CN117797405A

CN117797405A - Tumor treatment field system and regulation and control method thereof

Info

Publication number: CN117797405A
Application number: CN202311868514.4A
Authority: CN
Inventors: 王译; 王友好; 赵瑞麟; 边英男
Original assignee: Yingmai Medical Technology Shanghai Co ltd
Current assignee: Yingmai Medical Technology Shanghai Co ltd
Priority date: 2023-12-29
Filing date: 2023-12-29
Publication date: 2024-04-02

Abstract

The embodiment of the application relates to the technical field of medical equipment and discloses a tumor treatment field system and a regulation and control method thereof. The system comprises: an observation module configured to obtain observation parameters; the regulation and control module is configured to periodically acquire at least part of observation parameters as an observation parameter set, generate a target parameter set according to the observation parameter set, a preset system index set and a preset optimization algorithm, generate a regulation and control weight matrix according to the target parameter set, the observation parameter set, the preset regulation and control parameter set and a preset control algorithm, and generate a regulation and control instruction set according to the regulation and control weight matrix and the regulation and control parameter set; and the execution module is configured to regulate and control the alternating electric field applied to the target tissue according to the regulation and control instruction set. At least is beneficial to improving the flexibility and the treatment effect of the treatment scheme of the tumor treatment field system by realizing the self-adaptive regulation and control of the tumor treatment field system.

Description

Tumor treatment field system and regulation and control method thereof

Technical Field

The embodiment of the application relates to the technical field of medical equipment, in particular to a tumor treatment field system and a regulating and controlling method thereof.

Background

Tumor therapy fields (Tumor Treating Fields, TTFields) are an emerging anti-tumor technique for the treatment of Glioblastoma (GBM), recurrent Glioblastoma, and malignant pleural mesothelioma (Malignant Pleural Mesothelioma, MPM) for new diagnosis and show promising efficacy and safety in clinical trials. Clinical trials of tumor therapy fields are continually expanding to other types of cancer, as well as exploring combinations with other therapies. As an innovative cancer treatment technology, the novel cancer treatment technology has the advantages of high safety, small side effect, easy operation and the like, and provides a new hope for improving prognosis of GBM and other malignant tumor patients. The basic principle is to apply biophysical forces to charged and polarized molecules (called dipoles), through which various biological processes are affected, including mitosis, DNA repair, cell permeability, and immune responses, thereby inhibiting the growth and division of cancer cells, resulting in therapeutic effects.

However, current modulation of tumor treatment field devices is primarily using an open loop modulation mode. For example, the electric field parameters are adjusted and fixed by the doctor until the next review is readjusted again; still other oncology therapy field devices have parameters that are either triggered by setting specific conditions or rely on the performance of the examination results to adjust, lack of effective feedback and adjustment mechanisms during the course of therapy, are not adaptively adjustable, are not flexible enough, and are not properly adjustable according to the patient's instantaneous or long-term state changes. Thus, the therapeutic effect of these tumor treatment field devices has not yet been well expected.

Disclosure of Invention

The embodiment of the application provides a tumor treatment field system and a regulation and control method thereof, which are at least beneficial to improving the flexibility and the treatment effect of a treatment scheme of the tumor treatment field system by realizing the self-adaptive regulation and control of the tumor treatment field system.

According to some embodiments of the present application, there is provided in one aspect a tumor treatment field system comprising: an observation module configured to obtain an observation parameter, wherein the observation parameter is used for characterizing a treatment state; the regulation and control module is configured to periodically acquire at least part of the observation parameters as an observation parameter set, generate a target parameter set according to the observation parameter set, a preset system index set and a preset optimization algorithm, generate a regulation and control weight matrix according to the target parameter set, the observation parameter set, a preset regulation and control parameter set and a preset control algorithm, and generate a regulation and control instruction set according to the regulation and control weight matrix and the regulation and control parameter set, wherein the system index set is used for reflecting indexes of the system performance of the tumor treatment field, the target parameter set is used for representing specific values of expected parameters of the tumor treatment field system, the regulation and control parameter set is formed by parameters of the tumor treatment field system which allow regulation and control of an alternating electric field, and the regulation and control weight matrix is used for representing quantized values of each parameter in the regulation and control parameter set which needs regulation and control; and the execution module is configured to regulate and control the alternating electric field applied to the target tissue according to the regulation and control instruction set.

In some embodiments, the expression of the optimization algorithm is as follows: minimum f (B) =c (G ₁ (A，B)，G ₂ (A，B)，……，G _k (A，B))subject to h(A，B)≤0，G ₁ (A，B)，G ₂ (A，B)，……，G _k (A，B)∈S ₁ ，A，B∈S ₂ Wherein f (B) represents an optimization objective function, k represents the number of the system indexes contained in the system index set, G _i (A, B) represents the ith system index, C represents a preset function of deriving a comprehensive system index from each of the system indexes, A represents the observation parameter set, B represents the target parameter set, h (A, B) is a preset constraint function about A and B, S ₁ A calculated value feasible region representing each system index S ₂ Representing a feasible domain of the observed parameters in the preset observed parameter set and the target parameters in the target parameter set; iterative method of the optimization algorithmThe formula comprises: particle swarm optimization algorithms, genetic algorithms, or simulated annealing algorithms.

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

In some embodiments, the execution module includes an alternating electric field generation circuit for generating a corresponding alternating electric field according to the set of regulatory instructions and applying to the target tissue through the electrodes disposed about the target tissue.

In some embodiments, the execution module further comprises a driver for driving the electrode according to the set of regulatory instructions to adjust the pose of the electrode.

In some embodiments, the execution module is further configured to send the manual regulation instructions to the outside if the regulation instruction set contains manual regulation instructions.

In some embodiments, the regulation module comprises: a first storage unit configured to store the regulation parameter set; a second storage unit configured to store the system index set; and a calculation unit configured to generate the target parameter set according to the observation parameter set, the system index set acquired from the second storage unit, and the optimization algorithm, generate the regulation weight matrix according to the target parameter set, the observation parameter set, the regulation parameter set read from the first storage unit, and the control algorithm, generate the regulation instruction set according to the regulation weight matrix and the regulation parameter set read from the first storage unit, and output.

In some embodiments, the observed parameter includes at least one of the following information: temperature, current, electrode state, duty cycle, intensity of alternating electric field, frequency of alternating electric field variation, target tissue state, and impedance of target tissue; the regulatory parameters include at least one of the following information: current, alternating electric field frequency, alternating electric field intensity, duty cycle, electrode status; the system index includes at least one of the following information: system safety index, system energy saving index, system therapeutic efficacy index, and system adaptability index.

In some embodiments, the path selection module and the regulation module comprises at least two regulation sub-modules; the path selection module is configured to divide each observation parameter into a plurality of observation parameter sets according to the characteristics of each observation parameter which is selectively acquired; each regulation and control submodule is configured to generate the target parameter set according to the corresponding observation parameter set, the system index set and the optimization algorithm, generate the regulation and control weight matrix according to the target parameter set, the acquired observation parameter set, the regulation and control parameter set and the control algorithm, and generate the regulation and control instruction set according to the regulation and control weight matrix and the regulation and control parameter set.

In some embodiments, the path selection module is further configured to configure an observation parameter with an observation period greater than a first period to one of the regulation sub-modules, and configure an observation parameter with an observation period less than the first period to another of the regulation sub-modules, where the observation period is a period in which the observation module collects the observation parameter.

In some embodiments, the path selection module is further configured to configure the observation parameter with an observation period greater than the second period to one of the regulation sub-modules, and configure the observation parameter with an observation period less than the third period to another of the regulation sub-modules, where an observation period is a period in which the observation module collects the observation parameter.

In some embodiments, the path selection module is further configured to configure the observation parameters with importance levels greater than a first level to one of the regulation sub-modules and configure the observation parameters with importance levels less than a second level to another of the regulation sub-modules, the importance levels being quantized values of importance of the observation modules in a regulation process.

In some embodiments, the control algorithms corresponding to different regulation sub-modules are different.

In some embodiments, the policy selection module; the strategy selection module is configured to determine a current regulation strategy from a plurality of regulation strategies, wherein the regulation strategies comprise types and mutual relations of currently expected system indexes in the system index set; the regulation and control module is configured to generate the target parameter set according to the system index set corresponding to the current regulation and control strategy determined by the observation parameter set and the strategy selection module and a preset optimization algorithm, generate the regulation and control weight matrix according to the target parameter set, the observation parameter set, the regulation and control parameter set and the control algorithm, generate the regulation and control instruction set according to the regulation and control weight matrix and the regulation and control parameter set and output the regulation and control instruction set.

In some embodiments, the policy selection module is further configured to automatically adjust the current regulatory policy based on a change in a first information comprising at least one of: the current treatment stage, the power supply state of the tumor treatment field system and the physical condition of the patient.

According to some embodiments of the present application, there is also provided a method for controlling a tumor treatment field system according to another aspect of the embodiments of the present application, including: obtaining observation parameters, wherein the observation parameters are used for representing treatment states; periodically acquiring at least part of the observation parameters, constructing an observation parameter set, and generating a target parameter set according to the observation parameter set, a preset system index set and a preset optimization algorithm; generating a regulation weight matrix according to the target parameter set, the observation parameter set, a preset regulation parameter set and a preset control algorithm, wherein the system index set is used for reflecting the system performance index of the tumor treatment field, the target parameter set is used for representing a specific value of an expected parameter of the tumor treatment field system, the regulation parameter set is formed by parameters of a regulatable alternating electric field, and the regulation weight matrix is used for representing quantized values of all parameters in the regulation parameter set to be regulated; generating a regulation instruction set according to the regulation weight matrix and the regulation parameter set; and regulating and controlling the alternating electric field applied to the target tissue according to the regulating and controlling instruction set.

The technical scheme provided by the embodiment of the application has at least the following advantages:

the regulation and control module obtains a target parameter set representing a specific value of the system expected parameter according to an optimization algorithm based on an observation parameter set formed by an observation result of the observation module, further obtains a regulation and control weight matrix by combining the observation parameter set, a regulation and control parameter set representing parameters capable of actually regulating and controlling the alternating electric field and a control algorithm, and obtains a regulation and control instruction set according to the regulation and control weight matrix and the regulation and control parameter set so as to regulate and control the alternating electric field applied to target tissues (such as tumor tissues, a tumor removal cavity and tissues nearby by the execution module). Therefore, the system fully considers the internal relation among various expected indexes, observation parameters and regulation parameters, so that the regulation and control of the alternating electric field applied to the target tissue are more scientific, accurate and efficient. The observation module also continuously and autonomously acquires various observation parameters capable of representing the current treatment state, and the regulation and control module periodically acquires the observation parameters to correspondingly adjust. Therefore, the observation data set can be used as feedback for treatment results to influence the generation of the regulation and control instruction set, thereby forming closed-loop control and realizing self-adaptive regulation and control.

Drawings

One or more embodiments are illustrated by way of example and not limitation in the figures of the accompanying drawings, in which like references indicate similar elements, and in which the figures of the drawings are not to be taken in a limiting sense, unless otherwise indicated.

FIG. 1 is a schematic diagram of one configuration of a tumor treatment field system provided in an embodiment of the present application;

FIG. 2 is a schematic diagram of a control module in a tumor treatment field system provided in an embodiment of the present application;

FIG. 3 is a schematic diagram of a configuration of an execution module in a tumor treatment field system provided in an embodiment of the present application;

FIG. 4 is another schematic structural view of an execution module in the tumor treatment field system provided in an embodiment of the present application;

FIG. 5 is another schematic structural view of a tumor treatment field system provided in an embodiment of the present application;

FIG. 6 is a schematic diagram of yet another configuration of a tumor treatment field system provided in an embodiment of the present application;

FIG. 7 is a schematic diagram of yet another configuration of a regulatory module in a tumor treatment field system provided in an embodiment of the present application;

FIG. 8 is a flow chart of a regulation method provided in an embodiment of the present application;

Fig. 9 is a flow chart of processing of data related to the regulation method shown in fig. 8 provided in an embodiment of the present application.

Detailed Description

For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the embodiments of the present application will be described in detail below with reference to the accompanying drawings. However, as will be appreciated by those of ordinary skill in the art, in the various embodiments of the present application, numerous technical details have been set forth in order to provide a better understanding of the present application. However, the technical solutions claimed in the present application can be implemented without these technical details and with various changes and modifications based on the following embodiments.

The following embodiments are divided for convenience of description, and should not be construed as limiting the specific implementation of the present application, and the embodiments may be mutually combined and referred to without contradiction.

Some embodiments of the present application provide a tumor treatment field system, as shown in fig. 1, comprising: an observation module 101, a regulation module 102 and an execution module 103. It should be noted that, at least part of the modules of the tumor treatment field system provided in the embodiments of the present application may be located inside a human body, for example, the execution module 103 is disposed in the body at a position adjacent to glioblastoma by implantation; the tumor treatment field device provided in the embodiment of the present application may also be located entirely outside the human body, similar to a conventional tumor treatment field system, for example, the execution module 103 is disposed outside the body, and the generated alternating electric field is applied to the position of the glioblastoma corresponding to the outside of the body.

Wherein, the observation module 101 is configured to obtain observation parameters; the regulation and control module 102 is configured to periodically acquire at least part of the observation parameters as an observation parameter set, generate a target parameter set according to the observation parameter set, a preset system index set and a preset optimization algorithm, generate a regulation and control weight matrix according to the target parameter set, the observation parameter set, the preset regulation and control parameter set and a regulation and control instruction set according to the regulation and control weight matrix and the regulation and control parameter set, and the execution module 103 is configured to regulate and control the alternating electric field applied to the target tissue according to the regulation and control instruction set.

In this way, the regulation module 102 obtains a target parameter set representing a specific value of a desired parameter of the system according to the optimization algorithm based on an observation parameter set formed by the observation result of the observation module 101, and further obtains a regulation weight matrix by combining the observation parameter set, a regulation parameter set representing a parameter capable of actually regulating the alternating electric field and the control algorithm, and obtains a regulation instruction set according to the regulation weight matrix and the regulation parameter set, so as to regulate the alternating electric field applied to the target tissue (for example, tumor tissue, tumor removal cavity and tissues nearby) through the execution module 103. Therefore, the system fully considers the internal relation among various expected indexes, observation parameters and regulation parameters, so that the regulation and control of the alternating electric field applied to the target tissue are more scientific, accurate and efficient. The observation module 101 also obtains various observation parameters capable of representing the current treatment state constantly and autonomously, and the regulation and control module 102 periodically obtains the observation parameters to adjust accordingly. Therefore, the observation data set can be used as feedback for treatment results to influence the generation of the regulation and control instruction set, thereby forming closed-loop control and realizing self-adaptive regulation and control.

The system shown in fig. 1 will be explained below for the sake of a better understanding of those skilled in the art.

In the observation module 101, the acquired observation parameters are parameters for characterizing a treatment state, wherein the treatment state may include a state of a tumor treatment field system, a state of a patient (including a state of a target tissue). The number and the specific content of the observed parameters are not limited in this embodiment, and may be any parameter capable of reflecting the current treatment state of the patient. Accordingly, the specific type of the observation module 101 is not particularly limited, and may be a diagnostic device, such as CT, X-ray, and a sensor, such as a temperature sensor, a current sensor, a voltage sensor, an electric field intensity sensor, a pose sensor, and the like, which are located outside the body. These sensors may be provided in the body or may be provided outside the body.

In some examples, the observed parameter includes at least one of the following information: temperature, current, electrode state, duty cycle, alternating electric field strength, alternating electric field change frequency, target tissue state, and target tissue impedance.

Specifically, the temperature may be the temperature of the electrode tissue interface and surrounding tissue obtained by one or more temperature sensors disposed on the electrodes, so as to monitor the thermal effect during treatment by the temperature, and/or the temperature of the system obtained by one or more temperature sensors disposed on the circuit board or the stimulator housing, so that the control system operates within a safe and effective range. The current may be a current through the electrodes to reflect the alternating electric field output. The electrode status may be a record of the number of electrodes activated to participate in the treatment and their spatial pose. The duty cycle may be the ratio of the electrode stimulation time to the stop time in order to reflect the intermittence of the alternating electric field output. Wherein the duty cycle indicates that the electrode is intermittently stopped for a period of time without generating an electric field during each therapeutic stimulation period, so that the temperature can be regulated by controlling the electric field. The alternating electric field strength may be the strength of the alternating electric field near the target tissue or the strength of the alternating electric field near the electrode. The alternating electric field variation frequency may be a modulation of the alternating electric field frequency. The target tissue state can be the position, form and volume change condition of the target tissue judged by a medical image mode. The impedance of the target tissue may be an impedance obtained by the target tissue under ac excitation, the impedance value also reflecting the state of the target tissue to some extent.

Of course, the above is merely an exemplary illustration of the observed parameter, and in some examples, the observed parameter may further include physiological detection data of the patient, such as blood pressure, heartbeat, etc., which will not be described herein.

In some examples, the time required for the observation module 101 to obtain the above observations is inconsistent. Different observation parameters, the length of the observation period required to obtain the observation result is inconsistent. For example, the observation of temperature is instantaneous, and the volume change of the target tissue requires days or months.

In other examples, the frequency of periodic acquisitions of the regulatory module 102 for different observed parameters is not the same. The frequency of acquisition depends on the one hand on the time required for the observation described above and on the other hand on the importance of the observation parameters. That is, the regulation and control module 102 can periodically obtain a plurality of observation parameters, as a multi-dimensional observation parameter set, can be more beneficial to attaching the period of different observation parameters, which needs to be observed, and make relevant adjustment in time, so that a regulation and control strategy suitable for the current treatment state can be made, and a better treatment effect is achieved. And the multidimensional observation parameter set is favorable for supporting multidimensional regulation and control decisions, thereby supporting diversified regulation and control modes and providing personalized and customized treatment schemes for different patients, different treatment stages and different working states of the tumor treatment field device.

Further, in the present embodiment, the system index in the regulatory module 102 may be an index for reflecting the system performance of the tumor treatment field. The system index set is the set of system indexes. The system index is the optimization target of closed loop control of the system. Each system index has a target regulatory range. The number and the specific content of the system indexes are not limited in this embodiment.

In some examples, the system indicator includes at least one of the following information: system safety index, system energy saving index, system therapeutic efficacy index, and system adaptability index.

Specifically, the system safety index may reflect an index of a safety level during treatment, and may be synthesized by a plurality of parameters, such as an electrode temperature, an alternating electric field strength, a current magnitude, and the like. The system safety index may be expressed by a negative correlation with temperature and current, i.e. the lower the temperature and current, the higher the system safety index, for example. The energy saving index of the system may be an index reflecting the energy consumption level of the system, for example, considering parameters such as current, voltage, duty ratio and the like required by the generation of the alternating electric field, or considering factors such as the energy consumption level of the system in the case of unit target organization and unit alternating electric field intensity, or considering factors such as the current available electric quantity of the system, the residual running time estimation, the current energy consumption level and the like. The system treatment efficacy index may be an index reflecting the effect of treatment, for example, coverage rate and intensity of the alternating electric field on a tumor area, and sometimes, tumor volume change, tumor electrophysiological parameters and the like can be comprehensively considered, or alternating electric field intensity, stimulation time and the like of target tissues are considered. The system adaptability index can be an index reflecting the adaptability of the system to different treatment modes and conditions, and parameters such as the change range, the change rate, the change frequency and the like of the related parameters of the alternating electric field can be considered.

It should be noted that, the present embodiment is not limited to the calculation mode of the system index, and the system index may be an index defined by a doctor and obtained by a certain calculation of a plurality of observation parameters, or may be defined according to some experimental study tests.

In order to facilitate a better understanding of the system provided by the present embodiment, some calculation modes of the system indexes will be exemplified below, but this does not mean that the present embodiment must include and only includes the system indexes defined in the following calculation modes.

1. The calculation mode of the system safety index is as follows:

wherein Q is a system security index, n is the number of parameters, x _i Is the real-time value of the ith parameter, x _i Is the median value, k, of the safe range of the ith parameter _i Represents the weight and Σk _i ＝1。

In one example, n=3, i.e. a total of 3 observed parameters including temperature, current and alternating electric field strength. Wherein the parameter temperature x ₁ By observing the electrodes, the real-time value is 35 ℃ and the safety range is 30 ℃ to 40 ℃, x ₁ =35 ℃; parameter alternating electric field strength x ₂ Obtained by observing the surrounding of the target tissue, the real-time value is 2V/cm, the safety range is 1V/cm to 3V/cm, then x ₂ =2v/cm; parameter current x ₃ Obtained by observing the electrodes, the real-time value is 0.5A, the safety range is 0.4A to 0.6A, thenAnd->

Thus, current system security indicators are:

in the above formula, it is typically understood that a Q value of 0 represents complete safety of the system, a positive value of Q represents overshoot of the system parameter value, and a negative value of Q represents imbalance of the system parameter value. Meanwhile, whether the system parameters are within the safety range or not needs to be traversed and inquired, if the system parameters are beyond the safety range, the system starts emergency measures and performs intervention on the parameters outside the range.

In another example, the temperature t and the current I obtained from the electrode are taken as parameters, and after the temperature t and the current I are subjected to dimensionality treatment, such as averaging, min-max conversion, Z-score conversion and the like, the reciprocal is taken and weighted to obtain the system safety index Q. I.e.Wherein k is ₁ ，k ₂ Representing weights for adjusting the impact weight of temperature and current on the system safety index, Σk _i ＝1；ω ₁ ，ω ₂ To scale the coefficients to avoid one of the temperature t and the current I being too large, resulting in the effect of the other being ignored; f (), g () represent the dimensionality functions, respectively. The formula shows that the lower the temperature and current, the higher the system safety index.

Of course, the foregoing is merely illustrative, and in some examples, the system security indicator may be a piecewise function defined based on the inside and outside of the preset range, so as to consider the intervention out of the range, the dimensional stability in the range, and the like, which are not described herein.

2. The calculation mode of the energy-saving index of the system comprises the following steps:

wherein N is a system energy saving index (W/V cm) ² ) P is the total power (W) consumed during a stimulation period and V is the volume (cm) of the target tissue ³ ) E is the average alternating electric field strength (V/cm) of the target tissue. These parameters may be obtained by the observation module 101.

In one example, the total power consumed during a stimulation cycle is 10W and the volume of the target tissue is 10cm ³ The average alternating electric field intensity of the target tissue is 1V/cm, and the energy-saving index of the system is as follows:

of course, the above is merely illustrative, and in some examples, the system energy-saving index may also consider parameters such as the number of stimulation electrodes that are turned on, the energy consumed per minute, and the volume of the target tissue, which will not be described in detail herein.

3. The calculation mode of the system efficiency index is as follows:

where P is the therapeutic efficacy index of the system (V.montath/cm), C is the coverage (%) of the alternating electric field over the target tissue over a specified threshold alternating electric field strength, and E is the average strength of the alternating electric field (V/cm) in the region. These parameters may be obtained by observation by the observation module 101 of the system. G is the target tissue growth rate, which refers to the relative change in target tissue volume per unit time, and can be calculated using the following formula:

Wherein G is the target tissue growth rate (1/mole), V _t Is the target tissue volume (cm) after treatment ³ )，V ₀ Is the target tissue volume (cm) prior to treatment ³ ) T is the treatment time (monta). These parameters may be determined by imaging diagnostic parameters.

In one example, the target tissue volume prior to treatment is 100cm ³ The target tissue volume after treatment was 102cm ³ The treatment time is 1 month, and the target tissue growth rate is:

at the moment, assuming that the coverage rate of the alternating electric field to the target tissue exceeds a specified threshold value and the alternating electric field intensity is 80%, the average intensity of the alternating electric field is 2V/cm, and the stimulation time is 1 month, the treatment efficiency index of the system is as follows:

it should be noted that in some examples, the optimization algorithm of the control module 102 may be to balance all parameters, e.g., to save energy (goal) as much as possible while guaranteeing therapeutic effect (constraint), and to activate fewer electrodes. Of course, the optimization algorithm may also be to determine the optimization objective based on specific treatment needs.

In this embodiment, the target parameter set in the regulatory module 102 may be a specific parameter value that the system expects to reach through regulation. The target parameter set is obtained by calculating a system index set, an optimization algorithm and an observation parameter set. The observation parameter set and the system index set determine the parameter types and parameter values to be participated in the calculation of the optimization algorithm, and the solution of the optimization algorithm is a set of parameter values expected to be achieved by a specific system, namely a target parameter set. Since the system index in the system index set involves more parameters, the type of parameter in the observed parameter set may be less than or equal to the type of parameter in the target parameter set.

Further, in this embodiment, the regulation parameter set in the regulation module 102 is a parameter composition of the tumor therapeutic field system that allows regulation of the alternating electric field, and the regulation weight matrix is used to represent a quantization value that needs to be regulated for each parameter in the regulation parameter set. It should be noted that, the number and specific content of the parameters in the modulation parameters are not limited in this embodiment, and any parameter of the adjustable alternating electric field may be included.

In some examples, the regulatory parameters include at least one of the following information: current, alternating electric field frequency, alternating electric field strength, duty cycle, electrode status. The definition of these regulatory parameters may be referred to above as observed parameters.

Preferably, the alternating electric field frequency may be a frequency that sweeps a range, wherein in some cases it is also allowed to superimpose multiple frequencies or switch frequencies in a stepwise manner, etc. The alternating electric field strength may be an alternating electric field strength that is scanned over a range or set to a fixed strength.

Of course, the foregoing is merely illustrative of parameters, and in some examples, the regulatory parameters may include other parameters, which will not be described herein.

In this embodiment, the parameters in the target parameter set may or may not be consistent with the parameters in the regulation parameter set. For example, if the parameter in the target parameter set comprises a temperature, but the parameter in the regulation parameter set is not consistent with the parameter in the target parameter set, because the parameter temperature cannot be used to regulate the alternating electric field.

Furthermore, to facilitate a better understanding of the specific implementation of the above-described process by the regulatory module 102 of providing relevant information, the relevant algorithms are explained below.

In some examples, the expression of the optimization algorithm is as follows:

minimize f(B)＝C(G ₁ (A，B)，G ₂ (A，B)，……，G _k (A，B))，

subject to

h(A，B)≤0，

G ₁ (A，B)，G ₂ (A，B)，……，G _k (A，B)∈S ₁ ，

A，B∈S ₂ ，

wherein f (B) represents an optimization objective function, k represents the number of system indexes contained in the system index set, G _i (A, B) represents the ith system index, which is a function related to A, B, C represents a preset function of deriving a comprehensive system index from each system index, A represents an observation parameter set, B represents a target parameter set, h (A, B) is a preset constraint function about A and B, S ₁ Calculated value feasible region representing each system index S ₂ Representing the feasible fields of the observation parameters in the preset observation parameter set and the target parameters in the target parameter set. Where minimize indicates minimization and subject to indicates that the subsequent constraint is satisfied.

And the iterative mode of the optimization algorithm comprises the following steps: particle swarm optimization algorithms, genetic algorithms, or simulated annealing algorithms.

To facilitate a better understanding of the iterative algorithm of the optimization algorithm provided by the above-described embodiments by those skilled in the art, exemplary illustrations thereof will be described below.

1. Regarding particle swarm optimization algorithms:

it is assumed that our optimization objective is to find a set of parameters that will minimize the energy consumption while ensuring the security of the system. The objective function at this time can be expressed as:

minimize f(x)＝w ₁ * Energy consumption index (x) -w ₂ * A safety index (x),

where x is a vector comprising parameters such as alternating electric field strength, duty cycle, electrode selection, etc.

Accordingly, the solving process includes the steps of:

initializing: a population of particles is randomly initialized, each particle representing a set of possible alternating electric field-related parameters.

Evaluation: the fitness of each particle is evaluated using an objective function.

Updating personal and global optima: updating the personal best location if the current location of the particle is better than its historical best location; if the current position of the particle is better than the global optimal position, the global optimal position is updated.

Wherein the velocity and position of each particle is updated by the following formula:

wherein w represents an inertia factor, c1 and c2 represent acceleration constants, r1 and r2 are random numbers, and the value range is 0,1]，pbest _i Indicating the locally optimal position of particle i, gbest _i Indicating the global optimum position of the population of particles. From the above expression, the inertia factor w controls the degree of dependence of the particle on the previous velocity, and the acceleration constants c1 and c2 control the degree of following of the particle on the own local optimum position and the global optimum position.

Iteration: the steps of evaluating, updating the best position, updating the speed and position are repeated until a stop condition is met (e.g. a maximum number of iterations is reached or the global best position changes less than a certain threshold).

Through the process, the particle swarm optimization algorithm can find a group of parameters, so that the system can ensure the safety and minimize the energy consumption. This set of parameters can be used as optimization targets for the system and adjusted in real time by the subsequent control algorithm.

2. Concerning genetic algorithms (Genetic Algorithm, GA):

assuming that the objective is to minimize energy consumption and ensure system safety, the optimization objective is to:

accordingly, the solving process includes the steps of:

initializing: an initial population is randomly generated, each individual representing a set of possible alternating electric field related parameters.

Selecting: individuals are selected for reproduction based on fitness functions (e.g., objective functions).

Wherein the selection is achieved by the expression:

wherein P is _i Is the probability that the ith individual is selected, f (x _i ) Is the fitness of the ith individual.

Crossing: new offspring are created by exchanging part of the genes of the selected individuals.

Wherein the intersection may use a one-point intersection or a multi-point intersection, such as a one-point intersection: child 1 = front half of parent 1 + rear half of parent 2; child 2 = front half of parent 2 + rear half of parent 1. Assume that there are two parents:

Parent 1: current 1, electrode pose 1, temperature 1 current 1, electrode pose 1 and temperature 1;

parent 2: current 2, electrode pose 2, temperature 2;

one-point crossing is performed for parent 1 and parent 2, assuming that the crossing point is between the first and second genes, the resulting child generation is:

offspring 1: current 1, electrode pose 2, temperature 2;

progeny 2: current 2, electrode pose 1, temperature 1;

mutation: part of the genes of the new offspring are randomly changed with a certain probability. Part of the genes of the new offspring were randomly changed, assuming the probability of mutation is p.

The offspring are mutated, assuming that mutation occurs at the current value and the mutation probability is p. If a variation occurs, the current value will change randomly. For example, the current value of child 1 may change from "current 1" to "current 1'".

If possible, variant offspring 1: current 1', electrode pose 2, temperature 2, current 1', electrode pose 2, temperature 2.

Evaluating and selecting a new generation: the fitness of the new offspring is evaluated and the next generation population is selected.

Iteration: the steps of selecting, crossing, mutating, evaluating and selecting are repeated until a stop condition is met.

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

Through this process, the genetic algorithm can find a set of parameters that allow the system to minimize energy consumption while ensuring safety.

3. Regarding the simulated annealing algorithm (Simulated Annealing, SA):

assuming the goal is to minimize energy consumption and ensure system safety, at this point the optimization goal is still:

accordingly, the solving process includes the steps of:

initializing: an initial solution x (e.g., a set of alternating electric field related parameters is randomly selected) and an initial temperature T0 are selected. Note that "temperature" in the simulated annealing algorithm is one algorithm parameter, and "temperature" in the parameter related to the alternating electric field is a different concept.

Neighborhood search: a new solution x' is randomly selected in the neighborhood of the current solution.

Acceptance criteria: accepting the new solution if the new solution is better than the current solution; otherwise, a new solution is accepted with a certain probability, and the probability is determined by the difference of the current temperature and the solution.

For example, the probability is determined by the following expression:

where T is the current "temperature", exp is the natural exponential function, f (x') is the calculated value of the new solution brought-in objective function, and f (x) is the calculated value of the original solution brought-in objective function.

Assume that a new solution is accepted.

And (3) cooling: the reduction of the "temperature" is usually performed according to a certain cooling scheme.

Iteration: repeating the steps of neighborhood searching, acceptance criteria and cooling until a stop condition is met.

Further, the control algorithm preset in the regulation module 102 is not particularly limited in this embodiment, and may be any algorithm capable of determining a value to be regulated for the parameter related to the alternating electric field by using the regulation parameter set and the observation parameter.

In some examples, the control algorithm may be a PID algorithm or a synovial control algorithm.

In order to facilitate a better understanding of the functions provided by the control algorithm described above, a PID algorithm will be exemplified below, but this does not mean that only a PID algorithm can be used as the control algorithm.

Let us assume that our control target parameter is temperature, in particular, the temperature of the electrodes is adjusted to a safe value T to achieve an optimization target (e.g. to ensure system safety).

Therefore, the control algorithm needs to quantify the degree of regulation of the regulation parameter according to the observation parameter. That is, an error calculation is required, that is, an error between the current state and the target state is calculated for the control parameter. Specifically, it can be realized by the following expression:

e _{temperature (temperature)} (t) =target temperature-current temperature,

further, the change in the quick response system determined by the proportional control is obtained by the following expression:

P _{temperature (temperature)} (t)＝K _p *e _{Temperature (temperature)} (t)，

The steady state error of the cancellation system determined by the integral control is obtained by the following expression:

the change trend of the prediction system determined by differential control is obtained by the following expression:

D _{temperature (temperature)} (t)＝K _d de _{Temperature (temperature)} (t)/dt，

Each component may then be mapped to a duty cycle or current magnitude. For example, the proportional component P may be mapped to a duty cycle, the integral component I to a current magnitude, and the differential component D to a rate of change of the duty cycle. Therefore, if the difference e between the target temperature T and the current temperature is positive, the duty ratio may be increased. If the difference e between the target temperature T and the current temperature is negative, the duty cycle may decrease. If the system bias e is continuously present, the integral component I is continuously increased. The integral component I increases the duty cycle so that the deviation e of the system gradually decreases.

Furthermore, the execution module 103 adjusts parameters such as the intensity and the duty ratio of the alternating electric field according to the regulation instruction set.

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

Further, in the present embodiment, the regulation module 102 implements the above functions by different structures.

In some examples, as shown in fig. 2, the regulatory module 102 includes: a first storage unit 112, a second storage unit 132, and a computing unit 122.

Wherein the first storage unit 112 is configured to store a set of regulatory parameters. The second storage unit 132 is configured to store a system index set. The calculating unit 122 is configured to generate a target parameter set according to the system index set and the optimization algorithm acquired from the second storage unit 132, generate a regulation weight matrix according to the target parameter set, the observation parameter, the regulation parameter set read from the first storage unit 122, and the control algorithm, generate a regulation instruction set according to the regulation weight matrix and the regulation parameter set read from the first storage unit, and output.

Of course, fig. 2 is only an exemplary illustration, and in some examples, the regulation module 102 may have other structures, which are not described herein.

In some examples of this embodiment, as shown in fig. 3, the execution module 103 may further include an alternating electric field generating circuit 113 and an electrode 133 located around the target tissue, where the alternating electric field generating circuit 113 is configured to generate a corresponding alternating electric field according to the regulation instruction set, and apply the corresponding alternating electric field to the target tissue through the electrode 133. Further, in some examples, as shown in fig. 4, the execution module 103 further includes a driver 123, where the driver 123 is configured to drive the electrode 133 according to a set of regulatory instructions to adjust the pose of the electrode. The system also includes an electrically insulating electrode holder; the electrode is arranged on the electrode bracket; the electrode bracket is provided with a space structure so as to fill or cover target tissues, and electrodes are arranged in space so as to obtain a three-dimensional alternating electric field; the driver 123 drives the electrode-stent to change spatial configuration and/or pose to change the alternating electric field distribution around the target tissue.

In yet other examples, the partially executed instructions may not be fully automatically completed, requiring human intervention. This portion of the control instructions is typically set with a low generation priority and a high execution priority at the time of calculation.

Thus, in some examples, the execution module 103 is further configured to send the manual regulation instructions to the outside in the event that the regulation instruction set contains manual regulation instructions. The specific sending mode is not limited, such as short messages, mails, alarm prompting tones and the like. For example, in a system, the alternating electric field can be adjusted by manually adjusting the pose of the electrode, the execution module 103 can be connected with a terminal (such as a mobile phone, a computer, a PAD, etc.) in a wireless manner, and when the received regulation instruction set includes the electrode support which needs to be manually operated, the information is sent to the system operator, and the system operator manually adjusts the electrode support.

Obviously, as shown in fig. 1, after the system is executed by the execution module 103, the observation module can acquire the execution result again, the regulation module 102 periodically acquires the observation parameters again to form a regulation instruction set again, and the like, so that closed loop feedback is formed in a reciprocating manner, and the system can perform self-adaptive regulation and control, so that the alternating electric field is maintained at a stable target level.

However, as previously mentioned, even if closed loop feedback is formed, the system still faces problems such as out of sync acquisition of observed parameters, optimization target personalization requirements, and selection of optimization algorithms.

To this end, as shown in fig. 5, some preferred embodiments of the present application further provide a system that includes an observation module 501, a regulation module 502, an execution module 503, and a path selection module 504. At this time, the regulation module 503 includes at least two regulation sub-modules 512.

Wherein the observation module 501 is configured to obtain an observation parameter. The path selection module 504 is configured to divide each observation parameter into a plurality of observation parameter sets according to the characteristics of each observation parameter selectively acquired. Each of the regulation sub-modules 512 is configured to generate a target parameter set according to the corresponding observation parameter set, system index set, and optimization algorithm, and to generate a regulation weight matrix according to the target parameter set, the observation parameter set, the regulation parameter set, and the control algorithm, and to generate a regulation instruction set according to the regulation weight matrix and the regulation parameter set. The execution module 503 is configured to regulate the alternating electric field applied to the target tissue according to a set of regulation instructions. In this embodiment, the system goal set and the regulation parameter set are shared among the plurality of regulation sub-modules 512.

Thus, on the basis of the system shown in fig. 1, the path selection module 504 and the corresponding multiple regulation sub-modules 512 are further introduced, and on the basis of forming closed-loop feedback control and being capable of realizing adaptive regulation, different control algorithms can be supported for different observation parameter sets through the layered design of the multiple regulation sub-modules 512, so that the system can respond to different types of observation data more flexibly and accurately, and personalized and accurate treatment can be provided for different working states of patients, treatment stages and the system.

It should be noted that in some examples, different control sub-modules 512 support different control algorithms. For example, different regulatory sub-modules 512 maintain different hyper-parameters of the same type of control algorithm. Illustratively, different regulatory sub-modules 512 each employ a PID algorithm, but the 3 parameters of the PID algorithm are not exactly the same across different regulatory sub-modules 512. As another example, different regulatory sub-modules 512 maintain different kinds of control algorithms. Illustratively, some of the regulation sub-modules 512 employ PID algorithms, others of the regulation sub-modules 512 employ synovial control algorithms, and so forth.

The present embodiment is not particularly limited as to the criteria by which the path selection module 504 classifies the observed parameters into different sets of observed parameters. In some examples, one sensed parameter may be assigned to only one set of observed parameters. In other examples, a sensed parameter may be assigned to a plurality of standard-compliant observed parameter sets.

To facilitate a better understanding of the path selection module 504 in the system shown in fig. 5 by those skilled in the art, it will be explained below. It should be noted that, the rest of the system is described in the foregoing embodiments, and will not be described herein again.

The acquisition of the observation parameters in the observation parameter set is not synchronized and its importance varies significantly. For example, temperature data and temperature control are directly related to system safety, and more frequent monitoring is required, so that temperature data is easily obtained in a short period, and a typical acquisition period may be within 1 minute. The query for the charge data may be relatively infrequent, but is also relatively easy to obtain, and a typical acquisition period may be 1-10 minutes. On the other hand, some parameters, such as imaging diagnosis and diagnosis results of other patient body parameters, can be obtained with a longer period of 1-30 days, but are of higher importance.

Based on this, in some examples, the path selection module 504 is further configured to configure the one regulation sub-module 512 with an observation parameter having an observation period greater than the first period, and configure the other regulation sub-module 512 with an observation parameter having an observation period less than the first period, where the observation period is a period in which the observation module 501 collects the observation parameter.

Based on this, in other examples, the path selection module 504 is further configured to configure the one regulation sub-module 512 with an observation parameter having an observation period greater than the second period, and configure the other regulation sub-module 512 with an observation parameter having an observation period less than the third period, where the observation period is a period in which the observation module 501 collects the observation parameters.

In this way, the path selection module 504 can combine the long-term observation parameter and the short-term observation parameter to provide a long-term control function and a short-term control function, which can not only timely adjust according to the change in treatment, but also improve the long-term continuous effective quality scheme, and is beneficial to stability. That is, on the basis of the system shown in fig. 1, the system shown in fig. 5 also proposes a path selection method for the existing problem that the acquisition periods (events) of the parameters are not synchronous, and the observed parameters can be automatically guided to a specific regulation module 502 according to the acquisition periods, namely, a parameter adjustment method (multi-layer control) of long-short-period parameter adaptation. The long-term and short-term adaptive parameter adjustment method can adopt control methods with different layers or modes according to parameters (such as temperature, current, impedance, electric quantity, imaging diagnosis, etc.) of different acquisition periods or frequencies

It should be noted that the relative magnitude of the first period, the second period, and the third period are not limited, and for example, the same parameter may be considered to be applied to both long-term and short-term therapies, such as temperature data and electrical data for activating the short-term regulatory module path, and target tissue size and imaging evaluation data for activating the long-term regulatory module path. Thus, the second period may be set to be larger than the third period, so that a part of the parameters can be assigned to both the long-term regulation process and the short-term regulation process.

In addition to taking the observation period as a criterion, in other examples, the path selection module 504 is further configured to assign an observation parameter having an importance level greater than the first level to one regulation sub-module 512 and an observation parameter having an importance level less than the second level to another regulation sub-module 512, the importance level being a quantized value of importance of the observation module 501 in the regulation process. Here, similar to the above, the relationship between the first level and the second level is not limited.

That is, the regulation module 502 employs different path-finding matching mechanisms to handle asynchronous acquisition of the observed parameters and different degrees of importance. In this way, the routing module 504 can adjust the adjustment and control according to different needs during the treatment process, which is beneficial to providing a personalized treatment plan for the patient.

To this end, as shown in fig. 6, some preferred embodiments of the present application further provide a system including an observation module 601, a regulation module 602, an execution module 603, and a policy selection module 604.

Wherein, the observation module 601 is configured to obtain the observation parameters. The policy selection module 604 is configured to determine a current regulatory policy from a plurality of regulatory policies. Wherein each regulation strategy comprises the types and the mutual relations of the system indexes in the currently expected system index set. The regulation and control module 602 is configured to generate a target parameter set according to the system index set corresponding to the current regulation and control strategy determined by the observation parameter set and the strategy selection module 604 and a preset optimization algorithm, generate a regulation and control weight matrix according to the target parameter set, the observation parameter set, the regulation and control parameter set and a control algorithm, and generate a regulation and control instruction set according to the regulation and control weight matrix and the regulation and control parameter set. The execution module 603 is configured to regulate the alternating electric field applied to the target tissue according to a set of regulation instructions.

Thus, on the basis of the system shown in fig. 1, a policy selection module 604 is further introduced, the currently expected system indexes and the relationships between the system indexes are obtained from the system index set, and then regulation and control are realized by combining with the observation parameter set and the like. In this way, on the basis of forming closed loop feedback control and realizing self-adaptive regulation and control, different optimization targets can be supported for different individuals, different working states of the system and different treatment stages through the strategy selection module 604, so that personalized and accurate treatment can be provided for different treatment stages or different working states of the system for patients.

For example, in the present embodiment, the regulation strategy is represented by different modes such as a performance mode, a power saving mode, and a safety mode. Different modes (such as a performance mode, an energy-saving mode, a safety mode and the like) can be preset in advance, different treatment emphasis points are emphasized by distributing different weights to system indexes, and meanwhile, a conversion method between modes can be planned on the basis. For example, when the device is applied to a patient just after surgery, the device is first put into a safe mode, and after several rounds of treatment, the device is automatically put into a performance mode, so as to focus on improving the stimulation efficiency, and then put into an energy-saving mode during a low-power interval (for example, when the power is less than 20%) of the device, so as to increase the treatment time of the device. So that the treatment effect can be effectively improved.

Further, in some examples, the policy selection module 604 is further configured to automatically adjust the current regulatory policy based on a change in a first information, the first information including at least one of: the current stage (time) of treatment, the power state of the system and the patient's physical condition.

That is, the information such as the treatment stage, the power supply state of the system, the physical condition of the patient and the like can be considered, so that the regulation and control strategy can be automatically adjusted in real time, the treatment mode can be timely changed, the current treatment requirement can be met, and the treatment effect can be improved.

In other examples, the policy selection module 604 may also manually select the regulatory policies, making the regulation policies more flexible to adjust. Furthermore, the regulation strategy can also be manually adjusted, for example, the system indexes are added or deleted, and the proportional relation between the system indexes is added or reduced, so that a new mode is formed. Thus, the regulation strategy is more targeted.

To facilitate a better understanding of the policy selection module 604 in the system shown in FIG. 6 by those skilled in the art, it is illustrated below. It should be noted that, the rest of the system is described in the foregoing embodiments, and will not be described herein again.

In one example, different operation modes, such as a power saving mode, a safety mode, etc., are formed by adjusting the weights of the system indicators in the performance mode. These modes of operation accommodate different scenarios and requirements. For example, when the patient has just begun using the device, the policy selection module 604 may select the safe mode to power on to prevent inadaptation; when the system power supply is not sufficient, the policy selection module 604 may select the energy saving mode; when the power is sufficient, the policy selection module 604 may select the performance mode.

Further, the system shown in fig. 5 may be organically combined with the system shown in fig. 6, i.e. the system has both a path selection module and a policy selection module. At this time, the structure of the system may be as shown in fig. 7. Specifically, the regulation and control modules include a pair of regulation and control modules, namely a long-term regulation and control module and a short-term regulation and control module, which work cooperatively to realize a certain strategy: such as performance mode. Meanwhile, the regulation strategy also has an energy-saving mode and a safety mode. They trigger under different conditions. If the patient just operated uses the system for the first 3 days, the strategy selection module selects a regulation strategy (short-term regulation and long-term regulation exist in the strategy) of the safety mode, the regulation strategy pays attention to the safety index, and a higher weight and a stronger constraint are configured for the safety index of the system (for example, the safety index of the system needs to be constrained within +/-0.1); after the safety observation period is passed, the strategy selection module selects a regulation strategy for entering the efficiency mode, the constraint range of the safety index is widened, the constraint range of the efficiency index is reduced, and the weight of the efficiency index is increased; then, after the system is determined to be in low power, the strategy selection module selects a regulation strategy for entering the energy-saving mode, namely, the constraint range of the energy-saving index is widened, the weight is reduced, the constraint range of the energy-saving index is retracted, and the weight is increased. Under different modes, the path selection module selectively sends each observation parameter into the long-term regulation module and the short-term regulation module which accept the regulation strategy corresponding to the current mode according to whether the observation parameter belongs to the long-term parameter or the short-term parameter.

To facilitate a better understanding of the systems provided by the above embodiments by those skilled in the art, the following description will be given by way of example with reference to specific application scenarios.

The patient is assumed to be temperature sensitive, and therefore, the safe temperature range of the patient is set to 36-40 ℃. The operational capabilities of tumor treatment field systems include: the temperature observation once for 1 minute, the electric quantity energy consumption observation once for 5 minutes and the treatment effect estimated once for 1 month are supported, the initial electric quantity of the system is assumed to be 500mAh, the number of the provided electrodes is 5, the energy consumption per hour after each electrode is started is 10mAh, and the parameters for supporting and controlling the alternating electric field comprise current, electrode pose and electrode starting quantity. The target tissue is a tumor.

The system index calculation method is set as follows:

the curative effect index is as follows: the first derivative of tumor volume h=dddt was measured and obtained from CT.

The safety index and the energy-saving index adopt the calculation method provided in the previous embodiment.

The regulation and control module provides two regulation and control submodules: long term module (responsible for long term observation of tumor volume and treatment effect), short term module (responsible for short term observation of temperature and electrical quantity).

The optimization algorithm used by the regulation and control module is a particle swarm optimization algorithm, and the control algorithm is a PID algorithm.

3 modes, namely a safety mode, a performance mode and a energy-saving mode, are preset in the strategy selection module. In the safety mode, the weight ratio of the 3 indexes is as follows: efficacy 1: safety 2: energy saving 1; in the efficiency mode, the weight ratio of the 3 indexes is as follows: efficacy 2: safety 1: energy saving 1; in the energy-saving mode, the weight ratio of the 3 indexes is as follows: efficacy 1: safety 1: energy saving 2. And, the selection strategy among the 3 modes is as follows: a 3-day safety observation period, and in addition, the general case is an efficiency mode, and the low-power case is an energy-saving mode.

On days 1-3, the strategy selection module indicates the regulation strategy of the safety mode to the regulation module, so that after the system is started, PID control parameters of a short-term path and long-term PID parameters are distributed, the system enters the safety mode, and 3 electrodes are started. Next, short-term observation parameters were observed: the temperature is 39 ℃, and the safety range and the electric quantity are full, so that the strategy selection module does not need to be switched to an energy-saving mode, the regulation and control module can obtain a system index set, and then each system index is calculated as follows: safety index value q=2/37, efficacy index value h=dddt= -6cm ³ Month (assuming that tumor volume is shrinking), energy conservation index According to the index set and the weight (efficiency 1: safety 2: energy saving 1) of the current safety mode, the optimization target is to reduce Q and N, and simultaneously keep dVdt as much as possible; calculating a short-term regulation target by using a particle swarm optimization algorithm to obtain a regulation instruction set { current intensity: 8mA, electrode pose: unchanged electrode opening number: 3}. The execution module will then reduce the current to 8mA in response to the regulatory instruction set. And adjustments were continuously observed.

The treatment proceeds to day 3, and the strategy selection module indicates to the regulation module the regulation strategy for the efficacy pattern, so all 5 electrodes will be turned on. The observed parameters include: tumor volume v=20 cm ³ . Therefore, the security index is updated as(assuming an average temperature of 38 ℃ C. For 5 electrodes); curative effect index h=dddt= -3cm ³ 2/montath; energy saving index->And further, a regulation instruction set is generated to increase the current to 12mA while adjusting the position of the electrode so as to improve the tumor suppression effect after patient adaptation.

The treatment entered day 8, and the observed parameters observed by the observation module include: the electric quantity is 100mAh and is lower than 20%. Further, due to the reduction of the electric quantity, the strategy selection module indicates the regulation strategy of the energy-saving mode to the regulation module. At this time, the calculated optimization objective: q=0.03, h= -0.08, n=60/(30 x 2.5). Therefore, under the guidance of the regulation strategy of the energy-saving mode, the regulation instruction set obtained by the regulation module is { current intensity: 8mA, electrode pose: unchanged electrode opening number: 3, the executive module will turn off 2 electrodes, reduce the current to 6mA, while adjusting the position of the electrodes to maintain the efficacy. And adjustments were continuously observed.

Treatment was entered on day 10 by charging so that the observed parameters observed by the observation module included: the electric quantity is 300mAh, and the recovery is 60%. Thus, the strategy selection module indicates the regulatory strategy of the efficacy pattern to the regulatory module. And, the observation module observes the observation parameter: tumor volume v=28 cm ³ First derivative h=dddt= -6cm ³ /montath. Q=0.01, h= -0.2, n=18/(28×1); therefore, under the guidance of the regulation strategy of the efficiency mode, the obtained regulation instruction set is { current intensity: 12mA, electrode pose: optimizing the electrode opening quantity: 5, the executive module will turn on all 5 electrodes, maintaining the current at 12mA, while fine tuning the position of the electrodes to further optimize the efficacy.

Therefore, the system provided by the embodiment of the application represents the multidimensional information of the patient and the system by using various observation parameters (from a plurality of groups of sensors or diagnosis and treatment reports), and the parameters related to the alternating electric field are closed-loop and adaptively adjusted according to the information analysis result, so that the dynamic and intelligent control of the system is realized. On the basis, a self-adaptive path selection module and a strategy selection module are provided for the problems of asynchronous acquisition of observation parameters, personalized treatment requirements and the like, and the special problem encountered by a closed-loop system under the condition of a tumor treatment field is solved. The accuracy, safety and effectiveness of treatment are comprehensively improved. Specifically, the alternating electric field can be regulated and controlled accurately in real time according to the change of the specific body condition of the patient, so that the alternating electric field can act on the target tissue cells more accurately. The safety can be realized by adjusting the alternating electric field in a balanced way according to the influence of the alternating electric field, so that the alternating electric field can distribute and control the energy of the alternating electric field more evenly, thereby reducing the damage to normal cells. The alternating electric field can be flexibly regulated according to different requirements and conditions effectively, so that the alternating electric field can be more suitable for different treatment modes and durations.

In addition, energy conservation can be realized through different mode selections, namely, the working mode of the system can be changed according to first information such as electric quantity, temperature and the like, so that the alternating electric field can consume electric energy more sparingly, and the use of accessories is reduced. The system is stable, namely the working condition of the system can be monitored according to the observation parameters such as impedance, temperature and the like, and the parameters related to the alternating electric field can be fed back and regulated in time, so that the alternating electric field can be output and transmitted more stably. The target state of the system can be set according to data such as treatment plans, imaging diagnosis and the like, and parameters related to the alternating electric field can be adaptively adjusted according to data of various sensors, so that the alternating electric field can more intelligently control treatment of target tissues.

It should be noted that, each module in the above embodiment is a logic module, and in practical application, one logic unit may be one physical unit, or may be a part of one physical unit, or may be implemented by a combination of multiple physical units. In addition, in order to highlight the innovative part of the present application, elements that are not so close to solving the technical problem presented in the present application are not introduced in the present embodiment, but it does not indicate that other elements are not present in the present embodiment.

Accordingly, as shown in fig. 8, some embodiments of the present application further provide a method for controlling a tumor treatment field system, including the following steps:

in step 801, observation parameters are obtained.

Wherein the observed parameter is used to characterize the treatment state.

Step 802, periodically obtaining at least part of the observation parameters, constructing an observation parameter set, and generating a target parameter set according to the observation parameter set, a preset system index set and a preset optimization algorithm.

Step 803, generating a regulation weight matrix according to the target parameter set, the observation parameter set, the preset regulation parameter set and the preset control algorithm.

The system index set is used for reflecting indexes of the system performance of the tumor treatment field, the target parameter set is used for representing specific numerical values of expected parameters of the tumor treatment field system, the regulation parameter set is formed by parameters of the adjustable alternating electric field, and the regulation weight matrix is used for representing quantized values of all parameters in the regulation parameter set to be regulated.

Step 804, generating a regulation instruction set according to the regulation weight matrix and the regulation parameter set.

Step 805, modulating an alternating electric field applied to a target tissue according to a modulating command set.

The data flow and processing procedure shown in fig. 8 is shown in fig. 9.

The above steps of the methods are divided, for clarity of description, and may be combined into one step or split into multiple steps when implemented, so long as they include the same logic relationship, and they are all within the protection scope of this patent; it is within the scope of this patent to add insignificant modifications to the algorithm or flow or introduce insignificant designs, but not to alter the core design of its algorithm and flow.

It is to be noted that this embodiment is a method embodiment corresponding to the system embodiment, and this embodiment may be implemented in cooperation with the system embodiment. The related technical details mentioned in the system embodiment are still valid in this embodiment, and in order to reduce repetition, they are not described here again. Accordingly, the related technical details mentioned in the present embodiment can also be applied to the system embodiment.

It will be understood by those of ordinary skill in the art that the foregoing embodiments are specific embodiments in which the present application is implemented and that various changes in form and details may be made therein 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 an observation parameter, wherein the observation parameter is used for characterizing a treatment state;

the regulation and control module is configured to periodically acquire at least part of the observation parameters as an observation parameter set, generate a target parameter set according to the observation parameter set, a preset system index set and a preset optimization algorithm, generate a regulation and control weight matrix according to the target parameter set, the observation parameter set, a preset regulation and control parameter set and a preset control algorithm, and generate a regulation and control instruction set according to the regulation and control weight matrix and the regulation and control parameter set, wherein the system index set is used for reflecting indexes of the system performance of the tumor treatment field, the target parameter set is used for representing specific values of expected parameters of the tumor treatment field system, the regulation and control parameter set is formed by parameters of the tumor treatment field system which allow regulation and control of an alternating electric field, and the regulation and control weight matrix is used for representing quantized values of each parameter in the regulation and control parameter set which needs regulation and control;

and the execution module is configured to regulate and control the alternating electric field applied to the target tissue according to the regulation and control 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(G ₁ (A，B)，G ₂ (A，B)，……，G _k (A，B))

subject to

h(A，B)≤0，

G ₁ (A，B)，G ₂ (A，B)，……，G _k (A，B)∈S ₁ ，

A，B∈S ₂ ，

wherein f (B) represents an optimization objective function, k represents the number of the system indexes contained in the system index set, G _i (A, B) represents the ith system index, C represents a preset function of deriving a comprehensive system index from each of the system indexes, A represents the viewA measured parameter set, B represents the target parameter set, h (A, B) is a preset constraint function about A and B, S ₁ A calculated value feasible region representing each system index S ₂ Representing a feasible domain of the observed parameters in the preset observed parameter set and the target parameters in the target parameter set;

the iterative mode of the optimization algorithm comprises the following steps: particle swarm optimization algorithms, genetic algorithms, or simulated annealing algorithms.

3. The tumor treatment field system according to claim 1, wherein,

the control algorithm is a PID control algorithm or a synovial membrane control algorithm.

4. The tumor treatment field system according to claim 1, wherein,

the execution module comprises an alternating electric field generating circuit and electrodes arranged around the target tissue, wherein the alternating electric field generating circuit is used for generating a corresponding alternating electric field according to the regulation instruction set and applying the alternating electric field to the target tissue through the electrodes.

5. The tumor treatment field system according to claim 4, wherein,

the execution module further comprises a driver, wherein the driver is used for driving the electrode according to the regulation instruction set so as to adjust the pose of the electrode.

6. The tumor treatment field system according to claim 4, wherein,

the execution module is further configured to send the manual regulation instruction to the outside in the case where the regulation instruction set contains the manual regulation instruction.

7. The tumor treatment field system according to claim 1, wherein,

the regulation and control module comprises:

a first storage unit configured to store the regulation parameter set;

a second storage unit configured to store the system index set;

and a calculation unit configured to generate the target parameter set according to the observation parameter set, the system index set acquired from the second storage unit, and the optimization algorithm, generate the regulation weight matrix according to the target parameter set, the observation parameter set, the regulation parameter set read from the first storage unit, and the control algorithm, generate the regulation instruction set according to the regulation weight matrix and the regulation parameter set read from the first storage unit, and output.

8. The tumor treatment field system according to claim 1, wherein,

the observed parameter includes at least one of the following information: temperature, current, electrode state, duty cycle, intensity of alternating electric field, frequency of alternating electric field variation, target tissue state, and impedance of target tissue;

the regulatory parameters include at least one of the following information: current, alternating electric field frequency, alternating electric field intensity, duty cycle, electrode status;

the system index includes at least one of the following information: system safety index, system energy saving index, system therapeutic efficacy index, and system adaptability index.

9. The tumor treatment field system of claim 1, further comprising:

the path selection module comprises at least two regulation and control sub-modules;

the path selection module is configured to divide each observation parameter into a plurality of observation parameter sets according to the characteristics of each observation parameter which is selectively acquired;

each regulation and control submodule is configured to generate the target parameter set according to the corresponding observation parameter set, the system index set and the optimization algorithm, generate the regulation and control weight matrix according to the target parameter set, the acquired observation parameter set, the regulation and control parameter set and the control algorithm, and generate the regulation and control instruction set according to the regulation and control weight matrix and the regulation and control parameter set.

10. The tumor treatment field system according to claim 9, wherein,

the path selection module is further configured to configure an observation parameter with an observation period greater than a first period to one of the regulation and control sub-modules, and configure an observation parameter with an observation period less than the first period to the other regulation and control sub-module, wherein the observation period is a period during which the observation module collects the observation parameter.

11. The tumor treatment field system according to claim 9, wherein,

the path selection module is further configured to configure the observation parameters with the observation period being greater than the second period to one of the regulation and control sub-modules, and configure the observation parameters with the observation period being less than the third period to the other regulation and control sub-module, wherein the observation period is a period in which the observation parameters are collected by the observation module.

12. The tumor treatment field system according to claim 9, wherein,

the path selection module is further configured to configure the observation parameters with importance levels greater than a first level to one of the regulation sub-modules, and configure the observation parameters with importance levels less than a second level to the other regulation sub-module, wherein the importance levels are quantized values of importance of the observation modules in a regulation process.

13. The tumor treatment field system according to claim 9, wherein,

the control algorithms corresponding to different regulation and control sub-modules are different.

14. The tumor treatment field system of claim 1 or 9, further comprising:

a policy selection module;

the strategy selection module is configured to determine a current regulation strategy from a plurality of regulation strategies, wherein the regulation strategies comprise types and mutual relations of currently expected system indexes in the system index set;

the regulation and control module is configured to generate the target parameter set according to the system index set corresponding to the current regulation and control strategy determined by the observation parameter set and the strategy selection module and a preset optimization algorithm, generate the regulation and control weight matrix according to the target parameter set, the observation parameter set, the regulation and control parameter set and the control algorithm, generate the regulation and control instruction set according to the regulation and control weight matrix and the regulation and control parameter set and output the regulation and control instruction set.

15. The tumor treatment field system according to claim 14, wherein,

the policy selection module is further configured to automatically adjust the current regulatory policy based on a change in a first information comprising at least one of: the current treatment stage, the power supply state of the tumor treatment field system and the physical condition of the patient.

16. A method of modulating a tumor treatment field system, comprising:

obtaining observation parameters, wherein the observation parameters are used for representing treatment states;

periodically acquiring at least part of the observation parameters, constructing an observation parameter set, and generating a target parameter set according to the observation parameter set, a preset system index set and a preset optimization algorithm;

generating a regulation weight matrix according to the target parameter set, the observation parameter set, a preset regulation parameter set and a preset control algorithm, wherein the system index set is used for reflecting the system performance index of the tumor treatment field, the target parameter set is used for representing a specific value of an expected parameter of the tumor treatment field system, the regulation parameter set is formed by parameters of a regulatable alternating electric field, and the regulation weight matrix is used for representing quantized values of all parameters in the regulation parameter set to be regulated;

generating a regulation instruction set according to the regulation weight matrix and the regulation parameter set;

and regulating and controlling the alternating electric field applied to the target tissue according to the regulating and controlling instruction set.