WO2024050920A1 - 神经通路的激活检测方法、装置、设备及存储介质 - Google Patents

神经通路的激活检测方法、装置、设备及存储介质 Download PDF

Info

Publication number
WO2024050920A1
WO2024050920A1 PCT/CN2022/125245 CN2022125245W WO2024050920A1 WO 2024050920 A1 WO2024050920 A1 WO 2024050920A1 CN 2022125245 W CN2022125245 W CN 2022125245W WO 2024050920 A1 WO2024050920 A1 WO 2024050920A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
field potential
stimulation
potential data
post
Prior art date
Application number
PCT/CN2022/125245
Other languages
English (en)
French (fr)
Inventor
郭丰
韩传亮
张佳佳
蔚鹏飞
Original Assignee
中国科学院深圳先进技术研究院
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 中国科学院深圳先进技术研究院 filed Critical 中国科学院深圳先进技术研究院
Publication of WO2024050920A1 publication Critical patent/WO2024050920A1/zh

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
    • A61B5/40—Detecting, measuring or recording for evaluating the nervous system
    • A61B5/4058—Detecting, measuring or recording for evaluating the nervous system for evaluating the central nervous system
    • A61B5/4064—Evaluating the brain
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
    • A61B5/165—Evaluating the state of mind, e.g. depression, anxiety
    • 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]
    • A61B5/377—Electroencephalography [EEG] using evoked responses
    • A61B5/378—Visual stimuli
    • 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]
    • A61B5/377—Electroencephalography [EEG] using evoked responses
    • A61B5/38—Acoustic or auditory stimuli
    • 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]
    • A61B5/377—Electroencephalography [EEG] using evoked responses
    • A61B5/383—Somatosensory stimuli, e.g. electric stimulation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/7715—Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
    • G06V10/809—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level of classification results, e.g. where the classifiers operate on the same input data
    • G06V10/811—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level of classification results, e.g. where the classifiers operate on the same input data the classifiers operating on different input data, e.g. multi-modal recognition
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/20—Movements or behaviour, e.g. gesture recognition
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B2503/00—Evaluating a particular growth phase or type of persons or animals
    • A61B2503/40—Animals
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B2503/00—Evaluating a particular growth phase or type of persons or animals
    • A61B2503/42—Evaluating a particular growth phase or type of persons or animals for laboratory research

Definitions

  • This application relates to the technical field of brain science, for example, to a neural pathway activation detection method, device, equipment and storage medium.
  • the nervous system of the brain is an extremely complex, efficient and precise system, and its brain mechanism of perception and cognition has always been a hot issue in brain science research. There is a close connection between the behavior of animals and the activation of related neural pathways.
  • experimental subjects are usually given certain stimuli to make the experimental subjects produce behaviors corresponding to the stimuli, and changes in their behavior serve as relevant neural pathways. The basis for judging whether it is activated.
  • Embodiments of the present application provide a neural pathway activation detection method, device, equipment and storage medium to solve the problem of high misjudgment rate in neural pathway activation detection methods that rely solely on behavioral data, and improve the understanding of brain function. The credibility of the research results.
  • a method for detecting activation of neural pathways includes: obtaining pre-stimulation field potential data and post-stimulation field potential data corresponding to the neural pathway to be detected of the experimental subject; based on the pre-stimulation field potential The data and the post-stimulation field potential data are used to determine the connection strength change data of the neural pathway to be detected; based on the video data to be detected of the experimental subject, the behavioral change data of the experimental subject is determined; based on the connection strength change data and the behavioral change data to determine the activation state of the neural pathway to be detected.
  • a neural pathway activation detection device includes: a field potential data acquisition module configured to acquire pre-stimulation field potential data and post-stimulation field potential corresponding to the to-be-detected neural pathway of the experimental subject. data; the connection strength change data determination module is configured to determine the connection strength change data of the neural pathway to be detected based on the pre-stimulation field potential data and the post-stimulation field potential data; the behavior change data determination module is configured to determine based on the pre-stimulation field potential data and the post-stimulation field potential data.
  • the video data of the experimental subject to be detected determines the behavioral change data of the experimental subject; the activation state determination module is configured to determine the activation of the neural pathway to be detected based on the connection strength change data and the behavioral change data. state.
  • an electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores information that can be processed by the at least one processor.
  • a computer program executed by a processor. The computer program is executed by the at least one processor, so that the at least one processor can execute the neural pathway activation detection method described in any embodiment of the present application.
  • a computer-readable storage medium stores computer instructions, and the computer instructions are used to implement any of the embodiments of the present application when executed by a processor. Activation detection method of neural pathways.
  • Figure 1 is a flow chart of a neural pathway activation detection method provided in Embodiment 1 of the present application;
  • Figure 2 is a flow chart of a neural pathway activation detection method provided in Embodiment 2 of the present application.
  • FIG. 3 is a schematic diagram of the posture feature points of an experimental object provided in Embodiment 2 of the present application.
  • Figure 4 is a flow chart of an example of a neural pathway activation detection method provided in Embodiment 2 of the present application.
  • Figure 5 is a schematic structural diagram of a neural pathway activation detection device provided in Embodiment 3 of the present application.
  • FIG. 6 is a schematic structural diagram of an electronic device provided in Embodiment 4 of the present application.
  • Figure 1 is a flow chart of a neural pathway activation detection method provided in Embodiment 1 of the present application. This embodiment can be applied to detecting the activation status of neural pathways in the nervous system.
  • the method can be performed by an activation detection device for neural pathways.
  • the activation detection device for neural pathways can be implemented in the form of hardware and/or software.
  • the neural pathway activation detection device can be configured in the terminal device. As shown in Figure 1, the method includes the following steps.
  • the neural pathways to be detected can be the midbrain ventral tegmental area-nucleus accumbens-prefrontal cortex, superior colliculus-thalamus-pulvinar-lateral amygdala, hippocampus-mammary body-anterior thalamic nucleus-cingulate gyrus, etc.
  • the neural pathways to be detected There are no restrictions on the neural pathways to be detected, and users can customize settings according to actual needs.
  • the pre-stimulation field potential data is the field potential data of the neural pathway to be detected in the pre-stimulation period
  • the post-stimulation field potential data is the field potential data of the neural pathway to be detected in the post-stimulation period.
  • Field potential data can be collected through implanted electrodes or non-implanted electrodes. Field potential data are used to characterize the potential changes produced by target nuclei in the neural pathways to be detected.
  • the pre-stimulation time period may be determined based on the stimulation time point and the first duration
  • the post-stimulation time period may be determined based on the stimulation time point and the second duration.
  • the first duration and the second duration may be the same or different.
  • the first duration is 3 minutes and the second duration is 5 minutes.
  • the values of the first duration and the second duration are not limited here.
  • a marker when a stimulation signal is detected, a marker is used to generate a marking signal to record the stimulation time point. This setting avoids time errors caused by artificial observation and recording of stimulation time points, thereby improving the accuracy of recorded stimulation time points.
  • the stimulation given to the experimental subject can be physical stimulation or drug stimulation.
  • the physical stimulation can be electric shock, sound or light signal, etc.
  • the neural pathway to be detected contains at least one pair of nerve nuclei.
  • the neural pathway to be detected is the superior colliculus - pulvinar thalamus - lateral amygdala
  • the neural pathway to be detected corresponds to at least one of the superior colliculus - pulvinar thalamus - lateral amygdala
  • the connection strength change data corresponding to the neural pathway to be detected includes connection strength change data corresponding to at least one pair of nerve nuclei.
  • the pre-stimulation field potential data when the neural pathway to be detected contains a pair of nerve nuclei, includes the first nucleus and the second nucleus respectively corresponding to the pair of nerve nuclei in the neural pathway to be detected.
  • the first pre-stimulation field potential data and the second pre-stimulation field potential data, and the post-stimulation field potential data include the first post-stimulation field potential data and the second post-stimulation field potential data corresponding to the first and second nuclei in the nerve nucleus pair.
  • the post-stimulation field potential data is used to determine the connection strength change data of the neural pathway to be detected based on the pre-stimulation field potential data and the post-stimulation field potential data, including: based on the first pre-stimulation field potential data and the second pre-stimulation field potential data, determine The pre-stimulation connection strength corresponding to the nerve nuclei pair; based on the first post-stimulation field potential data and the second post-stimulation field potential data, determine the post-stimulation connection strength corresponding to the nerve nuclei pair; based on the pre-stimulation connection strength and post-stimulation connection strength , determine the connection strength change data of the nerve nucleus pairs in the neural pathway to be detected.
  • the neural pathway to be detected includes a pair of nerve nuclei. It is easy to understand that the connection strength change data of other pairs of nerve nuclei corresponding to the neural pathway to be detected can also be determined by the above method.
  • the parameter type of the pre-stimulus connection strength or the post-stimulation connection strength is a Granger causality value.
  • the Granger causality test is a statistical method for hypothesis testing that can be used to test whether the field potential data before the first stimulus is the cause of the field potential data before the second stimulus or whether the field potential data before the second stimulus is the cause of the field potential data before the first stimulus. field potential data.
  • the results of Granger causality analysis include three elements: connection direction, connection strength and connection significance between two nuclei.
  • the Multivariate Granger Causality (MVGC) toolbox in the Matlab software can be used to determine at least one neural nucleus based on the pre-stimulus field potential data corresponding to multiple nuclei.
  • the pre-stimulation Granger Causality (GC) values corresponding to the cluster pairs are determined.
  • the post-stimulation Granger Causality (GC) values corresponding to at least one pair of neural nuclei are determined. J causality value.
  • connection strength change data of a pair of nerve nuclei includes the connection strength before stimulation and the connection strength after stimulation, or the connection strength change data of the pair of nerve nuclei includes the intensity difference corresponding to the connection strength before stimulation and the connection strength after stimulation, or Trend.
  • the pre-stimulation connection strength is less than the post-stimulation connection strength
  • the strength difference is greater than 0, and the change trend is an increasing trend.
  • the pre-stimulation connection strength is greater than the post-stimulation connection strength
  • the strength difference is less than 0, and the change trend is a weakening trend.
  • the video data to be detected includes pre-stimulation video data and post-stimulation video data.
  • the pre-stimulation video data is the video data of the experimental subject in the pre-stimulation time period
  • the post-stimulation video data is the video data of the experimental subject in the post-stimulation time period.
  • the length of the pre-stimulation period can be the same as the length of the post-stimulation period, or they can be different.
  • the recording of the video data to be detected and the recording of the field potential data are synchronously recorded based on the same time stamp.
  • the pre-stimulus video data is input into a pre-trained target classification model to obtain the output pre-stimulus behavior type
  • the post-stimulation video data is input into the target classification model to obtain the output post-stimulus behavior type.
  • the stimulation Pre-behavior type and post-stimulus behavior type to determine the behavioral change data of the experimental subject.
  • behavior types include, but are not limited to, immobility, resting shaking, eating, circling, grooming, running, elimination, and social behaviors. There is no limit to the types of behaviors that can be classified here.
  • connection strength change data Based on the connection strength change data and behavior change data, determine the activation state of the neural pathway to be detected.
  • determining the activation state of the neural pathway to be detected based on the connection strength change data and the behavior change data includes: when the connection strength change data meets the preset connection conditions, determining the preset behavior change data set Whether there is behavior change data; if there is behavior change data in the preset behavior change data set, the activation state of the neural pathway to be detected is set to the activated state; if there is no behavior change data in the preset behavior change data set, the activation state of the neural pathway to be detected is set to the activated state; The activation state of the neural pathway is set to the inactive state.
  • the preset connection condition when the connection strength change data includes pre-stimulation connection strength and post-stimulation connection strength, the preset connection condition is that the pre-stimulation connection strength is less than the post-stimulation connection strength. In another optional embodiment, when the connection strength change data includes the strength difference or change trend corresponding to the pre-stimulation connection strength and the post-stimulation connection strength, the preset connection condition is that the strength difference satisfies the preset difference range or change. The trend is an increasing trend. For example, the preset difference range may be greater than the preset intensity threshold. For example, the preset intensity threshold may be 0 or 1.
  • connection strength change data of the neural pathway to be detected includes the connection strength change data of a nerve nucleus pair
  • connection strength change data satisfying the preset connection condition means that the connection strength change data of the nerve nucleus pair satisfies the preset connection condition.
  • connection strength change data of the neural pathway to be detected includes connection strength change data corresponding to at least two pairs of nerve nuclei
  • the connection strength change data satisfying the preset connection conditions represents the connection corresponding to at least two pairs of nerve nuclei.
  • the intensity change data all meet the preset connection conditions.
  • the preset behavior change data set contains at least one preset behavior change data corresponding to the stimulus given to the experimental subject.
  • the preset behavior change data set includes stillness-still trembling, stillness-running, eating-running, eating-excretion, etc.; when the stimulus is a depression stimulus, the preset behavior change data set The concentration includes eating-stillness, social behavior-stillness, etc.
  • the preset behavior change data set includes a pre-stimulus behavior data set and a post-stimulus behavior data set corresponding to the stimulation given to the experimental subject.
  • the pre-stimulus behavior data set includes resting, eating, grooming, and social behaviors
  • the post-stimulus behavior includes resting, shaking, turning in circles, excreting, and running.
  • Behavior change data is considered to exist in the preset behavior change data set if the pre-stimulus behavior data set contains the pre-stimulus behavior type in the behavior change data and the post-stimulus behavior data set contains the post-stimulus behavior type in the behavior change data.
  • the method further includes: if the connection strength change data does not meet the preset connection conditions, setting the activation state of the neural pathway to be detected to an inactive state.
  • the connection strength change data of the neural pathway to be detected includes connection strength change data corresponding to at least two pairs of nerve nuclei
  • the connection strength change data does not meet the preset connection conditions, which is characterized by the presence of a connection of at least one pair of nerve nuclei.
  • the intensity change data does not meet the preset connection conditions.
  • the technical solution of this embodiment determines the connection strength change data of the neural pathway to be detected based on the obtained pre-stimulation field potential data and post-stimulation field potential data corresponding to the experimental subject's neural pathway to be detected.
  • Video data and post-stimulation video data are used to determine the behavioral change data of the experimental subject.
  • the activation status of the neural pathway to be detected is determined, and the activation status of the neural pathway to be detected is determined comprehensively from the two dimensions of brain functional connection strength and behavioral information.
  • the activation status of neural pathways solves the problem of high misjudgment rates in neural pathway activation detection methods that rely solely on behavioral data, and improves the credibility of research results on brain function.
  • FIG 2 is a flow chart of a neural pathway activation detection method provided in Embodiment 2 of the present application.
  • the video data to be detected in this embodiment includes video data collected by at least three video collection devices. This embodiment is based on the "video data to be detected based on the experimental object to determine the behavioral change data of the experimental object" in the above embodiment. Be explained. As shown in Figure 2, the method includes the following steps.
  • obtaining the pre-stimulation field potential data and post-stimulation field potential data corresponding to the neural pathway to be detected of the experimental subject includes: obtaining at least 10% of the target nuclei in the neural pathway to be detected within a preset time period. Two channels of field potential data; perform dimensionality reduction operations on at least two channels of field potential data to obtain at least two dimensionality reduction field potential data, and compare the dimensionality reduction field potential with the largest principal component among the at least two dimensionality reduction field potential data.
  • the channel field potential data corresponding to the data is used as the target field potential data corresponding to the target nucleus; among them, when the target nucleus is the first nucleus and the preset time period is the pre-stimulation period, the target field potential data is before the first stimulation.
  • Field potential data when the target nucleus is the first nucleus and the preset time period is the post-stimulation time period, the target field potential data is the field potential data after the first stimulation, when the target nucleus is the second nucleus and the preset time period is When the time period is the pre-stimulation period, the target field potential data is the second pre-stimulation field potential data.
  • the target field potential data is the second Poststimulus field potential data.
  • Multi-channel electrodes are used to collect at least two channel field potential data corresponding to at least two nuclei in the neural pathway to be detected.
  • multi-channel electrodes can be implanted into corresponding nuclei based on brain maps.
  • the dimensionality reduction algorithm used in the dimensionality reduction operation is the Principal Components Analysis (PCA) algorithm.
  • This setting can make the obtained pre-stimulation field potential data and post-stimulation field potential data corresponding to the neural pathway to be detected contain more characteristic information, thereby improving the accuracy of the subsequently obtained connection strength change data.
  • the method before determining the connection strength change data of the neural pathway to be detected based on the pre-stimulation field potential data and the post-stimulation field potential data, the method further includes: comparing the pre-stimulation field potential data and the post-stimulation field potential data. Perform preprocessing operations respectively to obtain preprocessed pre-stimulation field potential data and post-stimulation field potential data; wherein the preprocessing operations include filtering operations and/or downsampling operations.
  • the zero-phase digital filter (filtfilt) function in matlab software can be used to input the pre-stimulation field potential data or the post-stimulation field potential data in the forward and reverse directions respectively, so as to realize the pre-stimulation field potential data or post-stimulation field data.
  • Zero-phase digital filtering of potentiometric data can be used to input the pre-stimulation field potential data or the post-stimulation field potential data in the forward and reverse directions respectively.
  • the resample function in matlab software can be used to reduce the sampling rate of the pre-stimulation field potential data or the post-stimulation field potential data to 1000 Hz.
  • This setting can remove the noise in the field potential data and reduce the lag value during the Granger causality test.
  • At least three video collection devices are used to collect video data of the experimental subjects during the experiment.
  • the number of video collection devices is 4. There is no limit on the number of video capture devices here.
  • the two-dimensional skeleton data is used to represent the position coordinates of at least one posture feature point of the experimental object in the key image frame.
  • the target acquisition video is input into a pre-trained feature point recognition model to obtain at least one output key image frame and the position coordinates corresponding to at least one posture feature point in each key image frame.
  • the model type of the feature point recognition model is the DeepLabCut deep learning model, and at least one posture feature point includes limbs, nose, ears, head, torso, tail, etc. There are no restrictions on the model type of the feature point recognition model and the settings of the posture feature points.
  • FIG. 3 is a schematic diagram of posture feature points of an experimental subject provided in Embodiment 2 of the present application.
  • the number of posture feature points shown in Figure 3 is 16, which are nose, left ear, right ear, neck, limbs, 5 trunk feature points, tail base, tail middle and tail tip. At least one posture feature point can be displayed differently using dots of different colors.
  • the method further includes: based on each video collection device, obtaining a preset number of standard checkerboard images collected by each video collection device, and using the stereo camera calibration graphical user interface in the matlab software (StereoCameraCalibrator Graphical User Interface, StereoCameraCalibrator GUI) toolbox performs calibration operations based on a preset number of standard checkerboard images to obtain camera parameter data corresponding to each video capture device.
  • the standard checkerboard size is 12*9
  • the preset number is 60
  • the camera parameter data includes internal parameter data and external parameter data.
  • a triangulation algorithm is used, based on camera parameter data corresponding to at least three video acquisition devices and the experimental object in the key image frame in the video data collected by at least three video acquisition devices respectively.
  • Two-dimensional skeleton data determines the three-dimensional posture data of the experimental object.
  • determining the behavioral change data of the experimental subject based on the three-dimensional posture data includes: obtaining the pre-stimulation posture data corresponding to the pre-stimulation time period in the three-dimensional posture data and the post-stimulation posture corresponding to the post-stimulation time period. data, and input the pre-stimulus posture data into the pre-trained target classification model to obtain the output pre-stimulus behavior type. Input the post-stimulation posture data into the target classification model to obtain the output post-stimulus behavior type. Based on the pre-stimulus Behavior type and post-stimulus behavior type determine the behavioral change data of the experimental subject.
  • determining the behavioral change data of the experimental subject based on the three-dimensional posture data includes: using an unsupervised machine learning algorithm to segment the three-dimensional posture data to obtain times corresponding to at least two time series. Attitude data; perform dimensionality reduction operations on the time posture data corresponding to at least two time series to obtain at least two dimensionality reduction posture data, and perform clustering operations on at least two dimensionality reduction posture data to obtain time behavior data; based on time Behavioral data and stimulation time points to determine behavioral change data of experimental subjects.
  • the time behavior data represents behavior types corresponding to at least two time series respectively.
  • the unsupervised machine learning algorithm can be the Behavior Atlas (BeA) algorithm
  • the dimensionality reduction algorithm used in the dimensionality reduction operation is the Uniform Manifold Approximation and Projection (UMAP) dimensionality reduction algorithm.
  • the clustering algorithm used in class operations is hierarchical clustering algorithm.
  • the behavior type corresponding to the time series with the highest overlap rate of the pre-stimulus time period is regarded as the pre-stimulus behavior type
  • the behavioral data corresponding to the time series with the highest overlap rate of the post-stimulus time period is regarded as the post-stimulus behavior type.
  • Based on the pre-stimulus behavior type and Post-stimulus behavior type determines the behavioral change data of the experimental subject.
  • S260 Determine the activation state of the neural pathway to be detected based on the connection strength change data and behavior change data.
  • FIG. 4 is a flow chart of an example of a neural pathway activation detection method provided in Embodiment 2 of the present application.
  • multi-channel electrodes are implanted into at least two nuclei corresponding to the neural pathways to be detected, and at least three cameras are calibrated respectively to obtain camera parameter data.
  • obtain the multi-channel field potential data in the pre-stimulation time period and the multi-channel field potential data in the post-stimulation time period perform preprocessing operations on the multi-channel field potential data, and obtain the pre-stimulation field potential data and Poststimulus field potential data.
  • preprocessing operations include principal component analysis operations, filtering operations, and downsampling operations.
  • GC value Granger causality value
  • the video data to be detected of the experimental subject is obtained, where the video data to be detected includes video data collected by at least three video collection devices.
  • the video data to be detected includes video data collected by at least three video collection devices.
  • determine the two-dimensional skeleton data of the experimental object in the key image frame in each video data based on the corresponding camera parameter data of at least three video collection devices, compare the videos collected by at least three video collection devices.
  • the two-dimensional skeleton data of the experimental subject in the key image frame in the data is three-dimensionally reconstructed to obtain the three-dimensional posture data of the experimental subject.
  • the behavioral change data of the experimental subject is determined.
  • the activation state of the neural pathway to be detected is determined.
  • the video data collected using a single video acquisition device only contains the two-dimensional posture information of the experimental subject. Since many behaviors of the experimental subject are relatively close, the accuracy of the behavior type of the experimental subject determined based on the two-dimensional posture information is poor.
  • the technical solution of this embodiment is to use at least three video collection devices to collect video data respectively, and based on each video data, determine the two-dimensional skeleton data of the experimental object in the key image frame in each video data, based on at least three video collections
  • the camera parameter data corresponding to the device and the two-dimensional skeleton data of the experimental object in the key image frame in the video data collected by at least three video acquisition devices respectively determine the three-dimensional posture data of the experimental object, and based on the three-dimensional posture data, determine the experiment
  • the object's behavior change data solves the problem of a large misjudgment rate in distinguishing behavior types based on two-dimensional video data.
  • the three-dimensional posture data contains more posture information of the experimental object, which can improve the accuracy of the behavior change data and increase the
  • FIG. 5 is a schematic structural diagram of a neural pathway activation detection device provided in Embodiment 3 of the present application. As shown in Figure 5, the device includes: a field potential data acquisition module 310, a connection strength change data determination module 320, a behavior change data determination module 330 and an activation state determination module 340.
  • the field potential data acquisition module 310 is configured to acquire the pre-stimulation field potential data and post-stimulation field potential data corresponding to the neural pathway to be detected in the experimental subject; the connection strength change data determination module 320 is configured to obtain the pre-stimulation field potential data and post-stimulation field potential data based on the pre-stimulation field potential data and post-stimulation field potential data.
  • the field potential data determines the connection strength change data of the neural pathway to be detected;
  • the behavior change data determination module 330 is configured to determine the behavior change data of the experimental subject based on the video data to be detected;
  • the activation state determination module 340 is configured to determine the behavior change data of the experimental subject based on the video data to be detected.
  • Connection strength change data and behavioral change data determine the activation status of the neural pathway to be detected.
  • the technical solution of this embodiment determines the connection strength change data of the neural pathway to be detected based on the obtained pre-stimulation field potential data and post-stimulation field potential data corresponding to the experimental subject's neural pathway to be detected.
  • Video data and post-stimulation video data are used to determine the behavioral change data of the experimental subject.
  • the activation status of the neural pathway to be detected is determined, and the activation status of the neural pathway to be detected is determined comprehensively from the two dimensions of brain functional connection strength and behavioral information.
  • the activation status of neural pathways solves the problem of high misjudgment rates in neural pathway activation detection methods that rely solely on behavioral data, and improves the credibility of research results on brain function.
  • the activation state determination module 340 is configured to: when the connection strength change data meets the preset connection conditions, determine whether there is behavior change data in the preset behavior change data set; if If there is behavior change data in the preset behavior change data set, the activation state of the neural pathway to be detected is set to the activated state; if there is no behavior change data in the preset behavior change data set, the activation state of the neural pathway to be detected is set to Inactive status.
  • the pre-stimulation field potential data includes the first pre-stimulation field potential data and the third pre-stimulation field potential data respectively corresponding to the first nucleus and the second nucleus of the pair of nerve nuclei in the neural pathway to be detected.
  • Pre-stimulation field potential data and post-stimulation field potential data include the first post-stimulation field potential data and the second post-stimulation field potential data corresponding to the first and second nuclei in the pair of nerve nuclei respectively, and the connection strength change data.
  • the determination module 320 is configured to: determine the pre-stimulation connection strength corresponding to the nerve nucleus pair based on the first pre-stimulation field potential data and the second pre-stimulation field potential data; based on the first post-stimulation field potential data and the second post-stimulation field potential data.
  • the field potential data determines the post-stimulation connection strength corresponding to the nerve nucleus pair; based on the pre-stimulation connection strength and the post-stimulation connection strength, the connection strength change data of the nerve nucleus pair in the neural pathway to be detected is determined.
  • the field potential data acquisition module 310 is configured to: acquire at least two channels of field potential data within a preset time period of the target nuclei in the neural pathway to be detected; Perform dimensionality reduction operations on the two channel field potential data respectively to obtain at least two dimensionality reduction field potential data, and use the channel field potential data corresponding to the dimensionality reduction field potential data with the largest principal component among the at least two dimensionality reduction field potential data as the target.
  • Target field potential data corresponding to the nucleus among them, when the target nucleus is the first nucleus and the preset time period is the pre-stimulation period, the target field potential data is the first pre-stimulation field potential data.
  • the target field potential data is the first post-stimulation field potential data.
  • the target field potential data is the second pre-stimulation field potential data.
  • the target field potential data is the second post-stimulation field potential data.
  • the parameter type of the pre-stimulation connection strength or the post-stimulation connection strength is a Granger causality value.
  • the device further includes:
  • the preprocessing module is configured to separately perform preprocessing operations on the pre-stimulation field potential data and the post-stimulation field potential data before determining the connection strength change data of the neural pathway to be detected based on the pre-stimulation field potential data and the post-stimulation field potential data, Preprocessed pre-stimulation field potential data and post-stimulation field potential data are obtained; wherein the preprocessing operation includes a filtering operation and/or a downsampling operation.
  • the video data to be detected includes video data collected by at least three video collection devices.
  • the behavior change data determination module 330 is configured to: based on each video data, determine each The two-dimensional skeleton data of the experimental object in the key image frame in the video data; based on the camera parameter data corresponding to at least three video acquisition devices and the experimental object in the key image frame in the video data collected by at least three video acquisition devices.
  • the two-dimensional skeleton data determines the three-dimensional posture data of the experimental subject, and based on the three-dimensional posture data, determines the behavioral change data of the experimental subject.
  • the neural pathway activation detection device provided by the embodiments of the present application can execute the neural pathway activation detection method provided by any embodiment of the present application, and has functional modules corresponding to the execution method.
  • FIG. 6 is a schematic structural diagram of an electronic device provided in Embodiment 4 of the present application.
  • Electronic device 10 is intended to represent many forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers.
  • Electronic devices may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices (eg, helmets, glasses, watches, etc.), and other similar computing devices.
  • the components shown in the embodiments of the present application, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application as described and/or claimed herein.
  • the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a read-only memory (Read-Only Memory, ROM) 12, a random access memory (Random Access Memory, RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor 11.
  • the processor 11 can perform the processing according to the computer program stored in the ROM 12 or loaded from the storage unit 18 into the RAM 13. Performs a variety of appropriate actions and processes.
  • various programs and data required for the operation of the electronic device 10 can also be stored.
  • the processor 11, the ROM 12 and the RAM 13 are connected to each other via the bus 14.
  • An input/output (I/O) interface 15 is also connected to the bus 14 .
  • the multiple components include: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as Disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless communication transceiver, etc.
  • the communication unit 19 allows the electronic device 10 to exchange information/data with other devices through a computer network such as the Internet and/or various telecommunications networks.
  • Processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (Central Processing Unit, CPU), a graphics processing unit (GPU), a variety of dedicated artificial intelligence (Artificial Intelligence, AI) computing chips, a variety of running Machine learning model algorithm processor, digital signal processor (Digital Signal Processor, DSP), and any appropriate processor, controller, microcontroller, etc.
  • the processor 11 performs a plurality of methods and processes described above, such as neural pathway activation detection methods.
  • the neural pathway activation detection method may be implemented as a computer program, which is tangibly embodied in a computer-readable storage medium, such as the storage unit 18 .
  • part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19.
  • the processor 11 may be configured to perform the neural pathway activation detection method in any other suitable manner (eg, by means of firmware).
  • FPGAs Field Programmable Gate Arrays
  • ASICs Application Specific Integrated Circuits
  • ASSP Application Specific Standard Parts
  • SOC System on Chip
  • CPLD Complex Programmable Logic Device
  • These various embodiments may include implementation in one or more computer programs executable and/or interpreted on a programmable system including at least one programmable processor, the programmable processor
  • the processor which may be a special purpose or general purpose programmable processor, may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
  • An output device may be a special purpose or general purpose programmable processor, may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
  • An output device may be a special purpose or general purpose programmable processor, may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
  • the computer program used to implement the neural pathway activation detection method of the present application can be written using any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that the computer program, when executed by the processor, causes the functions/operations specified in the flowcharts and/or block diagrams to be implemented. A computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
  • Embodiment 5 of the present application also provides a computer-readable storage medium.
  • the computer-readable storage medium stores computer instructions.
  • the computer instructions are used to cause the processor to execute a neural pathway activation detection method.
  • the method includes: obtaining an experimental subject.
  • the pre-stimulation field potential data and post-stimulation field potential data corresponding to the neural pathway to be detected are determined; based on the pre-stimulation field potential data and post-stimulation field potential data, the connection strength change data of the neural pathway to be detected is determined; based on the video of the experimental subject to be detected data to determine the behavioral change data of the experimental subject; based on the connection strength change data and behavioral change data, determine the activation state of the neural pathway to be detected.
  • a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device.
  • Computer-readable storage media may include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any suitable combination of the foregoing.
  • the computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media would include one or more wire-based electrical connections, laptop disks, hard drives, RAM, ROM, Erasable Programmable Read-Only Memory (EPROM), or Flash memory, optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
  • the systems and techniques described herein may be implemented on an electronic device having a display device (e.g., a cathode ray tube (CRT) or liquid crystal) for displaying information to the user.
  • a display device e.g., a cathode ray tube (CRT) or liquid crystal
  • a display Liquid Crystal Display, LCD monitor
  • a keyboard and pointing device e.g., a mouse or a trackball
  • Other kinds of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and may be provided in any form, including Acoustic input, voice input or tactile input) to receive input from the user.
  • the systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., A user's computer having a graphical user interface or web browser through which the user can interact with implementations of the systems and technologies described herein), or including such backend components, middleware components, or any combination of front-end components in a computing system.
  • the components of the system may be interconnected by any form or medium of digital data communication (eg, a communications network). Examples of communication networks include: Local Area Network (LAN), Wide Area Network (WAN), blockchain network, and the Internet.
  • Computing systems may include clients and servers.
  • Clients and servers are generally remote from each other and typically interact over a communications network.
  • the relationship of client and server is created by computer programs running on corresponding computers and having a client-server relationship with each other.
  • the server can be a cloud server, also known as cloud computing server or cloud host. It is a host product in the cloud computing service system to solve the problems that exist in traditional physical host and virtual private server (VPS) services. It has the disadvantages of difficult management and weak business scalability.
  • VPN virtual private server

Landscapes

  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • Medical Informatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Psychiatry (AREA)
  • Veterinary Medicine (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Pathology (AREA)
  • Molecular Biology (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • Biophysics (AREA)
  • Public Health (AREA)
  • Biomedical Technology (AREA)
  • Psychology (AREA)
  • Multimedia (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Neurology (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Databases & Information Systems (AREA)
  • Computing Systems (AREA)
  • Social Psychology (AREA)
  • Acoustics & Sound (AREA)
  • Educational Technology (AREA)
  • Neurosurgery (AREA)
  • Physiology (AREA)
  • Human Computer Interaction (AREA)
  • Child & Adolescent Psychology (AREA)
  • Developmental Disabilities (AREA)
  • Computational Linguistics (AREA)
  • Hospice & Palliative Care (AREA)
  • Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)

Abstract

本申请公开了一种神经通路的激活检测方法、装置、设备及存储介质。该方法包括：获取实验对象的待检测神经通路对应的刺激前场电位数据和刺激后场电位数据；基于所述刺激前场电位数据和所述刺激后场电位数据，确定所述待检测神经通路的连接强度变化数据；基于所述实验对象的待检测视频数据，确定所述实验对象的行为变化数据；基于所述连接强度变化数据和所述行为变化数据，确定所述待检测神经通路的激活状态。

Description

神经通路的激活检测方法、装置、设备及存储介质
本申请要求在2022年09月08日提交中国专利局、申请号为202211094734.1的中国专利申请的优先权，该申请的全部内容通过引用结合在本申请中。
技术领域
本申请涉及脑科学技术领域，例如涉及一种神经通路的激活检测方法、装置、设备及存储介质。
背景技术
大脑的神经***是一个极其复杂而高效精确的***，其感知和认知的脑机制一直是脑科学研究的热点问题。动物的行为与相关神经通路的激活存在紧密的联系，在进行实验研究时，通常会给实验对象给予一定的刺激，以使实验对象产生与刺激对应的行为，通过其行为的变化作为相关神经通路是否被激活的判断依据。
但是动物行为的变化可能是由于给予刺激产生的，也可能是与刺激无关的自发行为，并且，实验对象的有些行为并不能唯一标定一种神经通路，如奔跑行为可能对应与恐惧情绪相关的神经通路，也可能对应与焦虑情绪相关的神经通路。因此，仅依靠行为的变化作为相关神经通路是否被激活的判断依据会存在一定的误判率，使得关于脑功能的研究结果的可信度较低。
发明内容
本申请实施例提供了一种神经通路的激活检测方法、装置、设备及存储介质，以解决单纯依赖于行为数据的神经通路的激活检测方法存在的高误判率的问题，提高关于脑功能的研究结果的可信度。
根据本申请一个实施例提供了一种神经通路的激活检测方法，该方法包括：获取实验对象的待检测神经通路对应的刺激前场电位数据和刺激后场电位数据；基于所述刺激前场电位数据和所述刺激后场电位数据，确定所述待检测神经通路的连接强度变化数据；基于所述实验对象的待检测视频数据，确定所述实验对象的行为变化数据；基于所述连接强度变化数据和所述行为变化数据，确定所述待检测神经通路的激活状态。
根据本申请另一个实施例提供了一种神经通路的激活检测装置，该装置包括：场电位数据获取模块，设置为获取实验对象的待检测神经通路对应的刺激 前场电位数据和刺激后场电位数据；连接强度变化数据确定模块，设置为基于所述刺激前场电位数据和所述刺激后场电位数据，确定所述待检测神经通路的连接强度变化数据；行为变化数据确定模块，设置为基于所述实验对象的待检测视频数据，确定所述实验对象的行为变化数据；激活状态确定模块，设置为基于所述连接强度变化数据和所述行为变化数据，确定所述待检测神经通路的激活状态。
根据本申请另一个实施例提供了一种电子设备，所述电子设备包括：至少一个处理器；以及与所述至少一个处理器通信连接的存储器；其中，所述存储器存储有可被所述至少一个处理器执行的计算机程序，所述计算机程序被所述至少一个处理器执行，以使所述至少一个处理器能够执行本申请任一实施例所述的神经通路的激活检测方法。
根据本申请另一个实施例，提供了一种计算机可读存储介质，所述计算机可读存储介质存储有计算机指令，所述计算机指令用于使处理器执行时实现本申请任一实施例所述的神经通路的激活检测方法。
附图说明
下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1为本申请实施例一所提供的一种神经通路的激活检测方法的流程图；
图2为本申请实施例二所提供的一种神经通路的激活检测方法的流程图；
图3为本申请实施例二所提供的一种实验对象的姿态特征点的示意图；
图4为本申请实施例二所提供的一种神经通路的激活检测方法的实例的流程图；
图5为本申请实施例三所提供的一种神经通路的激活检测装置的结构示意图；
图6为本申请实施例四所提供的一种电子设备的结构示意图。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行描述，显然，所描述的实施例仅仅是本申请一部分的实施例。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都应当属于本申请保护的范围。
需要说明的是，本申请的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换，以便这里描述的本申请的实施例能够以除了在这里图示或描述的那些以外的顺序实施。此外，术语“包括”和“具有”以及他们的任何变形，意图在于覆盖不排他的包含，例如，包含了一系列步骤或单元的过程、方法、***、产品或设备不必限于清楚地列出的那些步骤或单元，而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。
实施例一
图1为本申请实施例一所提供的一种神经通路的激活检测方法的流程图。本实施例可适用于对神经***中的神经通路的激活状态进行检测情况，该方法可以由神经通路的激活检测装置来执行，该神经通路的激活检测装置可以采用硬件和/或软件的形式实现，该神经通路的激活检测装置可配置于终端设备中。如图1所示，该方法包括如下步骤。
S110、获取实验对象的待检测神经通路对应的刺激前场电位数据和刺激后场电位数据。
示例性的，待检测神经通路可以为中脑腹侧被盖区-伏核-前额叶皮质、上丘-丘脑枕-杏仁核外侧、海马-***体-丘脑前核-扣带回等，此处对待检测神经通路不作限定，用户可根据实际需求进行自定义设置。
刺激前场电位数据为待检测神经通路在刺激前时间段内的场电位数据，刺激后场电位数据为待检测神经通路在刺激后时间段内的场电位数据。场电位数据可以是通过植入性电极或非植入性电极采集到的，场电位数据用于表征待检测神经通路中目标核团产生的电位变化。
刺激前时间段可基于刺激时间点和第一时长确定，刺激后时间段可基于刺激时间点和第二时长确定。第一时长和第二时长可以相同也可以不同，示例性的，第一时长为3分钟，第二时长为5分钟。此处对第一时长和第二时长的数值不作限定。
在一个可选实施例中，在检测到刺激信号的情况下，采用打标器产生打标信号，以记录刺激时间点。这样设置避免了人为观察和记录刺激时间点带来的时间误差，从而提高记录的刺激时间点的准确度。
给予实验对象的刺激可以为物理刺激或药物刺激，示例性的，物理刺激可以为电击、声音或光信号等。此处对刺激的类型不作限定，用户可根据待检测神经通路与刺激之间的相关性进行自定义设置。
S120、基于刺激前场电位数据和刺激后场电位数据，确定待检测神经通路的连接强度变化数据。
待检测神经通路中包含至少一个神经核团对。举例而言，假设待检测神经通路为上丘-丘脑枕-杏仁核外侧，则待检测神经通路对应上丘-丘脑枕、丘脑枕-杏仁核外侧以及上丘-杏仁核外侧中至少一个神经核团对。待检测神经通路对应的连接强度变化数据中包含至少一个神经核团对分别对应的连接强度变化数据。
在一个可选实施例中，当待检测神经通路中包含一个神经核团对时，刺激前场电位数据包括待检测神经通路中的神经核团对中第一核团和第二核团分别对应的第一刺激前场电位数据和第二刺激前场电位数据，刺激后场电位数据包括神经核团对中第一核团和第二核团分别对应的第一刺激后场电位数据和第二刺激后场电位数据，基于刺激前场电位数据和刺激后场电位数据，确定待检测神经通路的连接强度变化数据，包括：基于第一刺激前场电位数据和第二刺激前场电位数据，确定神经核团对对应的刺激前连接强度；基于第一刺激后场电位数据和第二刺激后场电位数据，确定神经核团对对应的刺激后连接强度；基于刺激前连接强度和刺激后连接强度，确定待检测神经通路中神经核团对的连接强度变化数据。
本实施例以待检测神经通路中包含一个神经核团对进行示例性说明。容易理解的是，待检测神经通路对应的其他神经核团对的连接强度变化数据同样可通过上述方法确定。
在一个可选实施例中，刺激前连接强度或刺激后连接强度的参数类型为格兰杰因果关系值。
格兰杰因果关系检验是一种假设检定的统计方法，可用于检验第一刺激前场电位数据是否为第二刺激前场电位数据的原因或第二刺激前场电位数据是否为第一刺激前场电位数据的原因。格兰杰因果分析结果包括两个核团之间的连接方向、连接强度和连接的显著性三个要素。
示例性的，可采用矩阵实验室(matlab)软件中的多元格兰杰因果关系(Multivariate Granger Causality，MVGC)工具箱，基于多个核团分别对应的刺激前场电位数据，确定至少一个神经核团对分别对应的刺激前的格兰杰因果关系(Granger Causality，GC)值，基于多个核团分别对应的刺激后场电位数据，确定至少一个神经核团对分别对应的刺激后的格兰杰因果关系值。
示例性的，神经核团对的连接强度变化数据包括刺激前连接强度和刺激后连接强度，或者神经核团对的连接强度变化数据包括刺激前连接强度和刺激后 连接强度对应的强度差值或变化趋势。当刺激前连接强度小于刺激后连接强度时，强度差值大于0，变化趋势为增强趋势，当刺激前连接强度大于刺激后连接强度时，强度差值小于0，变化趋势为减弱趋势。
S130、基于实验对象的待检测视频数据，确定实验对象的行为变化数据。
在一个可选实施例中，待检测视频数据包括刺激前视频数据和刺激后视频数据。刺激前视频数据为实验对象在刺激前时间段内的视频数据，刺激后视频数据为实验对象在刺激后时间段内的视频数据。刺激前时间段的时长与刺激后时间段的时长可以相同，也可以不同。在本实施例中，待检测视频数据的录制和场电位数据的记录基于同一时间戳进行同步记录。
示例性的，将刺激前视频数据输入到预先训练完成的目标分类模型中，得到输出的刺激前行为类型，将刺激后视频数据输入到目标分类模型中，得到输出的刺激后行为类型，基于刺激前行为类型和刺激后行为类型，确定实验对象的行为变化数据。
举例而言，行为类型包括但不限于静止、静止战栗、进食、转圈、梳理毛发、奔跑、***和社交行为等。此处对可分类的行为类型不作限定。
S140、基于连接强度变化数据和行为变化数据，确定待检测神经通路的激活状态。
在一个可选实施例中，基于连接强度变化数据和行为变化数据，确定待检测神经通路的激活状态，包括：在连接强度变化数据满足预设连接条件的情况下，判断预设行为变化数据集中是否存在行为变化数据；如果预设行为变化数据集中存在行为变化数据，则将待检测神经通路的激活状态设置为已激活状态；如果预设行为变化数据集中不存在行为变化数据，则将待检测神经通路的激活状态设置为未激活状态。
在一个可选实施例中，当连接强度变化数据包括刺激前连接强度和刺激后连接强度时，预设连接条件为刺激前连接强度小于刺激后连接强度。在另一个可选实施例中，当连接强度变化数据包括刺激前连接强度和刺激后连接强度对应的强度差值或变化趋势时，预设连接条件为强度差值满足预设差值范围或变化趋势为增强趋势。示例性的，预设差值范围可以为大于预设强度阈值，示例性的，预设强度阈值可以为0或1。
在待检测神经通路的连接强度变化数据包括一个神经核团对的连接强度变化数据的情况下，连接强度变化数据满足预设连接条件表征该神经核团对的连接强度变化数据满足预设连接条件。在待检测神经通路的连接强度变化数据包括至少两个神经核团对分别对应的连接强度变化数据的情况下，连接强度变化 数据满足预设连接条件表征至少两个神经核团对分别对应的连接强度变化数据均满足预设连接条件。
在一个可选实施例中，预设行为变化数据集中包含与给予实验对象的刺激相对应的至少一个预设行为变化数据。示例性的，当刺激为恐惧类刺激时，预设行为变化数据集中包括静止-静止战栗、静止-奔跑、进食-奔跑、进食-***等；当刺激为抑郁类刺激时，预设行为变化数据集中包含进食-静止、社交行为-静止等。
在另一个可选实施例中，预设行为变化数据集中包含与给予实验对象的刺激相对应的刺激前行为数据集和刺激后行为数据集。示例性的，当刺激为恐惧类刺激时，刺激前行为数据集中包含静止、进食、梳理毛发和社交行为，刺激后行为包括静止战栗、转圈、***和奔跑。如果刺激前行为数据集中包含行为变化数据中的刺激前行为类型且刺激后行为数据集中包含行为变化数据中的刺激后行为类型，则认为预设行为变化数据集中存在行为变化数据。
在上述实施例的基础上，该方法还包括：如果连接强度变化数据不满足预设连接条件，则将待检测神经通路的激活状态设置为未激活状态。在待检测神经通路的连接强度变化数据包括至少两个神经核团对分别对应的连接强度变化数据的情况下，连接强度变化数据不满足预设连接条件表征为存在至少一个神经核团对的连接强度变化数据不满足预设连接条件。
本实施例的技术方案，通过基于获取到的实验对象的待检测神经通路对应的刺激前场电位数据和刺激后场电位数据，确定待检测神经通路的连接强度变化数据，基于实验对象的刺激前视频数据和刺激后视频数据，确定实验对象的行为变化数据，基于连接强度变化数据和行为变化数据，确定待检测神经通路的激活状态，从脑功能连接强度和行为信息两个维度综合确定待检测神经通路的激活状态，解决了单纯依赖于行为数据的神经通路的激活检测方法存在的高误判率的问题，提高了关于脑功能的研究结果的可信度。
实施例二
图2为本申请实施例二所提供的一种神经通路的激活检测方法的流程图。本实施例中的待检测视频数据包括至少三个视频采集设备分别采集到的视频数据，本实施例对上述实施例中的“基于实验对象的待检测视频数据，确定实验对象的行为变化数据”进行说明。如图2所示，该方法包括如下步骤。
S210、获取实验对象的待检测神经通路对应的刺激前场电位数据和刺激后场电位数据。
在一个可选实施例中，获取实验对象的待检测神经通路对应的刺激前场电 位数据和刺激后场电位数据，包括：获取待检测神经通路中的目标核团在预设时间段内的至少两个通道场电位数据；对至少两个通道场电位数据分别执行降维操作，得到至少两个降维场电位数据，并将至少两个降维场电位数据中主成分最大的降维场电位数据对应的通道场电位数据作为目标核团对应的目标场电位数据；其中，当目标核团为第一核团且预设时间段为刺激前时间段时，目标场电位数据为第一刺激前场电位数据，当目标核团为第一核团且预设时间段为刺激后时间段时，目标场电位数据为第一刺激后场电位数据，当目标核团为第二核团且预设时间段为刺激前时间段时，目标场电位数据为第二刺激前场电位数据，当目标核团为第二核团且预设时间段为刺激后时间段时，目标场电位数据为第二刺激后场电位数据。
采用多通道电极采集待检测神经通路中至少两个核团分别对应的至少两个通道场电位数据。示例性的，多通道电极可以是基于脑图谱植入到对应核团中的。
降维操作采用的降维算法为主成分分析(Principal Components Analysis，PCA)算法。
这样设置可以使得获取到的待检测神经通路对应的刺激前场电位数据和刺激后场电位数据包含更多的特征信息，进而提高后续得到的连接强度变化数据的准确度。
在上述实施例的基础上，在基于刺激前场电位数据和刺激后场电位数据，确定待检测神经通路的连接强度变化数据之前，方法还包括：对刺激前场电位数据和刺激后场电位数据分别执行预处理操作，得到预处理后的刺激前场电位数据和刺激后场电位数据；其中，预处理操作包括滤波操作和/或降采样操作。
示例性的，可采用matlab软件中的零相位数字滤波(filtfilt)函数，通过正向和反向分别输入刺激前场电位数据或刺激后场电位数据，实现对刺激前场电位数据或刺激后场电位数据的零相位数字滤波。
示例性的，可采用matlab软件中的重采样(resample)函数，将刺激前场电位数据或刺激后场电位数据的采样率降到1000Hz。
这样设置可以去除场电位数据中的噪声以及降低格兰杰因果检验过程中的lag值。
S220、基于刺激前场电位数据和刺激后场电位数据，确定待检测神经通路的连接强度变化数据。
S230、基于每个视频数据，确定每个视频数据中关键图像帧中实验对象的二维骨架数据。
在本实施例中，采用至少三个视频采集设备分别采集实验对象在实验过程中的视频数据。在一个可选实施例中，视频采集设备的数量为4个。此处对视频采集设备的数量不作限定。
二维骨架数据用于表征实验对象的至少一个姿态特征点分别在关键图像帧中的位置坐标。在一个可选实施例中，将目标采集视频输入到预先训练完成的特征点识别模型中，得到输出的至少一个关键图像帧以及每个关键图像帧中至少一个姿态特征点分别对应的位置坐标。
示例性的，特征点识别模型的模型类型为DeepLabCut深度学习模型，至少一个姿态特征点包括四肢、鼻子、双耳、头部、躯干和尾部等。此处对特征点识别模型的模型类型和姿态特征点的设置不作限定。
图3为本申请实施例二所提供的一种实验对象的姿态特征点的示意图。图3示出的姿态特征点的数量为16个，分别为鼻子、左耳、右耳、脖颈、四肢、5个躯干特征点、尾根部、尾中部和尾尖部。至少一个姿态特征点可采用不同颜色的圆点进行区分显示。
S240、基于至少三个视频采集设备分别对应的摄像头参数数据以及至少三个视频采集设备分别采集到的视频数据中关键图像帧中的实验对象的二维骨架数据，确定实验对象的三维姿态数据。
在上述实施例中的基础上，该方法还包括：基于每个视频采集设备，获取每个视频采集设备采集到的预设数量的标准棋盘格图像，采用matlab软件中的立体相机标定图形用户界面(StereoCameraCalibrator Graphical User Interface，StereoCameraCalibrator GUI)工具箱，基于预设数量的标准棋盘格图像执行定标操作，得到每个视频采集设备对应的摄像头参数数据。示例性的，标准棋盘格的规格为12*9，预设数量为60张，摄像头参数数据包括内参数据和外参数据。
在一个可选实施例中，采用三角划分(triangulation)算法，基于至少三视频采集设备分别对应的摄像头参数数据以及至少三个视频采集设备分别采集到的视频数据中关键图像帧中的实验对象的二维骨架数据，确定实验对象的三维姿态数据。
S250、基于三维姿态数据，确定实验对象的行为变化数据。
在一个可选实施例中，基于三维姿态数据，确定实验对象的行为变化数据，包括：获取三维姿态数据中与刺激前时间段对应的刺激前姿态数据以及与刺激后时间段对应的刺激后姿态数据，并将刺激前姿态数据输入到预先训练完成的目标分类模型中，得到输出的刺激前行为类型，将刺激后姿态数据输入到目标分类模型中，得到输出的刺激后行为类型，基于刺激前行为类型和刺激后行为 类型，确定实验对象的行为变化数据。
在另一个可选实施例中，基于三维姿态数据，确定实验对象的行为变化数据，包括：采用无监督机器学习算法，对三维姿态数据进行切分，得到与至少两个时间序列分别对应的时间姿态数据；对至少两个时间序列分别对应的时间姿态数据执行降维操作，得到至少两个降维姿态数据，并对至少两个降维姿态数据执行聚类操作，得到时间行为数据；基于时间行为数据和刺激时间点，确定实验对象的行为变化数据。时间行为数据表征与至少两个时间序列分别对应的行为类型。
示例性的，无监督机器学习算法可以为行为图谱(Behavior Atlas，BeA)算法，降维操作采用的降维算法为统一流形逼近与投影(Uniform Manifold Approximation and Projection，UMAP)降维算法，聚类操作采用的聚类算法为层次聚类算法。
基于时间行为数据和刺激时间点，确定实验对象的行为变化数据，包括：基于刺激时间点和第一时长，确定刺激前时间段以及基于刺激时间点和第二时长，确定刺激后时间段；将与刺激前时间段重叠率最高的时间序列对应的行为类型作为刺激前行为类型，并将与刺激后时间段重叠率最高的时间序列对应的行为数据作为刺激后行为类型，基于刺激前行为类型和刺激后行为类型，确定实验对象的行为变化数据。
S260、基于连接强度变化数据和行为变化数据，确定待检测神经通路的激活状态。
图4为本申请实施例二所提供的一种神经通路的激活检测方法的实例的流程图。基于脑图谱，将多通道电极植入到待检测神经通路对应的至少两个核团中，以及对至少三个摄像头分别进行定标，得到摄像头参数数据。给予实验对象一定的刺激，获取刺激前时间段内的多通道场电位数据和刺激后时间段内的多通道场电位数据，对多通道场电位数据进行预处理操作，得到刺激前场电位数据和刺激后场电位数据。示例性的，预处理操作包括主成分分析操作、滤波操作和降采样操作。基于刺激前场电位数据和刺激后场电位数据，确定待检测神经通路中至少两个核团分别对应的刺激前连接强度和刺激后连接强度，其中，刺激前连接强度或刺激后连接强度的参数类型为格兰杰因果关系值(GC值)，基于至少两个核团分别对应的刺激前连接强度和刺激后连接强度，确定待检测神经通路的连接强度变化数据。
同时，获取实验对象的待检测视频数据，其中，待检测视频数据包括至少三个视频采集设备分别采集到的视频数据。基于每个视频数据，确定每个视频数据中关键图像帧中实验对象的二维骨架数据；基于至少三个视频采集设备分 别对应的摄像头参数数据，对至少三个视频采集设备分别采集到的视频数据中关键图像帧中的实验对象的二维骨架数据进行三维重建得到实验对象的三维姿态数据，基于三维姿态数据，确定实验对象的行为变化数据。最后，基于连接强度变化数据和行为变化数据，确定待检测神经通路的激活状态。
采用单一视频采集设备采集到的视频数据仅包含实验对象的二维姿态信息，由于实验对象的很多行为比较接近，因此，基于二维姿态信息确定出的实验对象的行为类型准确度较差。本实施例的技术方案，通过采用至少三个视频采集设备分别采集视频数据，基于每个视频数据，确定每个视频数据中关键图像帧中实验对象的二维骨架数据，基于至少三个视频采集设备分别对应的摄像头参数数据以及至少三个视频采集设备分别采集到的视频数据中关键图像帧中的实验对象的二维骨架数据，确定实验对象的三维姿态数据，并基于三维姿态数据，确定实验对象的行为变化数据，解决了基于二维视频数据区分行为类型存在的较大误判率的问题，三维姿态数据包含实验对象更多的姿态信息，进而可以提高行为变化数据的准确度以及可以增加可区分的行为类型的类型数量。
实施例三
图5为本申请实施例三所提供的一种神经通路的激活检测装置的结构示意图。如图5所示，该装置包括：场电位数据获取模块310、连接强度变化数据确定模块320、行为变化数据确定模块330和激活状态确定模块340。
场电位数据获取模块310，设置为获取实验对象的待检测神经通路对应的刺激前场电位数据和刺激后场电位数据；连接强度变化数据确定模块320，设置为基于刺激前场电位数据和刺激后场电位数据，确定待检测神经通路的连接强度变化数据；行为变化数据确定模块330，设置为基于实验对象的待检测视频数据，确定实验对象的行为变化数据；激活状态确定模块340，设置为基于连接强度变化数据和行为变化数据，确定待检测神经通路的激活状态。
本实施例的技术方案，通过基于获取到的实验对象的待检测神经通路对应的刺激前场电位数据和刺激后场电位数据，确定待检测神经通路的连接强度变化数据，基于实验对象的刺激前视频数据和刺激后视频数据，确定实验对象的行为变化数据，基于连接强度变化数据和行为变化数据，确定待检测神经通路的激活状态，从脑功能连接强度和行为信息两个维度综合确定待检测神经通路的激活状态，解决了单纯依赖于行为数据的神经通路的激活检测方法存在的高误判率的问题，提高了关于脑功能的研究结果的可信度。
在上述实施例的基础上，可选的，激活状态确定模块340，是设置为：在连接强度变化数据满足预设连接条件的情况下，判断预设行为变化数据集中是否存在行为变化数据；如果预设行为变化数据集中存在行为变化数据，则将待检 测神经通路的激活状态设置为已激活状态；如果预设行为变化数据集中不存在行为变化数据，则将待检测神经通路的激活状态设置为未激活状态。
在上述实施例的基础上，可选的，刺激前场电位数据包括待检测神经通路中的神经核团对中第一核团和第二核团分别对应的第一刺激前场电位数据和第二刺激前场电位数据，刺激后场电位数据包括神经核团对中第一核团和第二核团分别对应的第一刺激后场电位数据和第二刺激后场电位数据，连接强度变化数据确定模块320，是设置为：基于第一刺激前场电位数据和第二刺激前场电位数据，确定神经核团对对应的刺激前连接强度；基于第一刺激后场电位数据和第二刺激后场电位数据，确定神经核团对对应的刺激后连接强度；基于刺激前连接强度和刺激后连接强度，确定待检测神经通路中神经核团对的连接强度变化数据。
在上述实施例的基础上，可选的，场电位数据获取模块310，是设置为：获取待检测神经通路中的目标核团在预设时间段内的至少两个通道场电位数据；对至少两个通道场电位数据分别执行降维操作，得到至少两个降维场电位数据，并将至少两个降维场电位数据中主成分最大的降维场电位数据对应的通道场电位数据作为目标核团对应的目标场电位数据；其中，当目标核团为第一核团且预设时间段为刺激前时间段时，目标场电位数据为第一刺激前场电位数据，当目标核团为第一核团且预设时间段为刺激后时间段时，目标场电位数据为第一刺激后场电位数据，当目标核团为第二核团且预设时间段为刺激前时间段时，目标场电位数据为第二刺激前场电位数据，当目标核团为第二核团且预设时间段为刺激后时间段时，目标场电位数据为第二刺激后场电位数据。
在上述实施例的基础上，可选的，刺激前连接强度或刺激后连接强度的参数类型为格兰杰因果关系值。
在上述实施例的基础上，可选的，该装置还包括：
预处理模块，设置为在基于刺激前场电位数据和刺激后场电位数据，确定待检测神经通路的连接强度变化数据之前，对刺激前场电位数据和刺激后场电位数据分别执行预处理操作，得到预处理后的刺激前场电位数据和刺激后场电位数据；其中，预处理操作包括滤波操作和/或降采样操作。
在上述实施例的基础上，可选的，待检测视频数据包括至少三个视频采集设备分别采集到的视频数据，行为变化数据确定模块330，是设置为：基于每个视频数据，确定每个视频数据中关键图像帧中实验对象的二维骨架数据；基于至少三个视频采集设备分别对应的摄像头参数数据以及至少三个视频采集设备分别采集到的视频数据中关键图像帧中的实验对象的二维骨架数据，确定实验对象的三维姿态数据，并基于三维姿态数据，确定实验对象的行为变化数据。
本申请实施例所提供的神经通路的激活检测装置可执行本申请任意实施例所提供的神经通路的激活检测方法，具备执行方法相应的功能模块。
实施例四
图6为本申请实施例四所提供的一种电子设备的结构示意图。电子设备10旨在表示多种形式的数字计算机，诸如，膝上型计算机、台式计算机、工作台、个人数字助理、服务器、刀片式服务器、大型计算机、和其它适合的计算机。电子设备还可以表示多种形式的移动装置，诸如，个人数字处理、蜂窝电话、智能电话、可穿戴设备(如头盔、眼镜、手表等)和其它类似的计算装置。本申请实施例所示的部件、它们的连接和关系、以及它们的功能仅仅作为示例，并且不意在限制本文中描述的和/或者要求的本申请的实现。
如图6所示，电子设备10包括至少一个处理器11，以及与至少一个处理器11通信连接的存储器，如只读存储器(Read-Only Memory，ROM)12、随机访问存储器(Random Access Memory，RAM)13等，其中，存储器存储有可被至少一个处理器11执行的计算机程序，处理器11可以根据存储在ROM 12中的计算机程序或者从存储单元18加载到RAM 13中的计算机程序，来执行多种适当的动作和处理。在RAM 13中，还可存储电子设备10操作所需的多种程序和数据。处理器11、ROM 12以及RAM 13通过总线14彼此相连。输入/输出(Input/Ouput，I/O)接口15也连接至总线14。
电子设备10中的多个部件连接至I/O接口15，多个部件包括：输入单元16，例如键盘、鼠标等；输出单元17，例如多种类型的显示器、扬声器等；存储单元18，例如磁盘、光盘等；以及通信单元19，例如网卡、调制解调器、无线通信收发机等。通信单元19允许电子设备10通过诸如因特网的计算机网络和/或多种电信网络与其他设备交换信息/数据。
处理器11可以是多种具有处理和计算能力的通用和/或专用处理组件。处理器11的一些示例包括但不限于中央处理单元(Central Processing Unit，CPU)、图形处理单元(Graphics Processing Unit，GPU)、多种专用的人工智能(Artificial Intelligence，AI)计算芯片、多种运行机器学习模型算法的处理器、数字信号处理器(Digital Signal Processor，DSP)、以及任何适当的处理器、控制器、微控制器等。处理器11执行上文所描述的多个方法和处理，例如神经通路的激活检测方法。
在一些实施例中，神经通路的激活检测方法可被实现为计算机程序，其被有形地包含于计算机可读存储介质，例如存储单元18。在一些实施例中，计算机程序的部分或者全部可以经由ROM 12和/或通信单元19而被载入和/或安装到电子设备10上。当计算机程序加载到RAM 13并由处理器11执行时，可以 执行上文描述的神经通路的激活检测方法的一个或多个步骤。可选地，在其他实施例中，处理器11可以通过其他任何适当的方式(例如，借助于固件)而被配置为执行神经通路的激活检测方法。
本文中以上描述的***和技术的多种实施方式可以在数字电子电路***、集成电路***、场可编程门阵列(Field Programmable Gate Array，FPGA)、专用集成电路(Application Specific Integrated Circuit，ASIC)、专用标准产品(Application Specific Standard Parts，ASSP)、芯片上***的***(System on Chip，SOC)、复杂可编程逻辑设备(Complex Programmable Logic Device，CPLD)、计算机硬件、固件、软件、和/或它们的组合中实现。这些多种实施方式可以包括：实施在一个或者多个计算机程序中，该一个或者多个计算机程序可在包括至少一个可编程处理器的可编程***上执行和/或解释，该可编程处理器可以是专用或者通用可编程处理器，可以从存储***、至少一个输入装置、和至少一个输出装置接收数据和指令，并且将数据和指令传输至该存储***、该至少一个输入装置、和该至少一个输出装置。
用于实施本申请的神经通路的激活检测方法的计算机程序可以采用一个或多个编程语言的任何组合来编写。这些计算机程序可以提供给通用计算机、专用计算机或其他可编程数据处理装置的处理器，使得计算机程序当由处理器执行时使流程图和/或框图中所规定的功能/操作被实施。计算机程序可以完全在机器上执行、部分地在机器上执行，作为独立软件包部分地在机器上执行且部分地在远程机器上执行或完全在远程机器或服务器上执行。
实施例五
本申请实施例五还提供了一种计算机可读存储介质，计算机可读存储介质存储有计算机指令，计算机指令用于使处理器执行一种神经通路的激活检测方法，该方法包括：获取实验对象的待检测神经通路对应的刺激前场电位数据和刺激后场电位数据；基于刺激前场电位数据和刺激后场电位数据，确定待检测神经通路的连接强度变化数据；基于实验对象的待检测视频数据，确定实验对象的行为变化数据；基于连接强度变化数据和行为变化数据，确定待检测神经通路的激活状态。
在本申请的上下文中，计算机可读存储介质可以是有形的介质，其可以包含或存储以供指令执行***、装置或设备使用或与指令执行***、装置或设备结合地使用的计算机程序。计算机可读存储介质可以包括但不限于电子的、磁性的、光学的、电磁的、红外的、或半导体***、装置或设备，或者上述内容的任何合适组合。可选地，计算机可读存储介质可以是机器可读信号介质。机器可读存储介质的更具体示例会包括基于一个或多个线的电气连接、便携式计 算机盘、硬盘、RAM、ROM、可擦除可编程只读存储器(Erasable Programmable Read-Only Memory，EPROM)或快闪存储器、光纤、便捷式紧凑盘只读存储器(Compact Disc Read-Only Memory，CD-ROM)、光学储存设备、磁储存设备、或上述内容的任何合适组合。
为了提供与用户的交互，可以在电子设备上实施此处描述的***和技术，该电子设备具有：用于向用户显示信息的显示装置(例如，阴极射线管(Cathode Ray Tube，CRT)或者液晶显示器(Liquid Crystal Display，LCD)监视器)；以及键盘和指向装置(例如，鼠标或者轨迹球)，用户可以通过该键盘和该指向装置来将输入提供给电子设备。其它种类的装置还可以用于提供与用户的交互；例如，提供给用户的反馈可以是任何形式的传感反馈(例如，视觉反馈、听觉反馈、或者触觉反馈)；并且可以用任何形式(包括声输入、语音输入或者、触觉输入)来接收来自用户的输入。
可以将此处描述的***和技术实施在包括后台部件的计算***(例如，作为数据服务器)、或者包括中间件部件的计算***(例如，应用服务器)、或者包括前端部件的计算***(例如，具有图形用户界面或者网络浏览器的用户计算机，用户可以通过该图形用户界面或者该网络浏览器来与此处描述的***和技术的实施方式交互)、或者包括这种后台部件、中间件部件、或者前端部件的任何组合的计算***中。可以通过任何形式或者介质的数字数据通信(例如，通信网络)来将***的部件相互连接。通信网络的示例包括：局域网(Local Area Network，LAN)、广域网(Wide Area Network，WAN)、区块链网络和互联网。
计算***可以包括客户端和服务器。客户端和服务器一般远离彼此并且通常通过通信网络进行交互。通过在相应的计算机上运行并且彼此具有客户端-服务器关系的计算机程序来产生客户端和服务器的关系。服务器可以是云服务器，又称为云计算服务器或云主机，是云计算服务体系中的一项主机产品，以解决了传统物理主机与虚拟专用服务器(Virtual Private Server，VPS)服务中，存在的管理难度大，业务扩展性弱的缺陷。

Claims (10)

  1. 一种神经通路的激活检测方法，包括：
    获取实验对象的待检测神经通路对应的刺激前场电位数据和刺激后场电位数据；
    基于所述刺激前场电位数据和所述刺激后场电位数据，确定所述待检测神经通路的连接强度变化数据；
    基于所述实验对象的待检测视频数据，确定所述实验对象的行为变化数据；
    基于所述连接强度变化数据和所述行为变化数据，确定所述待检测神经通路的激活状态。
  2. 根据权利要求1所述的方法，其中，所述基于所述连接强度变化数据和所述行为变化数据，确定所述待检测神经通路的激活状态，包括：
    在所述连接强度变化数据满足预设连接条件的情况下，判断预设行为变化数据集中是否存在所述行为变化数据；
    响应于所述预设行为变化数据集中存在所述行为变化数据，将所述待检测神经通路的激活状态设置为已激活状态；
    响应于所述预设行为变化数据集中不存在所述行为变化数据，将所述待检测神经通路的激活状态设置为未激活状态。
  3. 根据权利要求1所述的方法，其中，所述刺激前场电位数据包括所述待检测神经通路中的神经核团对中第一核团和第二核团分别对应的第一刺激前场电位数据和第二刺激前场电位数据，所述刺激后场电位数据包括所述神经核团对中第一核团和第二核团分别对应的第一刺激后场电位数据和第二刺激后场电位数据，所述基于所述刺激前场电位数据和所述刺激后场电位数据，确定所述待检测神经通路的连接强度变化数据，包括：
    基于所述第一刺激前场电位数据和所述第二刺激前场电位数据，确定所述神经核团对对应的刺激前连接强度；
    基于所述第一刺激后场电位数据和所述第二刺激后场电位数据，确定所述神经核团对对应的刺激后连接强度；
    基于所述刺激前连接强度和所述刺激后连接强度，确定所述待检测神经通路中所述神经核团对的连接强度变化数据。
  4. 根据权利要求3所述的方法，其中，所述获取实验对象的待检测神经通路对应的刺激前场电位数据和刺激后场电位数据，包括：
    获取所述待检测神经通路中的目标核团在预设时间段内的至少两个通道场 电位数据；
    对所述至少两个通道场电位数据分别执行降维操作，得到至少两个降维场电位数据，并将所述至少两个降维场电位数据中主成分最大的降维场电位数据对应的通道场电位数据作为所述目标核团对应的目标场电位数据；
    其中，在所述目标核团为所述第一核团且所述预设时间段为刺激前时间段的情况下，所述目标场电位数据为所述第一刺激前场电位数据，在所述目标核团为所述第一核团且所述预设时间段为刺激后时间段的情况下，所述目标场电位数据为所述第一刺激后场电位数据，在所述目标核团为所述第二核团且所述预设时间段为刺激前时间段的情况下，所述目标场电位数据为所述第二刺激前场电位数据，在所述目标核团为所述第二核团且所述预设时间段为刺激后时间段时，所述目标场电位数据为所述第二刺激后场电位数据。
  5. 根据权利要求3所述的方法，其中，所述刺激前连接强度或所述刺激后连接强度的参数类型为格兰杰因果关系值。
  6. 根据权利要求1所述的方法，在基于所述刺激前场电位数据和所述刺激后场电位数据，确定所述待检测神经通路的连接强度变化数据之前，还包括：
    对所述刺激前场电位数据和所述刺激后场电位数据分别执行预处理操作，得到预处理后的刺激前场电位数据和刺激后场电位数据；其中，所述预处理操作包括滤波操作和降采样操作中的至少之一。
  7. 根据权利要求1-6任一项所述的方法，其中，所述待检测视频数据包括至少三个视频采集设备分别采集到的视频数据，所述基于所述实验对象的待检测视频数据，确定所述实验对象的行为变化数据，包括：
    基于每个视频数据，确定所述每个视频数据中关键图像帧中实验对象的二维骨架数据；
    基于所述至少三个视频采集设备分别对应的摄像头参数数据以及所述至少三个视频采集设备分别采集到的视频数据中关键图像帧中的实验对象的二维骨架数据，确定所述实验对象的三维姿态数据，并基于所述三维姿态数据，确定所述实验对象的行为变化数据。
  8. 一种神经通路的激活检测装置，包括：
    场电位数据获取模块，设置为获取实验对象的待检测神经通路对应的刺激前场电位数据和刺激后场电位数据；
    连接强度变化数据确定模块，设置为基于所述刺激前场电位数据和所述刺激后场电位数据，确定所述待检测神经通路的连接强度变化数据；
    行为变化数据确定模块，设置为基于所述实验对象的待检测视频数据，确定所述实验对象的行为变化数据；
    激活状态确定模块，设置为基于所述连接强度变化数据和所述行为变化数据，确定所述待检测神经通路的激活状态。
  9. 一种电子设备，包括：
    至少一个处理器；以及
    与所述至少一个处理器通信连接的存储器；其中，
    所述存储器存储有可被所述至少一个处理器执行的计算机程序，所述计算机程序被所述至少一个处理器执行，以使所述至少一个处理器能够执行权利要求1-7中任一项所述的神经通路的激活检测方法。
  10. 一种计算机可读存储介质，存储有计算机指令，所述计算机指令用于使处理器执行时实现权利要求1-7中任一项所述的神经通路的激活检测方法。
PCT/CN2022/125245 2022-09-08 2022-10-14 神经通路的激活检测方法、装置、设备及存储介质 WO2024050920A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211094734.1A CN115414010A (zh) 2022-09-08 2022-09-08 一种神经通路的激活检测方法、装置、设备及存储介质
CN202211094734.1 2022-09-08

Publications (1)

Publication Number Publication Date
WO2024050920A1 true WO2024050920A1 (zh) 2024-03-14

Family

ID=84201378

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/125245 WO2024050920A1 (zh) 2022-09-08 2022-10-14 神经通路的激活检测方法、装置、设备及存储介质

Country Status (2)

Country Link
CN (1) CN115414010A (zh)
WO (1) WO2024050920A1 (zh)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101869093A (zh) * 2010-06-09 2010-10-27 中国科学院深圳先进技术研究院 果蝇行为学研究***及研究方法
CN109938727A (zh) * 2017-12-20 2019-06-28 中国科学院深圳先进技术研究院 非人灵长类动物三维视觉刺激实验***和方法
US20190299008A1 (en) * 2018-03-29 2019-10-03 University Of Washington Systems and methods for augmenting and/or restoring brain and nervous system function and inducing new neural connections using self-learning artificial networks
CN111839800A (zh) * 2020-07-27 2020-10-30 重庆医科大学附属第一医院 一种化学遗传癫痫持续状态疾病动物模型及其构建方法与应用
CN113080851A (zh) * 2021-03-26 2021-07-09 河北工业大学 基于格兰杰因果检测经颅磁刺激对工作记忆影响的方法
CN113712575A (zh) * 2021-07-16 2021-11-30 清华大学 一种全脑多模态神经活动探测的光电脑机接口***

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101869093A (zh) * 2010-06-09 2010-10-27 中国科学院深圳先进技术研究院 果蝇行为学研究***及研究方法
CN109938727A (zh) * 2017-12-20 2019-06-28 中国科学院深圳先进技术研究院 非人灵长类动物三维视觉刺激实验***和方法
US20190299008A1 (en) * 2018-03-29 2019-10-03 University Of Washington Systems and methods for augmenting and/or restoring brain and nervous system function and inducing new neural connections using self-learning artificial networks
CN111839800A (zh) * 2020-07-27 2020-10-30 重庆医科大学附属第一医院 一种化学遗传癫痫持续状态疾病动物模型及其构建方法与应用
CN113080851A (zh) * 2021-03-26 2021-07-09 河北工业大学 基于格兰杰因果检测经颅磁刺激对工作记忆影响的方法
CN113712575A (zh) * 2021-07-16 2021-11-30 清华大学 一种全脑多模态神经活动探测的光电脑机接口***

Also Published As

Publication number Publication date
CN115414010A (zh) 2022-12-02

Similar Documents

Publication Publication Date Title
EP4101371A1 (en) Electroencephalogram signal classifying method and apparatus, electroencephalogram signal classifying model training method and apparatus, and medium
EP2901342B1 (en) System for sensory and cognitive profiling
TWI686721B (zh) 登錄方法及裝置和電子設備
CN106569604B (zh) 视听双模态语义匹配和语义失配协同刺激脑机接口方法
CN111742332A (zh) 经由多预测模型架构进行异常检测的***和方法
TWI566746B (zh) 基於腦波建立預測模型的電子裝置
US20220047198A1 (en) Attention detection method and system
Yang et al. On the effectiveness of EEG signals as a source of biometric information
CN113723206B (zh) 一种基于量子神经网络算法的脑电波识别方法
WO2024050920A1 (zh) 神经通路的激活检测方法、装置、设备及存储介质
CN111223076A (zh) 神经***影像分析方法和装置
CN104793743B (zh) 一种虚拟社交***及其控制方法
Bastos et al. Discovering patterns in brain signals using decision trees
US20210298687A1 (en) Systems and methods for processing retinal signal data and identifying conditions
Shao et al. Clustering of heading selectivity and perception-related activity in the ventral intraparietal area
US11144123B2 (en) Systems and methods for human-machine subconscious data exploration
EP3733068B1 (en) Assessing cognitive reaction to over-the-air updates
WO2021037125A1 (zh) 对象识别方法及装置
CN108937925A (zh) 一种诱发脑电信号提取的方法、装置、设备及存储介质
Said et al. Spectral analysis and Bi-LSTM deep network-based approach in detection of mild cognitive impairment from electroencephalography signals
CN113842152B (zh) 脑电信号分类网络训练方法、分类方法、设备及存储介质
CN114220168A (zh) 行为与瞳孔信息同步分析方法、装置、设备及介质
WO2024108669A1 (zh) 觉醒状态检测***及方法
Evangelou et al. Electrophysiology and spike sorting on neuronal in vitro extracellular recordings with multi-modal CMOS multi-electrode array chip (Master Thesis)
Al-Darkazali et al. Spatial signatures for EEG-based biometric person recognition

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: 22957886

Country of ref document: EP

Kind code of ref document: A1