CN116491960A - Brain transient monitoring device, electronic device, and storage medium - Google Patents

Abstract

The application discloses a brain transient monitoring device, an electronic device and a storage medium. Collecting a plurality of original brain electrical signals of an object to be monitored at the current moment; tracing analysis is carried out on a plurality of original brain electrical signals based on the recombination matrix, so as to obtain a plurality of first brain power supply signals; intercepting brain electrical signals to be analyzed corresponding to the current moment from each first brain electrical source signal to obtain a plurality of brain electrical signals to be analyzed; processing a plurality of electroencephalogram signals to be analyzed to obtain a first delay autocovariance matrix; determining a plurality of first similarities between the first delay autocovariance matrix and a plurality of preset delay autocovariance matrices; determining the probability of various brain transients at the current moment according to the first similarity, the brain transients at the last moment, the transition probability matrixes of various brain transient states and the initial state probabilities of various brain transients; and determining the brain transient state at the current moment according to the probability of being in various brain transient states at the current moment.

Description

Translated fromChinese

脑瞬态监测设备、电子设备及存储介质Brain transient monitoring equipment, electronic equipment and storage medium

技术领域technical field

本申请涉及医疗技术领域，具体涉及一种脑瞬态监测设备、电子设备及存储介质。The present application relates to the field of medical technology, in particular to a brain transient monitoring device, an electronic device and a storage medium.

背景技术Background technique

人类大脑是一个复杂动态变化的非线性系统，由于大脑自发活动可以呈现为一些规律性的状态，并且这些状态与脑疾病的机制和发展密切关联，因此大脑活动状态的实时监测对于大脑疾病的评估和治疗具有极其重要的意义。The human brain is a complex and dynamically changing nonlinear system. Since the spontaneous activity of the brain can appear in some regular states, and these states are closely related to the mechanism and development of brain diseases, the real-time monitoring of brain activity status is essential for the evaluation of brain diseases and treatment are extremely important.

目前临床上应用最为广泛的基于脑电的脑状态监测技术是针对癫痫的视频脑电技术以及麻醉监护技术。视频脑电技术使用视频录像与脑电结合，同步观察癫痫发作的行为特征与脑电特征，进而确定癫痫类型。但是该技术只限于数据采集，脑状态的分析需要经验丰富的神经内科医生进行离线状态下的肉眼判断，这种监测受人工经验的影响，导致监测精度较低，并且无法对脑状态进行实时性监测，也无法在线对脑状态进行监测。麻醉监护技术一般通过脑电的计算实时评估麻醉深度并指导麻醉医生调整麻醉药物。但是这种技术只针对前额脑电进行监测和计算，不对全脑状态进行评估，并且该技术只利用一段时间内的脑电数据进行脑状态分析，导致脑状态监测精度较低，而且无法对脑状态进行实时性监测。At present, the most widely used EEG-based brain state monitoring technology is video EEG technology for epilepsy and anesthesia monitoring technology. Video EEG technology uses the combination of video recording and EEG to simultaneously observe the behavioral characteristics and EEG characteristics of epileptic seizures, and then determine the type of epilepsy. However, this technology is limited to data collection, and the analysis of the brain state requires experienced neurologists to judge with the naked eye in an offline state. This monitoring is affected by manual experience, resulting in low monitoring accuracy and the inability to monitor the brain state in real time. monitoring, and the brain status cannot be monitored online. Anesthesia monitoring technology generally evaluates the depth of anesthesia in real time through EEG calculations and guides anesthesiologists to adjust anesthesia drugs. However, this technology only monitors and calculates the forehead EEG, and does not evaluate the state of the whole brain. Moreover, this technology only uses EEG data within a period of time for brain state analysis, resulting in low accuracy of brain state monitoring and inability to evaluate brain state. The status is monitored in real time.

因此，如何进行实时在线监测大脑的脑状态，以及提高大脑的脑状态的监测精度是目前亟待解决的技术问题。Therefore, how to monitor the brain state of the brain online in real time and improve the monitoring accuracy of the brain state of the brain are currently technical problems to be solved urgently.

发明内容Contents of the invention

本申请实施例提供了一种脑瞬态监测设备、电子设备及存储介质，通过离线处理的参数，并结合上一时刻的脑瞬态，提高了脑瞬态监测的精度，以及能够实时在线进行脑状态监测。The embodiment of the present application provides a brain transient monitoring device, electronic equipment, and storage medium. Through offline processing parameters, combined with the brain transient at the previous moment, the accuracy of brain transient monitoring is improved, and real-time online monitoring can be performed. Brain state monitoring.

第一方面，本申请实施例提供一种脑瞬态监测设备，所述脑瞬态监测设备包括图像获取模块、离线处理模块、脑电采集模块和脑瞬态分析模块；In the first aspect, an embodiment of the present application provides a brain transient monitoring device, which includes an image acquisition module, an offline processing module, an EEG acquisition module, and a brain transient analysis module;

所述图像获取模块，用于获取待监测对象的脑部的原始核磁共振图像；The image acquisition module is used to acquire the original nuclear magnetic resonance image of the brain of the subject to be monitored;

所述脑电采集模块，用于在预设时间段内在多个通道上采集所述待监测对象的多个离线脑电信号；The EEG collection module is used to collect multiple offline EEG signals of the subject to be monitored on multiple channels within a preset time period;

所述离线处理模块，用于基于所述原始核磁共振图像，得到所述待监测对象的三维脑模型；The offline processing module is used to obtain a three-dimensional brain model of the subject to be monitored based on the original nuclear magnetic resonance image;

获取所述三维脑模型中的多个皮层网格；将所述多个通道上用于脑电信号采集的多个电极在所述待监测对象的脑部的位置与所述多个皮层网格在脑部的位置进行对齐，得到与所述待监测对象对应的Lead-field矩阵；Acquiring a plurality of cortical grids in the three-dimensional brain model; combining the positions of the plurality of electrodes used for EEG signal acquisition on the plurality of channels in the brain of the subject to be monitored with the plurality of cortical grids Aligning at the position of the brain to obtain a Lead-field matrix corresponding to the object to be monitored;

获取所述多个离线脑电信号的协方差矩阵；Obtaining the covariance matrix of the plurality of offline EEG signals;

基于所述协方差矩阵以及所述Lead-field矩阵，确定重组矩阵；Determine a recombination matrix based on the covariance matrix and the Lead-field matrix;

基于所述Lead-field矩阵，对所述多个离线脑电信号进行逆分解，得到所述多个皮层网格对应的多个皮层信号；将所述三维脑模型划分为多个源极子；Based on the Lead-field matrix, inversely decomposing the plurality of off-line EEG signals to obtain a plurality of cortical signals corresponding to the plurality of cortical grids; dividing the three-dimensional brain model into a plurality of source subunits;

对所述多个皮层信号进行加权映射，得到与所述多个源极子对应的多个第二脑电源信号；performing weighted mapping on the plurality of cortical signals to obtain a plurality of second brain power supply signals corresponding to the plurality of source electrodes;

基于预设时间窗口，对每个第二脑电源信号进行多次加窗，以对每个第二脑电源信号进行分割，得到与每个第二脑电源信号对应的多个子脑电源信号；Based on the preset time window, windowing is performed multiple times on each second brain power signal to segment each second brain power signal to obtain multiple sub-brain power signals corresponding to each second brain power signal;

基于每个第二脑电源信号对应的多个子脑电源信号，得到多个预设延时自协方差矩阵、多种脑瞬态之间的状态转移概率矩阵以及所述多种脑瞬态对应的初始状态概率，其中，每个预设延时自协方差矩阵用于表征一种脑瞬态；Based on the multiple sub-brain power signals corresponding to each second brain power signal, a plurality of preset delay autocovariance matrices, state transition probability matrices between various brain transient states, and the state transition probability matrices corresponding to the various brain transient states are obtained. initial state probabilities, wherein each preset time-delayed autocovariance matrix is used to characterize a brain transient state;

所述脑电采集模块，用于在当前时刻从多个通道上采集待监测对象的多个原始脑电信号；The EEG collection module is used to collect a plurality of original EEG signals of the object to be monitored from multiple channels at the current moment;

所述脑瞬态分析模块，用于基于所述重组矩阵对所述多个原始脑电信号进行溯源分析，得到多个第一脑电源信号；The brain transient analysis module is used to perform traceability analysis on the multiple original EEG signals based on the recombination matrix to obtain multiple first EEG signals;

从每个第一脑电源信号中截取与当前时刻对应的待分析脑电信号，得到多个待分析脑电信号；Intercepting the EEG signals to be analyzed corresponding to the current moment from each first EEG signal to obtain a plurality of EEG signals to be analyzed;

对所述多个待分析脑电信号进行处理，得到第一延时自协方差矩阵；Processing the plurality of EEG signals to be analyzed to obtain a first time-delayed autocovariance matrix;

确定所述第一延时自协方差矩阵与所述多个预设延时自协方差矩阵之间的相似度，得到多个第一相似度；Determining the similarity between the first delayed autocovariance matrix and the plurality of preset delayed autocovariance matrices to obtain a plurality of first similarities;

根据所述多个第一相似度、所述待监测对象在上一时刻的脑瞬态、所述状态转移概率矩阵以及所述初始状态概率，确定所述待监测对象当前时刻处于各种脑瞬态的概率；According to the plurality of first similarities, the brain transient state of the object to be monitored at the previous moment, the state transition probability matrix, and the initial state probability, it is determined that the object to be monitored is currently in various brain transient states. state probability;

根据当前时刻处于各种脑瞬态的概率，确定所述待监测对象在当前时刻的脑瞬态。According to the probability of being in various brain transient states at the current moment, the brain transient state of the subject to be monitored at the current moment is determined.

第二方面，本申请实施例提供一种脑瞬态监测方法，所述方法应用于所述脑瞬态监测设备，所述脑瞬态监测设备包括图像获取模块、离线处理模块、脑电采集模块和脑瞬态分析模块；所述方法包括：In the second aspect, an embodiment of the present application provides a brain transient monitoring method, the method is applied to the brain transient monitoring device, and the brain transient monitoring device includes an image acquisition module, an offline processing module, and an EEG acquisition module and a brain transient analysis module; the method comprising:

获取待监测对象的脑部的原始核磁共振图像；Obtaining raw MRI images of the brain of the subject to be monitored;

在预设时间段内在多个通道上采集所述待监测对象的多个离线脑电信号；collecting multiple offline EEG signals of the subject to be monitored on multiple channels within a preset time period;

基于所述原始核磁共振图像，得到所述待监测对象的三维脑模型；Obtaining a three-dimensional brain model of the subject to be monitored based on the original nuclear magnetic resonance image;

获取所述三维脑模型中的多个皮层网格；将所述多个通道上用于脑电信号采集的多个电极在所述待监测对象的脑部的位置与所述多个皮层网格在脑部的位置进行对齐，得到与所述待监测对象对应的Lead-field矩阵；Acquiring a plurality of cortical grids in the three-dimensional brain model; combining the positions of the plurality of electrodes used for EEG signal acquisition on the plurality of channels in the brain of the subject to be monitored with the plurality of cortical grids Aligning at the position of the brain to obtain a Lead-field matrix corresponding to the object to be monitored;

获取所述多个离线脑电信号的协方差矩阵；Obtaining the covariance matrix of the plurality of offline EEG signals;

基于所述协方差矩阵以及所述Lead-field矩阵，确定重组矩阵；Determine a recombination matrix based on the covariance matrix and the Lead-field matrix;

基于所述Lead-field矩阵，对所述多个离线脑电信号进行逆分解，得到所述多个皮层网格对应的多个皮层信号；将所述三维脑模型划分为多个源极子；Based on the Lead-field matrix, inversely decomposing the plurality of off-line EEG signals to obtain a plurality of cortical signals corresponding to the plurality of cortical grids; dividing the three-dimensional brain model into a plurality of source subunits;

对所述多个皮层信号进行加权映射，得到与所述多个源极子对应的多个第二脑电源信号；performing weighted mapping on the plurality of cortical signals to obtain a plurality of second brain power supply signals corresponding to the plurality of source electrodes;

基于预设时间窗口，对每个第二脑电源信号进行多次加窗，以对每个第二脑电源信号进行分割，得到与每个第二脑电源信号对应的多个子脑电源信号；Based on the preset time window, windowing is performed multiple times on each second brain power signal to segment each second brain power signal to obtain multiple sub-brain power signals corresponding to each second brain power signal;

基于每个第二脑电源信号对应的多个子脑电源信号，得到多个预设延时自协方差矩阵、多种脑瞬态之间的状态转移概率矩阵以及所述多种脑瞬态对应的初始状态概率，其中，每个预设延时自协方差矩阵用于表征一种脑瞬态；Based on the multiple sub-brain power signals corresponding to each second brain power signal, a plurality of preset delay autocovariance matrices, state transition probability matrices between various brain transient states, and the state transition probability matrices corresponding to the various brain transient states are obtained. initial state probabilities, wherein each preset time-delayed autocovariance matrix is used to characterize a brain transient state;

在当前时刻从多个通道上采集待监测对象的多个原始脑电信号；Collect multiple original EEG signals of the object to be monitored from multiple channels at the current moment;

基于所述重组矩阵对所述多个原始脑电信号进行溯源分析，得到多个第一脑电源信号；performing traceability analysis on the plurality of original EEG signals based on the recombination matrix to obtain a plurality of first EEG signals;

从每个第一脑电源信号中截取与当前时刻对应的待分析脑电信号，得到多个待分析脑电信号；Intercepting the EEG signals to be analyzed corresponding to the current moment from each first EEG signal to obtain a plurality of EEG signals to be analyzed;

对所述多个待分析脑电信号进行处理，得到第一延时自协方差矩阵；Processing the plurality of EEG signals to be analyzed to obtain a first time-delayed autocovariance matrix;

确定所述第一延时自协方差矩阵与所述多个预设延时自协方差矩阵之间的相似度，得到多个第一相似度；Determining the similarity between the first delayed autocovariance matrix and the plurality of preset delayed autocovariance matrices to obtain a plurality of first similarities;

根据所述多个第一相似度、所述待监测对象在上一时刻的脑瞬态、所述状态转移概率矩阵以及所述初始状态概率，确定所述待监测对象当前时刻处于各种脑瞬态的概率；According to the plurality of first similarities, the brain transient state of the object to be monitored at the previous moment, the state transition probability matrix, and the initial state probability, it is determined that the object to be monitored is currently in various brain transient states. state probability;

根据当前时刻处于各种脑瞬态的概率，确定所述待监测对象在当前时刻的脑瞬态。According to the probability of being in various brain transient states at the current moment, the brain transient state of the subject to be monitored at the current moment is determined.

第三方面，本申请提供一种电子设备，包括：处理器和存储器，所述处理器与存储器相连，所述存储器用于存储计算机程序，所述处理器用于执行所述存储器中存储的计算机程序，以使得所述电子设备执行如第二方面所述的方法。In a third aspect, the present application provides an electronic device, including: a processor and a memory, the processor is connected to the memory, the memory is used to store computer programs, and the processor is used to execute the computer programs stored in the memory , so that the electronic device executes the method described in the second aspect.

第四方面，本申请提供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程序，所述计算机程序使得计算机执行如第二方面所述的方法。In a fourth aspect, the present application provides a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and the computer program causes a computer to execute the method as described in the second aspect.

第五方面，本申请提供一种计算机程序产品，所述计算机程序产品包括存储了计算机程序的非瞬时性计算机可读存储介质，所述计算机可操作来使计算机执行如第二方面所述的方法。In a fifth aspect, the present application provides a computer program product, the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer is operable to cause the computer to execute the method as described in the second aspect .

实施本申请实施例，具有如下有益效果：Implementing the embodiment of the present application has the following beneficial effects:

可以看出，在本申请实施例中，首先离线计算出脑电信号到脑电源信号的重组矩阵，以及用于表征脑瞬态的预设延时自协方差矩阵，以及多种脑瞬态之间的状态转移概率矩阵，以及多种脑瞬态的初始状态概率，这样进行实时的在线监测时，可以利用离线计算好的重组矩阵，直接对在线采集到的多个原始脑电信号进行溯源，得到多个第一脑电源信号；以及从每个第一脑电源信号中截取与当前时刻对应的待分析脑电信号，得到多个待分析脑电信号，并获取多个待分析脑电信号对应的第一延时自协方差矩阵。然后，直接使用多个预设延时自协方差矩阵，确定出多个第一相似度。最后，直接基于多个第一相似度、待监测对象在上一时刻的脑瞬态、多种脑瞬态之间的状态转移概率矩阵、多种脑瞬态对应的初始状态概率，确定出待监测对象当前时刻处于各种脑瞬态的概率，进而确定出当前时刻的脑状态。由于在线监测的大部分复杂参数都是离线计算好的，大幅度的减轻了在线计算的复杂度，因此在线监测时可以快速地计算出当前时刻的脑状态，从而实现实时在线地监测大脑的脑状态。并且在确定当前时刻的脑瞬态时，不会只利用当前时刻下的脑电信号，与各种脑瞬态之间的相似度，还会结合上一个时刻的脑瞬态，以及多种脑瞬态之间的转移概率，从而可以精确地确定出当前时刻的脑瞬态，提高了对脑瞬态的监测精度。It can be seen that in the embodiment of the present application, the recombination matrix from the EEG signal to the EEG signal, the preset time-delay autocovariance matrix used to characterize the brain transient, and the various brain transients are firstly calculated offline. The inter-state transition probability matrix, as well as the initial state probabilities of various brain transients, so that when performing real-time online monitoring, the offline calculated recombination matrix can be used to directly trace the source of multiple original EEG signals collected online. Obtaining a plurality of first brain power signals; and intercepting the EEG signals to be analyzed corresponding to the current moment from each first EEG signal to obtain a plurality of EEG signals to be analyzed, and obtaining the corresponding EEG signals to be analyzed The first time-delayed autocovariance matrix of . Then, multiple first similarities are determined by directly using multiple preset delay autocovariance matrices. Finally, directly based on multiple first similarities, the brain transient state of the object to be monitored at the last moment, the state transition probability matrix between various brain transient states, and the initial state probabilities corresponding to various brain transient states, determine the The probability that the subject is in various brain transients at the current moment is monitored, and then the brain state at the current moment is determined. Since most of the complex parameters of online monitoring are calculated offline, the complexity of online calculation is greatly reduced, so the current brain state can be quickly calculated during online monitoring, so as to realize real-time online monitoring of the brain. state. And when determining the brain transient at the current moment, it will not only use the EEG signal at the current moment, and the similarity between various brain transients, but also combine the brain transient at the previous moment and various brain transients. The transition probability between transient states can accurately determine the brain transient state at the current moment, which improves the monitoring accuracy of the brain transient state.

附图说明Description of drawings

为了更清楚地说明本申请实施例中的技术方案，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。In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings that need to be used in the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are some embodiments of the present application. For Those of ordinary skill in the art can also obtain other drawings based on these drawings without making creative efforts.

图1为本申请实施例提供的一种脑瞬态监测的场景示意图；FIG. 1 is a schematic diagram of a scene of brain transient monitoring provided by an embodiment of the present application;

图2为本申请实施例提供的一种脑瞬态监测设备的示意图；FIG. 2 is a schematic diagram of a brain transient monitoring device provided in an embodiment of the present application;

图3为本申请实施例提供的一种基于预设时间窗口获取每个第二脑电源信号对应的多个子脑电源信号的示意图；Fig. 3 is a schematic diagram of obtaining multiple sub-brain power signals corresponding to each second brain power signal based on a preset time window provided by the embodiment of the present application;

图4为本申请实施例提供的一种获取每个时间窗口的第二延时自协方差矩阵的示意图；FIG. 4 is a schematic diagram of obtaining a second delayed autocovariance matrix for each time window provided by an embodiment of the present application;

图5为本申请实施例提供的一种脑瞬态监测的示意图；Fig. 5 is a schematic diagram of a brain transient monitoring provided by the embodiment of the present application;

图6为本申请实施例提供的一种脑瞬态监测方法的流程示意图；FIG. 6 is a schematic flowchart of a brain transient monitoring method provided in an embodiment of the present application;

图7为本申请实施例提供的一种电子设备的示意图。FIG. 7 is a schematic diagram of an electronic device provided by an embodiment of the present application.

具体实施方式Detailed ways

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清楚、完整地描述，显然，所描述的实施例是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of this application.

本申请的说明书和权利要求书及所述附图中的术语“第一”、“第二”、“第三”和“第四”等是用于区别不同对象，而不是用于描述特定顺序。此外，术语“包括”和“具有”以及它们任何变形，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、系统、产品或设备没有限定于已列出的步骤或单元，而是可选地还包括没有列出的步骤或单元，或可选地还包括对于这些过程、方法、产品或设备固有的其它步骤或单元。The terms "first", "second", "third" and "fourth" in the specification and claims of the present application and the drawings are used to distinguish different objects, rather than to describe a specific order . Furthermore, the terms "include" and "have", as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units is not limited to the listed steps or units, but optionally also includes unlisted steps or units, or optionally further includes For other steps or units inherent in these processes, methods, products or apparatuses.

在本文中提及“实施例”意味着，结合实施例描述的特定特征、结果或特性可以包含在本申请的至少一个实施例中。在说明书中的各个位置出现该短语并不一定均是指相同的实施例，也不是与其它实施例互斥的独立的或备选的实施例。本领域技术人员显式地和隐式地理解的是，本文所描述的实施例可以与其它实施例相结合。Reference herein to an "embodiment" means that a particular feature, result, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present application. The occurrences of this phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is understood explicitly and implicitly by those skilled in the art that the embodiments described herein can be combined with other embodiments.

参阅图1，图1为本申请实施例提供的一种脑瞬态监测的场景示意图。Referring to FIG. 1 , FIG. 1 is a schematic diagram of a brain transient monitoring scenario provided by an embodiment of the present application.

如图1所示，脑瞬态监测设备通过放置在待监测对象的脑皮层的电极（图1中脑皮层的圆圈）在当前时刻从多个通道上采集待监测对象的多个原始脑电信号；然后，基于离线处理得到的重组矩阵对所述多个原始脑电信号进行溯源分析，得到多个第一脑电源信号。然后，从每个第一脑电源信号中截取与当前时刻对应的待分析脑电信号，得到多个待分析脑电信号；对所述多个待分析脑电信号进行处理，得到第一延时自协方差矩阵；确定所述第一延时自协方差矩阵与多个预设延时自协方差矩阵之间的相似度，得到多个第一相似度，其中，每个预设延时自协方差矩阵用于表征一种脑瞬态；根据所述多个第一相似度、所述待监测对象在上一时刻的脑瞬态、多种脑瞬态之间的状态转移概率矩阵、所述多种脑瞬态对应的初始状态概率，确定所述待监测对象当前时刻处于各种脑瞬态的概率；根据当前时刻处于各种脑瞬态的概率，确定所述待监测对象在当前时刻的脑瞬态。最后，可以在脑瞬态监测设备显示界面显示待监测对象在当前时刻的脑瞬态。As shown in Figure 1, the brain transient monitoring device collects multiple original EEG signals of the subject to be monitored from multiple channels at the current moment through electrodes placed on the cortex of the subject to be monitored (the circle of the cortex in Figure 1) ; Then, perform traceability analysis on the plurality of original EEG signals based on the recombination matrix obtained by off-line processing, and obtain a plurality of first EEG power signals. Then, intercept the EEG signals to be analyzed corresponding to the current moment from each first EEG signal to obtain a plurality of EEG signals to be analyzed; process the plurality of EEG signals to obtain the first time delay Auto-covariance matrix; determine the similarity between the first delayed auto-covariance matrix and multiple preset delayed auto-covariance matrices to obtain multiple first similarities, wherein each preset delayed auto-covariance matrix The covariance matrix is used to characterize a brain transient; according to the multiple first similarities, the brain transient of the object to be monitored at the last moment, the state transition probability matrix between multiple brain transients, and the According to the initial state probabilities corresponding to the multiple brain transient states, the probability that the object to be monitored is in various brain transient states at the current moment is determined; according to the probability of being in various brain transient states at the current moment, it is determined that the object to be monitored is at the current moment brain transient. Finally, the brain transient of the subject to be monitored at the current moment can be displayed on the display interface of the brain transient monitoring device.

应说明，本申请所提到的脑瞬态也可以称为脑状态，两者在本质上是一致的，可以不用区分。It should be noted that the brain transient mentioned in this application can also be called the brain state, and the two are essentially the same and need not be distinguished.

参阅图2，图2为本申请实施例提供的一种脑瞬态监测设备的示意图。如图2所示，脑瞬态监测设备包括：脑电采集模块、脑瞬态分析模块、图像获取模块和离线处理模块。Referring to FIG. 2 , FIG. 2 is a schematic diagram of a brain transient monitoring device provided by an embodiment of the present application. As shown in Figure 2, the brain transient monitoring equipment includes: an EEG acquisition module, a brain transient analysis module, an image acquisition module and an offline processing module.

为了便于理解本申请的技术方案，首先对本申请的离线处理过程进行解释和说明。In order to facilitate the understanding of the technical solution of the present application, firstly, the offline processing process of the present application is explained and illustrated.

本申请的离线处理过程，主要是为了准备在线脑瞬态监测所需的参数。其中，在线脑瞬态所需的参数至少包括：重组矩阵、每种脑瞬态对应的预设延时自协方差矩阵、多种脑瞬态之间的状态转移概率矩阵以及多种脑瞬态对应的初始状态概率。The offline processing process of this application is mainly to prepare the parameters required for online brain transient monitoring. Among them, the parameters required for online brain transients include at least: a reorganization matrix, a preset delay autocovariance matrix corresponding to each brain transient, a state transition probability matrix between various brain transients, and a variety of brain transients The corresponding initial state probabilities.

下面结合附图说明本申请的离线处理过程。The offline processing process of the present application will be described below with reference to the accompanying drawings.

示例性的，图像获取模块用于获取待监测对象的脑部的原始核磁共振图像（Magnetic Resonance Imaging，MRI）。Exemplarily, the image acquisition module is used to acquire an original MRI image (Magnetic Resonance Imaging, MRI) of the brain of the subject to be monitored.

脑电采集模块，用于在预设时间段内在多个通道上采集待监测对象的多个离线脑电信号；该预设时间段可以是对待监测对象进行脑瞬态在线监测之前的一个时间段。例如，在待监测对象的脑部安装好电极（即采集脑电信号的脑电电极），且t时刻准备对待监测对象进行脑瞬态监测，则可以在位于t时刻之前的一个预设时间段内采集待监测对象的多个脑电信号，作为多个离线脑电信号进行离线分析。当然，预设时间段可以为进行脑瞬态监测之前的任意一个时间段，比如，在t时刻之前的任意一个预设时间段，本申请不对预设时间段进行具体限定。然后，离线处理模块用于基于核磁共振图像和多个离线脑电信号，确定多个预设延时自协方差矩阵、重组矩阵、状态转移概率矩阵以及初始状态概率。The EEG acquisition module is used to collect multiple offline EEG signals of the object to be monitored on multiple channels within a preset time period; the preset time period can be a time period before the on-line brain transient monitoring of the object to be monitored . For example, if the electrodes (i.e. EEG electrodes for collecting EEG signals) are installed on the brain of the subject to be monitored, and the subject to be monitored is ready for brain transient monitoring at time t, then a preset period of time before time t can be The multiple EEG signals of the subject to be monitored are collected internally and analyzed offline as multiple offline EEG signals. Of course, the preset time period may be any time period before brain transient monitoring, for example, any preset time period before time t, and this application does not specifically limit the preset time period. Then, the offline processing module is used to determine a plurality of preset time-delayed autocovariance matrices, recombination matrices, state transition probability matrices, and initial state probabilities based on the MRI images and a plurality of offline EEG signals.

具体地，离线处理模块先基于原始核磁共振图像，得到所述待监测对象的三维脑模型。具体地，离线处理模块对原始核磁共振图像进行重切片，得到目标核磁共振图像。然后，离线处理模块对目标核磁共振图像进行分割，得到脑组织、颅骨以及头皮，并基于所述分割出脑组织、颅骨以及头皮的所述目标核磁共振图像进行脑模型建立，即基于该目标核磁共振图像，以及使用各向一致性的传导参数建立信号传导正向脑模型，得到待监测对象的三维脑模型。然后，离线处理模块获取三维脑模型中的所有皮层网格，并对所有皮层网格进行降采样（即减少皮层网格的数量），并在降采样后将皮层网络与标准脑模型的皮层网格进行匹配校准，得到多个皮层网格。应说明，随着算力的不断提升，若离线处理模块能够处理的皮层网格的数量不受限制，则可以不用对皮层网格进行降采样，仅需对所有皮层网格进行校准即可。本申请中主要以降采样以及校准后得到的多个皮层网格为例进行说明。Specifically, the offline processing module first obtains the three-dimensional brain model of the subject to be monitored based on the original nuclear magnetic resonance image. Specifically, the offline processing module re-slices the original nuclear magnetic resonance image to obtain the target nuclear magnetic resonance image. Then, the offline processing module segments the target nuclear magnetic resonance image to obtain brain tissue, skull and scalp, and establishes a brain model based on the target nuclear magnetic resonance image of the segmented brain tissue, skull and scalp, that is, based on the target nuclear magnetic resonance image Resonance images, and the use of isotropically consistent conduction parameters to establish a forward brain model of signal conduction to obtain a three-dimensional brain model of the subject to be monitored. Then, the offline processing module obtains all the cortical grids in the 3D brain model, and downsamples all the cortical grids (that is, reduces the number of cortical grids), and compares the cortical network with the cortical network of the standard brain model after downsampling Grids are matched and calibrated to obtain multiple cortical grids. It should be noted that with the continuous improvement of computing power, if the number of cortical grids that can be processed by the offline processing module is not limited, it is not necessary to down-sample the cortical grids, and only need to calibrate all the cortical grids. In this application, multiple cortical grids obtained after downsampling and calibration are mainly used as an example for illustration.

然后，离线处理模块获取多个通道上用于脑电信号采集的多个电极在待监测对象的脑部的位置，以及多个皮层网格在待监测对象的脑部的位置，并将这两个位置进行对齐，得到与待监测对象对应的Lead-field矩阵（也可称为导联场矩阵）。最后，离线处理模块获取该多个离线脑电信号的协方差矩阵。例如，将每个离线脑电信号在各个时刻的幅值作为矩阵中的一行或一列元素，可得到第一幅值矩阵。基于该第一幅值矩阵，得到该多个离线脑电信号的协方差矩阵。最后，离线处理模块基于该Lead-field矩阵和该协方差矩阵，得到重组矩阵。Then, the off-line processing module acquires the positions of multiple electrodes used for EEG signal acquisition on multiple channels in the brain of the subject to be monitored, and the positions of multiple cortical grids in the brain of the subject to be monitored, and combines the two positions are aligned to obtain the Lead-field matrix (also called the lead field matrix) corresponding to the object to be monitored. Finally, the offline processing module obtains the covariance matrix of the plurality of offline EEG signals. For example, the first magnitude matrix can be obtained by taking the magnitude of each offline EEG signal at each moment as a row or a column of elements in the matrix. Based on the first magnitude matrix, a covariance matrix of the plurality of offline EEG signals is obtained. Finally, the offline processing module obtains a recombination matrix based on the Lead-field matrix and the covariance matrix.

示例性的，重组矩阵可以通过公式（1）表示：Exemplarily, the reorganization matrix can be expressed by formula (1):

公式（1）； Formula 1);

其中，W为重组矩阵，R上述协方差矩阵，L为上述Lead-field矩阵，T为转置操作。Among them, W is the reorganization matrix, R is the above covariance matrix, L is the above Lead-field matrix, and T is the transposition operation.

应说明，重组矩阵主要用于对脑电信号进行逆向分解，即将脑电信号分解到多个源极子对应的多个脑电源信号。由于对于一个个体来说，脑电信号的逆向分解主要与所使用的正向脑模型、电极位置、Lead-field矩阵和脑电信号的噪声水平相关。因此针对同一个个体，在相同的脑电环境（即电极位置相同以及使用的脑模型相同）下，则每次采集到的脑电信号逆向分解所使用的重组矩阵是相同的，也就是将每次采集到的脑电信号乘以该重组矩阵即可完成从脑电信号到脑电源信号的逆向分解。It should be noted that the recombination matrix is mainly used for decomposing the EEG signal in reverse, that is, decomposing the EEG signal into multiple EEG power signals corresponding to multiple source electrodes. For an individual, the reverse decomposition of the EEG signal is mainly related to the used forward brain model, electrode position, lead-field matrix and the noise level of the EEG signal. Therefore, for the same individual, under the same EEG environment (that is, the same electrode position and the same brain model used), the recombination matrix used for the reverse decomposition of the EEG signals collected each time is the same, that is, each The reverse decomposition from EEG signal to EEG signal can be completed by multiplying the EEG signal collected for the first time by the recombination matrix.

应说明，本申请中在线脑瞬态监测和离线处理过程，对待监测对象所使用的脑电环境是相同，即所使用的脑模型、电极位置都是相同的。这样也就保证本申请后续在线进行脑瞬态监测时，可以使用离线分析出的重组矩阵直接进行脑电信号到脑电源信号的逆分解，无需再次计算重组矩阵。It should be noted that the EEG environment used by the subject to be monitored is the same during the online transient brain monitoring and offline processing in this application, that is, the brain model and electrode positions used are the same. This also ensures that when the application conducts brain transient monitoring online later, the reorganization matrix analyzed offline can be used to directly decompose the EEG signal to the EEG power signal without recalculating the recombination matrix.

进一步地，在得到Lead-field矩阵后，离线处理模块还基于该Lead-field矩阵，对多个离线脑电信号进行逆分解，得到多个皮层网格对应的多个皮层信号，即使用该Lead-field矩阵，通过线性约束最小方差算法对该多个离线脑电信号进行逆分解，得到多个皮层信号。Further, after obtaining the Lead-field matrix, the offline processing module also performs inverse decomposition on multiple offline EEG signals based on the Lead-field matrix to obtain multiple cortical signals corresponding to multiple cortical grids, that is, using the Lead The -field matrix is used to inversely decompose the multiple offline EEG signals through the linear constraint minimum variance algorithm to obtain multiple cortical signals.

然后，离线处理模块将三维脑模型划分为多个源极子，即将脑模型中的一块皮层区域划分为一个源极子，可得到多个源极子。然后，对多个皮层信号进行加权映射，得到与多个源极子对应的多个第二脑电源信号。可选地，可以使用主成分分析方法，将多个皮层信号进行加权映射，得到多个第二脑电信号。可选地，在对多个皮层信号进行加权映射后，还需要对加权映射得到的脑电信号的空间泄露和源极子极性进行校正，将校正后的脑电信号作为多个第二脑电信号。Then, the offline processing module divides the three-dimensional brain model into multiple source subunits, that is, divides a cortical area in the brain model into one source subunit, and multiple source subunits can be obtained. Then, weighted mapping is performed on the plurality of cortical signals to obtain a plurality of second brain power supply signals corresponding to the plurality of source electrodes. Optionally, a principal component analysis method may be used to perform weighted mapping on multiple cortical signals to obtain multiple second EEG signals. Optionally, after performing weighted mapping on multiple cortical signals, it is also necessary to correct the spatial leakage and source polarity of the EEG signals obtained by the weighted mapping, and use the corrected EEG signals as multiple second brain signals. electric signal.

最后，离线处理模块基于预设时间窗口和所述多个第二脑电源信号，得到多个预设延时自协方差矩阵、多种脑瞬态之间的状态转移概率矩阵以及所述多种脑瞬态对应的初始状态概率，其中，每个预设延时自协方差矩阵用于表征一种脑瞬态。Finally, based on the preset time window and the multiple second brain power signals, the offline processing module obtains multiple preset delay autocovariance matrices, state transition probability matrices between multiple brain transients, and the multiple The initial state probability corresponding to the brain transient, where each preset delay autocovariance matrix is used to characterize a brain transient.

具体地，离线处理模块基于预设时间窗口，对每个第二脑电源信号进行多次加窗，以对每个第二脑电源信号进行分割，得到与每个第二脑电源信号对应的多个子脑电源信号。如图3所示，以预设时间窗口在每个第二脑电源信号上进行滑动，这样在滑动过程中就会产生多个时间窗口，并且每个时间窗口会从第二脑电源信号上分割出一个子脑电源信号。基于每个第二脑电源信号对应的多个子脑电源信号，确定多个预设延时自协方差矩阵、状态转移概率矩阵以及初始状态概率。Specifically, the offline processing module performs multiple windowing on each second brain power signal based on a preset time window, so as to segment each second brain power signal to obtain multiple Brain power signal. As shown in Figure 3, slide on each second brain power signal with a preset time window, so that multiple time windows will be generated during the sliding process, and each time window will be divided from the second brain power signal Send out a sub-brain power signal. Based on the multiple sub-brain power signals corresponding to each second brain power signal, multiple preset delay autocovariance matrices, state transition probability matrices, and initial state probabilities are determined.

具体地，离线处理模块获取多个第二脑电源信号在每个时间窗口下的多个子脑电源信号对应的第二延时自协方差矩阵，即获取该多个子脑电源信号的自协方差矩阵，其中，由于该多个子脑电源信号是从不同脑皮层区域的采集到的，并且该多个子脑电源信号是在一个时间窗口下的脑电信号，因此，该第二延时自协方差矩阵同时包含了空间维度和时间维度上的脑节律信息。举例来说，如图4所示，针对第一个时间窗口，获取每个第二脑电源信号在该第一个时间窗口下的子脑电源信号，可得到在第一个时间窗口下的多个子脑电源信号。然后，将每个子脑电源信号在各个时刻的幅值作为矩阵中的一行或者一列的元素，可得到与第一个时间窗口对应的第二幅值矩阵。然后，基于该第二幅值矩阵，得到与第一个时间窗口对应的第二延时自协方差矩阵。最后，针对每个时间窗口，可获取与每个时间窗口下的第二延时自协方差矩阵，进而得到多次加窗对应的多个时间窗口下的多个第二延时自协方差矩阵。Specifically, the offline processing module obtains the second delayed autocovariance matrix corresponding to the multiple sub-brain power supply signals of the multiple second brain power supply signals in each time window, that is, obtains the autocovariance matrix of the multiple sub-brain power supply signals , wherein, since the multiple sub-brain power signals are collected from different cortical areas, and the multiple sub-brain power signals are EEG signals in a time window, the second time-delayed autocovariance matrix It also contains brain rhythm information in both spatial and temporal dimensions. For example, as shown in Figure 4, for the first time window, the sub-brain power supply signals of each second brain power supply signal under the first time window can be obtained, and the multiple brain power supply signals under the first time window can be obtained. Brain power signal. Then, the amplitude of each sub-brain power supply signal at each moment is taken as an element of a row or a column in the matrix, and a second amplitude matrix corresponding to the first time window can be obtained. Then, based on the second magnitude matrix, a second time-delayed autocovariance matrix corresponding to the first time window is obtained. Finally, for each time window, the second time-delay autocovariance matrix under each time window can be obtained, and then multiple second time-delay autocovariance matrices under multiple time windows corresponding to multiple windowing can be obtained .

进一步地，离线处理模块对多个第二延时自协方差矩阵进行分组，得到多个延时自协方差矩阵组，其中，每个延时自协方差矩阵组包括该多个第二延时自协方差矩阵中的一个或多个。例如，离线处理模块可以对多个第二延时自协方差矩阵进行聚类，得到多个延时自协方差矩阵组。然后，获取每个延时自协方差矩阵组的中心，将每个延时自协方差矩阵组的中心作为一个预设延时自协方差矩阵组，进而得到多个预设延时自协方差矩阵组。例如，将每个延时自协方差矩阵组对应的聚类中心作为该延时自协方差矩阵组的中心，或者，获取每个延时自协方差矩阵组中的第二延时自协方差矩阵的平均值，将该平均值作为每个延时自协方差矩阵组的中心。然后，离线处理模块使用每个预设延时自协方差矩阵表征一种脑瞬态。在本申请中，也可以将每个预设延时自协方差矩阵称作一个高斯观测模型，故每种脑瞬态也可以通过一个高斯观测模型表征，则多种脑瞬态可以通过多个高斯观测模型，即高斯观测模型群进行表征。在本申请的一个实施方式中，在得到每种脑瞬态对应的预设延时自协方差矩阵后，为了使后续的在线脑瞬态监测泛化，可以使用主成分分析对预设延时自协方差矩阵降维，仅保留预设延时自协方差矩阵中的关键时间信息和关键空间信息，得到降维后的延时自协方差矩阵，然后可以将降维后的延时自协方差矩阵作为脑瞬态对应的预设延时自协方差矩阵。本申请中主要以不对预设延时自协方差矩阵进行降维为例进行说明。Further, the offline processing module groups a plurality of second delayed autocovariance matrices to obtain multiple delayed autocovariance matrix groups, wherein each delayed autocovariance matrix group includes the plurality of second delayed autocovariance matrices One or more of the autocovariance matrices. For example, the offline processing module may cluster multiple second time-delayed autocovariance matrices to obtain multiple time-delayed autocovariance matrix groups. Then, obtain the center of each delayed autocovariance matrix group, and use the center of each delayed autocovariance matrix group as a preset delayed autocovariance matrix group, and then obtain multiple preset delayed autocovariance matrices matrix group. For example, take the cluster center corresponding to each delayed autocovariance matrix group as the center of the delayed autocovariance matrix group, or obtain the second delayed autocovariance in each delayed autocovariance matrix group The mean of the matrix to use as the center for each group of delayed autocovariance matrices. Then, an offline processing module characterizes a brain transient using the autocovariance matrix for each preset delay. In this application, each preset delay autocovariance matrix can also be called a Gaussian observation model, so each brain transient can also be characterized by a Gaussian observation model, and multiple brain transients can be represented by multiple Gaussian observation model, that is, Gaussian observation model group for characterization. In one embodiment of the present application, after obtaining the preset delay autocovariance matrix corresponding to each brain transient, in order to generalize the subsequent online brain transient monitoring, principal component analysis can be used to analyze the preset delay Auto-covariance matrix dimensionality reduction, only retain the key time information and key space information in the preset time-delayed auto-covariance matrix, obtain the time-delayed auto-covariance matrix after dimensionality reduction, and then the time-delayed auto-covariance matrix after dimensionality reduction can be The variance matrix serves as the preset time-lapse autocovariance matrix corresponding to the brain transient. In this application, it is mainly explained by not performing dimensionality reduction on the preset delay autocovariance matrix as an example.

示例性的，本申请中的多种脑瞬态包括但不限于：前额瞬态、感觉运动瞬态、顶叶瞬态和视觉瞬态。进一步地，在得到多个预设延时自协方差矩阵后，为了将每种脑瞬态进行具化表示，可以将每个预设延时自协方差矩阵表征的脑瞬态进行编号，比如，可以分别编号为：脑瞬态1、脑瞬态2、……。为了方便解释，本申请中主要以分组出4种脑瞬态为例进行说明，并且这四种脑瞬态分别编号为脑瞬态1、脑瞬态2、脑瞬态3以及脑瞬态4。Exemplarily, various brain transients in this application include, but are not limited to: frontal transient, sensorimotor transient, parietal lobe transient, and visual transient. Further, after obtaining a plurality of preset delay autocovariance matrices, in order to express each brain transient, the brain transients represented by each preset delay autocovariance matrix can be numbered, such as , which can be respectively numbered as: brain transient 1, brain transient 2, . . . For the convenience of explanation, in this application, four kinds of brain transients are mainly grouped as an example for illustration, and these four kinds of brain transients are respectively numbered as brain transient 1, brain transient 2, brain transient 3 and brain transient 4 .

进一步地，离线处理模块获取每个时间窗口下的第二延时自协方差矩阵，与多个预设延时自协方差矩阵之间的多个第二相似度。然后，离线处理模块根据每个时间窗口下的多个第二相似度，确定所述待监测对象在每个时间窗口下的脑瞬态，即将第二相似度最大所对应的预设延时自协方差矩阵表征的脑瞬态作为每个时间窗口下的脑瞬态。然后，离线处理模块按照时间的先后顺序，对多个时间窗口下的多个脑瞬态进行排列，得到脑瞬态序列，即将多个时间窗口下的多个脑瞬态按照时间顺序组合起来，得到该脑瞬态序列。最后，基于脑瞬态序列，确定多种脑瞬态之间的状态转移概率矩阵以及多种脑瞬态对应的初始状态概率。Further, the offline processing module acquires multiple second similarities between the second delayed autocovariance matrix under each time window and multiple preset delayed autocovariance matrices. Then, the offline processing module determines the brain transient state of the subject to be monitored under each time window according to multiple second similarities under each time window, that is, the preset time delay corresponding to the second maximum similarity is automatically The brain transients characterized by the covariance matrix were taken as the brain transients under each time window. Then, the offline processing module arranges multiple brain transients under multiple time windows according to the order of time to obtain a brain transient sequence, that is, to combine multiple brain transients under multiple time windows in time order, Obtain this brain transient sequence. Finally, based on the brain transient sequence, the state transition probability matrix between various brain transients and the initial state probabilities corresponding to various brain transients are determined.

具体地，离线处理模块确定该脑瞬态序列中每种脑瞬态出现的次数，基于每种脑瞬态出现的次数，以及所述脑瞬态序列中脑瞬态的数量（也就是上述多个脑瞬态的数量或者可以理解为时间窗口的数量）确定每种脑瞬态的出现概率，即将每种脑瞬态出现的次数与脑瞬态序列中脑瞬态的数量之间的比值作为每种脑瞬态的出现概率。最后，将每种脑瞬态的出现概率，作为多种脑瞬态对应的初始状态概率。Specifically, the offline processing module determines the number of occurrences of each brain transient in the brain transient sequence, based on the number of occurrences of each brain transient, and the number of brain transients in the brain transient sequence (that is, the above-mentioned multiple The number of brain transients or the number of time windows) determines the occurrence probability of each brain transient, that is, the ratio between the number of occurrences of each brain transient and the number of brain transients in the brain transient sequence is taken as Occurrence probability of each brain transient. Finally, the occurrence probability of each brain transient is used as the initial state probability corresponding to multiple brain transients.

具体地，针对每种脑瞬态，离线处理模块确定所述脑瞬态序列中下一时刻与该脑瞬态相邻的脑瞬态，基于下一时刻与该脑瞬态相邻的脑瞬态，确每种脑瞬态下一时刻转移为各种脑瞬态的次数；基于每种脑瞬态下一时刻转移为各种脑瞬态的次数，以及每种脑瞬态出现的次数，确定每种脑瞬态转移为各种脑瞬态的概率。例如，将每种脑瞬态下一时刻转移为各种脑瞬态的次数与每种脑瞬态出现的次数之间的比值，作为每种脑瞬态转移为各种脑瞬态的概率；基于每种脑瞬态转移为各种脑瞬态的概率，确定多种脑瞬态之间的状态转移概率矩阵，即将每种脑瞬态转移为各种脑瞬态的概率分别作为状态转移概率矩阵中的每行元素，得到状态转移概率矩阵。Specifically, for each brain transient, the offline processing module determines the brain transient adjacent to the brain transient at the next moment in the brain transient sequence, based on the brain transient adjacent to the brain transient at the next moment state, confirming the number of times each brain transient transitions to various brain transients at the next moment; based on the number of times each brain transient transitions to various brain transients at the next moment, and the number of occurrences of each brain transient, Determine the probability that each brain transient transitions into various brain transients. For example, the ratio between the number of times each brain transient is transferred to various brain transients at the next moment and the number of occurrences of each brain transient is used as the probability of each brain transient being transferred to various brain transients; Based on the probability of each brain transient transitioning into various brain transients, determine the state transition probability matrix between multiple brain transients, that is, the probability of each brain transient transitioning into various brain transients as the state transition probability Each row element in the matrix gets the state transition probability matrix.

举例来说，时间窗口的数量为8，则脑瞬态序列中包含了8个脑瞬态，例如，脑瞬态序列为[脑瞬态1、脑瞬态2、脑瞬态1、脑瞬态3、脑瞬态4、脑瞬态2、脑瞬态1、脑瞬态4]。则脑瞬态1的出现次数为3，脑瞬态2出现的次数为2、脑瞬态3出现的次数为1，脑瞬态4出现的次数为2，故这四种脑瞬态对应的初始状态概率分别为：[3/8、1/4、1/8、1/4]。For example, if the number of time windows is 8, then the brain transient sequence contains 8 brain transients, for example, the brain transient sequence is [brain transient 1, brain transient 2, brain transient 1, brain transient State 3, Brain Transient 4, Brain Transient 2, Brain Transient 1, Brain Transient 4]. Then the number of occurrences of brain transient 1 is 3, the number of occurrences of brain transient 2 is 2, the number of occurrences of brain transient 3 is 1, and the number of occurrences of brain transient 4 is 2, so these four brain transients correspond to The initial state probabilities are: [3/8, 1/4, 1/8, 1/4].

然后，针对脑瞬态1，下一时刻转移为脑瞬态1的次数为0，下一时刻转移为脑瞬态2的次数为1，下一时刻转移为脑瞬态3的次数为1，下一时刻转移为脑瞬态4的次数为1，则脑瞬态1下一时刻转移为四种脑瞬态的概率分别为：0、1/3、1/3、1/3。针对脑瞬态2，下一时刻转移为脑瞬态1的次数为2，下一时刻转移为脑瞬态2的次数为0，下一时刻转移为脑瞬态3的次数为0，下一时刻转移为脑瞬态4的次数为0，则脑瞬态2下一时刻转移为四种脑瞬态的概率分别为：1、0、0、0。针对脑瞬态3，下一时刻转移为脑瞬态1的次数为0，下一时刻转移为脑瞬态2的次数为0，下一时刻转移为脑瞬态3的次数为0，下一时刻转移为脑瞬态4的次数为1，则脑瞬态3下一时刻转移为四种脑瞬态的概率分别为：0、0、0、1。针对脑瞬态4，下一时刻转移为脑瞬态1的次数为0，下一时刻转移为脑瞬态2的次数为1，下一时刻转移为脑瞬态3的次数为0，下一时刻转移为脑瞬态4的次数为0，则脑瞬态4下一时刻转移为四种脑瞬态的概率分别为：0、1、0、0。Then, for brain transient 1, the number of transitions to brain transient 1 at the next moment is 0, the number of transitions to brain transient 2 at the next moment is 1, and the number of transitions to brain transient 3 at the next moment is 1. The number of transitions to brain transient 4 at the next moment is 1, then the probabilities of transitioning to four brain transients at the next moment from brain transient 1 are: 0, 1/3, 1/3, and 1/3. For brain transient 2, the number of transitions to brain transient 1 at the next moment is 2, the number of transitions to brain transient 2 at the next moment is 0, the number of transitions to brain transient 3 at the next moment is 0, and the next time The number of time transitions to brain transient 4 is 0, so the probabilities of transitioning to four brain transients in the next moment of brain transient 2 are: 1, 0, 0, 0. For brain transient 3, the number of transitions to brain transient 1 at the next moment is 0, the number of transitions to brain transient 2 at the next moment is 0, the number of transitions to brain transient 3 at the next moment is 0, and the next time is 0. The number of time transitions to brain transient 4 is 1, then the probabilities of transitioning to four brain transients at the next moment of brain transient 3 are: 0, 0, 0, 1. For brain transient 4, the number of transitions to brain transient 1 at the next moment is 0, the number of transitions to brain transient 2 at the next moment is 1, the number of transitions to brain transient 3 at the next moment is 0, and the next time The number of time transitions to brain transient 4 is 0, then the probabilities of brain transient 4 transitioning to four brain transients at the next moment are: 0, 1, 0, 0.

故这四种脑瞬态之间的状态转移概率矩阵为：Therefore, the state transition probability matrix between these four brain transients is:

上面叙述了离线处理获取在线脑瞬态监测所需的参数的过程，下面结合离线过程获取到的参数，详细说明本申请的在线脑瞬态监测过程。The process of offline processing to obtain the parameters required for online brain transient monitoring is described above, and the online brain transient monitoring process of this application will be described in detail below in combination with the parameters obtained in the offline process.

示例性的，进行在线监测时，脑电采集模块用于在当前时刻从多个通道上采集待监测对象的多个原始脑电信号。具体地，脑瞬态监测设备上可设置有脑瞬态监测按钮，当按下该按钮后，脑电采集模块就会一直采集待监测对象的脑电信号。本申请中主要以分析当前时刻的脑瞬态为例进行说明，故主要以当前时刻采集到的脑电信号为例进行说明，其中，当前时刻可以为进行在线监测后的任意一个时刻。Exemplarily, when online monitoring is performed, the EEG acquisition module is used to acquire multiple original EEG signals of the subject to be monitored from multiple channels at the current moment. Specifically, the brain transient monitoring device may be provided with a brain transient monitoring button, and when the button is pressed, the EEG acquisition module will always collect the EEG signals of the subject to be monitored. In this application, the analysis of the brain transient state at the current moment is mainly used as an example for illustration, so the EEG signal collected at the current moment is mainly used as an example for illustration, wherein the current moment can be any moment after online monitoring.

进一步地，脑瞬态分析模块，用于基于重组矩阵对多个待分析脑电信号进行溯源分析，得到多个第一脑电源信号，即基于重组矩阵对多个原始脑电信号进行逆分解，得到与多个源极子对应的多个第一脑电源信号，即基于重组矩阵对多个原始脑电信号进行映射，可得到多个第一脑电源信号。然后，脑瞬态分析模块从每个第一脑电源信号中截取与当前时刻对应的待分析脑电信号，得到多个待分析脑电信号。即以当前时刻开始，分别从每个第一脑电源信号往前截取脑电信号，得到多个待分析脑电信号，其中，截取的长度为预设窗口所对应的长度。应说明的是，由于本申请是通过预设时间窗口进行信号截取，对各个时刻的脑瞬态进行分析，故当某个时刻之前的脑电信号的长度不够加窗时，则这个时刻可以不进行脑瞬态的监测。例如，预设时间窗口为30ms，则在启动在线监测功能后，前30ms的脑电信号无法加窗，故前30ms内可以不去输出各个时刻的脑瞬态，从30ms开始可以实时监测待监测对象在各个时刻下的脑瞬态，并将各个时刻下的脑瞬态进行输出显示。Further, the brain transient analysis module is used to perform traceability analysis on multiple EEG signals to be analyzed based on the reorganization matrix to obtain multiple first EEG power signals, that is, to inversely decompose multiple original EEG signals based on the reorganization matrix, To obtain multiple first brain power signals corresponding to multiple source electrodes, that is, to map multiple original brain electrical signals based on the recombination matrix, to obtain multiple first brain power signals. Then, the brain transient analysis module intercepts the EEG signal to be analyzed corresponding to the current moment from each first EEG signal to obtain a plurality of EEG signals to be analyzed. That is, starting from the current moment, the EEG signals are intercepted from each first EEG signal to obtain a plurality of EEG signals to be analyzed, wherein the intercepted length is the length corresponding to the preset window. It should be noted that since this application intercepts the signal through the preset time window and analyzes the brain transient at each moment, when the length of the EEG signal before a certain moment is not enough to add a window, then this moment may not Perform brain transient monitoring. For example, if the preset time window is 30ms, after the online monitoring function is activated, the EEG signals in the first 30ms cannot be windowed, so the brain transients at each moment can not be output in the first 30ms, and real-time monitoring can be started from 30ms. The brain transient state of the subject at each moment, and output and display the brain transient state at each moment.

进一步地，脑瞬态分析模块对多个待分析脑电信号进行处理，得到第一延时自协方差矩阵，即获取该多个待分析脑电信号对应的自协方差矩阵。例如，可以将每个待分析脑电信号在各个时刻下的幅值作为矩阵中的一行或一列元素，得到第三幅值矩阵。然后，基于幅值矩阵，可以确定出第一延时自协方差矩阵。Further, the brain transient analysis module processes a plurality of EEG signals to be analyzed to obtain a first time-delayed autocovariance matrix, that is, obtains an autocovariance matrix corresponding to the plurality of EEG signals to be analyzed. For example, the amplitude of each EEG signal to be analyzed at each moment may be used as a row or a column of elements in the matrix to obtain a third amplitude matrix. Then, based on the magnitude matrix, the first time-delayed autocovariance matrix can be determined.

进一步地，脑瞬态分析模块确定第一延时自协方差矩阵与多个预设延时自协方差矩阵之间的相似度，得到多个第一相似度。然后，根据多个第一相似度、所述待监测对象在上一时刻的脑瞬态、多种脑瞬态之间的状态转移概率矩阵、所述多种脑瞬态对应的初始状态概率，确定所述待监测对象当前时刻处于各种脑瞬态的概率。Further, the brain transient analysis module determines the similarity between the first delay autocovariance matrix and multiple preset delay autocovariance matrices to obtain multiple first similarities. Then, according to multiple first similarities, the brain transient state of the object to be monitored at the last moment, the state transition probability matrix between multiple brain transient states, and the initial state probabilities corresponding to the multiple brain transient states, The probability that the object to be monitored is in various brain transients at the current moment is determined.

示例性的，若当前时刻是首次确定所述待监测对象的脑瞬态时，则脑瞬态分析模块基于所述多种脑瞬态对应的初始状态概率与所述多个第一相似度，确定所述待监测对象当前时刻处于各种脑瞬态的概率。可选地，脑瞬态分析模块将所述多个第一相似度输入到隐马尔科夫模型中与该当前时刻对应的节点，得到待监测对象当前时刻处于各种脑瞬态的概率，其中，该隐马尔科夫模型中嵌入有与多种脑瞬态对应的初始状态概率以及状态转移概率矩阵。则将多个第一相似度输入到隐马尔科夫模型对应的节点后，可将多种脑瞬态对应的初始状态概率与多个第一相似度进行点乘，得到确定所述待监测对象当前时刻处于各种脑瞬态的概率，即将每种脑瞬态对应的第一相似度以及初始状态概率进行乘积，得到确定所述待监测对象当前时刻处于每种脑瞬态的概率。Exemplarily, if the current moment is the first time when the brain transient state of the subject to be monitored is determined, the brain transient analysis module is based on the initial state probabilities corresponding to the various brain transient states and the multiple first similarities, The probability that the object to be monitored is in various brain transients at the current moment is determined. Optionally, the brain transient analysis module inputs the plurality of first similarities into the node corresponding to the current moment in the hidden Markov model to obtain the probability that the object to be monitored is in various brain transients at the current moment, where , the initial state probabilities and state transition probability matrices corresponding to various brain transient states are embedded in the Cain Markov model. Then, after inputting multiple first similarities into the nodes corresponding to the hidden Markov model, the initial state probabilities corresponding to multiple brain transients can be multiplied by multiple first similarities to obtain the determination of the object to be monitored The probability of being in various brain transient states at the current moment is the product of the first similarity corresponding to each brain transient state and the initial state probability to obtain the probability that the subject to be monitored is in each brain transient state at the current moment.

示例性的，若当前时刻是首次确定所述待监测对象的脑瞬态时，脑瞬态分析模块基于所述状态转移概率矩阵、所述多个第一相似度以及所述待监测对象在上一时刻的脑瞬态，确定所述待监测对象当前时刻处于各种脑瞬态的概率。可选地，脑瞬态分析模块可将所述多个第一相似度输入到隐马尔科夫模型中与该当前时刻对应的节点，得到待监测对象当前时刻处于各种脑瞬态的概率。具体地，将多个第一相似度输入到隐马尔科夫模型对应的节点后，可从隐马尔科夫模型中获取上一个节点（即上一时刻）的脑瞬态；然后，从状态转移概率矩阵中获取所述待监测对象在上一时刻的脑瞬态转移为各种脑瞬态的概率序列；根据所述概率序列与所述多个第一相似度，确定所述待监测对象当前时刻处于各种脑瞬态的概率。例如，将所述概率序列与所述多个第一相似度进行点乘，得到待监测对象当前时刻处于各种脑瞬态的概率，即将每种脑瞬态对应的第一相似度以及上一时刻的脑瞬态转移为这种脑瞬态的概率进行乘积，得到待监测对象当前时刻处于各种脑瞬态的概率。Exemplarily, if the current moment is the first time when the brain transient state of the object to be monitored is determined, the brain transient analysis module is based on the state transition probability matrix, the plurality of first similarities, and the state of the object to be monitored. The brain transient state at a moment determines the probability that the subject to be monitored is in various brain transient states at the current moment. Optionally, the brain transient analysis module may input the multiple first similarities into the node corresponding to the current moment in the hidden Markov model to obtain the probability that the subject to be monitored is in various brain transients at the current moment. Specifically, after inputting a plurality of first similarities into the nodes corresponding to the hidden Markov model, the brain transient state of the previous node (that is, the previous moment) can be obtained from the hidden Markov model; then, from the state transfer Obtaining the probability sequence of the brain transient transition of the object to be monitored at the last moment into various brain transients in the probability matrix; according to the probability sequence and the plurality of first similarities, determine the current state of the object to be monitored The probability of being in various brain transients at any moment. For example, the probability sequence is dot-multiplied by the plurality of first similarities to obtain the probability that the object to be monitored is in various brain transients at the current moment, that is, the first similarity corresponding to each brain transient and the previous similarity The brain transient transition at any moment is multiplied by the probability of this brain transient, and the probability that the object to be monitored is in various brain transients at the current moment is obtained.

最后，脑瞬态分析模块基于该待监测对象当前时刻处于各种脑瞬态的概率，确定待检测对象在当前时刻的脑瞬态。例如，脑瞬态分析模块将概率最大所对应的脑瞬态作为待检测对象在当前时刻的脑瞬态。Finally, the brain transient analysis module determines the brain transient state of the object to be detected at the current moment based on the probability that the object to be monitored is in various brain transient states at the current moment. For example, the brain transient analysis module takes the brain transient corresponding to the highest probability as the brain transient of the object to be detected at the current moment.

在本申请的一个实施方式中，脑瞬态监测设备还包括显示模块。则在获取待检测对象在当前时刻的脑瞬态后，可通过显示模块显示待检测对象在当前时刻的脑瞬态，以便医生及时观看到待监测对象在当前时刻的脑瞬态。In one embodiment of the present application, the brain transient monitoring device further includes a display module. Then, after obtaining the brain transient state of the subject to be detected at the current moment, the display module can display the brain transient state of the subject to be detected at the current moment, so that the doctor can watch the brain transient state of the subject to be monitored at the current moment in time.

在本申请的一个实施方式中，脑瞬态监测设备还可以包括报警模块。则在获取待检测对象在当前时刻的脑瞬态后，可将脑瞬态与预设脑瞬态进行比对，以确定当前时刻的脑瞬态是否存在危险；若是，则通过报警模块进行报警，比如，向远端联系人或者医生发送报警信息，或者播放报警信号。In one embodiment of the present application, the brain transient monitoring device may further include an alarm module. Then, after obtaining the brain transient state of the object to be detected at the current moment, the brain transient state can be compared with the preset brain transient state to determine whether the brain transient state at the current moment is dangerous; if so, an alarm is issued through the alarm module , for example, send an alarm message to a remote contact or doctor, or play an alarm signal.

在本申请的一个实施方式中，脑瞬态监测设备还可将待监测对象在各个时刻下获取到的脑瞬态输出给其他设备，从而便于其他设备基于待监测对象在各个时刻的脑瞬态进行疾病分析、健康监测、个体化神经调控治疗策略等等。或者，脑瞬态监测设备还可将待监测对象在各个时刻下的脑瞬态进行缓存以及存档，以便后续进行分析。In one embodiment of the present application, the brain transient monitoring device can also output the brain transients obtained by the subject to be monitored at various moments to other devices, so that other devices can Perform disease analysis, health monitoring, individualized neuromodulation treatment strategies, and more. Alternatively, the brain transient monitoring device can also cache and archive the brain transients of the subject to be monitored at various moments for subsequent analysis.

可以看出，在本申请实施例中，首先离线计算出脑电信号到脑电源信号的重组矩阵，以及用于表征脑瞬态的预设延时自协方差矩阵，以及多种脑瞬态之间的状态转移概率矩阵，以及多种脑瞬态的初始状态概率，这样进行实时的在线监测时，可以利用离线计算好的重组矩阵，直接对在线采集到的多个原始脑电信号进行溯源，得到多个第一脑电源信号；以及从每个第一脑电源信号中截取与当前时刻对应的待分析脑电信号，得到多个待分析脑电信号，并获取多个待分析脑电信号对应的第一延时自协方差矩阵。然后，直接使用多个预设延时自协方差矩阵，确定出多个第一相似度。最后，直接基于多个第一相似度、待监测对象在上一时刻的脑瞬态、多种脑瞬态之间的状态转移概率矩阵、多种脑瞬态对应的初始状态概率，确定出待监测对象当前时刻处于各种脑瞬态的概率，进而确定出当前时刻的脑状态。由于在线监测的大部分复杂参数都是离线计算好的，大幅度的减轻了在线计算的复杂度，因此在线监测时可以快速地计算出当前时刻的脑状态，从而实现实时在线地监测大脑的脑状态。并且在确定当前时刻的脑瞬态时，不会只利用当前时刻下的脑电信号，与各种脑瞬态之间的相似度，还会结合上一个时刻的脑瞬态，以及多种脑瞬态之间的转移概率，从而可以精确地确定出当前时刻的脑瞬态，提高了对脑瞬态的监测精度。It can be seen that in the embodiment of the present application, the recombination matrix from the EEG signal to the EEG signal, the preset time-delay autocovariance matrix used to characterize the brain transient, and the various brain transients are firstly calculated offline. The inter-state transition probability matrix, as well as the initial state probabilities of various brain transients, so that when performing real-time online monitoring, the offline calculated recombination matrix can be used to directly trace the source of multiple original EEG signals collected online. Obtaining a plurality of first brain power signals; and intercepting the EEG signals to be analyzed corresponding to the current moment from each first EEG signal to obtain a plurality of EEG signals to be analyzed, and obtaining the corresponding EEG signals to be analyzed The first time-delayed autocovariance matrix of . Then, multiple first similarities are determined by directly using multiple preset delay autocovariance matrices. Finally, directly based on multiple first similarities, the brain transient state of the object to be monitored at the last moment, the state transition probability matrix between various brain transient states, and the initial state probabilities corresponding to various brain transient states, determine the The probability that the subject is in various brain transients at the current moment is monitored, and then the brain state at the current moment is determined. Since most of the complex parameters of online monitoring are calculated offline, the complexity of online calculation is greatly reduced, so the current brain state can be quickly calculated during online monitoring, so as to realize real-time online monitoring of the brain. state. And when determining the brain transient at the current moment, it will not only use the EEG signal at the current moment, and the similarity between various brain transients, but also combine the brain transient at the previous moment and various brain transients. The transition probability between transient states can accurately determine the brain transient state at the current moment, which improves the monitoring accuracy of the brain transient state.

上面分别从离线和在线两个角度叙述了对脑瞬态进行监测的过程。下面结合附图，整体叙述本申请的脑瞬态监测过程。The process of monitoring brain transients has been described above from both offline and online perspectives. The brain transient monitoring process of the present application will be described as a whole below in conjunction with the accompanying drawings.

如图5所示，首先进行离线处理，获取待监测对象的头皮脑电，得到离线脑电信号，以及获取待监测对象的头部的核磁共振图像；然后，对核磁共振图像进行脑皮层重构，得到三维脑模型，以及三维脑模型中的皮层网格，从而构建出Lead-field矩阵，以及重组矩阵，基于Lead-field矩阵对离线脑电信号进行逆分解，得到多个源极子对应的多个脑电源信号；基于多个脑电源信号，可构建出多个高斯观测模型，其中，每个高斯观测模型用于表征一种脑瞬态。同样，基于多个脑电源信号，可构造出离线处理时的脑瞬态序列；基于该脑瞬态序列，确定出多种脑瞬态对应的初始状态概率，以及多种脑瞬态之间的状态转移概率矩阵。As shown in Figure 5, first perform offline processing, obtain the scalp EEG of the subject to be monitored, obtain offline EEG signals, and obtain the MRI image of the head of the subject to be monitored; then, perform cerebral cortex reconstruction on the MRI image , to obtain the three-dimensional brain model, and the cortical grid in the three-dimensional brain model, thereby constructing the Lead-field matrix and the recombination matrix, based on the Lead-field matrix, the offline EEG signal is inversely decomposed, and multiple source sub-corresponding Multiple brain power signals; based on the multiple brain power signals, multiple Gaussian observation models can be constructed, wherein each Gaussian observation model is used to represent a brain transient state. Similarly, based on multiple brain power signals, a brain transient sequence during off-line processing can be constructed; based on the brain transient sequence, the initial state probabilities corresponding to various brain transients and the relationship between various brain transients can be determined. State transition probability matrix.

如图5所示，进行在线监测时，可获取当前时刻的脑电信号，基于重组矩阵将脑电信号逆分解（即脑电源信号重构）为多个脑电源信号；使用预设时间窗口从脑电源信号中截取当前时刻的待分析脑电信号，并计算待分析脑电信号的第一延时自协方差矩阵；计算第一延时自协方差矩阵与每个高斯观测模型之间的第一相似度，得到多个第一相似度；然后将多个第一相似度输入到隐马尔科夫模型，基于隐马尔科夫模型中的多种脑瞬态对应的初始状态概率，以及多种脑瞬态之间的状态转移概率矩阵、以及历史脑瞬态序列，得到待监测对象在当前时刻下的脑瞬态。As shown in Figure 5, during online monitoring, the EEG signal at the current moment can be obtained, and the EEG signal can be inversely decomposed (that is, the EEG signal is reconstructed) into multiple EEG signals based on the reorganization matrix; using the preset time window from Intercept the EEG signal to be analyzed at the current moment from the EEG signal, and calculate the first delay autocovariance matrix of the EEG signal to be analyzed; calculate the first delay autocovariance matrix between the first delay autocovariance matrix and each Gaussian observation model A similarity, to obtain a plurality of first similarities; then input a plurality of first similarities into the hidden Markov model, based on the initial state probabilities corresponding to various brain transients in the hidden Markov model, and various The state transition probability matrix between brain transients and the historical brain transient sequence are used to obtain the brain transient state of the object to be monitored at the current moment.

参阅图6，图6为本申请实施例提供的一种脑瞬态监测方法的流程示意图。该方法应用于上述脑瞬态监测设备。该方法包括但不限于以下步骤内容：Referring to FIG. 6 , FIG. 6 is a schematic flowchart of a brain transient monitoring method provided by an embodiment of the present application. The method is applied to the brain transient monitoring device described above. This method includes but is not limited to the following steps:

S601：所述脑电采集模块在当前时刻从多个通道上采集待监测对象的多个原始脑电信号。S601: The EEG collection module collects multiple original EEG signals of the subject to be monitored from multiple channels at the current moment.

S602：所述脑瞬态分析模块基于重组矩阵对所述多个原始脑电信号进行溯源分析，得到多个第一脑电源信号。S602: The brain transient analysis module performs traceability analysis on the multiple original EEG signals based on the recombination matrix to obtain multiple first EEG signals.

S603：所述脑瞬态分析模块从每个第一脑电源信号中截取与当前时刻对应的待分析脑电信号，得到多个待分析脑电信号。S603: The brain transient analysis module intercepts an EEG signal to be analyzed corresponding to the current moment from each first EEG signal to obtain a plurality of EEG signals to be analyzed.

S604：所述脑瞬态分析模块对所述多个待分析脑电信号进行处理，得到第一延时自协方差矩阵。S604: The brain transient analysis module processes the plurality of EEG signals to be analyzed to obtain a first time-delayed autocovariance matrix.

S605：所述脑瞬态分析模块确定所述第一延时自协方差矩阵与多个预设延时自协方差矩阵之间的相似度，得到多个第一相似度，其中，每个预设延时自协方差矩阵用于表征一种脑瞬态。S605: The brain transient analysis module determines the similarity between the first delayed autocovariance matrix and multiple preset delayed autocovariance matrices to obtain multiple first similarities, where each preset Let the time-delayed autocovariance matrix be used to characterize a brain transient.

S606：所述脑瞬态分析模块根据所述多个第一相似度、所述待监测对象在上一时刻的脑瞬态、多种脑瞬态之间的状态转移概率矩阵、所述多种脑瞬态对应的初始状态概率，确定所述待监测对象当前时刻处于各种脑瞬态的概率。S606: The brain transient analysis module is based on the multiple first similarities, the brain transient of the object to be monitored at the last moment, the state transition probability matrix between multiple brain transients, the multiple The initial state probability corresponding to the brain transient state determines the probability that the object to be monitored is in various brain transient states at the current moment.

S607：所述脑瞬态分析模块根据当前时刻处于各种脑瞬态的概率，确定所述待监测对象在当前时刻的脑瞬态。S607: The brain transient analysis module determines the brain transient state of the subject to be monitored at the current moment according to the probability of being in various brain transient states at the current moment.

其中，步骤S601~步骤S607的具体实现过程，可参照上述离线分析模块、图像获取模块、脑电采集模块以及脑瞬态分析模块的具体功能，不再赘述。Wherein, the specific implementation process of step S601~step S607 can refer to the specific functions of the above-mentioned offline analysis module, image acquisition module, EEG acquisition module and brain transient analysis module, and will not be repeated here.

参阅图7，图7是本申请实施例提供的一种电子设备的示意图。图7所示的电子设备700包括存储器701、处理器702、通信接口703以及总线704。其中，存储器701、处理器702、通信接口703通过总线704实现彼此之间的通信连接。电子设备700可以为上述脑瞬态监测装置。处理器702可以实现上述脑瞬态分析模块以及离线处理模块的功能。通信接口703可以实现上述图像获取模块和脑电采集模块的功能。Referring to FIG. 7, FIG. 7 is a schematic diagram of an electronic device provided by an embodiment of the present application. The electronic device 700 shown in FIG. 7 includes a memory 701 , a processor 702 , a communication interface 703 and a bus 704 . Wherein, the memory 701 , the processor 702 , and the communication interface 703 are connected to each other through a bus 704 . The electronic device 700 may be the above-mentioned brain transient monitoring device. The processor 702 can realize the functions of the above-mentioned brain transient analysis module and offline processing module. The communication interface 703 can realize the functions of the image acquisition module and the EEG acquisition module mentioned above.

其中，处理器702可以集成有上述脑瞬态分析模块以及离线处理模块的功能，用于离线计算（即离线计算重组矩阵、预设延时自协方差矩阵、种脑瞬态之间的状态转移概率矩阵、多种脑瞬态对应的初始状态概率）和在线计算（即计算当前时刻的脑瞬态）。通信接口703可以集成有上述图像获取模块和脑电采集模块的功能，例如，从待监测对象采集脑电信号，或者获取待监测对象的核磁共振图像。Among them, the processor 702 can be integrated with the functions of the above-mentioned brain transient analysis module and offline processing module for offline calculation (that is, offline calculation of recombination matrix, preset delay autocovariance matrix, and state transition between brain transients) Probability matrix, the initial state probability corresponding to various brain transients) and online calculation (that is, calculating the brain transient at the current moment). The communication interface 703 may integrate the functions of the above-mentioned image acquisition module and EEG acquisition module, for example, acquire EEG signals from the subject to be monitored, or acquire MRI images of the subject to be monitored.

存储器701可以是只读存储器（Read Only Memory，ROM），静态存储设备，动态存储设备或者随机存取存储器（Random Access Memory，RAM）。存储器701可以存储程序，当存储器701中存储的程序被处理器702执行时，处理器702和通信接口703用于执行本申请实施例的脑瞬态监测方法的各个步骤。The memory 701 may be a read only memory (Read Only Memory, ROM), a static storage device, a dynamic storage device or a random access memory (Random Access Memory, RAM). The memory 701 can store programs, and when the programs stored in the memory 701 are executed by the processor 702, the processor 702 and the communication interface 703 are used to execute various steps of the brain transient monitoring method of the embodiment of the present application.

处理器702可以采用通用的中央处理器（Central Processing Unit，CPU），微处理器，应用专用集成电路（Application Specific Integrated Circuit，ASIC），图形处理器（graphics processing unit，GPU）或者一个或多个集成电路，用于执行相关程序，以实现本申请实施例的音频特征补偿装置或音频识别装置中的单元所需执行的功能，或者执行本申请方法实施例的脑瞬态监测方法。The processor 702 may be a general-purpose central processing unit (Central Processing Unit, CPU), a microprocessor, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), a graphics processing unit (graphics processing unit, GPU) or one or more The integrated circuit is used to execute related programs to realize the functions required by the units in the audio feature compensation device or audio recognition device of the embodiment of the present application, or to execute the brain transient monitoring method of the method embodiment of the present application.

处理器702还可以是一种集成电路芯片，具有信号的处理能力。在实现过程中，本申请的刺激强度设定方法中的各个步骤可以通过处理器702中的硬件的集成逻辑电路或者软件形式的指令完成。上述的处理器702还可以是通用处理器、数字信号处理器（DigitalSignal Processing，DSP）、专用集成电路（ASIC）、现成可编程门阵列（Field ProgrammableGate Array，FPGA）或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件。可以实现或者执行本申请实施例中的公开的各方法、步骤及逻辑框图。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。结合本申请实施例所公开的方法的步骤可以直接体现为硬件译码处理器执行完成，或者用译码处理器中的硬件及软件模块组合执行完成。软件模块可以位于随机存储器，闪存、只读存储器，可编程只读存储器或者电可擦写可编程存储器、寄存器等本领域成熟的存储介质中。该存储介质位于存储器701，处理器702读取存储器701中的信息，结合其硬件完成本申请实施例的音频特征补偿装置或音频识别装置中包括的单元所需执行的功能，或者执行本申请方法实施例的脑瞬态监测方法中的各个步骤。The processor 702 may also be an integrated circuit chip, which has a signal processing capability. In the implementation process, each step in the stimulation intensity setting method of the present application can be completed by an integrated logic circuit of hardware in the processor 702 or instructions in the form of software. The above-mentioned processor 702 may also be a general-purpose processor, a digital signal processor (Digital Signal Processing, DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (Field Programmable Gate Array, FPGA) or other programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components. Various methods, steps, and logic block diagrams disclosed in the embodiments of the present application may be implemented or executed. A general-purpose processor may be a microprocessor, or the processor may be any conventional processor, or the like. The steps of the method disclosed in connection with the embodiments of the present application may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module can be located in a mature storage medium in the field such as random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, register. The storage medium is located in the memory 701, and the processor 702 reads the information in the memory 701, and combines its hardware to complete the functions required by the units included in the audio feature compensation device or the audio recognition device of the embodiment of the present application, or execute the method of the present application Various steps in the brain transient monitoring method of the embodiment.

通信接口703使用例如但不限于收发器、输入-输出设备一类的收发装置，来实现电子设备700与其他设备或通信网络之间的通信。例如，可以通过通信接口703采集脑电信号。The communication interface 703 implements communication between the electronic device 700 and other devices or communication networks by using transceiver devices such as but not limited to transceivers and input-output devices. For example, EEG signals can be collected through the communication interface 703 .

总线704可包括在电子设备700各个部件（例如，存储器701、处理器702、通信接口703）之间传送信息的通路。The bus 704 may include a path for transferring information between various components of the electronic device 700 (eg, memory 701 , processor 702 , communication interface 703 ).

应注意，尽管图7所示电子设备700仅仅示出了存储器、处理器、通信接口，但是在具体实现过程中，本领域的技术人员应当理解，电子设备700还包括实现正常运行所必须的其他器件。同时，根据具体需要，本领域的技术人员应当理解，电子设备700还可包括实现其他附加功能的硬件器件。此外，本领域的技术人员应当理解，电子设备700也可仅仅包括实现本申请实施例所必须的器件，而不必包括图7中所示的全部器件。It should be noted that although the electronic device 700 shown in FIG. 7 only shows a memory, a processor, and a communication interface, in a specific implementation process, those skilled in the art should understand that the electronic device 700 also includes other necessary components for normal operation. device. Meanwhile, according to specific needs, those skilled in the art should understand that the electronic device 700 may also include hardware devices for implementing other additional functions. In addition, those skilled in the art should understand that the electronic device 700 may only include components necessary to realize the embodiment of the present application, and does not necessarily include all the components shown in FIG. 7 .

所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统、装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。Those skilled in the art can clearly understand that for the convenience and brevity of the description, the specific working process of the above-described system, device and unit can refer to the corresponding process in the foregoing method embodiment, which will not be repeated here.

在本申请所提供的几个实施例中，应该理解到，所揭露的系统、装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods may be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated. to another system, or some features may be ignored, or not implemented. In another point, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in electrical, mechanical or other forms.

作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。A unit described as a separate component may or may not be physically separated, and a component displayed as a unit may or may not be a physical unit, that is, it may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit.

所述功能如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备（可以是个人计算机，服务器，或者网络设备等）执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器（Read-Only Memory，ROM）、随机存取存储器（Random Access Memory，RAM）、磁碟或者光盘等各种可以存储程序代码的介质。If the functions described above are realized in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including Several instructions are used to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk and other media that can store program codes. .

以上所述，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应以所述权利要求的保护范围为准。The above is only a specific implementation of the application, but the scope of protection of the application is not limited thereto. Anyone familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the application. Should be covered within the protection scope of this application. Therefore, the protection scope of the present application should be determined by the protection scope of the claims.

本申请实施例还提供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程序，所述计算机程序被处理器执行以实现如上述方法实施例中记载的任何一种脑瞬态监测方法的部分或全部步骤。The embodiment of the present application also provides a computer-readable storage medium, the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to realize any brain transient as described in the above-mentioned method embodiments Monitor some or all steps of the method.

本申请实施例还提供一种计算机程序产品，所述计算机程序产品包括存储了计算机程序的非瞬时性计算机可读存储介质，所述计算机程序可操作来使计算机执行如上述方法实施例中记载的任何一种脑瞬态监测方法的部分或全部步骤。The embodiment of the present application also provides a computer program product, the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable the computer to execute the method described in the above method embodiments Some or all of the steps of any method for monitoring brain transients.

需要说明的是，对于前述的各方法实施例，为了简单描述，故将其都表述为一系列的动作组合，但是本领域技术人员应该知悉，本申请并不受所描述的动作顺序的限制，因为依据本申请，某些步骤可以采用其他顺序或者同时进行。其次，本领域技术人员也应该知悉，说明书中所描述的实施例均属于可选实施例，所涉及的动作和模块并不一定是本申请所必须的。It should be noted that for the foregoing method embodiments, for the sake of simple description, they are expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited by the described action sequence. Depending on the application, certain steps may be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the application.

在上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有详述的部分，可以参见其他实施例的相关描述。In the foregoing embodiments, the descriptions of each embodiment have their own emphases, and for parts not described in detail in a certain embodiment, reference may be made to relevant descriptions of other embodiments.

在本申请所提供的几个实施例中，应该理解到，所揭露的装置，可通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性或其它的形式。In the several embodiments provided in this application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or can be Integrate into another system, or some features may be ignored, or not implemented. In another point, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in electrical or other forms.

所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件程序模块的形式实现。In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit. The above-mentioned integrated units can be implemented not only in the form of hardware, but also in the form of software program modules.

所述集成的单元如果以软件程序模块的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储器中。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储器中，包括若干指令用以使得一台计算机设备（可为个人计算机、服务器或者网络设备等）执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储器包括：U盘、只读存储器（ROM，Read-Only Memory）、随机存取存储器（RAM，Random Access Memory）、移动硬盘、磁碟或者光盘等各种可以存储程序代码的介质。The integrated units may be stored in a computer-readable memory if implemented in the form of a software program module and sold or used as an independent product. Based on this understanding, the technical solution of the present application is essentially or part of the contribution to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory. Several instructions are included to make a computer device (which may be a personal computer, server or network device, etc.) execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

本领域普通技术人员可以理解上述实施例的各种方法中的全部或部分步骤是可以通过程序来指令相关的硬件来完成，该程序可以存储于一计算机可读存储器中，存储器可以包括：闪存盘、只读存储器（英文：Read-Only Memory，简称：ROM）、随机存取器（英文：Random Access Memory，简称：RAM）、磁盘或光盘等。Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above-mentioned embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, and the memory can include: a flash disk , Read-only memory (English: Read-Only Memory, referred to as: ROM), random access device (English: Random Access Memory, referred to as: RAM), magnetic disk or optical disk, etc.

以上对本申请实施例进行了详细介绍，本文中应用了具体个例对本申请的原理及实施方式进行了阐述，以上实施例的说明只是用于帮助理解本申请的方法及其核心思想；同时，对于本领域的一般技术人员，依据本申请的思想，在具体实施方式及应用范围上均会有改变之处，综上所述，本说明书内容不应理解为对本申请的限制。The embodiments of the present application have been introduced in detail above, and specific examples have been used in this paper to illustrate the principles and implementation methods of the present application. The descriptions of the above embodiments are only used to help understand the methods and core ideas of the present application; meanwhile, for Those skilled in the art will have changes in specific implementation methods and application scopes based on the ideas of the present application. In summary, the contents of this specification should not be construed as limiting the present application.

Claims (7)

1. A brain transient monitoring device is characterized in that,

the brain transient monitoring equipment comprises an image acquisition module, an off-line processing module, an electroencephalogram acquisition module and a brain transient analysis module;

the image acquisition module is used for acquiring an original nuclear magnetic resonance image of the brain of the object to be monitored;

The electroencephalogram acquisition module is used for acquiring a plurality of off-line electroencephalograms of the object to be monitored on a plurality of channels in a preset time period;

the off-line processing module is used for obtaining a three-dimensional brain model of the object to be monitored based on the original nuclear magnetic resonance image;

acquiring a plurality of cortical grids in the three-dimensional brain model;

aligning the positions of a plurality of electrodes used for acquiring brain electrical signals on the channels with the positions of the cortex grids in the brain of the object to be monitored to obtain a Lead-field matrix corresponding to the object to be monitored;

acquiring covariance matrixes of the plurality of off-line electroencephalogram signals;

determining a reassembly matrix based on the covariance matrix and the Lead-field matrix;

performing inverse decomposition on the plurality of off-line electroencephalogram signals based on the Lead-field matrix to obtain a plurality of cortex signals corresponding to the cortex grids; dividing the three-dimensional brain model into a plurality of source sub-groups;

performing weighted mapping on the cortex signals to obtain a plurality of second brain power supply signals corresponding to the source electrodes;

windowing each second brain power supply signal for a plurality of times based on a preset time window so as to divide each second brain power supply signal and obtain a plurality of sub brain power supply signals corresponding to each second brain power supply signal;

Obtaining a plurality of preset delay autocovariance matrixes, a state transition probability matrix among a plurality of brain transients and initial state probabilities corresponding to the plurality of brain transients based on a plurality of sub-brain power signals corresponding to each second brain power signal, wherein each preset delay autocovariance matrix is used for representing one brain transient;

the electroencephalogram acquisition module is used for acquiring a plurality of original electroencephalograms of the object to be monitored from the channels at the current moment;

the brain transient analysis module is used for carrying out traceability analysis on the plurality of original brain electrical signals based on the recombination matrix to obtain a plurality of first brain power supply signals;

intercepting brain electrical signals to be analyzed corresponding to the current moment from each first brain electrical source signal to obtain a plurality of brain electrical signals to be analyzed;

processing the plurality of electroencephalogram signals to be analyzed to obtain a first delay autocovariance matrix;

determining the similarity between the first delay autocovariance matrix and the plurality of preset delay autocovariance matrices to obtain a plurality of first similarities;

determining the probability of the object to be monitored in various brain transients at the current moment according to the first similarity, the brain transient of the object to be monitored at the last moment, the state transition probability matrix and the initial state probability;

And determining the brain transient state of the object to be monitored at the current moment according to the probability that the current moment is in various brain transient states.

2. The apparatus of claim 1, wherein the device comprises a plurality of sensors,

the brain transient analysis module is specifically configured to determine probabilities that the current moment of the object to be monitored is in various brain transients according to the first similarities, the brain transient of the object to be monitored at the last moment, the state transition probability matrix and the initial state probability:

if the current moment is the brain transient of the object to be monitored, determining the probability that the current moment of the object to be monitored is in various brain transients based on the initial state probabilities corresponding to various brain transients and the first similarity;

if the current moment is not the first moment, determining a probability sequence of the brain transient of the object to be monitored to be changed into various brain transients at the last moment based on the state transition probability matrix; and determining the probability that the current moment of the object to be monitored is in various brain transients according to the probability sequence and the first similarities.

3. The apparatus according to claim 1 or 2, wherein,

The offline processing module is specifically configured to, based on a plurality of sub-brain power signals corresponding to each second brain power signal, obtain a plurality of preset delay autocovariance matrices, a state transition probability matrix between a plurality of brain transients, and initial state probabilities corresponding to the plurality of brain transients:

acquiring a plurality of sub-brain power supply signals of the plurality of second brain power supply signals under each time window;

determining a second delayed autocovariance matrix under each time window based on the plurality of sub-brain power supply signals under each time window;

obtaining a plurality of second delay autocovariance matrixes under a plurality of time windows corresponding to the windowing for a plurality of times based on the second delay autocovariance matrixes of each time window;

grouping the plurality of second delay autocovariance matrixes to obtain a plurality of delay autocovariance matrix groups;

taking the center of each delay autocovariance matrix group as a preset delay autocovariance matrix to obtain a plurality of preset delay autocovariance matrices;

determining a plurality of second similarities between a second delay autocovariance matrix under each time window and the plurality of preset delay autocovariance matrices;

Determining a brain transient of the subject to be monitored under each time window based on a plurality of second similarities under each time window;

arranging a plurality of brain transients under the plurality of time windows according to the sequence of time to obtain a brain transient sequence;

based on the brain transient sequence, a state transition probability matrix between the plurality of brain transients and an initial state probability corresponding to the plurality of brain transients are determined.

4. The apparatus of claim 3, wherein the device comprises a plurality of sensors,

in determining a state transition probability matrix between the plurality of brain transients and initial state probabilities corresponding to the plurality of brain transients based on the brain transient sequence, the offline processing module is specifically configured to:

determining the number of times each brain transient occurs in the sequence of brain transients;

determining the probability of occurrence of each brain transient based on the number of occurrences of each brain transient and the number of brain transients in the sequence of brain transients;

taking the occurrence probability of each brain transient as the initial state probability corresponding to the plurality of brain transients;

for each brain transient, determining a brain transient adjacent to the brain transient at a next moment in the sequence of brain transients, and determining the number of times the next moment of the brain transient is transferred to various brain transients based on the brain transient adjacent to the brain transient at the next moment;

Determining a probability of each brain transient transitioning to a variety of brain transients based on the number of times that the brain transient transitions to the variety of brain transients at a next time and the number of times that each brain transient occurs;

a state transition probability matrix between each of the plurality of brain transients is determined based on the probability of the transition of the brain transient to the respective brain transient.

5. The apparatus of claim 1, wherein the device comprises a plurality of sensors,

in the aspect of obtaining the three-dimensional brain model of the object to be monitored based on the original nuclear magnetic resonance image, the offline processing module is specifically configured to:

re-slicing the original nuclear magnetic resonance image to obtain a target nuclear magnetic resonance image;

dividing the target nuclear magnetic resonance image to obtain brain tissue, skull and scalp;

and establishing a brain model based on the target nuclear magnetic resonance image of the brain tissue, the skull and the scalp to obtain the three-dimensional brain model of the object to be monitored.

6. An electronic device, comprising: the electronic device comprises a processor and a memory, wherein the processor is connected with the memory, the memory is used for storing a computer program, and the processor is used for executing the computer program stored in the memory, so that the electronic device executes the following steps:

Acquiring an original nuclear magnetic resonance image of the brain of a subject to be monitored;

collecting a plurality of off-line electroencephalogram signals of the object to be monitored on a plurality of channels within a preset time period;

based on the original nuclear magnetic resonance image, obtaining a three-dimensional brain model of the object to be monitored;

acquiring a plurality of cortical grids in the three-dimensional brain model; aligning the positions of a plurality of electrodes used for acquiring brain electrical signals on the channels with the positions of the cortex grids in the brain of the object to be monitored to obtain a Lead-field matrix corresponding to the object to be monitored;

acquiring covariance matrixes of the plurality of off-line electroencephalogram signals;

determining a reassembly matrix based on the covariance matrix and the Lead-field matrix;

performing inverse decomposition on the plurality of off-line electroencephalogram signals based on the Lead-field matrix to obtain a plurality of cortex signals corresponding to the cortex grids; dividing the three-dimensional brain model into a plurality of source sub-groups;

performing weighted mapping on the cortex signals to obtain a plurality of second brain power supply signals corresponding to the source electrodes;

windowing each second brain power supply signal for a plurality of times based on a preset time window so as to divide each second brain power supply signal and obtain a plurality of sub brain power supply signals corresponding to each second brain power supply signal;

Obtaining a plurality of preset delay autocovariance matrixes, a state transition probability matrix among a plurality of brain transients and initial state probabilities corresponding to the plurality of brain transients based on a plurality of sub-brain power signals corresponding to each second brain power signal, wherein each preset delay autocovariance matrix is used for representing one brain transient;

collecting a plurality of original brain electrical signals of the object to be monitored from the channels at the current moment;

performing traceability analysis on the plurality of original brain electrical signals based on the recombination matrix to obtain a plurality of first brain power supply signals;

intercepting brain electrical signals to be analyzed corresponding to the current moment from each first brain electrical source signal to obtain a plurality of brain electrical signals to be analyzed;

processing the plurality of electroencephalogram signals to be analyzed to obtain a first delay autocovariance matrix;

determining the similarity between the first delay autocovariance matrix and the plurality of preset delay autocovariance matrices to obtain a plurality of first similarities;

determining the probability of the object to be monitored in various brain transients at the current moment according to the first similarity, the brain transient of the object to be monitored at the last moment, the state transition probability matrix and the initial state probability;

And determining the brain transient state of the object to be monitored at the current moment according to the probability that the current moment is in various brain transient states.

7. A computer readable storage medium storing a computer program, the computer program being executable by a processor to perform the steps of:

acquiring an original nuclear magnetic resonance image of the brain of a subject to be monitored;

collecting a plurality of off-line electroencephalogram signals of the object to be monitored on a plurality of channels within a preset time period;

based on the original nuclear magnetic resonance image, obtaining a three-dimensional brain model of the object to be monitored;

acquiring a plurality of cortical grids in the three-dimensional brain model; aligning the positions of a plurality of electrodes used for acquiring brain electrical signals on the channels with the positions of the cortex grids in the brain of the object to be monitored to obtain a Lead-field matrix corresponding to the object to be monitored;

acquiring covariance matrixes of the plurality of off-line electroencephalogram signals;

determining a reassembly matrix based on the covariance matrix and the Lead-field matrix;

performing inverse decomposition on the plurality of off-line electroencephalogram signals based on the Lead-field matrix to obtain a plurality of cortex signals corresponding to the cortex grids; dividing the three-dimensional brain model into a plurality of source sub-groups;

Performing weighted mapping on the cortex signals to obtain a plurality of second brain power supply signals corresponding to the source electrodes;

windowing each second brain power supply signal for a plurality of times based on a preset time window so as to divide each second brain power supply signal and obtain a plurality of sub brain power supply signals corresponding to each second brain power supply signal;

obtaining a plurality of preset delay autocovariance matrixes, a state transition probability matrix among a plurality of brain transients and initial state probabilities corresponding to the plurality of brain transients based on a plurality of sub-brain power signals corresponding to each second brain power signal, wherein each preset delay autocovariance matrix is used for representing one brain transient;

collecting a plurality of original brain electrical signals of the object to be monitored from the channels at the current moment;

performing traceability analysis on the plurality of original brain electrical signals based on the recombination matrix to obtain a plurality of first brain power supply signals;

intercepting brain electrical signals to be analyzed corresponding to the current moment from each first brain electrical source signal to obtain a plurality of brain electrical signals to be analyzed;

processing the plurality of electroencephalogram signals to be analyzed to obtain a first delay autocovariance matrix;

Determining the similarity between the first delay autocovariance matrix and the plurality of preset delay autocovariance matrices to obtain a plurality of first similarities;

determining the probability of the object to be monitored in various brain transients at the current moment according to the first similarity, the brain transient of the object to be monitored at the last moment, the state transition probability matrix and the initial state probability;

and determining the brain transient state of the object to be monitored at the current moment according to the probability that the current moment is in various brain transient states.