Catheter system and method for neurosurgical operation intervention

Abstract

The invention relates to the technical field of surgical intervention, in particular to a catheter system and method for neurosurgery surgical intervention, in the invention, through accurate path prediction, real-time monitoring and dynamic adjustment, the accuracy of catheter operation is remarkably improved, and through analysis of historical surgical data, information such as path, speed and angle in the surgical process is accurately extracted, so that the accuracy of catheter operation is improved. A more accurate neural structure position can be provided by timely adjusting the movement direction of the catheter, spatial positioning and form calculation, the spatial deviation between the current position of the catheter and a target neural structure is calculated in real time through a support vector machine algorithm, a path is adjusted according to a set threshold value, historical operation data is learned through a convolutional neural network, and the operation accuracy is improved. The catheter operation strategy is optimized, operation data and deviation are analyzed in real time, the operation precision is automatically adjusted, catheter operation in the operation process is more accurate, patient wounds are smaller, the recovery time is shorter, the treatment effect is better, and the recovery speed of patients is increased.

Description

Technical Field

[0001] The present invention relates to the technical field of surgical intervention, and particularly to a catheter system and method for neurosurgical intervention. Background Art

[0002] The technical field of surgical intervention aims to perform treatment in the least invasive way by using precise instruments and equipment, reducing the trauma, bleeding and complications suffered by patients during the treatment process, shortening the recovery time, reducing the surgical risk, and improving the treatment effect.

[0003] The catheter system for neurosurgical intervention, through precise pipeline design and operation methods, helps doctors to accurately position, deliver drugs and perform minimally invasive treatment through the catheter when performing nerve tube-related surgeries. The purpose is to improve the patient's nerve function through interventional surgery, reduce the damage to nerve tissues, achieve the treatment effect, and promote the patient's recovery.

[0004] The existing technologies have limitations in the accuracy of the path and the flexibility of the operation. The path error cannot be effectively corrected in a short time, resulting in high uncertainty during the surgical process. Moreover, the existing technologies cannot make full use of historical data and real-time feedback for dynamic optimization of the path, resulting in the inability to improve the accuracy of catheter operation, and the path correction is also relatively lagging, making it difficult to perform real-time fine adjustment of the catheter during the surgery, causing unnecessary risks that may occur during the treatment process. Summary of the Invention

[0005] The purpose of the present invention is to solve the disadvantages existing in the prior art, and to propose a catheter system and method for neurosurgical intervention.

[0006] To achieve the above purpose, the present invention adopts the following technical solution: A catheter system for neurosurgical intervention, historical surgical data and surgical operation data sets, the system includes:

[0007] Catheter operation path generation module: According to historical surgical data, analyze and extract operation path, speed, angle and inclination data, analyze the trend changes in the data, calculate the path errors at the starting point, ending point and each intermediate stage of the path, perform path prediction and update, and generate the optimized result of the catheter path;

[0008] Real-time monitoring module for catheter motion state: According to the real-time catheter position, angle, speed and inclination data, by comparing with the optimized result of the catheter path, judge the deviation between the current catheter position and the optimized path, calculate the adjustment parameters required for correction, and readjust the catheter motion parameters to generate a catheter deviation adjustment signal;

[0009] Neural Structure Localization Module: According to the CT and MRI image data of the patient, perform image segmentation and calibration, calculate the position of the neural structure, compare it with the anatomical markers in the image, extract key anatomical structure information, perform spatial localization and morphological calculation, and generate neural structure position information;

[0010] Catheter Path Dynamic Adjustment Module: According to the neural structure position information, use support vector machine to calculate the spatial deviation between the current position of the catheter and the target neural structure, judge whether the deviation exceeds the set threshold, adjust the direction, speed and angle of the catheter path when it exceeds, perform path correction operations, and correct the catheter movement path through the catheter deviation adjustment signal, and generate path adjustment instructions;

[0011] Catheter Operation Strategy Learning Module: Through the surgical operation data set, use convolutional neural network to obtain historical surgical data and catheter path optimization results, record catheter operation data and deviation in real time, combine the catheter deviation adjustment signal and path adjustment instructions, calculate the operation accuracy and deviation during the training process, analyze the deviation and optimization space in the operation, and adjust and generate operation strategy optimization data;

[0012] Catheter Operation Optimization Application Module: Based on the operation strategy optimization data, analyze and calculate the adaptation adjustment plan between the catheter operation path and the target neural structure, evaluate the operation accuracy after adjustment, and adjust the catheter movement in the actual surgical operation according to the catheter path optimization result, path adjustment instruction and catheter deviation adjustment signal, and generate a catheter operation execution plan.

[0013] As a further solution of the present invention, the catheter operation path generation module includes:

[0014] Path Data Extraction Sub-module: Based on historical surgical data, analyze and extract the operation path, speed, angle and inclination data of the catheter during the operation, and obtain the operation path data by cleaning irrelevant data and excluding abnormal points;

[0015] Trend Analysis Sub-module: Based on the operation path data, calculate the change trend of the path, identify the path errors at the starting point, ending point and intermediate stage, analyze the data trend, obtain the laws of path deviation and error, and generate path trend analysis results;

[0016] Path Optimization Result Generation Sub-module: Based on the path trend analysis results, adjust the path error, combine the successful paths of similar surgeries in historical data, update and predict future paths, generate a corrected path plan, and output the catheter path optimization result.

[0017] As a further solution of the present invention, the catheter movement state real-time monitoring module includes:

[0018] Position and Parameter Comparison Sub-module: According to the real-time catheter position, angle, speed, and inclination data, compare them one by one with the catheter path optimization result, identify the deviation between the current catheter position and the target path, record the error range, and generate a path deviation comparison result;

[0019] Deviation Calculation Sub-module: Based on the path deviation comparison result, calculate the catheter angle, speed, and position parameters that need to be adjusted, and calculate the deviation correction amount through historical data and standard correction methods to obtain deviation correction parameters;

[0020] Motion Parameter Adjustment Sub-module: Based on the deviation correction parameters, readjust the motion path of the catheter, modify the motion speed, angle, and inclination of the catheter, and perform dynamic correction on the catheter when necessary to generate a catheter deviation adjustment signal.

[0021] As a further solution of the present invention, the nerve structure positioning module includes:

[0022] Image Segmentation Sub-module: Based on the CT and MRI image data of the patient, extract the nerve tissue area in the image through threshold segmentation method, use edge detection algorithm to accurately locate the image edge, remove irrelevant areas and focus on the nerve structure, and generate a nerve structure segmentation map;

[0023] Structure Comparison Sub-module: Based on the nerve structure segmentation map, compare the position with the anatomical markers in the CT and MRI images, identify the position and morphological characteristics of each key nerve structure, extract the key anatomical information of areas such as the brain and spinal cord, and obtain the key anatomical structure information;

[0024] Positioning Calculation Sub-module: Based on the key anatomical structure information, perform coordinate transformation and morphological calculation in three-dimensional space, calibrate the spatial position of the nerve structure, calculate the positioning relationship of the nerve tissue relative to other structures, and generate nerve structure position information.

[0025] As a further solution of the present invention, the catheter path dynamic adjustment module includes:

[0026] Path Deviation Calculation Sub-module: Based on the nerve structure position information, use a support vector machine to calculate the spatial deviation between the current position of the catheter and the target nerve structure, judge whether the deviation exceeds the preset threshold by comparing the difference between the current direction, angle, and position of the catheter and the target position, and generate a path deviation calculation result;

[0027] Path Adjustment Sub-module: Based on the path deviation calculation result, when the deviation exceeds the set threshold, adjust the path of the catheter, modify the direction, speed, and angle of the catheter respectively, and execute the path correction operation through the real-time control system to generate a path adjustment plan;

[0028] Adjustment signal generation sub-module: Based on the path adjustment scheme, generate a correction signal to correct the catheter movement trajectory, and transmit the deviation adjustment signal in real time to drive the catheter system to make corresponding adjustments, and finally generate a path adjustment instruction.

[0029] As a further solution of the present invention, the support vector machine is calculated according to the following formula, and the specific formula is as follows:

[0030]

[0031] Where: x 1 is the x coordinate of the current position of the catheter, y 1 is the y coordinate of the current position of the catheter, z 1 is the z coordinate of the current position of the catheter, x 2 is the x coordinate of the target nerve structure, y 2 is the y coordinate of the target nerve structure, z 2 is the z coordinate of the target nerve structure, w 1 is the weight coefficient related to the catheter angle deviation, w 2 is the weight coefficient related to the catheter pitch angle deviation, w 3 is the weight coefficient related to the catheter roll angle deviation, θ x is the component of the direction angle deviation between the catheter and the target nerve structure in the x-axis direction, θ y is the component of the direction angle deviation between the catheter and the target nerve structure in the y-axis direction, θ z is the component of the direction angle deviation between the catheter and the target nerve structure in the z-axis direction.

[0032] As a further solution of the present invention, the catheter operation strategy learning module includes:

[0033] Historical data collection sub-module: Through the surgical operation data set, use a convolutional neural network to record catheter operation data in real time, collect the catheter path optimization results in historical surgeries, organize and store relevant data, and generate an operation history data set;

[0034] Deviation analysis sub-module: Based on the operation history data set, analyze the path deviation and actual operation error that occur during the surgery, record the deviation type and frequency, evaluate the source of the operation error, and generate a deviation analysis result;

[0035] Strategy optimization sub-module: Based on the deviation analysis result, deeply analyze the deviation that occurs during the surgery, combine historical surgery data, adjust the catheter operation strategy, generate an optimized strategy with strong adaptability, and obtain operation strategy optimization data.

[0036] As a further solution of the present invention, the convolutional neural network is calculated according to the following formula, and the specific formula is as follows:

[0037]

[0038] Where: L is the loss value, y′ i is the actual label, p′ i is the probability value predicted by the model, n is the number of categories, w′ 1 is the weight coefficient related to the actual label, w′ 2 is the weight coefficient related to the angle deviation from the x-axis, w′ 3 is the weight coefficient related to the angle deviation from the y-axis, w′ 4 is the weight coefficient related to the angle deviation from the z-axis, θ′ x is the angle deviation of the catheter relative to the target nerve structure in the x-axis direction, θ′ y is the angle deviation of the catheter relative to the target nerve structure in the y-axis direction, θ′ z is the angle deviation of the catheter relative to the target nerve structure in the z-axis direction.

[0039] As a further solution of the present invention, the catheter operation optimization application module includes a path adjustment calculation sub-module, an accuracy evaluation sub-module, and an operation adjustment suggestion generation sub-module, where:

[0040] Path adjustment calculation sub-module: Based on the operation strategy optimization data, analyze the difference between the catheter operation path and the target, calculate the adapted adjustment path, and generate a corrected path plan by analyzing the current state and target of the catheter, and obtain the path adjustment plan:

[0041] Accuracy evaluation sub-module: Based on the path adjustment plan, evaluate the adjusted operation accuracy, calculate the movement accuracy of the catheter under the new path, and conduct a comparative analysis to obtain the adjusted operation accuracy:

[0042] Operation adjustment suggestion generation sub-module: Based on the adjusted operation accuracy, combine the path adjustment plan and the operation strategy optimization data, generate suggestions for catheter movement adjustment in actual surgical operations, and output the catheter operation execution plan.

[0043] In addition, the present invention also provides a catheter method for neurosurgical intervention, including the following steps:

[0044] Step 1: According to the historical surgical data, extract the operation path, speed, angle, and inclination data, conduct a data trend analysis, calculate the errors of each stage path, predict the starting point, ending point, and path changes in the intermediate stage of the path, update the path prediction result, and generate the path optimization result;

[0045] Step 2: Based on the position information of the real-time catheter, obtain the angle, speed, and inclination data of the catheter, compare them with the path optimization result, judge the deviation between the current position and the optimized path, calculate the required correction parameters, adjust the catheter movement parameters, and generate a catheter deviation adjustment signal;

[0046] Step 3: Based on the catheter deviation adjustment signal, obtain the CT and MRI image data of the patient, perform image segmentation and calibration, calculate the position of the nerve structure, compare it with the anatomical markers in the image, extract the key nerve structure information, perform spatial positioning and morphological calculation, and generate nerve structure position information;

[0047] Step 4: Based on the nerve structure position information, use the support vector machine to calculate the spatial deviation between the current position of the catheter and the target nerve structure, judge whether the deviation exceeds the set threshold. If it exceeds the set threshold, adjust the direction, speed, and angle of the catheter path, perform a path correction operation, and correct the catheter movement path through the catheter deviation adjustment signal to generate a path adjustment instruction;

[0048] Step 5: Based on the path adjustment instruction, use the convolutional neural network to analyze in combination with historical surgical data, record the catheter operation data and deviation in real time, calculate the operation accuracy and deviation, analyze the deviation and optimization space during the operation, adjust the operation strategy, and generate operation strategy optimization data;

[0049] Step 6: Based on the operation strategy optimization data, calculate the adaptation adjustment plan between the catheter operation path and the target, evaluate the adjusted operation accuracy, and adjust the catheter movement in the actual surgery to generate a catheter operation execution plan

[0050] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0051] 1. In the present invention, through precise path prediction, real-time monitoring, and dynamic adjustment, the accuracy of catheter operation is significantly improved. By analyzing historical surgical data, information such as path, speed, and angle during the surgical process is accurately extracted, and the movement direction of the catheter is adjusted in a timely manner, which can effectively reduce path errors. Spatial positioning and morphological calculation can provide a more accurate nerve structure position, improving the reliability of the operation and the effectiveness of treatment;

[0052] 2. In the present invention, through the support vector machine algorithm, the spatial deviation between the current position of the catheter and the target nerve structure is calculated in real time, and the path is adjusted according to the set threshold, enabling the catheter to accurately navigate in complex nerve structures and avoiding nerve damage caused by path deviation;

[0053] 3. In the present invention, by learning historical surgical data through a convolutional neural network, the catheter operation strategy is optimized, and the operation data and deviations are analyzed in real time to automatically adjust the operation accuracy, making the catheter operation during the surgery more precise, causing less trauma to the patient, shortening the recovery time, achieving better treatment effects, and improving the patient's recovery speed. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 is the system flow chart of the present invention;

[0055] Figure 2 is the schematic diagram of the system framework of the present invention;

[0056] Figure 3 is the schematic diagram of the method steps of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0057] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0058] Please refer to Figure 1 , the present invention provides a technical solution: a catheter system for neurosurgical intervention, a historical surgical data and a surgical operation data set, and the system includes:

[0059] Catheter operation path generation module: According to historical surgical data, analyze and extract operation path, speed, angle and inclination data, analyze the trend changes in the data, calculate the path errors at the starting point, ending point and each intermediate stage of the path, perform path prediction and update, and generate an optimized result of the catheter path;

[0060] Catheter motion state real-time monitoring module: According to the real-time catheter position, angle, speed and inclination data, by comparing with the optimized result of the catheter path, judge the deviation between the current catheter position and the optimized path, calculate the adjustment parameters required for correction, and readjust the catheter motion parameters to generate a catheter deviation adjustment signal;

[0061] Neural structure positioning module: According to the CT and MRI image data of the patient, perform image segmentation and calibration, calculate the position of the neural structure, compare it with the anatomical markers in the image, extract key anatomical structure information, perform spatial positioning and morphological calculation, and generate neural structure position information;

[0062] Catheter path dynamic adjustment module: According to the nerve structure position information, using a support vector machine, calculate the spatial deviation between the current position of the catheter and the target nerve structure, determine whether the deviation exceeds the set threshold. When it exceeds, adjust the direction, speed and angle of the catheter path, perform a path correction operation, and correct the catheter movement path through the catheter deviation adjustment signal to generate a path adjustment instruction;

[0063] Catheter operation strategy learning module: Through the surgical operation data set, using a convolutional neural network, obtain historical surgical data and catheter path optimization results, record catheter operation data and deviations in real time, combine the catheter deviation adjustment signal and the path adjustment instruction, calculate the operation accuracy and deviation during the training process, analyze the deviations and optimization spaces that occur during the operation, and adjust and generate operation strategy optimization data;

[0064] Catheter operation optimization application module: Based on the operation strategy optimization data, analyze and calculate the adaptation adjustment plan between the catheter operation path and the target nerve structure, evaluate the operation accuracy after adjustment, and adjust the catheter movement in the actual surgical operation according to the catheter path optimization result, the path adjustment instruction and the catheter deviation adjustment signal to generate a catheter operation execution plan.

[0065] As a further solution of the present invention, the catheter operation path generation module includes:

[0066] Path data extraction sub-module: Based on historical surgical data, analyze and extract the operation path, speed, angle and inclination data of the catheter during the surgical process, and obtain the operation path data by cleaning irrelevant data and excluding abnormal points;

[0067] Trend analysis sub-module: Based on the operation path data, calculate the change trend of the path, identify the path errors at the starting point, end point and intermediate stage, analyze the data trend, obtain the rules of path deviation and error, and generate a path trend analysis result;

[0068] Path optimization result generation sub-module: Based on the path trend analysis result, by adjusting the path error, combining with the successful paths of similar surgeries in historical data, update and predict the future path, generate a corrected path plan, and output the catheter path optimization result.

[0069] As a further solution of the present invention, the catheter motion state real-time monitoring module includes:

[0070] Position and parameter comparison sub-module: According to the real-time catheter position, angle, speed and inclination data, compare them one by one with the catheter path optimization result, identify the deviation between the current catheter position and the target path, record the error range, and generate a path deviation comparison result;

[0071] Deviation calculation submodule: based on the path deviation comparison result, calculate the catheter angle, speed and position parameters that need to be adjusted, and calculate the deviation correction amount through historical data and standard correction method to obtain the deviation correction parameter;

[0072] Motion parameter adjustment submodule: based on the deviation correction parameter, readjust the motion path of the catheter, modify the movement speed, angle and inclination of the catheter, and dynamically correct the catheter when necessary to generate a catheter deviation adjustment signal.

[0073] See also Figure 2 , the catheter operation path generation module includes:

[0074] Path data extraction submodule: Based on historical surgical data, analyze and extract the operation path, speed, angle and inclination data of the catheter during the operation, and obtain the operation path data by cleaning irrelevant data and excluding abnormal points;

[0075] Trend analysis submodule: based on the operation path data, calculate the change trend of the path, identify the path errors at the starting point, the end point and the intermediate stage, analyze the data trend, derive the rules of path deviation and error, and generate path trend analysis results;

[0076] Path optimization result generation submodule: Based on the path trend analysis result, by adjusting the path error and combining the successful paths of similar surgeries in historical data, the future path is updated and predicted, a revised path plan is generated, and the catheter path optimization result is output;

[0077] Path data extraction submodule: Based on historical surgical data, the position-based Kalman filter algorithm is used to smooth the operation path of the catheter. The speed, angle and inclination data of the path are calculated using the polynomial fitting method. By setting the size of the sliding window to 5, the path data at each moment is smoothed and outliers are removed. The outliers are judged by the threshold setting method based on the standard deviation. Specifically, when the standard deviation of the path data exceeds the set threshold of 1.5, it is marked as an outlier and removed. After data cleaning, the valid path data is retained to generate the operation path data;

[0078] Trend analysis submodule: Based on the operation path data, the least square method is used to fit and analyze the change trend of the path data. The fitting threshold is set to 0.95, and the path errors of the starting point, end point and intermediate stage are identified. The SMA algorithm is used to calculate the path error in each time period. The error calculation method is the difference between the actual value and the fitting value of the path point, and then the trend change of the path is analyzed to obtain the path deviation law. The specific operation is to calculate the trend of each path segment through the recursive averaging method and identify the error law to generate the path trend analysis result;

[0079] Path optimization result generation sub-module: Based on the path trend analysis results, the Bayesian optimization algorithm is used to adjust the path error. Specifically, by defining an error function, appropriate historical data samples are selected to perform similar path matching using the K-nearest neighbor algorithm. The step size is set to 0.1, and the parameters are the path point position and deviation. Combining the successful paths of similar surgeries in the historical data, the particle swarm optimization algorithm is used to predict the future path. The specific operation is to select the optimal position of the individual in the particle swarm during path optimization, and adjust and update the path through a local search strategy to generate a corrected path plan and output the catheter path optimization result.

[0080] Please refer to Figure 2 , the real-time monitoring module of catheter motion state includes:

[0081] Position and parameter comparison sub-module: According to the real-time catheter position, angle, speed, and inclination data, compare them one by one with the catheter path optimization result, identify the deviation between the current catheter position and the target path, record the error range, and generate the path deviation comparison result;

[0082] Deviation calculation sub-module: Based on the path deviation comparison result, calculate the required adjusted catheter angle, speed, and position parameters, and calculate the deviation correction amount through historical data and standard correction methods to obtain the deviation correction parameters;

[0083] Motion parameter adjustment sub-module: Based on the deviation correction parameters, readjust the motion path of the catheter, modify the motion speed, angle, and inclination of the catheter, and perform dynamic correction on the catheter when necessary to generate a catheter deviation adjustment signal;

[0084] Position and parameter comparison sub-module: Based on the real-time catheter position, angle, speed, and inclination data, use the dynamic time warping algorithm to compare the catheter path optimization result one by one. The specific operation is to set the time window size to 10, calculate the difference between the actual position and the target path point at each moment, calculate the position deviation using the Euclidean distance formula, and comprehensively calculate the deviations of the angle, speed, and inclination through a weighted error function. The weight values are 0.3, 0.4, and 0.3 respectively, identify the deviation between the current catheter position and the target path, record the error range, and generate the path deviation comparison result;

[0085] Deviation calculation sub-module: Based on the path deviation comparison result, use the least squares method to calculate the required adjusted catheter angle, speed, and position parameters. The specific operation is to establish an error function, define the adjustment amount as the product of the error and the weight, calculate the deviation correction amount of the historical data through the mean square error minimization algorithm, set the step size to 0.05, obtain the deviation correction amount of each parameter, and obtain the deviation correction parameters;

[0086] Motion parameter adjustment sub-module: Based on the deviation correction parameter, the gradient descent method is used to re-adjust the motion path of the catheter. The specific operation is to calculate the correction gradient through the path position, angle, speed, and inclination at each time point, set the learning rate to 0.1, modify the motion speed, angle, and inclination of the catheter. During the correction process, the Kalman filter is used to make real-time adjustments to the dynamic changes during the catheter movement, and dynamic correction of the catheter is performed when necessary to generate a catheter deviation adjustment signal.

[0087] Please refer to Figure 2 , the nerve structure localization module includes:

[0088] Image segmentation sub-module: Based on the patient's CT and MRI image data, the nerve tissue area in the image is extracted by the threshold segmentation method, and the edge detection algorithm is used to accurately locate the image edge, remove the irrelevant area and focus on the nerve structure to generate a nerve structure segmentation map;

[0089] Structure comparison sub-module: Based on the nerve structure segmentation map, the position comparison is made with the anatomical markers in the CT and MRI images to identify the positions and morphological characteristics of each key nerve structure, extract the key anatomical information of areas such as the brain and spinal cord, and obtain the key anatomical structure information;

[0090] Positioning calculation sub-module: Based on the key anatomical structure information, coordinate transformation and morphological calculation in the three-dimensional space are performed to calibrate the spatial position of the nerve structure, calculate the positioning relationship of the nerve tissue relative to other structures, and generate the nerve structure position information;

[0091] Image segmentation sub-module: Based on the patient's CT and MRI image data, the Otsu threshold segmentation algorithm is used to extract the nerve tissue area in the image. The specific operation is to set the threshold segmentation method, automatically calculate the global threshold according to the image gray value, use the Sobel edge detection algorithm to accurately locate the image edge, set the convolution kernel size to 3x3 during the edge detection process, calculate the gradient value of the image, and remove the irrelevant area and focus on the nerve structure through threshold control to generate a nerve structure segmentation map;

[0092] Structure comparison sub-module: Based on the nerve structure segmentation map, the mutual information method is used to make a position comparison with the anatomical markers in the CT and MRI images. The specific operation is to calculate the similarity between the segmentation map and the marker map through the mutual information algorithm, set the window size to 7x7, identify the positions and morphological characteristics of each key nerve structure, extract the key anatomical information of areas such as the brain and spinal cord, and generate the key anatomical structure information;

[0093] Position calculation sub-module: Based on the key anatomical structure information, a rigid body transformation algorithm is used for coordinate transformation and morphology calculation in three-dimensional space. The specific operation is to calibrate the spatial position of the nerve structure by setting translation and rotation parameters, perform coordinate transformation using a homogeneous coordinate transformation matrix, calculate the positioning relationship of the nerve tissue relative to other structures, and generate nerve structure position information.

[0094] Please refer to Figure 2 , the catheter path dynamic adjustment module includes:

[0095] Path deviation calculation sub-module: Based on the nerve structure position information, a support vector machine is used to calculate the spatial deviation between the current position of the catheter and the target nerve structure. By comparing the differences in the direction, angle, and position of the current catheter with the target position, it is judged whether the deviation exceeds a preset threshold, and a path deviation calculation result is generated.

[0096] Path adjustment sub-module: Based on the path deviation calculation result, when the deviation exceeds the set threshold, the path of the catheter is adjusted. The direction, speed, and angle of the catheter are respectively modified, and the path correction operation is executed through a real-time control system to generate a path adjustment plan.

[0097] Adjustment signal generation sub-module: Based on the path adjustment plan, a correction signal is generated to correct the movement trajectory of the catheter, and the deviation adjustment signal is transmitted in real time to drive the catheter system to make corresponding adjustments, and finally a path adjustment instruction is generated.

[0098] Path deviation calculation sub-module: Based on the nerve structure position information, a support vector machine is used to calculate the spatial deviation between the current position of the catheter and the target nerve structure. The specific operation is to perform non-linear mapping by setting a radial basis function kernel, map the input data to a high-dimensional space, set the C parameter to 1, the gamma parameter to 0.5, and use the trained model to calculate the differences in the direction, angle, and position of the current catheter with the target position, judge whether the deviation exceeds a preset threshold, and generate a path deviation calculation result.

[0099] Path adjustment sub-module: Based on the path deviation calculation result, when the deviation exceeds the set threshold, the PID control algorithm is used to adjust the path of the catheter. The specific operation is to set the proportional coefficient Kp to 0.5, the integral coefficient Ki to 0.1, and the differential coefficient Kd to 0.05, respectively modify the direction, speed, and angle of the catheter, and execute the path correction operation through a real-time control system to generate a path adjustment plan.

[0100] Adjustment signal generation sub-module: Based on the path adjustment scheme, a correction signal is generated using the PWM signal generation algorithm. The specific operation is to correct the catheter movement trajectory by setting the frequency to 50 Hz and adjusting the duty cycle to 30%, and to transmit the deviation adjustment signal in real time to drive the catheter system to make corresponding adjustments and generate a path adjustment instruction.

[0101] Please refer to Figure 2 , the support vector machine is calculated according to the following formula, and the specific formula is as follows:

[0102]

[0103] where: x 1 is the x coordinate of the current position of the catheter, y 1 is the y coordinate of the current position of the catheter, z 1 is the z coordinate of the current position of the catheter, x 2 is the x coordinate of the target nerve structure, y 2 is the y coordinate of the target nerve structure, z 2 is the z coordinate of the target nerve structure, w 1 is the weight coefficient related to the angular deviation of the catheter, w 2 is the weight coefficient related to the pitch angle deviation of the catheter, w 3 is the weight coefficient related to the roll angle deviation of the catheter, θ x is the component of the direction angle deviation between the catheter and the target nerve structure in the x-axis direction, θ y is the component of the direction angle deviation between the catheter and the target nerve structure in the y-axis direction, θ z is the component of the direction angle deviation between the catheter and the target nerve structure in the z-axis direction;

[0104] Execution process: First, calculate the Euclidean distance between the catheter and the target through the spatial coordinates (x 1 , y 1 , z 1 and x 2 , y 2 , z 2 ) of the current position of the catheter and the target nerve structure, denoted as d, which reflects the position deviation of the catheter relative to the target nerve structure at present. Then, in order to improve the accuracy, considering the angular deviation of the catheter in different directions, calculate the components (θ x , θ y , θ z ) of the angular deviation of the catheter relative to the target structure in the x, y, and z-axis directions respectively. By introducing the corresponding weight coefficients (w 1 , w 2 , w 3) Weighting is performed, and the weight coefficient reflects the influence degree of the angular error in each direction on the total deviation. The weight coefficient can be obtained from experimental data to ensure more accurate calculation of the spatial deviation. Finally, by combining the spatial distance and the weighted angular deviation, an improved deviation value is obtained, providing more accurate spatial deviation information between the catheter and the target nerve structure to help accurately adjust the position of the catheter during the operation.

[0105] Please refer to Figure 2 , the catheter operation strategy learning module includes:

[0106] Historical data collection sub-module: Through the surgical operation data set, using a convolutional neural network, it records catheter operation data in real time, collects the catheter path optimization results in historical surgeries, organizes and stores relevant data, and generates an operation history data set;

[0107] Deviation analysis sub-module: Based on the operation history data set, it analyzes the path deviation and actual operation error that occur during the operation, records the deviation type and frequency, evaluates the source of the operation error, and generates a deviation analysis result;

[0108] Strategy optimization sub-module: Based on the deviation analysis result, it deeply analyzes the deviation that occurs during the operation, combines historical surgical data, adjusts the catheter operation strategy, generates a highly adaptable optimization strategy, and obtains operation strategy optimization data;

[0109] Historical data collection sub-module: Through the surgical operation data set, it uses a convolutional neural network to record catheter operation data in real time. The specific operation is to use a convolutional layer for feature extraction, set the convolutional kernel size to 3x3, the stride to 1, perform a convolutional operation on the input data, and perform dimensionality reduction through a pooling layer. Use the ReLU activation function to perform a non-linear transformation on the convolutional output, collect the catheter path optimization results in historical surgeries, organize and store relevant data, and generate an operation history data set;

[0110] Deviation analysis sub-module: Based on the operation history data set, it uses a clustering analysis algorithm to analyze the path deviation and actual operation error that occur during the operation. The specific operation is to use the K-means clustering algorithm to group the historical data, set the number of clusters to 3, calculate the Euclidean distance between each data point and its cluster center, record the deviation type and frequency, evaluate the source of the operation error, and generate a deviation analysis result;

[0111] Strategy Optimization Sub-module: Based on the deviation analysis results, the deep reinforcement learning algorithm is used to deeply analyze the deviations occurring during the surgical process. The specific operation is to evaluate the values of each state and action through the Q-learning algorithm, set the learning rate to 0.1 and the discount factor to 0.9, adjust the catheter operation strategy using historical surgical data, generate an optimized strategy with strong adaptability, and obtain the optimized data for the operation strategy.

[0112] Please refer to Figure 2 , the convolutional neural network, according to the formula:

[0113]

[0114] where: L is the loss value, y′ i is the actual label, p′ i is the probability value predicted by the model, n is the number of categories, w′ 1 is the weight coefficient related to the actual label, w′ 2 is the weight coefficient related to the angle deviation along the x-axis, w′ 3 is the weight coefficient related to the angle deviation along the y-axis, w′ 4 is the weight coefficient related to the angle deviation along the z-axis, θ′ x is the angle deviation of the catheter relative to the target nerve structure in the x-axis direction, θ′ y is the angle deviation of the catheter relative to the target nerve structure in the y-axis direction, θ′ z is the angle deviation of the catheter relative to the target nerve structure in the z-axis direction;

[0115] Execution Process: First, the surgical operation dataset is processed to evaluate the matching degree between the catheter path and the target nerve structure. The model calculates the difference between the actual label (y′ i ) and the predicted probability (p i ) of each catheter path, and uses the cross-entropy loss function to evaluate the effect of path optimization. Then, the weight coefficients (w′ 2 , w′ 3 , w′ 4 ) related to the angle deviations in different directions are introduced into the formula to measure the influence degree of the angle deviations of the catheter in different axial directions on the total path deviation. The role of the weight coefficients is to adjust the contribution of the deviations in each direction to the optimization process, which can be obtained through training with the historical surgical dataset to ensure the accuracy of optimization. Finally, by calculating the loss value (L), the optimization result is formed, providing a reference for the subsequent catheter path adjustment, helping to precisely control the catheter position during the surgery and optimize the surgical effect.

[0116] Please refer to Figure 2 , the catheter operation optimization application module includes:

[0117] Path adjustment calculation sub-module: Optimize data based on the operation strategy, analyze the difference between the catheter operation path and the target, calculate the adapted adjustment path, and generate a corrected path plan by analyzing the current state and target of the catheter, obtaining a path adjustment plan:

[0118] Precision evaluation sub-module: Based on the path adjustment plan, evaluate the adjusted operation precision, calculate the movement precision of the catheter under the new path, and conduct comparative analysis to obtain the adjusted operation precision:

[0119] Operation adjustment suggestion generation sub-module: Based on the adjusted operation precision, combine the path adjustment plan and the operation strategy optimization data, generate suggestions for catheter movement adjustment in actual surgical operations, and output the catheter operation execution plan;

[0120] Path adjustment calculation sub-module: Optimize data based on the operation strategy, use the genetic algorithm to analyze the difference between the catheter operation path and the target. The specific operation is to set the initial population to 100, the crossover probability to 0.8, the mutation probability to 0.05, calculate the error between the current catheter position and the target path, evaluate the path by selecting the fitness function, generate the best adjustment path, and generate a corrected path plan by analyzing the current state and target of the catheter, obtaining a path adjustment plan;

[0121] Precision evaluation sub-module: Based on the path adjustment plan, use the mean square error to calculate the movement precision of the catheter under the new path. The specific operation is to calculate the difference between the actual position and the target position of each path point, set the number of path points to 500, calculate the sum of the squares of all errors and take the average to generate the adjusted operation precision;

[0122] Operation adjustment suggestion generation sub-module: Based on the adjusted operation precision, combine the path adjustment plan and the operation strategy optimization data, use the decision tree algorithm to generate suggestions for catheter movement adjustment in actual surgical operations. The specific operation is to use the C4.5 algorithm to construct a decision tree, set the minimum sample split number to 20, calculate the conditions and results of each adjustment suggestion, and output the catheter operation execution plan.

[0123] Please refer to Figure 3 , a catheter method for neurosurgical intervention. The catheter method for neurosurgical intervention is executed based on the above-mentioned catheter system for neurosurgical intervention, including the following steps:

[0124] Step 1: According to historical surgical data, extract data on operation path, speed, angle, and inclination, conduct data trend analysis, calculate the error of each stage path, predict the path changes at the starting point, ending point, and intermediate stages of the path, update the path prediction result, and generate a path optimization result;

[0125] Step 2: Based on the real-time position information of the catheter, obtain the angle, speed, and inclination data of the catheter, compare them with the path optimization result, judge the deviation between the current position and the optimized path, calculate the required correction parameters, adjust the catheter movement parameters, and generate a catheter deviation adjustment signal;

[0126] Step 3: Based on the catheter deviation adjustment signal, obtain the CT and MRI image data of the patient, perform image segmentation and calibration, calculate the position of the nerve structure, compare it with the anatomical markers in the image, extract the key nerve structure information, perform spatial positioning and morphological calculation, and generate nerve structure position information;

[0127] Step 4: Based on the nerve structure position information, use a support vector machine to calculate the spatial deviation between the current position of the catheter and the target nerve structure, judge whether the deviation exceeds the set threshold. If it exceeds the set threshold, adjust the direction, speed, and angle of the catheter path, perform a path correction operation, and correct the catheter movement path through the catheter deviation adjustment signal to generate a path adjustment instruction;

[0128] Step 5: Based on the path adjustment instruction, use a convolutional neural network to analyze in combination with historical surgical data, record the catheter operation data and deviation in real time, calculate the operation accuracy and deviation, analyze the deviation and optimization space during the operation, adjust the operation strategy, and generate operation strategy optimization data;

[0129] Step 6: Based on the operation strategy optimization data, calculate the adaptation adjustment plan between the catheter operation path and the target, evaluate the adjusted operation accuracy, and adjust the catheter movement in the actual surgery to generate a catheter operation execution plan.

[0130] The historical surgical data and the surgical operation data set are obtained from the database of the hospital information system.

[0131] The above are only the preferred embodiments of the present invention, and the present invention is not limited to other forms. Any person skilled in the art may use the disclosed technical content to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as it does not depart from the technical content of the technical solution of the present invention, any simple modification, equivalent change, and modification made to the above embodiments based on the technical essence of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. A catheter system for neurosurgery intervention, historical surgical data and surgical operation data set, characterized in that: The system comprises: Catheter operation path generation module: Based on historical surgical data, analyze and extract operation path, speed, angle and inclination data, analyze trend changes in the data, calculate the path errors at the starting point, end point and intermediate stages of the path, predict and update the path, and generate catheter path optimization results; Catheter motion state real-time monitoring module: based on the real-time catheter position, angle, speed and inclination data, by comparing with the catheter path optimization result, determine the deviation between the current catheter position and the optimized path, calculate the adjustment parameters required for correction, and readjust the catheter motion parameters to generate a catheter deviation adjustment signal; Neural structure positioning module: Based on the patient's CT and MRI image data, image segmentation and calibration are performed to calculate the location of the neural structure, and the location is compared with the anatomical markers in the image to extract key anatomical structure information, perform spatial positioning and morphological calculation, and generate neural structure location information; Catheter path dynamic adjustment module: according to the neural structure position information, a support vector machine is used to calculate the spatial deviation between the current position of the catheter and the target neural structure, and whether the deviation exceeds the set threshold is determined. If the deviation exceeds the threshold, the direction, speed and angle of the catheter path are adjusted, and the path correction operation is performed. The catheter movement path is corrected through the catheter deviation adjustment signal, and a path adjustment instruction is generated; Catheter operation strategy learning module: through the surgical operation data set, using convolutional neural network, obtain historical surgical data and catheter path optimization results, record catheter operation data and deviations in real time, combine the catheter deviation adjustment signal and path adjustment instruction, calculate the operation accuracy and deviation during the training process, analyze the deviation and optimization space in the operation, adjust and generate operation strategy optimization data; Catheter operation optimization application module: Based on the operation strategy optimization data, analyze and calculate the adaptation adjustment plan between the catheter operation path and the target neural structure, evaluate the operation accuracy after adjustment, and adjust the catheter movement in the actual surgical operation according to the catheter path optimization results, path adjustment instructions and catheter deviation adjustment signals to generate a catheter operation execution plan.

2. The catheter system for neurosurgery intervention according to claim 1, characterized in that: The catheter operation path generation module includes: Path data extraction submodule: Based on historical surgical data, analyze and extract the operation path, speed, angle and inclination data of the catheter during the operation, and obtain the operation path data by cleaning irrelevant data and excluding abnormal points; Trend analysis submodule: based on the operation path data, calculate the change trend of the path, identify the path errors at the starting point, the end point and the intermediate stage, analyze the data trend, derive the rules of path deviation and error, and generate path trend analysis results; Path optimization result generation submodule: Based on the path trend analysis results, by adjusting the path error and combining the successful paths of similar surgeries in historical data, the future path is updated and predicted, a revised path plan is generated, and the catheter path optimization results are output.

3. The catheter system for neurosurgery intervention according to claim 1, characterized in that: The catheter movement state real-time monitoring module comprises: Position and parameter comparison submodule: compares the real-time catheter position, angle, speed and inclination data with the catheter path optimization results one by one, identifies the deviation between the current catheter position and the target path, records the error range, and generates path deviation comparison results; Deviation calculation submodule: based on the path deviation comparison result, calculate the catheter angle, speed and position parameters that need to be adjusted, and calculate the deviation correction amount through historical data and standard correction method to obtain the deviation correction parameter; Motion parameter adjustment submodule: based on the deviation correction parameter, readjust the motion path of the catheter, modify the movement speed, angle and inclination of the catheter, and dynamically correct the catheter when necessary to generate a catheter deviation adjustment signal.

4. The catheter system for neurosurgery intervention according to claim 1, characterized in that: The neural structure positioning module includes: Image segmentation submodule: Based on the patient's CT and MRI image data, the neural tissue area in the image is extracted through the threshold segmentation method, the edge detection algorithm is used to accurately locate the image edge, remove irrelevant areas and focus on the neural structure to generate a neural structure segmentation map; Structural comparison submodule: Based on the neural structure segmentation map, position comparison is performed with anatomical markers in CT and MRI images to identify the position and morphological characteristics of each key neural structure, extract key anatomical information of the brain, spinal cord and other regions, and obtain key anatomical structure information; Positioning calculation submodule: Based on the key anatomical structure information, coordinate transformation and morphological calculation are performed in three-dimensional space to calibrate the spatial position of the neural structure, calculate the positioning relationship of the neural tissue relative to other structures, and generate neural structure position information.

5. The catheter system for neurosurgery intervention according to claim 1, characterized in that: The catheter path dynamic adjustment module includes: Path deviation calculation submodule: Based on the neural structure position information, a support vector machine is used to calculate the spatial deviation between the current position of the catheter and the target neural structure, and by comparing the direction, angle and position of the current catheter with the target position, it is determined whether the deviation exceeds a preset threshold, and a path deviation calculation result is generated; Path adjustment submodule: based on the path deviation calculation result, when the deviation exceeds the set threshold, adjust the path of the catheter, modify the direction, speed and angle of the catheter respectively, perform the path correction operation through the real-time control system, and generate a path adjustment plan; Adjustment signal generation submodule: Based on the path adjustment scheme, a correction signal is generated to correct the movement trajectory of the catheter, and a deviation adjustment signal is transmitted in real time to drive the catheter system to make corresponding adjustments, and finally a path adjustment instruction is generated.

6. The catheter system for neurosurgery intervention according to claim 5, characterized in that: The support vector machine is calculated according to the following formula, and the specific formula is as follows: Where: x1 is the x-coordinate of the current position of the catheter, y1 is the y-coordinate of the current position of the catheter, z1 is the z-coordinate of the current position of the catheter, x2 is the x-coordinate of the target neural structure, y2 is the y-coordinate of the target neural structure, z2 is the z-coordinate of the target neural structure, w1 is the weight coefficient related to the catheter angle deviation, w2 is the weight coefficient related to the catheter pitch angle deviation, w3 is the weight coefficient related to the catheter roll angle deviation, θ x is the component of the angular deviation between the catheter and the target neural structure in the x-axis direction, θ y is the component of the angular deviation between the catheter and the target neural structure in the y-axis direction, θ z It is the component of the angular deviation between the catheter and the target neural structure in the z-axis direction.

7. The catheter system for neurosurgery intervention according to claim 1, characterized in that: The catheter operation strategy learning module includes: Historical data collection submodule: Through the surgical operation data set, a convolutional neural network is used to record the catheter operation data in real time, collect the catheter path optimization results in historical surgeries, organize and store relevant data, and generate an operation history data set; Deviation analysis submodule: Based on the operation history data set, the path deviation and actual operation error occurring during the operation are analyzed, the deviation type and frequency are recorded, the source of the operation error is evaluated, and the deviation analysis result is generated; Strategy optimization submodule: Based on the deviation analysis results, the deviations occurring during the operation are deeply analyzed, and the catheter operation strategy is adjusted in combination with historical operation data to generate an optimization strategy with strong adaptability and obtain operation strategy optimization data.

8. The catheter system for neurosurgery intervention according to claim 7, characterized in that: The convolutional neural network is calculated according to the following formula, and the specific formula is as follows: Where: L is the loss value, y′ i is the actual label, p′ i is the probability value predicted by the model, n is the number of categories, w′1 is the weight coefficient related to the actual label, w′2 is the weight coefficient related to the angle deviation of the x-axis, w′3 is the weight coefficient related to the angle deviation of the y-axis, w′4 is the weight coefficient related to the angle deviation of the z-axis, θ′ x is the angular deviation of the catheter relative to the target neural structure in the x-axis direction, θ′ y is the angular deviation of the catheter relative to the target neural structure in the y-axis direction, θ′ z is the angular deviation of the catheter relative to the target neural structure in the z-axis direction.

9. The catheter system for neurosurgery intervention according to claim 1, characterized in that: The catheter operation optimization application module includes: Path adjustment calculation submodule: Based on the operation strategy optimization data, analyze the difference between the catheter operation path and the target, calculate the adaptive adjustment path, and generate a corrected path plan by analyzing the current state and target of the catheter to obtain a path adjustment plan: Precision evaluation submodule: Based on the path adjustment scheme, the adjusted operation precision is evaluated, the movement precision of the catheter under the new path is calculated, and a comparative analysis is performed to obtain the adjusted operation precision: Operation adjustment suggestion generation submodule: Based on the adjusted operation accuracy, combined with the path adjustment plan and operation strategy optimization data, generate catheter movement adjustment suggestions for actual surgical operations and output the catheter operation execution plan.

10. A catheter method for neurosurgery intervention, characterized in that: The catheter system for neurosurgery intervention according to any one of claims 1 to 9 comprises the following steps: Step 1: Based on historical surgical data, extract the operation path, speed, angle and inclination data, perform data trend analysis, calculate the path errors at each stage, predict the path starting point, end point and path changes at the intermediate stage, update the path prediction results, and generate path optimization results; Step 2: Based on the real-time catheter position information, obtain the angle, speed, and inclination data of the catheter, compare them with the path optimization result, determine the deviation between the current position and the optimized path, calculate the required correction parameters, adjust the catheter motion parameters, and generate a catheter deviation adjustment signal; Step 3: Based on the catheter deviation adjustment signal, the patient's CT and MRI image data are acquired, image segmentation and calibration are performed, the position of the neural structure is calculated, and the position is compared with the anatomical markers in the image to extract key neural structure information, perform spatial positioning and morphological calculation, and generate neural structure position information; Step 4: Based on the neural structure position information, a support vector machine is used to calculate the spatial deviation between the current position of the catheter and the target neural structure, and whether the deviation exceeds a set threshold is determined. If the deviation exceeds the set threshold, the direction, speed and angle of the catheter path are adjusted, and a path correction operation is performed. The catheter movement path is corrected through a catheter deviation adjustment signal, and a path adjustment instruction is generated; Step 5: Based on the path adjustment instruction, a convolutional neural network is used to analyze the historical surgical data, record the catheter operation data and deviation in real time, calculate the operation accuracy and deviation, analyze the deviation and optimization space in the operation, adjust the operation strategy, and generate operation strategy optimization data; Step 6: Based on the operation strategy optimization data, calculate the adaptation adjustment plan between the catheter operation path and the target, evaluate the adjusted operation accuracy, adjust the catheter movement in the actual operation, and generate a catheter operation execution plan.

Images