技术领域technical field
本发明涉及医学技术领域，尤其涉及一种病灶定位方法、装置、设备及存储介质。The present invention relates to the field of medical technology, in particular to a lesion localization method, device, equipment and storage medium.
背景技术Background technique
目前，神经影像技术在对癫痫诊断领域广泛应用，通过磁共振扫描有助于整顿脑部病理区域，但是，在临床上，通过人工诊断费时费力，并可能因其它干扰因素而存在误诊的情况。At present, neuroimaging technology is widely used in the field of epilepsy diagnosis. Magnetic resonance scanning can help to rectify brain pathological areas. However, in clinical practice, manual diagnosis is time-consuming and laborious, and may cause misdiagnosis due to other interference factors.
上述内容仅用于辅助理解本发明的技术方案，并不代表承认上述内容是现有技术。The above content is only used to assist in understanding the technical solution of the present invention, and does not mean that the above content is admitted as prior art.
发明内容Contents of the invention
本发明的主要目的在于提供一种病灶定位方法、装置、设备及存储介质，旨在解决因人工诊断癫痫疾病不仅费时费力还可能存在误诊的技术问题。The main purpose of the present invention is to provide a lesion localization method, device, equipment and storage medium, aiming to solve the technical problem that manual diagnosis of epilepsy is not only time-consuming and laborious, but also may cause misdiagnosis.
为实现上述目的，本发明提供一种病灶定位方法，所述病灶定位方法包括以下步骤：In order to achieve the above object, the present invention provides a method for locating a lesion, and the method for locating a lesion comprises the following steps:
对预设范围内的信号进行时频分析，并根据分析后信号的包络确定目标信号；Perform time-frequency analysis on the signal within the preset range, and determine the target signal according to the envelope of the analyzed signal;
根据所述目标信号的频域变化、小波系数和局部峰值进行特征提取，获得特征分量；performing feature extraction according to frequency domain changes, wavelet coefficients, and local peaks of the target signal to obtain feature components;
根据空间滤波器构建头部模型，并根据矢量光束网格化所述头部模型；constructing a head model according to a spatial filter, and meshing said head model according to a vector beam;
确定所述特征分量的协方差矩阵，并根据所述协方差矩阵和网格化后头部模型的能量分布定位病灶。The covariance matrix of the feature components is determined, and the lesion is located according to the covariance matrix and the energy distribution of the meshed head model.
可选地，所述确定所述特征分量的协方差矩阵，并根据所述协方差矩阵和网格化后头部模型的能量分布定位病灶的步骤，包括：Optionally, the step of determining the covariance matrix of the feature components and locating the lesion according to the covariance matrix and the energy distribution of the meshed occipital model includes:
根据约束条件和所述空间滤波器确定所述特征分量的协方差矩阵；determining a covariance matrix of the feature components according to constraints and the spatial filter;
根据所述协方差矩阵确定所述头部模型的网格能量值，并确定所述头部模型的网格能量插值；determining a grid energy value of the head model according to the covariance matrix, and determining a grid energy interpolation value of the head model;
根据所述网格能量值和所述网格能量插值绘制所述头部模型的皮层能量分布，并根据所述皮层能量分布定位病灶。Draw the cortical energy distribution of the head model according to the grid energy value and the grid energy interpolation, and locate the lesion according to the cortical energy distribution.
可选地，所述根据约束条件和所述空间滤波器确定所述特征分量的协方差矩阵的步骤，包括：Optionally, the step of determining the covariance matrix of the feature components according to the constraints and the spatial filter includes:
根据偶极矩确定对应的空间滤波器，并根据所述空间滤波器形成的方差确定约束条件；determining a corresponding spatial filter according to the dipole moment, and determining a constraint condition according to a variance formed by the spatial filter;
根据约束条件和所述空间滤波器确定所述特征分量的协方差矩阵。A covariance matrix of the feature components is determined according to constraints and the spatial filter.
可选地，所述对预设范围内的信号进行时频分析，并根据分析后信号的包络确定目标信号的步骤，包括：Optionally, the step of performing time-frequency analysis on signals within a preset range, and determining the target signal according to the envelope of the analyzed signal includes:
获取预设范围内的信号，并划分所述信号确定划分后各段信号的小波熵；Obtaining a signal within a preset range, and dividing the signal to determine the wavelet entropy of each segment of the signal after division;
根据所述小波熵确定检测阈值，并确定所述各段信号的信号包络；Determine the detection threshold according to the wavelet entropy, and determine the signal envelope of each segment of the signal;
在所述信号包络大于所述检测阈值时，将所述信号包络对应的信号作为待检测信号；When the signal envelope is greater than the detection threshold, using the signal corresponding to the signal envelope as the signal to be detected;
在对所述待检测信号的检测时长超过预设阈值时，将所述待检测信号作为目标信号。When the detection duration of the signal to be detected exceeds a preset threshold, the signal to be detected is used as a target signal.
可选地，所述根据所述目标信号的频域变化、小波系数和局部峰值进行特征提取，获得特征分量的步骤之后，还包括：Optionally, the feature extraction is performed according to the frequency domain variation, wavelet coefficient and local peak of the target signal, and after the step of obtaining feature components, it also includes:
根据所述特征分量确定特征向量，并根据所述特征向量确定初始特征图；determining a feature vector according to the feature component, and determining an initial feature map according to the feature vector;
根据所述初始特征图确定初始列表集合，并从所述初始列表集合中选择任一两个列表集群进行比较；determining an initial list set according to the initial feature map, and selecting any two list clusters from the initial list set for comparison;
根据比较结果进行筛选，并根据筛选结果获得目标列表集群；Filter according to the comparison result, and obtain the target list cluster according to the filter result;
将所述目标列表集群与所述初始列表集合中任一列表集群进行比较，并返回所述根据比较结果进行筛选，并根据筛选结果获得目标列表集群的步骤，直至第一比较次数达到第一预设阈值获得目标特征集群。Comparing the target list cluster with any list cluster in the initial list set, and returning to the step of filtering according to the comparison result, and obtaining the target list cluster according to the screening result, until the first number of comparisons reaches the first preset Set a threshold to obtain target feature clusters.
可选地，所述根据比较结果进行筛选，并根据筛选结果获得目标列表集群的步骤包括：Optionally, the step of performing screening according to the comparison result and obtaining the target list cluster according to the screening result includes:
在任一两个列表集群都不为空集时，判断所述任一两个列表集群是否有相同的数据；When any two list clusters are not empty sets, determine whether any two list clusters have the same data;
在所述任一两个列表集群中存在相同的数据时，将所述任一两个列表集群合并，获得目标列表集群；When the same data exists in any two list clusters, merging any two list clusters to obtain a target list cluster;
在所述任一两个列表集群中不存在相同的数据时，返回所述从所述初始列表集合中选择任一两个列表集群进行比较的步骤，直至第二比较次数达到第二预设阈值获得目标特征集群。When the same data does not exist in any two list clusters, return to the step of selecting any two list clusters from the initial list set for comparison until the second number of comparisons reaches a second preset threshold Obtain target feature clusters.
可选地，所述将所述目标列表集群与所述初始列表集合中任一列表集群进行比较，并返回所述根据比较结果进行筛选，并根据筛选结果获得目标列表集群的步骤，直至第一比较次数达到第一预设阈值获得目标特征集群的步骤之后，还包括：Optionally, the step of comparing the target list cluster with any list cluster in the initial list set, and returning to the step of filtering according to the comparison result, and obtaining the target list cluster according to the screening result, until the first After the number of comparisons reaches the first preset threshold and obtains the target feature cluster, it also includes:
根据所述目标特征集群的数量和所述目标特征集群的相对频率确定所述目标特征集群的熵；determining the entropy of the target feature cluster based on the number of target feature clusters and the relative frequency of the target feature cluster;
根据所述熵和所述数量确定所述目标特征集群的熵率，并根据所述熵率定位病灶。An entropy rate of the target feature cluster is determined according to the entropy and the number, and a lesion is located according to the entropy rate.
此外，为实现上述目的，本发明还提出一种病灶定位装置，所述病灶定位装置包括：信号确定模块、分量确定模块、模型确定模块及病灶定位模块；In addition, in order to achieve the above purpose, the present invention also proposes a lesion localization device, the lesion localization device includes: a signal determination module, a component determination module, a model determination module and a lesion localization module;
所述信号确定模块，用于对预设范围内的信号进行时频分析，并根据分析后信号的包络确定目标信号；The signal determination module is configured to perform time-frequency analysis on signals within a preset range, and determine the target signal according to the envelope of the analyzed signal;
所述分量确定模块，用于根据所述目标信号的频域变化、小波系数和局部峰值进行特征提取，获得特征分量；The component determination module is used to perform feature extraction according to frequency domain changes, wavelet coefficients and local peaks of the target signal to obtain feature components;
所述模型确定模块，用于根据空间滤波器构建头部模型，并根据矢量光束网格化所述头部模型；The model determination module is configured to construct a head model according to a spatial filter, and grid the head model according to a vector beam;
所述病灶定位模块，用于确定所述特征分量的协方差矩阵，并根据所述协方差矩阵和网格化后头部模型的能量分布定位病灶。The lesion location module is configured to determine the covariance matrix of the feature components, and locate the lesion according to the covariance matrix and the energy distribution of the gridded head model.
此外，为实现上述目的，本发明还提出一种病灶定位设备，所述病灶定位设备包括存储器、处理器及存储在所述存储器上并可在所述处理器上运行病灶定位程序，所述病灶定位程序配置为实现如上文所述的病灶定位方法。In addition, in order to achieve the above object, the present invention also proposes a lesion locating device, the lesion locating device includes a memory, a processor, and a lesion locating program stored in the memory and capable of running on the processor, the lesion locating The localization program is configured to implement the lesion localization method as described above.
此外，为实现上述目的，本发明还提出一种存储介质，所述存储介质上存储有病灶定位程序，所述病灶定位程序被处理器执行时实现如上文所述的病灶定位方法。In addition, in order to achieve the above object, the present invention also proposes a storage medium, on which a lesion localization program is stored, and when the lesion localization program is executed by a processor, the lesion localization method as described above is implemented.
本发明公开了一种病灶定位方法、装置、设备及存储介质，该方法包括：对预设范围内的信号进行时频分析，并根据分析后信号的包络确定目标信号；根据目标信号的频域变化、小波系数和局部峰值进行特征提取，获得特征分量；根据空间滤波器构建头部模型，并根据矢量光束网格化头部模型；确定特征分量的协方差矩阵，并根据协方差矩阵和网格化后头部模型的能量分布定位病灶。本发明对滤波进行时频分析并根据分析后的信号包络确定目标信号，对目标信号进行特征提取获得特征分量并确定特征分量的协方差矩阵，建立头部模型并对头部模型网格化，根据网格化后的头部模型和协方差矩阵定位病灶，从而能防止因人工诊断而导致的误诊，并提高了诊断的效率。The invention discloses a lesion location method, device, equipment and storage medium. The method includes: performing time-frequency analysis on signals within a preset range, and determining a target signal according to the envelope of the analyzed signal; domain changes, wavelet coefficients and local peaks for feature extraction to obtain feature components; construct the head model according to the spatial filter, and grid the head model according to the vector beam; determine the covariance matrix of the feature components, and according to the covariance matrix and The energy distribution of the head model after meshing localizes the lesion. The invention performs time-frequency analysis on filtering and determines the target signal according to the analyzed signal envelope, performs feature extraction on the target signal to obtain feature components and determines the covariance matrix of the feature components, establishes a head model and grids the head model , according to the meshed head model and covariance matrix to locate the lesion, so as to prevent misdiagnosis caused by manual diagnosis and improve the efficiency of diagnosis.
附图说明Description of drawings
图1是本发明实施例方案涉及的硬件运行环境的病灶定位设备的结构示意图；Fig. 1 is a schematic structural diagram of a lesion locating device in a hardware operating environment involved in an embodiment of the present invention;
图2为本发明病灶定位方法第一实施例的流程示意图；Fig. 2 is a schematic flowchart of the first embodiment of the method for locating a lesion according to the present invention;
图3为本发明病灶定位方法第二实施例的流程示意图；Fig. 3 is a schematic flow chart of the second embodiment of the lesion localization method of the present invention;
图4为本发明病灶定位装置第一实施例的结构框图。Fig. 4 is a structural block diagram of the first embodiment of the lesion locating device of the present invention.
本发明目的的实现、功能特点及优点将结合实施例，参照附图做进一步说明。The realization of the purpose of the present invention, functional characteristics and advantages will be further described in conjunction with the embodiments and with reference to the accompanying drawings.
具体实施方式Detailed ways
应当理解，此处所描述的具体实施例仅仅用以解释本发明，并不用于限定本发明。It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.
参照图1，图1为本发明实施例方案涉及的硬件运行环境的病灶定位设备结构示意图。Referring to FIG. 1 , FIG. 1 is a schematic structural diagram of a lesion localization device in a hardware operating environment involved in an embodiment of the present invention.
如图1所示，该病灶定位设备可以包括：处理器1001，例如中央处理器（CentralProcessing Unit，CPU），通信总线1002、用户接口1003，网络接口1004，存储器1005。其中，通信总线1002用于实现这些组件之间的连接通信。用户接口1003可以包括显示屏（Display），可选用户接口1003还可以包括标准的有线接口、无线接口，对于用户接口1003的有线接口在本发明中可为USB接口。网络接口1004可选的可以包括标准的有线接口、无线接口（如无线保真（Wireless-Fidelity，Wi-Fi）接口）。存储器1005可以是高速的随机存取存储器（Random Access Memory，RAM），也可以是稳定的存储器（Non-volatile Memory，NVM），例如磁盘存储器。存储器1005可选的还可以是独立于前述处理器1001的存储装置。As shown in FIG. 1 , the device for locating a lesion may include: a processor 1001 , such as a central processing unit (Central Processing Unit, CPU), a communication bus 1002 , a user interface 1003 , a network interface 1004 , and a memory 1005 . Wherein, the communication bus 1002 is used to realize connection and communication between these components. The user interface 1003 may include a display screen (Display). The optional user interface 1003 may also include a standard wired interface and a wireless interface. The wired interface of the user interface 1003 may be a USB interface in the present invention. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a Wireless-Fidelity (Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM), or a stable memory (Non-volatile Memory, NVM), such as a disk memory. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001 .
本领域技术人员可以理解，图1中示出的结构并不构成对病灶定位设备的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置。Those skilled in the art can understand that the structure shown in FIG. 1 does not constitute a limitation on the lesion locating device, and may include more or less components than those shown in the illustration, or combine some components, or arrange different components.
如图1所示，认定为一种计算机存储介质的存储器1005中可以包括操作系统、网络通信模块、用户接口模块以及病灶定位程序。As shown in FIG. 1 , the memory 1005 identified as a computer storage medium may include an operating system, a network communication module, a user interface module, and a lesion localization program.
在图1所示的病灶定位设备中，网络接口1004主要用于连接后台服务器，与所述后台服务器进行数据通信；用户接口1003主要用于连接用户设备；所述病灶定位设备通过处理器1001调用存储器1005中存储的病灶定位程序，并执行本发明实施例提供的病灶定位方法。In the lesion locating device shown in FIG. 1 , the network interface 1004 is mainly used to connect to the background server and perform data communication with the background server; the user interface 1003 is mainly used to connect to user equipment; the lesion locating device is called by the processor 1001 The focus location program stored in the memory 1005 executes the focus location method provided by the embodiment of the present invention.
基于上述硬件结构，提出本发明病灶定位方法的实施例。Based on the above hardware structure, an embodiment of the lesion localization method of the present invention is proposed.
参照图2，图2为本发明病灶定位方法第一实施例的流程示意图，提出本发明病灶定位方法第一实施例。Referring to FIG. 2 , which is a schematic flowchart of the first embodiment of the method for locating a lesion according to the present invention, the first embodiment of the method for locating a lesion according to the present invention is proposed.
步骤S10：对预设范围内的信号进行时频分析，并根据分析后信号的包络确定目标信号。Step S10: Perform time-frequency analysis on the signal within the preset range, and determine the target signal according to the envelope of the analyzed signal.
需要说明的是，本实施例的执行主体可以是具有数据处理、网络通信以及程序运行功能的计算机软件服务设备，例如，病灶定位设备等，或者是其他能够实现相同或相似功能的电子设备，本实施例对此不加限制。It should be noted that the execution subject of this embodiment may be a computer software service device with functions of data processing, network communication and program operation, for example, a lesion locating device, etc., or other electronic devices capable of realizing the same or similar functions. The embodiments do not limit this.
需要说明的是，以往对病灶定位的方法是4-70Hz的脑电/电磁信号，但是这个频段容易收到信号的干扰，因此，本实施例进行时频分析的是80Hz以上的癫痫脑信号，并且高频振荡的信号与癫痫区域密切相关。It should be noted that in the past, the method of locating the lesion was the EEG/EM signal of 4-70 Hz, but this frequency band is easily interfered by the signal. Therefore, the time-frequency analysis in this embodiment is the epileptic brain signal above 80 Hz. And the high-frequency oscillation signal is closely related to the epileptic area.
需要说明的是，预设范围内的信号可以是通过滤波器在80-250Hz范围内进行的带通滤波，即只接收80-250Hz这个范围内的信号，在这范围之外的信号都可以过滤掉，本实施例对80-250Hz这个范围的上限区间不做限制。It should be noted that the signals within the preset range can be band-pass filtered through the filter in the range of 80-250Hz, that is, only signals within the range of 80-250Hz are received, and signals outside this range can be filtered However, this embodiment does not limit the upper limit interval of the range of 80-250 Hz.
可以理解的是，对80-250Hz这个范围内的信号进行时频分析，可以是对80-250Hz这个范围内的信号进行希尔伯特变换，即根据希尔伯特变换计算80-250Hz这个范围内信号的包络。It can be understood that the time-frequency analysis of the signal in the range of 80-250Hz can be carried out by Hilbert transform on the signal in the range of 80-250Hz, that is, the range of 80-250Hz is calculated according to the Hilbert transform The envelope of the inner signal.
需要说明的是，将计算出来的信号包络与阈值进行比较，从而判断信号包络对应的信号是否为高频振荡信号。It should be noted that the calculated signal envelope is compared with the threshold to determine whether the signal corresponding to the signal envelope is a high-frequency oscillation signal.
进一步地，为了提高病灶定位的准确率，因此本实施例步骤S10可包括：Further, in order to improve the accuracy of lesion location, step S10 of this embodiment may include:
获取预设范围内的信号，并划分所述信号确定划分后各段信号的小波熵；Obtaining a signal within a preset range, and dividing the signal to determine the wavelet entropy of each segment of the signal after division;
根据所述小波熵确定检测阈值，并确定所述各段信号的信号包络；Determine the detection threshold according to the wavelet entropy, and determine the signal envelope of each segment of the signal;
在所述信号包络大于所述检测阈值时，将所述信号包络对应的信号作为待检测信号；When the signal envelope is greater than the detection threshold, using the signal corresponding to the signal envelope as the signal to be detected;
在对所述待检测信号的检测时长超过预设阈值时，将所述待检测信号作为目标信号。When the detection duration of the signal to be detected exceeds a preset threshold, the signal to be detected is used as a target signal.
可以理解的是，可以将80-250Hz这个范围内的信号划分成每段60ms的信号，并计算每段信号自相关小波熵。It can be understood that the signal in the range of 80-250 Hz can be divided into signal segments of 60 ms each, and the autocorrelation wavelet entropy of each signal segment can be calculated.
需要说明的是，根据小波熵的信号概率分布将检测阈值设置在信号概率分布在95%处对应的熵值。It should be noted that, according to the signal probability distribution of wavelet entropy, the detection threshold is set at the entropy value corresponding to the signal probability distribution at 95%.
应理解的是，可以通过希尔伯特变换确定各段信号的信号包络，即根据希尔伯特变换确定各段信号的高频信号。It should be understood that the signal envelope of each segment of signal may be determined through Hilbert transform, that is, the high frequency signal of each segment of signal may be determined according to Hilbert transform.
需要说明的是，当信号包络超过检测阈值的99.99%并且持续时间超过6ms时，将信号包络对应的信号作为目标信号。It should be noted that when the signal envelope exceeds 99.99% of the detection threshold and lasts longer than 6 ms, the signal corresponding to the signal envelope is taken as the target signal.
步骤S20：根据所述目标信号的频域变化、小波系数和局部峰值进行特征提取，获得特征分量。Step S20: Perform feature extraction according to frequency domain variation, wavelet coefficients and local peaks of the target signal to obtain feature components.
需要说明的是，可以根据傅里叶变换提取目标信号的在频域上的变化，根据连续小波变化确定小波系数以及根据多通过经验模态分解对目标信号的区域峰值进行提取。It should be noted that the change of the target signal in the frequency domain can be extracted according to the Fourier transform, the wavelet coefficient can be determined according to the continuous wavelet change, and the regional peak value of the target signal can be extracted through empirical mode decomposition.
步骤S30：根据空间滤波器构建头部模型，并根据矢量光束网格化所述头部模型。Step S30: Construct a head model according to the spatial filter, and grid the head model according to the vector beam.
需要说明的是，由于大脑信号中的信源在大脑中每一个地方包括三个偶极矩，每一个偶极矩都需要对应一个滤波器，每个滤波器能够被限定信号对应于大脑的特定位置，以此来模拟大脑内的信号传递以及活动。It should be noted that since the source of the brain signal includes three dipole moments in each place in the brain, each dipole moment needs to correspond to a filter, and each filter can be limited to the specific signal of the brain. position, in order to simulate the signal transmission and activity in the brain.
需要说明的是，可以通过3D矢量波形三个方向的矢量波束形成器计算头部模型的网格化的物理场。It should be noted that the meshed physical field of the head model can be calculated by using the vector beamformer in three directions of the 3D vector waveform.
步骤S40：确定所述特征分量的协方差矩阵，并根据所述协方差矩阵和网格化后头部模型的能量分布定位病灶。Step S40: Determine the covariance matrix of the feature components, and locate the lesion according to the covariance matrix and the energy distribution of the gridded posterior head model.
在具体实现中，根据约束条件确定特征分量的协方差矩阵，根据协方差矩阵确定头部模型每个网格点的能量值以及网格皮层的能量插值，根据网格点的能量值和网格皮层的能量插值进行能量场绘制，根据能量场的分布定位病灶。In the specific implementation, the covariance matrix of the feature components is determined according to the constraints, and the energy value of each grid point of the head model and the energy interpolation of the grid cortex are determined according to the covariance matrix. The energy interpolation of the cortex is used to draw the energy field, and the lesion is located according to the distribution of the energy field.
需要说明的是，可以根据能量场的分布强度定位病灶，能量场的强度越高代表是癫痫区域的可能越大。It should be noted that the lesion can be located according to the distribution intensity of the energy field, and the higher the intensity of the energy field, the greater the possibility of an epileptic area.
进一步地，为了提高病灶定位的效率，因此本实施例步骤S40可包括：Further, in order to improve the efficiency of focus location, step S40 in this embodiment may include:
根据约束条件和所述空间滤波器确定所述特征分量的协方差矩阵；determining a covariance matrix of the feature components according to constraints and the spatial filter;
根据所述协方差矩阵确定所述头部模型的网格能量值，并确定所述头部模型的网格能量插值；determining a grid energy value of the head model according to the covariance matrix, and determining a grid energy interpolation value of the head model;
根据所述网格能量值和所述网格能量插值绘制所述头部模型的皮层能量分布，并根据所述皮层能量分布定位病灶。Draw the cortical energy distribution of the head model according to the grid energy value and the grid energy interpolation, and locate the lesion according to the cortical energy distribution.
需要说明的是，空间滤波器会输出N*3的矩阵，根据线性相关约束矩阵的最小方差，即设置的预设条件为限制滤波器输出协方差矩阵为方差为最小方差。It should be noted that the spatial filter will output a matrix of N*3, according to the minimum variance of the linear correlation constraint matrix, that is, the preset condition is set to limit the variance of the filter output covariance matrix to the minimum variance.
可以理解的是，可以利用溯源方法根据协方差矩阵计算头部模型每个网格点的能量值并对头部模型进行插值。It can be understood that the traceability method can be used to calculate the energy value of each grid point of the head model according to the covariance matrix and interpolate the head model.
进一步地，为了提高病灶定位的效率，所述根据约束条件和所述空间滤波器确定所述特征分量的协方差矩阵的步骤，包括：Further, in order to improve the efficiency of lesion localization, the step of determining the covariance matrix of the feature components according to the constraints and the spatial filter includes:
根据偶极矩确定对应的空间滤波器，并根据所述空间滤波器形成的方差确定约束条件；determining a corresponding spatial filter according to the dipole moment, and determining a constraint condition according to a variance formed by the spatial filter;
根据约束条件和所述空间滤波器确定所述特征分量的协方差矩阵。A covariance matrix of the feature components is determined according to constraints and the spatial filter.
需要说明的是，每一个偶极矩对应一个空间滤波器，信源大脑中每一个地方对应三个偶极矩，因此每一个信源所在的地方需要设置三个空间滤波器。It should be noted that each dipole moment corresponds to a spatial filter, and each place in the brain of the source corresponds to three dipole moments, so three spatial filters need to be set where each source is located.
需要说明的是，空间滤波器生成的转换矩阵可能是线性独立，也可能是线性相关，如果线性相关则空间滤波器会产生较大的方差，导致最终的病灶定位结果不准确，因此需要设置方差最小的约束条件控制生成的协方差矩阵的方差。It should be noted that the transformation matrix generated by the spatial filter may be linearly independent or linearly correlated. If it is linearly correlated, the spatial filter will generate a large variance, resulting in inaccurate final lesion localization results. Therefore, it is necessary to set the variance The smallest constraint governs the variance of the resulting covariance matrix.
本实施例对预设范围内的信号进行时频分析，并根据分析后信号的包络确定目标信号；根据目标信号的频域变化、小波系数和局部峰值进行特征提取，获得特征分量；根据空间滤波器构建头部模型，并根据矢量光束网格化头部模型；确定特征分量的协方差矩阵，并根据协方差矩阵和网格化后头部模型的能量分布定位病灶。本实施例对滤波进行时频分析并根据分析后的信号包络确定目标信号，对目标信号进行特征提取获得特征分量并确定特征分量的协方差矩阵，建立头部模型并对头部模型网格化，根据网格化后的头部模型和协方差矩阵定位病灶，从而能防止因人工诊断而导致的误诊，并提高了诊断的效率。In this embodiment, the time-frequency analysis is performed on the signal within the preset range, and the target signal is determined according to the envelope of the analyzed signal; feature extraction is performed according to the frequency domain change, wavelet coefficient and local peak value of the target signal to obtain the feature component; according to the spatial The filter constructs the head model, and grids the head model according to the vector beam; determines the covariance matrix of the characteristic components, and localizes the lesion according to the covariance matrix and the energy distribution of the gridded head model. This embodiment performs time-frequency analysis on the filtering and determines the target signal according to the analyzed signal envelope, performs feature extraction on the target signal to obtain the feature components and determines the covariance matrix of the feature components, establishes the head model and meshes the head model According to the gridded head model and covariance matrix to locate the lesion, it can prevent misdiagnosis caused by manual diagnosis and improve the efficiency of diagnosis.
参照图3，图3为本发明病灶定位方法第二实施例的流程示意图，基于上述图2所示的第一实施例，提出本发明病灶定位方法的第二实施例。Referring to FIG. 3 , FIG. 3 is a schematic flowchart of a second embodiment of the method for locating a lesion of the present invention. Based on the first embodiment shown in FIG. 2 above, a second embodiment of the method for locating a lesion of the present invention is proposed.
在第二实施例中，所述步骤S20之后，包括：In the second embodiment, after the step S20, it includes:
步骤S201：根据所述特征分量确定特征向量，并根据所述特征向量确定初始特征图。Step S201: Determine a feature vector according to the feature components, and determine an initial feature map according to the feature vector.
需要说明的是，本实施例提出了另一种进行病灶定位的方法，通过递归图和递归图的熵进行病灶定位。It should be noted that this embodiment proposes another method for locating the lesion, which uses the recursive graph and the entropy of the recursive graph to locate the lesion.
可以理解的是，根据特征分量形成多通道向量，根据多通道向量和时间序列形成初始特征图。It can be understood that a multi-channel vector is formed from the feature components, and an initial feature map is formed from the multi-channel vector and the time series.
需要说明的是，初始特征图可以是一个N*N的递归图，即可以是一个N*N的矩阵。It should be noted that the initial feature map can be an N*N recursive map, that is, it can be an N*N matrix.
步骤S202：根据所述初始特征图确定初始列表集合，并从所述初始列表集合中选择任一两个列表集群进行比较。Step S202: Determine an initial list set according to the initial feature map, and select any two list clusters from the initial list set for comparison.
需要说明的是，根据初始特征图定义一个初始列表集合，初始列表集合中包含多个列表集群，每个列表集群包含每一列的向量。It should be noted that an initial list set is defined according to the initial feature map, and the initial list set contains multiple list clusters, and each list cluster contains a vector of each column.
可以理解的是，如果任一两个列表集群不为空，则将任一两个列表集群进行比较。It is understood that either two list clusters are compared if they are not empty.
步骤S203：根据比较结果进行筛选，并根据筛选结果获得目标列表集群。Step S203: Perform screening according to the comparison result, and obtain target list clusters according to the screening result.
需要说明的是，判断任一两个列表集群中是否存在相同的数据，如果有相同的数据则对任一两个列表集群进行调整，如果没有则判断任一两个列表集群是否与其他的集群列表进行比较，如果有，则在初始列表集合中选择列表集群与任一两个集群进行比较。It should be noted that it is judged whether there is the same data in any two list clusters, if there is the same data, any two list clusters are adjusted, if not, it is judged whether any two list clusters are consistent with other clusters lists to compare, and if there are any, select list clusters to compare with either two clusters in the initial set of lists.
进一步地，为了提高病灶定位的准确度，因此本实施例步骤S203可包括：Further, in order to improve the accuracy of focus location, step S203 of this embodiment may include:
在任一两个列表集群都不为空集时，判断所述任一两个列表集群是否有相同的数据；When any two list clusters are not empty sets, determine whether any two list clusters have the same data;
在所述任一两个列表集群中存在相同的数据时，将所述任一两个列表集群合并，获得目标列表集群；When the same data exists in any two list clusters, merging any two list clusters to obtain a target list cluster;
在所述任一两个列表集群中不存在相同的数据时，返回所述从所述初始列表集合中选择任一两个列表集群进行比较的步骤，直至第二比较次数达到第二预设阈值获得目标特征集群。When the same data does not exist in any two list clusters, return to the step of selecting any two list clusters from the initial list set for comparison until the second number of comparisons reaches a second preset threshold Obtain target feature clusters.
在具体实现中，判断任一两个列表集群是否为空集，在任一两个列表集群不存在空集时，对比任一两个列表集群是否存在相同的数据，在任一两个列表集群中不存在相同数据时，将任一两个列表集群合并形成目标列表集群，从初始列表集合中选择新的列表集群与目标列表集群进行对比，不断迭代直至所有的列表集群都进行比对。如果任一两个列表集群中不存在相同数据，则从初始列表集群中重新选择任一两个列表集群进行比较，知道比较次数达到预设一致，获得目标特征集群。In the specific implementation, it is judged whether any two list clusters are empty sets. When there is no empty set in any two list clusters, compare whether there is the same data in any two list clusters. When the same data exists, merge any two list clusters to form a target list cluster, select a new list cluster from the initial list set to compare with the target list cluster, and iterate continuously until all list clusters are compared. If the same data does not exist in any two list clusters, reselect any two list clusters from the initial list clusters for comparison, until the number of comparisons reaches the preset consistency, and obtain the target feature cluster.
步骤S204：将所述目标列表集群与所述初始列表集合中任一列表集群进行比较，并返回所述根据比较结果进行筛选，并根据筛选结果获得目标列表集群的步骤，直至第一比较次数达到第一预设阈值获得目标特征集群。Step S204: Compare the target list cluster with any list cluster in the initial list set, and return to the step of filtering according to the comparison result, and obtaining the target list cluster according to the screening result, until the first number of comparisons reaches The first preset threshold is used to obtain target feature clusters.
可以理解的是，通过不断将新生成的牧宝列表集群与初始列表集群中的剩余未进行比较的列表集群进行比较，不断的递归最终获得目标特征集群。It can be understood that by continuously comparing the newly generated Mubao list cluster with the remaining uncompared list clusters in the initial list cluster, the target feature cluster is finally obtained through continuous recursion.
进一步地，为了提高病灶定位的准确度，因此本实施例步骤S204之后还可包括：Further, in order to improve the accuracy of focus location, this embodiment may also include after step S204:
根据所述目标特征集群的数量和所述目标特征集群的相对频率确定所述目标特征集群的熵；determining the entropy of the target feature cluster based on the number of target feature clusters and the relative frequency of the target feature cluster;
根据所述熵和所述数量确定所述目标特征集群的熵率，并根据所述熵率定位病灶。An entropy rate of the target feature cluster is determined according to the entropy and the number, and a lesion is located according to the entropy rate.
需要说明的是，癫痫发病期间的熵率要高于不发病期间的熵率，因此可以根据熵率定位病灶。It should be noted that the entropy rate during the onset of epilepsy is higher than that during the non-onset period, so the lesion can be located according to the entropy rate.
需要说明的是，目标特征集群的熵和目标特征集群的熵率可以是：It should be noted that the entropy of the target feature cluster and the entropy rate of the target feature cluster can be:
； ;
； ;
式中，表示目标特征集群的熵，/>表示目标特征集群的熵率，/>表示目标特征集群的数量，/>表示目标特征集群的相对频率，/>表示常数。In the formula, Indicates the entropy of the target feature cluster, /> Indicates the entropy rate of the target feature cluster, /> Indicates the number of target feature clusters, /> Indicates the relative frequency of target feature clusters, /> represents a constant.
本实施例根据所述特征分量确定特征向量，并根据所述特征向量确定初始特征图；根据所述初始特征图确定初始列表集合，并从所述初始列表集合中选择任一两个列表集群进行比较；根据比较结果进行筛选，并根据筛选结果获得目标列表集群；将所述目标列表集群与所述初始列表集合中任一列表集群进行比较，并返回所述根据比较结果进行筛选，并根据筛选结果获得目标列表集群的步骤，直至第一比较次数达到第一预设阈值获得目标特征集群。本实施例根据初始列表集合不断的进行比较递归，从而获得目标特征集群，并根据目标特征集群确定熵率进行病灶定位，进而提高对病灶定位的精确度。In this embodiment, the feature vector is determined according to the feature components, and the initial feature map is determined according to the feature vector; the initial list set is determined according to the initial feature map, and any two list clusters are selected from the initial list set to perform Compare; filter according to the comparison result, and obtain the target list cluster according to the filter result; compare the target list cluster with any list cluster in the initial list set, and return the filter according to the comparison result, and obtain the target list cluster according to the filter As a result, in the step of obtaining target list clusters, the target feature clusters are obtained until the first number of comparisons reaches a first preset threshold. In this embodiment, the comparison and recursion are continuously performed according to the initial list set, so as to obtain target feature clusters, and the entropy rate is determined according to the target feature clusters to locate lesions, thereby improving the accuracy of locating lesions.
此外，本发明实施例还提出一种存储介质，所述存储介质上存储有病灶定位程序，所述病灶定位程序被处理器执行时实现如上文所述的病灶定位方法。In addition, an embodiment of the present invention also proposes a storage medium, on which a lesion localization program is stored, and when the lesion localization program is executed by a processor, the above-mentioned lesion localization method is realized.
此外，参照图4，本发明实施例还提出一种病灶定位装置，所述病灶定位装置包括：信号确定模块10、分量确定模块20、模型确定模块30及病灶定位模块40；In addition, referring to FIG. 4 , an embodiment of the present invention also proposes a lesion localization device, which includes: a signal determination module 10 , a component determination module 20 , a model determination module 30 and a lesion localization module 40 ;
所述信号确定模块10，用于对预设范围内的信号进行时频分析，并根据分析后信号的包络确定目标信号；The signal determination module 10 is configured to perform time-frequency analysis on signals within a preset range, and determine a target signal according to the envelope of the analyzed signal;
所述分量确定模块20，用于根据所述目标信号的频域变化、小波系数和局部峰值进行特征提取，获得特征分量；The component determination module 20 is configured to perform feature extraction according to frequency domain changes, wavelet coefficients and local peaks of the target signal to obtain feature components;
所述模型确定模块30，用于根据空间滤波器构建头部模型，并根据矢量光束网格化所述头部模型；The model determination module 30 is configured to construct a head model according to a spatial filter, and grid the head model according to a vector beam;
所述病灶定位模块40，用于确定所述特征分量的协方差矩阵，并根据所述协方差矩阵和网格化后头部模型的能量分布定位病灶。The lesion localization module 40 is configured to determine the covariance matrix of the feature components, and locate the lesion according to the covariance matrix and the energy distribution of the gridded posterior head model.
本实施例对预设范围内的信号进行时频分析，并根据分析后信号的包络确定目标信号；根据目标信号的频域变化、小波系数和局部峰值进行特征提取，获得特征分量；根据空间滤波器构建头部模型，并根据矢量光束网格化头部模型；确定特征分量的协方差矩阵，并根据协方差矩阵和网格化后头部模型的能量分布定位病灶。本实施例对滤波进行时频分析并根据分析后的信号包络确定目标信号，对目标信号进行特征提取获得特征分量并确定特征分量的协方差矩阵，建立头部模型并对头部模型网格化，根据网格化后的头部模型和协方差矩阵定位病灶，从而能防止因人工诊断而导致的误诊，并提高了诊断的效率。In this embodiment, the time-frequency analysis is performed on the signal within the preset range, and the target signal is determined according to the envelope of the analyzed signal; feature extraction is performed according to the frequency domain change, wavelet coefficient and local peak value of the target signal to obtain the feature component; according to the spatial The filter constructs the head model, and grids the head model according to the vector beam; determines the covariance matrix of the characteristic components, and localizes the lesion according to the covariance matrix and the energy distribution of the gridded head model. This embodiment performs time-frequency analysis on the filtering and determines the target signal according to the analyzed signal envelope, performs feature extraction on the target signal to obtain the feature components and determines the covariance matrix of the feature components, establishes the head model and meshes the head model According to the gridded head model and covariance matrix to locate the lesion, it can prevent misdiagnosis caused by manual diagnosis and improve the efficiency of diagnosis.
基于本发明上述病灶定位装置第一实施例，提出本发明病灶定位装置的第二实施例。Based on the first embodiment of the above-mentioned lesion localization device of the present invention, a second embodiment of the lesion localization device of the present invention is proposed.
在本实施例中，所述病灶定位模块40，用于根据约束条件和所述空间滤波器确定所述特征分量的协方差矩阵。In this embodiment, the lesion localization module 40 is configured to determine the covariance matrix of the feature components according to the constraints and the spatial filter.
进一步地，所述病灶定位模块40，还用于根据所述协方差矩阵确定所述头部模型的网格能量值，并确定所述头部模型的网格能量插值。Further, the lesion localization module 40 is further configured to determine the grid energy value of the head model according to the covariance matrix, and determine the grid energy interpolation of the head model.
进一步地，所述病灶定位模块40，还用于根据所述网格能量值和所述网格能量插值绘制所述头部模型的皮层能量分布，并根据所述皮层能量分布定位病灶。Further, the lesion localization module 40 is further configured to draw the cortical energy distribution of the head model according to the grid energy value and the grid energy interpolation, and locate the lesion according to the cortical energy distribution.
进一步地，所述病灶定位模块40，还用于根据偶极矩确定对应的空间滤波器，并根据所述空间滤波器形成的方差确定约束条件。Further, the lesion localization module 40 is further configured to determine the corresponding spatial filter according to the dipole moment, and determine the constraint condition according to the variance formed by the spatial filter.
进一步地，所述病灶定位模块40，还用于根据约束条件和所述空间滤波器确定所述特征分量的协方差矩阵。Further, the lesion localization module 40 is further configured to determine the covariance matrix of the feature components according to the constraints and the spatial filter.
进一步地，所述信号确定模块10，还用于获取预设范围内的信号，并划分所述信号确定划分后各段信号的小波熵。Further, the signal determination module 10 is further configured to obtain signals within a preset range, and divide the signals to determine the wavelet entropy of each segment of the signal after division.
进一步地，所述信号确定模块10，还用于根据所述小波熵确定检测阈值，并确定所述各段信号的信号包络。Further, the signal determination module 10 is further configured to determine a detection threshold according to the wavelet entropy, and determine a signal envelope of each segment of the signal.
进一步地，所述信号确定模块10，还用于在所述信号包络大于所述检测阈值时，将所述信号包络对应的信号作为待检测信号。Further, the signal determination module 10 is further configured to use the signal corresponding to the signal envelope as the signal to be detected when the signal envelope is greater than the detection threshold.
进一步地，所述信号确定模块10，还用于在对所述待检测信号的检测时长超过预设阈值时，将所述待检测信号作为目标信号。Further, the signal determining module 10 is further configured to use the signal to be detected as a target signal when the detection duration of the signal to be detected exceeds a preset threshold.
进一步地，所述分量确定模块20，还用于根据所述特征分量确定特征向量，并根据所述特征向量确定初始特征图。Further, the component determining module 20 is further configured to determine a feature vector according to the feature component, and determine an initial feature map according to the feature vector.
进一步地，所述分量确定模块20，还用于根据所述初始特征图确定初始列表集合，并从所述初始列表集合中选择任一两个列表集群进行比较。Further, the component determining module 20 is further configured to determine an initial list set according to the initial feature map, and select any two list clusters from the initial list set for comparison.
进一步地，所述分量确定模块20，还用于根据比较结果进行筛选，并根据筛选结果获得目标列表集群。Further, the component determination module 20 is further configured to perform screening according to the comparison result, and obtain target list clusters according to the screening result.
进一步地，所述分量确定模块20，还用于将所述目标列表集群与所述初始列表集合中任一列表集群进行比较，并返回所述根据比较结果进行筛选，并根据筛选结果获得目标列表集群的步骤，直至第一比较次数达到第一预设阈值获得目标特征集群。Further, the component determination module 20 is further configured to compare the target list cluster with any list cluster in the initial list set, and return the filter according to the comparison result, and obtain the target list according to the filter result In the step of clustering, the target feature cluster is obtained until the first number of comparisons reaches a first preset threshold.
进一步地，所述分量确定模块20，还用于在任一两个列表集群都不为空集时，判断所述任一两个列表集群是否有相同的数据。Further, the component determination module 20 is further configured to determine whether any two list clusters have the same data when any two list clusters are not empty sets.
进一步地，所述分量确定模块20，还用于在所述任一两个列表集群中存在相同的数据时，将所述任一两个列表集群合并，获得目标列表集群。Further, the component determining module 20 is further configured to merge any two list clusters to obtain a target list cluster when the same data exists in any two list clusters.
进一步地，所述分量确定模块20，还用于在所述任一两个列表集群中不存在相同的数据时，返回所述从所述初始列表集合中选择任一两个列表集群进行比较的步骤，直至第二比较次数达到第二预设阈值获得目标特征集群。Further, the component determination module 20 is further configured to return the result of selecting any two list clusters from the initial list set for comparison when the same data does not exist in any two list clusters. step until the second number of comparisons reaches a second preset threshold to obtain the target feature cluster.
进一步地，所述分量确定模块20，还用于根据所述目标特征集群的数量和所述目标特征集群的相对频率确定所述目标特征集群的熵。Further, the component determining module 20 is further configured to determine the entropy of the target feature cluster according to the quantity of the target feature cluster and the relative frequency of the target feature cluster.
进一步地，所述分量确定模块20，还用于根据所述熵和所述数量确定所述目标特征集群的熵率，并根据所述熵率定位病灶。Further, the component determination module 20 is further configured to determine the entropy rate of the target feature cluster according to the entropy and the quantity, and locate the lesion according to the entropy rate.
本发明所述病灶定位装置的其他实施例或具体实现方式可参照上述各方法实施例，此处不再赘述。For other embodiments or specific implementations of the lesion locating device of the present invention, reference may be made to the above-mentioned method embodiments, which will not be repeated here.
需要说明的是，在本文中，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者系统不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者系统所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括该要素的过程、方法、物品或者系统中还存在另外的相同要素。It should be noted that, as used herein, the term "comprises", "comprises" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article or system comprising a set of elements includes not only those elements, It also includes other elements not expressly listed, or elements inherent in the process, method, article, or system. Without further limitations, an element defined by the phrase "comprising a..." does not preclude the presence of additional identical elements in the process, method, article or system comprising that element.
上述本发明实施例序号仅仅为了描述，不代表实施例的优劣。The serial numbers of the above embodiments of the present invention are for description only, and do not represent the advantages and disadvantages of the embodiments.
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到上述 实施例方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通 过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本发明的技术方案本质上或者说对现有技术做出贡献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(如只读存储器镜像（Read Only Memory image，ROM）/随机存取存储器（Random AccessMemory，RAM）、磁碟、光盘)中，包括若干指令用以使得一台终端设备(可以是手机，计算机，服务器，空调器，或者网络设备等)执行本发明各个实施例所述的方法。Through the description of the above embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus a necessary general-purpose hardware platform, and of course also by hardware, but in many cases the former is better implementation. Based on such an understanding, the essence of the technical solution of the present invention or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product is stored in a storage medium (such as a read-only memory image (Read Only Memory image, ROM)/random access memory (Random Access Memory, RAM, disk, CD), including several instructions to make a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) ) to perform the methods described in various embodiments of the present invention.
以上仅为本发明的优选实施例，并非因此限制本发明的专利范围，凡是利用本发明说明书及附图内容所作的等效结构或等效流程变换，或直接或间接运用在其他相关的技术领域，均同理包括在本发明的专利保护范围内。The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process conversion made by using the description of the present invention and the contents of the accompanying drawings, or directly or indirectly used in other related technical fields , are all included in the scope of patent protection of the present invention in the same way.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310851595.0ACN116548950B (en) | 2023-07-12 | 2023-07-12 | Lesion localization methods, devices, equipment and storage media |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310851595.0ACN116548950B (en) | 2023-07-12 | 2023-07-12 | Lesion localization methods, devices, equipment and storage media |
| Publication Number | Publication Date |
|---|---|
| CN116548950Atrue CN116548950A (en) | 2023-08-08 |
| CN116548950B CN116548950B (en) | 2023-11-10 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310851595.0AActiveCN116548950B (en) | 2023-07-12 | 2023-07-12 | Lesion localization methods, devices, equipment and storage media |
| Country | Link |
|---|---|
| CN (1) | CN116548950B (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5263488A (en)* | 1992-10-05 | 1993-11-23 | Nicolet Instrument Corporation | Method and apparatus for localization of intracerebral sources of electrical activity |
| US20130249784A1 (en)* | 2012-03-22 | 2013-09-26 | Fredrik BR Gustafson | Method and Device for Pose Tracking Using Vector Magnetometers |
| CN107080534A (en)* | 2017-02-24 | 2017-08-22 | 浙江大学 | The epileptogenic focus point rough localization method being imaged based on EEG sources |
| CN108024752A (en)* | 2015-09-07 | 2018-05-11 | 加利福尼亚大学董事会 | Brian Imaging system based on ultra dense electrode |
| US20180360372A1 (en)* | 2017-06-20 | 2018-12-20 | The Board Of Trustees Of The University Of Illinois | Method of identifying epileptic brain regions |
| CN113269225A (en)* | 2021-04-08 | 2021-08-17 | 浙江大学 | Non-invasive liver epithelium sample vascular smooth muscle lipoma image classification device based on image omics |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5263488A (en)* | 1992-10-05 | 1993-11-23 | Nicolet Instrument Corporation | Method and apparatus for localization of intracerebral sources of electrical activity |
| US20130249784A1 (en)* | 2012-03-22 | 2013-09-26 | Fredrik BR Gustafson | Method and Device for Pose Tracking Using Vector Magnetometers |
| CN108024752A (en)* | 2015-09-07 | 2018-05-11 | 加利福尼亚大学董事会 | Brian Imaging system based on ultra dense electrode |
| CN107080534A (en)* | 2017-02-24 | 2017-08-22 | 浙江大学 | The epileptogenic focus point rough localization method being imaged based on EEG sources |
| US20180360372A1 (en)* | 2017-06-20 | 2018-12-20 | The Board Of Trustees Of The University Of Illinois | Method of identifying epileptic brain regions |
| CN113269225A (en)* | 2021-04-08 | 2021-08-17 | 浙江大学 | Non-invasive liver epithelium sample vascular smooth muscle lipoma image classification device based on image omics |
| Publication number | Publication date |
|---|---|
| CN116548950B (en) | 2023-11-10 |
| Publication | Publication Date | Title |
|---|---|---|
| WO2021017307A1 (en) | Non-contact heart rate measurement method, system, device, and storage medium | |
| EP3718473A1 (en) | Intracerebral network activity estimation system, intracerebral network activity estimation method, intracerebral network activity estimation program, and learned brain activity estimation model | |
| US10303447B2 (en) | Program generating apparatus and method therefor | |
| US20160314800A1 (en) | Computationally efficient method for filtering noise | |
| CN115363523B (en) | An epileptic seizure zone positioning system, device and medium | |
| CN110598696A (en) | Medical image scanning positioning method, medical image scanning method and computer equipment | |
| CN111863014A (en) | Audio processing method and device, electronic equipment and readable storage medium | |
| CN108937920B (en) | Ventricular fibrillation signal detection method, system and ventricular fibrillation detection device | |
| CN119279530A (en) | Pulse detection method, system and device based on optimization of micro-motion amplification parameters | |
| CN116548950B (en) | Lesion localization methods, devices, equipment and storage media | |
| CN114882901B (en) | A method for extracting time-frequency features of shrimp sound signals based on frequency domain convolution and marginal spectrum feedback | |
| US12150814B2 (en) | Ultrasonic signal processing method and apparatus, device and storage medium | |
| CN110464345B (en) | Independent head biological power supply signal interference elimination method and system | |
| WO2019028551A1 (en) | Systems and methods for assessing functional magnetic resonance imaging data quality using regularization of frequency-domain entrophy | |
| Safara | Cumulant-based trapezoidal basis selection for heart sound classification | |
| CN117952195A (en) | Brain network construction method and display equipment based on task related brain electrical activity | |
| CN108113669A (en) | A kind of epileptic focus localization method and system | |
| CN112200072A (en) | A method and device for evaluating data quality | |
| Kulik et al. | Comparing individual and group-level simulated neurophysiological brain connectivity using the Jansen and Rit neural mass model | |
| Lenz et al. | Joint EEG/fMRI state space model for the detection of directed interactions in human brains—a simulation study | |
| KR101508436B1 (en) | Apparatus and method for detecting signal optimally | |
| CN119949794A (en) | Wearable device, heart rate tracking method and heart rate tracking device thereof | |
| WO2020168697A1 (en) | Ai identification method of embolism based on vrds 4d medical image, and product | |
| KR102406917B1 (en) | Recorded media recording of the signal compression apparatus, method and program for performing the analysis based on template signal | |
| CN113380423B (en) | Epidemic situation scale prediction method and device, electronic equipment and storage medium |
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |