Closed-loop brain stimulation system and method based on brain-computer interface, electronic equipment and storage medium
Through a closed-loop brain stimulation system based on brain-computer interface, deep signals are reconstructed using superficial signals and stimulation parameters are adjusted, which solves the problem that existing systems cannot adjust adaptively, and achieves higher treatment accuracy and detection accuracy.
Patent Information
- Application Number
- CN202510538571.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-27
- Publication Date
- 2025-08-12
Smart Images
Figure CN120459529A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of medical device technology, and in particular to a closed-loop brain stimulation system and method based on a brain-computer interface, an electronic device, and a storage medium. Background Art
[0002] Brain stimulation is a technique that uses physical, chemical, or electromagnetic means to directly act on specific brain regions to modulate neural activity, improve brain function, or treat neuropsychiatric disorders. It provides an important tool for neuroscience research and clinical treatment, and particularly shows great potential in the rehabilitation of movement disorders.
[0003] Brain stimulation can be categorized as open-loop or closed-loop. In open-loop stimulation, stimulation parameters are preset and cannot be adaptively adjusted based on the patient's neural activity. Unlike open-loop stimulation, closed-loop stimulation automatically optimizes the stimulation plan based on real-time feedback from the brain's state.
[0004] However, in clinical practice, it has been found that it is not possible to provide accurate closed-loop brain stimulation to patients, and the expected effects cannot be achieved or maintained. Therefore, the accuracy of closed-loop brain stimulation needs to be improved. Summary of the Invention
[0005] In view of this, the present disclosure proposes a closed-loop brain stimulation scheme based on brain-computer interface.
[0006] According to one aspect of the present disclosure, a closed-loop brain stimulation system based on a brain-computer interface is provided, comprising:
[0007] A dual-modal recording unit for acquiring superficial and deep brain signals in a time-sequential manner;
[0008] a superficial signal sub-time series determining unit, configured to determine a superficial signal sub-time series corresponding to any of the deep signals;
[0009] a reconstruction data determining unit, configured to generate reconstruction data corresponding to any of the deep signals according to the superficial signal sub-time series;
[0010] A stimulation parameter adjustment unit is used to adjust brain stimulation parameters based on the reconstructed data corresponding to the deep signal.
[0011] In a possible implementation, the device further includes a quality inspection unit configured to:
[0012] Determining, according to the quality inspection frequency, a quality index of the deep signal to be detected, for the deep signal to be detected acquired between two adjacent quality inspection moments;
[0013] When the quality indicator is less than a threshold, determining that the deep signal to be detected is in a failed state;
[0014] When the quality indicator is not less than a threshold, determining that the deep signal to be detected is in a valid state;
[0015] The shallow signal sub-time series determination unit is further configured to:
[0016] The superficial signal collected between the two adjacent quality inspection moments is used as the superficial signal sub-time series.
[0017] In a possible implementation, the stimulation parameter adjustment unit is further configured to:
[0018] When the deep signal is in the valid state, determining a human motion state by using the deep signal and information representing non-deep signals in the reconstructed data;
[0019] The stimulation parameters are determined based on the human body action state.
[0020] In a possible implementation, the stimulation parameter adjustment unit is further configured to include:
[0021] In the case where the deep signal is in the failed state, determining a human body motion state using the reconstructed data;
[0022] The stimulation parameters are determined based on the human body action state.
[0023] In a possible implementation, the action state includes: the behavioral state of a patient suffering from a movement disorder, wherein the movement disorder includes at least: Parkinson's disease, dystonia, and Tourette syndrome; the behavioral state includes at least: a sleep state and a movement state.
[0024] In a possible implementation, the reconstructed data includes: characteristic information of a first signal generated by brain activity during a period of collecting the superficial signal sub-time series;
[0025] The reconstruction data determination unit is further configured to:
[0026] Performing time convolution processing on the shallow signal sub-time series to obtain a signal time series;
[0027] parsing the signal time series to obtain an parsed signal time series;
[0028] Characteristic information of the analytical signal time series is determined, and the characteristic information is used as the reconstructed data.
[0029] In one possible implementation, the reconstructed data includes: a first signal generated by brain activity during a period of time during which the superficial signal sub-time series is collected;
[0030] The reconstruction data determination unit is further configured to:
[0031] The shallow signal sub-time series is processed using a diffusion model to generate a plurality of the first signals, thereby obtaining a first signal time series, and the first signal time series is used as the reconstructed data.
[0032] According to another aspect of the present disclosure, a closed-loop brain stimulation method based on a brain-computer interface is provided, comprising: acquiring superficial signals and deep signals of the brain in a time sequence; determining a superficial signal sub-time series corresponding to any of the deep signals; generating reconstructed data corresponding to any of the deep signals based on the superficial signal sub-time series; and adjusting brain stimulation parameters based on the reconstructed data corresponding to the deep signals.
[0033] In a possible implementation, it also includes: determining the quality index of the deep signal to be detected collected between two adjacent quality inspection moments; when the quality index is less than a threshold, determining that the deep signal to be detected is in an invalid state; when the quality index is not less than a threshold, determining that the deep signal to be detected is in a valid state; determining the superficial signal sub-time series corresponding to any of the deep signals includes: taking the superficial signal collected between the two adjacent quality inspection moments as the superficial signal sub-time series.
[0034] In one possible implementation, adjusting the stimulation parameters of the brain based on the reconstructed data corresponding to the deep signal includes: when the deep signal is in the valid state, using the deep signal and the information representing the non-deep signal in the reconstructed data to determine the human body's action state; and determining the stimulation parameters based on the human body's action state.
[0035] In one possible implementation, adjusting the stimulation parameters of the brain based on the reconstructed data corresponding to the deep signal includes: when the deep signal is in the failed state, using the reconstructed data to determine the human body's action state; and determining the stimulation parameters based on the human body's action state.
[0036] In a possible implementation, the action state includes: the behavioral state of a patient suffering from a movement disorder, wherein the movement disorder includes at least: Parkinson's disease, dystonia, and Tourette syndrome; the behavioral state includes at least: a sleep state and a movement state.
[0037] In a possible implementation, the reconstructed data includes: characteristic information of a first signal generated by brain activity during a period of collecting the superficial signal sub-time series;
[0038] The method of generating the reconstruction data corresponding to any of the deep signals based on the superficial signal sub-time series includes: performing time convolution processing on the superficial signal sub-time series to obtain a signal time series; parsing the signal time series to obtain an analytical signal time series; determining characteristic information of the analytical signal time series, and using the characteristic information as the reconstruction data.
[0039] In one possible implementation, the reconstructed data includes: a first signal generated by brain activity during a period of time in which the superficial signal sub-time series is collected;
[0040] Generating the reconstruction data corresponding to any of the deep signals based on the superficial signal sub-time series includes: using a diffusion model to process the superficial signal sub-time series to generate multiple first signals, obtaining a first signal time series, and using the first signal time series as the reconstruction data.
[0041] According to another aspect of the present disclosure, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the above method.
[0042] According to another aspect of the present disclosure, a non-volatile computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above method are implemented.
[0043] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, or a non-volatile computer-readable storage medium carrying the computer program, wherein the computer program implements the steps of the above method when executed by a processor.
[0044] In various aspects of the closed-loop brain stimulation scheme disclosed herein, when the acquired deep signal is missing or of poor quality, the reconstructed data can make the deep signal equivalent to being in a continuous and stable state. Moreover, when the acquired deep signal itself is continuously stable, the reconstructed data can provide a supplement to the deep signal of other channels. In this way, regardless of whether the acquired deep signal is in a continuous and stable state, the reconstructed data can help the stimulation parameter adjustment unit improve the accuracy of the stimulation parameters. Furthermore, the use of the closed-loop brain stimulation system disclosed herein can improve the accuracy of brain stimulation.
[0045] Further features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0046] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate exemplary embodiments, features, and aspects of the disclosure and, together with the description, serve to explain the principles of the disclosure.
[0047] Figure 1 A schematic diagram of the structure of a closed-loop brain stimulation system provided in an embodiment of the present disclosure.
[0048] Figure 2 A schematic flow chart of the closed-loop brain stimulation method provided in an embodiment of the present disclosure.
[0049] Figure 3 A schematic diagram of the structure of an electronic device for closed-loop brain stimulation provided in an embodiment of the present disclosure. DETAILED DESCRIPTION
[0050] Various exemplary embodiments, features, and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise indicated.
[0051] As used herein, the terms "comprises," "comprising," "having," or variations thereof are open ended and include one or more stated features, integers, elements, steps, parts, or functions, but do not preclude the presence or addition of one or more other features, integers, elements, steps, parts, functions, or groups thereof.
[0052] When an element is referred to as being "connected," "coupled," "responsive" or variations thereof to another element, it can be directly connected, coupled or responsive to the other element or intervening elements may be present.
[0053] Although the terms first, second, third, etc. may be used herein to describe various elements / operations, these elements / operations should not be limited by these terms. These terms are only used to distinguish one element / operation from another element / operation. Therefore, without departing from the teachings of the present invention, the first element / operation in some embodiments may be referred to as the second element / operation in other embodiments.
[0054] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.
[0055] In addition, numerous specific details are provided in the following detailed description to better illustrate the present disclosure. Those skilled in the art will appreciate that the present disclosure can be practiced without certain specific details. In some instances, methods, means, components, and circuits well known to those skilled in the art are not described in detail in order to highlight the main points of the present disclosure.
[0056] In clinical practice, it is necessary to acquire deep brain signals and use them as a basis for closed-loop brain stimulation. However, obtaining sustained and stable deep signals is difficult due to a variety of factors. These include stimulation artifacts, electrode impedance variations and displacement, tissue scarring (which degrades signal quality), and battery power constraints.
[0057] However, the system relies on a continuous and stable deep signal to accurately determine the stimulation parameters to effectively and efficiently stimulate the brain. Therefore, providing a continuous and stable deep signal is key to providing accurate closed-loop brain stimulation for patients.
[0058] Figure 1 This is a schematic diagram of the structure of the closed-loop brain stimulation system provided by the embodiment of the present disclosure. Figure 1 As shown, the system 10 includes: a dual-modal recording unit 11, used to collect superficial signals and deep signals of the brain in time sequence; a superficial signal sub-time series determination unit 12, used to determine the superficial signal sub-time series corresponding to any of the deep signals; a reconstruction data determination unit 13, used to generate reconstruction data corresponding to any of the deep signals based on the superficial signal sub-time series; and a stimulation parameter adjustment unit 14, used to adjust the stimulation parameters of the brain based on the reconstruction data corresponding to the deep signal.
[0059] The dual-modality recording unit 11 can acquire deep signals at a preset first acquisition frequency and superficial signals at a preset second acquisition frequency. The second acquisition frequency is no less than the first acquisition frequency. In one example, the second acquisition frequency can be equal to the first acquisition frequency. This allows for simultaneous acquisition of deep and superficial signals. A single deep signal can correspond to one or more superficial signals.
[0060] Superficial signals may include electrical signals acquired from the cerebral cortex and / or electrical signals acquired from the surface of the scalp. For ease of description, electrical signals acquired from the cerebral cortex are referred to as cortical electrical signals, and electrical signals acquired from the surface of the scalp are referred to as epidermal electrical signals. Deep signals may be electrical signals acquired from within the cerebral cortex. Deep and superficial signals can be acquired using different acquisition terminals on the same device. Deep and superficial signals can also be acquired using separate acquisition terminals on different devices.
[0061] The superficial signal sub-time series may contain at least one superficial signal. The superficial signals in the superficial signal sub-time series are arranged according to the acquisition time sequence. For example, when the second acquisition frequency is greater than the first acquisition frequency, a single deep signal may correspond to multiple superficial signals. Multiple superficial signals are arranged in time sequence to obtain a superficial signal sub-time series corresponding to the deep signal. For another example, when the second acquisition frequency is equal to the first acquisition frequency, a single deep signal may correspond to a superficial signal. The superficial signal can serve as a superficial signal sub-time series corresponding to the single deep signal. The superficial signal sub-time series may include: a first superficial signal sub-time series obtained by arranging the cerebral cortical electrical signals in time sequence, and / or a second superficial signal sub-time series obtained by arranging the epidermal electrical signals in time sequence.
[0062] Exemplarily, the dual-modality recording unit 11 can collect cortical electrical signals and deep signals at the same frequency. And it can collect epidermal electrical signals. Among them, the acquisition frequency of epidermal electrical signals is higher than the acquisition frequency of cortical electrical signals (and / or deep electrical signals). The superficial signal sub-time series determination unit 12 can determine a cortical electrical signal for a single deep signal, and use the cortical electrical signal as the first superficial signal sub-time series corresponding to the single deep signal. In addition, multiple epidermal electrical signals can be determined for a single deep signal, and these multiple epidermal electrical signals can be arranged in time sequence to obtain a second superficial signal sub-time series corresponding to the single deep signal. In this way, the first superficial signal sub-time series and the second superficial sub-time series can be determined based on the deep signal.
[0063] Because the cerebral cortex, scalp, and deep brain are physiologically related, and in particular, the cerebral cortex and basal ganglia are physiologically connected, the corresponding deep and superficial signals are correlated. Therefore, the reconstruction data determination unit 13 can use the superficial signals to generate reconstruction data for the deep signals.
[0064] Exemplarily, the reconstruction data determining unit 13 may generate the reconstruction data of the deep signal corresponding to the superficial signal sub-time series according to the superficial signal sub-time series based on deep learning technology.
[0065] To acquire deep brain signals, electrodes must be placed below the cerebral cortex. These electrodes must deliver electrical stimulation and acquire deep signals. Due to the limited number of electrodes, only one or two channels of deep signals can be acquired. This also affects the accuracy of stimulation parameters. Reconstructed data can be generated for all channels, for example, eight or more channels.
[0066] Thus, in the case where the acquired deep signal is missing or of poor quality, the reconstructed data can make the deep signal equivalent to being in a continuous and stable state. Moreover, when the acquired deep signal itself is continuously stable, the reconstructed data can provide a supplement to the deep signal of other channels. In this way, regardless of whether the acquired deep signal is in a continuous and stable state, the reconstructed data can help the stimulation parameter adjustment unit 14 improve the accuracy of the stimulation parameters. Furthermore, the use of the system 10 in the present disclosure can improve the accuracy of closed-loop brain stimulation. Among them, closed-loop brain stimulation can be deep brain stimulation and / or non-invasive brain stimulation. The stimulation parameter adjustment unit 14 can be connected to the brain through a brain-computer interface and stimulate the brain according to the stimulation parameters.
[0067] In one example, the stimulation parameter adjustment unit 14 may include a decoder. The decoder in the stimulation parameter adjustment unit 14 may determine the stimulation parameters according to a deep signal time series consisting of the acquired deep signal and the deep signal reconstructed using the reconstruction data.
[0068] In a possible implementation, it also includes: a quality inspection unit, which is used to: determine the quality index of the deep signal to be detected collected between two adjacent quality inspection moments according to the quality inspection frequency; when the quality index does not meet the quality condition, determine that the deep signal to be detected is in an invalid state; when the quality index meets the quality condition, determine that the deep signal to be detected is in a valid state; the superficial signal sub-time series determination unit 12 is further used to: use the superficial signal collected between the two adjacent quality inspection moments as the superficial signal sub-time series.
[0069] The quality inspection unit can perform quality inspection on the collected deep signals. For the convenience of description, the deep signals that have not undergone quality inspection can be named as deep signals to be detected. The quality inspection frequency can be set in advance, and the quality inspection frequency can be less than the first acquisition frequency. The collected deep signals can be quality inspected according to the quality inspection frequency. For the convenience of the following description, the moment when each quality inspection starts can be named as the quality inspection moment. For example, multiple quality inspection moments can be set at equal time intervals. The time intervals between two adjacent quality inspection moments are equal.
[0070] The superficial signal sub-time series determination unit 12 may use the superficial signals collected between two adjacent quality inspection moments as the superficial signal sub-time series. This superficial signal sub-time series may correspond to the deep signal collected at the later quality inspection moment of the two adjacent quality inspection moments. Alternatively, this superficial signal sub-time series may correspond to the deep signal collected near the later quality inspection moment of the two adjacent quality inspection moments. As the quality inspection moments arrive, superficial signal sub-time series may be continuously determined.
[0071] The quality inspection unit can determine the quality index of the deep signal to be detected between two quality inspection moments as the quality inspection moments arrive, thereby completing near-real-time quality inspection of the acquired deep signal. The quality index can indicate whether the deep signal to be detected acquired between the two quality inspection moments is missing or distorted.
[0072] In the disclosed embodiment, a quality condition can be pre-set. If the quality indicator satisfies the quality condition, it means that the deep signal to be detected at least meets the minimum quality requirement for accurately determining the stimulation parameters. Therefore, if the quality indicator does not meet the quality condition, the deep signal to be detected cannot be used to accurately determine the stimulation parameters. Then, it means that the deep signal to be detected is in an invalid state. If the quality indicator satisfies the quality condition, the deep signal to be detected can be used to accurately determine the stimulation parameters. It means that the deep signal to be detected is in a valid state.
[0073] Exemplarily, the quality indicator may include a first quality indicator, and the quality condition may include a first quality condition. A first mean value of the deep signal to be detected between a single quality inspection moment and a quality inspection moment before the quality inspection moment may be determined. And a second mean value of the deep signal within a first time period before the quality inspection moment may be determined. The duration of the first time period may be longer than the duration between two adjacent quality inspection moments. Determine the absolute value of the difference between the second mean value and the first mean value. Use the absolute value as the first quality indicator. The first quality condition may be that the first quality indicator is less than a preset first threshold value. Then, when the first quality indicator is less than the first threshold value, the deep signal to be detected is in a valid state. When the first quality indicator is not less than the first threshold value, the deep signal to be detected is in an invalid state.
[0074] Exemplarily, the quality indicator may include a second quality indicator, and the quality condition may include a second quality condition. The amplitude of the deep signal to be detected between a single quality inspection moment and the quality inspection moment before the quality inspection moment may be determined. And the amplitude distribution range of the deep signal in the first time period before the quality inspection moment may be determined. The amplitude of each deep signal to be detected is used as the second quality indicator. The second quality condition may be that all second quality indicators fall within the amplitude distribution range. Then, when all second quality indicators fall within the amplitude distribution range, the deep signal to be detected is in a valid state. When any second quality indicator does not fall within the amplitude distribution range, the deep signal to be detected is in an invalid state.
[0075] In the disclosed embodiments, the quality indicators of the deep signal to be detected, collected between two adjacent quality inspection moments, can be detected in near real time to determine the effectiveness of the deep signal to be detected in near real time. If the deep signal to be detected is in an invalid state, the deep signal can be reconstructed using reconstruction data; if the deep signal to be detected is in a valid state, the reconstruction data can be used as supplementary information to enrich the deep signal from the channel dimension. In this way, the reconstruction data can be used based on different effectiveness states to improve the accuracy of stimulation parameters in a targeted manner according to different situations.
[0076] In one possible implementation, the stimulation parameter adjustment unit 14 is further used to: when the deep signal is in the valid state, use the deep signal and the information representing the non-deep signal in the reconstructed data to determine the human body's action state; and determine the stimulation parameters based on the human body's action state.
[0077] The stimulation parameter adjustment unit 14 may be provided with a first decoder that can identify the patient's body motion state based on the deep signals corresponding to one channel or multiple channels.
[0078] As mentioned above, the collected deep signal can be a deep signal corresponding to 1 or 2 channels. The reconstructed data can be the reconstructed data corresponding to all channels. Since the collected deep signal is in a valid state, the reconstructed data of each channel except the channel corresponding to the collected deep signal can be input into the decoder together with the collected deep signal. In this way, the decoder can determine the human body's action state based on the deep signal or reconstructed data corresponding to all channels. The collected deep signal is collected based on the real state of the human body, which is more reliable and closer to the actual situation of the human body than the reconstructed data. The channels corresponding to the reconstructed data are richer and can serve as supplementary information for the collected deep signal. Therefore, in the embodiment of the present disclosure, retaining the valid deep signal together with the reconstructed data corresponding to other channels to determine the human body's action state can improve the accuracy of determining the human body's action state, and further improve the accuracy of the stimulation parameters.
[0079] In a possible implementation, the stimulation parameter adjustment unit 14 is further configured to: when the deep signal is in the failure state, use the reconstructed data to determine the human body's motion state; and determine the stimulation parameters based on the human body's motion state.
[0080] Since the acquired deep signal is in an invalid state, it cannot be used. As mentioned above, the reconstructed data can be the reconstruction data corresponding to each channel. Therefore, the reconstructed data can be used to replace the acquired deep signal to make up for the defect of the missing deep signal, which is equivalent to making the deep signal in a continuous and stable state, thereby improving the accuracy of the stimulation parameters. The reconstructed data can be input into the decoder to determine the human body's action state. This improves the overall stability of the deep signal and enriches the deep signal in the channel dimension. In turn, the accuracy of the stimulation parameters is improved.
[0081] In a possible implementation, the action state includes: the behavioral state of a patient suffering from a movement disorder, wherein the movement disorder includes at least: Parkinson's disease, dystonia, and Tourette syndrome; the behavioral state includes at least: a sleep state and a movement state.
[0082] The closed-loop brain stimulation system in the disclosed embodiments can provide brain stimulation for patients with various movement disorders. It significantly improves the accuracy of sleep classification and movement state detection for patients with different movement disorders, providing reliable data support for clinical research.
[0083] In one possible implementation, the reconstructed data includes: first characteristic information of a first deep signal generated by brain activity during the period of collecting the superficial signal sub-time series; the reconstructed data determination unit 13 is further used to: perform time convolution processing on the superficial signal sub-time series to obtain a signal time series; analyze the signal time series to obtain an analyzed signal time series; determine second characteristic information of the analyzed signal time series, and use the second characteristic information as the first characteristic information.
[0084] Brain activity generates deep signals. For ease of description, the deep signals generated by brain activity during the period of collecting the superficial signal sub-time series are referred to as the first deep signal. Signal characteristic information refers to key parameters or indicators that describe the signal's essential properties and are used for signal analysis, identification, or processing. The characteristic information of the first deep signal can include its amplitude, frequency, phase, and other information.
[0085] In an embodiment of the present disclosure, a temporal convolutional neural network can be used to process a shallow signal sub-time series to obtain a signal time series. Compared with the shallow sub-time series, the signal time series has lower noise and more prominent characteristic information carried by the shallow signal sub-time series. The signal time series can be parsed. For example, at least one of the following methods, such as Hilbert transform, fractional-order Hilbert transform, and complex-valued sparse Bayes, can be used to parse the signal time series to obtain an analyzed signal time series. Then, the second characteristic information of the analyzed signal time series is determined, and the second characteristic information is used as the first characteristic information. In this way, reconstructed data is obtained.
[0086] The decoder may include a first decoder. The first decoder may determine the human motion state based on the second feature information (reconstructed data). And / or, the first decoder may further determine the human motion state based on the collected deep signal and the second feature information (reconstructed data).
[0087] In the disclosed embodiment, the reconstruction data determination unit 13 can determine the second characteristic information and use the second characteristic information as the reconstruction data, thereby increasing the efficiency of determining the stimulation parameters without simulating the first deep signal or analyzing the simulated first deep signal.
[0088] In one possible implementation, the reconstructed data includes: a first deep signal generated by brain activity during the period of collecting the superficial signal sub-time series; the reconstructed data determination unit 13 is further used to: use a diffusion model to process the superficial signal sub-time series to generate a second deep signal; and use the second deep signal as the first deep signal.
[0089] In the embodiment of the present disclosure, a diffusion model can be pre-trained. Using the diffusion model, a second deep signal is simulated based on the superficial signal sub-time series. The number of second deep signals can be one or more. If brain activity generates a first deep signal during the period of collecting the superficial signal sub-time series, then a second deep signal can be simulated. If brain activity generates multiple first deep signals during the period of collecting the superficial signal sub-time series, then multiple second deep signals can be simulated. The second deep signal is used as the first deep signal, and thus reconstructed data is obtained.
[0090] The decoder may include a second decoder. The second decoder may determine the human motion state based on the second deep signal (reconstructed data). And / or, the second decoder may further determine the human motion state based on the acquired deep signal and the second deep signal (reconstructed data).
[0091] In this way, the simulation efficiency is improved, and the similarity between the simulated second deep signal and the first deep signal actually generated by the brain can be improved. In the embodiment of the present disclosure, the second deep signal can be obtained to obtain a completed deep signal, thereby improving the integrity of the deep signal.
[0092] In some embodiments, the functions or modules included in the device provided by the embodiments of the present disclosure can be used to execute the method described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments. For the sake of brevity, it will not be repeated here.
[0093] Figure 2 Schematic diagram of the closed-loop brain stimulation method provided in the embodiment of the present disclosure. Figure 2 As shown, the method includes:
[0094] S21, collecting superficial and deep brain signals in time sequence.
[0095] S22, determining a superficial signal sub-time series corresponding to any of the deep signals.
[0096] S23, generating reconstruction data corresponding to any of the deep signals according to the superficial signal sub-time series.
[0097] S24, adjusting brain stimulation parameters based on the reconstructed data corresponding to the deep signal.
[0098] In a possible implementation, it also includes: determining the quality index of the deep signal to be detected collected between two adjacent quality inspection moments; when the quality index is less than a threshold, determining that the deep signal to be detected is in an invalid state; when the quality index is not less than a threshold, determining that the deep signal to be detected is in a valid state; determining the superficial signal sub-time series corresponding to any of the deep signals includes: taking the superficial signal collected between the two adjacent quality inspection moments as the superficial signal sub-time series.
[0099] In one possible implementation, adjusting the stimulation parameters of the brain based on the reconstructed data corresponding to the deep signal includes: when the deep signal is in the valid state, using the deep signal and the information representing the non-deep signal in the reconstructed data to determine the human body's action state; and determining the stimulation parameters based on the human body's action state.
[0100] In one possible implementation, adjusting the stimulation parameters of the brain based on the reconstructed data corresponding to the deep signal includes: when the deep signal is in the failed state, using the reconstructed data to determine the human body's action state; and determining the stimulation parameters based on the human body's action state.
[0101] In a possible implementation, the action state includes: the behavioral state of a patient suffering from a movement disorder, wherein the movement disorder includes at least: Parkinson's disease, dystonia, and Tourette syndrome; the behavioral state includes at least: a sleep state and a movement state.
[0102] In a possible implementation, the reconstructed data includes: characteristic information of a first signal generated by brain activity during a period of collecting the superficial signal sub-time series;
[0103] The method of generating the reconstruction data corresponding to any of the deep signals based on the superficial signal sub-time series includes: performing time convolution processing on the superficial signal sub-time series to obtain a signal time series; parsing the signal time series to obtain an analytical signal time series; determining characteristic information of the analytical signal time series, and using the characteristic information as the reconstruction data.
[0104] In one possible implementation, the reconstructed data includes: a first signal generated by brain activity during a period of time during which the superficial signal sub-time series is collected;
[0105] Generating the reconstruction data corresponding to any of the deep signals based on the superficial signal sub-time series includes: using a diffusion model to process the superficial signal sub-time series to generate multiple first signals, obtaining a first signal time series, and using the first signal time series as the reconstruction data.
[0106] An embodiment of the present disclosure further provides an electronic device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the above method.
[0107] An embodiment of the present disclosure further provides a non-volatile computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the above method when executed by a processor.
[0108] An embodiment of the present disclosure further provides a computer program product, including a computer program, or a non-volatile computer-readable storage medium carrying the computer program, wherein the computer program implements the steps of the above method when executed by a processor.
[0109] Figure 3 Schematic diagram of the electronic device structure for closed-loop brain stimulation provided by the embodiment of the present disclosure. For example, the electronic device 1900 can be provided as a server or terminal device. Figure 3The electronic device 1900 includes a processing component 1922, which further includes one or more processors, and a memory resource represented by a memory 1932 for storing instructions executable by the processing component 1922, such as an application. The application stored in the memory 1932 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 1922 is configured to execute the instructions to perform the above-described method.
[0110] The electronic device 1900 may further include a power supply component 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input / output interface 1958 (I / O interface). The electronic device 1900 may operate based on an operating system stored in the memory 1932, such as Windows Server 2003. TM , Mac OS X TM , Unix TM ,Linux TM , FreeBSD TM or similar.
[0111] In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as a memory 1932 including computer program instructions that can be executed by the processing component 1922 of the electronic device 1900 to perform the above method.
[0112] A computer-readable storage medium can be a tangible device that can hold and store programs / instructions used by an instruction execution device. A computer-readable storage medium can be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination thereof. As used herein, a computer-readable storage medium is not to be construed as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through an electrical wire.
[0113] The computer programs (or computer-readable program instructions) described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions to be stored in the computer-readable storage medium in each computing / processing device.
[0114] The computer program (or computer program instructions) for performing the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages such as Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The computer readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, by utilizing state information of computer-readable program instructions to personalize and customize an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), the electronic circuit can execute the computer-readable program instructions to implement various aspects of the present disclosure.
[0115] Various aspects of the present disclosure are described herein with reference to flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present disclosure. It should be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.
[0116] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device is generated that implements the functions / actions specified in one or more blocks in the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium, where these instructions cause the computer, programmable data processing device, and / or other device to operate in a specific manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing various aspects of the functions / actions specified in one or more blocks in the flowchart and / or block diagram.
[0117] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more blocks in the flowchart and / or block diagram.
[0118] The flow charts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to multiple embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and the part of the module, program segment or instruction contains one or more executable instructions for realizing the prescribed logical function. In some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the prescribed function or action, or can be implemented by a combination of dedicated hardware and computer instructions.
[0119] While various embodiments of the present disclosure have been described above, the foregoing description is intended to be illustrative, non-exhaustive, and not limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is selected to best explain the principles of the embodiments, their practical applications, or technological improvements in the marketplace, or to enable others skilled in the art to understand the embodiments disclosed herein.
Claims
1. A closed-loop brain stimulation system based on a brain-computer interface, characterized in that: include: A dual-modal recording unit for acquiring superficial and deep brain signals in a time-sequential manner; a superficial signal sub-time series determining unit, configured to determine a superficial signal sub-time series corresponding to any of the deep signals; a reconstruction data determining unit, configured to generate reconstruction data corresponding to any of the deep signals according to the superficial signal sub-time series; A stimulation parameter adjustment unit is used to adjust brain stimulation parameters based on the reconstructed data corresponding to the deep signal.
2. The system according to claim 1, wherein: Also includes: A quality inspection unit, the quality inspection unit is used to: Determining, according to the quality inspection frequency, a quality index of the deep signal to be detected, for the deep signal to be detected acquired between two adjacent quality inspection moments; When the quality indicator is less than a threshold, determining that the deep signal to be detected is in a failed state; When the quality indicator is not less than a threshold, determining that the deep signal to be detected is in a valid state; The shallow signal sub-time series determination unit is further configured to: The superficial signal collected between the two adjacent quality inspection moments is used as the superficial signal sub-time series.
3. The system according to claim 2, characterized in that The stimulation parameter adjustment unit is further configured to: When the deep signal is in the valid state, determining a human motion state by using the deep signal and information representing non-deep signals in the reconstructed data; The stimulation parameters are determined based on the human body action state.
4. The system according to claim 2, wherein: The stimulation parameter adjustment unit is further configured to include: In the case where the deep signal is in the failed state, determining a human body motion state using the reconstructed data; The stimulation parameters are determined based on the human body action state.
5. The system according to claim 3 or 4, characterized in that The action state includes: the behavioral state of a patient suffering from a movement disorder, wherein the movement disorder includes at least: Parkinson's disease, dystonia, and Tourette syndrome; the behavioral state includes at least: a sleeping state and a movement state.
6. The system according to any one of claims 1 to 4, characterized in that: The reconstructed data includes: characteristic information of a first signal generated by brain activity during the period of collecting the superficial signal sub-time series; The reconstruction data determination unit is further configured to: Performing time convolution processing on the shallow signal sub-time series to obtain a signal time series; parsing the signal time series to obtain an parsed signal time series; Characteristic information of the analytical signal time series is determined, and the characteristic information is used as the reconstructed data.
7. The system according to any one of claims 1 to 4, characterized in that: The reconstructed data includes: a first signal generated by brain activity during the period of collecting the superficial signal sub-time series; The reconstruction data determination unit is further configured to: The shallow signal sub-time series is processed using a diffusion model to generate a plurality of the first signals, thereby obtaining a first signal time series, and the first signal time series is used as the reconstructed data.
8. A closed-loop brain stimulation method based on a brain-computer interface, characterized in that: include: Collect superficial and deep brain signals in time sequence; Determine a superficial signal sub-time series corresponding to any of the deep signals; generating, according to the superficial signal sub-time series, reconstruction data corresponding to any of the deep signals; Based on the reconstructed data corresponding to the deep signal, brain stimulation parameters are adjusted.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the functions of the system according to any one of claims 1 to 7.
10. A non-volatile computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the function of the system according to any one of claims 1 to 7 is realized.