Tumor electric field treatment device control system based on cloud computing

Abstract

The invention relates to the technical field of intelligent control, in particular to a tumor electric field treatment device control system based on cloud computing, which comprises a tumor positioning and tracking module, a position prediction and analysis module, an electric field intensity distribution module, a collaborative management module and a dynamic response execution module. According to the method, by accurately tracking the image data and the electrical impedance scanning data of the tumor area, the gradient direction and the gray distribution of the tumor edge are extracted, the feature point displacement and the electrical impedance change between the image frames are matched, the dynamic repositioning of the tumor center position is allowed, the accuracy and the response speed of tumor positioning are optimized, and the accuracy and the response speed of tumor positioning are improved. Potential damage to surrounding healthy tissues is reduced, electric field parameters are dynamically adjusted according to tumor motion prediction data and electrical impedance changes, real-time optimization of the electric field intensity is achieved, maximization of the treatment effect is ensured, meanwhile, side effect risks are reduced, the relation between the electric field intensity and the conductivity of the tumor area is dynamically mapped, and treatment adaptability and safety are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent control, and particularly to a control system for a tumor electrotherapy device based on cloud computing. Background Art

[0002] The technical field of intelligent control includes multiple aspects such as automation control, information processing, robot control, and medical device control. Its core content is to intelligently adjust and control an object through devices such as computers, sensors, and actuators. The goal of this technical field is to improve the system's adaptability, response speed, and accuracy to achieve precise regulation of complex environments and systems. In this field, special emphasis is placed on the application of intelligent algorithms, such as regulation decisions based on real-time data and optimization of feedback mechanisms, enabling the control system to automatically adjust in a dynamic environment to adapt to changing conditions. Intelligent control technology is widely used in multiple fields such as industrial automation, smart home, medical devices, and traffic management, and with the combination of artificial intelligence and big data technologies, the application prospects of intelligent control technology are broad in all walks of life.

[0003] Among them, the control system of the tumor electrotherapy device refers to a system used to control electrotherapy equipment, aiming to treat tumor cells through precise electric field control. This technical theme focuses on the problems of electric field generation, regulation, and precise positioning during tumor treatment. The patent realizes real-time adjustment of electric field parameters through the control system to ensure the maximization of the electric field effect and no damage to surrounding healthy tissues. By monitoring the tumor position and treatment progress, parameters such as the intensity and frequency of the electric field are adjusted to achieve the best treatment effect. The design focus of this control system lies in high-precision control and dynamic adjustment to ensure the accurate electric field distribution during the treatment process, optimize the treatment effect, and improve the treatment safety of patients.

[0004] The existing technology has obvious deficiencies in tumor positioning and electric field regulation in a dynamic environment. Especially when dealing with the position changes of tumors caused by physiological activities such as breathing during treatment, the existing technology cannot adjust the electric field parameters in real time and accurately, resulting in poor treatment effects and accidental injuries to surrounding healthy tissues. The lack of an efficient prediction mechanism and real-time data processing ability makes the treatment process unable to well adapt to the rapid changes in the patient's body position and tumor movement, reducing the adaptability and precision of the treatment. The deficiencies limit the efficiency and safety of the treatment, leading to uncertainty in the treatment effect of patients and potential treatment risks. Summary of the Invention

[0005] The purpose of the present invention is to solve the deficiencies existing in the prior art, and a control system for a tumor electrotherapy device based on cloud computing is proposed.

[0006] To achieve the above object, the present invention adopts the following technical solutions. The control system of the tumor electric field therapy device based on cloud computing includes:

[0007] The tumor positioning and tracking module acquires the image data and impedance scanning data of the tumor area, extracts the tumor edge gradient direction and gray-scale distribution, matches the displacement amount of feature points and the impedance change amount in adjacent frame images, and generates a tumor center positioning coordinate set;

[0008] The position prediction and analysis module calls the tumor center positioning coordinate set, combines the tumor movement trajectory data stored in the cloud platform and the three-dimensional offset output by the patient body position sensor, evaluates the linear relationship between the real-time displacement rate and acceleration, predicts the range of the tumor center coordinates in the future time period, and obtains the tumor movement prediction path data;

[0009] The electric field intensity distribution module, based on the coordinate range in the tumor movement prediction path data, compares the impedance scanning data with the frequency and intensity safety intervals in the preset electric field model, and adjusts the electric field intensity distribution ratio according to the geometric coverage area of the prediction path to obtain the dynamic adjustment result of the electric field parameters;

[0010] The collaborative management module uses the dynamic adjustment result of the electric field parameters to evaluate the dynamic mapping relationship between the electric field intensity and the conductivity of the tumor area, adjusts the electric field intensity distribution ratio of the corresponding coordinates in the mapping relationship, and generates a dynamic intensity distribution table.

[0011] As a further solution of the present invention, the tumor center positioning coordinate set includes the tumor boundary position, abnormal displacement point coordinates, and center position correction amount. The tumor movement prediction path data includes the displacement rate prediction interval, acceleration change trend, and tumor position range in the future time period. The dynamic adjustment result of the electric field parameters includes the frequency safety range, intensity gradient ratio, and area coverage adjustment factor. The dynamic intensity distribution table includes the intensity position mapping relationship, conductivity adaptation factor, and coordinate intensity proportionality coefficient.

[0012] As a further solution of the present invention, the tumor positioning and tracking module includes:

[0013] The edge extraction sub-module acquires the image data and impedance scanning data of the tumor area, calculates the pixel gray-scale difference and extracts the edge gradient direction distribution of the image data, extracts the tumor edge coordinate point set for the gradient direction change area, and performs matching judgment in combination with the impedance intensity change value of the corresponding image area of the impedance data. According to the gray-scale change trend in the matching area, the edge structure stability interval is judged, and the edge direction gradient value interval is generated;

[0014] The feature matching sub-module calls the corresponding edge coordinate points in the edge direction gradient value range, calculates the pixel position difference value of the feature points between adjacent frames, and combines the frame-to-frame impedance change intensity recorded in the impedance scanning to perform position mapping on the displacement amount of the feature points and the impedance strength change value to form a comparison group, and obtains a feature point displacement difference group;

[0015] The position reconstruction sub-module makes a point-by-point comparison based on the displacement change value of the feature points in the feature point displacement difference group and a set displacement amount threshold, screens the feature points exceeding the displacement amount threshold, and extracts the coordinate values as the input point set to generate a tumor center positioning coordinate set.

[0016] As a further solution of the present invention, the position prediction and analysis module includes:

[0017] The displacement parameter integration sub-module calls the tumor center positioning coordinate set, collects the tumor motion trajectory data stored in the cloud platform, and calculates the displacement increments in the horizontal, vertical, and longitudinal axes based on the three-dimensional offset output by the patient position sensor to obtain a dynamic trajectory parameter set;

[0018] The linear relationship evaluation sub-module calls the dynamic trajectory parameter set, extracts the coordinate difference between adjacent timestamps as the real-time displacement rate, and combines the axial change amount of the three-dimensional offset. Using the formula:

[0019]

[0020] Calculate the correlation degree between the rate and acceleration, compare the correlation degree with a set linear reference value, screen the time periods that meet the linear relationship, and establish a linear correlation factor;

[0021] Among them, LA is the correlation degree between the rate and acceleration, v i represents the real-time displacement rate at the i-th time point, Δa i represents the acceleration change amount at the i-th time point, Δd i represents the modulus length of the three-dimensional offset vector at the i-th time point, μ represents the tumor tissue density compensation coefficient, ρ represents the respiratory motion phase weight value, Δt max represents the peak time interval, and n is the number of time points;

[0022] The path prediction sub-module calculates the extreme difference of the displacements in the horizontal, vertical, and longitudinal axes within the future time window according to the linear correlation factor, and calls the selected time period data in the dynamic trajectory parameter set, and superimposes the standard deviation of the three-dimensional offset to obtain the tumor motion prediction path data.

[0023] As a further solution of the present invention, the electric field strength distribution module includes:

[0024] The impedance scanning data comparison sub-module detects the electric field strength changes in multiple regions and generates a comparison result of the safety interval range based on the coordinate range in the tumor motion prediction path data by comparing the impedance data with the frequency and intensity safety intervals in the preset electric field model;

[0025] The electric field model adjustment sub-module optimizes the parameters of the scanning data and the preset electric field model according to the comparison result of the safety interval range, determines whether the real-time electric field model conforms to the tumor motion prediction path data, and uses the formula:

[0026]

[0027] Adjust the electric field strength and frequency in the model, calculate the adjusted electric field strength, and obtain the electric field model adjustment record;

[0028] Among them, EQ represents the adjusted electric field strength, AE represents the original electric field strength, BF represents the base frequency value, d represents the distance between the electric field and the tumor, and AR represents the reference impedance value;

[0029] The electric field strength distribution sub-module obtains the geometric coverage area of the prediction path according to the electric field model adjustment record, dynamically adjusts the electric field strength, and generates a dynamic adjustment result of the electric field parameters according to the adjusted electric field strength distribution ratio.

[0030] As a further solution of the present invention, the collaborative management module includes:

[0031] The electric field strength analysis sub-module extracts the coverage area in the dynamic adjustment result of the electric field parameters, analyzes the relationship between the electric field strength and the conductivity of the tumor area, and obtains the mapping relationship between the electric field strength and the conductivity by comparing and analyzing the electric field parameters;

[0032] The electric field mapping adjustment sub-module optimizes and adjusts the mapping relationship between the electric field strength and the conductivity based on the mapping relationship between the electric field strength and the conductivity, dynamically adjusts the electric field strength distribution ratio according to the change of the tumor area, and generates an updated mapping model;

[0033] The dynamic strength distribution sub-module dynamically adjusts the distribution ratio of the electric field strength at different coordinate points according to the updated mapping model and the real-time tumor position data, and generates a dynamic strength distribution table.

[0034] As a further solution of the present invention, the system further includes a dynamic response execution module:

[0035] The dynamic response execution module calls the dynamic strength distribution table, combines the real-time impedance fluctuation value with the output limit of the electric field device, dynamically adapts the electric field strength value to the device output ability, and generates a safe electric field execution instruction;

[0036] The safety electric field execution instruction includes the device output power limit value, the real-time electric field intensity index, and the safety margin adjustment amount.

[0037] As a further solution of the present invention, the dynamic response execution module includes:

[0038] Based on the dynamic intensity distribution table, the electric field intensity mapping sub-module extracts the electric field intensity limit interval and the corresponding stage control value in the differentiation stage, obtains the reference sequence of the output limit parameter and the impedance fluctuation value, and combines the real-time call stage identification information and the electric field device output capacity to obtain the mapped intensity screening value;

[0039] The impedance determination sub-module calls the mapped intensity screening value, monitors the interval change sequence of the impedance fluctuation value, extracts the boundary extreme value and the median offset in the fluctuation value, and judges whether the real-time fluctuation state is within the acceptable range interval of the screening intensity based on the difference calculation between the median offset amount of the fluctuation value and the stage electric field response record, and screens out the intensity items that do not meet the response conditions to obtain the impedance adaptation interval value;

[0040] The adaptation instruction sub-module extracts the response sequence characteristics of the intensity item and the corresponding output load coefficient according to the impedance adaptation interval value, identifies the peak load threshold and the low valley capacitance change rate of the real-time electric field device, and uses the formula:

[0041]

[0042] Calculate the adaptation execution intensity ratio, compare the adaptation execution intensity ratio with the boundary of the output load limit interval, identify the range of executable intensity instructions, extract the intensity items that match the response sequence, and generate the safety electric field execution instruction;

[0043] Among them, SQ represents the adaptation execution intensity ratio, Q j represents the charge response value of the j-th intensity item, C min,j represents the low valley capacitance value of the j-th item, ΔC j represents the capacitance change rate of the j-th item, P max represents the peak load threshold of the device, V j represents the voltage offset value of the j-th intensity response, and m is the number of adaptation intensity items.

[0044] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0045] In the present invention, by precisely tracking the image data and electrical impedance scanning data of the tumor region, the extraction of the tumor edge gradient direction and gray-scale distribution is achieved, and the displacement of feature points and the change in electrical impedance between image frames are matched, allowing for the dynamic repositioning of the tumor center position, optimizing the accuracy and response speed of tumor positioning, making the electric field treatment more precise, and reducing the potential damage to surrounding healthy tissues. According to the tumor motion prediction data and the change in electrical impedance, the electric field parameters are dynamically adjusted to achieve real-time optimization of the electric field intensity, ensuring the maximization of the treatment effect while reducing the risk of side effects, dynamically mapping the relationship between the electric field intensity and the conductivity of the tumor region, further optimizing the safety and effect of the electric field treatment, and improving the adaptability and safety of the treatment. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 is the system flowchart of the present invention;

[0047] Figure 2 is the flowchart of the tumor positioning and tracking module in the present invention;

[0048] Figure 3 is the flowchart of the position prediction and analysis module in the present invention;

[0049] Figure 4 is the flowchart of the electric field intensity distribution module in the present invention;

[0050] Figure 5 is the flowchart of the collaborative management module in the present invention;

[0051] Figure 6 is the flowchart of the dynamic response execution module in the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0052] In order to make the objectives, technical solutions and advantages of the present invention more clear and 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.

[0053] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the accompanying drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention. In addition, in the description of the present invention, the meaning of "a plurality of" is two or more, unless otherwise specifically defined.

[0054] Please refer to Figure 1, the control system of the tumor electro-field therapy device based on cloud computing includes:

[0055] The tumor positioning and tracking module acquires the image data and impedance scanning data of the tumor area, extracts the tumor edge gradient direction and gray-scale distribution, matches the displacement amount and impedance change amount of the feature points in adjacent frames of images, recalculates the tumor center position according to the coordinates of the feature points whose displacement amount exceeds the set threshold, and generates a tumor center positioning coordinate set;

[0056] The position prediction and analysis module calls the tumor center positioning coordinate set, combines the tumor motion trajectory data stored in the cloud platform and the three-dimensional offset output by the patient body position sensor, evaluates the linear relationship between the real-time displacement rate and acceleration, predicts the range of the tumor center coordinates in the future time period, and obtains the tumor motion prediction path data;

[0057] The electric field intensity distribution module, based on the coordinate range in the tumor motion prediction path data, compares the impedance scanning data with the frequency and intensity safety intervals in the preset electric field model, and adjusts the electric field intensity distribution ratio according to the geometric coverage area of the prediction path to obtain the dynamic adjustment result of the electric field parameters;

[0058] The collaborative management module uses the dynamic adjustment result of the electric field parameters, combines the coverage area in the tumor motion prediction path data, evaluates the dynamic mapping relationship between the electric field intensity and the conductivity of the tumor area, adjusts the electric field intensity distribution ratio of the corresponding coordinates in the mapping relationship, and generates a dynamic intensity distribution table;

[0059] The dynamic response execution module calls the dynamic intensity distribution table, combines the real-time impedance fluctuation value and the output limit of the electric field device, dynamically adapts the electric field intensity value to the device output capacity, and generates a safe electric field execution instruction;

[0060] The tumor center positioning coordinate set includes the tumor boundary position, abnormal displacement point coordinates, and center position correction amount. The tumor motion prediction path data includes the displacement rate prediction interval, acceleration change trend, and tumor position range in the future time period. The dynamic adjustment result of the electric field parameters includes the frequency safety range, intensity gradient ratio, and area coverage adjustment factor. The dynamic intensity distribution table includes the intensity position mapping relationship, conductivity adaptation factor, and coordinate intensity proportional coefficient. The safe electric field execution instruction includes the device output power limit value, real-time electric field intensity index, and safety margin adjustment amount.

[0061] Please refer to Figure 2 , the tumor positioning and tracking module includes:

[0062] The edge extraction sub-module obtains the image data and impedance scanning data of the tumor region, calculates the pixel gray-scale difference of the image data and extracts the edge gradient direction distribution, extracts the set of tumor edge coordinate points for the region with changing gradient direction, and performs matching judgment by combining the impedance intensity change value of the corresponding image region of the impedance data. The stability interval of the edge structure is judged according to the gray-scale change trend in the matching region, and the edge direction gradient value interval is generated.

[0063] Obtain the image data and impedance scanning data of the tumor region, number the collected image data and establish an image frame sequence. At the same time, extract the pixel gray-scale of each region in the image, record the pixel gray-scale values of different regions in each frame, and correspondingly extract the impedance values measured by the impedance probe in the image region. It is set that in the frames with image numbers from 1 to 5, the gray-scale values from 120 to 148 and the impedance values from 32.5Ω to 37.4Ω are obtained respectively. Calculate the difference values in the horizontal and vertical directions based on the gray-scale difference between pixel points to obtain the edge change intensity of each point. Extract the edge gradient direction through the angle change and count its distribution in intervals of 5°. It is set that the edge gradient direction of frame number 3 is 55°, which is in the edge change dense area. Further extract the coordinate points of the region with continuous change in gradient direction to form an edge structure set, and correspond the pixel gray-scale change trend in the above set with the corresponding impedance change value to judge whether there is a synchronous mutation phenomenon of impedance and gray-scale in this region. It is set that in frames 3 to 4, the gray-scale increases from 145 to 160 while the impedance decreases from 38.3Ω to 36.0Ω. Such reverse changes are regarded as the edge unstable area. On the contrary, if both the gray-scale and the impedance increase or decrease in the same direction, it is regarded as the edge stable area. By comparing whether the change slope of the gray-scale of the edge points in consecutive frames is consistent with the change slope of the impedance value, it is determined that it belongs to the region with high stability. It is set that in the region with a gradient direction of 50° to 55°, the gray-scale increases by 10 to 15 units per frame and the impedance increases synchronously by 2.6Ω to 3.2Ω, then this region is considered stable. On this basis, a mapping table of the gradient ranges in each direction in the stable interval is established, the stable direction set is output and the maximum and minimum gradient direction values are recorded. It is set that the maximum direction is 55° and the minimum direction is 45°, and the edge direction gradient value interval is generated.

[0064] The feature matching sub-module calls the edge coordinate points corresponding to the edge direction gradient value interval, calculates the pixel position difference value of the feature points between adjacent frames, and combines the inter-frame impedance change intensity recorded in the impedance scanning to perform position mapping on the displacement amount of the feature points and the impedance intensity change value to form a comparison group, and obtains the feature point displacement difference group.

[0065] Calculate the change value of the pixel position of feature points for each pair of adjacent frames. Specifically, extract the pixel positions of the same edge coordinate points in the previous frame and the current frame, and perform a difference operation on the scale of pixel units. Set the pixel coordinates of the edge point P in frame 2 and frame 3 to change from (x = 130, y = 220) to (x = 133, y = 224). Then the pixel displacement difference is Δx = 3, Δy = 4, and the displacement modulus is 5 pixels. Furthermore, combine the impedance change values of the corresponding frames. Compare the impedance of frame 2 and frame 3, which changes from 35.1Ω to 38.3Ω, and the change value is 3.2Ω. Bind the pixel displacement value and the impedance change value of this feature point to form a mapping unit. After performing the same operation to traverse all feature points, a complete mapping set is formed. Use the ratio of the displacement modulus value to the impedance change value in the mapping set as the analysis basis. Set the ratio of the above feature point to be 5 / 3.2 ≈ 1.56. Combine the ratios of feature points into an array for summary. Screen the points whose comparison values exceed the set proportional factor and mark them as sensitive offset points. Construct a feature point - impedance comparison mapping group to obtain a feature point displacement difference group.

[0066] The position reconstruction sub-module makes a point-by-point comparison based on the displacement change values of the feature points in the feature point displacement difference group and the set displacement threshold, screens the feature points that exceed the displacement threshold, and extracts the coordinate values as the input point set to generate a tumor center positioning coordinate set;

[0067] Compare the displacement modulus values of the feature points recorded in the feature point displacement difference group with the set threshold. The threshold setting adopts the method of adding twice the standard deviation to the mean value of the displacement modulus of all feature points. Suppose there are 10 feature points in total, the mean value of their displacement modulus is 4.8 pixels, and the standard deviation is 0.9 pixels. Then the threshold is set to 4.8 + 2×0.9 = 6.6 pixels. For the feature points with a displacement modulus greater than 6.6 pixels, extract their coordinate points and form a new coordinate point set. The coordinate point set is like {(134, 221), (145, 230), (139, 219)}. Calculate the coordinate centroid of this point set using the formula:

[0068]

[0069] and

[0070]

[0071] where n is the number of points, and the substitution value for the x coordinate is 134, 145, 139. Then:

[0072] x c = (134 + 145 + 139) / 3 = 139.3;

[0073] For the y coordinate of 221, 230, 219, then:

[0074] yc =(221 + 230 + 219) / 3 = 223.3, generating the center positioning coordinates of the current frame as (139.3, 223.3). Then, combined with the centroid coordinates of the previous frame, a positioning trajectory coordinate chain between consecutive frames is formed. Record the center coordinates of each frame as elements in the positioning sequence to form a tumor center positioning coordinate set.

[0075] Please refer to Figure 3 , the position prediction and analysis module includes:

[0076] The displacement parameter integration sub-module calls the tumor center positioning coordinate set, collects the tumor motion trajectory data stored in the cloud platform, and calculates the displacement increments in the horizontal, vertical, and longitudinal axes based on the three-dimensional offset output by the patient position sensor to obtain a dynamic trajectory parameter set.

[0077] By calling the real-time positioning coordinate set (the tumor center point coordinate sequence recorded at 5-second intervals), collecting the tumor motion trajectory data stored in the cloud platform (as shown in Table 1, including timestamp, X / Y / Z axis displacement), and combining the three-dimensional offset output by the patient position sensor (such as X-axis offset +1.2mm, Y-axis -0.8mm, Z-axis +0.5mm), calculate the mean value of the displacement increments in each axis. Take the arithmetic mean of the displacement amounts at adjacent timestamps on the X-axis to obtain the X-axis mean value ΔX = 0.75mm / s, Y-axis ΔY = -0.4mm / s, Z-axis ΔZ = 0.3mm / s. Integrate the timestamp and the axial displacement amounts to generate a dynamic trajectory parameter set (in the format of [timestamp, ΔX, ΔY, ΔZ, three-dimensional offset modulus], calculate the three-dimensional offset modulus, such as modulus = 1.02mm), and obtain the dynamic trajectory parameter set.

[0078] Table 1 Fragment of tumor motion trajectory data

[0079] Timestamp X-axis displacement Y-axis displacement Z-axis displacement 0 0.0 0.0 0.0 5 3.8 -2.1 1.5 10 7.2 -4.3 3.0

[0080] As shown in Table 1, the displacement amount on the X-axis increases successively within the time window, the Y-axis has a negative offset, the Z-axis has a positive accumulation, and the three-dimensional offset modulus increases from the initial 0mm to 7.2mm.

[0081] The linear relationship evaluation sub-module calls the dynamic trajectory parameter set, extracts the coordinate differences at adjacent timestamps as the real-time displacement rate, and combines the axial change amounts of the three-dimensional offset. Using the formula:

[0082]

[0083] Calculate the correlation degree between the rate and acceleration, compare the correlation degree with the set linear reference value, screen the time periods that meet the linear relationship, and establish a linear correlation factor.

[0084] Among them, LA is the correlation degree between the rate and acceleration, v iRepresents the real-time displacement rate at the i-th time point, Δa i Represents the change in acceleration at the i-th time point, Δd i Represents the magnitude of the three-dimensional offset vector at the i-th time point, μ represents the tumor tissue density compensation coefficient, ρ represents the respiratory motion phase weight value, Δt max Represents the peak time interval, and n is the number of time points;

[0085] By introducing the tissue density compensation coefficient (μ) and the respiratory phase weight (ρ), the static anatomical features are combined with the dynamic physiological signals to enhance the biomechanical rationality of displacement prediction,

[0086] The formula parameters are assigned as follows:

[0087] v i : Based on the dynamic trajectory parameter set, the displacement difference between adjacent time stamps is divided by the time interval (5 seconds). The X-axis rate at the 5th second is (3.8 - 0) / 5 = 0.76 mm / s;

[0088] Δa i : The change in acceleration is calculated by the difference in adjacent rates. The X-axis acceleration from the 5th second to the 10th second is (7.2 - 3.8) / (5 2 ) = 0.136 mm / s 2 ;

[0089] Δd i : The difference in the magnitude of the three-dimensional offset is 4.52 mm;

[0090] μ: The tumor tissue density compensation coefficient is quantified through medical image data (such as CT values) and is set to 0.85 (range 0.7 - 1.2);

[0091] ρ: The respiratory motion phase weight value is divided into the inhalation phase (0.9) and the exhalation phase (0.6) according to the respiratory sensor periodic signal, and the average value is 0.75;

[0092] Δt max : The maximum time interval threshold is set to 10 seconds (based on the average clinical respiratory cycle);

[0093] Set n = 2 sets of data (0 - 5 seconds and 5 - 10 seconds in Table 1), then:

[0094]

[0095] The result shows that the correlation degree between the rate and the acceleration is 0.1998. Compared with the linear reference value of 0.15, it is determined to conform to the linear relationship, and a linear correlation factor is generated.

[0096] The path prediction sub-module calculates the extreme differences in the horizontal, vertical, and vertical axial displacements within the future time window according to the linear correlation factor, calls the period data screened from the dynamic trajectory parameter set, and superimposes the standard deviation of the three-dimensional offset to obtain the tumor motion prediction path data;

[0097] Call the linear correlation factor (0.1998) and the dynamic trajectory parameter set to calculate the extreme differences in the axial displacements within the future time window (such as 15 seconds):

[0098] Range of the X-axis = 7.2 mm (the maximum value in Table 1) - 0.0 mm = 7.2 mm, standard deviation = 2.4 mm;

[0099] Range of the Y-axis = |-4.3 mm - 0.0 mm| = 4.3 mm, standard deviation = 1.5 mm;

[0100] Range of the Z-axis = 3.0 mm - 0.0 mm = 3.0 mm, standard deviation = 0.9 mm;

[0101] Superimpose the standard deviations of the three-dimensional offsets to generate a spatial range matrix:

[0102] Upper limit of the X-axis = 7.2 + 2.4 = 9.6 mm, lower limit = 7.2 - 2.4 = 4.8 mm;

[0103] Upper limit of the Y-axis = -4.3 + 1.5 = -2.8 mm, lower limit = -4.3 - 1.5 = -5.8 mm;

[0104] Upper limit of the Z-axis = 3.0 + 0.9 = 3.9 mm, lower limit = 3.0 - 0.9 = 2.1 mm,

[0105] The matrix data is combined as 9.6 ≤ X ≤ 4.8, -2.8 ≤ Y ≤ -5.8, 3.9 ≤ Z ≤ 2.1 to obtain the tumor motion prediction path data.

[0106] Please refer to Figure 4 , the electric field intensity distribution module includes:

[0107] The impedance scan data comparison sub-module detects the changes in the electric field intensity in multiple regions based on the coordinate range in the tumor motion prediction path data, and generates a comparison result of the safety interval range by comparing the impedance data with the frequency and intensity safety intervals in the preset electric field model;

[0108] During the impedance scan data comparison process, obtain the impedance scan data of the target region, measure the impedance value of the region where the tumor is located using sensors and measurement equipment, and collect data in combination with the estimated position and size of the tumor. After the tumor position is determined, scan the impedance value of this region through an electronic sensor to obtain the impedance change data in the region. Set the impedance of the scanned data display region A as R A= 500 Ω, while the standard impedance value in the preset electric field model is R ref = 1000 Ω. On this data set, a comparison is made to determine whether the impedance value is within the set safe electric field strength range. If the measured impedance value is high, it indicates that the electric field strength requirement in this area is strong; otherwise, it is weak. Further, according to the scan results, the electric field strength model is adjusted to ensure that the electric field strength and frequency are kept within the range safe for the human body, generating a new electric field strength setting. In this way, precise control of the electric field strength around the tumor location can be achieved, providing an effective reference value for subsequent treatment. After the electric field strength is adjusted, the safe electric field interval in this area is identified to ensure that the electric field strength during the treatment process will not cause damage to normal tissues, generating a comparison result of the safe interval range.

[0109] According to the comparison result of the safe interval range, the electric field model adjustment sub-module optimizes the parameters of the scan data and the preset electric field model, and determines whether the real-time electric field model conforms to the tumor motion prediction path data. The formula is used:

[0110]

[0111] Adjust the electric field strength and frequency in the model, calculate the adjusted electric field strength, and obtain the electric field model adjustment record;

[0112] Among them, EQ represents the adjusted electric field strength, AE represents the original electric field strength, BF represents the base frequency value, d represents the distance between the electric field and the tumor, and AR represents the reference impedance value;

[0113] Meaning of parameters and derivation process of formula calculation:

[0114] AE: The original electric field strength, with the unit of volts per meter (V / m), provided by the preset electric field model, and AE = 150 V / m is set;

[0115] BF: The base frequency value, with the unit of hertz (Hz), provided by the initial settings of the device, and BF = 1000 Hz is set,

[0116] d: The distance between the electric field and the tumor, with the unit of centimeters (cm), measured by the imaging device and the scanning instrument for the physical distance between the tumor and the electric field source, and d = 5 cm is set;

[0117] AR: The reference impedance value, with the unit of ohm (Ω), provided by the device or the preset model, used for comparison with the actual scan data, and R ref = 1000 Ω;

[0118] Parameter acquisition and assignment:

[0119] AE and BF are the set values of the initial electric field model, provided by the preset values of the treatment device and not affected by impedance scanning;

[0120] AR is the reference impedance value set in the model, set according to device standards or regional characteristics, and set as AR = 1000Ω;

[0121] d is the specific physical distance value obtained through an imaging device or tumor detection instrument. In this example, the distance from the tumor location to the electric field source is set to 5 cm;

[0122] Formula calculation and derivation: Substitute the known parameter values:

[0123]

[0124] Calculate the numerator:

[0125] 1.5 × 150 = 225;

[0126] 1.5 × 1000 = 1500;

[0127] 225 + 1500 = 1725;

[0128] Calculate the denominator:

[0129] 0.005 2 = 0.000025;

[0130] 1 + 0.000025 = 1.000025;

[0131]

[0132]

[0133] The results show that the adjusted electric field strength obtained is 1724.98 V / m, indicating that according to the impedance scanning data and the optimization of the electric field model, the adjusted electric field strength is 1724.98 V / m. Compared with the original electric field strength (150 V / m), the optimized strength has increased significantly. This adjustment is reflected in practical applications. To ensure effective irradiation of the tumor, the electric field strength must be dynamically adjusted according to the changes in scanning data and tumor location. This value is directly related to the matching degree of the preset target area and electric field strength, ensuring that the electric field distribution during the treatment process can effectively cover the tumor area.

[0134] The electric field strength distribution sub-module adjusts the records according to the electric field model, obtains the geometric coverage area of the predicted path, dynamically adjusts the electric field strength, and generates the dynamic adjustment result of the electric field parameters according to the adjusted electric field strength distribution ratio;

[0135] According to the optimized electric field model, obtain the geometric coverage area of the target region, determine the specific location and shape of the tumor, and dynamically adjust the electric field strength based on this information to achieve uniform coverage. Set the geometric coverage area of the tumor location as a circle with a radius of r = 5 cm. At this time, the electric field strength needs to be distributed according to the region radius and location. If the impedance change scanned in this region is 800, then according to the optimized electric field model, by adjusting this impedance value, a new electric field strength value is obtained. Set the adjusted value of the electric field strength as EQ ≈ 1724.98. This value can ensure appropriate electric field coverage around the tumor while minimizing the impact on non-target areas. The distribution result of the adjusted electric field strength will directly affect the treatment effect, ensuring a high degree of matching between the electric field strength and the tumor target region during the treatment process, and improving the treatment accuracy and effectiveness.

[0136] Please refer to Figure 5 , and the collaborative management module includes:

[0137] The electric field strength analysis sub-module extracts the coverage area in the dynamic adjustment result of the electric field parameters, and analyzes the relationship between the electric field strength and the conductivity of the tumor region. By comparing and analyzing the electric field parameters, the mapping relationship between the electric field strength and the conductivity is obtained;

[0138] To extract the coverage area in the dynamic adjustment result of the electric field parameters, the electric field parameters in the adjustment result need to be mapped to the target analysis region in a rasterized manner, and the electric field strength values at each grid point are recorded in the form of a two-dimensional matrix. Set the tumor region to be divided into 50×50 grid cells, and the area of each cell is 1 mm 2Then, the extraction of the coverage area can be achieved by setting a threshold electric field strength (e.g., set to 10 V / cm) and traversing all grid points. When the electric field strength value at a certain grid point is greater than the threshold, mark it as the "effective electric field area". Suppose after adjustment, a certain tumor sample has an electric field strength greater than 10 V / cm within the grid range from (10, 10) to (30, 30), then this area is the coverage area. To analyze the relationship between the electric field strength and the conductivity of the tumor area, it is necessary to call the electric field strength matrix and the pre-stored conductivity matrix at the same coordinate points for differential analysis of the corresponding elements. Calculate the ratio of the electric field strength to the conductivity at each grid point. For example: at the (20, 20) grid, the electric field strength is 12 and the conductivity is 0.18, then the ratio is 66.7. Further, statistically analyze the ratio data of all effective coverage areas, and use the sectional statistical method to divide intervals according to the conductivity values: (0.1, 0.15), (0.15, 0.2), (0.2, 0.25), etc., and calculate the corresponding average electric field strength within each interval. Suppose the conductivity covers a total of 16 grid points within the range of (0.15, 0.2), and the average electric field strength is 11.3 V / cm; within the range of (0.2, 0.25), it covers 24 grid points, and the average electric field strength is 13.6 V / cm. Compare the electric field distribution trends under different conductivities, and establish a mapping table through normalization processing. The mapping relationship is the pairing result of the conductivity interval and the electric field strength interval, and the mapping relationship between the electric field strength and the conductivity is obtained.

[0139] Table 2 Corresponding Relationship Table between Conductivity and Electric Field Strength

[0140]

[0141] As shown in Table 2, as the conductivity increases, the corresponding electric field strength also shows an increasing trend, reflecting that the electric field distribution has an obvious correlation with the conductivity of the tumor area.

[0142] Based on the mapping relationship between the electric field strength and the conductivity, the electric field mapping adjustment sub-module optimizes and adjusts the mapping relationship between the electric field strength and the conductivity, dynamically adjusts the electric field strength distribution ratio according to the changes in the tumor area, and generates an updated mapping model;

[0143] Each time new tumor area images or diagnostic data are received, the system will re-obtain the conductivity change map of this area, and match the new conductivity data with the existing electric field strength mapping table one by one. When a conductivity interval not covered in the original mapping table is found, calculate the estimated value of the electric field strength through linear interpolation. If the 0.225 S / m interval is not covered in the original table, linear estimation can be performed using the two end values within the (0.2, 0.25) interval:

[0144] (13.6 - 11.3) / (0.25 - 0.15) = 2.3 / 0.1 = 23;

[0145] The estimated value of the corresponding electric field strength for the newly added 0.225 S / m is as follows:

[0146] 11.3 + 0.075 × 23 = 13.025 V / cm;

[0147] Based on the estimated electric field strength corresponding to each conductivity change value, construct an updated mapping table, and update the corresponding intensity parameter field in the electric field distribution model. At the same time, compare the values before and after each adjustment, and calculate the deviation percentage:

[0148] δ = |E new - E old | / E old × 100%;

[0149] When the deviation exceeds the ±10% threshold, the mapping relationship is marked as "requiring review", and only the mapping with the deviation value in the interval [0, 10%] is retained as the final updated value, covering the old model in the system and generating an updated mapping model.

[0150] The dynamic intensity allocation sub-module dynamically adjusts the allocation ratio of the electric field strength at different coordinate points according to the updated mapping model, combined with the real-time tumor position data, and generates a dynamic intensity allocation table;

[0151] Combined with the real-time tumor position data, the system calls the superimposition of multi-time point image data within a short distance, establishes a tumor displacement trajectory map, extracts feature points from this trajectory map, and extracts the range of changes in the coordinates of the tumor center point in the key frames. Assuming that the tumor center point of a certain patient moves from (t0, x = 32, y = 40) to (t1, x = 36, y = 43), then within the entire electric field allocation area, establish an electric field strength function for the coordinate point (x, y), assign the target electric field strength to different conductivity points according to the mapping model, then traverse the electric field strength values corresponding to the coordinate points in the updated model according to the set of coordinate points occupied by the current tumor position, and then calculate the total required allocation strength. Use the ratio of the electric field strength of each point to the total as the allocation coefficient:

[0152]

[0153] Multiply the total input intensity P of the system (for example, set to 500 V / cm) by w a That is the actual intensity value to be allocated to each point. For example, if the electric field strength E a of a certain point is 15 V / cm and the total is 150 V / cm, then the allocation ratio of this point is 10%, and the corresponding intensity is 50 V / cm, and output the dynamic intensity allocation table.

[0154] Please refer to Figure 6 , the dynamic response execution module includes:

[0155] Based on the dynamic intensity allocation table, the electric field intensity mapping sub-module extracts the electric field intensity limit intervals and corresponding phased control values in different phases, obtains the reference sequences of output limit parameters and impedance fluctuation values, and combines the real-time called phase identification information and the output capacity of the electric field device to obtain the mapped intensity screening value;

[0156] It is necessary to extract the electric field intensity limit intervals in different phases. Suppose in an actual scenario, the system is divided into three phases: A, B, and C. The corresponding intensity intervals are [1.0, 2.5] V / m, [2.6, 4.0] V / m, and [4.1, 6.0] V / m respectively, and the corresponding control values are set to 2.0, 3.5, and 5.0 V / m. Collect the output limit parameters of the current system, set the maximum current limit to 3.2 A, and the impedance fluctuation reference sequence is [0.8, 1.1, 1.3] Ω. Combine the current phase identification information and set the current phase to phase B. Then call the corresponding control value and its limit interval in phase B for comparison. According to the output capacity of the electric field device, set the maximum allowable output intensity of the current device to 3.8 V / m. Compare it with all candidate intensity items in phase B of the intensity limit table, and screen out all intensity items that meet the requirement of below 3.8 V / m. In this example, the intensity candidates are 2.6 V / m, 3.2 V / m, and 3.5 V / m. Number and classify the selected intensity items uniformly to form an intensity screening list, and then associate its electric field response record number through the database record. The content of the generated candidate list is used as the basic data for the next phase determination process to obtain the mapped intensity screening value.

[0157] The impedance determination sub-module calls the mapped intensity screening value, monitors the interval change sequence of the impedance fluctuation value, extracts the boundary extreme value and median offset in the fluctuation value, and judges that the real-time fluctuation state is within the acceptable range interval of the screening intensity based on the difference calculation between the median offset of the fluctuation value and the phased electric field response record, screens out the intensity items that do not meet the response conditions, and obtains the impedance adaptation interval value;

[0158] After calling the mapping intensity screening value, it is necessary to monitor the current impedance fluctuation in real time, calculate its interval change value. Set the impedance values collected by a certain electrode as [0.84, 0.89, 0.91, 0.93, 0.96] Ω, then its boundary extreme values are 0.84 Ω and 0.96 Ω, and the median value is 0.91 Ω. Further extract the median offset. This offset refers to the difference compared with the average response impedance value in the response record. Set the real-time value as 0.88 Ω, then the offset is 0.91 - 0.88 = 0.03 Ω. Judge whether there is any value falling within the allowable offset interval in the response records corresponding to each intensity item. Set the allowable offset interval corresponding to a certain intensity item as ±0.05 Ω. Then the current offset of 0.03 Ω meets the requirement. If it does not meet the requirement, it will be excluded from the list. Repeat the above process to traverse the screening intensity list, obtain all intensity items within the allowable fluctuation range, form a new intensity range list, and obtain the impedance adaptation interval value.

[0159] The adaptation instruction sub-module extracts the response sequence characteristics of the intensity item and the corresponding output load coefficient according to the impedance adaptation interval value, identifies the peak load threshold and the low valley capacitance change rate of the real-time electric field device, and uses the formula:

[0160]

[0161] Calculate the adaptation execution intensity ratio, compare the adaptation execution intensity ratio with the boundary of the output load limit interval, identify the executable intensity instruction range, extract the intensity items that match the response sequence, and generate a safe electric field execution instruction;

[0162] Among them, SQ represents the adaptation execution intensity ratio, Q j represents the charge response value of the jth intensity item, C min,j represents the low valley capacitance value of the jth item, ΔC j represents the capacitance change rate of the jth item, P max represents the peak load threshold of the device, V j represents the voltage offset value of the jth intensity response, and m is the number of adaptation intensity items;

[0163] Through the joint operation of multiple physical participation items such as charge response value, capacitance change rate, and voltage offset, and introducing square root, fraction, and absolute value, while accurately calculating the intensity execution ratio, it improves the overall perception ability of the system's charge-capacitance coupling characteristics and enhances the stability of the adaptation instruction determination;

[0164] Table 3 Response parameter table of the intensity items of the electric field device

[0165] Strength item number Charge response value Minimum capacitance value Capacitance change rate Voltage offset value S1 0.15 1.0 0.2 0.3 S2 0.22 0.9 0.15 0.25 S3 0.18 1.1 0.18 0.28 S4 0.19 1.05 0.2 0.31

[0166] Table 3 lists the original data of the intensity response parameters participating in the formula calculation of this paragraph for the call of step operation and judgment basis;

[0167] Extract the charge response values, capacitance change rates, and voltage offset values of each intensity term. Obtain the maximum load threshold of the current electric field device, which is set to 2.0 W, and record the minimum capacitance values of each intensity term as 1.0 F, 0.9 F, 1.1 F, and 1.05 F. The corresponding capacitance change rates are 0.2 F, 0.15 F, 0.18 F, 0.2 F, the charge response values are 0.15 C, 0.22 C, 0.18 C, 0.19 C, and the voltage offset values are 0.3 V, 0.25 V, 0.28 V, 0.31 V. Substitute these values into the formula for calculation:

[0168] Molecular part:

[0169]

[0170] Denominator part:

[0171]

[0172] Compare the result 0.141 with the preset allowable intensity threshold range of the device, which is 0.12 to 0.16. It is found that it is within the allowable range. This result indicates that the selectable intensity instruction is effective, and the system can enter the next stage of the instruction setting process to generate a safe electric field execution instruction.

[0173] The above is only a preferred embodiment of the present invention, and it does not limit the present invention in 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 solution content 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 control system for a tumor electro-field therapy device based on cloud computing, characterized in that, The system includes: The tumor location and tracking module acquires the image data and impedance scanning data of the tumor area, extracts the tumor edge gradient direction and gray scale distribution, matches the displacement amount of feature points and the impedance change amount in adjacent frame images, and generates a tumor center location coordinate set; The position prediction and analysis module calls the tumor center location coordinate set, combines the tumor motion trajectory data stored in the cloud platform and the three-dimensional offset output by the patient body position sensor, evaluates the linear relationship between the real-time displacement rate and acceleration, predicts the range of tumor center coordinates in the future time period, and obtains the tumor motion prediction path data; The electric field strength distribution module, based on the coordinate range in the tumor motion prediction path data, compares the impedance scanning data with the frequency and intensity safety intervals in the preset electric field model, and adjusts the electric field strength distribution ratio according to the geometric coverage area of the prediction path to obtain the dynamic adjustment result of electric field parameters; The collaborative management module uses the dynamic adjustment result of electric field parameters to evaluate the dynamic mapping relationship between the electric field strength and the conductivity of the tumor area, adjusts the electric field strength distribution ratio of the corresponding coordinates in the mapping relationship, and generates a dynamic strength distribution table.

2. The control system of the tumor electric field therapy device based on cloud computing according to claim 1, wherein The tumor center location coordinate set includes the tumor boundary position, abnormal displacement point coordinates, and center position correction amount. The tumor motion prediction path data includes the displacement rate prediction interval, acceleration change trend, and tumor position range in the future time period. The dynamic adjustment result of electric field parameters includes the frequency safety range, intensity gradient ratio, and regional coverage adjustment factor. The dynamic strength distribution table includes the intensity position mapping relationship, conductivity adaptation factor, and coordinate intensity proportional coefficient.

3. The control system of the tumor electro-field therapy device based on cloud computing according to claim 1, wherein The tumor location and tracking module includes: The edge extraction sub-module acquires the image data and impedance scanning data of the tumor area, calculates the pixel gray scale difference of the image data and extracts the edge gradient direction distribution, extracts the tumor edge coordinate point set for the gradient direction change area, and combines the impedance intensity change value of the corresponding image area of the impedance data for matching judgment. According to the gray scale change trend in the matching area, it judges the edge structure stability interval and generates the edge direction gradient value interval; The feature matching sub-module calls the edge coordinate points corresponding to the edge direction gradient value interval, calculates the pixel position difference value of feature points between adjacent frames, and combines the inter-frame impedance change intensity recorded in the impedance scanning to perform position mapping on the displacement amount of feature points and the impedance intensity change value to form a comparison group, and obtains the feature point displacement difference group; The position reconstruction sub-module compares the displacement change value of feature points in the feature point displacement difference group with the set displacement amount threshold point by point, screens out the feature points exceeding the displacement amount threshold, and extracts the coordinate values as the input point set to generate the tumor center location coordinate set.

4. The control system of the tumor electric field therapy device based on cloud computing according to claim 3, characterized in that The position prediction and analysis module includes: The displacement parameter integration sub-module calls the tumor center location coordinate set, collects the tumor motion trajectory data stored in the cloud platform, and calculates the displacement increments in the horizontal, vertical, and longitudinal axes based on the three-dimensional offset output by the patient body position sensor to obtain the dynamic trajectory parameter set; The linear relationship evaluation sub-module calls the dynamic trajectory parameter set, extracts the coordinate difference between adjacent timestamps as the real-time displacement rate, combines it with the axial change amount of the three-dimensional offset, and uses the formula: Calculate the correlation degree of the rate and acceleration, compare the correlation degree with the set linear reference value, screen the time periods that meet the linear relationship, and establish a linear correlation factor; Among them, LA is the rate and acceleration correlation degree, v i represents the real-time displacement rate at the i-th time point, Δa i represents the acceleration change at the i-th time point, Δd i represents the three-dimensional offset vector modulus at the i-th time point, μ represents the tumor tissue density compensation coefficient, ρ represents the respiratory motion phase weight value, Δt max represents the peak time interval, and n is the number of time points; The path prediction sub-module calls the time period data screened from the dynamic trajectory parameter set according to the linear correlation factor, calculates the extreme difference of the horizontal, vertical and vertical axial displacements within the future time window, and superimposes the standard deviation of the three-dimensional offset to obtain the tumor motion prediction path data.

5. The control system of the tumor electro-field therapy device based on cloud computing according to claim 4, characterized in that, The electric field strength distribution module includes: The impedance scan data comparison sub-module, based on the coordinate range in the tumor motion prediction path data, detects the change of the electric field strength in multiple regions by comparing the impedance data with the frequency and intensity safety intervals in the preset electric field model, and generates a comparison result of the safety interval range; The electric field model adjustment sub-module optimizes the parameters of the scan data and the preset electric field model according to the comparison result of the safety interval range, judges whether the real-time electric field model conforms to the tumor motion prediction path data, and uses the formula: Adjust the electric field strength and frequency in the model, calculate the adjusted electric field strength, and obtain the electric field model adjustment record; Among them, EQ represents the adjusted electric field strength, AE represents the original electric field strength, BF represents the base frequency value, d represents the distance between the electric field and the tumor, and AR represents the reference impedance value; The electric field strength distribution sub-module obtains the geometric coverage area of the prediction path according to the electric field model adjustment record, dynamically adjusts the electric field strength, and generates a dynamic adjustment result of the electric field parameters according to the adjusted electric field strength distribution ratio.

6. The control system of the tumor electric field therapy device based on cloud computing according to claim 5, characterized in that, The collaborative management module includes: The electric field strength analysis sub-module extracts the coverage area in the dynamic adjustment result of the electric field parameters, analyzes the relationship between the electric field strength and the conductivity of the tumor area, and obtains the mapping relationship between the electric field strength and the conductivity by comparing and analyzing the electric field parameters; The electric field mapping adjustment sub-module optimizes and adjusts the mapping relationship between the electric field strength and the conductivity based on the mapping relationship between the electric field strength and the conductivity, and dynamically adjusts the electric field strength distribution ratio according to the change of the tumor area to generate an updated mapping model; The dynamic strength distribution sub-module dynamically adjusts the distribution ratio of the electric field strength at different coordinate points according to the updated mapping model, combined with the real-time tumor position data, and generates a dynamic strength distribution table.

7. The control system of the tumor electric field therapy device based on cloud computing according to claim 1, characterized in that, The system also includes a dynamic response execution module: The dynamic response execution module calls the dynamic strength distribution table, combines the real-time impedance fluctuation value with the output limit of the electric field device, and dynamically adapts the electric field strength value to the device output ability to generate a safe electric field execution instruction; The safe electric field execution instruction includes the device output power limit value, the real-time electric field strength index, and the safety margin adjustment amount.

8. The control system of the tumor electric field therapy device based on cloud computing according to claim 7, characterized in that The dynamic response execution module includes: Based on the dynamic intensity allocation table, the electric field intensity mapping sub-module extracts the electric field intensity limit intervals and corresponding phased control values in different differentiation stages, obtains the reference sequences of output limit parameters and impedance fluctuation values, and combines the real-time called stage identification information and the output capacity of the electric field device to obtain the mapped intensity screening value; The impedance determination sub-module calls the mapped intensity screening value, monitors the interval change sequence of the impedance fluctuation value, extracts the boundary extreme values and median offsets in the fluctuation value, and judges whether the real-time fluctuation state is within the acceptable range interval of the screening intensity based on the difference calculation between the median offset of the fluctuation value and the phased electric field response record, screens out the intensity items that do not meet the response conditions, and obtains the impedance adaptation interval value; The adaptation instruction sub-module extracts the response sequence characteristics of the intensity items and the corresponding output load coefficients according to the impedance adaptation interval value, identifies the peak load threshold and the low valley capacitance change rate of the real-time electric field device, and uses the formula: Calculate the adaptation execution intensity ratio, compare the adaptation execution intensity ratio with the boundary of the output load limit interval, identify the range of executable intensity instructions, extract the intensity items that match the response sequence, and generate a safe electric field execution instruction; Among them, SQ represents the adaptation execution intensity ratio, Q j represents the charge response value of the j-th intensity, C min,j represents the valley capacitance value of the j-th item, ΔC j represents the capacitance change rate of the j-th item, P max represents the peak load threshold of the device, V j represents the voltage offset value of the j-th intensity response, and m is the number of adaptation intensity items.

Images