WO2019103188A1 - System and method for evaluating traumatic brain damage through brain wave analysis - Google Patents

System and method for evaluating traumatic brain damage through brain wave analysis Download PDF

Info

Publication number
WO2019103188A1
WO2019103188A1 PCT/KR2017/013455 KR2017013455W WO2019103188A1 WO 2019103188 A1 WO2019103188 A1 WO 2019103188A1 KR 2017013455 W KR2017013455 W KR 2017013455W WO 2019103188 A1 WO2019103188 A1 WO 2019103188A1
Authority
WO
WIPO (PCT)
Prior art keywords
network
brain
connectivity
unit
analysis
Prior art date
Application number
PCT/KR2017/013455
Other languages
French (fr)
Korean (ko)
Inventor
강승완
진승현
홍슬기
윤혜진
배영우
Original Assignee
주식회사 아이메디신
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 주식회사 아이메디신 filed Critical 주식회사 아이메디신
Publication of WO2019103188A1 publication Critical patent/WO2019103188A1/en

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/25—Bioelectric electrodes therefor
    • A61B5/279—Bioelectric electrodes therefor specially adapted for particular uses
    • A61B5/291—Bioelectric electrodes therefor specially adapted for particular uses for electroencephalography [EEG]
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316—Modalities, i.e. specific diagnostic methods
    • A61B5/369—Electroencephalography [EEG]
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316—Modalities, i.e. specific diagnostic methods
    • A61B5/369—Electroencephalography [EEG]
    • A61B5/372—Analysis of electroencephalograms
    • A61B5/374—Detecting the frequency distribution of signals, e.g. detecting delta, theta, alpha, beta or gamma waves
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7225—Details of analog processing, e.g. isolation amplifier, gain or sensitivity adjustment, filtering, baseline or drift compensation
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235—Details of waveform analysis
    • A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/74—Details of notification to user or communication with user or patient ; user input means
    • A61B5/742—Details of notification to user or communication with user or patient ; user input means using visual displays
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/22—Social work or social welfare, e.g. community support activities or counselling services
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
    • G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment

Definitions

  • the present invention relates to a system and a method for evaluating traumatic brain injury through EEG analysis, and more particularly, to a system and method for evaluating traumatic brain injury by analyzing EEG in a stable state and confirming functional connectivity, and comparing the distribution of a healthy standard brain network constructed with ages and genders To a method and system for determining a traumatic brain injury.
  • traumatic brain injury which is caused by an artificial shock and causing damage to the brain, is frequent.
  • the number of patients complaining of chronic pain due to accidents resulting from traffic accidents is rapidly increasing.
  • no abnormality is found in brain imaging, There is a problem in that it is not provided.
  • the most commonly used method for evaluating and diagnosing traumatic brain injury in the past is a method of photographing a brain image and examining the image by a doctor such as a doctor to determine the degree of damage and degree of brain damage.
  • a doctor such as a doctor to determine the degree of damage and degree of brain damage.
  • it is difficult to detect a slight brain damage .
  • the above apparatus has a problem that external impact is applied to the wearer, change in the magnitude and duration of the external impact is detected, and it is not applicable to patients suspected of traumatic brain injury.
  • the present invention has been made in view of the above problems, and it is an object of the present invention to provide a system and a method for evaluating traumatic brain injury through EEG analysis capable of detecting a slight traumatic brain injury.
  • Another problem to be solved by the present invention is to provide a more systematic and reliable traumatic brain injury assessment system and method using the difference in characteristics of brain networks according to gender.
  • a system for assessing traumatic brain injury through EEG analysis comprising: a measurement unit for measuring a stable state EEG; a noise canceling unit for removing noise from the EEG measured by the measurement unit; An analyzing unit for analyzing the network index and for comparing the degree of traumatic brain injury with the health standard network index classified by gender and age and an output unit for outputting the analysis result of the analyzing unit.
  • the analysis unit may include a filter unit for removing noise from the EEG signals measured by the measurement unit, a correlation unit for analyzing the association and the network of noise- A comparator for comparing the analysis results of the association and network index calculator with a brain network of a health person stored in a network index database; And calculating a result to calculate a degree of traumatic brain injury.
  • the association and network index calculator performs functional connectivity and network analysis of the brain, and the functional connectivity includes a default mode network (DMN), a front- functional connectivity between the constituent areas of the network defined by the fronto-parietal network (FPN).
  • DNN default mode network
  • FPN fronto-parietal network
  • the functional connectivity can be expressed by the following equation (1).
  • f is a frequency
  • Sxy (f) is a cross-spectrum between X and Y
  • Sxx (f) and Syy (f) are X and Y spectrums, respectively. im denotes the imaginary part of coherence
  • () is the interval average in ().
  • the comparison unit can compare the default mode network and the alpha-wave region of the front-port parity network to check the location and degree of brain damage.
  • the connectivity between the left brain and the right brain at the same position in the traumatic brain injury patient group is larger than that in the healthy control group and the connectivity between the left brain and the right brain is lower .
  • the calculation unit can calculate the degree of brain damage through the following equation (2).
  • X is the detected brain network intensity
  • Is the standardized brain network intensity of the healthy person and is the mean value of the same age and gender database
  • ⁇ is the standard deviation value
  • the output unit may tag the text data to the visualized image of the traumatic brain damage data of the measurement subject and output the text data together.
  • a method for evaluating traumatic brain injury through EEG analysis comprising the steps of: a) measuring stable EEG data; b) filtering EEG data to remove noise; c) Calculating an indicator; d) comparing the result of step c) with a standard brain network index of the same gender, and calculating the degree of brain damage; e) And comparing the individual indices of the brain network to identify the location and degree of brain damage.
  • the step c) performs functional connectivity and network analysis of the brain, wherein the functional connectivity includes a default mode network (DMN), a fronto- parietal network (FPN), which is a network-based network.
  • DDN default mode network
  • FPN fronto- parietal network
  • the functional connectivity can be expressed by the following equation (1).
  • f is a frequency
  • Sxy (f) is a cross-spectrum between X and Y
  • Sxx (f) and Syy (f) are X and Y spectrums, respectively. im denotes the imaginary part of coherence
  • () is the interval average in ().
  • the default mode network and the alpha-wave region of the frontal parity network may be compared to determine the position and degree of brain damage.
  • the connectivity between the left brain and the right brain at the same position in the traumatic brain injury patient group is larger than that in the healthy control group, and the connectivity between the left brain and the right brain is lower .
  • the step d) may calculate the degree of brain damage through the following equation (2).
  • X is the detected brain network intensity
  • Is the standardized brain network intensity of the healthy person and is the mean value of the same age and gender database
  • ⁇ is the standard deviation value
  • the present invention relates to a method and apparatus for measuring a brain injury by measuring EEG in a stable state, confirming functional connectivity, realizing a stable state brain network by using functional connectivity, comparing with a healthy standard brain network, .
  • the present invention has the effect of determining more objective and reliable traumatic brain injury considering the specificity of the brain network according to sex and age.
  • FIG. 1 is a configuration diagram of a traumatic brain injury evaluation system through EEG analysis according to a preferred embodiment of the present invention.
  • FIG. 2 is a flowchart of a method for evaluating traumatic brain injury through EEG analysis according to a preferred embodiment of the present invention.
  • 3 is an electrode arrangement diagram of the measurement sensor.
  • FIG. 5 is a graph of the network connection strength between the traumatic brain injury patient group (mTBI) and the healthy control group (HC) in the DMN alpha network.
  • FIGS. 6 and 7 are diagrams comparing the connectivity of the DMN alpha network, respectively.
  • FIG. 8 is a graph of the network connection strength between the traumatic brain injury patient group (mTBI) and the health control group (HC) in the FPN alpha network.
  • 9 and 10 are graphs showing the connectivity of the FPN alpha network, respectively.
  • 11 is a graph of the network connection strength between a patient with a traumatic brain injury and a healthy control group during a connection in an AN network.
  • FIG. 12 is a graph of the network connection strength between a patient with traumatic brain injury and a healthy control group in the SMN network.
  • Measuring section 11 Measuring sensor
  • first, second, etc. may be used to describe various elements, but the elements are not limited to these terms. The terms are used only for the purpose of distinguishing one component from another.
  • first component may be referred to as a second component, and similarly, the second component may also be referred to as a first component.
  • / or < / RTI &gt includes any combination of a plurality of related listed items or any of a plurality of related listed items.
  • FIG. 1 is a configuration diagram of a traumatic brain injury evaluation system through EEG analysis according to a preferred embodiment of the present invention.
  • a traumatic brain injury evaluation system through EEG analysis includes a measurement unit 10 for measuring an EEG in a stable state, a noise measurement unit 10 for measuring noise in the EEG measured by the measurement unit 10, An output unit 30 for outputting the analysis result of the analysis unit 20, an analysis unit 20 for analyzing the connectivity, the network index, .
  • the EEG analysis according to the preferred embodiment of the present invention shown in FIG. Refer to the flow chart of the traumatic brain injury assessment method.
  • the measurement unit 10 includes a measurement sensor 11 for measuring brain waves, and an amplification unit 12 for amplifying a measurement signal of the measurement sensor 11.
  • EEG is an electrical signal generated when a signal is transmitted between brain cells.
  • a measurement sensor also referred to as a recording electrode 11
  • S10 the scalp
  • the attachment position of the measurement sensor 11 is in accordance with the international standard 10-20 system (Nuwer, 1987).
  • Fig. 3 shows an electrode arrangement diagram of the measurement sensor 11.
  • EEG Since the EEG is a signal containing various frequency components, the EEG is divided into frequency bands in order to observe the characteristics of the constituent frequency components.
  • a delta (delta, 1 to 4 Hz), ata (4 to 8 Hz), alpha (alpha, 8 to 13 Hz) ⁇ 21 Hz), Beta 2 (Beta 2, ⁇ 2, 21 ⁇ 30 Hz) can be used.
  • Electroencephalogram which is an electroencephalogram (EGG) which is normally stable, has an amplitude of about 50,, amplifies it through the amplification unit 12, and makes it easy to analyze in the analysis unit 20 including the averaging process.
  • the electrical signals amplified by the measured EEG signals are input to the analyzer 20 in step S20 of FIG.
  • the analysis unit 20 includes a filter unit 21 for removing noise from the signals input from the measurement unit 10 and performs an EEG preprocessing in step S30.
  • the analysis unit 20 may be a computer such as a PC or a notebook computer, or may use hardware produced separately.
  • the filter unit 21 for performing noise cancellation may be hardware or software that can be filtered.
  • the filter unit 21 filters an electrical signal of the input unit 10 and extracts only valid signals.
  • the filter unit 21 may simply remove the noise of the signal, but it may remove other components except the EEG through the deep neural network analysis.
  • Each node layer of the neural network can extract different features from measured EEG data and different layer features can be learned from layer to layer.
  • the characteristics of the lower level can be simple and concrete, and the higher the level, the more complex and abstract the character can be.
  • the EEG signal including the noise measured by the measuring unit 10 can be classified into a pure EEG component, a horizontal eye motion component, a vertical eye motion component, a muscle motion component, and other noise components using the features of the deep neural network have.
  • the remaining noise components other than the EEG component are removed from the input EEG data, and the EEG elimination noise can be finally output.
  • the in-depth neural network that can be used for the depth neural network analysis may be Convolution Neural Network (CNN), Recurrent Neural Network (RNN) or Hybrid Neural Network (HNN).
  • CNN Convolution Neural Network
  • RNN Recurrent Neural Network
  • HNN Hybrid Neural Network
  • the analysis unit 20 further includes a connectivity and network index calculation unit 22, a network index database 23, a comparison unit 24, and a calculation unit 25.
  • the electrical signals obtained by amplifying the EEG filtered by the filter unit 21 are used to calculate the functional connectivity of the brain in the connectivity and network index calculator 22 as in step S40.
  • Different regions of the brain or neuronal cells cooperate or compete through the complex network of the brain and process complex information efficiently. Analyzes the connections between specific regions of the brain and calculates the strength of the connections.
  • the functional connectivity of the brain is calculated by calculating the EEG sources at 5810 positions in the cerebral cortex and then using the default mode network (DMN), the attention network (AN), the fronto- the functional connectivity between the constituent areas of the network defined by the parietal network (FPN) and the sensorimotor network (SMN).
  • DNN default mode network
  • AN attention network
  • FPN parietal network
  • SSN sensorimotor network
  • the network strength of each network is divided by frequency band (delta (1 ⁇ 4Hz), theta (4 ⁇ 8Hz), alpha (8 ⁇ 13Hz), beta 1 (13 ⁇ 21Hz) ).
  • Various indicators can be used as functional connectivity indicators, and imaginary coherence (iCoh) is used in the present invention.
  • the functional connectivity index can be calculated by the following equation (1).
  • F is the frequency
  • Sxy (f) is the cross-spectrum between X and Y
  • Sxx (f) and Syy (f) are the spectra of X and Y, respectively.
  • im denotes the imaginary part of coherence
  • () is the interval average in ().
  • the value of iCo xy is determined between 0 and 1.
  • iCoh xy If the value of iCoh xy is 0, it means that the two signals at the positions of X and Y at a given frequency are linearly independent. Conversely, a value of 1 means that the two signals are at maximum correlated at a given frequency.
  • the computation of the brain network is a total connection strength index that calculates the mean value of the total connectivity index after calculating the brain connectivity between each network constitution area.
  • the clustering coefficient, the path length, , And a centrality indicator is a total connection strength index that calculates the mean value of the total connectivity index after calculating the brain connectivity between each network constitution area.
  • the connectivity and network index calculator 22 of the analyzer 20 analyzes the connectivity and the network and the comparison unit 24 compares the indicators stored in the network index database 23 with the indicators stored in the network index database 23, And the analysis results of the connectivity and network index calculation unit 22 are compared.
  • the calculating unit 25 of the analyzing unit 20 calculates the intensity of each index, performs an average, and calculates the degree of brain damage Z by using the average.
  • the degree of brain damage can be expressed by the following equation (2).
  • Equation (2) X is the intensity of the detected index, Is the same age and gender database mean value as calculated from the network index database of the health standard and ⁇ is the same age and gender database standard deviation value calculated from the healthy standard network index database.
  • the brain damage degree (Z) value calculated as in step S60 is determined to determine whether or not the brain is damaged.
  • the degree of brain damage (Z) is zero or a positive real or negative real value, and the brain damage level is determined using the positive real or negative real value.
  • the degree of brain damage (Z) is 0, it is determined that there is no damage since it is the same as the standard network index of the healthy person, and the degree of brain damage can be judged according to the magnitude of the real number. If the absolute value of the degree of brain damage (Z) is less than 2.5 in consideration of the individual deviation of the calculated brain damage degree (Z), it can be judged that there is no brain damage.
  • the degree of damage is diagnosed by comparing the network indicators of the same age, gender, health, and the detected network index as in step S70.
  • the damage connectivity region and the degree of damage may be estimated by separately comparing the brain connectivity (network configuration connectivity) between the healthy person group and the brain damage patient.
  • an example of the network configuration connectivity may be a connectivity value between MFG_L and MFG_R, and in step S70, all the connectivity is compared to determine the damage location and degree.
  • the brain network connection strength of the brain damage patient in a certain position of the brain may be stronger or weaker than the brain network connection strength of the health person, and the position and degree of the damage are judged by considering the difference of the network by the position.
  • Applicants of the present invention compared the steady state brain networks of twenty patients with traumatic brain injury and twenty healthy persons of the same age and sex.
  • FIG. 5 is a graph of the network connection strength between the traumatic brain injury patient group (mTBI) and the healthy control group (HC) in the DMN alpha network.
  • the difference in the network intensity between the traumatic brain injury patient group (mTBI) and the health control group (HC) in the DMN alpha network is remarkable.
  • the intensity of the DMN alpha network can be compared to determine the traumatic brain injury.
  • FIG. 6 shows that the healthy control group (HC) exhibits stronger connectivity than the traumatic brain injury patient group (mTBI) in the DMN alpha network.
  • FIG. 7 shows that the traumatic brain injury patient group (mTBI) HC), as compared with the case of the non-HC.
  • the connectivity of the traumatic brain injury patient may show a stronger or weaker connection than the HC (healthy control group)
  • the occurrence of damage can be detected, and the degree of damage can be confirmed using the difference in strength of connectivity.
  • FIG. 8 is a graph of the network connection strength between the traumatic brain injury patient group (mTBI) and the health control group (HC) in the FPN alpha network.
  • the network intensity of the traumatic brain injury group (mTBI) and the healthy control group (HC) are significantly different, and the traumatic brain injury can be judged by using the intensity of the DMN alpha network.
  • FIG. 9 shows the case where the health control group (HC) exhibits stronger connectivity than the traumatic brain injury patient group (mTBI) in the FPN alpha network
  • FIG. 10 shows that the traumatic brain injury patient group (mTBI) HC), as compared with the case of the non-HC.
  • DLPFC L -DLPFC R the connectivity between the left brain and the right brain
  • mTBI traumatic brain injury patient group
  • HC healthy control group
  • RTI ID 0.0 &gt
  • the intensity differences between the health control group (HC) and the traumatic brain damage patient group (mTBI) are not clearly distinguished from each frequency band, Traumatic brain injury is difficult to judge.
  • the degree of brain damage analyzed by the analysis unit 20 is output through the output unit 30 as in step S80.
  • the term "output" refers to an output of a report that can be easily understood by a person to be measured, which may be a concept including display on a display device or direct printing on paper, etc., and includes transmission to another device using communication Should be understood.
  • the present invention proposes an automated method for performing step S80.
  • the contents can be tagged and outputted together with the brain wave data.
  • the text data determined according to the degree of damage may be stored in the output unit 30 and the text data determined according to the degree of brain damage analyzed by the analysis unit 20 may be output together. That is, text can be added to a visualized image of traumatic brain injury data and output.
  • the content may be text data describing each brain wave data
  • the output unit 30 may tag the text data to the visualized image of the brain wave data of the measurement subject and output it together.
  • the content may include clinical interpretation information according to the assessed degree of traumatic brain injury.
  • the present invention can be used industrially because it can determine the objective and reliable traumatic brain injury degree by calculating the functional relevance and network strength of each brain position and comparing with the standard network strength of health of the same age and sex.

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Public Health (AREA)
  • Medical Informatics (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Pathology (AREA)
  • Physics & Mathematics (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • Molecular Biology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Biophysics (AREA)
  • Veterinary Medicine (AREA)
  • Primary Health Care (AREA)
  • Psychiatry (AREA)
  • Epidemiology (AREA)
  • Artificial Intelligence (AREA)
  • Signal Processing (AREA)
  • Business, Economics & Management (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Physiology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Tourism & Hospitality (AREA)
  • Psychology (AREA)
  • Human Resources & Organizations (AREA)
  • Fuzzy Systems (AREA)
  • Child & Adolescent Psychology (AREA)
  • Evolutionary Computation (AREA)
  • Power Engineering (AREA)
  • Economics (AREA)
  • Mathematical Physics (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)

Abstract

The present invention relates to a system and a method for evaluating a traumatic brain damage through brain wave analysis, including: a measurement unit for measuring brain waves in a steady state; an analysis unit which removes noise from the brain waves measured by the measurement unit, analyzes connectivity and network indicators, and compares same with normal people's standard network indicators classified by gender and age, thereby computing the magnitude of a traumatic brain damage; and an output unit for outputting the analysis result of the analysis unit.

Description

뇌파 분석을 통한 외상성 뇌손상 평가 시스템 및 방법Traumatic Brain Injury Assessment System and Method through EEG Analysis
본 발명은 뇌파 분석을 통한 외상성 뇌손상 평가 시스템 및 방법에 관한 것으로, 더 상세하게는 안정상태에서의 뇌파를 측정하고, 기능적 연결성을 확인하여 연령대 및 성별로 구축된 건강인 표준 뇌 네트워크 분포와 비교하여 외상성 뇌손상을 판단하는 방법 및 시스템에 관한 것이다.The present invention relates to a system and a method for evaluating traumatic brain injury through EEG analysis, and more particularly, to a system and method for evaluating traumatic brain injury by analyzing EEG in a stable state and confirming functional connectivity, and comparing the distribution of a healthy standard brain network constructed with ages and genders To a method and system for determining a traumatic brain injury.
일반적으로, 인위적인 충격이 가해져 뇌의 손상이 유발되는 외상성 뇌손상의 발생이 빈번하다. 특히, 교통사고에 따른 사고 후유증으로 만성 통증 등을 호소하는 환자는 급증하고 있으나, 이러한 사고로 인한 외상성 뇌손상의 증상이 경미한 경우에는 뇌 영상 검사 등에서는 이상이 발견되지 않아 환자가 적절한 진단 및 치료를 제공 받지 못하는 문제점이 있다. In general, traumatic brain injury, which is caused by an artificial shock and causing damage to the brain, is frequent. In particular, the number of patients complaining of chronic pain due to accidents resulting from traffic accidents is rapidly increasing. However, when the symptoms of traumatic brain injury due to such accidents are mild, no abnormality is found in brain imaging, There is a problem in that it is not provided.
종래 외상성 뇌손상을 평가 및 진단하기 위해서 가장 많이 사용되는 방법으로는 뇌의 영상을 촬영하고 의사 등 전문가가 영상을 확인하여 뇌손상 여부 및 정도를 판정하는 방법이지만, 경미한 뇌손상을 발견하기 어렵다는 문제점이 있었다.The most commonly used method for evaluating and diagnosing traumatic brain injury in the past is a method of photographing a brain image and examining the image by a doctor such as a doctor to determine the degree of damage and degree of brain damage. However, it is difficult to detect a slight brain damage .
위의 방법과는 다르게, 공개특허 10-2017-0071951호(외상성 뇌손상 검출 장치 및 이를 이용하는 외상성 뇌손상 검출 방법, 2017년 6월 26일 공개)와 같이 신체에 착용하는 장치가 개발되었다.Unlike the above method, a body-worn device such as the patent 10-2017-0071951 (Traumatic Brain Injury Detection Apparatus and Traumatic Brain Injury Detection Method Utilizing Same, published June 26, 2017) has been developed.
그러나 위의 장치는 착용자에게 외부의 충격을 가하고, 외부 충격의 크기 및 지속 시간의 변화를 검출하는 것으로, 이미 외상성 뇌손상이 의심되는 환자에게는 적용할 수 없는 등의 문제점이 있었다.However, the above apparatus has a problem that external impact is applied to the wearer, change in the magnitude and duration of the external impact is detected, and it is not applicable to patients suspected of traumatic brain injury.
따라서, 객관적인 진단 방법을 통해 외상성 뇌손상의 유무 및 손상 정도를 진단하여 환자가 상태에 따라 적절한 치료를 받을 수 있도록 하는 진단 시스템이 필요하다.Therefore, there is a need for a diagnostic system that diagnoses the presence or severity of traumatic brain injury through an objective diagnostic method and allows the patient to receive appropriate treatment according to the condition.
상기와 같은 종래의 문제점들을 감안한 본 발명이 해결하고자 하는 과제는, 경미한 외상성 뇌손상을 검출할 수 있는 뇌파 분석을 통한 외상성 뇌손상 평가 시스템 및 방법을 제공함에 있다.SUMMARY OF THE INVENTION The present invention has been made in view of the above problems, and it is an object of the present invention to provide a system and a method for evaluating traumatic brain injury through EEG analysis capable of detecting a slight traumatic brain injury.
또한, 본 발명이 해결하고자 하는 다른 과제는, 성별에 따른 뇌 네트워크의 특성 차이를 이용하여 더욱 객관적이고 신뢰성이 높은 외상성 뇌손상 평가 시스템 및 방법을 제공함에 있다.Another problem to be solved by the present invention is to provide a more systematic and reliable traumatic brain injury assessment system and method using the difference in characteristics of brain networks according to gender.
상기와 같은 과제를 해결하기 위한 본 발명의 일측면에 따른 뇌파 분석을 통한 외상성 뇌 손상 평가 시스템은, 안정 상태 뇌파를 측정하는 측정부와, 측정부에서 측정된 뇌파에서 잡음을 제거하고, 연결성 및 네트워크 지표를 분석하고, 성별 및 연령별로 분류된 건강인 표준 네트워크 지표와 비교하여, 외상성 뇌손상 정도를 산출하는 분석부와, 상기 분석부의 분석결과를 출력하는 출력부를 포함할 수 있다.According to an aspect of the present invention, there is provided a system for assessing traumatic brain injury through EEG analysis, comprising: a measurement unit for measuring a stable state EEG; a noise canceling unit for removing noise from the EEG measured by the measurement unit; An analyzing unit for analyzing the network index and for comparing the degree of traumatic brain injury with the health standard network index classified by gender and age and an output unit for outputting the analysis result of the analyzing unit.
본 발명의 일실시예에 따르면, 분석부는, 상기 측정부에서 측정된 뇌파 신호들에서 잡음을 제거하는 필터부와, 상기 필터부에서 잡음이 제거된 뇌파 신호들의 연관성 및 네트워크를 분석하는 연관성 및 네트워크 지표 산출부와, 건강인의 뇌 네트워크 강도를 저장하는 네트워크 지표 데이터베이스와, 상기 연관성 및 네트워크 지표 산출부의 분석결과를 네트워크 지표 데이터베이스에 저장된 건강인의 뇌 네트워크와 비교하는 비교부와, 상기 비교부의 비교 결과를 연산하여 외상성 뇌손상 정도를 산출하는 연산부를 포함할 수 있다.According to an embodiment of the present invention, the analysis unit may include a filter unit for removing noise from the EEG signals measured by the measurement unit, a correlation unit for analyzing the association and the network of noise- A comparator for comparing the analysis results of the association and network index calculator with a brain network of a health person stored in a network index database; And calculating a result to calculate a degree of traumatic brain injury.
본 발명의 일실시예에 따르면, 상기 연관성 및 네트워크 지표 산출부는, 뇌의 기능적 연결성 및 네트워크 분석을 수행하며, 상기 기능적 연결성은, 디폴트 모드 네트워크(default mode network, DMN), 프론토 패리에탈 네트워크(fronto-parietal network, FPN)로 정의된 네트워크의 구성 영역들 사이의 기능적 연결성(functional connectivity)을 계산할 수 있다.According to an embodiment of the present invention, the association and network index calculator performs functional connectivity and network analysis of the brain, and the functional connectivity includes a default mode network (DMN), a front- functional connectivity between the constituent areas of the network defined by the fronto-parietal network (FPN).
본 발명의 일실시예에 따르면, 상기 기능적 연결성은, 아래의 수학식 1로 표현될 수 있다.According to an embodiment of the present invention, the functional connectivity can be expressed by the following equation (1).
수학식 1 Equation 1
Figure PCTKR2017013455-appb-I000001
Figure PCTKR2017013455-appb-I000001
상기 수학식 1에서 f는 주파수, Sxy(f)는 X와 Y 사이의 크로스 스펙트럼(cross-spectrum), Sxx(f)와 Syy(f)는 각각 X와 Y의 스펙트럼을 나타낸다. im은 허수부 코히어런스(imaginary part of coherence)를 의미하고, ()는 () 내의 구간 평균이다.In the above equation (1), f is a frequency, Sxy (f) is a cross-spectrum between X and Y, Sxx (f) and Syy (f) are X and Y spectrums, respectively. im denotes the imaginary part of coherence, and () is the interval average in ().
본 발명의 일실시예에 따르면, 상기 비교부는, 상기 디폴트 모드 네트워크와 상기 프론토 패리에탈 네트워크의 알파파 영역을 비교하여 뇌손상 위치와 정도를 확인할 수 있다.According to an embodiment of the present invention, the comparison unit can compare the default mode network and the alpha-wave region of the front-port parity network to check the location and degree of brain damage.
본 발명의 일실시에에 따르면, 상기 알파파 영역에서, 외상성 뇌손상 환자군의 경우 좌뇌와 우뇌의 동일 위치간의 연결성은 건강 대조군에 비하여 더 크고, 좌뇌와 우뇌의 다른 위치 간의 연결성은 더 낮은 것을 특징으로 할 수 있다.According to one embodiment of the present invention, in the above-described alpha-wave region, the connectivity between the left brain and the right brain at the same position in the traumatic brain injury patient group is larger than that in the healthy control group and the connectivity between the left brain and the right brain is lower .
상기 연산부는, 아래의 수학식 2를 통해 뇌손상 정도를 산출할 수 있다.The calculation unit can calculate the degree of brain damage through the following equation (2).
수학식 2 Equation 2
Figure PCTKR2017013455-appb-I000002
Figure PCTKR2017013455-appb-I000002
X는 검출된 뇌 네트워크 강도이며,
Figure PCTKR2017013455-appb-I000003
는 건강인 표준 뇌 네트워크 강도로서 동일 연령대 및 성별 데이터베이스 평균값이고, σ는 건강인 표준 뇌 네트워크 강도의 표준편차값X is the detected brain network intensity,
Figure PCTKR2017013455-appb-I000003
Is the standardized brain network intensity of the healthy person and is the mean value of the same age and gender database and σ is the standard deviation value
본 발명의 일실시예에 따르면 상기 출력부는, 측정 대상자의 외상성 뇌손상 데이터의 시각화된 이미지에 텍스트 데이터를 태깅하여 함께 출력할 수 있다.According to an embodiment of the present invention, the output unit may tag the text data to the visualized image of the traumatic brain damage data of the measurement subject and output the text data together.
본 발명의 다른 측면에 따른 뇌파 분석을 통한 외상성 뇌손상 평가 방법은, a) 안정상태의 뇌파 데이터를 측정하는 단계와, b) 뇌파 데이터를 필터링하여 잡음을 제거하는 단계와, c) 연결성 및 네트워크 지표를 산출하는 단계와, d) 상기 c) 단계의 결과를 동일 성별 건강인 표준 뇌 네트워크 지표와 비교하고, 뇌손상 정도를 산출하는 단계와, e) 상기 뇌손상 정도의 절대값이 설정값을 초과하는 경우 뇌 네트워크의 개별 지표들을 비교하여 뇌손상 위치 및 정도를 확인하는 단계를 포함할 수 있다.According to another aspect of the present invention, there is provided a method for evaluating traumatic brain injury through EEG analysis, comprising the steps of: a) measuring stable EEG data; b) filtering EEG data to remove noise; c) Calculating an indicator; d) comparing the result of step c) with a standard brain network index of the same gender, and calculating the degree of brain damage; e) And comparing the individual indices of the brain network to identify the location and degree of brain damage.
본 발명의 일실시예에 따르면, 상기 c) 단계는, 뇌의 기능적 연결성 및 네트워크 분석을 수행하되, 상기 기능적 연결성은, 디폴트 모드 네트워크(default mode network, DMN), 프론토 패리에탈 네트워크(fronto-parietal network, FPN)로 정의된 네트워크의 구성 영역들 사이의 기능적 연결성(functional connectivity)을 계산할 수 있다.According to an embodiment of the present invention, the step c) performs functional connectivity and network analysis of the brain, wherein the functional connectivity includes a default mode network (DMN), a fronto- parietal network (FPN), which is a network-based network.
본 발명의 일실시예에 따르면, 상기 기능적 연결성은, 아래의 수학식 1로 표현될 수 있다.According to an embodiment of the present invention, the functional connectivity can be expressed by the following equation (1).
Figure PCTKR2017013455-appb-I000004
Figure PCTKR2017013455-appb-I000004
상기 수학식 1에서 f는 주파수, Sxy(f)는 X와 Y 사이의 크로스 스펙트럼(cross-spectrum), Sxx(f)와 Syy(f)는 각각 X와 Y의 스펙트럼을 나타낸다. im은 허수부 코히어런스(imaginary part of coherence)를 의미하고, ()는 () 내의 구간 평균이다.In the above equation (1), f is a frequency, Sxy (f) is a cross-spectrum between X and Y, Sxx (f) and Syy (f) are X and Y spectrums, respectively. im denotes the imaginary part of coherence, and () is the interval average in ().
본 발명의 일실시예에 따르면, 상기 디폴트 모드 네트워크와 상기 프론토 패리에탈 네트워크의 알파파 영역을 비교하여 뇌손상 위치와 정도를 확인할 수 있다.According to an embodiment of the present invention, the default mode network and the alpha-wave region of the frontal parity network may be compared to determine the position and degree of brain damage.
본 발명의 일실시예에 따르면, 상기 알파파 영역에서, 외상성 뇌손상 환자군의 경우 좌뇌와 우뇌의 동일 위치간의 연결성은 건강 대조군에 비하여 더 크고, 좌뇌와 우뇌의 다른 위치 간의 연결성은 더 낮은 것을 특징으로 할 수 있다.According to one embodiment of the present invention, in the above-described alpha-wave region, the connectivity between the left brain and the right brain at the same position in the traumatic brain injury patient group is larger than that in the healthy control group, and the connectivity between the left brain and the right brain is lower .
본 발명의 일실시예에 따르면, 상기 d) 단계는, 아래의 수학식 2를 통해 뇌손상 정도를 산출할 수 있다.According to an embodiment of the present invention, the step d) may calculate the degree of brain damage through the following equation (2).
수학식 2 Equation 2
Figure PCTKR2017013455-appb-I000005
Figure PCTKR2017013455-appb-I000005
X는 검출된 뇌 네트워크 강도이며,
Figure PCTKR2017013455-appb-I000006
는 건강인 표준 뇌 네트워크 강도로서 동일 연령대 및 성별 데이터베이스 평균값이고, σ는 건강인 표준 뇌 네트워크 강도의 표준편차값X is the detected brain network intensity,
Figure PCTKR2017013455-appb-I000006
Is the standardized brain network intensity of the healthy person and is the mean value of the same age and gender database and σ is the standard deviation value
본 발명의 일실시예에 따르면, e) 측정 대상자의 외상성 뇌손상 데이터의 시각화된 이미지에 텍스트 데이터를 태깅하여 함께 출력하는 단계를 더 포함할 수 있다.According to an embodiment of the present invention, e) tagging the text data on the visualized image of the traumatic brain injury data of the measurement subject and outputting together.
본 발명은, 안정상태에서의 뇌파를 측정하여 기능적 연결성을 확인하고, 기능적 연결성을 이용하여 안정상태 뇌 네트워크를 구현하고, 건강인 표준 뇌 네트워크와 비교함으로써, 경미한 외상성 뇌손상을 판단할 수 있는 효과가 있다.The present invention relates to a method and apparatus for measuring a brain injury by measuring EEG in a stable state, confirming functional connectivity, realizing a stable state brain network by using functional connectivity, comparing with a healthy standard brain network, .
또한 본 발명은 성별 및 연령에 따른 뇌 네트워크의 특이성을 고려하여 더 객관적이고 신뢰성이 높은 외상성 뇌손상을 판단할 수 있는 효과가 있다.In addition, the present invention has the effect of determining more objective and reliable traumatic brain injury considering the specificity of the brain network according to sex and age.
도 1은 본 발명의 바람직한 실시예에 따른 뇌파 분석을 통한 외상성 뇌손상 평가 시스템의 구성도이다.1 is a configuration diagram of a traumatic brain injury evaluation system through EEG analysis according to a preferred embodiment of the present invention.
도 2는 본 발명의 바람직한 실시예에 따른 뇌파 분석을 통한 외상성 뇌손상 평가 방법의 순서도이다.2 is a flowchart of a method for evaluating traumatic brain injury through EEG analysis according to a preferred embodiment of the present invention.
도 3은 측정 센서의 전극 배치도이다.3 is an electrode arrangement diagram of the measurement sensor.
도 4는 네트워크 구성 영역 정보이다.4 is network configuration area information.
도 5는 DMN 알파 네트워크 내의 연결중 외상성 뇌손상 환자군(mTBI)과 건강대조군(HC)의 네트워크 연결강도 그래프이다.FIG. 5 is a graph of the network connection strength between the traumatic brain injury patient group (mTBI) and the healthy control group (HC) in the DMN alpha network.
도 6과 도 7은 각각 DMN 알파 네트워크의 연결성을 비교한 그림이다.FIGS. 6 and 7 are diagrams comparing the connectivity of the DMN alpha network, respectively.
도 8은 FPN 알파 네트워크 내의 연결중 외상성 뇌손상 환자군(mTBI)과 건강대조군(HC)의 네트워크 연결강도 그래프이다.FIG. 8 is a graph of the network connection strength between the traumatic brain injury patient group (mTBI) and the health control group (HC) in the FPN alpha network.
도 9와 도 10은 각각 FPN 알파 네트워크의 연결성을 비교한 그림이다.9 and 10 are graphs showing the connectivity of the FPN alpha network, respectively.
도 11은 AN 네트워크 내의 연결중 외상성 뇌손상 환자군과 건강 대조군의 네트워크 연결강도 그래프이다.11 is a graph of the network connection strength between a patient with a traumatic brain injury and a healthy control group during a connection in an AN network.
도 12는 SMN 네트워크 내의 연결중 외상성 뇌손상 환자군과 건강 대조군의 네트워크 연결강도 그래프이다.12 is a graph of the network connection strength between a patient with traumatic brain injury and a healthy control group in the SMN network.
-부호의 설명-- Explanation of symbols -
10:측정부 11:측정센서10: Measuring section 11: Measuring sensor
12:증폭부 20:분석부 12: amplification unit 20:
21:필터부 22:연결성 및 네트워크 지표 산출부21: Filter part 22: Connectivity and network index calculation part
23:네트워크 지표 데이터베이스 24:비교부 23: network index database 24: comparison section
25:연산부 30:출력부25: operation unit 30: output unit
이하, 본 발명의 바람직한 실시예에 따른 뇌파 분석을 통한 외상성 뇌손상 평가 시스템 및 방법에 대하여 첨부한 도면을 참조하여 상세히 설명한다.Hereinafter, a system and a method for evaluating traumatic brain injury through EEG analysis according to a preferred embodiment of the present invention will be described in detail with reference to the accompanying drawings.
본 발명의 실시 예들은 다양한 변경을 가할 수 있고 여러 가지 실시 예를 가질 수 있는바, 특정 실시 예들을 도면에 예시하여 상세하게 설명한다. 그러나 이는 본 발명의 실시 예들을 특정한 실시 형태에 대해 한정하려는 것이 아니며, 본 발명의 실시 예들의 사상 및 기술 범위에 포함되는 모든 변경, 균등물 내지 대체물을 포함하는 것으로 이해되어야 한다.The embodiments of the present invention can make various changes and have various embodiments, and specific embodiments will be described in detail with reference to the drawings. It should be understood, however, that the embodiments of the present invention are not limited to specific embodiments, but include all modifications, equivalents, and alternatives falling within the spirit and scope of embodiments of the present invention.
제1, 제2 등과 같이 서수를 포함하는 용어는 다양한 구성요소들을 설명하는데 사용될 수 있지만, 상기 구성요소들은 상기 용어들에 의해 한정되지는 않는다. 상기 용어들은 하나의 구성요소를 다른 구성요소로부터 구별하는 목적으로만 사용된다. 예를 들어, 본 발명의 실시 예들의 권리 범위를 벗어나지 않으면서 제1 구성요소는 제2 구성요소로 명명될 수 있고, 유사하게 제2 구성요소도 제1 구성요소로 명명될 수 있다. 및/또는 이라는 용어는 복수의 관련된 기재된 항목들의 조합 또는 복수의 관련된 기재된 항목들 중의 어느 항목을 포함한다.Terms including ordinals, such as first, second, etc., may be used to describe various elements, but the elements are not limited to these terms. The terms are used only for the purpose of distinguishing one component from another. For example, without departing from the scope of the embodiments of the present invention, the first component may be referred to as a second component, and similarly, the second component may also be referred to as a first component. And / or < / RTI > includes any combination of a plurality of related listed items or any of a plurality of related listed items.
본 발명의 실시 예들에서 사용한 용어는 단지 특정한 실시 예를 설명하기 위해 사용된 것으로, 본 발명의 실시 예들을 한정하려는 의도가 아니다. 단수의 표현은 문맥상 명백하게 다르게 뜻하지 않는 한, 복수의 표현을 포함한다. 본 발명의 실시 예들에서, "포함하다" 또는 "가지다" 등의 용어는 명세서상에 기재된 특징, 숫자, 단계, 동작, 구성요소, 부품 또는 이들을 조합한 것이 존재함을 지정하려는 것이지, 하나 또는 그 이상의 다른 특징들이나 숫자, 단계, 동작, 구성요소, 부품 또는 이들을 조합한 것들의 존재 또는 부가 가능성을 미리 배제하지 않는 것으로 이해되어야 한다.The terminology used in the embodiments of the present invention is used only to describe a specific embodiment and is not intended to limit the embodiments of the present invention. The singular expressions include plural expressions unless the context clearly dictates otherwise. In the embodiments of the present invention, terms such as " comprise " or " comprise ", etc. designate the presence of stated features, integers, steps, operations, elements, parts, or combinations thereof, It should be understood that the foregoing does not preclude the presence or addition of other features, numbers, steps, operations, elements, parts, or combinations thereof.
다르게 정의되지 않는 한, 기술적이거나 과학적인 용어를 포함해서 여기서 사용되는 모든 용어들은 본 발명의 실시 예들이 속하는 기술 분야에서 통상의 지식을 가진 자에 의해 일반적으로 이해되는 것과 동일한 의미가 있다. 일반적으로 사용되는 사전에 정의되어 있는 것과 같은 용어들은 관련 기술의 문맥상 가지는 의미와 일치하는 의미를 갖는 것으로 해석되어야 하며, 본 발명의 실시 예들에서 명백하게 정의하지 않는 한, 이상적이거나 과도하게 형식적인 의미로 해석되지 않는다.Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which the embodiments of the present invention belong. Terms such as those defined in commonly used dictionaries are to be interpreted as having a meaning consistent with the meaning of the context in the related art and, unless explicitly defined in the embodiments of the present invention, are intended to mean ideal or overly formal .
도 1은 본 발명의 바람직한 실시예에 따른 뇌파 분석을 통한 외상성 뇌손상 평가 시스템의 구성도이다.1 is a configuration diagram of a traumatic brain injury evaluation system through EEG analysis according to a preferred embodiment of the present invention.
도 1을 참조하면 본 발명의 바람직한 실시예에 따른 뇌파 분석을 통한 외상성 뇌손상 평가 시스템은, 안정 상태의 뇌파를 측정하는 측정부(10)와, 측정부(10)에서 측정된 뇌파에서 잡음을 제거하고, 연결성 및 네트워크 지표를 분석하고, 건강인 표준 뇌 네트워크와 비교하여, 뇌손상 정도를 출력하는 분석부(20)와, 상기 분석부(20)의 분석결과를 출력하는 출력부(30)를 포함하여 구성된다.Referring to FIG. 1, a traumatic brain injury evaluation system through EEG analysis according to a preferred embodiment of the present invention includes a measurement unit 10 for measuring an EEG in a stable state, a noise measurement unit 10 for measuring noise in the EEG measured by the measurement unit 10, An output unit 30 for outputting the analysis result of the analysis unit 20, an analysis unit 20 for analyzing the connectivity, the network index, .
이하 상기와 같이 구성되는 본 발명의 바람직한 실시예에 따른 뇌파 분석을 통한 외상성 뇌손상 평가 시스템의 구성과 작용에 대하여 더 상세히 설명하며, 도 2에 도시한 본 발명의 바람직한 실시예에 따른 뇌파 분석을 통한 외상성 뇌손상 평가 방법의 순서도를 참조한다.Hereinafter, the configuration and operation of the traumatic brain injury evaluation system through the EEG analysis according to the preferred embodiment of the present invention will be described in detail. The EEG analysis according to the preferred embodiment of the present invention shown in FIG. Refer to the flow chart of the traumatic brain injury assessment method.
먼저, 측정부(10)는 뇌파를 측정하기 위한 측정센서(11), 측정센서(11)의 측정 신호를 증폭하는 증폭부(12)를 포함한다.First, the measurement unit 10 includes a measurement sensor 11 for measuring brain waves, and an amplification unit 12 for amplifying a measurement signal of the measurement sensor 11.
뇌파는 뇌신경세포 사이에 신호가 전달될 때 발생하는 전기적 신호를 측정한 것으로, 측정센서(또는 기록 전극이라고도 함, 11)을 두피에 붙여 측정한다(S10). EEG is an electrical signal generated when a signal is transmitted between brain cells. A measurement sensor (also referred to as a recording electrode 11) is attached to the scalp (S10).
상기 측정센서(11)의 부착위치는 국제표준 10-20 시스템(Nuwer, 1987)에 따른다. The attachment position of the measurement sensor 11 is in accordance with the international standard 10-20 system (Nuwer, 1987).
도 3에 측정센서(11)의 전극배치도를 도시하였다. Fig. 3 shows an electrode arrangement diagram of the measurement sensor 11. Fig.
총 19개의 전극(Fp1, Fp2, F7, F8, F3, F4, Fz, T3, T4, C3, C4, Cz, T5, T6, P3, P4, Pz, O1, O2)를 사용하여 배치된 것이며, 뇌파는 다양한 주파수 성분이 포함된 신호이므로 구성 주파수 성분의 특성을 관찰하기 위해 주파수 대역별로 구분하여 관찰한다.And 19 electrodes (Fp1, Fp2, F7, F8, F3, F4, Fz, T3, T4, C3, C4, Cz, T5, T6, P3, P4, Pz, O1, O2) Since the EEG is a signal containing various frequency components, the EEG is divided into frequency bands in order to observe the characteristics of the constituent frequency components.
본 발명에서는 델타파(Delta, δ, 1~4 Hz), 세타파(Theta, θ, 4~8 Hz), 알파파(Alpha, α, 8~13 Hz), 베타파1(Beta1, β1, 13~21Hz), 베타파2(Beta2, β2, 21~30Hz)로 구분한 주파수 대역을 사용할 수 있다.In the present invention, a delta (delta, 1 to 4 Hz), ata (4 to 8 Hz), alpha (alpha, 8 to 13 Hz) ~ 21 Hz), Beta 2 (Beta 2, β 2, 21 ~ 30 Hz) can be used.
통상 안정 상태의 뇌파인 뇌전도(Electroencephalogram, EGG)는 50㎶ 정도의 진폭을 가지며, 이를 증폭부(12)를 통해 증폭하고, 평균화 과정을 포함한 분석부(20)에서 분석이 용이하도록 한다. Electroencephalogram (EGG), which is an electroencephalogram (EGG) which is normally stable, has an amplitude of about 50,, amplifies it through the amplification unit 12, and makes it easy to analyze in the analysis unit 20 including the averaging process.
이처럼 측정된 뇌파들이 증폭된 전기적인 신호들은 도 2의 S20단계와 같이 분석부(20)로 입력된다.The electrical signals amplified by the measured EEG signals are input to the analyzer 20 in step S20 of FIG.
분석부(20)는 상기 측정부(10)에서 입력된 신호들에서 잡음을 제거하는 필터부(21)를 포함하여, S30단계의 뇌파 전처리를 수행한다.The analysis unit 20 includes a filter unit 21 for removing noise from the signals input from the measurement unit 10 and performs an EEG preprocessing in step S30.
상기 분석부(20)는 PC, 노트북 등 컴퓨터일 수 있으며, 별도로 제작된 하드웨어를 사용할 수 있다. 위의 잡음 제거를 수행하는 필터부(21)는 필터링 가능한 하드웨어 또는 소프트웨어일 수 있으며, 입력된 측정부(10)의 전기적신호를 필터링하여 유효한 신호만을 추출하는 역할을 한다.The analysis unit 20 may be a computer such as a PC or a notebook computer, or may use hardware produced separately. The filter unit 21 for performing noise cancellation may be hardware or software that can be filtered. The filter unit 21 filters an electrical signal of the input unit 10 and extracts only valid signals.
상기 필터부(21)는 단순히 신호의 잡음을 제거하는 것일 수 있으나, 심층신경망 분석을 통해 뇌파를 제외한 다른 성분들을 제거할 수 있다.The filter unit 21 may simply remove the noise of the signal, but it may remove other components except the EEG through the deep neural network analysis.
심층신경망의 각 노드 층위는 측정된 뇌파 데이터로부터 각자 다른 특징들을 추출할 수 있으며, 층마다 다른 층위의 특징이 학습될 수 있다. 낮은 층위의 특징은 단순하고 구체적일 수 있으며 높은 층위로 갈수록 더욱 복잡하고 추상적인 특징을 가질 수 있다.Each node layer of the neural network can extract different features from measured EEG data and different layer features can be learned from layer to layer. The characteristics of the lower level can be simple and concrete, and the higher the level, the more complex and abstract the character can be.
이러한 심층신경망의 특징을 이용하여 상기 측정부(10)에서 측정된 잡음이 포함된 뇌파 신호를 순수 뇌파 성분, 수평 눈 움직임 성분, 수직 눈 움직임 성분, 근육 움직임 성분, 기타 노이즈 성분 등으로 분류할 수 있다.The EEG signal including the noise measured by the measuring unit 10 can be classified into a pure EEG component, a horizontal eye motion component, a vertical eye motion component, a muscle motion component, and other noise components using the features of the deep neural network have.
그리고 분류된 신호를 바탕으로 뇌파 성분 이외의 나머지 잡음 성분을 입력된 뇌파 데이터로부터 제거하여 잡음이 제거된 뇌파를 최종적으로 출력할 수 있다.Then, based on the classified signal, the remaining noise components other than the EEG component are removed from the input EEG data, and the EEG elimination noise can be finally output.
이때 심층신경망 분석에 사용될 수 있는 심층신경망으로는 콘벌루션 신경망(CNN), 리커런트 신경망(RNN) 또는 하이브리드 신경망(HNN)일 수 있다.The in-depth neural network that can be used for the depth neural network analysis may be Convolution Neural Network (CNN), Recurrent Neural Network (RNN) or Hybrid Neural Network (HNN).
상기 분석부(20)는 연결성 및 네트워크 지표 산출부(22), 네트워크 지표 데이터베이스(23), 비교부(24) 및 연산부(25)를 더 포함한다.The analysis unit 20 further includes a connectivity and network index calculation unit 22, a network index database 23, a comparison unit 24, and a calculation unit 25.
상기 필터부(21)에서 필터링된 뇌파들이 증폭된 전기적인 신호들은 S40단계와 같이 연결성 및 네트워크 지표 산출부(22)에서 뇌의 기능적 연결성을 산출한다.The electrical signals obtained by amplifying the EEG filtered by the filter unit 21 are used to calculate the functional connectivity of the brain in the connectivity and network index calculator 22 as in step S40.
뇌의 여러 영역들 또는 뇌신경 세포들은 뇌의 복잡한 네트워크를 통해 상호 협력하거나 경쟁하며 복잡한 정보를 효율적으로 처리한다. 뇌의 특정 영역들 사이의 연결관계를 분석하고, 그 연결관계의 강도를 산출한다.Different regions of the brain or neuronal cells cooperate or compete through the complex network of the brain and process complex information efficiently. Analyzes the connections between specific regions of the brain and calculates the strength of the connections.
뇌의 기능적 연결성은 대뇌 피질의 5810개 위치에서 뇌파 발생 신호원을 계산한 후, 디폴트 모드 네트워크(default mode network, DMN), 어텐션 모드 네트워크(attention network, AN), 프론토 패리에탈 네트워크(fronto-parietal network, FPN), 감각운동기 네트워크(sensorimotor network, SMN)으로 정의된 네트워크의 구성 영역들 사이의 기능적 연결성(functional connectivity)을 계산한다.The functional connectivity of the brain is calculated by calculating the EEG sources at 5810 positions in the cerebral cortex and then using the default mode network (DMN), the attention network (AN), the fronto- the functional connectivity between the constituent areas of the network defined by the parietal network (FPN) and the sensorimotor network (SMN).
각 네트워크의 연결강도(Network strength)를 주파수 대역별(델타(1~4Hz), 세타(4~8Hz), 알파(8~13Hz), 베타1(13~21Hz), 베타2(21~30Hz))로 산출할 수 있다.The network strength of each network is divided by frequency band (delta (1 ~ 4Hz), theta (4 ~ 8Hz), alpha (8 ~ 13Hz), beta 1 (13 ~ 21Hz) ).
기능적 연결성 지표로는 다양한 지표가 사용 가능하며, 본 발명에서는 imaginary coherence(iCoh)를 사용한다. 기능적 연결성 지표는 아래의 수학식 1로 산출할 수 있다.Various indicators can be used as functional connectivity indicators, and imaginary coherence (iCoh) is used in the present invention. The functional connectivity index can be calculated by the following equation (1).
Figure PCTKR2017013455-appb-M000001
Figure PCTKR2017013455-appb-M000001
수학식 1에서 f는 주파수, Sxy(f)는 X와 Y 사이의 크로스 스펙트럼(cross-spectrum), Sxx(f)와 Syy(f)는 각각 X와 Y의 스펙트럼을 나타낸다. im은 허수부 코히어런스(imaginary part of coherence)를 의미하고, ()는 () 내의 구간 평균이다. 상기 iCohxy의 값은 0과 1 사이에서 결정된다. F is the frequency, Sxy (f) is the cross-spectrum between X and Y, Sxx (f) and Syy (f) are the spectra of X and Y, respectively. im denotes the imaginary part of coherence, and () is the interval average in (). The value of iCo xy is determined between 0 and 1.
iCohxy의 값이 0이면 주어진 주파수에서 X와 Y의 위치의 두 신호는 선형적으로 독립인 것을 의미한다. 반대로 1이면 주어진 주파수에서 두 신호는 최대로 상관되어 있음을 의미한다.If the value of iCoh xy is 0, it means that the two signals at the positions of X and Y at a given frequency are linearly independent. Conversely, a value of 1 means that the two signals are at maximum correlated at a given frequency.
뇌 네트워크의 산출은 뇌 연결성을 각 네트워크 구성 영역 사이에서 계산한 후, 전체 연결성 지표의 평균값을 계산한 전체 연결 강도(total connection strength) 지표이며, 클러스터링 상수(clustering coefficient), 연결길이(path length), 집중성(centrality) 지표를 포함할 수 있다.The computation of the brain network is a total connection strength index that calculates the mean value of the total connectivity index after calculating the brain connectivity between each network constitution area. The clustering coefficient, the path length, , And a centrality indicator.
이와 같이 분석부(20)의 연결성 및 네트워크 지표 산출부(22)에서는 연결성 및 네트워크를 분석하며, 비교부(24)에서는 도 2의 S50단계와 같이 네트워크 지표 데이터베이스(23)에 저장된 지표들과 상기 연결성 및 네트워크 지표 산출부(22)의 분석결과를 비교한다.The connectivity and network index calculator 22 of the analyzer 20 analyzes the connectivity and the network and the comparison unit 24 compares the indicators stored in the network index database 23 with the indicators stored in the network index database 23, And the analysis results of the connectivity and network index calculation unit 22 are compared.
그 다음, 분석부(20)의 연산부(25)는 각 지표별 강도를 산출하여 평균을 하고, 이를 이용하여 뇌손상 정도(Z)를 산출한다. Then, the calculating unit 25 of the analyzing unit 20 calculates the intensity of each index, performs an average, and calculates the degree of brain damage Z by using the average.
뇌손상 정도는 아래의 수학식 2로 표현할 수 있다.The degree of brain damage can be expressed by the following equation (2).
Figure PCTKR2017013455-appb-M000002
Figure PCTKR2017013455-appb-M000002
상기 수학식 2에서 X는 검출된 지표의 강도이며,
Figure PCTKR2017013455-appb-I000007
는 건강인 표준의 네트워크 지표 데이터베이스로부터 산출한 동일 연령대 및 성별 데이터베이스 평균값이고, σ는 건강인 표준 네트워크 지표 데이터베이스로부터 산출한 동일 연령대 및 성별 데이터베이스 표준편차값이다.In Equation (2), X is the intensity of the detected index,
Figure PCTKR2017013455-appb-I000007
Is the same age and gender database mean value as calculated from the network index database of the health standard and σ is the same age and gender database standard deviation value calculated from the healthy standard network index database.
그 다음, S60단계와 같이 산출된 뇌손상 정도(Z) 값을 판단하여 뇌손상 여부를 판단한다.Then, the brain damage degree (Z) value calculated as in step S60 is determined to determine whether or not the brain is damaged.
상기 뇌손상 정도(Z)는 0이거나, 양의 실수 또는 음의 실수의 값을 보이며, 양의 실수 또는 음의 실수 값의 절대값을 이용하여 뇌손상 정도를 판단한다.The degree of brain damage (Z) is zero or a positive real or negative real value, and the brain damage level is determined using the positive real or negative real value.
뇌손상 정도(Z)가 0이면 건강인 표준 네트워크 지표와 동일한 것이므로 손상이 없는 것으로 판단하며, 실수 값의 크기에 따라 뇌손상 정도를 판단할 수 있다. 산출된 뇌손상 정도(Z)에 대하여 개인적인 편차등을 고려하여 뇌손상 정도(Z)의 절대값이 2.5이하이면 뇌손상이 없는 것으로 판단할 수 있다.If the degree of brain damage (Z) is 0, it is determined that there is no damage since it is the same as the standard network index of the healthy person, and the degree of brain damage can be judged according to the magnitude of the real number. If the absolute value of the degree of brain damage (Z) is less than 2.5 in consideration of the individual deviation of the calculated brain damage degree (Z), it can be judged that there is no brain damage.
그 다음, S60단계의 판단결과 뇌손상 정도(Z)의 절대값이 2.5를 초과하는 경우 S70단계와 같이 동일 연령 성별 건강인 표준 네트워크 지표들과 검출된 네트워크 지표들을 비교하여 손상정도를 진단한다.Then, if the absolute value of the degree of brain damage (Z) exceeds 2.5 as a result of the determination in step S60, the degree of damage is diagnosed by comparing the network indicators of the same age, gender, health, and the detected network index as in step S70.
상기 S70단계에서는 건강인 그룹과 뇌손상 환자의 뇌 연결성(네트워크 구성 연결성)을 개별 비교하여 손상 연결 부위와 정도를 추정할 수 있다.In step S70, the damage connectivity region and the degree of damage may be estimated by separately comparing the brain connectivity (network configuration connectivity) between the healthy person group and the brain damage patient.
도 4는 네트워크 구성 영역 정보이다.4 is network configuration area information.
도 4를 참조하여 네트워크 구성 연결성의 예로는 MFG_L과 MFG_R 사이의 연결성 값이 될 수 있으며, S70단계는 모든 연결성을 상호 비교하여 손상 위치 및 정도를 판단하게 된다.Referring to FIG. 4, an example of the network configuration connectivity may be a connectivity value between MFG_L and MFG_R, and in step S70, all the connectivity is compared to determine the damage location and degree.
뇌의 특정 위치에서 뇌손상 환자의 뇌 네트워크 연결강도는 건강인의 뇌 네트워크 연결강도에 비하여 더 강하거나 더 약할 수도 있으며, 이러한 위치별 네트워크의 차이를 고려하여 손상 위치와 정도를 판단한다.The brain network connection strength of the brain damage patient in a certain position of the brain may be stronger or weaker than the brain network connection strength of the health person, and the position and degree of the damage are judged by considering the difference of the network by the position.
본 발명의 출원인은 15명의 외상성 뇌손상 환자와 동일 연령 및 성별의 건강인 20명의 안정상태 뇌 네트워크를 비교하였다.Applicants of the present invention compared the steady state brain networks of twenty patients with traumatic brain injury and twenty healthy persons of the same age and sex.
도 5는 DMN 알파 네트워크 내의 연결중 외상성 뇌손상 환자군(mTBI)과 건강대조군(HC)의 네트워크 연결강도 그래프이다.FIG. 5 is a graph of the network connection strength between the traumatic brain injury patient group (mTBI) and the healthy control group (HC) in the DMN alpha network.
도 5를 참조하면 DMN 알파 네트워크 내에서 외상성 뇌손상 환자군(mTBI)과 건강대조군(HC)의 네트워크 강도는 그 차이가 확연하게 나타난다. 즉 DMN 알파 네트워크의 강도를 비교하여 외상성 뇌손상의 판정을 할 수 있다.Referring to FIG. 5, the difference in the network intensity between the traumatic brain injury patient group (mTBI) and the health control group (HC) in the DMN alpha network is remarkable. In other words, the intensity of the DMN alpha network can be compared to determine the traumatic brain injury.
도 6에 DMN 알파 네트워크에서 건강 대조군(HC)이 외상성 뇌손상 환자군(mTBI)에 비하여 더 강한 연결성을 나타내는 경우를 도시하였고, 도 7에는 DMN 알파 네트워크에서 외상성 뇌손상 환자군(mTBI)이 건강 대조군(HC)에 비하여 더 강한 연결성을 나타내는 경우를 도시하였다.FIG. 6 shows that the healthy control group (HC) exhibits stronger connectivity than the traumatic brain injury patient group (mTBI) in the DMN alpha network. FIG. 7 shows that the traumatic brain injury patient group (mTBI) HC), as compared with the case of the non-HC.
도 6과 도 7을 참조하면 외상성 뇌손상 환자군(mTBI)의 경우 좌뇌와 우뇌의 동일 위치간의 연결성(MFGL-MFGR 등)은 건강 대조군(HC)에 비하여 더 큰 것으로 확인되며, 좌뇌와 우뇌의 다른 위치간의 연결성은 더 낮은 것으로 확인되었다.6 and 7, in the case of traumatic brain injury patients (mTBI), the connectivity between the left brain and the right brain (MFG L -MFG R ) is larger than that of the healthy control group (HC) Lt; RTI ID = 0.0 > connectivity. ≪ / RTI >
이처럼 동일한 뇌 네트워크 내에서도 위치에 따라 외상성 뇌손상 환자군(mTBI)의 연결성이 건강대조군(HC)에 비하여 상대적으로 더 강한 연결성을 보이거나 더 약한 연결성을 보일 수 있으며, 이러한 특징을 고려하여 특정 위치에서 뇌손상 발생을 검출할 수 있으며, 연결성의 강도 차이를 이용하여 손상의 정도를 확인할 수 있다.In this same brain network, the connectivity of the traumatic brain injury patient (mTBI) may show a stronger or weaker connection than the HC (healthy control group) The occurrence of damage can be detected, and the degree of damage can be confirmed using the difference in strength of connectivity.
도 8은 FPN 알파 네트워크 내의 연결중 외상성 뇌손상 환자군(mTBI)과 건강대조군(HC)의 네트워크 연결강도 그래프이다.FIG. 8 is a graph of the network connection strength between the traumatic brain injury patient group (mTBI) and the health control group (HC) in the FPN alpha network.
도 8에서도 DMN 알파 네트워크의 경우와 동일하게 외상성 뇌손상 환자군(mTBI)과 건강 대조군(HC)의 네트워크 강도가 확연한 차이를 보이며, DMN 알파 네트워크의 강도를 이용하여 외상성 뇌손상을 판단할 수 있다.In FIG. 8, as in the DMN alpha network, the network intensity of the traumatic brain injury group (mTBI) and the healthy control group (HC) are significantly different, and the traumatic brain injury can be judged by using the intensity of the DMN alpha network.
도 9는 FPN 알파 네트워크에서 건강 대조군(HC)이 외상성 뇌손상 환자군(mTBI)에 비하여 더 강한 연결성을 나타내는 경우를 도시하였고, 도 10에는 FPN 알파 네트워크에서 외상성 뇌손상 환자군(mTBI)이 건강 대조군(HC)에 비하여 더 강한 연결성을 나타내는 경우를 도시하였다.FIG. 9 shows the case where the health control group (HC) exhibits stronger connectivity than the traumatic brain injury patient group (mTBI) in the FPN alpha network, and FIG. 10 shows that the traumatic brain injury patient group (mTBI) HC), as compared with the case of the non-HC.
도 9와 도 10을 참조하면 외상성 뇌손상 환자군(mTBI)의 경우 좌뇌와 우뇌의 동일 위치간의 연결성(DLPFCL-DLPFCR 등)은 건강 대조군(HC)에 비하여 더 큰 것으로 확인되며, 좌뇌와 우뇌의 다른 위치간의 연결성은 더 낮은 것으로 확인되었다.Referring to FIGS. 9 and 10, it is found that the connectivity between the left brain and the right brain (DLPFC L -DLPFC R, etc.) is greater in the traumatic brain injury patient group (mTBI) than in the healthy control group (HC) Lt; RTI ID = 0.0 > connectivity. ≪ / RTI >
반면, 도 11의 AN 네트워크에서는 각 주파수 대역별 검출결과 모두 건강 대조군(HC)과 외상성 뇌손상 환자군(mTBI) 사이에 강도의 차이가 명확하게 구분되지 않으며, 따라서 AN 네트워크로의 강도 비교를 통해서는 외상성 뇌손상을 판단하기 어렵다.On the other hand, in the AN network shown in FIG. 11, the intensity differences between the health control group (HC) and the traumatic brain damage patient group (mTBI) are not clearly distinguished from each frequency band, Traumatic brain injury is difficult to judge.
이는 도 12에 도시한 SMN 네트워크에서도 동일하게 나타난다.This also applies to the SMN network shown in Fig.
이상 설명한 바와 같이 분석부(20)에서 분석된 뇌손상 정도는 S80단계와 같이 출력부(30)를 통해 출력된다. 여기서 출력이라 함은 측정 대상자가 쉽게 이해할 수 있는 보고서의 출력을 뜻하며, 이는 디스플레이 장치상의 표시 또는 종이 등에 직접 인쇄를 포함하는 개념일 수 있으며, 통신을 이용하여 다른 장치로 전송하는 것을 포함하는 개념으로 이해되어야 한다.As described above, the degree of brain damage analyzed by the analysis unit 20 is output through the output unit 30 as in step S80. Here, the term "output" refers to an output of a report that can be easily understood by a person to be measured, which may be a concept including display on a display device or direct printing on paper, etc., and includes transmission to another device using communication Should be understood.
본 발명에서는 S80단계의 수행을 위하여 자동화된 방법을 제안한다.The present invention proposes an automated method for performing step S80.
좀 더 구체적으로, 출력부(30)에서 출력을 하는 과정에서 뇌파 데이터에 컨텐츠를 태깅하여 함께 출력할 수 있다.More specifically, in the process of outputting from the output unit 30, the contents can be tagged and outputted together with the brain wave data.
예를 들어 손상 정도에 따라 정해진 텍스트 데이터를 상기 출력부(30)에 저장하고, 상기 분석부(20)에서 분석된 뇌손상 정도에 따라 정해진 텍스트 데이터를 함께 출력할 수 있다. 즉, 외상성 뇌손상 데이터의 시각화된 이미지에 텍스트를 더하여 출력할 수 있다.For example, the text data determined according to the degree of damage may be stored in the output unit 30 and the text data determined according to the degree of brain damage analyzed by the analysis unit 20 may be output together. That is, text can be added to a visualized image of traumatic brain injury data and output.
위에서 컨텐츠라 함은 각 뇌파 데이터를 설명하는 텍스트 데이터 일 수 있으며, 출력부(30)는 측정 대상자의 뇌파 데이터의 시각화된 이미지에 텍스트 데이터를 태깅하여 함께 출력할 수 있다.The content may be text data describing each brain wave data, and the output unit 30 may tag the text data to the visualized image of the brain wave data of the measurement subject and output it together.
또한, 상기 컨텐츠는 평가된 외상성 뇌손상 정도에 따라 임상적 해석 정보를 포함할 수 있다. In addition, the content may include clinical interpretation information according to the assessed degree of traumatic brain injury.
본 발명은 상기 실시예에 한정되지 않고 본 발명의 기술적 요지를 벗어나지 아니하는 범위 내에서 다양하게 수정, 변형되어 실시될 수 있음은 본 발명이 속하는 기술분야에서 통상의 지식을 가진 자에 있어서 자명한 것이다.It will be apparent to those skilled in the art that various modifications and variations can be made in the present invention without departing from the spirit and scope of the invention will be.
본 발명은 뇌의 위치별 기능적 연관성 및 네트워크 강도를 산출하고, 동일 연령 및 성별의 건강인 표준 네트워크 강도와 비교하여 객관적이고 신뢰성 높은 외상성 뇌손상 정도를 확인할 수 있는 것으로, 산업상 이용 가능성이 있다.The present invention can be used industrially because it can determine the objective and reliable traumatic brain injury degree by calculating the functional relevance and network strength of each brain position and comparing with the standard network strength of health of the same age and sex.

Claims (15)

  1. 안정 상태 뇌파를 측정하는 측정부;A measurement unit for measuring stable state brain waves;
    측정부에서 측정된 뇌파에서 잡음을 제거하고, 연결성 및 네트워크 지표를 분석하고, 성별 및 연령별로 분류된 건강인 표준 네트워크 지표와 비교하여, 외상성 뇌손상 정도를 산출하는 분석부; 및An analysis unit for calculating the degree of traumatic brain injury by removing noise from the EEG measured at the measurement unit, analyzing the connectivity and network index, and comparing with the health standard network index classified by gender and age; And
    상기 분석부의 분석결과를 출력하는 출력부를 포함하여 된 것을 특징으로 하는 뇌파 분석을 통한 외상성 뇌손상 평가 시스템.And an output unit for outputting an analysis result of the analysis unit.
  2. 제1항에 있어서,The method according to claim 1,
    분석부는, However,
    상기 측정부에서 측정된 뇌파 신호들에서 잡음을 제거하는 필터부;A filter unit for removing noise from the EEG signals measured by the measuring unit;
    상기 필터부에서 잡음이 제거된 뇌파 신호들의 연관성 및 네트워크를 분석하는 연관성 및 네트워크 지표 산출부;A correlation and network index calculator for analyzing a correlation and a network of EEG signals from which noise has been removed from the filter unit;
    건강인의 뇌 네트워크 강도를 저장하는 네트워크 지표 데이터베이스;Network index database to store the brain network strength of the health person;
    상기 연관성 및 네트워크 지표 산출부의 분석결과를 네트워크 지표 데이터베이스에 저장된 건강인의 뇌 네트워크와 비교하는 비교부; 및A comparing unit comparing the analysis results of the association and network index calculator with a brain network of a health person stored in a network index database; And
    상기 비교부의 비교 결과를 연산하여 외상성 뇌손상 정도를 산출하는 연산부를 포함하는 뇌파 분석을 통한 외상성 뇌손상 평가 시스템. And calculating a comparison result of the comparison unit to calculate a degree of traumatic brain injury.
  3. 제2항에 있어서,3. The method of claim 2,
    상기 연관성 및 네트워크 지표 산출부는,The association and network index calculation unit calculates,
    뇌의 기능적 연결성 및 네트워크 분석을 수행하며,Perform functional connectivity and network analysis of the brain,
    상기 기능적 연결성은, 디폴트 모드 네트워크(default mode network, DMN), 프론토 패리에탈 네트워크(fronto-parietal network, FPN)로 정의된 네트워크의 구성 영역들 사이의 기능적 연결성(functional connectivity)을 계산하는 것을 특징으로 하는 뇌파 분석을 통한 외상성 뇌손상 평가 시스템.The functional connectivity is characterized by calculating functional connectivity between the configuration areas of the network defined as a default mode network (DMN), a fronto-parietal network (FPN) Traumatic Brain Injury Assessment System Using EEG Analysis.
  4. 제3항에 있어서,The method of claim 3,
    상기 기능적 연결성은,Preferably,
    아래의 수학식 1로 표현되는 것을 특징으로 하는 뇌파 분석을 통한 외상성 뇌손상 평가 시스템.Wherein the system is characterized by being expressed by the following equation (1).
    수학식 1Equation 1
    Figure PCTKR2017013455-appb-I000008
    Figure PCTKR2017013455-appb-I000008
    상기 수학식 1에서 f는 주파수, Sxy(f)는 X와 Y 사이의 크로스 스펙트럼(cross-spectrum), Sxx(f)와 Syy(f)는 각각 X와 Y의 스펙트럼, im은 허수부 코히어런스(imaginary part of coherence)를 의미하고, ()는 () 내의 구간 평균(F) is a cross-spectrum between X and Y, Sxx (f) and Syy (f) are a spectrum of X and Y respectively, im is an imaginary part coherent () Denotes an imaginary part of coherence,
  5. 제3항에 있어서,The method of claim 3,
    상기 비교부는,Wherein,
    상기 디폴트 모드 네트워크와 상기 프론토 패리에탈 네트워크의 알파파 영역을 비교하여 뇌손상 위치와 정도를 확인하는 것을 특징으로 하는 뇌파 분석을 통한 외상성 뇌손상 평가 시스템.Wherein the default mode network is compared with the alpha region of the frontal parity network to determine the location and degree of brain damage.
  6. 제5항에 있어서,6. The method of claim 5,
    상기 알파파 영역에서, In the alpha wave region,
    외상성 뇌손상 환자군의 경우 좌뇌와 우뇌의 동일 위치간의 연결성은 건강 대조군에 비하여 더 크고, 좌뇌와 우뇌의 다른 위치 간의 연결성은 더 낮은 것을 특징으로 하는 뇌파 분석을 통한 외상성 뇌손상 평가 시스템.The traumatic brain injury evaluation system through brain wave analysis is characterized in that the connectivity between the left brain and the right brain in the traumatic brain injury group is larger than that in the healthy control group, and the connectivity between the left brain and the other right brain regions is lower.
  7. 제3항에 있어서,The method of claim 3,
    상기 연산부는,The operation unit,
    아래의 수학식 2를 통해 뇌손상 정도를 산출하는 것을 특징으로 하는 뇌파 분석을 통한 외상성 뇌손상 평가 시스템.Wherein the degree of brain damage is calculated through Equation (2) below.
    수학식 2Equation 2
    Figure PCTKR2017013455-appb-I000009
    Figure PCTKR2017013455-appb-I000009
    X는 검출된 뇌 네트워크 강도이며,
    Figure PCTKR2017013455-appb-I000010
    는 건강인 표준 뇌 네트워크 강도로서 동일 연령대 및 성별 데이터베이스 평균값이고, σ는 건강인 표준 뇌 네트워크 강도의 표준편차값    X is the detected brain network intensity,
    Figure PCTKR2017013455-appb-I000010
    Is the standardized brain network intensity of the healthy person and is the mean value of the same age and gender database and σ is the standard deviation value
  8. 제1항에 있어서,The method according to claim 1,
    상기 출력부는,The output unit includes:
    측정 대상자의 외상성 뇌손상 데이터의 시각화된 이미지에 텍스트 데이터를 태깅하여 함께 출력하는 것을 특징으로 하는 뇌파 분석을 통한 외상성 뇌손상 평가 시스템.Wherein the text data is tagged on the visualized image of the traumatic brain injury data of the subject to be measured and is output together.
  9. a) 안정상태의 뇌파 데이터를 측정하는 단계;a) measuring stable brain wave data;
    b) 뇌파 데이터를 필터링하여 잡음을 제거하는 단계;b) filtering EEG data to remove noise;
    c) 연결성 및 네트워크 지표를 산출하는 단계;c) calculating connectivity and network indicators;
    d) 상기 c) 단계의 결과를 동일 성별 건강인 표준 뇌 네트워크 지표와 비교하고, 뇌손상 정도를 산출하는 단계;d) comparing the result of step c) with a standard brain network index of the same gender, and calculating the degree of brain damage;
    e) 상기 뇌손상 정도의 절대값이 설정값을 초과하는 경우 뇌 네트워크의 개별 지표들을 비교하여 뇌손상 위치 및 정도를 확인하는 단계를 포함하는 뇌파 분석을 통한 외상성 뇌손상 평가 방법.e) comparing the individual indicators of the brain network to determine the location and extent of brain damage if the absolute value of the brain damage degree exceeds a set value.
  10. 제9항에 있어서,10. The method of claim 9,
    상기 c) 단계는,The step c)
    뇌의 기능적 연결성 및 네트워크 분석을 수행하되,Perform functional connectivity and network analysis of the brain,
    상기 기능적 연결성은, 디폴트 모드 네트워크(default mode network, DMN), 프론토 패리에탈 네트워크(fronto-parietal network, FPN)로 정의된 네트워크의 구성 영역들 사이의 기능적 연결성(functional connectivity)을 계산하는 것을 특징으로 하는 뇌파 분석을 통한 외상성 뇌손상 평가 방법.The functional connectivity is characterized by calculating functional connectivity between the configuration areas of the network defined as a default mode network (DMN), a fronto-parietal network (FPN) To evaluate the traumatic brain injury.
  11. 제10항에 있어서,11. The method of claim 10,
    상기 기능적 연결성은,Preferably,
    아래의 수학식 1로 표현되는 것을 특징으로 하는 뇌파 분석을 통한 외상성 뇌손상 평가 시스템.Wherein the system is characterized by being expressed by the following equation (1).
    수학식 1Equation 1
    Figure PCTKR2017013455-appb-I000011
    Figure PCTKR2017013455-appb-I000011
    상기 수학식 1에서 f는 주파수, Sxy(f)는 X와 Y 사이의 크로스 스펙트럼(cross-spectrum), Sxx(f)와 Syy(f)는 각각 X와 Y의 스펙트럼, im은 허수부 코히어런스(imaginary part of coherence)를 의미하고, ()는 () 내의 구간 평균(F) is a cross-spectrum between X and Y, Sxx (f) and Syy (f) are a spectrum of X and Y respectively, im is an imaginary part coherent () Denotes an imaginary part of coherence,
  12. 제10항에 있어서,11. The method of claim 10,
    상기 디폴트 모드 네트워크와 상기 프론토 패리에탈 네트워크의 알파파 영역을 비교하여 뇌손상 위치와 정도를 확인하는 것을 특징으로 하는 뇌파 분석을 통한 외상성 뇌손상 평가 방법.Wherein the default mode network is compared with an alpha wave region of the frontal parity network to verify the location and extent of brain damage.
  13. 제12항에 있어서,13. The method of claim 12,
    상기 알파파 영역에서, In the alpha wave region,
    외상성 뇌손상 환자군의 경우 좌뇌와 우뇌의 동일 위치간의 연결성은 건강 대조군에 비하여 더 크고, 좌뇌와 우뇌의 다른 위치 간의 연결성은 더 낮은 것을 특징으로 하는 뇌파 분석을 통한 외상성 뇌손상 평가 시스템.The traumatic brain injury evaluation system through brain wave analysis is characterized in that the connectivity between the left brain and the right brain in the traumatic brain injury group is larger than that in the healthy control group, and the connectivity between the left brain and the other right brain regions is lower.
  14. 제9항에 있어서,10. The method of claim 9,
    상기 d) 단계는,The step d)
    아래의 수학식 2를 통해 뇌손상 정도를 산출하는 것을 특징으로 하는 뇌파 분석을 통한 외상성 뇌손상 평가 시스템.Wherein the degree of brain damage is calculated through Equation (2) below.
    수학식 2Equation 2
    Figure PCTKR2017013455-appb-I000012
    Figure PCTKR2017013455-appb-I000012
    X는 검출된 뇌 네트워크 강도이며,
    Figure PCTKR2017013455-appb-I000013
    는 건강인 표준 뇌 네트워크 강도로서 동일 연령대 및 성별 데이터베이스 평균값이고, σ는 건강인 표준 뇌 네트워크 강도의 표준편차값    X is the detected brain network intensity,
    Figure PCTKR2017013455-appb-I000013
    Is the standardized brain network intensity of the healthy person and is the mean value of the same age and gender database and σ is the standard deviation value
  15. 제9항에 있어서,10. The method of claim 9,
    e) 측정 대상자의 외상성 뇌손상 데이터의 시각화된 이미지에 텍스트 데이터를 태깅하여 함께 출력하는 단계를 더 포함하는 뇌파 분석을 통한 외상성 뇌손상 평가 방법.e) tagging the text data to a visualized image of traumatic brain injury data of the subject to be measured and outputting together.
PCT/KR2017/013455 2017-11-23 2017-11-24 System and method for evaluating traumatic brain damage through brain wave analysis WO2019103188A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
KR1020170156922A KR20190059377A (en) 2017-11-23 2017-11-23 Traumatic brain injury evaluation system and method using brain wave analysis
KR10-2017-0156922 2017-11-23

Publications (1)

Publication Number Publication Date
WO2019103188A1 true WO2019103188A1 (en) 2019-05-31

Family

ID=66630617

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2017/013455 WO2019103188A1 (en) 2017-11-23 2017-11-24 System and method for evaluating traumatic brain damage through brain wave analysis

Country Status (2)

Country Link
KR (1) KR20190059377A (en)
WO (1) WO2019103188A1 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111931603A (en) * 2020-07-22 2020-11-13 北方工业大学 Human body action recognition system and method based on double-current convolution network of competitive combination network

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102321395B1 (en) 2019-02-07 2021-11-03 재단법인 아산사회복지재단 Method and program for calculating brain injury index of status epilepticus
KR102151497B1 (en) * 2019-12-02 2020-09-04 가천대학교 산학협력단 Method, System and Computer-Readable Medium for Prescreening Brain Disorders of a User

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20080068003A (en) * 2005-08-02 2008-07-22 브레인스코프 컴퍼니 인코퍼레이티드 Method for assessing brain function and portable automatic brain function assessment apparatus
US20120271148A1 (en) * 2011-04-20 2012-10-25 Medtronic, Inc. Brain condition monitoring based on co-activation of neural networks
JP2014525787A (en) * 2011-07-20 2014-10-02 エルミンダ リミテッド Method and system for estimating concussion
US20160367812A1 (en) * 2015-03-24 2016-12-22 Dirk De Ridder Methods of neuromodulation

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20080068003A (en) * 2005-08-02 2008-07-22 브레인스코프 컴퍼니 인코퍼레이티드 Method for assessing brain function and portable automatic brain function assessment apparatus
US20120271148A1 (en) * 2011-04-20 2012-10-25 Medtronic, Inc. Brain condition monitoring based on co-activation of neural networks
JP2014525787A (en) * 2011-07-20 2014-10-02 エルミンダ リミテッド Method and system for estimating concussion
US20160367812A1 (en) * 2015-03-24 2016-12-22 Dirk De Ridder Methods of neuromodulation

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
NOLTE, GUIDO ET AL.: "Identifying True Brain Interaction from EEG Ddata Using the Imaginary Part of Coherency", CLINICAL NEUROPHYSIOLOGY, vol. 115, no. 10, October 2004 (2004-10-01), pages 2292 - 2307, XP004559973 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111931603A (en) * 2020-07-22 2020-11-13 北方工业大学 Human body action recognition system and method based on double-current convolution network of competitive combination network
CN111931603B (en) * 2020-07-22 2024-01-12 北方工业大学 Human body action recognition system and method of double-flow convolution network based on competitive network

Also Published As

Publication number Publication date
KR20190059377A (en) 2019-05-31

Similar Documents

Publication Publication Date Title
WO2019103187A1 (en) Platform and method for evaluating cognitive function of brain through brain waves
WO2019103188A1 (en) System and method for evaluating traumatic brain damage through brain wave analysis
WO2010032929A2 (en) Apparatus and method for dementia diagnosis through eeg (electroencephalogram) analysis
WO2019088462A1 (en) System and method for generating blood pressure estimation model, and blood pressure estimation system and method
WO2015008936A1 (en) Diagnostic apparatus using habit, diagnosis management apparatus, and diagnostic method using same
WO2019103186A1 (en) Method and system for estimating age of brain through brain wave analysis
WO2020242239A1 (en) Artificial intelligence-based diagnosis support system using ensemble learning algorithm
WO2022169037A1 (en) Method for predicting mental health and providing mental health solutions by learning psychological indicator data and physical indicator data on basis of machine learning, and mental health evaluation device using same
WO2018135693A1 (en) In-ear headset device for measuring stress, and method for measuring stress using same
WO2020119403A1 (en) Hospitalization data abnormity detection method, apparatus and device, and readable storage medium
WO2022145519A1 (en) Electrocardiogram visualization method and device using deep learning
WO2018135692A1 (en) Wearable device for motion recognition and control, and method for motion recognition control using same
KR100945197B1 (en) A system for performing a medical examination, a method for performing a vision examination, and a method of synchronizing the presentation of a series of sensory stimuli with the rate of sampling visual evoked potential signals
WO2018147477A1 (en) Worker health management method using smartphone application
US9633168B2 (en) Biometric identity validation for use with unattended tests for medical conditions
WO2021107309A1 (en) Method for labelling intervals of interest, associated with eeg analysis, in eeg signal, and eeg analysis system for performing same
WO2015186963A1 (en) Biological brain age calculation device and calculation method therefor
WO2023059116A1 (en) Method and device for determining visual fatigue occurrence section
WO2020119118A1 (en) Abnormal data processing method, apparatus and device, and computer readable storage medium
WO2019014955A1 (en) Mobile terminal for blood sugar detection
WO2013077558A1 (en) Robot-based autism diagnosis device using electroencephalogram and method therefor
WO2018147560A1 (en) Worker health management system and monitoring method using biosignal-based safety management workwear
WO2018048072A1 (en) Apparatus for eliminating motion artifacts by using ppg signal and method thereof
WO2021201582A1 (en) Method and device for analyzing causes of skin lesion
WO2016200243A1 (en) Computing apparatus and method for aiding classification of mibyeong

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17932619

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 17932619

Country of ref document: EP

Kind code of ref document: A1