WO2021246922A1 - Procédé de détection de crises épileptiques dans des enregistrements eeg longs - Google Patents

Procédé de détection de crises épileptiques dans des enregistrements eeg longs Download PDF

Info

Publication number
WO2021246922A1
WO2021246922A1 PCT/RU2021/050226 RU2021050226W WO2021246922A1 WO 2021246922 A1 WO2021246922 A1 WO 2021246922A1 RU 2021050226 W RU2021050226 W RU 2021050226W WO 2021246922 A1 WO2021246922 A1 WO 2021246922A1
Authority
WO
WIPO (PCT)
Prior art keywords
extremum
epileptiform
signal
eeg signal
discharges
Prior art date
Application number
PCT/RU2021/050226
Other languages
English (en)
Russian (ru)
Inventor
Павел Викторович ПРИХОДЬКО
Иван Игоревич ПАНИН
Original Assignee
ОБЩЕСТВО С ОГРАНИЧЕННОЙ ОТВЕТСТВЕННОСТЬЮ "СберМедИИ"
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 ОБЩЕСТВО С ОГРАНИЧЕННОЙ ОТВЕТСТВЕННОСТЬЮ "СберМедИИ" filed Critical ОБЩЕСТВО С ОГРАНИЧЕННОЙ ОТВЕТСТВЕННОСТЬЮ "СберМедИИ"
Publication of WO2021246922A1 publication Critical patent/WO2021246922A1/fr

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/14—Fourier, Walsh or analogous domain transformations, e.g. Laplace, Hilbert, Karhunen-Loeve, transforms
    • G06F17/148—Wavelet transforms
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning

Definitions

  • This technical solution relates to the fields of medicine and computing, in particular, to a computer-implemented method for automated detection of generalized epileptiform discharges (hereinafter referred to as GER) in long-term recording of an electroencephalogram (hereinafter referred to as EEG).
  • GER generalized epileptiform discharges
  • EEG electroencephalogram
  • epilepsy - seizures - are poorly suited for regular monitoring of the course of the disease due to their unpredictability and health risks.
  • characteristic patterns of epileptiform activity can be observed - epileptiform discharges (ER), assessing the frequency of which it is possible to conclude about the intensity and dynamics of the disease.
  • ER epileptiform discharges
  • ER is usually determined by specialist epileptologists by visual examination of long-term EEG recordings (the recording should include a signal taken in a dream to improve the accuracy of the conclusion). This is a very monotonous and tedious process, as it requires a person to review and manually mark off approximately 10 or more hours of recording.
  • the specialist must mark each ER, and then, on the basis of the obtained markup, determine the localization in the case of focal epileptiform discharges (hereinafter - FER) and calculate the indices of epileptiform activity to assess the condition and write a conclusion. This work takes 3-4 hours and has the following problems.
  • the prior art discloses a source of information US 8,972,001 B2 03.03.2015 disclosing a method and a data display system in which a plurality of epochs are stitched together with an overlapping section to represent a continuous EEG recording. Artifact reduction is performed in epochs, and then epochs are merged together with overlapping sections, preferably between two and four seconds.
  • the initial EEG signal is generated from a machine containing a plurality of electrodes and a processor; split the original EEG signal into many epochs, each of the many epochs having an epoch duration and an overlap increment; performing artifact reduction for a plurality of epochs to generate a plurality of artifact-reduced epochs; and also combine multiple reduced artifact epochs to generate a continuous processed EEG recording, with each of the multiple reduced artifact epochs having an epoch duration of two seconds and in one second increments, with each of the multiple reduced artifact epochs overlapping the reduced epoch of adjacent artifacts to produce a continuous processed EEG recording without discontinuities in a continuous processed EEG recording, with each of the plurality of artifact-reduced epochs and artifact-reduced contiguous epochs being combined using a weighted average, with the weight proportional to the
  • the proposed solution is aimed at automatic marking of focal epileptiform discharges of the EEG signal.
  • the closest analogue is the Persyst 13 software package, in which only 60% of the spikes are marked using an automatic procedure. This tells the doctor that when using the package, 40% of the digits will remain unmarked and means the need to carefully review the entire original signal to make sure that nothing important has been missed. The need to carefully review the entire signal increases the signal processing time.
  • the technical problem to be solved by the claimed technical solution is the creation of a computer-implemented method for detecting generalized epileptiform discharges in a long-term EEG recording, which is described in an independent claim. Additional embodiments of the present invention are presented in the dependent claims.
  • the technical result consists in providing accurate detection of generalized epileptiform discharges, reducing the number of missed discharges and reducing the time for detecting generalized epileptiform discharges.
  • the claimed result is achieved through the implementation of a computer-implemented method for automated detection of generalized epileptiform discharges in a long-term EEG recording, containing the stages at which: on a computing device preprocessing of at least one EEG signal is performed, where in at least one EEG signal local extrema with a window of 0.02 seconds, with each extreme being marked in accordance with the existing markup. for each extremum, signs are calculated based on the original EEG signal and the wavelet transform of the original EEG signal; a sample of features and marked marks is fed to the input of the classifier; to reduce the number of false negative alarms, the probability threshold is set at 5%. post-processing of the obtained results of the classifier is carried out; close extrema marked as epileptiform are combined into one epileptiform discharge.
  • the maximum amplitude in the window is 0.05 seconds around the extremum.
  • FIG. 2 illustrates the general scheme of the proposed method.
  • FIG. 3 illustrates an example of a general arrangement of a computing device.
  • GER generalized epileptiform discharges
  • FED focal epileptiform discharges
  • the present invention is directed to the implementation of a computer-implemented method for detecting generalized epileptiform discharges in a long-term EEG recording.
  • ERs can have various shapes, however, as a rule, they contain a common element - a spike or a sharp wave. These patterns differ only in duration (20-70 ms for a spike, 70-200 ms for a sharp wave) and do not carry any other qualitative difference, therefore, for simplicity, the term spike will be used everywhere, except when it is required to explicitly separate these concepts.
  • a spike is a burst of activity in the form of a short sharp peak clearly visible on the signal.
  • a spike is often followed by a slow wave - a high-amplitude hilly disturbance with a duration of 150-350 ms at a spectral frequency of the order of 3.5-4 Hz. The combination of these patterns is called the spike-slow wave complex.
  • GER can have a rather diverse form, usually the following types of discharge forms are distinguished (their form is shown in Fig. 1):
  • the task of the proposed method in automatic mode, is to display the GER markup and the indices of epileptiform activity calculated from the markup to a specialist.
  • the indices of epileptiform activity are understood as a numerical indicator in the conclusion, on the basis of which an assessment is made of the severity and dynamics of the condition, as well as the effectiveness of therapy and, accordingly, the final result of the proposed method.
  • the accuracy of the index determination depends on the number of bits missed and the number of manually uncorrected false positives.
  • the solution of the problem is carried out in the construction of an algorithm that, based on the training sample (a set of X-Y pairs), using the solution of the unbalanced classification problem, builds a model that can distinguish between benign and epileptiform EEG patterns in patients that were not included in the training set.
  • the specialist has preliminary information that the recording shows an encephalogram of a person who, upon preliminary examination, found activity similar to GER.
  • Each EEG recording is accompanied by an expert markup, indicating the places and durations detected by the GER.
  • a conclusion with information about the person's condition and the values of the indices is attached to each patient.
  • the markings and conclusions are drawn up in accordance with applicable standards.
  • the specified data is in the database.
  • the specialist downloads to the computing device a file with a long-term EEG recording (7-12 hours) made according to the 10-20 system and starts the proposed method for marking the GER.
  • the 10-20 system refers to the standardized scalp electrode positioning system recommended by the International Federation of Clinical Neurophysiology (IFCN). According to this system, the location of the electrodes is determined by measuring the head between the external landmarks and taking 10 or 20% of these measurements.
  • IFCN International Federation of Clinical Neurophysiology
  • the computing device preprocesses at least one EEG signal from the database, where local extrema with a window of 0.02 seconds are highlighted in at least one EEG signal, and each extremum is marked in accordance with the existing markup.
  • local extrema in the signal are identified, which were considered “candidates” in the ER, in addition, the numerical derivative of the signal with respect to time is estimated.
  • step 102 of the attached solution for each extremum, features are calculated based on the original EEG signal and the wavelet transform of the original EEG signal.
  • the first group consisted of various statistics over the baseline signal.
  • the second group of features contained statistics based on the wavelet transform of the signal.
  • the first group has the following common features:
  • Such filtering reduces the amplitude of the slow wave, practically without affecting the amplitude of the spike, which allows this feature to distinguish them.
  • delta_grad_w0.05 the modulus of the difference between the averaged signal gradient to the right and to the left of the extremum in a window of 0.05 seconds ("sharpness").
  • the second group - wavelet signs - consisted of statistics on the wavelet transform of the initial EEG signal.
  • the wavelet transform can be used, in particular, to find areas of fast and slow signal variability, which is useful in the selection of spikes and slow waves.
  • the next step (103) of the proposed method is the submission of a sample of features and marked marks to the input of the classifier.
  • Xi - a set of variables characterizing various pre-calculated characteristics of a small segment of the EEG signal
  • Yi is a binary variable characterizing the presence of epileptiform patterns during this signal segment, which is the mark of a specialist. This variable is taken from the database.
  • Algorithm output a predictive model that takes Xi as input and estimates the probability of the presence of epileptiform patterns in the corresponding signal segment (real number in the range [0, 1]).
  • the proposed solution uses the XGBoost (Extreme Gradient Boosting) library that implements the gradient boosting model.
  • the method consists in creating an ensemble of successively refining each other decision trees.
  • a typical way to account for class imbalance in many methods, including XGBoost, is to introduce a scaling factor that increases the contribution of each of the elements of the positive class to the overall optimized error function.
  • a probability threshold of 5% is set.
  • the probability threshold was additionally shifted, on the basis of which the model makes a decision up to 5%.
  • the classifier considers epileptiform events for which its estimated probability exceeds 50%.
  • step 105 post-processing of the obtained results of the classifier is carried out, close extrema marked as epileptiform are combined into one epileptiform discharge.
  • the proposed method was compared with the solution offered by the Persyst 13 software package .
  • Persyst 13 When Persyst 13 is launched, it simultaneously tries to mark both focal and generalized discharges, therefore, for completeness of comparison, the values of the metrics of the proposed method were compared with two Persyst markings: with a markup containing only predicted generalized discharges , and markup containing all types of bits.
  • FIG. 3 a general diagram of a computing device (300) that provides data processing necessary for the implementation of the claimed solution will be presented below.
  • the device (300) contains such components as: one or more processors (301), at least one memory (302), data storage means (303), input / output interfaces (304), I / O means ( 305), networking tools (306).
  • the processor (301) of the device performs the basic computational operations necessary for the operation of the device (300) or the functionality of one or more of its components.
  • the processor (301) executes the necessary machine-readable instructions contained in the main memory (302).
  • Memory (302) is made in the form of RAM and contains the necessary program logic that provides the required functionality.
  • the data storage medium (303) can be performed in the form of HDD, SSD disks, raid array, network storage, flash memory, optical information storage devices (CD, DVD, MD, Blue-Ray disks), etc.
  • the means (303) allows performing long-term storage of various types of information, for example, the aforementioned files with user data sets, a database containing records of time intervals measured for each user, user identifiers, etc.
  • Interfaces (304) are standard means for connecting and working with the server side, for example, USB, RS232, RJ45, LPT, COM, HDMI, PS / 2, Lightning, FireWire, etc.
  • interfaces (304) depends on the specific implementation of the device (300), which can be a personal computer, mainframe, server cluster, thin client, smartphone, laptop, etc.
  • a keyboard should be used.
  • the hardware design of the keyboard can be any known: it can be either a built-in keyboard used on a laptop or netbook, or a stand-alone device connected to a desktop computer, server or other computer device.
  • the connection can be as wired, in which the keyboard connecting cable is connected to the PS / 2 or USB port located on the system unit of a desktop computer, and wireless, in which the keyboard exchanges data via a wireless channel, for example, a radio channel, with a base station, which, in turn, is directly connected to the system unit, for example, to one of the USB ports.
  • I / O data can also include: joystick, display (touch screen), projector, touchpad, mouse, trackball, light pen, speakers, microphone, etc.
  • Networking means (306) are selected from a device that provides network reception and transmission of data, for example, Ethernet card, WLAN / Wi-Fi module, Bluetooth module, BLE module, NFC module, IrDa, RFID module, GSM modem, etc.
  • the means (305) provide the organization of data exchange via a wired or wireless data transmission channel, for example, WAN, PAN, LAN, Intranet, Internet, WLAN, WMAN or GSM.
  • the components of the device (300) are interconnected via a common data bus (310).

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Mathematical Physics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Software Systems (AREA)
  • Mathematical Optimization (AREA)
  • General Engineering & Computer Science (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Pure & Applied Mathematics (AREA)
  • Computing Systems (AREA)
  • Medical Informatics (AREA)
  • Evolutionary Computation (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Artificial Intelligence (AREA)
  • Algebra (AREA)
  • Databases & Information Systems (AREA)
  • Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)

Abstract

La présente invention se rapporte au domaine de la médecine et des techniques informatiques. L'invention concerne un procédé mis en oeuvre par ordinateur de détection automatique de crises épileptiques généralisées dans des enregistrements EEG longs, comprenant les étapes suivantes: effectuer dans un dispositif informatique un prétraitement d'au moins un signal EEG, dans lequel on sépare dans ledit au moins un signal EEG des extrêmes locaux avec une fenêtre de 0,02 seconde et on marque chaque extrême en fonction de la signalisation existante; pour chaque extrême, on calcule des indices sur la base du signal EEG initial et d'une conversion par ondelettes du signal EEG initial; la sélection des indices et des étiquettes marquées est envoyée vers l'entrée d'une unité de tri; afin de réduire le nombre d'actionnements faux négatifs, on établit un seuil de probabilité de 5%; on effectue un post-traitement des résultats obtenus de l'unité de tri, et les extrêmes proches marqués comme épileptiques sont regroupés en une catégorie épileptique. Le résultat technique consiste en une détection précise des crises épileptiques généralisées, une diminution du nombre de crises passées inaperçues et une diminution du temps de détection des crises épileptiques généralisées.
PCT/RU2021/050226 2020-06-01 2021-07-19 Procédé de détection de crises épileptiques dans des enregistrements eeg longs WO2021246922A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
RU2020118039 2020-06-01
RU2020118039A RU2747712C1 (ru) 2020-06-01 2020-06-01 Способ детектирования эпилептиформных разрядов в длительной записи ээг

Publications (1)

Publication Number Publication Date
WO2021246922A1 true WO2021246922A1 (fr) 2021-12-09

Family

ID=75919917

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/RU2021/050226 WO2021246922A1 (fr) 2020-06-01 2021-07-19 Procédé de détection de crises épileptiques dans des enregistrements eeg longs

Country Status (2)

Country Link
RU (1) RU2747712C1 (fr)
WO (1) WO2021246922A1 (fr)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115530845A (zh) * 2022-10-17 2022-12-30 常州瑞神安医疗器械有限公司 一种检测癫痫脑电信号中异常放电的方法
CN116048282A (zh) * 2023-03-06 2023-05-02 中国医学科学院生物医学工程研究所 一种数据处理方法、系统、装置、设备及存储介质

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117033988B (zh) * 2023-09-27 2024-03-12 之江实验室 基于神经电信号的癫痫样棘波处理方法和装置

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
RU2294696C1 (ru) * 2005-11-21 2007-03-10 Юлия Исааковна Вайншенкер Способ оценки областей эпилептической активности головного мозга
US20140135643A1 (en) * 2011-11-25 2014-05-15 Persyst Development Corporation Method And System For Displaying Data
WO2016154298A1 (fr) * 2015-03-23 2016-09-29 Temple University-Of The Commonwealth System Of Higher Education Système et procédé d'interprétation automatique de signaux d'un eeg à l'aide d'un modèle statistique d'apprentissage en profondeur
WO2018178333A1 (fr) * 2017-03-31 2018-10-04 Bioserenity Procédé d'identification d'activité cérébrale pathologique à partir d'un électroencéphalogramme du cuir chevelu

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
RU2462987C1 (ru) * 2011-08-05 2012-10-10 Дмитрий Валерьевич Котов Способ выявления эпилептиформной активности
WO2016028888A1 (fr) * 2014-08-19 2016-02-25 The General Hospital Corporation Système et procédé d'annotation et d'analyse de formes d'onde d'électroencéphalogramme (eeg)

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
RU2294696C1 (ru) * 2005-11-21 2007-03-10 Юлия Исааковна Вайншенкер Способ оценки областей эпилептической активности головного мозга
US20140135643A1 (en) * 2011-11-25 2014-05-15 Persyst Development Corporation Method And System For Displaying Data
WO2016154298A1 (fr) * 2015-03-23 2016-09-29 Temple University-Of The Commonwealth System Of Higher Education Système et procédé d'interprétation automatique de signaux d'un eeg à l'aide d'un modèle statistique d'apprentissage en profondeur
WO2018178333A1 (fr) * 2017-03-31 2018-10-04 Bioserenity Procédé d'identification d'activité cérébrale pathologique à partir d'un électroencéphalogramme du cuir chevelu

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115530845A (zh) * 2022-10-17 2022-12-30 常州瑞神安医疗器械有限公司 一种检测癫痫脑电信号中异常放电的方法
CN116048282A (zh) * 2023-03-06 2023-05-02 中国医学科学院生物医学工程研究所 一种数据处理方法、系统、装置、设备及存储介质
CN116048282B (zh) * 2023-03-06 2023-08-04 中国医学科学院生物医学工程研究所 一种数据处理方法、系统、装置、设备及存储介质

Also Published As

Publication number Publication date
RU2747712C1 (ru) 2021-05-13

Similar Documents

Publication Publication Date Title
WO2021246922A1 (fr) Procédé de détection de crises épileptiques dans des enregistrements eeg longs
Aziz et al. ECG-based machine-learning algorithms for heartbeat classification
US10869610B2 (en) System and method for identifying cardiac arrhythmias with deep neural networks
US20210358611A1 (en) Method for Detecting Epileptic Spike, Method for Training Network Model, and Computer Device
CA2942904C (fr) Systeme et procede permettant l'identification de source focale
Naseri et al. Computerized quality assessment of phonocardiogram signal measurement-acquisition parameters
Venton et al. Robustness of convolutional neural networks to physiological electrocardiogram noise
Lachner-Piza et al. Automatic detection of high-frequency-oscillations and their sub-groups co-occurring with interictal-epileptic-spikes
CN106923820B (zh) 一种心电信号伪差识别方法及心电信号伪差识别装置
Malik et al. An adaptive QRS detection algorithm for ultra-long-term ECG recordings
JP5449207B2 (ja) 生理学データの形態フィーチャ解析のシステム
Charupanit et al. Detection of anomalous high‐frequency events in human intracranial EEG
US11331048B2 (en) Brain connectivity analysis system and brain connectivity analysis method
KR102380501B1 (ko) 다차원 성격 검사 장치 및 방법
RU2754779C1 (ru) Способ выявления депрессии на основе данных ээг
RU2753267C1 (ru) Способ детектирования фокальных эпилептиформных разрядов в длительной записи ээг
CN112057068A (zh) 一种癫痫病理数据分类方法、装置及存储介质
Georgieva-Tsaneva et al. Cardio-diagnostic assisting computer system
Khan et al. Optimized arterial line artifact identification algorithm cleans high-frequency arterial line data with high accuracy in critically ill patients
WO2021168121A1 (fr) Méthodes et systèmes pour prédire des taux d'évolution de la dégénérescence maculaire liée à l'âge
Botros et al. Automatic Heart Failure Stratification Using a Convolutional Neural Network
US20240099640A1 (en) Electrocardiogram analysis
US20240099638A1 (en) Electrocardiogram interpretation
CN117770832B (zh) 基于交叉验证的心电信号错误标记训练样本识别方法
RU2767157C2 (ru) Способ и система автоматического анализа экг

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: 21818894

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: 21818894

Country of ref document: EP

Kind code of ref document: A1