Systems and methods for brain activity interpretation

• US 9,955,905 B2
• Filed: 02/16/2016
• Issued: 05/01/2018
• Est. Priority Date: 02/16/2015
• Status: Active Grant

• Current Assignee: Neurosteer Inc.
• Original Assignee: Neurosteer Ltd.
• Inventors: Intrator, Nathan
• Primary Examiner(s): HARWARD, SOREN T
• Application Number:
  US15/045,089
• Publication Number:
  US 20160235351A1
• Time in Patent Office: 805 Days
• Field of Search: None
• CPC Class Codes: A61B 5/0022 Monitoring a patient using a global network, e.g. telephone networks, internet
• CPC Class Codes: A61B 5/165 Evaluating the state of mind, e.g. depression, anxiety
• CPC Class Codes: A61B 5/291 for electroencephalography [EEG]
• 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 5/4076 Diagnosing or monitoring particular conditions of the nervous system A61B5/4821, A61B5/4824 take precedence
• CPC Class Codes: A61B 5/4088 Diagnosing of monitoring cognitive diseases, e.g. Alzheimer, prion diseases or dementia
• CPC Class Codes: A61B 5/4824 Touch or pain perception evaluation A61B5/4821 takes precedence
• CPC Class Codes: A61B 5/4848 Monitoring or testing the effects of treatment, e.g. of medication
• CPC Class Codes: A61B 5/726 using Wavelet transforms
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• CPC Class Codes: G06F 17/148 Wavelet transforms
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients

Abstract

The present invention provides a computer-implemented method, including:

• • a. obtaining, in real-time, by a specifically programmed processor, electrical signal data representative of brain activity of a particular individual;
  • b. processing, in real-time the electrical signal data representative of brain activity of a particular individual based upon a pre-determined predictor associated with a particular brain state, selected from a library of predictors containing a plurality of pre-determined predictors, wherein each individual pre-determined predictor is associated with a unique brain state,
    • wherein the pre-determined predictor associated with a particular brain state includes:
      • i. a pre-determined mother wavelet,
      • ii. a pre-determined representative set of wavelet packet atoms, created from the pre-determined mother wavelet,
      • iii. a pre-determined ordering of wavelet packet atoms, and
      • iv. a pre-determined set of normalization factors,
    • wherein the processing includes:
      • i. causing, by the specifically programmed processor, the electrical signal data to be deconstructed into a plurality of pre-determined deconstructed wavelet packet atoms, utilizing the pre-determined representative set of wavelet packet atoms,
        • wherein time windows of the electrical signal data are projected onto the pre-determined representative set of wavelet packet atoms
        •  wherein the projection is via convolution or inner product, and
        • wherein each pre-determined representative wavelet packet atom corresponds to a particular pre-determined brain activity feature from a library of a plurality of pre-determined brain activity features;
      • ii. storing the plurality of pre-determined deconstructed wavelet packet atoms in at least one computer data object;
      • iii. causing, by the specifically programmed processor, the stored plurality of pre-determined deconstructed wavelet packet atoms to be re-ordered within the computer data object, based on utilizing a pre-determined order;
      • iv. obtaining a statistical measure of the activity of each of the re-ordered plurality of pre-determined deconstructed wavelet packet atoms; and
      • v. normalizing the re-ordered plurality of pre-determined wavelet packet atoms, based on utilizing a pre-determined normalization factor; and
  • c. outputting, a visual indication of at least one personalized mental state of the particular individual, at least one personalized neurological condition of the particular individual, or both, based on the processing,
    • wherein the individual pre-determined predictor associated with a particular brain state from within the plurality of pre-determined predictors is generated by the steps including:
      • i. obtaining the pre-determined representative set of wavelet packet atoms by:
        • a. obtaining from a plurality of individuals, by the specifically programmed processor, at least one plurality of electrical signal data representative of a brain activity of a particular brain state;
        • b. selecting a mother wavelet from a plurality of mother wavelets,
        •  wherein mother wavelet is selected from an wavelet family selected from the group consisting of: Haar, Coiflet Daubehies, and Mayer wavelet families;
        • c. causing, by the specifically programmed processor, the at least one plurality electrical signal data to be deconstructed into a plurality of wavelet packet atoms, using the selected mother wavelet;
        • d. storing the plurality of wavelet packet atoms in at least one computer data object;
        • e. determining, an optimal set of wavelet packet atoms using the pre-determined mother wavelet, and storing the optimal set of wavelet packet atoms in at least one computer data object,
        •  wherein the determining is via utilizing analysis Best Basis algorithm; and
        • f. applying, by the specifically programmed processor, wavelet denoising to the number of wavelet packet atoms in the optimal set;
      • ii. obtaining the pre-determined ordering of wavelet packet atoms by:
        • a. projecting, by the specifically programmed processor, the at least one plurality of electrical signal data representative of a brain activity for each 4 second window of the data onto the pre-determined representative set of wavelet packet atoms;
        • b. storing the projections in at least one computer data object;
        • c. determining, by the specifically programmed processor, the wire length for every data point in the projection by determining the mean absolute distance of the statistical measure of the projections of different channels from their adjacent channels;
        • d. storing the wire length data in at least one computer data object; and
        • e. re-ordering the stored projections, by the specifically programmed computer to minimize a statistical value of the wire length value across each time window, and across all individuals within the plurality of individuals, and across the projections; and
      • iii. obtaining the pre-determined set of normalization factors by:
        • a. determining, by the specifically programmed computer, the mean and standard deviation of the values of the stored projections.

Claims

1. A method for detection of at least one abnormal electrical brain activity, comprising:

a) utilizing a first electroencephalographic (EEG) monitoring device having a first set of three electrodes and applying the first set of three electrodes to particular points on a head of each individual of a plurality of individuals, wherein the three electrodes of the first set are;

1) a first recording electrode,

2) a second recording electrode, and

3) a reference electrode;

b) collecting, by the first EEG monitoring device, at least 100 recordings of electrical signal data representative of brain activity of the plurality of individuals to form recorded electrical data;

c) utilizing a first processor configured, when executing a first set of software instructions stored in a first non-transient computer-readable hardware storage medium, to perform at least the following operations;

1) obtaining a pre-determined ordering of a denoised optimal set of wavelet packet atoms, by;

i) obtaining an optimal set of wavelet packet atoms from the recorded electrical signal data from the recordings from the plurality of individuals, by;

1) selecting a mother wavelet;

2) determining an optimal set of wavelet packet atoms, by;

 

a) deconstructing the recorded electrical signal data into a plurality of wavelet packet atoms, using the selected mother wavelet;

 

b) storing the plurality of wavelet packet atoms in at least one first computer data object;

 

c) determining the optimal set of wavelet packet atoms using the pre-determined mother wavelet and storing the optimal set of wavelet packet atoms in at least one second computer data object, wherein the determining is via utilizing a Coifman-Wickerhauser Best Basis algorithm;

ii) denoising the obtained optimal set of wavelet packet atoms from the recordings from the plurality of individuals;

iii) reordering the denoised optimal set of wavelet packet atoms from the recorded electrical signal data from the plurality of individuals to obtain a pre-determined ordering of the denoised optimal set of wavelet packet atoms, by determining a minimum path based on;

1) projecting the recorded electrical signal data onto the denoised optimal set of wavelet packet atoms to obtain a set of projections,

wherein a projection is a result of a convolution of an electrical signal in each time window of the signal and a wavelet packet atom;

2) determining a collection of wire lengths within the set of projections;

3) storing the collection of wire lengths for the set of projections in at least one third computer data object;

4) iteratively determining a plurality of (i) orders of the projections, and (ii) respective wire lengths, by;

i) determining the wire length between every two projections by at least one of;

 

1) determining either mean or sum of absolute distance of a statistical measure of an energy of each projection from adjacent projections, and

 

2)1 - a correlation of every two projections onto the wavelet packet atoms; and

ii) storing the wire length data in at least one fourth computer data object;

5) determining, from the plurality of respective wire lengths, a particular order of projections that minimizes either the mean or sum of the wire lengths across the projections, across each time window, and across all individuals within the plurality of individuals;

d) defining a set of pre-determined normalization factors, and storing the pre-determined normalization factors in at least one fifth computer data object;

e) utilizing a second EEG monitoring device having a second set of three electrodes and applying the second set of three electrodes to the particular points on a head of a particular individual;

f) collecting, by the second EEG monitoring device, in real-time, a recording of particular electrical signal data representative of brain activity of the particular individual;

g) utilizing a second processor configured, when executing a second set of software instructions stored in a second non-transient computer-readable hardware storage medium, to further perform at least the following additional operations;

1) projecting, in real time, the collected particular electrical signal data representative of the brain activity of the particular individual onto the pre-determined ordering of the denoised optimal set of wavelet packet atoms to obtain a particular set of projections of the particular individual;

2) normalizing, in real time, the particular set of projections of the particular individual using the pre-determined set of normalization factors to form a particular set of normalized projections of the particular individual;

3) applying at least one machine learning algorithm to the particular set of normalized projections of the particular individual to determine, in real time, at least one particular normalized projection in the particular set of normalized projections which corresponds to the at least one abnormal electrical brain activity, wherein the processor is configured to determine the at least one abnormal electrical brain activity from the particular set of normalized projections of the particular individual; and

4) generating, in real time, an indication of the at least one abnormal electrical brain activity of the particular individual.

2. The method of claim 1,

wherein the second set of software instructions causes the second processor to further perform:

assigning, based on energy of each normalized projection of the particular individual, a plurality of colors to the particular set of normalized projections of the particular individual; and

wherein the indication comprises an output that is configured to visually illustrate, via a color of the at least one particular normalized projection, when the at least one abnormal electrical brain activity of the particular individual has occurred at a particular time.

3. The method of claim 1, wherein the mother wavelet is selected from the group consisting of:

Haar, Coiflet Daubehies, and Meyer wavelet families.

4. The method of claim 1, wherein the second set of three electrodes is located on a forehead of the particular individual.

5. A method for detection of at least one abnormal electrical brain activity, comprising:

utilizing a first electroencephalographic (EEG) monitoring device having a first set of three electrodes and applying the first set of three electrodes to particular points on a head of each individual of a plurality of individuals;

collecting, by the first EEG monitoring device, at least 100 recordings of electrical signal data representative of brain activity of the plurality of individuals to form recorded electrical data;

utilizing a first processor configured, when executing a first set of software instructions stored in a first non-transient computer-readable hardware storage medium, to perform at least the following operations;

1) obtaining a pre-determined ordering of a denoised optimal set of wavelet packet atoms, by;

i) obtaining an optimal set of wavelet packet atoms from the recorded electrical signal data from the recordings from the plurality of individuals, by;

1) selecting a mother wavelet;

2) determining an optimal set of wavelet packet atoms, by;

 

a) deconstructing the recorded electrical signal data into a plurality of wavelet packet atoms, using the selected mother wavelet,

 

b) storing the plurality of wavelet packet atoms in at least one first computer data object;

 

c) determining the optimal set of wavelet packet atoms using the pre-determined mother wavelet and storing the optimal set of wavelet packet atoms in at least one second computer data object, wherein the determining is via utilizing a Coifman-Wickerhauser Best Basis algorithm;

2) denoising the obtained optimal set of wavelet packet atoms from the recordings from the plurality of individuals;

3) reordering the denoised optimal set of wavelet packet atoms from the recorded electrical signal data from the recordings from the plurality of individuals to obtain a pre-determined ordering of the denoised optimal set of wavelet packet atoms, by determining a minimum path based on;

a) projecting the recorded electrical signal data onto the denoised optimal set of wavelet packet atoms to obtain a set of projections,

wherein a projection is a result of a convolution of an electrical signal in each time window of the signal and a wavelet packet atom;

b) determining a collection of wire lengths for every data point within the set of projections;

c) storing the collection of wire lengths for the set of projections in at least one third computer data object

d) iteratively determining a plurality of (i) orders of the projections, and (ii) respective wire lengths, by;

1) determining the wire length between every two projections by at least one of;

 

i) determining either mean or sum of absolute distance of a statistical measure of an energy of each projection from adjacent projections, and

 

ii) 1 - a correlation of every two projections onto the wavelet packet atoms; and

2) storing the wire length data in at least one fourth computer data object;

e) determining, from the plurality of respective wire lengths, a particular order of projections that minimizes either the mean or sum of the wire lengths across the projections, across each time window, and across all individuals within the plurality of individuals; and

f) defining a set of pre-determined normalization factors, and storing the set of pre-determined normalization factors in at least one fifth computer data object;

utilizing a second EEG monitoring device having a second set of three electrodes and applying the second set of three electrodes to particular points on a head of a particular individual, wherein the three electrodes of the second set are;

1) a first recording electrode,

2) a second recording electrode, and

3) a reference electrode;

collecting, by the second EEG monitoring device, in real-time, a recording of electrical signal data representative of brain activity of the particular individual;

utilizing a second processor configured, when executing a second set of software instructions stored in a second non-transient computer-readable hardware storage medium, to perform at least the following operations;

1) projecting, in real time, the collected particular electrical signal data representative of the brain activity of the particular individual onto the pre-determined ordering of the denoised optimal set of wavelet packet atoms to obtain a particular set of projections of the particular individual;

2) normalizing, in real time, the particular set of projections of the particular individual using the set of pre-determined normalization factors to form a particular set of normalized projections of the particular individual;

3) applying at least one machine learning algorithm to the particular set of normalized projections of the particular individual to determine, in real time, at least one particular normalized projection in the particular set of normalized projections which corresponds to at least one particular abnormal electrical brain activity, wherein the processor is configured to determine the at least one particular abnormal electrical brain activity from the particular set of normalized projections of the particular individual; and

4) generating, in real time, an output associating the at least one particular normalized projection of the particular set of normalized projections of the particular individual to the at least one particular abnormal electrical brain activity.

6. The method of claim 5, wherein the mother wavelet is selected from the group consisting of:

Haar, Coiflet Daubehies, and Meyer wavelet families.

7. The method of claim 5, wherein the second set of software instructions causes the second processor to further perform:

assigning, based on energy of each normalized projection of the particular individual, a plurality of colors to the particular set of normalized projections of the particular individual of the particular individual; and

wherein the output comprises a map that is configured to visually illustrate, via a color of the at least one particular normalized projection, when the at least one abnormal electrical brain activity of the particular individual has occurred at a particular time.

8. The method of claim 5, wherein the second set of three electrodes is located on a forehead of the particular individual.

9. A method for determining a state of pain being felt by a particular individual at a particular state of anesthesia, comprising:

a) utilizing a first electroencephalographic (EEG) monitoring device having a first set of three electrodes and applying the first set of three electrodes to particular points on a head of each individual of a plurality of individuals, wherein the three electrodes of the first set are;

1) a first recording electrode,

2) a second recording electrode, and

3) a reference electrode;

b) collecting, by the first EEG monitoring device, at least 100 recordings of electrical signal data representative of brain activity of the plurality of individuals to form recorded electrical data;

c) utilizing a first processor configured, when executing a first set of software instructions stored in a non-transient computer-readable hardware storage medium, to perform at least the following operations;

1) obtaining a pre-determined ordering of a denoised optimal set of wavelet packet atoms, by;

i) obtaining an optimal set of wavelet packet atoms from the recorded electrical signal data from the recordings from the plurality of individuals, by;

1) selecting a mother wavelet;

2) determining an optimal set of wavelet packet atoms, by;

 

a) deconstructing the recorded into a plurality of wavelet packet atoms, using the selected mother wavelet;

 

b) storing the plurality of wavelet packet atoms in at least one first computer data object;

 

c) determining the optimal set of wavelet packet atoms using the pre-determined mother wavelet and storing the optimal set of wavelet packet atoms in at least one second computer data object, wherein the determining is via utilizing a Coifman-Wickerhauser Best Basis algorithm;

ii) denoising the obtained optimal set of wavelet packet atoms from the recordings from the plurality of individuals;

iii) reordering the denoised optimal set of wavelet packet atoms from the recorded electrical signal data from the recordings from the plurality of individuals to obtain a pre-determined ordering of the denoised optimal set of wavelet packet atoms, by determining a minimum path based on;

1) projecting the recorded electrical signal data onto the denoised optimal set of wavelet packet atoms to obtain a set of projections,

wherein a projection is a result of a convolution of an electrical signal in each time window of the signal and a wavelet packet atom;

2) determining a collection of wire lengths for every data point within the set of projections;

3) storing the collection of wire lengths for the set of projections in at least one third computer data object;

4) iteratively determining a plurality of (i) orders of the projections, and (ii) respective wire lengths, by;

i) determining the wire length between every two projections by at least one of;

 

1) determining either mean or sum of absolute distance of a statistical measure of an energy of each projection from adjacent projections, and

 

2) 1 - a correlation of every two projections onto the wavelet packet atoms; and

ii) storing the wire length data in at least one fourth computer data object;

5) determining, from the plurality of respective wire lengths, a particular order of projections that minimizes either the mean or sum of the wire lengths across the projections, across each time window, and across all individuals within the plurality of individuals;

d) defining a set of pre-determined normalization factors, and storing the pre-determined normalization factors in at least one fifth computer data object;

e) utilizing a second EEG monitoring device having a second set of three electrodes and applying the second set of three electrodes to the particular points on a head of a particular individual;

f) collecting, by the second EEG monitoring device, in real-time, a recording of particular electrical signal data representative of brain activity of the particular individual;

g) utilizing a second processor configured to further perform at least the following additional operations when executing a second set of software instructions stored in the non-transient computer-readable hardware storage medium;

1) projecting, in real time, the collected particular electrical signal data representative of the brain activity of the particular individual onto the pre-determined ordering of the denoised optimal set of wavelet packet atoms to obtain a particular set of projections of the particular individual;

2) normalizing, in real time, the particular set of projections of the particular individual using the pre-determined set of normalization factors to form a particular set of normalized projections of the particular individual;

3) applying at least one machine learning algorithm to the particular set of normalized projections of the particular individual to determine, in real time, at least one particular normalized projection in the particular set of normalized projections which corresponds to the state of pain being felt by the particular individual at the particular state of anesthesia, wherein the processor is configured to determine the state of pain being felt by the particular individual at the particular state of anesthesia from the particular set of normalized projections of the particular individual; and

4) generating, in real time, an indication of the state of pain being felt by the particular individual at the particular state of anesthesia.

10. The method of claim 9, wherein the mother wavelet is selected from the group consisting of:

Haar, Coiflet Daubehies, and Meyer wavelet families.

11. The method of claim 9, wherein the method further comprises:

administering, based on the indication, a dose of an anesthetic to the particular individual.

12. The method of claim 9, wherein the indication is configured to cause a stop in a medical procedure being performed on the particular individual.

13. The method of claim 9, wherein the second set of software instructions causes the second processor to further perform:

assigning, based on energy of each normalized projection of the particular individual, a plurality of colors to the particular set of normalized projections of the particular individual of the particular individual; and

wherein the indication comprises an output that is configured to visually illustrate, via a color of the at least one particular normalized projection, the state of pain being felt by the particular individual at the particular state of anesthesia at a particular time.

14. The method of claim 9, wherein the second set of three electrodes is located on a forehead of the particular individual.

15. A method for determining a state of pain being felt by a particular individual at a particular state of anesthesia, comprising:

utilizing a first electroencephalographic (EEG) monitoring device having a first set of three electrodes and applying the first set of three electrodes to particular points on a head of each individual of a plurality of individuals;

collecting, by the first EEG monitoring device, at least 100 recordings of electrical signal data representative of brain activity of the plurality of individuals to form recorded electrical data;

utilizing a first processor configured, when executing a second set of software instructions stored in a non-transient computer-readable hardware storage medium, to perform at least the following operations;

1) obtaining a pre-determined ordering of a denoised optimal set of wavelet packet atoms, by;

i) obtaining an optimal set of wavelet packet atoms from the recorded electrical signal data from the recordings from the plurality of individuals, by;

1) selecting a mother wavelet;

2) determining an optimal set of wavelet packet atoms, by;

 

a) deconstructing the recorded electrical signal data into a plurality of wavelet packet atoms, using the selected mother wavelet;

 

b) storing the plurality of wavelet packet atoms in at least one first computer data object;

 

c) determining the optimal set of wavelet packet atoms using the pre-determined mother wavelet and storing the optimal set of wavelet packet atoms in at least one second computer data object, wherein the determining is via utilizing a Coifman-Wickerhauser Best Basis algorithm;

2) denoising the obtained optimal set of wavelet packet atoms from the recordings from the plurality of individuals;

3) reordering the denoised optimal set of wavelet packet atoms from the recorded electrical signal data from the recordings from the plurality of individuals to obtain a pre-determined ordering of the denoised optimal set of wavelet packet atoms, by determining a minimum path based on;

a) projecting the recorded electrical signal data onto the denoised optimal set of wavelet packet atoms to obtain a set of projections,

wherein a projection is a result of a convolution of an electrical signal in each time window of the signal and a wavelet packet atom;

b) determining a collection of wire lengths for every data point within the set of projections;

c) storing the collection of wire lengths for the set of projections in at least one third computer data object;

d) iteratively, determining a plurality of (i) orders of the projections, and (ii) respective wire lengths, by;

1) determining the wire length between every two projections by at least one of

 

i) determining either mean or sum of absolute distance of a statistical measure of an energy of each projection from adjacent projections, and

 

ii) 1 - a correlation of every two projections onto the wavelet packet atoms; and

2) storing the wire length data in at least one fourth computer data object;

e) determining, from the plurality of respective wire lengths, a particular order of projections that minimizes either the mean or sum of the wire lengths across the projections, across each time window, and across all individuals within the plurality of individuals; and

f) defining a set of pre-determined normalization factors, and storing the pre-determined normalization factors in at least one fifth computer data object;

utilizing a second EEG monitoring device having a second set of three electrodes and applying the second set of three electrodes to particular points on a head of a particular individual, wherein the three electrodes of the second set are;

1) a first recording electrode,

2) a second recording electrode, and

3) a reference electrode;

collecting, by the second EEG monitoring device, in real-time, a recording of electrical signal data representative of brain activity of the particular individual;

utilizing a second processor configured, when executing a second set of software instructions stored in a second non-transient computer-readable hardware storage medium, to perform at least the following operations;

1) projecting, in real time, the collected particular electrical signal data representative of the brain activity of the particular individual onto the pre-determined ordering of the denoised optimal set of wavelet packet atoms to obtain a particular set of projections of the particular individual;

2) normalizing, in real time, the particular set of projections of the particular individual using the set of pre-determined normalization factors to form a particular set of normalized projections of the particular individual;

3) applying at least one machine learning algorithm to the particular set of normalized projections of the particular individual to determine, in real time, at least one particular normalized projection in the particular set of normalized projections which corresponds to the state of pain being felt by the particular individual at the particular state of anesthesia, wherein the processor is configured to determine the state of pain being felt by the particular individual at the particular state of anesthesia from the particular set of normalized projections of the particular individual;

4) generating, in real time, an output associating the at least one particular normalized projection of the particular set of normalized projections of the particular individual to the state of pain being felt by the particular individual at the particular state of anesthesia.

16. The method of claim 15, wherein the mother wavelet is selected from the group consisting of:

Haar, Coiflet Daubehies, and Meyer wavelet families.

17. The method of claim 15, wherein the method further comprises:

administering, based on the output, a dose of an anesthetic to the particular individual.

18. The method of claim 15, wherein the output is configured to cause a stop in a medical procedure being performed on the particular individual.

19. The method of claim 15, wherein the second set of software instructions causes the second processor to further perform:

assigning, based on energy of each normalized projection of the particular individual, a plurality of colors to the particular set of normalized projections of the particular individual of the particular individual; and

wherein the output comprises a map that is configured to visually illustrate, via a color of the at least one particular normalized projection, the state of pain being felt by the particular individual at the particular state of anesthesia at a particular time.

20. The method of claim 15, wherein the second set of three electrodes is located on a forehead of the particular individual.