Closed-loop nerve regulation and control method and system based on transcranial light

Abstract

The invention provides a closed-loop nerve regulation and control method and system based on transcranial light, and the method comprises the steps: obtaining scale data, brain blood oxygen information and electroencephalogram information of a target user, and inputting the information into a pre-trained target brain function rehabilitation prediction model; and the target brain function rehabilitation prediction model outputs a brain function rehabilitation prediction result of the target user based on the information, and adjusts a light regulation and control scheme of the target user based on the brain function rehabilitation prediction result. Therefore, the target brain function rehabilitation prediction model obtains sufficient and comprehensive input information, an accurate brain function rehabilitation prediction result can be output, the accuracy of a light regulation and control scheme obtained based on the brain function rehabilitation prediction result is improved, and the gain of transcranial light regulation and control is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical devices, and in particular, to a closed-loop neuromodulation method and system based on transcranial light. Background Art

[0002] Stroke is the leading cause of death and disability among residents, showing the characteristics of high incidence, high disability rate, high mortality rate, and high recurrence rate. Although patients can receive rehabilitation treatment, about 60%-80% of stroke patients still have obvious motor function impairments, bringing heavy care costs to families and society.

[0003] Non-invasive stimulation of the brain, central nervous system, muscles, etc. of patients through physical stimuli such as sound, light, electricity, and magnetism can improve cortical activity after a period of stimulation to promote the reconstruction of neural circuits and motor functions, which is an important development direction of neuromodulation. Correspondingly, how to perform transcranial light stimulation on patients and improve the accuracy of transcranial light stimulation is an important issue in neuromodulation. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a closed-loop neuromodulation method and system based on transcranial light to improve the accuracy of transcranial light stimulation.

[0005] According to one aspect of the present invention, there is provided a closed-loop neuromodulation method based on transcranial light, the method comprising:

[0006] Obtaining detection data to be detected of a target user, wherein the detection data to be detected includes scale data, cerebral blood oxygen data, and electroencephalogram data of the target user;

[0007] Inputting the detection data to be detected into a pre-trained target brain function rehabilitation prediction model, and obtaining a target brain function rehabilitation result output by the target brain function rehabilitation prediction model based on the detection data to be detected;

[0008] Adjusting a target light modulation scheme of the target user based on the target brain function rehabilitation result, wherein the target light modulation scheme includes the position of transcranial light stimulation;

[0009] Wherein, the target brain function rehabilitation prediction model is pre-trained through the following steps:

[0010] Obtaining a training data set, the training data set contains multiple pieces of training data, each piece of training data includes scale data, cerebral blood oxygen data, and electroencephalogram data of a user; each piece of training data corresponds to a brain function rehabilitation label, and the brain function rehabilitation label is the actual brain function rehabilitation result of the user;

[0011] Input the training data set into the initial brain function rehabilitation prediction model, so that the initial brain function rehabilitation prediction model outputs the brain function rehabilitation prediction results corresponding to each training data based on the training data set;

[0012] Adjust the parameters of the brain function rehabilitation prediction model based on the target difference between the brain function rehabilitation prediction results corresponding to each training data and the brain function rehabilitation labels of each training data until the target difference converges;

[0013] Take the brain function rehabilitation prediction model corresponding to the convergence of the target difference as the target brain function rehabilitation prediction model.

[0014] In a possible embodiment, before inputting the data to be detected into the pre-trained target brain function rehabilitation prediction model, it includes:

[0015] Extract the brain hemisphere activation index, brain lateralization index and hemisphere functional connectivity index based on the brain blood oxygen data of the target user;

[0016] Extract the global efficiency index and local efficiency index of different frequency bands based on the electroencephalogram data of the target user;

[0017] The step of inputting the data to be detected into the pre-trained target brain function rehabilitation prediction model includes:

[0018] Input the brain hemisphere activation index, brain lateralization index, hemisphere functional connectivity index, global efficiency index and local efficiency index of different frequency bands into the target brain function rehabilitation prediction model.

[0019] In a possible embodiment, the method further includes:

[0020] Normalize the scale data for the data to be detected, and filter the noise of the brain blood oxygen data and electroencephalogram data;

[0021] The step of inputting the data to be detected into the pre-trained target brain function rehabilitation prediction model includes:

[0022] Input the normalized scale data, filtered brain blood oxygen data and electroencephalogram data into the pre-trained target brain function rehabilitation prediction model.

[0023] In a possible embodiment, the step of adjusting the target light regulation scheme of the target user based on the target brain function rehabilitation result includes:

[0024] In the case where the target brain function rehabilitation result is higher than the first preset threshold, perform transcranial light stimulation on the first brain functional area of the target user;

[0025] When the target brain function rehabilitation result is lower than the second preset threshold, transcranial light stimulation is performed on the second brain function area of the target user, where the second preset threshold is smaller than the first preset threshold;

[0026] When the target brain function rehabilitation result is between the second preset threshold and the first preset threshold, transcranial light stimulation is performed on the first brain function area and the second brain function area of the target user.

[0027] In a possible embodiment, the method further includes:

[0028] During the process of performing transcranial light stimulation on the target user according to the target light regulation scheme, the real-time electroencephalogram data of the target user is continuously monitored, and the light stimulation parameters of the transcranial light are adjusted based on the real-time electroencephalogram data, where the light stimulation parameters include light stimulation intensity.

[0029] According to another aspect of the present invention, a closed-loop neural regulation system based on transcranial light is provided, and the system includes:

[0030] An acquisition module, configured to acquire the data to be detected of the target user, where the data to be detected includes the scale data, cerebral blood oxygen data, and electroencephalogram data of the target user;

[0031] An input module, configured to input the data to be detected into a pre-trained target brain function rehabilitation prediction model, and acquire the target brain function rehabilitation result output by the target brain function rehabilitation prediction model based on the data to be detected;

[0032] An adjustment module, configured to adjust the target light regulation scheme of the target user based on the target brain function rehabilitation result, where the target light regulation scheme includes the position of the transcranial light stimulation;

[0033] Wherein, the target brain function rehabilitation prediction model is pre-trained through the following steps:

[0034] Acquire a training data set, where the training data set contains multiple pieces of training data, and each piece of training data contains the scale data, cerebral blood oxygen data, and electroencephalogram data of the user; each piece of training data corresponds to a brain function rehabilitation label, and the brain function rehabilitation label is the actual brain function rehabilitation result of the user;

[0035] Input the training data set into an initial brain function rehabilitation prediction model, so that the initial brain function rehabilitation prediction model outputs the brain function rehabilitation prediction results corresponding to each piece of training data based on the training data set;

[0036] Adjust the parameters of the brain function rehabilitation prediction model based on the target difference between the brain function rehabilitation prediction results corresponding to each of the training data and the brain function rehabilitation labels of each of the training data until the target difference converges;

[0037] Use the brain function rehabilitation prediction model corresponding to the convergence of the target difference as the target brain function rehabilitation prediction model.

[0038] In a possible embodiment, the system further includes:

[0039] An extraction module, configured to extract a brain hemisphere activation index, a brain lateralization index, and a hemisphere functional connectivity index based on the cerebral blood oxygen data of the target user; and extract a global efficiency index and a local efficiency index of different frequency bands based on the electroencephalogram data of the target user;

[0040] The step of inputting the data to be detected into the pre-trained target brain function rehabilitation prediction model includes:

[0041] Input the brain hemisphere activation index, the brain lateralization index, the hemisphere functional connectivity index, the global efficiency index of different frequency bands, and the local efficiency index into the target brain function rehabilitation prediction model.

[0042] In a possible embodiment, the system further includes:

[0043] A preprocessing module, configured to normalize the scale data for the data to be detected, and filter noise from the cerebral blood oxygen data and the electroencephalogram data;

[0044] The step of inputting the data to be detected into the pre-trained target brain function rehabilitation prediction model includes:

[0045] Input the normalized scale data, the filtered cerebral blood oxygen data, and the electroencephalogram data into the pre-trained target brain function rehabilitation prediction model.

[0046] In a possible embodiment, the step of adjusting the target light regulation scheme of the target user based on the target brain function rehabilitation result includes:

[0047] In the case where the target brain function rehabilitation result is higher than a first preset threshold, perform transcranial light stimulation on the first brain functional area of the target user;

[0048] In the case where the target brain function rehabilitation result is lower than a second preset threshold, perform transcranial light stimulation on the second brain functional area of the target user, where the second preset threshold is less than the first preset threshold;

[0049] When the target brain function rehabilitation result is between the second preset threshold and the first preset threshold, transcranial light stimulation is performed on the first brain functional area and the second brain functional area of the target user.

[0050] In a possible embodiment, the system further includes:

[0051] A feedback module, configured to continuously monitor the real-time electroencephalogram data of the target user during the transcranial light stimulation of the target user according to the target light regulation scheme, and adjust the light stimulation parameters of the transcranial light based on the real-time electroencephalogram data, where the light stimulation parameters include the light stimulation intensity.

[0052] In one or more technical solutions provided in the embodiments of the present invention, by obtaining the scale data, cerebral blood oxygen information, and electroencephalogram information of the target user, and inputting this information into a pre-trained target brain function rehabilitation prediction model, the target brain function rehabilitation prediction model outputs the brain function rehabilitation prediction result of the target user based on the above information, and adjusts the light regulation scheme of the target user based on the brain function rehabilitation prediction result. Since the scale data, cerebral blood oxygen information, and electroencephalogram information contain multi-faceted brain function information of the target user, the target brain function rehabilitation prediction model obtains sufficiently comprehensive input information, and thus can output an accurate brain function rehabilitation prediction result, improving the accuracy of the light regulation scheme obtained based on the brain function rehabilitation prediction result, and further improving the gain of transcranial light regulation. Furthermore, the target brain function rehabilitation training model is trained based on the multi-faceted brain function data of a large number of users, enabling the target brain function rehabilitation prediction model to learn the correlation between a large amount of brain function data and the brain function rehabilitation result, further improving the accuracy of the output brain function rehabilitation prediction result and the gain of transcranial light regulation. Description of the Drawings

[0053] In the following description of the exemplary embodiments in conjunction with the drawings, more details, features, and advantages of the present invention are disclosed. In the drawings:

[0054] Figure 1 It is a schematic flowchart of a method for closed-loop neural regulation based on transcranial light provided by an embodiment of the present invention;

[0055] Figure 2 It is a schematic flowchart of the training of a target brain function rehabilitation prediction model in the method for closed-loop neural regulation based on transcranial light provided by an embodiment of the present invention;

[0056] Figure 3 It is a schematic logical structure diagram of a closed-loop neural regulation system based on transcranial light provided by an embodiment of the present invention;

[0057] Figure 4Another schematic diagram of the logical structure of the closed-loop neural regulation system based on transcranial light provided by the embodiments of the present invention. Detailed implementation manners

[0058] Embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although some embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Instead, these embodiments are provided to more thoroughly and completely understand the present invention. It should be understood that the drawings and embodiments of the present invention are only for exemplary purposes and are not used to limit the protection scope of the present invention.

[0059] It should be understood that the steps described in the method embodiments of the present invention can be executed in different orders and / or executed in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this regard.

[0060] As used herein, the term "including" and its variations are open-ended, that is, "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description. It should be noted that the concepts such as "first" and "second" mentioned in the present invention are only used to distinguish different devices, modules or units, and are not used to limit the order of the functions executed by these devices, modules or units or the interdependent relationship.

[0061] It should be noted that the modifications of "one" and "multiple" mentioned in the present invention are illustrative rather than restrictive. Those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0062] The names of the messages or information exchanged between multiple devices in the embodiments of the present invention are only for illustrative purposes and are not used to limit the scope of these messages or information.

[0063] In order to improve the accuracy of transcranial light stimulation, the present invention provides a closed-loop neural regulation method and system based on transcranial light. The closed-loop neural regulation method based on transcranial light provided by the present invention can be applied to any electronic device with closed-loop neural regulation function. The electronic device can be a computer, a mobile terminal, etc. The solution of the present invention will be described below with reference to the accompanying drawings:

[0064] Figure 1 A flowchart of a closed-loop neural regulation method based on transcranial light provided by an embodiment of the present invention,

[0065] S101. Obtain the data to be detected of the target user, where the data to be detected includes the scale data, cerebral blood oxygen data, and electroencephalogram data of the target user;

[0066] S102. Input the data to be detected of the target user into a pre-trained target brain function rehabilitation prediction model, and obtain the target brain function rehabilitation result output by the target brain function rehabilitation prediction model based on the data to be detected;

[0067] S103. Adjust the target light regulation plan of the target user based on the target brain function rehabilitation result, where the target light regulation plan includes the position of transcranial light stimulation;

[0068] Among them, the target brain function rehabilitation prediction model is pre-trained through the following steps:

[0069] S201. Obtain a training data set, where the training data set contains multiple pieces of training data, and each piece of training data includes the scale data, cerebral blood oxygen data, and electroencephalogram data of the user; each piece of training data corresponds to a brain function rehabilitation label, and the brain function rehabilitation label is the actual brain function rehabilitation result of the user;

[0070] S202. Input the training data set into an initial brain function rehabilitation prediction model, so that the initial brain function rehabilitation prediction model outputs the brain function rehabilitation prediction results corresponding to each piece of training data based on the training data set;

[0071] S203. Adjust the parameters of the brain function rehabilitation prediction model based on the target difference between the brain function rehabilitation prediction results corresponding to each piece of training data and the brain function rehabilitation labels of each piece of training data until the target difference converges;

[0072] S204. Use the brain function rehabilitation prediction model corresponding to when the target difference converges as the target brain function rehabilitation prediction model.

[0073] Applying the embodiments of the present invention, by obtaining the scale data, cerebral blood oxygen information, and electroencephalogram information of the target user, and inputting this information into a pre-trained target brain function rehabilitation prediction model, the target brain function rehabilitation prediction model outputs the brain function rehabilitation prediction result of the target user based on the above information, and adjusts the light regulation scheme of the target user based on this brain function rehabilitation prediction result. Since the scale data, cerebral blood oxygen information, and electroencephalogram information contain the brain function information of multiple aspects of the target user, the target brain function rehabilitation prediction model obtains sufficient and comprehensive input information, and thus can output an accurate brain function rehabilitation prediction result, improving the accuracy of the light regulation scheme obtained based on the brain function rehabilitation prediction result, and further improving the gain of transcranial light regulation. Moreover, the target brain function rehabilitation training model is trained based on the brain function data of multiple aspects of a large number of users, enabling the target brain function rehabilitation prediction model to learn the correlation between a large amount of brain function data and the brain function rehabilitation result, further improving the accuracy of the output brain function rehabilitation prediction result and the gain of transcranial light regulation.

[0074] The following is an exemplary description of the above S101 - S103 and S201 - S204:

[0075] In the present invention, the target user refers to a user who needs to undergo transcranial light neuroregulation. In a possible embodiment, the data to be detected of the target user can be collected before the target user undergoes transcranial light neuroregulation to generate or adjust the light regulation scheme of the target user. In a possible embodiment, the data to be detected of the target user can be collected during the process of the target user's rehabilitation training, and the rehabilitation training can include any rehabilitation training scenarios, such as upper limb rehabilitation, lower limb rehabilitation, etc.

[0076] As a possible implementation manner, the data to be detected of the target user can be collected when the target user is in the resting state and the upper limb rehabilitation training state. Among them, the resting state refers to the state where the target user is in a non - active and resting state, in which the body and brain of the target user are in a relatively relaxed and static state; the upper limb rehabilitation training state refers to the state where the target user is undergoing upper limb rehabilitation training, in which the body of the user is in a moving state. By collecting the data to be detected of the target user in the static state and the moving state, the data to be detected can more comprehensively reflect the brain function of the user.

[0077] The above data to be detected may include the clinical scale data, cerebral blood oxygen data, and electroencephalogram data of the target user. Among them, the clinical scale data refers to the physical signs information and laboratory examination data of the target user, etc., such as the upper limb movement condition rating and lower limb movement condition rating of the target user. Exemplarily, various clinical scale data generated by the target user can be stored corresponding to the target user identifier, and the target user identifier can be the code or identity information of the target user. Correspondingly, the corresponding clinical scale data can be obtained based on the target user identifier. As a possible implementation manner, a near-infrared brain function imaging device can be used to collect the cerebral blood oxygen data of the target patient.

[0078] After obtaining the data to be detected of the target user, the data to be detected can be input into a pre-trained target brain function rehabilitation prediction model, and the target brain function rehabilitation prediction model outputs the target brain function rehabilitation result of the target user based on the data to be detected.

[0079] The above target brain function rehabilitation prediction model can be pre-trained based on a preset training data set, and the training data set includes multiple pieces of training data. Each piece of training data can include the clinical scale information, cerebral blood oxygen information, and electroencephalogram information of the user. As a possible implementation manner, the clinical scale data, cerebral blood oxygen data, and electroencephalogram data of each user who needs to perform transcranial optoneuroregulation can be stored corresponding to the user identifier in a historical database, and when the model is trained, the clinical scale data, cerebral blood oxygen data, and electroencephalogram data of each user can be obtained from the historical database based on the user identifier to form a training data set.

[0080] In a possible embodiment, each piece of user data stored in the historical database can be divided according to a preset ratio to obtain a training data set and a validation data set. The preset ratio can be set according to the actual application scenario. Exemplarily, the user data in the historical database can be divided according to a ratio of 7:3 to obtain a training data set and a validation data set.

[0081] Each training data set in the training data set corresponds to a specific brain function rehabilitation label, and the brain function rehabilitation label identifies the brain function recovery result of the user. The specific content of the brain function recovery result can be set according to the actual application scenario. Exemplarily, it can be set that the brain function rehabilitation label can identify good recovery, medium recovery, and poor recovery, and the specific content of the brain function rehabilitation label can be 1, 0.5, and 0 respectively.

[0082] The structure of the above target brain function rehabilitation model can be flexibly selected according to the actual application scenario. For example, it can be a CNN (Convolutional Neural Network), an RNN (Recurrent Neural Network), etc.

[0083] In a possible embodiment, the above training data set can be output to an initial brain function rehabilitation prediction model, which can extract features from each piece of training data and output a predicted brain function improvement prediction result corresponding to each training data based on the extracted features.

[0084] After that, the target difference between the predicted brain function improvement result corresponding to each piece of training data and the brain function rehabilitation label corresponding to the training data can be calculated. The target difference can be calculated based on a preset loss function, which can be a cross-entropy loss function, a variance loss function, etc.

[0085] After obtaining the target difference, the parameters of the brain function improvement model can be adjusted based on the target difference. Specifically, the model parameters can be adjusted by methods such as gradient descent and gradient ascent until the above target difference converges. The convergence of the target difference means that the difference between the target differences obtained in two consecutive iterative trainings is less than a preset difference threshold, or the target difference is less than a preset difference threshold.

[0086] In a possible embodiment, before inputting the above training data set into the brain function rehabilitation prediction model, the training data can be preprocessed and index data can be extracted. The preprocessing process can include normalizing clinical scale data. Specifically, the scale data can be normalized by methods such as maximum normalization and Z-core normalization. The above preprocessing process can also include filtering the cerebral blood oxygen signal and the electroencephalogram signal to remove noise and artifacts. Exemplarily, the cerebral blood oxygen signal and the electroencephalogram signal can be filtered by low-pass filtering, high-pass filtering, etc. according to the actual application scenario.

[0087] The above index data extraction can specifically include extracting cerebral hemisphere activation indexes, laterality, and hemisphere functional connection indexes from the cerebral blood oxygen signal; extracting global efficiency and local efficiency indexes of different frequency bands from the electroencephalogram signal.

[0088] The cerebral hemisphere activation index is used to evaluate the activity level of the two hemispheres of the brain in a specific task or state. In the rehabilitation task, the two hemispheres of the brain are usually divided into the affected side and the non-affected side. Among them, the affected side usually refers to the cerebral hemisphere with a lower activation level in a specific task or state, while the non-affected side is the cerebral hemisphere with a higher activation level. Correspondingly, the above cerebral hemisphere activation index can be divided into the affected side cerebral activation index, the non-affected side cerebral activation index, and the whole brain activation index.

[0089] Exemplarily, the affected side cerebral activation index can be obtained by the following formula:

[0090]

[0091] Among them, GC SL is the brain activation index of the affected side, p is the number of channels in the affected cerebral hemisphere under the task state, W RWi is the cerebral blood oxygen wavelet amplitude of the i-th channel in the affected cerebral hemisphere under the task state, g RWi is the proportion of the connection number of the i-th channel in the affected cerebral hemisphere with other channels to the total number of channels in the affected hemisphere under the task state, q is the number of channels in the affected cerebral hemisphere under the task state, W JXi is the cerebral blood oxygen wavelet amplitude of the i-th channel in the affected cerebral hemisphere at rest, g RWi is the proportion of the connection number of the i-th channel in the affected cerebral hemisphere with other channels to the total number of channels in the affected hemisphere at rest.

[0092] The brain activation index of the non-affected side can be calculated by the following formula:

[0093]

[0094] Among them, GC FSL is the brain activation value of the non-affected side, a is the number of channels in the non-affected cerebral hemisphere under the task state, W RWj is the cerebral blood oxygen wavelet amplitude of the j-th channel in the affected cerebral hemisphere under the task state, g RWj is the proportion of the connection number of the j-th channel in the affected cerebral hemisphere with other channels to the total number of channels in the affected hemisphere under the task state, b is the number of channels in the non-affected cerebral hemisphere under the task state, W JXj' is the cerebral blood oxygen wavelet amplitude of the j-th channel in the non-affected cerebral hemisphere at rest, g RWj is the proportion of the connection number of the j-th channel in the non-affected cerebral hemisphere with other channels to the total number of channels in the non-affected hemisphere at rest.

[0095] The whole-brain activation index can be calculated by the following formula:

[0096]

[0097] Among them, GC NL is the whole-brain activation value, m is the number of channels in the whole brain under the task state, W RWk is the cerebral blood oxygen wavelet amplitude of the k-th channel in the whole brain under the task state, g RWk is the proportion of the connection number of the k-th channel in the whole brain with other channels to the total number of all channels under the task state, n is the number of channels in the whole brain under the task state, W JXk' is the cerebral blood oxygen wavelet amplitude of the k-th channel in the whole brain at rest, g RWk is the proportion of the connection number of the k-th channel in the whole brain with other channels to the total number of all channels in the whole brain at rest.

[0098] Laterality refers to the functional asymmetry between the two hemispheres of the brain, where one side may be dominant in certain functions. Exemplarily, for most right-handed people, the left brain usually controls language and logical functions, while the right brain is more involved in spatial processing and face recognition. In the embodiments of the present invention, the brain laterality index can be calculated by the following formula:

[0099]

[0100] Wherein, PI is the laterality index, and RC SRW is the number of channel connections in the non-affected hemisphere in the task state, and RC SJX is the number of channel connections in the non-affected hemisphere in the resting state, and RC RW is the number of channel connections in the affected hemisphere in the task state, and RC JX is the number of channel connections in the affected hemisphere in the resting state, and L ij is the information transmission efficiency between channel i and channel j.

[0101] The hemisphere functional connectivity index is used to quantify the degree of functional connectivity between different regions of the two hemispheres of the brain. High functional connectivity indicates strong interaction and information flow between two regions. This hemisphere functional connectivity index can also include the functional connectivity index of the affected hemisphere, the functional connectivity index of the non-affected hemisphere, and the functional connectivity index of the whole brain. Exemplarily, the functional connectivity value index of the affected hemisphere can be calculated by the following formula:

[0102]

[0103] Wherein, KM SLJ is the functional connectivity value of the affected hemisphere, DZ SRWLJ is the number of channels with functional connectivity in the affected hemisphere in the task state, DZ SJXLJ is the number of channels with functional connectivity in the affected hemisphere in the resting state, FS RWij is the transmission efficiency between the i-th channel and the j-th channel in the affected hemisphere in the task state, FS JXij is the transmission efficiency between the i-th channel and the j-th channel in the affected hemisphere in the resting state.

[0104] The functional connectivity index of the non-affected hemisphere can be calculated by the following formula:

[0105]

[0106] Wherein, KM FSLJ is the functional connectivity value of the non-affected hemisphere, DZ FSRWLJ is the number of channels with functional connectivity in the non-affected hemisphere in the task state, DZ FSJXLJThe number of channels with functional connectivity in the non - affected cerebral hemisphere at rest, FS FRWij The transmission efficiency between the i - th and j - th channels in the non - affected cerebral hemisphere during the task state, FS FJXij The transmission efficiency between the i - th and j - th channels in the non - affected cerebral hemisphere at rest.

[0107] The whole - brain functional connectivity index can be calculated by the following formula:

[0108]

[0109] Among them, KM LJ is the whole - brain functional connectivity value, DZ RWLJ is the number of channels with functional connectivity in the whole - brain during the task state, DZ JXLJ is the number of channels with functional connectivity in the whole - brain at rest, FS RWij is the transmission efficiency between the i - th and j - th channels in the whole - brain during the task state, FS JXij is the transmission efficiency between the i - th and j - th channels in the whole - brain at rest.

[0110] The electroencephalogram (EEG) information includes 4 frequency bands: θ - band (4 - 8HZ), α - band (8 - 13HZ), β - band (13 - 30HZ), γ - band (30 - 40HZ). Therefore, the information of the above - mentioned different frequency bands can be extracted from each channel of the EEG information, so as to calculate the global efficiency and local efficiency indexes of different frequency bands. The above - mentioned channels refer to the conductive paths connecting the scalp and acquisition devices such as electroencephalographs, which can reflect the electrical activities of different parts of the brain. The global efficiency and local efficiency indexes of the above - mentioned different frequency bands can reflect the connection characteristics of the brain network function, and their specific calculation formulas are as follows:

[0111] The global efficiency index in the θ - band:

[0112]

[0113] Among them, FN θ is the global efficiency of the θ - band of the EEG signal; QB RWθ is the number of node channels connected by the θ - band of the EEG signal during the task state; QB JXθ is the number of node channels connected by the θ - band of the EEG signal at rest; K ij is the shortest path length between node i and node j, that is, the connection efficiency.

[0114] The local efficiency in the θ - band:

[0115]

[0116] Among them, HL θis the local efficiency of the θ frequency band of the electroencephalogram signal; N is the number of nodes; f RWijθ is the number of channels through which node i and node j are connected and pass through node k in the θ frequency band of the electroencephalogram signal in the task state; l RWijθ is the shortest path length when node i and node j are connected and pass through node h in the θ frequency band of the electroencephalogram signal in the task state; d RWijθ The shortest path length between node i and node j in the θ frequency band of the electroencephalogram signal in the task state; f JXijθ is the number of channels through which node i and node j are connected and pass through node k in the θ frequency band of the electroencephalogram signal in the resting state; l JXijθ is the shortest path length when node i and node j are connected and pass through node h in the θ frequency band of the electroencephalogram signal at rest; d JXijθ is the shortest path length between node i and node j in the θ frequency band of the electroencephalogram signal at rest; G RWijθ is the total number of connections between node i and other nodes in the θ frequency band of the electroencephalogram signal in the task state.

[0117] Global efficiency in the a frequency band:

[0118]

[0119] Among them, FN a is the global efficiency of the a frequency band of the electroencephalogram signal; QB RWa is the number of node channels connected in the a frequency band of the electroencephalogram signal in the task state; QB JXa is the number of node channels connected in the a frequency band of the electroencephalogram signal in the resting state; K ij is the shortest path length between node i and node j, that is, the connection efficiency.

[0120] Local efficiency in the a frequency band:

[0121]

[0122] Among them, HL a is the local efficiency of the a frequency band of the electroencephalogram signal; N is the number of nodes;

[0123] f RWija is the number of channels through which node i and node j are connected and pass through node k in the a frequency band of the electroencephalogram signal in the task state; l RWija is the shortest path length when node i and node j are connected and pass through node h in the a frequency band of the electroencephalogram signal in the task state; d RWia The shortest path length between node i and node j in the a frequency band of the electroencephalogram signal in the task state; f JXija is the number of channels through which node i and node j are connected and pass through node k in the a frequency band of the electroencephalogram signal in the resting state; l JXija is the shortest path length when node i and node j are connected and pass through node h in the a frequency band of the electroencephalogram signal at rest; dJXija is the shortest path length between node i and node j in the a-band of the resting-state EEG signal; G RWija is the total number of connections between node i and other nodes in the a-band of the task-state EEG signal.

[0124] Global efficiency in the β-band:

[0125]

[0126] where FN β is the global efficiency of the β-band of the EEG signal; QB RWβ is the number of node channels connected in the β-band of the task-state EEG signal; QB JXβ is the number of node channels connected in the β-band of the resting-state EEG signal; K ij is the shortest path length between node i and node j, i.e., the connection efficiency.

[0127] Local efficiency in the β-band:

[0128]

[0129] where HL β is the local efficiency of the β-band of the EEG signal; N is the number of nodes; f RWijβ is the number of channels through which node i and node j are connected and pass through node k in the β-band of the task-state EEG signal; l RWijβ is the shortest path length when node i and node j are connected and pass through node h in the β-band of the task-state EEG signal; d RWiβ The shortest path length between node i and node j in the β-band of the task-state EEG signal; f JXijβ is the number of channels through which node i and node j are connected and pass through node k in the β-band of the resting-state EEG signal; l JXijβ is the shortest path length when node i and node j are connected and pass through node h in the β-band of the resting-state EEG signal; d JXijβ is the shortest path length between node i and node j in the β-band of the resting-state EEG signal; G RWijβ is the total number of connections between node i and other nodes in the β-band of the task-state EEG signal.

[0130] Global efficiency in the γ-band:

[0131]

[0132] where FN γ is the global efficiency of the γ-band of the EEG signal; QB RWγ is the number of node channels connected in the γ-band of the task-state EEG signal; QB JXγ is the number of node channels connected in the γ-band of the resting-state EEG signal; Kij is the shortest path length between node i and node j, that is, the connection efficiency.

[0133] Local efficiency in the γ band:

[0134]

[0135] Among them, HL γ is the local efficiency of the γ band of the EEG signal; N is the number of nodes; f RWijγ is the number of channels through which node i and node j are connected in the γ band of the EEG signal in the task state and pass through node k; l RWijγ is the shortest path length when node i and node j are connected in the γ band of the EEG signal in the task state and pass through node h; d RWiγ The shortest path length between node i and node j in the γ band of the EEG signal in the task state; f JXijγ is the number of channels through which node i and node j are connected in the γ band of the EEG signal in the resting state and pass through node k; l JXijγ is the shortest path length when node i and node j are connected in the γ band of the EEG signal in the resting state and pass through node h; d JXijγ is the shortest path length between node i and node j in the γ band of the EEG signal in the resting state; G RWijγ is the total number of connections between node i and other nodes in the γ band of the EEG signal in the task state.

[0136] By extracting various indexes of cerebral blood oxygen information and EEG information and outputting them to the brain function rehabilitation prediction model, since the above various index information can reflect the cerebral blood oxygen and EEG conditions of the user in multiple levels and aspects, this enables the brain function recovery prediction model to learn the cerebral blood oxygen and EEG conditions contained in each training data more comprehensively and deeply, improving the prediction accuracy of the model.

[0137] Correspondingly, in actual application, before outputting the data to be detected of the target user to the target brain function recovery prediction model, the data to be detected can be preprocessed and index extracted. Specifically, in one possible embodiment, the above method may further include the following steps:

[0138] Extract the cerebral hemisphere activation index, cerebral hemispheric lateralization index, and hemispheric functional connection index based on the cerebral blood oxygen data of the target user;

[0139] Extract the global efficiency index and local efficiency index of different frequency bands based on the EEG data of the target user.

[0140] Correspondingly, the cerebral hemisphere activation index, cerebral hemispheric lateralization index, hemispheric functional connection index, global efficiency index and local efficiency index of different frequency bands can be input into the target brain function rehabilitation prediction model.

[0141] In a possible embodiment, the above method may further include normalizing the scale data for the data to be detected, and filtering the noise of the cerebral blood oxygen data and the electroencephalogram data; correspondingly, the normalized scale data, the filtered cerebral blood oxygen data, and the electroencephalogram data can be input into a pre-trained target brain function rehabilitation prediction model.

[0142] After obtaining the target brain function recovery result of the target user output by the target brain function recovery result prediction model, the transcranial light regulation scheme of the target user can be adjusted based on this recovery result. As described above, the brain function recovery result can be represented by a numerical value. Therefore, as a possible implementation manner, when the target brain function rehabilitation result is higher than the first preset threshold, transcranial light stimulation is performed on the first brain function area of the target user; when the target brain function rehabilitation result is lower than the second preset threshold, transcranial light stimulation is performed on the second brain function area of the target user, where the second preset threshold is less than the first preset threshold; when the target brain function rehabilitation result is between the second preset threshold and the first threshold, transcranial light stimulation is performed on the first brain function area and the second brain function area of the target user.

[0143] The above first preset threshold is used to distinguish between good brain function recovery and medium brain function recovery, and the second preset threshold is used to distinguish between medium brain function recovery and poor brain function recovery. The above first brain function area and the second brain function area can be the affected cerebral hemisphere and the non-affected cerebral hemisphere, respectively.

[0144] Exemplarily, when the target brain function rehabilitation result is poor, it indicates that the affected cerebral hemisphere of the user recovers poorly. Therefore, it is recommended to perform light stimulation on the affected cerebral hemisphere of the user; when the target brain function rehabilitation result is medium, it indicates that both the affected and non-affected cerebral hemispheres of the user are recovering. Therefore, it is recommended to perform light stimulation on both the affected and non-affected cerebral hemispheres of the user; when the target brain function rehabilitation result is good, it indicates that the affected cerebral hemisphere of the user recovers well. Therefore, it is recommended to perform light stimulation on the non-affected cerebral hemisphere of the user.

[0145] In a possible embodiment, during the process of transcranial light stimulation of a target user, real-time cerebral blood oxygen information, real-time electroencephalogram information, etc. of the target user can be continuously monitored, and the light stimulation parameters of the transcranial light can be adjusted based on the real-time cerebral blood oxygen information and the real-time electroencephalogram information. The light stimulation parameters can include light stimulation frequency, light stimulation wavelength, light stimulation intensity, etc. The parameter adjustment process can be determined according to the actual application scenario. Exemplarily, during the process of transcranial light regulation of the target user according to the target light stimulation scheme, if the intensity of the electroencephalogram signal of the target user increases, it can be determined that the target user has a good response to the current light stimulation parameters. Therefore, the light stimulation intensity can be enhanced to achieve a greater light regulation gain.

[0146] By means of the above technical means, a feedback mechanism is applied to adjust the light stimulation parameters, so that the light stimulation parameters can change in a timely manner with the change of the user's electroencephalogram information, which helps to find a greater light regulation gain.

[0147] In a possible embodiment, information such as the above model output process, target transcranial light regulation scheme, feedback process, etc. can be displayed on a display device to improve the operation convenience of relevant personnel.

[0148] Applying the embodiments of the present invention, the improvement of the patient's brain function is predicted through the multi-level information changes of the global efficiency and local efficiency of electroencephalogram signals in different frequency bands, as well as the activation index, laterality index, and functional connection index of different cerebral hemispheres of cerebral blood oxygen signals. The synergistic control effect of the electroencephalogram signals in different frequency bands and the cerebral blood oxygen signals in different cerebral hemispheres of the patient is fully considered, and the brain function state of the patient can be comprehensively evaluated and predicted. Furthermore, a personalized adaptive light stimulation regulation scheme can be provided according to the prediction result of the improvement of the patient's brain function, so that the light stimulation-assisted rehabilitation training can exert the maximum gain effect and improve the efficiency and effect of the patient's rehabilitation training.

[0149] Moreover, the electroencephalogram signals of the patient are fully utilized while the light stimulation is performed, and the light regulation stimulation parameters for the patient are adjusted in real time according to the change of the electroencephalogram signals, promoting the collaborative optimization and real-time feedback of the brain and light stimulation data.

[0150] Based on the same inventive concept, the embodiments of the present invention also provide a closed-loop neuromodulation system based on transcranial light, as Figure 3 shown. The system 300 may include:

[0151] An acquisition module 301, configured to acquire the data to be detected of the target user, where the data to be detected includes the scale data, cerebral blood oxygen data, and electroencephalogram data of the target user;

[0152] An input module 302, configured to input the data to be detected into a pre-trained target brain function rehabilitation prediction model, and obtain a target brain function rehabilitation result output by the target brain function rehabilitation prediction model based on the data to be detected;

[0153] An adjustment module 303, configured to adjust a target light regulation scheme of the target user based on the target brain function rehabilitation result, where the target light regulation scheme includes the position of transcranial light stimulation;

[0154] Wherein, the target brain function rehabilitation prediction model is pre-trained through the following steps:

[0155] Obtain a training data set, where the training data set contains multiple pieces of training data, and each piece of training data includes the user's scale data, cerebral blood oxygen data, and electroencephalogram data; each piece of training data corresponds to a brain function rehabilitation label, and the brain function rehabilitation label is the actual brain function rehabilitation result of the user;

[0156] Input the training data set into an initial brain function rehabilitation prediction model, so that the initial brain function rehabilitation prediction model outputs a brain function rehabilitation prediction result corresponding to each piece of training data based on the training data set;

[0157] Based on the target difference between the brain function rehabilitation prediction result corresponding to each piece of training data and the brain function rehabilitation label of each piece of training data, adjust the parameters of the brain function rehabilitation prediction model until the target difference converges;

[0158] Use the brain function rehabilitation prediction model when the target difference converges as the target brain function rehabilitation prediction model.

[0159] In a possible embodiment, the system further includes:

[0160] An extraction module, configured to extract a cerebral hemisphere activation index, a cerebral lateralization index, and a hemispheric functional connectivity index based on the cerebral blood oxygen data of the target user; extract a global efficiency index and a local efficiency index of different frequency bands based on the electroencephalogram data of the target user;

[0161] The step of inputting the data to be detected into a pre-trained target brain function rehabilitation prediction model includes:

[0162] Input the cerebral hemisphere activation index, the cerebral lateralization index, the hemispheric functional connectivity index, the global efficiency index and the local efficiency index of different frequency bands into the target brain function rehabilitation prediction model.

[0163] In a possible embodiment, the system further includes:

[0164] A preprocessing module for normalizing the scale data for the data to be detected, and filtering noise from the cerebral blood oxygen data and electroencephalogram data;

[0165] Inputting the data to be detected into a pre-trained target brain function rehabilitation prediction model includes:

[0166] Inputting the normalized scale data, the filtered cerebral blood oxygen data, and electroencephalogram data into a pre-trained target brain function rehabilitation prediction model.

[0167] In a possible embodiment, adjusting the target light regulation scheme of the target user based on the target brain function rehabilitation result includes:

[0168] When the target brain function rehabilitation result is higher than a first preset threshold, performing transcranial light stimulation on a first brain function area of the target user;

[0169] When the target brain function rehabilitation result is lower than a second preset threshold, performing transcranial light stimulation on a second brain function area of the target user, where the second preset threshold is less than the first preset threshold;

[0170] When the target brain function rehabilitation result is between the second preset threshold and the first preset threshold, performing transcranial light stimulation on the first brain function area and the second brain function area of the target user.

[0171] In a possible embodiment, the system further includes:

[0172] A feedback module for continuously monitoring the real-time electroencephalogram data of the target user during the process of performing transcranial light stimulation on the target user according to the target light regulation scheme, and adjusting the light stimulation parameters of the transcranial light based on the real-time electroencephalogram data, where the light stimulation parameters include light stimulation intensity.

[0173] In a possible embodiment, the above system may further include a display device for displaying the feedback process of the feedback module, the model output result, the target light regulation scheme, etc.

[0174] As Figure 4 shown, Figure 4Another schematic diagram of the logical structure of the transcranial light closed-loop neuromodulation system provided by the embodiments of the present invention. The system may include: an information acquisition and analysis module, a brain function rehabilitation prediction module, a light regulation recommendation module, a light stimulation module, an electroencephalogram synchronization monitoring module, and a feedback module. Among them, the information acquisition and analysis module is used to collect and analyze the cerebral blood oxygen and electroencephalogram information of the user in the resting state and the upper limb rehabilitation training task state; the brain function rehabilitation prediction module is used to predict the improvement of the user's brain function according to the information of the information acquisition and analysis module; the light regulation recommendation module recommends light stimulation parameters according to the prediction results of the brain function rehabilitation prediction module; the light stimulation module is used to perform light stimulation according to the light stimulation parameters recommended by the light regulation recommendation module; the electroencephalogram synchronization monitoring module is used to synchronously monitor the electroencephalogram information while performing light regulation; the feedback module is used to adjust the parameters of the light stimulation module according to the monitoring and analysis results of the electroencephalogram information of the electroencephalogram synchronization monitoring module.

[0175] Among them, the collection, storage, use, processing, transmission, provision, and disclosure of the user's personal information involved in the present invention all comply with the provisions of relevant laws and regulations and do not violate public order and good customs.

Claims

1. A closed-loop neuromodulation method based on transcranial light, characterized in that The method includes: Obtaining the data to be detected of the target user, where the data to be detected includes the scale data, cerebral blood oxygen data, and electroencephalogram data of the target user; Inputting the data to be detected into a pre-trained target brain function rehabilitation prediction model, and obtaining the target brain function rehabilitation result output by the target brain function rehabilitation prediction model based on the data to be detected; Adjusting the target light regulation scheme of the target user based on the target brain function rehabilitation result, where the target light regulation scheme includes the position of transcranial light stimulation; Among them, the target brain function rehabilitation prediction model is pre-trained through the following steps: Obtaining a training data set, where the training data set contains multiple pieces of training data, and each piece of training data includes the scale data, cerebral blood oxygen data, and electroencephalogram data of the user; each piece of training data corresponds to a brain function rehabilitation label, and the brain function rehabilitation label is the actual brain function rehabilitation result of the user; Inputting the training data set into an initial brain function rehabilitation prediction model, so that the initial brain function rehabilitation prediction model outputs the brain function rehabilitation prediction results corresponding to each piece of training data based on the training data set; Adjusting the parameters of the brain function rehabilitation prediction model based on the target difference between the brain function rehabilitation prediction results corresponding to each piece of training data and the brain function rehabilitation labels of each piece of training data until the target difference converges; Taking the brain function rehabilitation prediction model when the target difference converges as the target brain function rehabilitation prediction model.

2. The method according to claim 1, wherein Before inputting the data to be detected into a pre-trained target brain function rehabilitation prediction model, it includes: Extracting brain hemisphere activation index, brain lateralization index, and hemisphere functional connectivity index based on the cerebral blood oxygen data of the target user; Extracting global efficiency index and local efficiency index of different frequency bands based on the electroencephalogram data of the target user; The inputting the data to be detected into a pre-trained target brain function rehabilitation prediction model includes: Inputting the brain hemisphere activation index, the brain lateralization index, the hemisphere functional connectivity index, the global efficiency index of different frequency bands, and the local efficiency index into the target brain function rehabilitation prediction model.

3. The method according to claim 1, wherein The method further includes: Normalizing the scale data and filtering the noise of the cerebral blood oxygen data and the electroencephalogram data for the data to be detected; The inputting the data to be detected into a pre-trained target brain function rehabilitation prediction model includes: Inputting the normalized scale data, the filtered cerebral blood oxygen data, and the electroencephalogram data into a pre-trained target brain function rehabilitation prediction model.

4. The method according to claim 1, wherein The adjusting the target light regulation scheme of the target user based on the target brain function rehabilitation result includes: Performing transcranial light stimulation on the first brain functional area of the target user when the target brain function rehabilitation result is higher than a first preset threshold; When the target brain function rehabilitation result is lower than the second preset threshold, transcranial light stimulation is performed on the second brain function area of the target user, where the second preset threshold is smaller than the first preset threshold; When the target brain function rehabilitation result is between the second preset threshold and the first preset threshold, transcranial light stimulation is performed on the first brain function area and the second brain function area of the target user.

5. The method according to claim 1, characterized in that, The method further includes: During the process of performing transcranial light stimulation on the target user according to the target light regulation scheme, continuously monitor the real-time electroencephalogram data of the target user, and adjust the light stimulation parameters of the transcranial light based on the real-time electroencephalogram data, where the light stimulation parameters include light stimulation intensity.

6. A closed-loop neural regulation system based on transcranial light, characterized in that, The system includes: An acquisition module, configured to acquire the data to be detected of the target user, where the data to be detected includes the scale data, cerebral blood oxygen data, and electroencephalogram data of the target user; An input module, configured to input the data to be detected into a pre-trained target brain function rehabilitation prediction model, and obtain the target brain function rehabilitation result output by the target brain function rehabilitation prediction model based on the data to be detected; An adjustment module, configured to adjust the target light regulation scheme of the target user based on the target brain function rehabilitation result, where the target light regulation scheme includes the position of transcranial light stimulation; Wherein, the target brain function rehabilitation prediction model is pre-trained through the following steps: Acquire a training data set, where the training data set contains multiple pieces of training data, and each piece of training data contains the scale data, cerebral blood oxygen data, and electroencephalogram data of the user; each piece of training data corresponds to a brain function rehabilitation label, and the brain function rehabilitation label is the actual brain function rehabilitation result of the user; Input the training data set into an initial brain function rehabilitation prediction model, so that the initial brain function rehabilitation prediction model outputs the brain function rehabilitation prediction results corresponding to each piece of training data based on the training data set; Based on the target difference between the brain function rehabilitation prediction results corresponding to each piece of training data and the brain function rehabilitation labels of each piece of training data, adjust the parameters of the brain function rehabilitation prediction model until the target difference converges; Use the brain function rehabilitation prediction model when the target difference converges as the target brain function rehabilitation prediction model.

7. The system according to claim 6, characterized in that, The system further includes: An extraction module, configured to extract a brain hemisphere activation index, a cerebral lateralization index, and a hemisphere functional connectivity index based on the cerebral blood oxygen data of the target user; extract a global efficiency index and a local efficiency index of different frequency bands based on the electroencephalogram data of the target user; The step of inputting the data to be detected into a pre-trained target brain function rehabilitation prediction model includes: Input the brain hemisphere activation index, the cerebral lateralization index, the hemisphere functional connectivity index, the global efficiency index of different frequency bands, and the local efficiency index into the target brain function rehabilitation prediction model.

8. The system according to claim 6, wherein The system further includes: A preprocessing module, configured to normalize the scale data for the data to be detected, and filter noise from the cerebral blood oxygen data and the electroencephalogram data; Said inputting the data to be detected into a pre-trained target brain function rehabilitation prediction model includes: Inputting the normalized scale data, the filtered cerebral blood oxygen data, and the electroencephalogram data into a pre-trained target brain function rehabilitation prediction model.

9. The system according to claim 6, wherein Said adjusting the target light regulation scheme of the target user based on the target brain function rehabilitation result includes: In the case where the target brain function rehabilitation result is higher than a first preset threshold, performing transcranial light stimulation on the first brain function area of the target user; In the case where the target brain function rehabilitation result is lower than a second preset threshold, performing transcranial light stimulation on the second brain function area of the target user, wherein the second preset threshold is less than the first preset threshold; In the case where the target brain function rehabilitation result is between the second preset threshold and the first preset threshold, performing transcranial light stimulation on the first brain function area and the second brain function area of the target user.

10. The system according to claim 6, wherein The system further includes: A feedback module, configured to continuously monitor the real-time electroencephalogram data of the target user during the process of performing transcranial light stimulation on the target user according to the target light regulation scheme, and adjust the light stimulation parameters of the transcranial light based on the real-time electroencephalogram data, wherein the light stimulation parameters include light stimulation intensity.

Images