNA) pattern having a plurality of nodes, each representing a feature of said activity-related features;

assigning a connectivity weight to each pair of nodes in said BNA pattern;

comparing said constructed BNA to at least one reference BNA pattern;

wherein said estimation of said a brain function of the subject is also based on said comparison to said reference BNA.

12. The method according to claim 11, wherein said at least one reference BNA pattern comprises an annotated BNA pattern stored in a BNA database having a plurality of entries, and the method further comprises accessing said database.

13. The method according to claim 11, wherein said at least one reference BNA pattern comprises a baseline BNA pattern extracted from neurophysiological data acquired from the same subject at a different time.

14. The method according to claim 11, wherein said at least one reference BNA pattern comprises a BNA pattern extracted from neurophysiological data acquired form a different subject or a group of subjects.

15. The method according to claim 1, further comprising, prior to said comparison, applying a feature selection procedure to said plurality of capsules to provide at least one sub-set of capsules, wherein said comparison is executed separately for each of said at least one sub-set of capsules.

16. The method according to claim 1, wherein said brain function is a temporary abnormal brain function.

17. The method according to claim 1, wherein said brain function is a chronic abnormal brain function.

18. The method according to claim 1, wherein said brain function is a response to a stimulus or lack thereof.

19. The method according to claim 1, comprising assessing the likelihood of brain concussion.

20. The method according to claim 1, comprising applying local stimulation to the brain responsively to said estimated brain function, said local stimulation being at one or more locations corresponding to a spatial location of at least one of said capsules.

21. The method according to claim 1, comprising applying local stimulation to the brain responsively to said estimated brain function.

22. The method according to claim 21, wherein said local stimulation is at one or more locations corresponding to a spatial location of at least one of said capsules.

23. The method according to claim 21, wherein said estimation of said brain function is executed repeatedly, and the method comprises varying said local stimulation responsively to variations in said brain function.

24. The method according to claim 21, wherein said local stimulation comprises transcranial stimulation.

25. The method according to claim 21, wherein said local stimulation comprises transcranial direct current stimulation (tDCS).

26. The method according to claim 21, wherein said local stimulation comprises high-definition transcranial direct current stimulation (HD-tDCS).

27. The method according to claim 21, wherein said local stimulation comprises electrocortical stimulation on the cortex.

28. The method according to claim 21, wherein said local stimulation comprises deep brain stimulation.

29. The method according to claim 21, wherein said local stimulation comprises both transcranial stimulation and deep brain stimulation, and wherein said transcranial stimulation is executed to control activation thresholds for said deep brain stimulation.

30. The method according to claim 20, wherein said local stimulation comprises both transcranial stimulation and deep brain stimulation, and wherein said transcranial stimulation is executed to control activation thresholds for said deep brain stimulation.