DETECTION OF EPILEPTIFORM ACTIVITY

• US 20070197930A1
• Filed: 12/28/2006
• Published: 08/23/2007
• Est. Priority Date: 02/17/2006
• Status: Active Grant

• Current Assignee: General Electric Company
• Original Assignee: General Electric Company
• Inventors: SARKELA, Mika
• Granted Patent: US 9,579,035 B2
• Time in Patent Office: Days
• US Class Current: 600/544
• 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 5/4094 Diagnosing or monitoring seizure diseases, e.g. epilepsy
• CPC Class Codes: A61B 5/726 using Wavelet transforms
• CPC Class Codes: G06F 2218/08 Feature extraction

Abstract

The invention relates to detection of epileptiform activity. In order to accomplish a mechanism with improved specificity to epileptiform activity and with the capability to detect specific type of epileptic patterns, brain wave signal data obtained from a subject is decomposed into at least one predetermined subband, each subband being indicative of a specific type of epileptiform activity. The subband-specific output data obtained represents a time series of a quantitative characteristic of the brain wave signal data. At least one measure is determined for any one or more of the at least one predetermined subband, the at least one measure belonging to a measure set comprising a first measure indicative of the entropy of the subband-specific output data and a second measure indicative of a normalized form of k:th order central moment of the subband-specific output data, where k is an integer higher than three. The presence of a specific type of epileptiform activity may be detected based on the at least one measure of the respective subband.

Claims

1. A method for detecting epileptiform activity, the method comprising:

obtaining brain wave signal data from a subject;

decomposing the brain wave signal data into at least one predetermined subband, to obtain subband-specific output data representing a time series of a quantitative characteristic of the brain wave signal data, wherein each subband is indicative of a specific type of epileptiform activity;

determining at least one measure for at least one of the at least one predetermined subband, the at least one measure belonging to a measure set comprising a first measure indicative of the entropy of the subband-specific output data and a second measure indicative of a normalized form of k;

th order central moment of the subband-specific output data, where k is an integer higher than three; and

indicating, based on the at least one measure of the respective subband, whether a specific type of epileptiform activity is present in the brain wave signal data.

2. A method according to claim 1, wherein the brain wave signal data is selected from a group including electroencephalogram (EEG) signal data and magnetoencephalogram (MEG) signal data.

3. A method according to claim 1, wherein the decomposing includes employing at least one filter to obtain the subband-specific output data.

4. A method according to claim 1, wherein the at least one filter is configured to perform a wavelet transform.

5. A method according to claim 4, wherein the wavelet transform is a discrete wavelet transform.

6. A method according to claim 4, wherein the wavelet transform has a basis function from a group of Daubechies wavelets or from a group of Symmlet wavelets.

7. A method according to claim 1, wherein at least one of the at least one predetermined subband is indicative of epileptiform spikes or of phasic waveforms.

8. A method according to claim 1, wherein the determining includes determining one measure for each predetermined subband.

9. A method according to claim 1, wherein the indicating includes

comparing the at least one measure of each predetermined subband with a respective threshold value, whereby a comparison result is obtained for each predetermined sub-band;

deciding on the presence of a specific epileptiform activity in the brain wave signal data based on the comparison result of the respective subband, thereby to obtain presence information; and

presenting the presence information to a user.

10. A method according to claim 1, wherein the indicating includes presenting the at least one measure to a user.

11. A method according to claim 1, wherein the second measure is indicative of the kurtosis of wavelet coefficients of the respective subband.

12. An apparatus for detecting epileptiform activity, the apparatus comprising:

measurement means for obtaining brain wave signal data from a subject;

signal processing means for decomposing the brain wave signal data into at least one predetermined subband, each subband being indicative of a specific type of epileptiform activity and the signal processing means being configured to provide subband-specific output data representing a time series of a quantitative characteristic of the brain wave signal data;

calculation means for determining at least one measure for at least one of the at least one predetermined subband, the at least one measure belonging to a measure set comprising a first measure indicative of the entropy of the subband-specific output data and a second measure indicative of a normalized form of k;

th order central moment of the subband-specific output data, where k is an integer higher than three; and

indicator means for indicating, based on the at least one measure of the respective subband, whether a specific type of epileptiform activity is present in the brain wave signal data.

13. An apparatus according to claim 12, wherein the measurement means are configured to provide the brain wave data from a group including electroencephalogram (EEG) signal data and magnetoencephalogram (MEG) signal data.

14. An apparatus according to claim 12, wherein the signal processing means comprise at least one filter.

15. An apparatus according to claim 14, wherein the at least one filter is configured to perform a wavelet transform.

16. An apparatus according to claim 15, wherein the at least one filter is configured to perform a discrete wavelet transform.

17. An apparatus according to claim 15, wherein the at least one filter is configured to perform a wavelet transform having a basis function from a group of Daubechies wavelets or from a group of Symmlet wavelets.

18. An apparatus according to claim 12, wherein at least one of the at least one predetermined subband is indicative of epileptiform spikes or of phasic waveforms.

19. An apparatus according to claim 12, wherein the calculation means is configured to determine one measure for each predetermined subband.

20. An apparatus according to claim 12, wherein the indicator means is configured to

compare the at least one measure of each predetermined subband with a respective threshold value, thereby to obtain a comparison result for each predetermined sub-band;

decide on the presence of a specific epileptiform activity in the brain wave signal data based on the comparison result of the respective subband, thereby to obtain presence information; and

present the presence information to a user.

21. An apparatus according to claim 12, wherein the indicator means is configured to present the at least one measure to a user.

22. An apparatus according to claim 12, wherein the second measure is indicative of the kurtosis of the wavelet coefficients of the respective subband.

23. An apparatus for detecting epileptiform activity, the apparatus comprising:

a measurement module configured to obtain brain wave signal data from a subject;

a signal processing module configured to decompose the brain wave signal data into at least one predetermined subband, each subband being indicative of a specific type of epileptiform activity and the signal processing module being configured to provide subband-specific output data representing a time series of a quantitative characteristic of the brain wave signal data;

a calculation module configured to determine at least one measure for at least one of the at least one predetermined subband, the at least one measure belonging to a measure set comprising a first measure indicative of the entropy of the subband-specific output data and a second measure indicative of a normalized form of k;

th order central moment of the subband-specific output data, where k is an integer higher than three; and

a indicator module configured to indicate, based on the at least one measure of the respective subband, whether a specific type of epileptiform activity is present in the brain wave signal data.

24. An apparatus according to claim 23, wherein the signal processing module comprises at least one filter.

25. An apparatus according to claim 24, wherein the at least one filter is configured to perform a wavelet transform.

26. A computer program comprising computer program code means adapted to perform the steps of:

decomposing brain wave signal data obtained from a subject into at least one predetermined subband, each subband being indicative of a specific type of epileptiform activity, to obtain sub-band specific output data representing a time series of a quantitative characteristic of the brain wave signal data;

determining at least one measure for at least one of the at least one predetermined subband, the at least one measure belonging to a measure set comprising a first measure indicative of the entropy of the subband-specific output data and a second measure indicative of a normalized form of k;

th order central moment of the subband-specific output data, where k is an integer higher than three; and

indicating, based on the at least one measure of the respective subband, whether a specific type of epileptiform activity is present in the brain wave signal data.