Injection regulation and control system, method and equipment based on brain planar graph mapping

Abstract

The invention provides an injection regulation and control system, method and equipment based on brain planar graph mapping, and relates to the technical field of injection regulation and control. The system comprises a needle inserting position monitoring module, an injection pre-regulation and control module and an injection emergency regulation and control module. The needle insertion position of the injection needle is obtained through the deployed needle insertion position detection tool, then injection presetting is carried out according to the predicted needle insertion position, the electroencephalogram of the injection object is obtained in real time, and when the electroencephalogram of the injection object predicts the neural reaction, the injection object is subjected to neural reaction prediction. If yes, the predicted needle inserting position is matched with the actual needle inserting position to obtain a needle inserting position matching result, and corresponding injection regulation and control are conducted according to the needle inserting position matching result, so that the effect of improving the timeliness of ventricular injection regulation and control of the injection object is achieved. The problem that in the prior art, when the needle inserting position of an injection object deviates, ventricular injection regulation and control response is not timely is solved.

Description

Technical Field

[0001] This invention relates to the field of injection modulation technology, and in particular to an injection modulation system, method and device based on brain planar mapping. Background Technology

[0002] With the deepening of brain science research, mice are increasingly being used as important animal models in the field of neuroscience. Intraventricular injection is one of the key means to achieve precise drug delivery and neuromodulation. However, traditional injection devices suffer from insufficient precision and portability. A portable mouse intraventricular injection system based on brain planar mapping and precise depth adjustment, combining precise brain planar mapping positioning and depth adjustment functions, can effectively improve injection accuracy and provide a more precise means of operation for mouse neuroscience experiments.

[0003] Current intraventricular injection techniques primarily rely on fixed equipment and manual operation, resulting in low precision and cumbersome procedures. Most systems currently lack convenient depth adjustment and precise brain region localization, limiting the efficiency and accuracy of mouse neuroscience experiments. Furthermore, traditional equipment is bulky and inconvenient to carry, failing to meet the needs of researchers in diverse experimental environments. Therefore, developing a portable injection system with precise depth adjustment and brain planar mapping capabilities has become an urgent problem to be solved.

[0004] For example, the invention patent with publication number CN112168414B discloses an injection device for rat brain experiments, including: a fixed base with a fixed seat for fixing the rat on its top surface; a support slidably mounted on the fixed base, with an electric push rod connected between the support and the fixed base; a displacement device mounted on the support, and a syringe fixed base connected to the displacement device; a syringe fixed slide slidably mounted on the syringe fixed base, with a sliding drive device connected between the syringe fixed slide and the syringe fixed base, and a syringe connected to the syringe fixed slide; a TOF camera mounted on the syringe fixed base, the TOF camera electrically connected to a controller, the controller electrically connected to the displacement device, and the controller controlling the displacement device to operate according to the image information from the TOF camera, so as to align the syringe with the rat's brain.

[0005] For example, invention patent CN118178785B discloses an analgesic drug delivery regulation system, including: a hand gripper, an analgesic drug delivery device connected to the hand gripper, and an information processing unit. The system also includes a uterine contraction detection module and an electroencephalogram (EEG) signal detection module. Upon receiving a request signal from a patient request unit, the information processing unit generates a drug injection dosage corresponding to the brain information presented by the EEG signal detection module. The drug injection dosage, regulated based on the brain information, is limited by the original bioelectric potential signal related to uterine muscle contraction presented by the uterine contraction detection module and is adjusted within a range matching the uterine contraction rhythm reflected by the original bioelectric potential signal.

[0006] However, the above technology has the following technical problems: because the injection subject may experience slight brain displacement or vibration during the injection process, especially unexpected movements caused by nerve reflexes or other physiological changes, the brain region injected into the ventricle of the injection subject may deviate, resulting in a problem of untimely ventricle injection control response when the injection subject deviates from the needle insertion position. Summary of the Invention

[0007] To address the aforementioned problems, embodiments of the present invention provide an injection control system, method, and device based on brain planar mapping, which solves the problem of untimely ventricular injection control response when the needle insertion position of the injection subject deviates in the prior art, thereby improving the timeliness of ventricular injection control for the injection subject.

[0008] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0009] On one hand, an injection control system based on brain plane mapping is provided, comprising: a needle insertion location monitoring module, an injection pre-control module, and an injection emergency control module. The needle insertion location monitoring module acquires the needle insertion location using a deployed needle insertion location detection tool. The needle insertion location includes a predicted needle insertion location and an actual needle insertion location. The predicted needle insertion location is obtained by inputting the predicted neural response signal of the injection subject obtained from an electroencephalogram (EEG) into a pre-trained model. The actual needle insertion location is obtained by mapping using a high-resolution brain plane projection system. The injection pre-control module performs injection pre-control based on the predicted needle insertion location and acquires the EEG of the injection subject in real time. The injection emergency control module matches the predicted needle insertion location with the actual needle insertion location to obtain a needle insertion location matching result when the EEG of the injection subject predicts a neural response, and performs corresponding injection control based on the needle insertion location matching result.

[0010] Optionally, the specific content of the injection pre-adjustment based on the predicted needle insertion position is as follows: obtaining corresponding injection pre-adjustment data from a preset database based on the obtained predicted needle insertion position, the injection pre-adjustment data including the pre-adjustment injection position, pre-adjustment injection depth, and pre-adjustment injection dose; and pre-regulating the injection data of the injection needle according to the pre-adjustment ratio obtained from the preset database, the injection data including the injection position, injection depth, and injection dose.

[0011] Optionally, the specific steps for corresponding injection control based on the needle insertion position matching result are as follows: If the needle insertion position matching result is successful, injection pre-control is performed, and the injection needle is controlled according to the injection pre-control data; a pre-control ratio mapping set of the number of successful matches and the ratio adjustment rate is constructed, and the real-time accumulated number of successful matches is input into the pre-control ratio mapping set to obtain the ratio adjustment rate; the pre-control ratio is adjusted according to the ratio adjustment rate to obtain the optimized pre-control ratio; if the optimized pre-control ratio is not less than the preset ratio limit, the ratio adjustment calculation is not continued; if the needle insertion position matching result is a failed match, injection emergency control is performed.

[0012] Optionally, the specific process of the emergency injection control is as follows: based on the actual needle insertion position, obtain the corresponding injection adjustment data from a preset database; perform compensation calculation on the injection data according to the injection adjustment data to obtain the target injection data; and combine the obtained real-time injection data to obtain the injection adjustment force coefficient. The compensation calculation is used to supplement and delay the injection data to obtain the target injection data; input the real-time injection adjustment force coefficient into the adjustment force mapping set to obtain the adjustment ratio. The adjustment force mapping set represents the set of mapping relationships between the injection adjustment force coefficient and the adjustment ratio; and adjust the injection data of the injection needle according to the adjustment ratio, while simultaneously adjusting the mapping frequency.

[0013] Optionally, the specific process of adjusting the injection data of the injection needle is as follows: when the needle insertion position matching result is successful, the injection needle is adjusted, and the default adjustment speed of the injection position is adjusted according to the pre-adjustment ratio; otherwise, the default adjustment speed of the injection position is adjusted according to the actual adjustment ratio; the position adjustment completion time is acquired in real time, and a depth adjustment influence factor is obtained by mapping the position adjustment completion time; the depth adjustment speed of the injection depth is calculated by performing depth adjustment calculation based on the depth adjustment influence factor to obtain an optimized depth adjustment speed, and the injection depth is adjusted based on the optimized depth adjustment speed, while the depth adjustment completion time is acquired in real time; the dose adjustment influence factor is obtained by mapping the depth adjustment completion time, and the dose adjustment speed of the injection dose is calculated by performing dose adjustment calculation based on the dose adjustment influence factor to obtain an optimized dose adjustment speed, and the injection dose is adjusted based on the optimized dose adjustment speed.

[0014] Optionally, the injection adjustment force coefficient is obtained as follows: real-time injection data and target injection data are acquired, wherein the real-time injection data includes real-time injection location, real-time injection depth, and real-time injection dose, and the target injection data includes target injection location, target injection depth, and target injection dose; injection force adjustment weights are obtained from a preset database, wherein the injection force adjustment weights include location force weights, depth force weights, and dose force weights; the real-time injection data and the corresponding target injection data are used to calculate the adjustment deviation to obtain an injection adjustment deviation value; the injection adjustment deviation value and the corresponding injection force adjustment weights are weighted and coupled to obtain the injection adjustment force coefficient.

[0015] Optionally, the specific process of the mapping frequency regulation is as follows: Prediction deviation analysis is performed using injection-adjusted data and injection-pre-adjusted data to obtain a prediction confidence coefficient. This prediction deviation analysis is used to comprehensively quantify the confidence level of the predicted needle insertion location. The prediction confidence coefficient is input into a confidence mapping set to obtain a planar map mapping frequency multiple. This confidence mapping set represents a set of mapping relationships between the planar map mapping frequency multiple and the prediction confidence coefficient. An optimized mapping frequency is obtained by performing a frequency adjustment operation on the planar map mapping frequency based on the planar map mapping frequency multiple. This frequency adjustment operation is used to optimize the planar map mapping frequency using the planar map mapping frequency multiple. Brain planar mapping is then performed based on the optimized mapping frequency.

[0016] Optionally, the specific method for obtaining the prediction confidence coefficient is as follows: Obtain actual injection data, including actual injection location, actual injection depth, and actual injection dose; obtain prediction confidence weights from a preset database, including location confidence weight, depth confidence weight, and dose confidence weight; perform prediction deviation calculation between the actual injection data and the pre-adjusted injection data to obtain an injection prediction deviation value, whereby the prediction deviation calculation is used to quantify the degree of difference between the actual injection data and the pre-adjusted injection data; and couple the injection prediction deviation value with the corresponding prediction confidence weights to obtain the prediction confidence coefficient.

[0017] On the other hand, a device for an injection control system based on brain planar mapping is also provided, including a syringe body, a processor, a camera, a sensor, and a touch screen; the camera is used to capture images of the brain surface of the injection subject in real time; the sensor is used to monitor the needle contact point and injection depth of the injection needle in real time; the processor is used to receive and process the data from the camera and sensor and control the injection needle based on the processing results; the touch screen is used to display the injection data of the injection needle in real time or to input control information for adjusting the injection data.

[0018] On the other hand, an injection modulation method based on brain plane mapping is also provided, including the following steps: obtaining the needle insertion position of the injection needle through a deployed needle insertion position detection tool, wherein the needle insertion position includes a predicted needle insertion position and an actual needle insertion position. The predicted needle insertion position is obtained by inputting the predicted neural response signal of the injection subject obtained by electroencephalography (EEG) into a pre-trained model, and the actual needle insertion position is obtained by mapping through a high-resolution brain plane projection system; performing injection pre-modulation based on the predicted needle insertion position and acquiring the EEG of the injection subject in real time; when the EEG of the injection subject predicts a neural response, the predicted needle insertion position is matched with the actual needle insertion position to obtain a needle insertion position matching result, and corresponding injection modulation is performed based on the needle insertion position matching result.

[0019] One or more technical solutions provided in the embodiments of the present invention have at least the following technical effects or advantages:

[0020] 1. The needle insertion position is obtained by deploying a needle insertion position detection tool. Then, injection pre-adjustment is performed based on the predicted needle insertion position, and the EEG of the injection subject is acquired in real time. When the EEG of the injection subject predicts a neural response, the predicted needle insertion position is matched with the actual needle insertion position to obtain the needle insertion position matching result. The corresponding injection control is then performed based on the needle insertion position matching result, thereby responding to the injection subject's injection control more promptly and improving the timeliness of ventricular injection control. This effectively solves the problem of untimely ventricular injection control response when the needle insertion position of the injection subject deviates in the existing technology.

[0021] 2. By acquiring real-time injection data and target injection data, and obtaining the injection force adjustment weight from the preset database, the real-time injection data and the corresponding target injection data are then used to calculate the injection control deviation value. Finally, the injection control deviation value is coupled with the corresponding injection force adjustment weight to obtain the injection control force coefficient, thereby more accurately quantifying the urgency of injection control and realizing dynamic control of injection needle injection.

[0022] 3. By acquiring actual injection data and obtaining prediction confidence weights from a preset database, the prediction deviation value of the actual injection data and the pre-adjusted injection data is calculated. Finally, the prediction confidence coefficient is obtained by weighting the prediction deviation value and the corresponding prediction confidence weights. This allows for a more accurate assessment of the confidence level of the current prediction mechanism, thereby enabling adjustments to the prediction mechanism for more accurate injection control. Attached Figure Description

[0023] Figure 1 This is a schematic diagram of the structure of an injection control system based on brain planar mapping, provided in an embodiment of the present invention.

[0024] Figure 2 A flowchart provided for an embodiment of the present invention. Detailed Implementation

[0025] This invention provides an injection control system, method, and device based on brain planar mapping, solving the problem of untimely ventricular injection control response when the needle insertion position deviates in the prior art. It obtains the needle insertion position using a deployed needle insertion position detection tool, performs injection pre-adjustment based on the predicted insertion position, and acquires the electroencephalogram (EEG) of the injection subject in real time. When the EEG predicts a neural response, the predicted insertion position is matched with the actual insertion position to obtain a matching result. Corresponding injection control is then performed based on the matching result. If the matching result is satisfactory... If a match is successful, pre-injection control is performed, and the injection needle is adjusted based on the pre-injection control data. Simultaneously, a pre-adjustment ratio mapping set is constructed, which maps the number of successful matches to the ratio adjustment rate. The real-time accumulated number of successful matches is then input into the pre-adjustment ratio mapping set to obtain the ratio adjustment rate. The pre-adjustment ratio is then adjusted based on the ratio adjustment rate to obtain the optimized pre-adjustment ratio. If the optimized pre-adjustment ratio is not less than the preset ratio limit, the ratio adjustment calculation is not performed. Finally, if the needle insertion position matching result is a match failure, emergency injection control is performed, thereby improving the timeliness of intraventricular injection control for the injection subject.

[0026] The technical solution in this invention aims to address the problem of untimely intraventricular injection control response when the needle insertion position deviates from the target. The overall approach is as follows:

[0027] The needle insertion position is obtained by deploying a needle insertion position detection tool. Then, the injection is pre-adjusted according to the predicted needle insertion position. The EEG of the injection subject is acquired in real time. When the EEG of the injection subject predicts a neural response, the predicted needle insertion position is matched with the actual needle insertion position to obtain the needle insertion position matching result. The corresponding injection control is then performed according to the needle insertion position matching result, which improves the timeliness of intraventricular injection control for the injection subject.

[0028] To better understand the above technical solutions, the following will provide a detailed explanation of the technical solutions in conjunction with the accompanying drawings and specific implementation methods.

[0029] like Figure 1The diagram shows a schematic of an injection control system based on brain plane mapping provided in an embodiment of the present invention. The system includes: a needle insertion location monitoring module, an injection pre-control module, and an injection emergency control module. The needle insertion location monitoring module uses a deployed needle insertion location detection tool to obtain the needle insertion location, which includes a predicted needle insertion location and an actual needle insertion location. The predicted needle insertion location is obtained by inputting the predicted neural response signal of the injection subject, acquired from an electroencephalogram (EEG), into a pre-trained model. The actual needle insertion location is obtained by mapping using a high-resolution brain plane projection system. The injection pre-control module performs injection pre-control based on the predicted needle insertion location and acquires the EEG of the injection subject in real time. The injection emergency control module matches the predicted needle insertion location with the actual needle insertion location to obtain a needle insertion location matching result when the EEG of the injection subject predicts a neural response, and performs corresponding injection control based on the matching result.

[0030] In this embodiment, experimental mice are used as an example for explanation. Injection regulation is performed on the ventricles of the injection subject based on brain planar mapping. However, during the injection regulation process, the ventricles of the injection subject may experience brain displacement, especially unexpected movements caused by nerve reflexes or other physiological changes. This results in untimely ventricular injection regulation response when the injection subject deviates from the needle insertion position. The needle insertion position detection tool refers to an ultrasonic sensor and a pre-trained model. Through the needle insertion position monitoring module, injection pre-regulation module, and injection emergency regulation module of this system, the needle insertion position of the injection subject can be reflected in a timely manner, and corresponding predictive regulation or emergency regulation can be taken. This ensures that the corresponding injection regulation can respond more promptly when the injection subject deviates from the needle insertion position, thereby improving the efficiency of injection regulation.

[0031] It should be added that the needle insertion position of the injection object on the experimental table is stored in the preset database in advance. The needle insertion position corresponding to the range of motion of the injection needle of the injection object is mapped one by one with the corresponding injection data to obtain the needle insertion position-injection data mapping set. When the needle insertion position of the injection object is displaced, the real-time needle insertion position is input into the needle insertion position-injection data mapping set to obtain the corresponding injection data.

[0032] It needs to be explained that electroencephalography (EEG) records the electrical activity of the brain of experimental mice by placing electrodes on the scalp of the injection subject (i.e., laboratory mice). This method monitors and predicts neural responses, especially under anesthesia or behavioral stimulation. The injection data is labeled with the corresponding brain region number and the corresponding EEG signal. The brain region numbering uses known brain atlases (such as the Paxinos rat and mouse brain atlases) to define different brain regions, and each brain region has a unique number or label in the atlas. The labeled EEG signals with known needle insertion locations and other labeled EEG signals are input into a deep neural network model (such as CNN) for pre-training to obtain a pre-trained model used to predict the needle insertion location. The real-time EEG signals are input into the pre-trained model, and the pre-trained model outputs the corresponding predicted needle insertion location.

[0033] Optionally, the specific details of injection pre-adjustment based on the predicted needle insertion position are as follows: obtaining corresponding injection pre-adjustment data from a preset database based on the obtained predicted needle insertion position, the injection pre-adjustment data including the pre-adjustment injection location, pre-adjustment injection depth, and pre-adjustment injection dose; and pre-adjusting the injection data of the injection needle based on the pre-adjustment ratio obtained from the preset database, the injection data including the injection location, injection depth, and injection dose.

[0034] In this embodiment, the current predicted needle insertion position is input into the needle insertion position-injection data mapping set to obtain the corresponding injection data, and the difference between the current real-time injection data is calculated to obtain the injection pre-adjustment data; the pre-adjustment ratio is preset by professional experimenters according to the specific experimental requirements of the ventricle of the injection subject and stored in a preset database; the pre-adjustment ratio is multiplied by the injection pre-adjustment data to obtain the corresponding pre-adjustment data to be pre-adjusted, and the pre-adjustment data to be pre-adjusted is summed with the current injection data to obtain the pre-adjustment data to be adjusted. The injection data is adjusted to the pre-adjustment data to be pre-adjusted for pre-control, which helps to improve the timeliness of the injection control response when the needle insertion position of the injection subject is displaced.

[0035] Optionally, the specific steps for injection control based on the needle insertion position matching result are as follows: If the needle insertion position matching result is successful, injection pre-control is performed, and the injection data of the injection needle is controlled according to the injection pre-control data; a pre-control ratio mapping set of the number of successful matches and the ratio adjustment rate is constructed, and the number of successful matches accumulated in real time is input into the pre-control ratio mapping set to obtain the ratio adjustment rate; the pre-control ratio is adjusted according to the ratio adjustment rate to obtain the optimized pre-control ratio; if the optimized pre-control ratio is not less than the preset ratio limit, the ratio adjustment calculation is not continued; if the needle insertion position matching result is a failure, injection emergency control is performed.

[0036] In this embodiment, the proportional adjustment operation refers to the product operation of the proportional adjustment rate and the pre-adjustment ratio, and the proportional limit is preset by professional experimental personnel according to the specific experimental requirements of the ventricle of the injection subject and stored in a preset database; by adopting different injection control measures through different matching structures, timely response is ensured when the needle insertion position of the injection subject is displaced, thereby improving the efficiency of ventricle injection control of the injection subject.

[0037] Optionally, the specific process of emergency injection control is as follows: based on the actual needle insertion position, obtain the corresponding injection adjustment data from the preset database; perform compensation calculation on the injection data according to the injection adjustment data to obtain the target injection data; and combine the obtained real-time injection data to obtain the injection adjustment force coefficient. The compensation calculation is used to supplement and delay the injection data to obtain the target injection data; input the real-time injection adjustment force coefficient into the adjustment force mapping set to obtain the adjustment ratio. The adjustment force mapping set represents the set of mapping relationships between the injection adjustment force coefficient and the adjustment ratio; adjust the injection data of the injection needle according to the adjustment ratio, and simultaneously adjust the mapping frequency.

[0038] In this embodiment, the current actual needle insertion position is input into the needle insertion position-injection data mapping set to obtain the corresponding injection data, and the difference is calculated with the current real-time injection data to obtain the actual injection adjustment data; the compensation operation represents the addition operation between the actual injection adjustment data and the injection data; the adjustment force mapping set is a set obtained from a preset database that represents the mapping relationship between the injection adjustment force coefficient and the actual adjustment ratio, and the real-time injection adjustment force coefficient is input into the adjustment force mapping set to obtain the corresponding actual adjustment ratio; the method provided in this embodiment ensures that the injection solution is injected more accurately into the predetermined ventricular region, reducing the risk of accidental damage to surrounding brain tissue.

[0039] Optionally, the specific process of adjusting the injection data of the injection needle is as follows: When the needle insertion position matching result is successful, the injection needle is adjusted, and the default adjustment speed of the injection position is adjusted according to the pre-adjustment ratio; otherwise, the default adjustment speed of the injection position is adjusted according to the actual adjustment ratio. The position adjustment completion time is acquired in real time, and the depth adjustment influence factor is obtained by mapping the position adjustment completion time. The depth adjustment speed is calculated by performing depth adjustment calculation on the default adjustment speed of the injection depth according to the depth adjustment influence factor to obtain the optimized depth adjustment speed. The injection depth is adjusted based on the optimized depth adjustment speed, and the depth adjustment completion time is acquired in real time. The dose adjustment influence factor is obtained by mapping the depth adjustment completion time. The dose adjustment speed is calculated by performing dose adjustment calculation on the default adjustment speed of the injection dose according to the dose adjustment influence factor to obtain the optimized dose adjustment speed. The injection dose is adjusted based on the optimized dose adjustment speed.

[0040] In this embodiment, the depth modulation influence factor is obtained through a position-depth influence mapping set. The position-depth influence mapping set is obtained by constructing a set of mapping relationships between the position modulation completion time and pre-set depth modulation influence factors. The depth modulation influence factor is obtained by inputting the real-time position modulation completion time into the position-depth influence mapping set. Similarly, the dose modulation influence factor is obtained through a depth-dose influence mapping set. The depth-dose influence mapping set is obtained by constructing a set of mapping relationships between the depth adjustment completion time and pre-set dose modulation influence factors. The dose modulation influence factor is obtained by inputting the real-time depth adjustment completion time into the position-depth influence mapping set. The depth modulation operation is represented as follows: The depth regulation influencing factor is multiplied by the default injection depth adjustment speed, while the dose regulation operation is multiplied by the dose regulation influencing factor and the default injection dose adjustment speed. A shorter adjustment time for the injection position results in a lower requirement for adjustment of the injection depth, and a smaller depth regulation influencing factor. Conversely, a longer adjustment time for the injection depth results in a higher requirement for adjustment of the injection dose, and a larger dose regulation influencing factor. By optimizing the default adjustment speed of the injection data, the entire injection process becomes more efficient, reducing delays and enabling smoother experimental execution, thus improving overall experimental efficiency.

[0041] It should be added that the default speed of injection position adjustment refers to the speed at which the injection needle position is automatically adjusted when the needle insertion position of the injection target is detected to deviate from the target needle insertion position; the default speed of injection depth adjustment refers to the speed at which the injection depth of the injection needle is automatically adjusted; and the default speed of injection dosage adjustment refers to the speed at which the drug injection dosage is adjusted during the injection process based on the position, depth, vibration, or other physiological changes of the injection target. Through machine learning algorithms and deep neural networks, structural changes in the mouse brain regions are recorded in each experiment, and the calculation of positioning points is automatically adjusted in subsequent operations. Automatic control is also achieved through a touch screen or APP interface.

[0042] Optionally, the specific method for obtaining the injection adjustment force coefficient is as follows: Obtain real-time injection data and target injection data. The real-time injection data includes the real-time injection location, real-time injection depth, and real-time injection dose. The target injection data includes the target injection location, target injection depth, and target injection dose. Obtain the injection force adjustment weights from a preset database. The injection force adjustment weights include location force weights, depth force weights, and dose force weights. Calculate the injection adjustment deviation value by performing a control deviation calculation on the real-time injection data and the corresponding target injection data. The injection location control deviation value is obtained through a distance algorithm (such as...). The shortest path distance between the real-time injection location and the target injection location is calculated using algorithms such as Dijkstra's algorithm and Bellman-Ford algorithm. The injection control deviation value is then coupled with the corresponding injection force adjustment weight to obtain the injection control force coefficient.

[0043] The specific expression for the injection adjustment force coefficient is as follows:

[0044] ;

[0045] In the formula, WP represents the injection site adjustment deviation value, D represents the real-time injection depth, J represents the real-time injection dose, and D M J represents the target injection depth. M β1 represents the target injection dose, β2 represents the position force weight, β3 represents the depth force weight, and ω represents the injection adjustment force coefficient.

[0046] In this embodiment, the algorithm combines real-time injection data, target injection data, and injection force adjustment weights to obtain an injection adjustment force coefficient. In this coefficient, the greater the deviation of the real-time injection location from the target injection location, the higher the need for needle adjustment. Similarly, the greater the deviation of the real-time injection depth and real-time injection dose from the target injection location and target injection dose, the more urgent the need for needle adjustment, resulting in a larger injection adjustment force coefficient and thus greater needle adjustment. By analyzing the injection adjustment force coefficient, the urgency of needle control is more accurately quantified. This allows for control of the injection data based on the injection adjustment force coefficient, thereby improving the efficiency of needle control and ensuring efficient intraventricular injection into the target body.

[0047] It should be added that the real-time injection position is obtained by using a displacement sensor to provide real-time feedback on the precise position of the injection needle; the real-time injection depth is obtained by using an ultrasonic sensor to measure the depth of the injection needle; and the real-time injection dose is obtained by using a flow sensor to detect the flow rate of the injection fluid.

[0048] Specifically, the injection force adjustment weights are obtained from a preset database. These weights represent the degree of influence of real-time injection data on the injection force adjustment coefficient. Each real-time injection data point has a unique mapping relationship with its injection force adjustment weight, and the value ranges from 0 to 1. For example, a mapping set between real-time injection data and preset injection force adjustment weights is constructed. The real-time injection location, injection depth, and injection dose are input into the mapping set to obtain the corresponding location force weight, depth force weight, and dose force weight, which respectively represent the degree of influence of the real-time injection location, injection depth, and injection dose on the injection force adjustment coefficient, and the sum of these three is 1.

[0049] Optionally, the specific process of mapping frequency regulation is as follows: Prediction deviation analysis is performed using injection-adjusted data and injection-preset data to obtain a prediction confidence coefficient. This prediction deviation analysis is used to comprehensively quantify the confidence level of the predicted needle insertion location. The prediction confidence coefficient is input into a confidence mapping set to obtain a planar map mapping frequency multiple. The confidence mapping set represents the set of mapping relationships between the planar map mapping frequency multiple and the prediction confidence coefficient. Based on the planar map mapping frequency multiple, a frequency adjustment operation is performed on the planar map mapping frequency to obtain an optimized mapping frequency. This frequency adjustment operation is used to optimize the planar map mapping frequency using the planar map mapping frequency multiple. Brain planar mapping is then performed based on the optimized mapping frequency.

[0050] In this embodiment, the frequency adjustment operation represents multiplying the planar map mapping frequency multiple by the planar map mapping frequency. The smaller the prediction confidence coefficient input to the confidence mapping set, the lower the confidence of the injection pre-adjustment, and the greater the need for accurate acquisition of the actual needle insertion position. Therefore, the corresponding output planar map mapping frequency multiple is larger. By generating the prediction confidence coefficient, the accuracy of the displacement prediction of the needle insertion position of the current injection object can be automatically evaluated based on the real-time feedback matching results. This allows for timely adjustment of the pre-adjustment ratio to reduce reliance on the prediction mechanism, ensuring the accuracy of intraventricular injection control of the injection object and improving the timeliness and efficiency of injection control.

[0051] Optionally, the specific method for obtaining the prediction confidence coefficient is as follows: Obtain actual injection data, including actual injection location, actual injection depth, and actual injection dose; obtain prediction confidence weights from a preset database, including location confidence weight, depth confidence weight, and dose confidence weight; perform prediction deviation calculations between the actual injection data and the pre-adjusted injection data to obtain the injection prediction deviation value, wherein the injection location prediction deviation value is represented by the shortest path distance between the actual injection location and the pre-adjusted injection location calculated using a distance algorithm; the prediction deviation calculation is used to quantify the degree of difference between the actual injection data and the pre-adjusted injection data; and obtain the prediction confidence coefficient by coupling the injection prediction deviation value with the corresponding prediction confidence weights.

[0052] The specific constraint expression for the prediction confidence coefficient is as follows:

[0053] ;

[0054] In the formula, AP represents the predicted deviation value of the injection site, and B P Indicates the pre-adjusted injection depth, C P Indicates pre-adjusted injection dosage, B A Indicates the actual injection depth, C Aα represents the actual injection dose, α1 represents the location confidence weight, α2 represents the depth confidence weight, α3 represents the dose confidence weight, and ρ represents the prediction confidence coefficient.

[0055] In this embodiment, the algorithm combines actual injection data, pre-injection data, and prediction confidence weights to obtain a prediction confidence coefficient. In this formula, the greater the deviation of the pre-adjusted injection location from the actual injection location, the less accurate the prediction of needle control. Similarly, the greater the deviation of the pre-adjusted injection depth and dose from the actual injection depth and dose, the less accurate the prediction of needle control, resulting in a larger prediction confidence coefficient and lower confidence in the needle control prediction. By analyzing the prediction confidence coefficient, the reliability of the needle control prediction is more accurately quantified. This allows for adjustment of the pre-adjustment ratio based on the prediction confidence coefficient, thereby improving the efficiency of needle control and ensuring efficient intraventricular injection into the target body.

[0056] Specifically, the prediction confidence weights are obtained from a pre-set database. Each prediction confidence weight represents the degree of influence of the actual injection data on the prediction confidence coefficient. There is a unique mapping relationship between each actual injection data point and the prediction confidence weight, and the value ranges from 0 to 1. For example, a mapping set between the actual injection data and the pre-set prediction confidence weights is constructed. The real-time actual injection location, actual injection depth, and actual injection dose are input into the mapping set to obtain the corresponding location confidence weight, depth confidence weight, and dose confidence weight, which respectively represent the degree of influence of the actual injection location, actual injection depth, and actual injection dose on the prediction confidence coefficient, and the sum of the three is 1.

[0057] This invention provides an injection control method based on brain plane mapping, with the following specific steps: The needle insertion position is obtained using a deployed needle insertion position detection tool. The needle insertion position includes a predicted needle insertion position and an actual needle insertion position. The predicted needle insertion position is obtained by inputting the predicted neural response signal of the injection subject obtained from an electroencephalogram (EEG) into a pre-trained model. The actual needle insertion position is obtained by mapping using a high-resolution brain plane projection system. Injection pre-adjustment is performed based on the predicted needle insertion position, and the EEG of the injection subject is acquired in real time. When the EEG of the injection subject predicts a neural response, the predicted needle insertion position is matched with the actual needle insertion position to obtain a needle insertion position matching result, and corresponding injection control is performed based on the needle insertion position matching result.

[0058] In this embodiment, by combining the predicted needle insertion location and the actual needle insertion location, injection data can be dynamically evaluated and adjusted. Real-time monitoring of the predicted needle insertion location ensures that the position data can be adjusted in advance when there is a slight displacement of the head of the injection subject, ensuring that the injection needle is always aligned with the target area of ​​the ventricle of the injection subject. This improves the timeliness of injection control when the brain of the injection subject is displaced, and also improves the efficiency of injection control based on brain planar mapping of the injection subject's ventricle.

[0059] This invention provides a device for applying an injection control system based on brain planar mapping. The device, employing this system, includes a syringe body, a processor, a camera, a sensor, and a touchscreen. The camera captures real-time images of the brain surface of the injection target. The sensor monitors the needle's contact point and injection depth in real-time. The processor receives and processes data from the camera and sensor, and controls the injection needle based on the processing results. The touchscreen displays real-time injection data or allows for the input of control information to adjust the injection data.

[0060] In summary, this invention uses a deployed needle insertion position detection tool to obtain the needle insertion position, performs injection pre-adjustment based on the predicted needle insertion position, and acquires the EEG of the injection subject in real time. When the EEG of the injection subject predicts a neural response, the predicted needle insertion position is matched with the actual needle insertion position to obtain a needle insertion position matching result. Based on the needle insertion position matching result, corresponding injection control is performed, thereby responding to the injection subject's injection control more promptly. This improves the timeliness of ventricular injection control and effectively solves the problem of untimely ventricular injection control response when the needle insertion position of the injection subject deviates in the prior art.

[0061] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0062] This invention is described with reference to flowchart illustrations and / or block diagrams of systems, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0063] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0064] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0065] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0066] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. An injection control system based on brain planar mapping, characterized in that, It includes a needle insertion position monitoring module, an injection pre-control module, and an injection emergency control module: The needle insertion position monitoring module is used to obtain the needle insertion position of the injection needle through a deployed needle insertion position detection tool. The needle insertion position includes a predicted needle insertion position and an actual needle insertion position. The predicted needle insertion position is obtained by inputting the neural response signal of the predicted injection object obtained by electroencephalography into a pre-trained model. The actual needle insertion position is obtained by mapping through a high-resolution brain plane projection system. The injection pre-adjustment module is used to pre-adjust the injection based on the predicted needle insertion location and to acquire the electroencephalogram of the injection subject in real time. The injection emergency control module is used to match the predicted needle insertion location with the actual needle insertion location when the electroencephalogram of the injection subject predicts a neural response, and to perform corresponding injection control based on the needle insertion location matching result.

2. The injection control system based on brain planar mapping as described in claim 1, characterized in that, The specific details of the injection pre-adjustment based on the predicted needle insertion location are as follows: The corresponding injection pre-adjustment data is obtained from a preset database by acquiring the predicted needle insertion position. The injection pre-adjustment data includes the pre-adjustment injection position, pre-adjustment injection depth, and pre-adjustment injection dose. The injection data of the injection needle is pre-adjusted according to the pre-adjustment ratio obtained from the preset database. The injection data includes the injection location, injection depth, and injection dose.

3. The injection control system based on brain planar mapping as described in claim 1, characterized in that, The specific steps for adjusting the injection based on the needle insertion location matching result are as follows: If the needle insertion position matching result is successful, then injection pre-adjustment is performed, and the injection needle is adjusted according to the injection pre-adjustment data. Construct a pre-adjusted ratio mapping set of the number of successful matches and the ratio adjustment rate, and input the real-time accumulated number of successful matches into the pre-adjusted ratio mapping set to obtain the ratio adjustment rate; The optimized pre-adjustment ratio is obtained by performing a ratio adjustment calculation on the pre-adjustment ratio based on the ratio adjustment rate. If the optimized pre-adjustment ratio is not less than the preset ratio limit, the ratio adjustment calculation will not be performed again. If the needle insertion location matching result is a failure, emergency injection adjustment will be performed.

4. The injection control system based on brain planar mapping as described in claim 3, characterized in that, The specific procedure for emergency injection control is as follows: Based on the actual needle insertion position, the corresponding injection adjustment data is obtained from the preset database. The injection data is then compensated according to the injection adjustment data to obtain the target injection data. The injection adjustment force coefficient is obtained by combining the obtained real-time injection data. The compensation calculation is used to supplement and delay the injection data to obtain the target injection data. The real-time injection adjustment force coefficient is input into the adjustment force mapping set to obtain the actual adjustment ratio. The adjustment force mapping set represents the set of mapping relationships between the injection adjustment force coefficient and the actual adjustment ratio. The injection data of the injection needle is adjusted according to the actual adjustment ratio, and the mapping frequency is adjusted at the same time.

5. The injection control system based on brain planar mapping as described in claim 4, characterized in that, The specific process of adjusting the injection data of the injection needle is as follows: When the needle insertion position matching result is successful, adjust the injection needle and adjust the default adjustment speed of the injection position according to the preset ratio; otherwise, adjust the default adjustment speed of the injection position according to the actual adjustment ratio. Real-time acquisition of location control completion time; mapping of location control completion time to obtain depth control influencing factors. The injection depth is adjusted based on the depth regulation influencing factor to obtain the optimized depth regulation speed by performing depth regulation calculation on the default adjustment speed. The injection depth is then adjusted based on the optimized depth regulation speed, and the depth adjustment completion time is obtained in real time. The dose regulation influencing factor is obtained by adjusting the time mapping based on the depth. The dose regulation influencing factor is used to perform dose regulation calculation on the default adjustment speed of the injection dose to obtain the optimized dose regulation speed. The injection dose is then regulated based on the optimized dose regulation speed.

6. The injection control system based on brain planar mapping as described in claim 4, characterized in that, The specific method for obtaining the injection adjustment force coefficient is as follows: Acquire real-time injection data and target injection data. The real-time injection data includes real-time injection location, real-time injection depth, and real-time injection dose. The target injection data includes target injection location, target injection depth, and target injection dose. The injection force adjustment weights are obtained from a preset database, and the injection force adjustment weights include position force weights, depth force weights, and dose force weights. The injection control deviation value is obtained by calculating the control deviation between the real-time injection data and the corresponding target injection data. The injection control deviation value is coupled with the corresponding injection force adjustment weight after weighting calculation to obtain the injection control force coefficient.

7. The injection control system based on brain planar mapping as described in claim 4, characterized in that, The specific process of the mapping frequency control is as follows: Prediction deviation analysis is performed using actual injection data and pre-injection data to obtain a prediction reliability coefficient. The prediction deviation analysis is used to comprehensively quantify the reliability of the predicted needle insertion position. The predicted confidence coefficient is input into the confidence mapping set to obtain the planar graph mapping frequency multiple, wherein the confidence mapping set represents the set of mapping relationships between the planar graph mapping frequency multiple and the predicted confidence coefficient; The optimized mapping frequency is obtained by performing a frequency adjustment operation on the planar mapping frequency based on the planar mapping frequency multiple. The frequency adjustment operation is used to optimize the planar mapping frequency by using the planar mapping frequency multiple. Brain planar mapping is performed based on optimized mapping frequency.

8. The injection control system based on brain planar mapping as described in claim 7, characterized in that, The specific method for obtaining the prediction confidence coefficient is as follows: Acquire injection calibration data, which includes calibration injection location, calibration injection depth, and calibration injection dose; The prediction confidence weights are obtained from a preset database, and the prediction confidence weights include location confidence weights, depth confidence weights, and dose confidence weights. The degree of injection prediction deviation is obtained by performing a prediction deviation calculation on the actual injection data and the pre-injection data. The prediction deviation calculation is used to quantify the degree of difference between the actual injection data and the pre-injection data. The prediction confidence coefficient is obtained by coupling the prediction deviation value and the corresponding prediction confidence weight through weighting operations.

9. A device that applies the brain-plane mapping-based injection control system as described in any one of claims 1-8, characterized in that, Includes the syringe body, processor, camera, sensors, and touchscreen; The camera is used to capture images of the brain surface of the injection recipient in real time. The sensor is used to monitor the needle insertion point and injection depth of the injection needle in real time. The processor is used to receive and process data from the camera and sensors, and to control the injection needle based on the processing results. The touchscreen is used to display injection data from the injection needle in real time or to input control information for adjusting the injection data.

10. An injection modulation method based on brain planar mapping, characterized in that, Includes the following steps: The needle insertion position of the injection needle is obtained by deploying a needle insertion position detection tool. The needle insertion position includes a predicted needle insertion position and an actual needle insertion position. The predicted needle insertion position is obtained by inputting the neural response signal of the predicted injection object obtained by electroencephalography into a pre-trained model. The actual needle insertion position is obtained by mapping through a high-resolution brain plane projection system. Injection pre-adjustment is performed based on the predicted needle insertion location, and the electroencephalogram of the injection subject is acquired in real time; When the electroencephalogram (EEG) of the injection recipient predicts a neural response, the predicted needle insertion location is matched with the actual needle insertion location to obtain a needle insertion location matching result, and corresponding injection control is performed based on the needle insertion location matching result.

Images