Systems and methods for brain activity interpretation
Inventors
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-11911171-B2
Publication Date
2024-02-27
Expiration Date
Abstract
A method includes receiving electroencephalographic (EEG) signal data recordings collected from a plurality of individuals via at least one EEG monitoring device. An optimized plurality of wavelet packet atoms is constructed based on the EEG signal data recordings and a mother wavelet. The optimized plurality of wavelet packet atoms is reordered to obtain an optimal reordered set of wavelet packet atoms. The optimal reordered set of wavelet packet atoms is normalized to obtain an optimal normalized set of wavelet packet atoms that is representative of brain activities of the plurality of individuals. A particular EEG signal data recording of a particular individual is received, which is projected onto the optimal normalized set of wavelet packet atoms to obtain an individual-specific set of projections for the particular individual on the optimal normalized set of wavelet packet atoms. A brain activity representation of the particular individual is generated based on the individual-specific set of projections.
Core Innovation
The invention provides a computer-implemented EEG interpretation framework that interfaces with at least one electroencephalographic (EEG) monitoring device to receive EEG signal data recordings collected from a plurality of individuals using an electrode combination with a recording electrode and a reference electrode applied to particular points on a head. The total number of electrodes in the electrode combination is less than the number of electrodes utilized by a standard 10/20 EEG system. The received EEG data is used to construct an optimized plurality of wavelet packet atoms based on the plurality of EEG signal data recordings and a mother wavelet.
The framework reorders the optimized plurality of wavelet packet atoms to obtain an optimal reordered set and normalizes the optimal reordered set to obtain an optimal normalized set representative of a plurality of brain activities of the plurality of individuals. For a particular EEG monitoring device attached to a particular individual using a single particular electrode combination with fewer electrodes than the standard 10/20 system, the framework projects the particular EEG signal data recording onto the optimal normalized set of wavelet packet atoms to obtain an individual-specific set of projections.
Based on the individual-specific set of projections, the framework generates a brain activity representation of the particular individual. The particular EEG data recording received via the single particular electrode combination is sufficient to generate the particular brain activity representation of the particular individual. In additional refinements, the brain activity representation may be used to identify an underlying mental state and/or an underlying neurological condition and assign at least one specific brain state using machine learning.
Further refinements include outputting a visual indication of the brain activity representation and relating the brain activity representation to therapy assessment, including anesthetic agent effectiveness and migraine therapy.
Claims Coverage
Two independent claims are provided: a method claim and a system claim. Across these independent claims, the core inventive features consist of EEG monitoring with fewer-than-10/20 electrodes using recording and reference electrodes on particular head points, constructing optimized wavelet packet atom representations from multiple individuals using a mother wavelet, including reordering and normalization to obtain an individual-interpretable atom basis, and projecting a single individual’s EEG recording onto the normalized atom basis to generate an individual-specific brain activity representation that is sufficient from limited-electrode input.
Fewer-than-10/20 EEG electrode combination with recording and reference electrodes
Interfacing with at least one electroencephalographic (EEG) monitoring device to receive a plurality of electroencephalographic (EEG) signal data recordings collected from a plurality of individuals via at least one electrode combination comprising a recording electrode and a reference electrode applied to particular points on a head of each individual, wherein a total number of electrodes is less than a number of electrodes utilized by a standard 10/20 EEG system.
Optimized, reordered, and normalized wavelet packet atom construction using a mother wavelet
Constructing an optimized plurality of wavelet packet atoms based on the plurality of EEG signal data recordings and a mother wavelet, reordering the optimized plurality of wavelet packet atoms to obtain an optimal reordered set of wavelet packet atoms, and normalizing the optimal reordered set of wavelet packet atoms to obtain an optimal normalized set of wavelet packet atoms that is representative of a plurality of brain activities of the plurality of individuals.
Single device, single electrode-combination projection onto normalized wavelet packet atoms
Interfacing with a particular EEG monitoring device, comprising a single particular electrode combination and attached to a head of a particular individual, to receive a particular EEG signal data recording of the particular individual, wherein a total number of electrodes of the single particular electrode combination is less than the number of electrodes utilized by the standard 10/20 EEG system, and projecting the particular EEG data recording onto the optimal normalized set of wavelet packet atoms to obtain an individual-specific set of projections for the particular individual.
Generating an individual-specific brain activity representation from sufficient limited-electrode EEG
Generating, based on the individual-specific set of projections, a brain activity representation of the particular individual, wherein the particular EEG data recording of the particular individual as received via the single particular electrode combination of the particular EEG monitoring device is sufficient to generate the particular brain activity representation of the particular individual.
The independent claims are directed to generating an individual-specific brain activity representation from EEG recordings obtained using a limited electrode count (less than standard 10/20), by projecting the EEG onto an optimized, reordered, and normalized wavelet packet atom set constructed from multi-individual data using a mother wavelet.
Stated Advantages
Enables generating a brain activity representation for a particular individual using EEG data sufficient from a single particular electrode combination with fewer electrodes than a standard 10/20 EEG system.
Documented Applications
Monitoring and diagnosis of neurological conditions, including Alzheimer’s disease, dementia, stress, fatigue, anxiety, epilepsy, traumatic brain injury, loss of cognitive function, migraine, chronic pain, coma, lack of response, autism spectrum disorders, and lack of concentration, as described in the dependent claim set.
Therapy assessment by determining, from changes in a brain activity representation, the effectiveness of an anesthetic agent in changing the individual’s ability to feel and/or perceive pain, and assessing migraine therapy effectiveness.
Brain-computer interface (BCI) command application, as described in the provided description summary.
Interested in licensing this patent?