Biological signal analysis device, waveform generation specification method, and program

The biological signal analysis device automates the identification of epileptic lesion onset times in epilepsy diagnosis, enhancing diagnostic efficiency and accuracy by analyzing waveform data from multiple sensors.

JP2024166991AInactive Publication Date: 2024-11-29RICOH CO LTD
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
JP2023083473
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-05-19
Publication Date
2024-11-29
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Existing methods for diagnosing epilepsy using magnetoencephalography and electroencephalography require manual search for the onset time of epileptic lesions, which is time-consuming and prone to variability based on expert skill.

Method used

A biological signal analysis device and method that automatically identifies the onset time of epileptic lesions by analyzing waveform data from multiple sensors, using detection and search units to determine the time of signal generation from the lesioned part of the brain.

Benefits of technology

Improves the efficiency and stability of epilepsy diagnosis by accurately specifying the time of signal generation from epileptic lesions, reducing reliance on manual searches and expert variability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024166991000001_ABST
    Figure 2024166991000001_ABST
Patent Text Reader

Abstract

To provide a biological signal analysis device, a waveform generation specification method, and a program capable of automatically specifying the time when a signal is generated from a lesioned part of the brain, and improving efficiency of diagnosis and stability of diagnosis accuracy for epilepsia.SOLUTION: A biological signal analysis device includes an acquisition unit for acquiring waveform data on a biological signal measured by a plurality of sensors; a detection unit for detecting the time when characteristic waveform information on IED (Interictal Epileptiform Discharge) of the waveform data acquired by the acquisition unit; and a search unit for searching for the onset time when a signal is generated from a lesioned part of the brain in a predetermined search range in the waveform data with the time detected by the detection unit as a reference.SELECTED DRAWING: Figure 4
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present invention relates to a biological signal analysis device, a waveform generation specifying method, and a program. [Background technology]

[0002] In clinical epilepsy diagnosis using magnetoencephalography and electroencephalography, a technique called the equivalent current dipole method is used to evaluate the localization of epileptic lesions in the brain. In the equivalent current dipole method, the location of the epileptic lesion is estimated by estimating the current source (dipole) that generates the magnetic field measured on the scalp. In order to estimate the dipole, it is necessary to identify the time when characteristic waveform information (also called spikes) called interictal epileptic discharges (IEDs) appeared from the time-series waveform data detected by multiple sensors, and the sensor where the waveform information appeared.

[0003] However, the signal generated from the epileptic lesion may move over time, and the signal strength is not necessarily the maximum when the signal is generated from the epileptic lesion. Therefore, after detecting the characteristic waveform of an IED in the waveform data, the position estimated based on the waveform data corresponding to the time of the peak part of the waveform is not necessarily the epileptic lesion. Therefore, it is necessary to manually search for the time when the signal was generated from the actual epileptic lesion (onset time) based on information such as an isomagnetic field map by going back in time from the peak part of the waveform data, which is very time-consuming. In addition, when performing such a manual search, there is also a problem that the search results vary depending on the skill of the expert such as a doctor.

[0004] As a technique for extracting the time and sensor at which characteristic waveform information appears in such waveform data, a method has been disclosed that uses a comparison step in which each waveform data acquired by multiple sensors is compared with at least one or more pieces of characteristic waveform information, a determination step in which the probability of occurrence of the characteristic waveform information in at least a certain section of the waveform data is determined based on the correlation rate between the peak section of the waveform data and the characteristic waveform information, and an identification step in which the time at which a section matching the characteristic waveform information appeared and the corresponding sensor are identified based on the probability of occurrence (for example, Patent Document 1). Summary of the Invention [Problem to be solved by the invention]

[0005] However, in the technology described in Patent Document 1, although the time is specified based on the occurrence probability of the IED, this method often infers the time near the peak of the characteristic waveform of the IED. Therefore, the problem that the time when the signal was generated from the epileptic lesion (onset time) must be manually searched remains.

[0006] The present invention has been made in consideration of the above, and aims to provide a biological signal analysis device, a waveform generation identification method, and a program that can automatically identify the time when a signal is generated from an epileptic lesion, thereby improving the efficiency of epilepsy diagnosis and the stability of diagnostic accuracy. [Means for solving the problem]

[0007] In order to solve the above-mentioned problems and achieve the object, the present invention is characterized by comprising an acquisition unit that acquires waveform data of biological signals measured by a plurality of sensors, a detection unit that detects a time at which characteristic waveform information of an IED (Interictal Epileptiform Discharge) appears in the waveform data acquired by the acquisition unit, and a search unit that searches for an onset time at which a signal was generated from a lesion in the brain within a predetermined search range in the waveform data based on the time detected by the detection unit. Effect of the Invention

[0008] According to the present invention, the time at which a signal is generated from a lesion in the brain can be automatically identified, thereby making it possible to improve the efficiency of epilepsy diagnosis and the stability of diagnostic accuracy. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram showing an example of the overall configuration of a biological signal measuring system according to a first embodiment. [Diagram 2] FIG. 2 is a diagram illustrating an example of a functional block configuration of the server according to the first embodiment. [Diagram 3] FIG. 3 is a diagram illustrating an example of a hardware configuration of the information processing device according to the first embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of a functional block configuration of the information processing device according to the first embodiment. [Diagram 5] FIG. 5 is a diagram showing an example of waveform data in which characteristic waveform information of an IED appears. [Figure 6] FIG. 6 is a flowchart showing an example of the flow of the onset search process of the information processing device according to the first embodiment. [Figure 7] FIG. 7 is a flowchart showing an example of the flow of the origin / peak determination process of the information processing device according to the first embodiment. [Figure 8]FIG. 8 is a flowchart showing an example of the flow of a search range determination process of the information processing device according to the first embodiment. [Figure 9] FIG. 9 is a diagram illustrating an example of a functional block configuration of an information processing device according to the second embodiment. As illustrated in FIG. [Figure 10] FIG. 10 is a flowchart showing an example of the flow of an onset time identification process of the information processing device according to the second embodiment. [Figure 11] FIG. 11 is a flowchart showing an example of the flow of an onset search process of the information processing device according to the third embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Hereinafter, the embodiments of the biosignal analysis device, the waveform generation identification method, and the program according to the present invention will be described in detail with reference to the drawings. Furthermore, the present invention is not limited to the following embodiments, and the components in the following embodiments include those that a person skilled in the art can easily conceive, those that are substantially the same, and those that are within the scope of what is called equivalent. Furthermore, various omissions, substitutions, modifications, and combinations of the components can be made without departing from the spirit of the following embodiments.

[0011] [First embodiment] (Overall configuration of biosignal measurement system) Fig. 1 is a diagram showing an example of the overall configuration of a biosignal measurement system according to the first embodiment. Fig. 2 is a diagram showing an example of the functional block configuration of a server according to the first embodiment. The overall configuration of a biosignal measurement system 1 according to this embodiment will be described with reference to Figs. 1 and 2.

[0012] The biosignal measurement system 1 is a system that measures and displays multiple types of biosignals (e.g., magneto-encephalography (MEG) signals and electro-encephalography (EEG) signals) of a subject from a specific source (body part). Note that the biosignals to be measured are not limited to magneto-encephalography (MEG) signals and electro-encephalography (EEG) signals, but may be, for example, electrical signals generated in response to cardiac activity (electrical signals that can be expressed as an electrocardiogram).

[0013] As shown in Fig. 1, the biosignal measurement system 1 includes a measurement device 3 that measures one or more biosignals of a subject, a server 40 that records one or more types of biosignals measured by the measurement device 3, and an information processing device 50 that is a biosignal analysis device that analyzes one or more types of biosignals recorded in the server 40. The measurement device 3 is a magnetoencephalograph that measures, for example, a brain magnetic field or a magnetoencephalogram (an example of a biosignal) generated at the timing of application of a stimulus. Note that, although the server 40 and the information processing device 50 are depicted separately in Fig. 1, for example, at least a part of the functions of the server 40 may be incorporated into the information processing device 50.

[0014] In the example of FIG. 1, the subject (subject) lies on his / her back on the measurement table 4 with electrodes (or sensors) for measuring electroencephalograms attached to his / her head, and places his / her head in a recess 32 of a Dewar 31 of the measurement device 3. The Dewar 31 is a holding container in an extremely low temperature environment using liquid helium. A number of magnetic sensors (e.g., SQUID (Superconducting Quantum Interference Device) sensors) for measuring magnetoencephalograms are arranged inside the recess 32 of the Dewar 31. The measurement device 3 collects electroencephalogram signals from the electrodes and magnetoencephalogram signals from the magnetic sensors, and outputs time-series waveform data (hereinafter, sometimes simply referred to as waveform data) including the collected electroencephalogram signals and magnetoencephalogram signals to a server 40. The waveform data output to the server 40 is read out and displayed by an information processing device 50, and is analyzed. In general, the Dewar 31 and the measurement table 4 incorporating the magnetic sensors are arranged in a magnetically shielded room, but for convenience, the magnetically shielded room is not shown in FIG. 1.

[0015] The information processing device 50 is a device that analyzes waveform data of MEG signals from multiple magnetic sensors and waveform data of EEG signals from multiple electrodes. For example, the information processing device 50 displays waveform data of MEG signals and EEG signals in synchronization on the same time axis. Here, the EEG signal is a signal that represents the electrical activity of nerve cells (the flow of ionic charges that occurs in the dendrites of neurons during synaptic transmission) as a voltage value between electrodes. Also, the MEG signal is a signal that represents minute electric field fluctuations caused by electrical activity of the brain.

[0016] As shown in FIG. 2, the server 40 includes a data acquisition unit 401 and a data storage unit 402.

[0017] The data acquisition unit 401 is a functional unit that periodically acquires waveform data such as MEG signals and EEG signals measured by the measurement device 3. The waveform data includes time series data of each MEG signal measured by a plurality of magnetic sensors in the Dewar 31 of the measurement device 3, and time series data of each signal measured by a plurality of electrodes for measuring EEG attached to the head of the subject (person to be measured).

[0018] The data storage unit 402 is a functional unit that stores the waveform data acquired from the measurement device 3 .

[0019] 1 shows a configuration in which the measuring device 3 and the server 40 are directly connected, and the server 40 and the information processing device 50 are directly connected, but they may be configured to communicate data with each other via a network. The network connection method may be wired or wireless. The server 40 may also be configured to be a server on a network and connected to the cloud, for example.

[0020] (Hardware configuration of information processing device) 3 is a diagram showing an example of a hardware configuration of an information processing device according to the first embodiment. The hardware configuration of an information processing device 50 according to the present embodiment will be described with reference to FIG.

[0021] As shown in FIG. 3, the information processing device 50 includes a CPU (Central Processing Unit) 101, a RAM (Random Access Memory) 102, a ROM (Read Only Memory) 103, an auxiliary storage device 104, a network I / F 105, an input device 106, and a display device 107.

[0022] The CPU 101 is a calculation device that controls the overall operation of the information processing device 50. The RAM 102 is a volatile storage device that is used as a work area for the CPU 101. The ROM 103 is a non-volatile storage device that stores programs for the information processing device 50.

[0023] The auxiliary storage device 104 is a storage device such as a hard disk drive (HDD) or a solid state drive (SSD) that stores various data, programs, and the like.

[0024] The network I / F 105 is an interface for communicating data with an external device such as the server 40 via a network. The network I / F 105 is, for example, a network interface card (NIC) that supports Ethernet (registered trademark) and is capable of wired or wireless communication in accordance with TCP (Transmission Control Protocol) / IP (Internet Protocol) or the like.

[0025] The input device 106 is a touch panel input function, a mouse, a keyboard, etc. for selecting letters, numbers, various instructions, and moving a cursor.

[0026] The display device 107 is a display configured with liquid crystal or organic EL (Electro-Luminescence) or the like, which displays various information such as a cursor, a menu, a window, characters, or an image.

[0027] The above-mentioned CPU 101, RAM 102, ROM 103, auxiliary storage device 104, network I / F 105, input device 106 and display device 107 are communicably connected to one another via a bus 108 such as an address bus and a data bus.

[0028] It should be noted that the hardware configuration of the information processing device 50 shown in FIG. 3 is merely an example, and it is not necessary for the information processing device 50 to include all of the components shown in FIG. 3, or it may include other components.

[0029] (Configuration and operation of functional blocks of information processing device) Fig. 4 is a diagram showing an example of the configuration of the functional blocks of the information processing device according to the first embodiment. Fig. 5 is a diagram showing an example of waveform data in which characteristic waveform information of an IED appears. The configuration and operation of the functional blocks of the information processing device 50 according to this embodiment will be described with reference to Figs. 4 and 5.

[0030] As shown in FIG. 4, the information processing device 50 includes an acquisition unit 501, an IED detection unit 502 (detection unit), an onset search unit 503 (search unit), a dipole estimation unit 504, and a display control unit 505.

[0031] The acquiring unit 501 is a functional unit that acquires waveform data of the magnetoencephalogram signal and the electroencephalogram signal from the server 40 via the network I / F 105. Note that, here, the description focuses on the waveform data of the magnetoencephalogram signal among the waveform data. The waveform data acquired by the acquiring unit 501 may be any of waveform data measured by the measurement device 3, waveform data accumulated in the data storage unit 402 of the server 40, and waveform data stored in the auxiliary storage device 104 of the information processing device 50.

[0032] The IED detection unit 502 is a functional unit that detects a time manually designated by an expert such as a doctor as the time when characteristic waveform information of an IED appears in the waveform data acquired by the acquisition unit 501. For example, the IED detection unit 502 detects a time designated by an expert, such as a doctor, via the input device 106 as the time when characteristic waveform information of an IED appears, the expert visually determining that the characteristic waveform information of an IED appears after checking the waveform data corresponding to each sensor displayed on the display device 107.

[0033] Here, an example of waveform data in which specific IED characteristic waveform information appears is shown in FIG. 5. A user such as an expert specifies, for example, the center of the IED characteristic waveform information (spike waveform), that is, the time that is thought to be the peak part of the spike waveform shown in FIG. 5. Here, the peak part refers to the top part of the IED characteristic waveform, and the beginning part shown in FIG. 5 refers to the part where the mountain-shaped waveform of the waveform begins. In addition, the background activity shown in FIG. 5 refers to the waveform part having the magnitude of normal brain activity or noise signal other than the characteristic waveform derived from epilepsy such as epileptic seizures or interictal epileptic discharges.

[0034] The onset search unit 503 is a functional unit that searches for an onset based on the time (time of the peak portion) detected by the IED detection unit 502. Here, an onset refers to a portion in the waveform data where an IED actually occurs (a signal is generated from an actual epileptic lesion). Specifically, the onset search unit 503 identifies the time of the onset (onset time) based on the time (time of the peak portion) detected by the IED detection unit 502. As shown in FIG. 4, the onset search unit 503 has an origin / peak determination unit 5031 (first determination unit), a range determination unit 5032 (second determination unit), and an onset time identification unit 5033 (identification unit).

[0035] The origin / peak determination unit 5031 is a functional unit that determines the origin and peak in the waveform data in which characteristic waveform information of an IED appears, based on the time (peak time) detected by the IED detection unit 502. The process of determining the origin and peak by the origin / peak determination unit 5031 will be described in detail later with reference to FIG.

[0036] The range determination unit 5032 is a functional unit that determines, as a search range, a section in which the signal intensity is greater than the background activity, within the range from the origin to the peak determined by the origin / peak determination unit 5031. The process of determining the search range by the range determination unit 5032 will be described in detail later with reference to FIG.

[0037] The onset time identifying unit 5033 is a functional unit that identifies the earliest time within the search range determined by the range determining unit 5032 as the onset time.

[0038] The dipole estimation unit 504 is a functional unit that performs dipole estimation using the waveform data at the onset time searched for by the onset search unit 503.

[0039] The display control unit 505 is a functional unit that performs the display operation of the display device 107. The display control unit 505 displays, for example, the waveform data acquired by the acquisition unit 501, the process contents and processing results of the onset search unit 503, the estimation results of the dipole estimation unit 504, and the like.

[0040] The above-mentioned acquisition unit 501, IED detection unit 502, onset search unit 503, dipole estimation unit 504, and display control unit 505 are realized by executing a program by CPU 101 shown in Fig. 3. Note that some or all of the functional units of the acquisition unit 501, IED detection unit 502, onset search unit 503, dipole estimation unit 504, and display control unit 505 may be realized by a hardware circuit (integrated circuit) such as an FPGA (Field-Programmable Gate Array) or an ASIC (Application Specific Integrated Circuit) instead of a software program.

[0041] Note that the functions of each functional unit of the information processing device 50 shown in Fig. 4 are conceptually shown, and the configuration is not limited to this. For example, the multiple functional units illustrated as independent functional units in the information processing device 50 shown in Fig. 4 may be configured as one functional unit. On the other hand, the function of one functional unit in the information processing device 50 shown in Fig. 4 may be divided into multiple functions and configured as multiple functional units.

[0042] (Flow of onset search process of information processing device) Fig. 6 is a flowchart showing an example of the flow of an onset search process of the information processing device according to the first embodiment. Fig. 7 is a flowchart showing an example of the flow of an origin / peak determination process of the information processing device according to the first embodiment. Fig. 8 is a flowchart showing an example of the flow of a search range determination process of the information processing device according to the first embodiment. The flow of an onset search process of the information processing device 50 according to this embodiment will be described with reference to Figs. 6 to 8.

[0043] <Step S11> The acquiring unit 501 acquires waveform data of the magnetoencephalographic signal from the server 40 via the network I / F 105. Then, the process proceeds to step S12.

[0044] <Step S12> The IED detection unit 502 detects a time manually designated by an expert such as a doctor as the time when characteristic waveform information of an IED appears in the waveform data acquired by the acquisition unit 501. For example, the IED detection unit 502 detects the time when the characteristic waveform information of an IED appears by visual inspection, determined by an expert who has confirmed the waveform data corresponding to each sensor displayed on the display device 107, via the input device 106, and detects the time designated by the designation operation as the time when the characteristic waveform information of an IED appears. Then, the process proceeds to step S13.

[0045] <Step S13> An origin / peak determination unit 5031 of the onset search unit 503 determines an origin and a peak in the waveform data in which characteristic waveform information of an IED appears, based on the time detected by the IED detection unit 502. Specifically, the origin / peak determination unit 5031 executes the processes of steps S131 to S137 shown in FIG.

[0046] <<Step S131>> The start point / peak determination unit 5031 first selects a predetermined range (for example, a range of ±40 [msec] centered on the time of the peak point) based on the time detected by the IED detection unit 502. Then, the process proceeds to step S132.

[0047] <<Step S132>> Next, the start / peak determining unit 5031 performs baseline correction (or high-pass filter processing, etc.) on the waveform data within the selected range and for all channels (i.e., all sensors), and then proceeds to step S133.

[0048] <<Step S133>> Next, the start / peak determining unit 5031 averages the baseline-corrected waveform data of all channels (i.e., all sensors). When averaging, the waveform data of all channels may be averaged as is, or the absolute values ​​of the waveform data may be averaged. Then, the process proceeds to step S134.

[0049] <<Step S134>> Next, the start point / peak determining unit 5031 searches for the maximum and minimum values ​​from the averaged waveform data, and then the process proceeds to step S135.

[0050] <<Step S135>> Next, the start point / peak determination unit 5031 searches for a combination of the local minimum value and the local maximum value in the order of the time from the searched local maximum value and the local minimum value. If a combination of the local minimum value and the local maximum value in the order of the time is not searched, the start point / peak determination unit 5031 may process a certain time after the time detected by the IED detection unit 502 (for example, 40 [msec] after the time of the peak point) as the peak point. Then, the process proceeds to step S136.

[0051] <<Step S136>> Next, the start point / peak determining unit 5031 determines the largest maximum value among the maximum values ​​contained in each of the searched combinations as the peak point, and then proceeds to step S137.

[0052] <<Step S137>> Then, the origin / peak determination unit 5031 determines the minimum value immediately before the determined peak, i.e., the minimum value combined with the determined maximum value, as the origin. Note that if the time detected by the IED detection unit 502 is the time of the peak, the origin may be determined by going back from that point. Then, step S13 (FIG. 6) is terminated, and the process proceeds to step S14.

[0053] <Step S14> The range determination unit 5032 of the onset searching unit 503 determines a search range for searching for an onset, based on the peak and origin determined by the origin / peak determination unit 5031. Specifically, the range determination unit 5032 executes the processes of steps S141 to S145 shown in FIG.

[0054] <<Step S141>> The range determination unit 5032 first selects a predetermined range going back a certain time from the time detected by the IED detection unit 502 (for example, a range of -2040 to -40 [msec] from the time of the peak). Note that the selection is made from the range of the time before the time detected by the IED detection unit 502, but this is not limiting, and a range going forward a certain time from the time detected by the IED detection unit 502 may be selected, or waveform data for the entire time may be used. Then, the process proceeds to step S142.

[0055] <<Step S142>> Next, the range determination unit 5032 performs baseline correction on the waveform data within the selected range and for all channels (i.e., all sensors), and then proceeds to step S143.

[0056] <<Step S143>> Next, the range determination unit 5032 averages the baseline-corrected waveform data of all channels (i.e., all sensors). When averaging, the waveform data of all channels may be averaged as is, or the absolute values ​​of the waveform data may be averaged. The range determination unit 5032 may also use the waveform data averaged by the start / peak determination unit 5031 in the above-mentioned step S133 (FIG. 7). Alternatively, the range determination unit 5032 may use the raw waveform data as is, instead of the averaged waveform data. Then, the process proceeds to step S144.

[0057] <<Step S144>> Next, the range determination unit 5032 determines the value at which the proportion of the signal value reaches a predetermined threshold value (for example, the value at which the signal value is the 95th percentile) in the cumulative frequency distribution of the signal value at each time of the averaged waveform data as the magnitude of the background activity. Note that the maximum value, median value, average value, or average value + 2SD (SD: standard deviation) within the above-mentioned predetermined range of the averaged waveform data may be determined as the magnitude of the background activity. Then, the process proceeds to step S145.

[0058] <<Step S145>> Then, the range determining unit 5032 determines, as the search range, a section having a value larger than the determined background activity within the range from the onset to the peak determined by the onset-peak determining unit 5031. Note that the background data to be compared with the background activity may be averaged waveform data or raw waveform data measured by a sensor. Then, step S14 (FIG. 6) is ended, and the process proceeds to step S15.

[0059] <Step S15> The onset time identifying section 5033 of the onset search section 503 identifies, as the onset time, the earliest time within the search range determined by the range determining section 5032. This ends the onset search process.

[0060] In this way, based on the onset time specified by the above-mentioned onset search process and the waveform data used at the onset time, dipole estimation is performed by the dipole estimation unit 504. Note that the dipole estimation process itself can be performed by adopting a conventional method.

[0061] As described above, in the information processing device 50 according to this embodiment, the acquisition unit 501 acquires waveform data of biological signals measured by a plurality of sensors, the IED detection unit 502 detects the time at which characteristic waveform information of an IED appears from the waveform data acquired by the acquisition unit 501, and the onset search unit 503 searches for an onset time at which a signal is generated from an epileptic lesion within a predetermined search range in the waveform data based on the time detected by the IED detection unit 502. This makes it possible to automatically identify the time at which a signal is generated from an epileptic lesion, thereby realizing an improvement in the efficiency of epilepsy diagnosis and the stability of diagnostic accuracy.

[0062] Moreover, the onset search unit 503 has an origin / peak determination unit 5031 which determines an origin and a peak of waveform data in which characteristic waveform information appears based on the time detected by the IED detection unit 502, a range determination unit 5032 which determines, as a previous search range, a section in which the signal intensity of the background activity of the waveform data is greater than that of the origin and peak determined by the origin / peak determination unit 5031, and an onset time identification unit 5033 which identifies the onset time from the search range determined by the range determination unit 5032. Since the search range is determined based on the magnitude of the background activity in this way, the accuracy of identifying the onset time can be improved.

[0063] [Second embodiment] The biosignal measurement system 1 according to the second embodiment will be described, focusing on the differences from the biosignal measurement system 1 according to the first embodiment. In the above-mentioned first embodiment, the operation of identifying the earliest time in the determined search range as the onset time was described. In this embodiment, the operation of identifying the onset time based on various dipole-estimated index values ​​will be described. Note that the overall configuration of the biosignal measurement system 1 according to this embodiment and the hardware configuration of the information processing device are similar to the configurations described in the first embodiment.

[0064] (Configuration and operation of functional blocks of information processing device) Fig. 9 is a diagram showing an example of the configuration of functional blocks of an information processing device according to the second embodiment. The configuration and operation of the functional blocks of an information processing device 50a according to the present embodiment will be described with reference to Fig. 9.

[0065] 9, the information processing device 50a includes an acquisition unit 501, an IED detection unit 502 (detection unit), an onset search unit 503a (search unit), a dipole estimation unit 504, and a display control unit 505. Among these, the operations of the acquisition unit 501, the IED detection unit 502, the dipole estimation unit 504, and the display control unit 505 are similar to those of the information processing device 50 according to the above-described first embodiment.

[0066] The onset search unit 503a is a functional unit that searches for an onset based on the time (time of the peak portion) detected by the IED detection unit 502. As shown in Fig. 9, the onset search unit 503a has an origin / peak determination unit 5031 (first determination unit), a range determination unit 5032 (second determination unit), an index value calculation unit 5034 (calculation unit), a judgment unit 5035, and an onset time identification unit 5033 (identification unit). Note that the operations of the origin / peak determination unit 5031 and the range determination unit 5032 are similar to those of the information processing device 50 according to the above-mentioned first embodiment.

[0067] The index value calculation unit 5034 is a functional unit that calculates index values ​​(GOF: Goodness Of Fit) (see Non-Patent Document 1, for example), signal strength, confidence volume, etc.) related to the estimation result by dipole estimation using waveform data at each time within the search range determined by the range determination unit 5032. The calculation process of the index value by the index value calculation unit 5034 will be described in detail later with reference to FIG.

[0068] The determination unit 5035 is a functional unit that determines whether or not the GOF as an index value calculated by the index value calculation unit 5034 is equal to or greater than a predetermined threshold, whether or not the signal strength is within a predetermined threshold range, and whether or not the confidence volume is equal to or less than a predetermined threshold within the search range determined by the range determination unit 5032. Here, for example, the threshold for the GOF is 80[%], and the threshold range for the confidence strength is 0.5e -7 ~5e -7 [A] range, and the confidence volume threshold is 2e -5 [m 2 The above thresholds are merely examples, and other thresholds may be used.

[0069] The onset time identifying unit 5033 identifies, within the search range determined by the range determining unit 5032, the earliest time among times that satisfy the condition determined by the determining unit 5035 as the onset time.

[0070] The above-mentioned acquiring unit 501, IED detecting unit 502, onset searching unit 503a, dipole estimating unit 504, and display controlling unit 505 are realized by executing a program by CPU 101 shown in Fig. 3. Note that some or all of the functional units of the acquiring unit 501, IED detecting unit 502, onset searching unit 503a, dipole estimating unit 504, and display controlling unit 505 may be realized by a hardware circuit (integrated circuit) such as an FPGA or ASIC, instead of a software program.

[0071] Note that the functions of each functional unit of the information processing device 50a shown in Fig. 9 are conceptually shown, and the present invention is not limited to such a configuration. For example, the multiple functional units illustrated as independent functional units in the information processing device 50a shown in Fig. 9 may be configured as one functional unit. On the other hand, the function of one functional unit in the information processing device 50a shown in Fig. 9 may be divided into multiple functions and configured as multiple functional units.

[0072] (Flow of onset search process of information processing device) Fig. 10 is a flowchart showing an example of the flow of the onset time identification process of the information processing device according to the second embodiment. With reference to Fig. 10, the flow of the onset time identification process of the onset search process by the information processing device 50a according to the present embodiment will be described. That is, the details of the process for the above-mentioned step S15 (Fig. 6) will be described.

[0073] (Onset time identification process flow) <Step S151> The index value calculation unit 5034 of the onset search unit 503a calculates GOF, signal strength, and confidence volume as index values ​​related to the estimation result by dipole estimation using waveform data at each time within the search range determined by the range determination unit 5032. Note that dipole estimation is not limited to being performed at all times within the search range, and dipole estimation may be performed only in the first half of the search range or at every other time within the search range. Then, the process proceeds to step S152.

[0074] <Step S152> The determination unit 5035 of the onset search unit 503a determines whether or not the GOF as an index value calculated by the index value calculation unit 5034 is equal to or greater than a predetermined threshold, whether or not the signal strength is within a predetermined threshold range, and whether or not the confidence volume is equal to or less than a predetermined threshold within the search range determined by the range determination unit 5032. If there is a dipole whose GOF is equal to or greater than the predetermined threshold, whose signal strength is within a predetermined threshold range, and whose confidence volume is equal to or less than a predetermined value (step S152: Yes), the process proceeds to step S153, and if there is no such dipole (step S152: No), the process proceeds to step S154.

[0075] It is not necessary to satisfy all three of the above conditions, and for example, when two of the three conditions are satisfied, or when at least one of the conditions is satisfied, the process may proceed to step S153. Also, the index values ​​calculated by the index value calculation unit 5034 are not limited to the above three, and other index values ​​may be calculated.

[0076] <Step S153> An onset time identifying section 5033 of the onset search section 503a identifies, as the onset time, the earliest time among times that satisfy the condition determined by the determining section 5035 within the search range determined by the range determining section 5032. Then, the onset time identifying process ends.

[0077] <Step S154> If there is no time satisfying the conditions determined by the determination unit 5035, the onset time identifying unit 5033 terminates the onset time identifying process as it is unable to identify the corresponding onset time. If there is no time satisfying the conditions determined by the determination unit 5035, it is also possible to employ a method of determining the time detected by the IED detection unit 502 as the onset time, or a method of determining the midpoint between the start point and the peak point as the onset time.

[0078] As described above, in the information processing device 50a according to this embodiment, in the onset search unit 503a, the index value calculation unit 5034 calculates one or more index values ​​related to dipole estimation using the waveform data at each time within the search range determined by the range determination unit 5032, the determination unit 5035 determines whether or not the index value calculated by the index value calculation unit 5034 satisfies a predetermined condition, and the onset time identification unit 5033 identifies the earliest time among the times that satisfy the condition determined by the determination unit 5035 in the search range as the onset time. In this way, it is determined whether or not the index value related to dipole estimation for the waveform data in the search range satisfies a predetermined condition, and the earliest time that satisfies the condition is identified as the onset time, so that the accuracy of identifying the onset time can be further improved.

[0079] [Third embodiment] The biosignal measurement system 1 according to the third embodiment will be described, focusing on the differences from the biosignal measurement system 1 according to the first embodiment. In the above-mentioned first embodiment, the operation of manually specifying the time when characteristic waveform information of an IED appears was described. In this embodiment, the operation of automatically detecting the time when characteristic waveform information of an IED appears using a machine learning trained model will be described. Note that the overall configuration of the biosignal measurement system 1 according to this embodiment, as well as the hardware configuration and functional block configuration of the information processing device, are similar to the configurations described in the first embodiment.

[0080] (Flow of onset search process of information processing device) 11 is a flowchart showing an example of the flow of the onset search process of the information processing device according to the third embodiment. The flow of the onset search process of the information processing device 50 according to the present embodiment will be described with reference to FIG.

[0081] <Step S11a> The acquiring unit 501 acquires waveform data of the magnetoencephalographic signal from the server 40 via the network I / F 105. Then, the process proceeds to step S12a.

[0082] <Step S12a> The IED detection unit 502 detects a time when characteristic waveform information of an IED appears, using a model trained by machine learning for the waveform data acquired by the acquisition unit 501. For the trained model, for example, a model trained by machine learning as described in Patent Document 1 can be adopted. Then, the process proceeds to step S13a.

[0083] <Steps S13a to S15a> The processes in steps S13a to S15a are the same as those in steps S13 to S15 (FIG. 6) described above, respectively, and then the onset search process is completed.

[0084] As described above, it is possible for the IED detection unit 502 to automatically detect time, thereby enabling the detection of the time at which characteristic waveform information of an IED appears in the waveform data and the automation of identifying the onset time.

[0085] In each of the above-mentioned embodiments, when at least one of the functional units of the information processing device 50, 50a is realized by executing a program, the program is provided by being incorporated in advance in a ROM or the like. In each of the above-mentioned embodiments, the program executed by the information processing device 50, 50a may be provided by being recorded in a computer-readable recording medium such as a CD-ROM (Compact Disc Read Only Memory), a flexible disk (FD), a CD-R (Compact Disk-Recordable), or a DVD (Digital Versatile Disc) in the form of an installable or executable file. In each of the above-mentioned embodiments, the program executed by the information processing device 50, 50a may be provided by being stored on a computer connected to a network such as the Internet and downloaded via the network. In each of the above-mentioned embodiments, the program executed by the information processing device 50, 50a may be provided or distributed via a network such as the Internet. Furthermore, in each of the above-mentioned embodiments, the program executed by the information processing device 50, 50a has a modular configuration including at least any one of the above-mentioned functional units, and in terms of actual hardware, the CPU 101 reads out and executes the program from the above-mentioned storage device (e.g., ROM 103 or auxiliary storage device 104, etc.), so that each of the above-mentioned functional units is loaded and generated on the main storage device (RAM 102).

[0086] The aspects of the present invention are as follows. <1> An acquisition unit that acquires waveform data of biological signals measured by a plurality of sensors; A detection unit that detects a time when characteristic waveform information of an IED (Interictal Epileptiform Discharge) appears in the waveform data acquired by the acquisition unit; a search unit that searches for an onset time at which a signal is generated from a lesion in the brain within a predetermined search range in the waveform data based on the time detected by the detection unit; The present invention is a biosignal analysis device equipped with the above. <2> The search unit is a first determination unit that determines a start point and a peak point of the waveform data in which the characteristic waveform information appears based on the time detected by the detection unit; a second determination unit that determines, as the search range, a section in the range from the onset to the peak determined by the first determination unit, in which the signal intensity of the background activity of the waveform data is greater than the signal intensity of the onset; a determination unit that determines the onset time from the search range determined by the second determination unit; The above-mentioned <1> The present invention relates to a biological signal analysis device. <3> The specifying unit specifies the earliest time in the search range as the onset time. <2> The present invention relates to a biological signal analysis device. <4> The search unit is a calculation unit that calculates one or more index values ​​related to dipole estimation using the waveform data at each time within the search range determined by the second determination unit; and a determination unit that determines whether or not the index value calculated by the calculation unit satisfies a predetermined condition; and The identification unit identifies, as the onset time, the earliest time among the times that satisfy the condition by the determination unit in the search range. <2> The present invention relates to a biological signal analysis device. <5> The calculation unit calculates at least one of GOF (Good Of Fitness), confidence intensity, or confidence volume as the index value by dipole estimation using the waveform data at each time within the search range determined by the second determination unit. <4> The present invention relates to a biological signal analysis device. <6> The first determination unit determines the start portion and the peak portion in data obtained by averaging the waveform data acquired by the acquisition unit. <2> ~ <5> 1 is a biological signal analysis device according to any one of claims 1 to 9. <7> The second determination unit calculates the background activity from data obtained by averaging the waveform data acquired by the acquisition unit, and determines the search range using the background activity. <2> ~ <5> 1 is a biological signal analysis device according to any one of claims 1 to 9. <8> the detection unit detects a time designated via an input device as a time at which the characteristic waveform information appears in the waveform data acquired by the acquisition unit. <1> ~ <7> 1 is a biological signal analysis device according to any one of claims 1 to 9. <9> The detection unit detects a time when the characteristic waveform information appears from the waveform data acquired by the acquisition unit by using a model learned by machine learning. <1> ~ <7> 1 is a biological signal analysis device according to any one of claims 1 to 9. <10> An acquisition step of acquiring waveform data of biological signals measured by a plurality of sensors; a detection step of detecting a time when characteristic waveform information of an IED (Interictal Epileptiform Discharge) appears in the acquired waveform data; a searching step of searching for an onset time at which a signal is generated from a lesion in the brain within a predetermined search range in the waveform data based on the detected time; The method for identifying waveform occurrence includes the steps of: <11> On the computer, An acquisition step of acquiring waveform data of biological signals measured by a plurality of sensors; a detection step of detecting a time when characteristic waveform information of an IED (Interictal Epileptiform Discharge) appears in the acquired waveform data; a searching step of searching for an onset time at which a signal is generated from a lesion in the brain within a predetermined search range in the waveform data based on the detected time; This is a program for executing the above. [Explanation of symbols]

[0087] 1. Biosignal measurement system 3. Measuring Equipment 4 Measurement Table 31 Duwa 32 Depression 40 Servers 50, 50a Information processing device 101 CPU 102 RAM 103 ROM 104 Auxiliary storage 105 Network I / F 106 Input Devices 107 Display device 108 Bus 401 Data Acquisition Department 402 Data storage unit 501 Acquisition Department 502 IED Detector 503, 503a Onset search section 504 Dipole Estimation Unit 505 Display control unit 5031 Starting part / peak determination part 5032 Range determination unit 5033 Onset Time Identification Unit 5034 Index value calculation unit 5035 Judgment section [Prior art documents] [Patent documents]

[0088] [Patent Document 1] Japanese Patent Application Laid-Open No. 2021-069929

Non-Patent Document

[0089]

Non-Patent Document 1

Claims

1. An acquisition unit that acquires waveform data of biological signals measured by a plurality of sensors; a detection unit that detects a time when characteristic waveform information of an IED (Internal Epileptiform Discharge) appears in the waveform data acquired by the acquisition unit; a search unit that searches for an onset time at which a signal is generated from a lesion in the brain within a predetermined search range in the waveform data based on the time detected by the detection unit; A biosignal analysis device equipped with the above.

2. The search unit is a first determination unit that determines a start point and a peak point of the waveform data in which the characteristic waveform information appears based on the time detected by the detection unit; a second determination unit that determines, as the search range, a section in the range from the onset to the peak determined by the first determination unit, in which the signal intensity of the waveform data is greater than the signal intensity of the background activity; a determination unit that determines the onset time from the search range determined by the second determination unit; The biological signal analysis device according to claim 1 ,

3. The biological signal analysis device according to claim 2 , wherein the specifying unit specifies the earliest time within the search range as the onset time.

4. The search unit is a calculation unit that calculates one or more index values ​​related to dipole estimation using the waveform data at each time within the search range determined by the second determination unit; and a determination unit that determines whether or not the index value calculated by the calculation unit satisfies a predetermined condition; and The biological signal analysis device according to claim 2 , wherein the specifying unit specifies, as the onset time, the earliest time among times that satisfy the condition determined by the determining unit within the search range.

5. 5. The biological signal analysis device according to claim 4, wherein the calculation unit calculates at least one of GOF (Good Of Fitness), confidence intensity, or confidence volume as the index value by dipole estimation using the waveform data at each time within the search range determined by the second determination unit.

6. The biological signal analysis device according to any one of claims 2 to 5, wherein the first determination unit determines the beginning and the peak in data obtained by averaging the waveform data acquired by the acquisition unit.

7. The biological signal analysis device according to any one of claims 2 to 5, wherein the second determination unit calculates the background activity from averaged data of the waveform data acquired by the acquisition unit, and determines the search range using the background activity.

8. A biosignal analysis device as described in any one of claims 1 to 5, wherein the detection unit detects a time specified via an input device as the time at which the characteristic waveform information appears in the waveform data acquired by the acquisition unit.

9. A biological signal analysis device as described in any one of claims 1 to 5, wherein the detection unit detects the time at which the characteristic waveform information appears from the waveform data acquired by the acquisition unit using a model learned by machine learning.

10. An acquisition step of acquiring waveform data of biological signals measured by a plurality of sensors; a detection step of detecting a time when characteristic waveform information of an IED (Intellectual Epileptiform Discharge) appears in the acquired waveform data; a searching step of searching for an onset time at which a signal is generated from a lesion in the brain within a predetermined search range in the waveform data based on the detected time; The method for determining waveform occurrence comprising:

11. On the computer, An acquisition step of acquiring waveform data of biological signals measured by a plurality of sensors; a detection step of detecting a time when characteristic waveform information of an IED (Intellectual Epileptiform Discharge) appears in the acquired waveform data; a searching step of searching for an onset time at which a signal is generated from a lesion in the brain within a predetermined search range in the waveform data based on the detected time; A program for executing.

Citation Information

Patent Citations

  • Waveform generation specification method and program

    JP2021069929A