Tumor treating field system and regulation and control method therefor

Abstract

A tumor treating field system and a regulation and control method therefor, relating to the technical field of medical instruments. The tumor treating field system comprises: an observation module, configured to acquire observation parameters; a regulation module, configured to periodically acquire at least part of observation parameters as an observation parameter set, generate a target parameter set on the basis of the observation parameter set, a preset system index set, and a preset optimization algorithm, generate a regulation weight matrix on the basis of the target parameter set, the observation parameter set, a preset regulation parameter set, and a preset control algorithm, and generate a regulation instruction set on the basis of the regulation weight matrix and the regulation parameter set; and an execution module, configured to regulate an alternating electric field applied to a target tissue on the basis of the regulation and control instruction set. By achieving self-adaptive regulation and control of the tumor treating field system, the flexibility of a treatment scheme of the tumor treating field system is improved, thereby improving the therapeutic effect.

Description

A tumor treatment field system and its control method CROSS-REFERENCE TO RELATED APPLICATIONS This application is based on the Chinese patent application with application number "202311868514.4" and application date of December 29, 2023, and claims the above-mentioned Chinese patent application The entire contents of the above-mentioned Chinese patent application are hereby incorporated into this application by reference. Technical Field

[0001] The embodiments of the present application relate to the field of medical device technology, and in particular to a tumor treatment field system and a control method thereof. Background Art

[0002] Tumor Treating Fields (TTFields) is an emerging anti-tumor technology used to treat newly diagnosed glioblastoma (GBM), recurrent glioblastoma, and malignant pleural mesothelioma (MPM), and has shown promising efficacy and safety in clinical trials. Clinical trials of tumor treating field devices are continuously expanding to other types of cancer, and combined applications with other treatments are also being explored. As an innovative cancer treatment device, it has the advantages of high safety, minimal side effects, and ease of operation, providing new hope for improving the prognosis of patients with malignant tumors such as GBM. Its basic principle is to apply an external physical field to charged and polarized molecules (called dipoles), affecting the mitosis of cancer cells through the action of the external physical field, thereby inhibiting the growth and division of cancer cells and producing a therapeutic effect.

[0003] However, current tumor treatment field devices primarily utilize an open-loop control model. For example, a physician adjusts the electric field parameters and maintains them until readjustment at the next follow-up visit. Other tumor treatment field devices adjust their parameters based on specific conditions or test results. These devices lack effective feedback and control mechanisms during treatment, lacking adaptive control and flexibility, and are unable to adapt appropriately to changes in the patient's condition, whether transient or long-term. Consequently, the therapeutic effects of these devices have yet to meet expectations. Summary of the Invention

[0004] The embodiments of the present application provide a tumor treatment field system and a control method thereof, which can at least improve the flexibility of the treatment plan of the tumor treatment field system and improve the treatment effect by realizing adaptive control of the tumor treatment field system.

[0005] According to some embodiments of the present application, on one hand, embodiments of the present application provide a tumor treatment field system, comprising: an observation module configured to obtain observation parameters, wherein the observation parameters are used to characterize a treatment state; a control module configured to periodically obtain at least some of the observation parameters as an observation parameter set, and generate a target parameter set based on the observation parameter set, a preset system indicator set, and a preset optimization algorithm; generate a control weight matrix based on the target parameter set, the observation parameter set, the preset control parameter set, and the preset control algorithm; and generate a control instruction set based on the control weight matrix and the control parameter set, wherein the system indicator set is used to reflect an indicator of the performance of the tumor treatment field system, the target parameter set is used to represent specific values ​​of expected parameters of the tumor treatment field system, the control parameter set is composed of parameters that allow the tumor treatment field system to control the alternating electric field, and the control weight matrix is ​​used to characterize the quantitative value that each parameter in the control parameter set needs to be controlled; and an execution module configured to control the alternating electric field applied to the target tissue according to the control instruction set.

[0006] In some embodiments, the optimization algorithm is expressed as follows: minimize f(B) = C(G1(A, B), G2(A, B), ..., G k (A,B))subject to h(A,B)≤0,G1(A,B),G2(A,B),...,G k (A, B)∈S1, A, B∈S2, where f(B) represents the function corresponding to the optimization objective, k represents the number of system indicators included in the system indicator set, G i (A, B) represents the i-th system index, C(G1(A, B), G2(A, B), ..., G k (A, B)) represents a preset function for obtaining a comprehensive system indicator from each of the system indicators, A represents the observation parameter set, B represents the target parameter set, h(A, B) is a preset constraint function about A and B, S1 represents the feasible domain of the calculated values ​​of each of the system indicators, and S2 represents the feasible domain of the preset observation parameters in the observation parameter set and the target parameters in the target parameter set; the iterative method of the optimization algorithm includes: particle swarm optimization algorithm, genetic algorithm or simulated annealing algorithm.

[0007] In some embodiments, the control algorithm is a PID control algorithm or a synovial control algorithm.

[0008] In some embodiments, the execution module includes an alternating electric field generating circuit and electrodes arranged around the target tissue, and the alternating electric field generating circuit is used to generate a corresponding alternating electric field according to the control instruction set and apply it to the target tissue through the electrodes.

[0009] In some embodiments, the execution module further includes a driver, configured to drive the electrode according to the control instruction set to adjust the posture of the electrode.

[0010] In some embodiments, the execution module is further configured to send the manual control instruction to the outside when the control instruction set includes the manual control instruction.

[0011] In some embodiments, the control module includes: a first storage unit, configured to store the control parameter set; a second storage unit, configured to store the system indicator set; a computing unit, configured to generate the target parameter set based on the observation parameter set, the system indicator set obtained from the second storage unit and the optimization algorithm, and generate the control weight matrix based on the target parameter set, the observation parameter set, the control parameter set read from the first storage unit and the control algorithm, and generate and output the control instruction set based on the control weight matrix and the control parameter set read from the first storage unit.

[0012] In some embodiments, the observation parameters include at least one of the following information: temperature, current, electrode state, duty cycle, intensity of the alternating electric field, frequency of alternating electric field change, target tissue state and impedance of the target tissue; the control parameters include at least one of the following information: current, frequency of the alternating electric field, intensity of the alternating electric field, duty cycle, electrode selection; the system indicators include at least one of the following information: system safety indicator, system energy saving indicator, system treatment efficacy indicator, system adaptability indicator.

[0013] In some embodiments, the path selection module, and the control module includes at least two control sub-modules; the path selection module is configured to divide each observation parameter into multiple observation parameter sets according to the characteristics of each selectively obtained observation parameter; each control sub-module is configured to generate the target parameter set according to the corresponding observation parameter set, the system indicator set and the optimization algorithm, and generate the control weight matrix according to the target parameter set, the obtained observation parameter set, the control parameter set and the control algorithm, and generate the control instruction set according to the control weight matrix and the control parameter set.

[0014] In some embodiments, the path selection module is further configured to configure observation parameters with an observation period greater than the first period to one of the control sub-modules, and to configure observation parameters with an observation period less than the first period to another of the control sub-modules, where the observation period is the period for the observation module to collect observation parameters.

[0015] In some embodiments, the path selection module is further configured to configure the observation parameters with an observation period greater than the second period to one of the control sub-modules, and to configure the observation parameters with an observation period less than the third period to another of the control sub-modules, where the observation period is the period for the observation module to collect the observation parameters.

[0016] In some embodiments, the path selection module is further configured to configure the observation parameters with an importance level greater than the first level to one of the regulation sub-modules, and to configure the observation parameters with an importance level less than the second level to another of the regulation sub-modules, wherein the importance level is a quantitative value of the importance of the observation module in the regulation process.

[0017] In some embodiments, different regulatory submodules correspond to different control algorithms.

[0018] In some embodiments, a strategy selection module; the strategy selection module is configured to determine the current control strategy from multiple control strategies, wherein the control strategy includes the types of system indicators in the currently expected system indicator set and the relationships between them; the control module is configured to generate the target parameter set based on the observation parameter set and the system indicator set corresponding to the current control strategy determined by the strategy selection module, as well as a preset optimization algorithm, and generate the control weight matrix based on the target parameter set, the observation parameter set, the control parameter set and the control algorithm, and generate and output the control instruction set based on the control weight matrix and the control parameter set.

[0019] In some embodiments, the strategy selection module is further configured to automatically adjust the current control strategy according to changes in the first information, wherein the first information includes at least one of the following information: the current treatment stage, the power supply status of the tumor treatment field system, and the patient's physical condition.

[0020] According to some embodiments of the present application, another aspect of the present application embodiments further provides a method for controlling a tumor treatment field system, the tumor treatment field system comprising an observation module, a control module, and an execution module, the method comprising: the observation module acquiring observation parameters, wherein the observation parameters are used to characterize a treatment state; the control module periodically acquiring at least some of the observation parameters, constructing an observation parameter set, and generating a target parameter set based on the observation parameter set, a preset system indicator set, and a preset optimization algorithm; the control module generating a control weight matrix based on the target parameter set, the observation parameter set, the preset control parameter set, and a preset control algorithm, wherein the system indicator set is used to reflect performance indicators of the tumor treatment field system, the target parameter set is used to represent specific values ​​of desired parameters of the tumor treatment field system, the control parameter set is composed of parameters of a controllable alternating electric field, and the control weight matrix is ​​used to characterize the quantitative values ​​that require control of each parameter in the control parameter set; the control module generating a control instruction set based on the control weight matrix and the control parameter set; and the execution module controlling the alternating electric field applied to the target tissue based on the control instruction set.

[0021] The technical solution provided by the embodiments of the present application has at least the following advantages:

[0022] The control module generates a set of observation parameters based on the observation results of the observation module, representing the desired system indicators. Using an optimization algorithm, it obtains a set of target parameters representing the specific values ​​of the desired system parameters. This set of observation parameters, the set of control parameters representing the parameters that can actually control the alternating electric field, and the control algorithm are then combined to generate a control weight matrix. Based on the control weight matrix and the set of control parameters, a set of control instructions is generated to enable the execution module to control the alternating electric field applied to the target tissue (e.g., tumor tissue, the tumor removal cavity, and surrounding tissue). Therefore, the tumor treatment field system fully considers the inherent connections between the desired indicators, observation parameters, and control parameters, making the control of the alternating electric field applied to the target tissue more scientific, accurate, and efficient. Furthermore, the observation module continuously and autonomously acquires various observation parameters that can characterize the current treatment state. The control module periodically obtains these observation parameters and makes corresponding adjustments. Therefore, the observation data set can serve as feedback on treatment results, influencing the generation of the control instruction set, forming a closed-loop control loop and enabling adaptive control of the tumor treatment field system, increasing the flexibility of the tumor treatment field system's treatment plans and improving treatment efficacy. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] One or more embodiments are exemplarily illustrated by pictures in the corresponding drawings. These exemplifications do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings are represented as similar elements. Unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0024] FIG1 is a schematic structural diagram of a tumor treatment field system provided in an embodiment of the present application;

[0025] FIG2 is a schematic structural diagram of a control module in a tumor treatment field system provided in an embodiment of the present application;

[0026] FIG3 is a schematic structural diagram of an execution module in a tumor treatment field system provided in an embodiment of the present application;

[0027] FIG4 is another structural diagram of an execution module in the tumor treatment field system provided in an embodiment of the present application;

[0028] FIG5 is another structural schematic diagram of a tumor treatment field system provided in an embodiment of the present application;

[0029] FIG6 is another structural diagram of a tumor treatment field system provided in an embodiment of the present application;

[0030] FIG7 is another structural diagram of a control module in the tumor treatment field system provided in an embodiment of the present application;

[0031] FIG8 is a flow chart of the control method provided in an embodiment of the present application;

[0032] FIG9 is a flowchart of processing data involved in the control method shown in FIG8 provided in an embodiment of the present application. DETAILED DESCRIPTION

[0033] To make the purpose, technical solutions, and advantages of the embodiments of the present application more clear, each embodiment of the present application will be described in detail below with reference to the accompanying drawings. However, those skilled in the art will appreciate that many technical details are provided in each embodiment of the present application to help readers better understand the present application. However, even without these technical details and various variations and modifications based on the following embodiments, the technical solutions claimed in the present application can still be implemented.

[0034] The following embodiments are divided for the convenience of description and should not constitute any limitation on the specific implementation of the present application. The various embodiments can be combined with each other and referenced to each other without contradiction.

[0035] Some embodiments of the present application provide a tumor treatment field system, as shown in FIG1 , comprising: an observation module 101, a control module 102, and an execution module 103. It should be noted that at least some of the modules in the tumor treatment field system provided in the embodiments of the present application can be located inside the human body, such as by arranging the execution module 103 in the body near a malignant tumor such as a glioblastoma or a tumor removal cavity through intervention. Of course, the tumor treatment field system provided in the embodiments of the present application can also be located entirely outside the human body, similar to a traditional tumor treatment field device, and the execution module 103 is set at an external position corresponding to a malignant tumor such as a glioblastoma, and the alternating electric field generated by the system is applied to a malignant tumor such as a glioblastoma after passing through organs and tissues such as the skin.

[0036] Among them, the observation module 101 is configured to obtain observation parameters; the control module 102 is configured to periodically obtain at least part of the observation parameters as an observation parameter set, and generate a target parameter set based on the observation parameter set, a preset system indicator set and a preset optimization algorithm, and then generate a control weight matrix based on the target parameter set, the observation parameter set, the preset control parameter set and the preset control algorithm, and generate a control instruction set based on the control weight matrix and the control parameter set; the execution module 103 is configured to control the alternating electric field applied to the target tissue according to the control instruction set.

[0037] In this embodiment, the control module 102 forms an observation parameter set based on the observation results of the observation module 101, a system indicator set representing the system performance index, and obtains a target parameter set representing the specific numerical values ​​of the system's desired parameters according to the optimization algorithm. Then, the control weight matrix is ​​obtained by combining the above-mentioned observation parameter set, the control parameter set representing the parameters that can actually control the alternating electric field, and the control algorithm. The control instruction set is obtained based on the control weight matrix and the control parameter set, so that the alternating electric field applied to the target tissue (e.g., tumor tissue, tumor removal cavity and nearby tissue) is controlled through the execution module 103. Therefore, the system fully considers the inherent relationship between each desired indicator, observation parameter, and control parameter, making the control of the alternating electric field applied to the target tissue more scientific, accurate, and efficient. In addition, the observation module 101 can also continuously obtain various observation parameters that can characterize the current treatment state, and the control module 102 periodically obtains the observation parameters and makes corresponding adjustments. Therefore, the observation data set can serve as feedback on the treatment results, affecting the generation of the control instruction set, forming a closed-loop control, and achieving adaptive control.

[0038] To facilitate those skilled in the art to better understand the system shown in FIG1 , an explanation will be provided below with reference to the accompanying drawings.

[0039] In some examples, the observation parameters acquired by the observation module 101 are parameters used to characterize the treatment state. The treatment state may include the state of the tumor treatment field system and the state of the patient (including the state of the target tissue). This embodiment does not limit the number of observation parameters and the specific content of the observations, and the observation parameters may include any parameters that can reflect the patient's current treatment state. In some examples, the observation parameters may include at least one of the following information: temperature, current, electrode state, duty cycle, alternating electric field strength, alternating electric field frequency, target tissue state, and target tissue impedance.

[0040] In some examples, the temperature may include the temperature of the electrode-tissue interface and surrounding tissue, obtained via one or more temperature sensors located on the electrodes. This temperature can be used to monitor thermal effects during treatment. In some examples, the temperature may include the temperature of the tumor treatment field system, obtained via one or more temperature sensors located on a circuit board or housing of the stimulator. This temperature can be used to control the operation of the tumor treatment field system within a safe and effective range. In some examples, the current may include the current flowing through the electrodes, which can reflect the output of the alternating electric field. In some examples, the electrode status may include the number of electrodes activated for treatment. In some examples, the electrode status may include the number of electrodes activated for treatment and their spatial positions. In some examples, the duty cycle may include the ratio of electrode stimulation time to electrode rest time, reflecting the intermittent nature of the alternating electric field output. During each treatment stimulation cycle, the electrodes intermittently stop generating the alternating electric field for a period of time. This allows temperature regulation by controlling the alternating electric field. In some examples, the alternating electric field strength may include the strength of the alternating electric field near the target tissue. In some examples, the alternating electric field intensity may include the strength of the alternating electric field near the electrodes. In some examples, the frequency of the alternating electric field can be used to reflect the modulation of the alternating electric field frequency. In some examples, the target tissue status can include one or more of the target tissue's location, morphology, volume, and changes therein, as determined through medical imaging or other means. In some examples, the impedance of the target tissue can be the impedance of the target tissue under alternating current excitation. The impedance value also reflects the target tissue status to a certain extent.

[0041] Of course, the above is only an exemplary description of the observation parameters. In some examples, the observation parameters may also include one or more of the patient's physiological test data, such as blood pressure, heart rate, etc., which will not be described in detail here.

[0042] This embodiment does not specifically limit the specific type of observation module 101. In some examples, observation module 101 may be a diagnostic device, such as an external imaging diagnostic device such as a CT machine, X-ray machine, or MRI machine. In some examples, observation module 101 may be a sensor, such as a temperature sensor, current sensor, voltage sensor, electric field strength sensor, or posture sensor. These sensors may be located inside or outside the body.

[0043] In some cases, the time required for observation module 101 to obtain observation results may vary. Different observation parameters may require different observation periods to obtain observation results. For example, temperature observation results may be available instantly, while observation results for target tissue volume changes may take days or even months to obtain.

[0044] In some examples, the control module 102 periodically acquires different observation parameters, with different acquisition periods for different observation parameters. The period for acquiring different observation parameters can depend on, on the one hand, the time required to obtain the observation results for the corresponding observation parameters, i.e., the corresponding observation period; on the other hand, it can also depend on the importance of the observation parameters. In other words, the control module 102 can periodically acquire multiple observation parameters to form a multi-dimensional observation parameter set. When different observation parameters require different observation periods, by acquiring observation parameters at intervals, richer data can be accumulated during the acquisition period to more comprehensively and accurately reflect the patient status and system status, allowing for timely and accurate adjustments to be made. This allows for the development of a control strategy that is appropriate for the current treatment status and achieves better treatment outcomes. Furthermore, a multi-dimensional observation parameter set facilitates multi-dimensional control decision-making, thereby supporting diverse control methods. This allows for personalized, customized treatment plans for different patients, patients at different treatment stages, and the different operating states of the tumor treatment field system.

[0045] In some examples, the system indicators in control module 102 may be indicators used to reflect the performance of the tumor treatment field system. A system indicator set is a collection of system indicators. System indicators are the optimization targets for closed-loop system control. Each system indicator has a target control range. It should be noted that this embodiment does not limit the number or specific content of system indicators.

[0046] In some examples, the system indicator may include at least one of the following information: a system safety indicator, a system energy saving indicator, a system treatment efficacy indicator, and a system adaptability indicator.

[0047] In some examples, a system safety index can reflect the safety level during treatment and can be a composite of one or more parameters, such as electrode temperature, alternating electric field intensity, and current magnitude. In some examples, parameters related to the system safety index include temperature and current. The system safety index can be represented by a negative correlation with temperature and current, i.e., the lower the temperature and current, the higher the system safety index. In some examples, a system energy conservation index can reflect the energy consumption of the system. For example, parameters related to the system energy conservation index can include parameters such as the current, voltage, and duty cycle required to generate the alternating electric field; or the system energy consumption per target tissue and per unit alternating electric field intensity; or the current available power, estimated remaining run time, and current energy consumption of the system. In some examples, a system treatment efficacy index can reflect the effectiveness of treatment. For example, parameters related to the system energy conservation index can include the coverage and intensity of the alternating electric field on the target tissue area; or the coverage and intensity of the alternating electric field on the target tissue area combined with changes in target tissue volume and electrophysiological parameters of the target tissue; or the alternating electric field intensity and stimulation duration of the target tissue. In some examples, the system adaptability index can be an index reflecting the system's adaptability to different treatment modes and conditions. For example, parameters related to the system adaptability index can include the range, rate, and frequency of change of parameters related to the alternating electric field.

[0048] It should also be noted that this embodiment does not limit the calculation method of the system indicators. For example, it can be a formula defined by a doctor based on experience. For another example, it can be defined based on some experimental research tests.

[0049] To help those skilled in the art better understand the tumor treatment field system provided in this embodiment, the calculation methods of some system indicators will be illustrated below. However, this does not mean that this embodiment must include or only includes system indicators defined by the following calculation methods.

[0050] 1. Calculation method of system security index:

[0051]

[0052] Among them, Q is the system security index, n is the number of observation parameters involved in the system security index, and x i is the measured value of the i-th observation parameter, is the median of the upper and lower limits of the safety range of the i-th observation parameter ， k i represents the weight and ∑k i=1. It should be noted that the present embodiment does not limit the specific value of n, the meaning of each observation parameter involved in the calculation, and the safety range of the corresponding observation parameters. They can be determined based on different patients, different operating conditions of the system, different treatment stages, etc. The above observation parameters can all be observed by the control module 102.

[0053] In one example, n=3, that is, the system safety index involves three observation parameters, such as temperature, current, and alternating electric field strength. Among them, the parameter temperature x1 is obtained by observing the temperature of the electrode through the sensor. The measured value is 35℃, and its safety range is 30℃ to 40℃. The parameter alternating electric field strength x2 is obtained by observing the alternating electric field strength around the target tissue through the sensor. The measured value is 2V / cm, and its safety range is 1V / cm to 3V / cm. The parameter current x3 is obtained by observing the current of the electrode through the sensor. The measured value is 0.5A, and its safety range is 0.4A to 0.6A. and

[0054] Therefore, the current system security indicators are:

[0055]

[0056] In the above formula, a typical understanding is that a Q value of 0 represents a completely safe system, a positive Q value indicates an overshoot of the system parameter value, and a negative Q value indicates an undershoot of the system parameter value. At the same time, it is necessary to iterate and check whether the system parameters are within the safe range. If they are outside the safe range, the system will initiate emergency measures and perform interventions on the parameters whose measured values ​​are outside the safe range.

[0057] In other examples, the temperature t and current I obtained from the electrode are used as observation parameters, and the temperature t and current I are dedimensionalized, such as by averaging, min-max transformation, Z-score transformation, etc., and then the reciprocal is taken and weighted to obtain the system safety index Q. That is, Among them, k1 and k2 represent weights, which are used to adjust the weight of the impact of temperature and current on the system safety index. i = 1; ω1 and ω2 are scaling factors to prevent the influence of either temperature t or current I from being negligible due to an excessively large temperature or current; f() and g() represent dimensionless functions. The formula indicates that lower temperature and current increase the system safety index.

[0058] Of course, the above is only an example. In other examples, the system safety index can also be based on a piecewise function defined within and outside the preset range to consider intervention outside the range and stability maintenance within the range, etc., which will not be elaborated here.

[0059] 2. Calculation method of system energy-saving index:

[0060]

[0061] Among them, N is the system energy saving index (unit: W / V*cm 2 ), P is the total power consumed during a stimulation cycle (unit: W), and V is the volume of the target tissue (unit: cm 3 ), E is the average alternating electric field strength of the target tissue (unit: V / cm). The measured values ​​of these observation parameters can be obtained by the observation module 101.

[0062] In one example, the total power consumed during one stimulation cycle is 10 W and the volume of the target tissue is 10 cm 3 , the average alternating electric field strength of the target tissue is 1V / cm, then the energy-saving index of the system is:

[0063]

[0064] Of course, the above is merely an example. In other examples, the system energy efficiency index may also consider observation parameters such as the number of activated stimulation electrodes, energy consumed per minute, and target tissue volume. I will not elaborate on these here.

[0065] 3. Calculation method of system performance index:

[0066]

[0067] Where P is the system's therapeutic efficacy indicator (unit: V·month / cm), C is the coverage of the alternating electric field above the specified threshold alternating electric field intensity on the target tissue (unit: percentage %), and E is the average intensity of the alternating electric field within the region (unit: V / cm). The measured values ​​of these observation parameters can be obtained by the system's observation module 101. G is the target tissue growth rate, which refers to the relative change in the target tissue volume per unit time and can be calculated using the following formula:

[0068]

[0069] Where G is the target organization growth rate (unit: 1 / month), V t is the target tissue volume after treatment (unit: cm 3), V0 is the target tissue volume before treatment (unit: cm 3 ), t is the treatment time (unit: month). The measured values ​​of these observation parameters can be obtained by the observation module 101, such as imaging diagnostic equipment.

[0070] In one example, the target tissue volume before treatment was 100 cm 3 The target tissue volume after treatment is 102 cm 3 , the treatment time is 1 month, then the target tissue growth rate is:

[0071]

[0072] Assuming that the coverage rate of the alternating electric field on the target tissue exceeds the specified threshold alternating electric field strength is 80%, and the average intensity of the alternating electric field is 2V / cm, the system treatment efficacy index is:

[0073]

[0074] Of course, the above is only an example. In some examples, the system performance indicator may also consider observation parameters such as the number of open stimulation electrodes, which will not be detailed here.

[0075] In some examples, the optimization algorithm of control module 102 may be designed to achieve a balance across all parameters. For example, it may be necessary to maximize energy savings (target) while maintaining therapeutic efficacy (constraint) and activate fewer electrodes. Of course, the optimization algorithm may also determine the optimization target based on specific treatment needs.

[0076] In some examples, the target parameter set in the control module 102 can be a set of specific parameter values ​​that the system expects to achieve through control. Accordingly, the target parameter is each specific value that the system expects to achieve. The target parameter set is a set of target parameters. The target parameter set is obtained by calculating the system indicator set in combination with the optimization algorithm and the observation parameter set. The observation parameter set and the system indicator set determine the types of parameters and parameter values ​​to be calculated by the optimization algorithm. The solution of the optimization algorithm is the set of specific parameter values ​​that the system expects to achieve, namely the target parameter set. Since the system indicators in the system indicator set involve more parameters, the types of parameters in the observation parameter set (i.e., observation parameters) may be less than or equal to the types of parameters in the target parameter set (i.e., target parameters).

[0077] In some examples, the control parameter set in control module 102 comprises parameters that allow the tumor treatment field system to control the alternating electric field. A control parameter set is a collection of control parameters. In some examples, a control weight matrix is ​​used to represent the quantized value that requires control for each parameter (i.e., control parameter) in the control parameter set. This embodiment does not limit the number or specific content of the control parameters, and the control parameters may include any parameters that can control the alternating electric field.

[0078] In some examples, the control parameters may include at least one of the following information: current, alternating electric field frequency, alternating electric field strength, duty cycle, and electrode selection. The definitions of these control parameters can refer to the observation parameters above.

[0079] In some examples, the alternating electric field frequency may be a frequency that sweeps across a certain range. In some examples, the alternating electric field frequency may be a superposition of multiple frequencies. In some examples, the alternating electric field frequency may be switched in a stepwise manner. In some examples, the alternating electric field strength may be a frequency that sweeps across a certain range or is set to a fixed strength. In some examples, electrode selection may be a change in the number of electrodes in an on state and / or a change in the position of the on electrodes.

[0080] Of course, the above is only an exemplary description of the parameters. In other examples, the control parameters may also include other parameters, which will not be described in detail here.

[0081] In some cases, the parameters in the target parameter set may or may not be consistent with the parameters in the control parameter set. For example, if the target parameter set includes temperature, the parameters in the control parameter set will be inconsistent with the parameters in the target parameter set. This is because temperature cannot be used to control the alternating electric field and therefore cannot be included as a parameter in the control parameter set.

[0082] In addition, in order to facilitate those skilled in the art to better understand the specific implementation of the processing of the relevant information provided by the above-mentioned control module 102, the relevant algorithms are explained below.

[0083] In some examples, the optimization algorithm is expressed as follows:

[0084] minimize f(B)=C(G1(A,B),G2(A,B),...,G k (A,B)),

[0085] subject to

[0086] h(A,B)≤0,

[0087] G1(A,B),G2(A,B),...,G k (A,B)∈S1,

[0088] A,B∈S2,

[0089] Among them, f(B) represents the function corresponding to the optimization objective, k represents the number of system indicators contained in the system indicator set, G i (A, B) represents the i-th system index, which is a function related to A and B, C(G1(A, B), G2(A, B), ..., G k (A,B) represents the predefined function that derives the comprehensive system indicator from the individual system indicators. A represents the observation parameter set, B represents the target parameter set, h(A,B) represents the predefined constraint function on A and B, S1 represents the feasible region for the calculated values ​​of the individual system indicators, and S2 represents the feasible region for the observed parameters in the predefined observation parameter set and the target parameters in the target parameter set. In the formula, minimize represents minimization, and subject to represents satisfying the subsequent constraints.

[0090] The iterative methods of the optimization algorithm include: particle swarm optimization algorithm, genetic algorithm or simulated annealing algorithm. Of course, the optimization algorithm can also be iterated in other ways, which will not be listed here.

[0091] In order to facilitate those skilled in the art to better understand the iterative algorithm of the optimization algorithm provided in the above embodiment, an exemplary example will be given below.

[0092] 1. About Particle Swarm Optimization Algorithm:

[0093] Assume that our optimization goal is to find a set of parameters that minimizes energy consumption while ensuring system safety. The objective function can be expressed as:

[0094] minimize f(x)=w1×g1(x)-w2×g2(x),

[0095] Among them, x is a vector including parameters such as alternating electric field strength, duty cycle, electrode selection, etc., g1(x) represents the energy consumption index, g2(x) represents the safety index, and w i is the weight, i=1,2.

[0096] Accordingly, the solution process includes the following steps:

[0097] Initialization: Randomly initialize the particle swarm, where each particle represents a set of possible parameters related to the alternating electric field.

[0098] Evaluation: Evaluate the fitness of each particle using the objective function.

[0099] Update personal and global best: If the particle's current position is better than its historical best, update the personal best; if the particle's current position is better than the global best, update the global best.

[0100] The speed and position of each particle are updated using the following formula:

[0101]

[0102]

[0103] Among them, v i t+1 is the velocity of particle i at generation t+1, w represents the inertia factor, v i t is the velocity of particle i in generation t, c1 and c2 represent acceleration constants, r1 and r2 are random numbers with a value range of [0, 1], represents the local optimal position of particle i, represents the global optimal position of the particle swarm, x i t is the position of particle i in generation t, x i t+1 is the position of particle i at generation t+1. As can be seen from the above expression, the inertia factor w controls the degree to which the particle depends on its previous velocity, and the acceleration constants c1 and c2 control the degree to which the particle follows its own local optimal position and global optimal position.

[0104] Iteration: Repeat the steps of evaluation, updating the best position, updating the speed and position until a stopping condition is met (e.g., the maximum number of iterations is reached or the change in the global best position is less than a certain threshold).

[0105] Through this process, the particle swarm optimization algorithm can find a set of parameters that minimizes energy consumption while ensuring safety. This set of parameters can be used as the system's optimization target and adjusted in real time by the subsequent control algorithm.

[0106] 2. About Genetic Algorithm (GA):

[0107] Assuming the goal is to minimize energy consumption and ensure system safety, the optimization objective is:

[0108] minimize f(x)=w1×g1(x)-w2×g2(x),

[0109] Similarly, x is a vector including parameters such as alternating electric field strength, duty cycle, electrode selection, etc., g1(x) represents the energy consumption index, g2(x) represents the safety index, and w iis the weight, i=1,2.

[0110] Accordingly, the solution process includes the following steps:

[0111] Initialization: Randomly generate the initial population, each individual represents a set of possible alternating electric field related parameters.

[0112] Selection: Select individuals for reproduction based on a fitness function (e.g., an objective function).

[0113] The selection is achieved by the following expression:

[0114]

[0115] Among them, P i is the probability of the i-th individual being selected, f(x i ) is the fitness of the i-th individual.

[0116] Crossover: Creating new offspring by exchanging some of the genes of selected individuals.

[0117] Crossover can be done using one-point crossover or multi-point crossover. For example, one-point crossover: offspring 1 = the first half of parent 1 + the second half of parent 2; offspring 2 = the first half of parent 2 + the second half of parent 1. Assume there are two parents:

[0118] Parent 1: current 1, electrode posture 1, temperature 1 current 1, electrode posture 1, temperature 1;

[0119] Parent 2: Current 2, Electrode Position 2, Temperature 2 Current 2, Electrode Position 2, Temperature 2;

[0120] Perform a one-point crossover on parent 1 and parent 2. Assuming the crossover point is between the first and second genes, the resulting offspring are:

[0121] Offspring 1: current 1, electrode position 2, temperature 2 current 1, electrode position 2, temperature 2;

[0122] Offspring 2: current 2, electrode position 1, temperature 1; current 2, electrode position 1, temperature 1;

[0123] Mutation: Randomly change some genes of the new offspring with a certain probability. Randomly change some genes of the new offspring, assuming the probability of mutation is p.

[0124] Mutate the offspring. Suppose the mutation occurs in the current value with probability p. If the mutation occurs, the current value will change randomly. For example, the current value of offspring 1 may change from "current 1" to "current 1'".

[0125] For example, the mutated offspring 1 may be obtained as follows: current 1′, electrode position 2, temperature 2, current 1′, electrode position 2, temperature 2.

[0126] Evaluation and selection of the new generation: The fitness of the new offspring is evaluated and the next generation of the population is selected.

[0127] Iteration: Repeat the selection, crossover, mutation, evaluation, and selection steps until a stopping condition is met.

[0128] In the above process, the genes of the genetic algorithm refer to the parameters representing the individuals. In the parameter optimization problem related to the alternating electric field, each individual represents a set of possible alternating electric field parameters, such as the alternating electric field intensity and the alternating electric field frequency.

[0129] Through this process, the genetic algorithm is able to find a set of parameters that allows the system to minimize energy consumption while ensuring safety.

[0130] 3. About Simulated Annealing (SA):

[0131] Assuming the goal is to minimize energy consumption and ensure system safety, the optimization goal is still:

[0132] minimize f(x)=w1×g1(x)-w2×g2(x)

[0133] Similarly, x is a vector of parameters related to the alternating electric field, including the alternating electric field strength, duty cycle, electrode selection, etc. g1(x) represents the energy consumption index, g2(x) represents the safety index, and w i is the weight, i=1,2.

[0134] Accordingly, the solution process includes the following steps:

[0135] Initialization: Select an initial solution x (for example, randomly select a set of parameters related to the alternating electric field) and an initial temperature T0. Note that the "temperature" in the simulated annealing algorithm is an algorithm parameter, and the "temperature" in the parameters related to the alternating electric field is a different concept.

[0136] Neighborhood search: randomly selects a new solution in the neighborhood of the current solution.

[0137] Acceptance criterion: If the new solution is better than the current solution, then accept the new solution; otherwise, accept the new solution with a certain probability, which is determined by the difference between the current temperature and the solution.

[0138] For example, the probability is determined by the following expression:

[0139]

[0140] Where T is the current "temperature", exp() is the natural exponential function, f(x') is the calculated value of the new solution into the objective function, and f(x) is the calculated value of the original solution into the objective function.

[0141] Assume that the new solution is accepted.

[0142] Cooling: To reduce the "temperature", usually according to a certain cooling plan.

[0143] Iteration: Repeat the neighborhood search, acceptance criterion, and cooling steps until a stopping criterion is met.

[0144] The above description is only an exemplary explanation of the optimization algorithm provided to help understanding. When implementing it, the optimization goal is not limited to considering energy consumption indicators and safety indicators as in the above example, but can also consider one or more of the system treatment efficacy indicators, system adaptability indicators, or other indicators, etc., which will not be elaborated here.

[0145] This embodiment does not impose any particular limitation on the control algorithm preset in the control module 102 , which may be any algorithm capable of determining the values ​​that need to be controlled for parameters related to the alternating electric field based on a control parameter set and observation parameters.

[0146] In some examples, the control algorithm may be a PID algorithm or a sliding membrane control algorithm.

[0147] To facilitate those skilled in the art to better understand the functions provided by the above control algorithm, the PID algorithm will be used as an example for illustrative explanation below, but this does not mean that only the PID algorithm can be used as the control algorithm.

[0148] Assume that our control target parameter is temperature. Specifically, we adjust the temperature of the electrode to a safe value T, ie, the target temperature, to achieve the optimization goal (eg, ensuring system safety).

[0149] Therefore, the control algorithm needs to first quantify the degree to which the control parameters need to be controlled based on the observed parameters. In other words, an error calculation is required, that is, for the control parameters, the error between the current state and the target state is calculated. Specifically, this can be achieved through the following expression:

[0150] e(t)=Tt(t), where T represents the target temperature and t(t) represents the current temperature.

[0151] Furthermore, the change of the fast response system determined by proportional control is obtained by the following expression:

[0152] P(t)=K p e(t), where K p Represents the proportional gain, which is used to control the strength of the response.

[0153] The steady-state error of the system determined by the integral control is obtained by the following expression:

[0154] Among them, K i Represents the integral gain, which is used to eliminate steady-state errors.

[0155] The changing trend of the prediction system determined by differential control is obtained by the following expression:

[0156] D(t)=K d de(t) / dt, where K d Represents the differential gain, which is used to suppress rapid changes in error.

[0157] Each component can then be mapped to a duty cycle or current magnitude. For example, the proportional component P can be mapped to the duty cycle, the integral component I to the current magnitude, and the differential component D to the rate of change of the duty cycle. Therefore, if the difference e between the target temperature T and the current temperature t(t) is positive, the duty cycle increases. If the difference e between the target temperature T and the current temperature t(t) is negative, the duty cycle decreases. If the system deviation e persists, the integral component I will continue to increase. This integral component I will increase the duty cycle, thereby gradually reducing the system deviation e.

[0158] Furthermore, the execution module 103 adjusts parameters such as the intensity and duty cycle of the alternating electric field according to the control instruction set.

[0159] It should also be noted that the executable instructions need to determine not only the quantized value of the control, but also the control parameters corresponding to the quantized value, or the control operation. Therefore, the control module 202 also needs to combine the control weight matrix and the control parameter set to obtain specific feasible instructions to form a control instruction set.

[0160] In some examples, the control module 102 can implement the above functions by using different structures.

[0161] In some examples, as shown in FIG. 2 , the control module 102 may include: a first storage unit 112 , a second storage unit 132 , and a computing unit 122 .

[0162] The first storage unit 112 is configured to store a control parameter set. The second storage unit 132 is configured to store a system indicator set. The computing unit 122 is configured to generate a target parameter set based on the observed parameter set, the system indicator set obtained from the second storage unit 132, and the optimization algorithm. The computing unit 122 is configured to generate a control weight matrix based on the target parameter set, the observed parameters, the control parameter set read from the first storage unit 122, and the control algorithm. The computing unit 122 is configured to generate and output a control instruction set based on the control weight matrix and the control parameter set read from the first storage unit.

[0163] Of course, FIG2 is only an example. In some examples, the control module 102 may also have other structures, which will not be described in detail here.

[0164] In some examples, as shown in FIG3 , the execution module 103 may further include an alternating electric field generating circuit 113 and electrodes 133 located around the target tissue, wherein the alternating electric field generating circuit 113 is configured to generate a corresponding alternating electric field according to a control instruction set, and apply the alternating electric field to the target tissue through the electrodes 133. In some examples, as shown in FIG4 , the execution module 103 further includes a driver 123, wherein the driver 123 is configured to drive the electrodes 133 according to the control instruction set to adjust the posture of the electrodes. Posture is an abbreviation for position and posture. In some examples, the system further includes an electrically insulating electrode holder; the electrodes are disposed on the electrode holder; the electrode holder has a spatial structure to fill or cover the target tissue, and the electrodes are spatially arranged to obtain a three-dimensional alternating electric field; the driver 123 drives the electrode holder to change its spatial structure and / or posture to change the distribution of the alternating electric field around the target tissue.

[0165] In some cases, some execution instructions cannot be completed fully automatically and require human intervention. These control instructions are usually set with low generation priority and high execution priority during calculation.

[0166] Therefore, in some examples, the execution module 103 is further configured to send manual control instructions to the outside when the control instruction set includes manual control instructions. The specific method of sending is not limited, such as text message, email, alarm tone, etc. For example, in one example, the alternating electric field can be adjusted by manually adjusting the electrode posture. The execution module 103 can be connected to the terminal (such as a mobile phone, computer, tablet, etc.) wirelessly. When the received control instruction set includes the need to manually operate the above-mentioned electrode holder, the information is sent to the system operator, and the system operator manually adjusts the electrode holder.

[0167] Obviously, as shown in Figure 1, after the execution module 103 is completed, the observation module 101 can obtain the execution result again, and the control module 102 periodically obtains the observation parameters again to form a control instruction set again, and so on. A closed-loop feedback is formed, so that the system can perform adaptive control to maintain the alternating electric field at a stable target level.

[0168] However, as mentioned above, even if a closed-loop feedback is formed, the system may still face problems in some cases, such as asynchronous acquisition of observation parameters, personalized requirements for optimization targets, and selection of optimization algorithms.

[0169] 5 , some embodiments of the present application further provide a system including an observation module 501 , a control module 502 , an execution module 503 and a path selection module 504 . In this case, the control module 503 includes at least two control submodules 512 .

[0170] Among them, the observation module 501 is configured to obtain observation parameters. The path selection module 504 is configured to divide each observation parameter into multiple observation parameter sets based on the characteristics of each selectively obtained observation parameter. Each control submodule 512 is configured to generate a target parameter set based on the corresponding observation parameter set, system indicator set and optimization algorithm, and generate a control weight matrix based on the target parameter set, observation parameter set, control parameter set and control algorithm, and generate a control instruction set based on the control weight matrix and control parameter set. The execution module 503 is configured to control the alternating electric field applied to the target tissue according to the control instruction set. In this embodiment, the system target set and control parameter set are shared among multiple control submodules 512.

[0171] In this way, on the basis of the system shown in Figure 1, a path selection module 504 and corresponding multiple control sub-modules 512 are also introduced. On the basis of forming a closed-loop feedback control and being able to achieve adaptive control, the hierarchical design of the above-mentioned multiple control sub-modules 512 can also support providing different control algorithms for different observation parameter sets, so that the system can respond to different types of observation data more flexibly and accurately, which is conducive to providing personalized, customized precision treatment for different patients, different treatment stages, and different working states of the system.

[0172] It should be noted that, in some examples, different control submodules 512 support different control algorithms. In some examples, different control submodules 512 maintain the same type of control algorithms with different hyperparameters. For example, different control submodules 512 all use the PID algorithm, but the three parameters of the PID algorithm are not exactly the same on different control submodules 512. In some examples, different control submodules 512 can also maintain different types of control algorithms. For example, some control submodules 512 use the PID algorithm, and other control submodules 512 use the synovial control algorithm, etc. Of course, the above is only an example explanation of the control algorithms supported by each control submodule 512. In some cases, other control algorithms besides the PID algorithm and the synovial control algorithm can also be used, which will not be described here one by one.

[0173] This embodiment does not particularly limit the criteria for the path selection module 504 to divide the observation parameters into different observation parameter sets. In some examples, a sensing parameter can only be assigned to one observation parameter set. In other examples, a sensing parameter can be assigned to multiple observation parameter sets that meet the criteria. In this case, the sensing parameters in different observation parameter sets are weighted according to the criteria. Among them, the embodiment of the present application does not limit the criteria for assigning weights, which can be set according to the importance of the sensing parameters in different observation parameter sets, or can also be set according to the ratio of the observation time corresponding to different observation parameter sets, etc.

[0174] To help those skilled in the art better understand the path selection module 504 in the system shown in Figure 5, the following will explain it. It should be noted that the rest of the system has been described in the above embodiments and will not be repeated here.

[0175] In some cases, the acquisition of observation parameters in the observation parameter set is not synchronized, and their importance varies significantly. For example, temperature data and temperature control are directly related to system safety and require more frequent monitoring, while temperature data can be obtained in a shorter period. Generally speaking, the period required to obtain temperature data can be less than 1 minute, which is relatively easy. Relatively speaking, the observation of electrical quantity data may not be so frequent, but it can also be relatively easy to obtain in a shorter period. Generally speaking, the period required for the observation and acquisition of electrical quantity data is 1-10 minutes. On the other hand, some parameters, such as imaging diagnoses such as target tissue status and diagnostic results of other patient body parameters, require a longer period to obtain, generally 1-30 days, but their importance is higher.

[0176] Based on this, in some examples, the path selection module 504 is also configured to configure the observation parameters with an observation period greater than the first period to one regulation submodule 512, and configure the observation parameters with an observation period less than the first period to another regulation submodule 512, where the observation period is the period for the observation module 501 to collect the observation parameters.

[0177] Based on this, in some examples, the path selection module 504 is also configured to configure the observation parameters with an observation period greater than the second period to one regulation sub-module 512, and configure the observation parameters with an observation period less than the third period to another regulation sub-module 512, where the observation period is the period for the observation module 501 to collect the observation parameters.

[0178] In this way, the path selection module 504 can combine long-term observation parameters and short-term observation parameters to provide long-term control functions and short-term control functions, which can not only make timely adjustments based on changes in treatment, but also improve the long-term and effective quality plan, which is conducive to stability. Among them, the embodiment of the present application does not limit whether each observation data is suitable for long-term observation, short-term observation, or both long-term and short-term observation. For example, temperature data and power data are suitable for short-term observation and can be used to activate the short-term control module path; the patient's target tissue size and imaging assessment data are suitable for long-term observation and can be used to activate the long-term control module path. That is, based on the system shown in Figure 1, the system shown in Figure 5 also proposes a path selection method to address the existing problem of asynchronous acquisition cycles (events) of various parameters. It can automatically guide the observed parameters to specific control submodules 512 according to the acquisition cycle, that is, a parameter adjustment method for long-term and short-term parameters (multi-layer control). The long-term and short-term adaptive parameter adjustment method can adopt different levels or methods of control methods according to the parameters of different acquisition cycles (such as temperature, current, impedance, power, target tissue state, etc.).

[0179] It should be noted that the relative size of the second and third cycles is not limited. In some cases, the same parameter may be used for both long-term and short-term treatment. Therefore, the second cycle can be set to be larger than the third cycle, so that some parameters can be allocated to both long-term and short-term regulation processes.

[0180] In addition to using the observation period as a criterion for path selection, in some examples, the importance of observed parameters can also be categorized and used as a criterion for path selection. Path selection module 504 is further configured to assign observation parameters with an importance level greater than a first level to one control submodule 512, and to assign observation parameters with an importance level less than a second level to another control submodule 512. The importance level is a quantitative value that quantifies the importance of observation module 501 in the control process. Similar to the above, the relationship between the first level and the second level is not limited.

[0181] In this embodiment, the control module 502 uses different pathfinding and matching mechanisms to address at least one of the issues of asynchronous acquisition of observation parameters, varying levels of importance, etc. In this way, the path selection module 504 can adjust the control method according to different needs during the treatment process, which is conducive to providing personalized treatment plans for patients.

[0182] As shown in FIG6 , some embodiments of the present application further provide a system including an observation module 601 , a control module 602 , an execution module 603 and a strategy selection module 604 .

[0183] Among them, the observation module 601 is configured to obtain observation parameters. The strategy selection module 604 is configured to determine the current control strategy from multiple control strategies. Among them, each control strategy includes the types of system indicators in the currently desired system indicator set and the relationship between them. The control module 602 is configured to generate a target parameter set based on the observation parameter set and the system indicator set corresponding to the current control strategy determined by the strategy selection module 604, as well as a preset optimization algorithm, and generate a control weight matrix based on the target parameter set, the observation parameter set, the control parameter set and the control algorithm, and generate a control instruction set based on the control weight matrix and the control parameter set. The execution module 603 is configured to control the alternating electric field applied to the target tissue according to the control instruction set.

[0184] This embodiment, based on the system shown in FIG1 , further introduces a strategy selection module 604 to obtain the currently desired system indicators and their relationships from the system indicator set, and then implements regulation in combination with the observed parameter set. In this way, while forming a closed-loop feedback control and enabling adaptive regulation, strategy selection module 604 can also support different optimization targets for different individuals, different system operating states, and different stages of treatment, facilitating personalized and precise treatment for patients at different treatment stages or in different system operating states.

[0185] In some examples, the control strategy includes different modes such as efficiency mode, energy-saving mode, and safety mode. Different modes can be preset in advance. For example, different weights are assigned to system indicators in different modes (such as efficiency mode, energy-saving mode, safety mode, etc.) to emphasize different treatment focuses). At the same time, the conversion method between modes can be planned on this basis. For example, when the device is applied to a patient who has just undergone surgery, it first enters the safety mode. After several rounds of treatment, it automatically switches to the efficiency mode, focusing on improving the efficiency of stimulation. Subsequently, when the device is in a low-power range (such as less than 20% power), it enters the energy-saving mode to increase the treatment time of the device. In this way, the treatment effect of the system can be effectively improved.

[0186] In some examples, the strategy selection module 604 may also be configured to automatically adjust the current control strategy based on changes in the first information. For example, the first information includes at least one of the following: the current treatment stage (time), the power supply status of the system, and the patient's physical condition.

[0187] In other words, the strategy selection module 604 can automatically adjust the control strategy in real time based on information such as the treatment stage, the system's power supply status and the patient's physical condition, so that the system can change the treatment method in a timely manner to better meet the current treatment needs, thereby improving the treatment effect.

[0188] In some examples, the strategy selection module 604 can also manually select the control strategy, making the control strategy adjustment more flexible. In some examples, the control strategy can also be manually adjusted, such as adding or deleting system indicators, increasing or decreasing the proportional relationship between system indicators, and forming a new pattern. In this way, the control strategy is more targeted.

[0189] To facilitate those skilled in the art to better understand the strategy selection module 604 in the system shown in Figure 6, an example will be given below to illustrate it. It should be noted that the rest of the system has been described in the above embodiments and will not be repeated here.

[0190] In some examples, by adjusting the weights of system indicators in the performance mode, different operating modes are formed, such as energy-saving mode and safety mode. These operating modes are adapted to different scenarios and needs. For example, when a patient first uses the device, the policy selection module 604 may select safety mode to start the device to prevent discomfort; when the system power supply is low, the policy selection module 604 may select energy-saving mode; and when the power supply is sufficient, the policy selection module 604 may select performance mode.

[0191] In some embodiments, the system shown in FIG5 can be organically combined with the system shown in FIG6 , that is, the system includes both a path selection module and a policy selection module. In this case, the system structure can be as shown in FIG7 . In this case, the control module can include multiple control submodules. For example, the control module can be provided with a pair of control submodules, namely a long-term control module and a short-term control module, which work together to implement a certain strategy, such as an efficiency mode. At the same time, the control strategy can also include an energy-saving mode and a safety mode. These are triggered under different conditions. For example, during the first three days of a patient's use of the system after surgery, the strategy selection module will select the safety mode control strategy (which includes short-term and long-term control). This control strategy focuses on system safety indicators and assigns higher weights and stronger constraints to system safety indicators (for example, system safety indicators must be constrained between ±0.1). After the safety observation period, the strategy selection module will select the efficiency mode control strategy, relaxing the constraints on system safety indicators, narrowing the constraints on system treatment efficiency indicators, and increasing the weight of system treatment efficiency indicators. Subsequently, if the system is determined to be low on power, the strategy selection module will select the energy-saving mode control strategy, which relaxes the constraints on system treatment efficiency indicators and reduces their weights, while narrowing the constraints on system energy-saving indicators and increasing their weights. In different modes, the path selection module selectively sends each observation parameter to the long-term control module or short-term control module that receives the control strategy corresponding to the current mode, depending on whether the observation parameter is a long-term or short-term parameter.

[0192] To help those skilled in the art better understand the system provided by the above embodiment, examples will be given below in combination with specific application scenarios.

[0193] Assuming that the patient is sensitive to temperature, the patient's safe temperature range is set to 36°C-40°C. The working capabilities of the tumor treatment field system include: supporting temperature observation every one minute (i.e., confirming the current temperature once every minute), power consumption observation every five minutes (confirming the current power consumption every five minutes), and evaluating changes in the state of target tissue once a month. It is assumed that the system has an initial power of 500mAh, 5 electrodes are provided, and each electrode consumes 10mAh per hour after being turned on. The parameters it supports for regulating the alternating electric field include current, electrode posture, and the number of electrodes turned on. The target tissue is a tumor.

[0194] In addition, the calculation method of the system indicators is set as follows:

[0195] Efficacy index: measured by the first derivative of tumor volume, obtained from CT scan.

[0196] The safety index and energy-saving index are calculated using the calculation method provided in the above embodiments.

[0197] The control module provides two control sub-modules: a long-term module (based on long-term observation of target tissue status such as tumor volume) and a short-term module (based on short-term observation of temperature and power).

[0198] The optimization algorithm used in the control module is the particle swarm optimization algorithm, and the control algorithm is the PID algorithm.

[0199] The strategy selection module has three preset modes: safety mode, performance mode, and energy-saving mode. In safety mode, the weighted ratio of the three indicators is: system treatment efficacy index: system safety index: system energy-saving index = 1:2:1; in performance mode, the weighted ratio of the three indicators is: system treatment efficacy index: system safety index: system energy-saving index = 2:1:1; and in energy-saving mode, the weighted ratio of the three indicators is: system treatment efficacy index: system safety index: system energy-saving index = 1:1:2. Furthermore, the selection strategy between the three modes is as follows: the first three days are a safety observation period, the performance mode is used in normal conditions, and the energy-saving mode is used in low-battery conditions.

[0200] On days 1-3, the strategy selection module instructed the control module to adopt the safe mode control strategy. Therefore, after the system was turned on, the PID control parameters for the short-term path and the long-term PID parameters were assigned, and the system entered safe mode, turning on the three electrodes. Subsequently, the short-term observation parameters were observed: the temperature was 39°C, within the safe range, and the battery was fully charged. Therefore, the strategy selection module no longer needed to switch to energy-saving mode. The control module then obtained the system indicator set and calculated the various system indicators: system safety indicator Q = 2 / 37, system treatment efficacy indicator H = dV / dt = -6cm 3 / month (assuming the tumor size is shrinking), system energy saving index Based on the current safety mode's indicator set and weights (i.e., 1:2:1), the optimization goal is to reduce Q and N while minimizing dV / dt. A particle swarm optimization algorithm is used to calculate the short-term control objectives, resulting in a control instruction set of {current intensity: 8mA, electrode position: unchanged, number of electrodes open: 3}. The execution module then responds to the control instruction set by reducing the current to 8mA. The adjustments are continuously monitored.

[0201] On the third day of treatment, the strategy selection module instructs the control module on the efficacy mode control strategy, so all five electrodes will be turned on. Observation parameters include: tumor volume V = 20 cm 3 Therefore, the system security index is updated to (Assuming the average temperature of the five electrodes is 38°C); the system treatment efficacy index is updated to H = dV / dt = -3cm 3 / month; the system energy saving index is updated to Furthermore, a control instruction set is generated to increase the current to 12 mA and adjust the position of the electrode at the same time, so as to improve the tumor suppression effect after the patient adapts.

[0202] On the eighth day of treatment, the observation parameters observed by the observation module include: the battery level is 100mAh, which is less than 20%. As the battery level decreases, the strategy selection module instructs the control module to adopt the energy-saving mode control strategy. At this time, the calculated optimization targets are: Q = 0.03, H = -0.08, N = 60 / (30*2.5). Therefore, under the guidance of the energy-saving mode control strategy, the control module obtains the control instruction set of {current intensity: 8mA, electrode posture: unchanged, number of electrodes turned on: 3}. Therefore, the execution module will turn off two electrodes, reduce the current to 6mA, and adjust the position of the electrodes to maintain the therapeutic effect. And continue to observe and adjust.

[0203] On the 10th day of treatment, the observation module observed the following parameters: the battery level is 300 mAh, which has recovered to 60%. Therefore, the strategy selection module indicates the efficiency mode control strategy to the control module. In addition, the observation module observed the following observation parameters: tumor volume V = 28 cm 3 , first-order derivative H=dV / dt=-6cm 3 / month. Q = 0.01, H = -0.2, N = 18 / (28*1); therefore, under the guidance of the efficacy mode control strategy, the resulting control instruction set is {current intensity: 12mA, electrode position: optimized, number of electrodes turned on: 5}. Therefore, the execution module will turn on all five electrodes, maintain the current at 12mA, and fine-tune the electrode positions to further optimize the therapeutic effect.

[0204] Thus, it can be seen that the system provided by the embodiment of the present application uses a variety of observation parameters (for example, from multiple sets of sensors or diagnosis and treatment reports) to represent the multi-dimensional information of the patient and the system, and according to the information analysis results, closes the loop and adaptively adjusts the parameters related to the alternating electric field to achieve dynamic and intelligent control of the system. On this basis, an adaptive path selection module and a strategy selection module are proposed to address the problems of asynchronous acquisition of observation parameters and personalized treatment needs, which solve the special problems encountered by the closed-loop system under the conditions of the tumor treatment field, and achieve a comprehensive improvement in the accuracy, safety and effectiveness of the treatment. Specifically, accurate means that the alternating electric field can be regulated in real time according to the changes in the patient's specific physical condition, so that the alternating electric field can act on the target tissue cells more accurately. Safe means that the alternating electric field can be balanced according to the influence of the alternating electric field, so that the alternating electric field can distribute and control its energy more evenly, thereby reducing damage to normal cells. Effective means that the alternating electric field can be flexibly adjusted according to different needs and conditions, so that the alternating electric field can be more adapted to different treatment modes and durations.

[0205] In addition, energy conservation can be achieved by selecting different modes. That is, the system's operating mode can be changed based on primary information such as power level and temperature, allowing the alternating electric field to consume electricity more economically and reduce the use of accessories. Stability means that the system's operating conditions can be monitored based on observation parameters such as impedance and temperature, and parameters related to the alternating electric field can be fed back and adjusted in a timely manner, allowing the alternating electric field to be output and transmitted more stably. Personalization means that the system's target state can be set based on treatment plans, imaging diagnoses, etc., and parameters related to the alternating electric field can be adaptively adjusted based on data from multiple sensors, allowing the alternating electric field to more intelligently control the treatment of target tissues.

[0206] It is worth mentioning that the modules involved in the above embodiments are all logical modules. In actual applications, a logical unit can be a physical unit, a part of a physical unit, or a combination of multiple physical units. In addition, to highlight the innovation of this application, this embodiment does not introduce units that are not closely related to solving the technical problems proposed by this application. However, this does not mean that other units do not exist in this embodiment.

[0207] As shown in FIG8 , some embodiments of the present application further provide a method for controlling a tumor treatment field system. The tumor treatment field system includes an observation module, a control module, and an execution module. The method includes the following steps:

[0208] Step 801: The observation module obtains observation parameters.

[0209] Among them, the observation parameters are used to characterize the treatment status.

[0210] In step 802 , the control module periodically obtains at least part of the observation parameters, constructs an observation parameter set, and generates a target parameter set according to the observation parameter set, a preset system indicator set, and a preset optimization algorithm.

[0211] In step 803 , the control module generates a control weight matrix according to the target parameter set, the observation parameter set, the preset control parameter set and the preset control algorithm.

[0212] Among them, the system indicator set is used to reflect the performance indicators of the tumor treatment field system, the target parameter set is used to represent the specific values ​​of the expected parameters of the tumor treatment field system, the control parameter set is the parameter composition of the controllable alternating electric field, and the control weight matrix is ​​used to represent the quantitative values ​​that need to be controlled for each parameter in the control parameter set.

[0213] Step 804: The control module generates a control instruction set according to the control weight matrix and the control parameter set.

[0214] Step 805: The execution module regulates the alternating electric field applied to the target tissue according to the regulation instruction set.

[0215] The data flow and processing shown in Figure 8 is shown in Figure 9. The relevant features are described in the previous system embodiment. The data flow process corresponds to the working mechanism of the tumor treatment field system described in the previous system embodiment and will not be described in detail here.

[0216] The steps of the various methods above are divided only for the purpose of clear description. During implementation, they can be combined into one step or some steps can be split and decomposed into multiple steps. As long as they include the same logical relationship, they are all within the scope of protection of this patent. Adding insignificant modifications or introducing insignificant designs to the algorithm or process without changing the core design of the algorithm and process are all within the scope of protection of this patent.

[0217] It is not difficult to find that this embodiment is a method embodiment corresponding to the system embodiment, and this embodiment can be implemented in conjunction with the system embodiment. The relevant technical details mentioned in the system embodiment are still valid in this embodiment, and to reduce repetition, they are not repeated here. Accordingly, the relevant technical details mentioned in this embodiment can also be applied to the system embodiment.

[0218] Those skilled in the art will appreciate that the above embodiments are specific embodiments for implementing the present application, and that in actual applications, various changes may be made thereto in form and detail without departing from the spirit and scope of the present application.

Claims

1. A tumor treatment field system, comprising: An observation module configured to obtain observation parameters, where the observation parameters are used to characterize the treatment state; A regulation module configured to periodically obtain at least some of the observation parameters as an observation parameter set, and generate a target parameter set according to the observation parameter set, a preset system index set, and a preset optimization algorithm. According to the target parameter set, the observation parameter set, a preset regulation parameter set, and a preset control algorithm, generate a regulation weight matrix, and generate a regulation instruction set according to the regulation weight matrix and the regulation parameter set. Wherein, the system index set is used to reflect the performance indicators of the tumor treatment field system, the target parameter set is used to represent the specific numerical values of the expected parameters of the tumor treatment field system, the regulation parameter set is composed of the parameters that the tumor treatment field system allows to regulate the alternating electric field, and the regulation weight matrix is used to characterize the quantization value of each parameter in the regulation parameter set that needs to be regulated; An execution module configured to regulate the alternating electric field applied to the target tissue according to the regulation instruction set.

2. The tumor treatment field system according to claim 1, wherein The expression of the optimization algorithm is as follows: minimize f(B)=C(G1(A,B),G2(A,B),...,G k (A,B)) subject to h(A,B)≤0, G1(A,B), G2(A,B),..., G k (A,B) ∈ S1, A,B∈S2, Among them, f(B) represents the function corresponding to the optimization objective, k represents the number of the system indicators included in the system indicator set, and G i (A,B) represents the i-th system indicator, and C(G1(A,B), G2(A,B),..., G k (A,B)) represents a preset function for obtaining a comprehensive system indicator from each of the system indicators. A represents the set of observation parameters, B represents the set of target parameters, h(A,B) is a preset constraint function regarding A and B, S1 represents the feasible region of the calculated values of each of the system indicators, and S2 represents the feasible region of the observation parameters in the preset set of observation parameters and the target parameters in the set of target parameters.

3. The tumor treatment field system according to claim 2, wherein The iteration methods of the optimization algorithm include: particle swarm optimization algorithm, genetic algorithm, or simulated annealing algorithm.

4. The tumor treatment field system according to any one of claims 1 to 3, wherein The control algorithm is a PID control algorithm or a sliding mode control algorithm.

5. The tumor treatment field system according to any one of claims 1 to 4, wherein The execution module includes an alternating electric field generation circuit and electrodes arranged around the target tissue. The alternating electric field generation circuit is used to generate a corresponding alternating electric field according to the regulation instruction set and apply it to the target tissue through the electrodes.

6. The tumor treatment field system according to claim 5, wherein The execution module further includes a driver, and the driver is used to drive the electrodes according to the regulation instruction set to adjust the pose of the electrodes.

7. The tumor treatment field system according to claim 5 or 6, wherein The execution module is further configured to send the manual regulation instruction to the outside when the regulation instruction set includes a manual regulation instruction.

8. The tumor treatment field system according to any one of claims 1 to 7, wherein The regulation module includes: A first storage unit configured to store the regulation parameter set; A second storage unit configured to store the system index set; A calculation unit, configured to generate the target parameter set according to the set of observation parameters, the set of system metrics obtained from the second storage unit, and the optimization algorithm, and generate the regulation weight matrix according to the target parameter set, the set of observation parameters, the set of regulation parameters read from the first storage unit, and the control algorithm, and generate and output the set of regulation instructions according to the regulation weight matrix and the set of regulation parameters read from the first storage unit.

9. The tumor treatment field system according to any one of claims 1 to 8, wherein the observation parameters include at least one of the following information: temperature, current, electrode state, duty cycle, intensity of the alternating electric field, alternating electric field change frequency, target tissue state, and impedance of the target tissue; the regulation parameters include at least one of the following information: current, alternating electric field frequency, alternating electric field intensity, duty cycle, electrode selection; the system metrics include at least one of the following information: system safety metric, system energy saving metric, system treatment efficacy metric, system adaptability metric.

10. The tumor treatment field system according to any one of claims 1 to 9, wherein, It further includes: a path selection module, and the regulation module includes at least two regulation sub-modules; the path selection module, configured to divide each of the observation parameters into multiple sets of observation parameters according to the characteristics of each selectively obtained observation parameter; each of the regulation sub-modules is configured to generate the target parameter set according to the corresponding set of observation parameters, the set of system metrics, and the optimization algorithm, and generate the regulation weight matrix according to the target parameter set, the obtained set of observation parameters, the set of regulation parameters, and the control algorithm, and generate the set of regulation instructions according to the regulation weight matrix and the set of regulation parameters.

11. The tumor treatment field system according to claim 10, wherein the path selection module is further configured to configure the observation parameters with an observation period greater than a first period to one of the regulation sub-modules, and configure the observation parameters with an observation period less than the first period to another regulation sub-module, and the observation period is the period for the observation module to collect the observation parameters.

12. The tumor treatment field system according to claim 10 or 11, wherein the path selection module is further configured to configure the observation parameters with an observation period greater than a second period to one of the regulation sub-modules, and configure the observation parameters with an observation period less than a third period to another regulation sub-module, and the observation period is the period for the observation module to collect the observation parameters.

13. The tumor treatment field system according to any one of claims 10 to 12, wherein the path selection module is further configured to configure the observation parameters with an importance level greater than a first level to one of the regulation sub-modules, and configure the observation parameters with an importance level less than a second level to another regulation sub-module, and the importance level is a quantified value of the importance of the observation module in the regulation process.

14. The tumor treatment field system according to any one of claims 10 to 13, wherein the control algorithms corresponding to different regulation sub-modules are different.

15. The tumor treatment field system according to any one of claims 1 to 14, wherein It further includes: A strategy selection module; The strategy selection module is configured to determine the current regulation strategy from multiple regulation strategies, where the regulation strategy includes the types of system indicators in the currently desired system indicator set and the relationships between them; The regulation module is configured to generate the target parameter set according to the observation parameter set, the system indicator set corresponding to the current regulation strategy determined by the strategy selection module, and a preset optimization algorithm, and generate the regulation weight matrix according to the target parameter set, the observation parameter set, the regulation parameter set, and the control algorithm. Generate the regulation instruction set according to the regulation weight matrix and the regulation parameter set and output it.

16. The tumor treatment field system according to claim 15, wherein, The strategy selection module is further configured to automatically adjust the current regulation strategy according to the change of the first information, and the first information includes at least one of the following information: the treatment stage where the current patient is located, the power supply state of the tumor treatment field system, and the patient's physical condition.

17. A regulation method for a tumor treatment field system, the tumor treatment field system includes an observation module, a regulation module, and an execution module, and the method includes: The observation module obtains observation parameters, where the observation parameters are used to characterize the treatment state; The regulation module periodically obtains at least part of the observation parameters, constructs an observation parameter set, and generates a target parameter set according to the observation parameter set, a preset system indicator set, and a preset optimization algorithm; The regulation module generates a regulation weight matrix according to the target parameter set, the observation parameter set, a preset regulation parameter set, and a preset control algorithm, where the system indicator set is used to reflect the performance indicators of the tumor treatment field system, the target parameter set is used to represent the specific numerical values of the expected parameters of the tumor treatment field system, the regulation parameter set is composed of the parameters of the adjustable alternating electric field, and the regulation weight matrix is used to characterize the quantization values of the parameters in the regulation parameter set that need to be regulated; The regulation module generates a regulation instruction set according to the regulation weight matrix and the regulation parameter set; The execution module regulates the alternating electric field applied to the target tissue according to the regulation instruction set.

Images