Radio frequency tumor thermal therapy system with adjustable radio frequency source

Abstract

The invention relates to the technical field of radio frequency thermotherapy equipment control, in particular to a radio frequency tumor thermotherapy system with adjustable radio frequency sources, which comprises two or more radio frequency sources and a radio frequency source controller, the radio frequency control module is used for reducing the frequency of the abnormal radio frequency source when the abnormal radio frequency source appears, and changing the frequency of the normal radio frequency source according to the heat loss amount and the distribution proportion generated by the abnormal radio frequency source after the frequency is reduced; and when the abnormal radio frequency source appears again, reducing the frequency of the abnormal radio frequency source again, adjusting the distribution proportion according to the temperature change of the normal radio frequency source after the frequency is changed at the historical moment, and changing the frequency of the normal radio frequency source according to the heat loss amount generated by the abnormal radio frequency source after the frequency is reduced again and the adjusted distribution proportion. According to the invention, the fat overheating phenomenon is avoided while the deep part of the body tissue is ensured to reach enough temperature, and the device adapts to the specific thermal therapy condition of a patient.

Description

Technical Field

[0001] The present invention relates to the technical field of radio frequency hyperthermia equipment control, and in particular to a radio frequency tumor hyperthermia system with an adjustable radio frequency source. Background Art

[0002] Current hyperthermia devices use oscillation frequencies of 8 MHz, 13.56 MHz, 27.12 MHz, 40.68 MHz, and other frequencies, with two-electrode output and a capacitive electric field. Based on the principle that high-frequency electromagnetic waves generate heat in the human body, these devices suffer from a disadvantage: during clinical treatment, the patient's surface temperature can be too high to tolerate. To reduce capacitive reactance and prevent excessive heat generation in the skin and fat, cold water circulation can be used to achieve a coupled reduction in surface temperature. However, achieving sufficient temperatures deep within the body still involves overheating of the fat, and power loss is significant. This approach still fails to fully address the problem of elevated surface temperatures, preventing the patient from achieving the desired temperature for deep lesions. Summary of the Invention

[0003] To solve the above problems, the present invention provides a radio frequency tumor hyperthermia treatment system with an adjustable radio frequency source.

[0004] The radio frequency tumor hyperthermia system of the present invention with an adjustable radio frequency source adopts the following technical solutions:

[0005] One embodiment of the present invention provides a radio frequency tumor hyperthermia treatment system with an adjustable radio frequency source, comprising: a radio frequency source, a body temperature sensor, and a radio frequency source controller;

[0006] The number of radio frequency sources is greater than or equal to 2, and a body temperature sensor is installed at each radio frequency source position;

[0007] The RF source controller includes the following modules:

[0008] The body temperature detection module is used to collect and record the temperature of each RF source location at each moment during hyperthermia treatment, and to determine in real time whether the temperature exceeds the upper limit of the tolerance temperature. The RF source at the location exceeding the upper limit of the tolerance temperature is recorded as an abnormal RF source, and the RF source at the location not exceeding the upper limit of the tolerance temperature is recorded as a normal RF source;

[0009] A radio frequency control module is used to reduce the frequency of an abnormal radio frequency source when an abnormal radio frequency source appears, and change the frequency of a normal radio frequency source according to the amount of heat loss generated by the abnormal radio frequency source after the frequency reduction and the distribution ratio;

[0010] When the abnormal RF source appears again, the frequency of the abnormal RF source is reduced again, the allocation ratio is adjusted according to the temperature change of the normal RF source after the frequency is changed in the historical moment, and the frequency of the normal RF source is changed according to the heat loss generated by the abnormal RF source after the frequency is reduced again and the adjusted allocation ratio;

[0011] The specific method for obtaining the heat loss is:

[0012] The amount of heat loss is estimated based on the frequency of the abnormal RF source after frequency reduction and the location of the tumor;

[0013] Changing the frequency of the normal radio frequency source includes the following steps:

[0014] The heat loss amount is distributed to each normal RF source according to the distribution characteristics to obtain the frequency that each normal RF source needs to increase; the frequency of each normal RF source is changed according to the frequency that needs to be increased; the distribution characteristics include the distribution ratio and the adjusted distribution ratio, and each normal RF source corresponds to one distribution characteristic.

[0015] Preferably, the estimating of the amount of heat loss based on the frequency of the abnormal radio frequency source after frequency reduction and the location of the tumor comprises the following steps:

[0016] The frequency of the abnormal RF source after frequency reduction and the location of the tumor are substituted into the frequency-heat model to estimate the amount of heat loss.

[0017] Preferably, allocating the heat loss amount to each normal radio frequency source according to the distribution characteristics to obtain the frequency that each normal radio frequency source needs to increase includes the following specific steps:

[0018] The product of the heat loss amount and the allocation characteristics of each normal RF source is recorded as the heat loss amount allocated to each normal RF source. The allocated heat loss amount and the location of the tumor are substituted into the frequency-heat model to obtain the frequency that each normal RF source needs to increase.

[0019] Preferably, the step of adjusting the allocation ratio according to the temperature change of the normal radio frequency source after the frequency is changed at a historical moment includes the following specific steps:

[0020] The heat loss generated by the abnormal RF source after the frequency is reduced again is recorded as P, and the heat loss P is distributed to each normal RF source according to the distribution ratio to obtain the frequency that each normal RF source needs to increase, which is recorded as L1;

[0021] For each frequency change amount of each normal RF source at each frequency change in a historical moment, the adjusted allocation ratio of each normal RF source is obtained according to the difference between L1 and the frequency change amount at each frequency change and the temperature change after each frequency change.

[0022] Preferably, the step of obtaining the adjusted distribution ratio of each normal RF source according to the difference between L1 and the frequency change amount each time the frequency is changed and the temperature change after each frequency change comprises the following specific steps:

[0023] Several frequency changes with the smallest difference from L1 are obtained and recorded as reference frequency changes. The temperature change rate is obtained based on the change in temperature after each frequency change. Each reference frequency change corresponds to a temperature change rate. The adjusted distribution ratio of each normal RF source is obtained based on the temperature change rates corresponding to all reference frequency changes. The adjusted distribution ratio is negatively correlated with the temperature change rate.

[0024] Preferably, the specific steps of obtaining the frequency-heat model are as follows:

[0025] During each radiofrequency tumor hyperthermia treatment in history, the tumor location, the location of each radiofrequency source, and the average frequency of each radiofrequency source during the entire treatment process were recorded and used as a sample. The inverse of the tumor ablation time during each radiofrequency tumor hyperthermia treatment process was used as the sample label.

[0026] The input of the frequency-heat model is the tumor location contained in each sample, the location of each RF source, and the frequency of each RF source, and the output is the heat at the tumor location;

[0027] The frequency-heat model is trained using samples and labels obtained from all historical radiofrequency tumor hyperthermia treatment processes.

[0028] Preferably, the temperature change rate is the absolute value of the average slope of the temperature over time after each frequency change.

[0029] Preferably, the step of obtaining the adjusted distribution ratio of each normal RF source according to the temperature change rates corresponding to all reference frequency changes includes the following specific steps:

[0030] The average of the temperature change rates corresponding to all reference frequency changes is used as the allocation index w of each normal RF source. The allocation index w of the normal RF source is linearly normalized to obtain w1. The allocation ratio of each normal RF source is recorded as a. The adjusted allocation ratio of each normal RF source is negatively correlated with w1 and positively correlated with a.

[0031] Preferably, it also includes a tumor positioning module for obtaining the tumor position according to the magnetic resonance imaging device.

[0032] Preferably, each RF source includes two electrodes, and a body temperature sensor is installed at each electrode position. When the temperature value output by any temperature sensor at the two electrode positions exceeds the upper limit of the tolerable temperature, the RF sources corresponding to the two electrodes are recorded as abnormal RF sources; when the temperature values ​​output by all temperature sensors at the two electrode positions do not exceed the upper limit of the tolerable temperature, the RF sources corresponding to the two electrodes are recorded as normal RF sources.

[0033] The beneficial effects of the technical solution of the present invention are as follows: the number of RF sources of the present invention is greater than or equal to 2, which can ensure that the deep lesion site of the human body reaches the required temperature. In addition, the RF control module of the present invention is used to reduce the frequency of the abnormal RF source when an abnormal RF source appears, and change the frequency of the normal RF source according to the heat loss amount and distribution ratio generated by the abnormal RF source after the frequency reduction; ensure that the heat loss amount is apportioned to the normal RF source, and avoid the situation where a certain RF source position has a continuous high temperature. At the same time, the distribution ratio is adjusted according to the temperature change of the normal RF source after the frequency is changed at a historical moment, and the distribution ratio is dynamically adjusted in combination with the physiological conditions of the specific tissue parts during the working process of the normal RF source to adapt to the specific conditions of different parts of the patient.

[0034] In summary, the present invention ensures that the deep lesion site of the human body reaches the required temperature while reasonably changing the frequency of the radio frequency source to adapt to the thermal treatment conditions of different parts of the patient, thereby avoiding fat overheating and power loss. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0036] Figure 1 The figure is a schematic diagram of the framework structure of a radio frequency tumor hyperthermia treatment system with an adjustable radio frequency source according to an embodiment of the present invention. DETAILED DESCRIPTION

[0037] To further illustrate the technical means and effectiveness of the present invention in achieving its intended objectives, the following, in conjunction with the accompanying drawings and preferred embodiments, provides a detailed description of the specific implementation, structure, features, and effectiveness of a radiofrequency tumor hyperthermia system with an adjustable radiofrequency source. In the following description, references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0038] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0039] The specific scheme of the radio frequency tumor hyperthermia system with adjustable radio frequency source provided by the present invention is described in detail below with reference to the accompanying drawings.

[0040] Example 1:

[0041] See also Figure 1 , which shows a structural diagram of a radio frequency tumor hyperthermia system with an adjustable radio frequency source provided by the first embodiment of the present invention, the system includes a radio frequency source, a body temperature sensor, a radio frequency source controller, and a tumor positioning module;

[0042] The number of RF sources is greater than or equal to 2, and this embodiment is described by taking 4 RF sources as an example.

[0043] In this embodiment, multiple radio frequency sources jointly emit high-frequency electromagnetic waves to perform thermal ablation on the tumor, effectively solving the problems of fat overheating and insufficient heating energy deep in the body.

[0044] The body temperature sensor is installed at the location of each radio frequency source to collect the temperature generated by each radio frequency source on the body surface during radio frequency hyperthermia therapy.

[0045] In order to avoid the problem that multiple RF sources generate too much heat in the skin and fat during hyperthermia, and that adjacent electrode plates generate frequencies that are too close to each other and directly create loops, thereby generating heat on the surface of the human body and failing to affect deep parts, it is necessary to use an RF source controller to automatically control multiple RF sources so that multiple RF sources can cooperate with each other to ensure that the heat of tumor hyperthermia is eliminated while avoiding excessive heat generation on the surface of the human body.

[0046] The tumor localization module is used to obtain the tumor location based on the MRI device or CT device.

[0047] In this embodiment, the RF source controller includes two parts: a body temperature detection module and a RF control module.

[0048] The body temperature detection module is used to collect and record the temperature at each RF source location during hyperthermia therapy at each moment, and to determine in real time whether the temperature exceeds the upper temperature tolerance limit. RF sources located at locations exceeding the upper temperature tolerance limit are marked as abnormal, while those located within the upper temperature tolerance limit are marked as normal. In this embodiment, the upper temperature tolerance limit is set to 41 degrees Celsius; other values ​​may be set in other embodiments and are not specifically limited in this embodiment.

[0049] It should be noted that each RF source includes two electrodes, and a body temperature sensor is installed at each electrode position; when the temperature value output by any temperature sensor at the two electrode positions exceeds the upper limit of the tolerance temperature, the RF sources corresponding to the two electrodes are recorded as abnormal RF sources; when the temperature values ​​output by all temperature sensors at the two electrode positions do not exceed the upper limit of the tolerance temperature, the RF sources corresponding to the two electrodes are recorded as normal RF sources.

[0050] The RF control module is used to reduce the frequency of the abnormal RF source when an abnormal RF source appears, and change the frequency of the normal RF source according to the heat loss amount and distribution ratio generated by the abnormal RF source after the frequency reduction.

[0051] When the abnormal RF source appears again, the frequency of the abnormal RF source is reduced again, and the allocation ratio is adjusted according to the temperature change of the normal RF source after the frequency is changed at a historical moment. The frequency of the normal RF source is changed according to the heat loss generated by the abnormal RF source after the frequency is reduced again and the adjusted allocation ratio.

[0052] In the aforementioned RF control module, whenever an abnormal RF source appears, the frequency of the abnormal RF source is reduced to prevent excessive skin temperature. When the frequency is reduced, heat loss occurs at the tumor site, necessitating the increase in the power of the normal RF source to compensate for the heat loss at the tumor site. To reasonably increase the frequency of the normal RF source, the frequency must be adjusted proportionally based on the temperature change of each normal RF source when the frequency is changed. Each time an abnormal RF source appears, the skin and fat tissue in different parts of the body are different, and the heat recording patterns of RF sources in different parts of the body at different frequencies are also different. Therefore, in this embodiment, the frequency change ratio of each normal RF source is different to facilitate the specific use of different body parts and different frequency RF sources.

[0053] For example, when an abnormal RF source appears for the i-th time, according to the heat loss amount P i and distribution ratio a i Changing the frequency of the normal RF source;

[0054] When the abnormal RF source appears for the i+1th time, according to the heat loss P i+1 and distribution ratio a i+1 Change the frequency of the normal RF source; where a i+1 Not equal to a i ;a i+1 Compared to a i For example, a i+1 Is to adjust the distribution ratio a i The distribution ratio after adjustment is referred to as the adjusted distribution ratio;

[0055] When an abnormal RF source appears for the i+2th time, according to the heat loss P i+2 and distribution ratio a i+2 Change the frequency of the normal RF source, where a i+2 Not equal to a i+1 ;a i+2 Compared to a i+1 For example, a i+2 Is to adjust the distribution ratio a i+1 The distribution ratio after adjustment is referred to as the adjusted distribution ratio;

[0056] Therefore, the allocation ratio and the adjusted allocation ratio are relative to the two consecutive occurrences of abnormal RF sources.

[0057] During this process, the distribution ratio is dynamically adjusted in real time based on the temperature changes of specific parts of the patient and the working conditions of the radio frequency source.

[0058] In this embodiment, the specific method for obtaining the heat loss is:

[0059] The amount of heat loss was estimated based on the frequency of the reduced-frequency abnormal RF source and the location of the tumor.

[0060] For example, when an abnormal RF source appears for the i-th time, the frequency of the abnormal RF source is reduced, and the frequency of the abnormal RF source after the frequency reduction is recorded as A1 i , according to A1 i and the location of the tumor to estimate the amount of heat loss P i ;

[0061] When the abnormal RF source appears for the i+1th time, the frequency of the abnormal RF source is reduced. The frequency of the abnormal RF source after the frequency reduction is recorded as A1 i+1 , according to A1 i+1 and the location of the tumor to estimate the amount of heat loss P i+1 ;

[0062] As an example, in this embodiment, each time an abnormal radio frequency source appears, the frequency of the abnormal radio frequency source is reduced by 5%. Other embodiments may reduce the frequency by other values, which is not specifically limited in this embodiment.

[0063] If multiple abnormal RF sources appear simultaneously each time, the frequency of each abnormal RF source is reduced by 5%. At this time, the heat loss amount is estimated based on the frequencies of all the abnormal RF sources after the frequencies are reduced and the position of the tumor.

[0064] The amount of heat loss is estimated based on the frequency of the abnormal RF source after frequency reduction and the location of the tumor, specifically including:

[0065] First, a frequency-heat model is obtained. The input of the frequency-heat model is the tumor location, the location of each RF source, and the frequency of each RF source. The output is heat. Then, the frequency and location of the abnormal RF source after frequency reduction and the location of the tumor are substituted into the frequency-heat model to obtain the amount of heat loss.

[0066] In this embodiment, changing the frequency of the normal radio frequency source includes the following steps:

[0067] The heat loss amount is distributed to each normal RF source according to the distribution characteristics to obtain the frequency that each normal RF source needs to increase; the frequency of each normal RF source is changed according to the frequency that needs to be increased; the distribution characteristics include the above-mentioned distribution ratio and the adjusted distribution ratio.

[0068] For example, when an abnormal RF source appears for the i-th time, the heat loss P i According to the distribution ratio a iAssign it to each normal RF source to obtain the frequency that each normal RF source needs to increase; that is, when an abnormal RF source appears for the i-th time, the frequency of each normal RF source is increased.

[0069] When the abnormal RF source appears for the i+1th time, the heat loss P i+1 According to the distribution ratio a i+1 Assigned to each normal RF source to obtain the frequency that each normal RF source needs to increase; that is, when an abnormal RF source appears for the (i+1)th time, the frequency of each normal RF source is increased.

[0070] It should be noted that each normal RF source corresponds to a distribution feature. For example, when an abnormal RF source appears for the i-th time, there are 3 normal RF sources. When the distribution is based on the ratio of 0.1:0.8:0.1, the distribution ratio of the 3 normal RF sources is a i They are 0.1, 0.8, and 0.1 respectively.

[0071] It should be noted that the normal RF source when the abnormal RF source appears for the (i+1)th time is not necessarily the normal RF source when the abnormal RF source appears for the i-th time; the normal RF source needs to be re-acquired in real time each time the abnormal RF source appears.

[0072] Before hyperthermia, all RF sources are considered normal, and their initial allocation ratio is the same. For example, if there are four normal RF sources before hyperthermia, the allocation ratio of the four normal RF sources is set to the same, that is, 0.25:0.25:0.25:0.25. If an abnormal RF source occurs for the first, second, or third time, the allocation ratio needs to be adjusted based on the temperature change after the normal RF source changes its frequency at that time.

[0073] In summary, heat loss is distributed among the normal RF sources according to the distribution ratio, preventing persistent high temperatures at a single RF source location. Furthermore, the distribution ratio is adjusted based on the temperature changes after the normal RF source frequency changes over time. This ratio is dynamically adjusted based on the physiological conditions of specific tissue locations during the normal RF source's operation to accommodate the specific conditions of different patient locations.

[0074] As an example, the heat loss amount is distributed to each normal RF source according to the distribution characteristics to obtain the frequency that needs to be increased for each normal RF source, including the following steps:

[0075] The product of the heat loss amount and the distribution characteristic of each normal RF source is recorded as the heat loss amount distributed to each normal RF source.

[0076] For example, when an abnormal RF source appears for the i-th time, the heat loss amount P i According to the distribution ratio a iAllocated to each normal RF source, of which there are 3 normal RF sources, the allocation ratio is a i =0.1:0.8:0.1, then the heat loss of the first normal RF source is 0.1×P i The heat loss of the second normal RF source is 0.8×P i The heat loss of the third normal RF source is 0.1×P i .

[0077] For example, when an abnormal RF source appears for the i+1th time, the heat loss P i+1 According to the adjusted distribution ratio a i+1 Assigned to each normal RF source.

[0078] The frequency that needs to be increased for each normal RF source is obtained according to the amount of heat loss allocated to each normal RF source, the location of the tumor, and a frequency-heat model of the location of each normal RF source.

[0079] Example 2:

[0080] In this embodiment, as an optional example, the allocation ratio is adjusted according to the temperature change of the normal RF source after the frequency is changed at a historical moment, including the following method:

[0081] The average temperature of the normal RF source after the frequency is changed in the historical time is obtained and recorded as M. A larger M indicates that the normal RF source is prone to temperature accumulation. In this case, the allocation ratio of the normal RF source needs to be reduced. The reciprocal of the average values ​​corresponding to all normal RF sources is normalized to obtain the adjusted allocation ratio of each normal RF source.

[0082] The average temperature after the frequency is changed refers to the average temperature during a period of time between each frequency change and the next frequency change.

[0083] In this example, the amount of calculation is small, but the appropriateness of the distribution ratio when the abnormal heat source appeared last time is not taken into account. Instead, the ratio is directly redistributed, and the distribution ratio cannot be further adjusted step by step according to the specific situation of the patient. As a result, it is impossible to efficiently find a suitable distribution ratio to adapt to the heat therapy conditions of different parts of the patient.

[0084] In this embodiment, as a preferred example, the allocation ratio is adjusted according to the temperature change of the normal RF source after the frequency is changed at a historical moment, including the following method:

[0085] Assume that when an abnormal RF source appears for the i-th time, the heat loss P i According to the distribution ratio a i Assigned to each normal RF source, the frequency that each normal RF source needs to increase is obtained; that is, when an abnormal RF source appears for the i-th time, it is assigned according to the allocation ratio ai To allocate the frequency that needs to be increased to each normal RF source.

[0086] Then when the abnormal RF source appears for the i+1th time, the distribution ratio a needs to be adjusted. i Make adjustments to suit the patient's real-time physical condition, and express the adjusted distribution ratio as a i+1 .

[0087] Distribution ratio a i The specific steps to make adjustments are:

[0088] When the abnormal RF source appears for the i+1th time, the heat loss generated by the abnormal RF source after the frequency is reduced for the i+1th time is recorded as P i+1 ;

[0089] First, the heat loss P i+1 According to the distribution ratio a i The frequency L1 that needs to be increased is allocated to each normal radio frequency source, and the specific process has been described in the first embodiment and will not be repeated here.

[0090] It should be noted that the normal RF sources here refer to the normal RF sources when the abnormal RF sources appear for the (i+1)th time. These normal RF sources may be normal RF sources or abnormal RF sources in history.

[0091] The frequency L1 that needs to be increased for each normal RF source obtained at this time represents the frequency that needs to be increased when allocation is performed using the last allocation ratio, rather than the frequency that needs to be increased when an abnormal RF source appears this time.

[0092] For each normal RF source, the frequency change amount at each frequency change at a historical moment is calculated, and the adjusted allocation ratio of each normal RF source is obtained based on the difference between L1 and the frequency change amount at each frequency change and the temperature change after each frequency change; wherein changing the frequency includes increasing the frequency and decreasing the frequency.

[0093] The temperature change after each frequency change describes: the temperature characteristics of the body tissue at the normal location of the RF source during the historical operation of the normal RF source under different frequency changes, such as the characteristics of slow or rapid temperature increases and decreases. This characteristic is used to adjust the previous allocation ratio to make the current allocation ratio more suitable for the specific conditions of the patient's body tissue, such as avoiding a rapid temperature increase.

[0094] The difference between L1 and the frequency change amount at each frequency change describes: if the heat loss amount when the abnormal RF source appears at the current time (i.e., the i+1th time) is based on the distribution ratio a when the abnormal RF source appears last time (i.e., the i-th time), iWhen the distribution is performed, the difference between the frequency increase and the historical frequency change is different. Different differences correspond to different temperature characteristics. i The adjustment range is also different.

[0095] Therefore, this embodiment adjusts the previous allocation ratio a based on the difference in the frequency change and the temperature characteristics of the temperature change. i , which can ensure the adjusted distribution ratio a i+1 More adaptable to the specific conditions of the patient's body tissue.

[0096] As an example, the adjusted allocation ratio of each normal RF source is obtained according to the difference between L1 and the frequency change amount each time the frequency is changed and the temperature change after each frequency change, including the following method:

[0097] Obtain N frequency changes (excluding L1) with the smallest difference from L1 and record them as reference frequency changes. Obtain a temperature change rate based on the change in temperature after each frequency change. Each reference frequency change corresponds to a temperature change rate. Obtain an adjusted allocation ratio for each normal RF source based on the temperature change rates corresponding to all reference frequency changes. The adjusted allocation ratio is negatively correlated with the temperature change rate.

[0098] This process is also for each normal RF source when the abnormal RF source appears for the (i+1)th time.

[0099] This embodiment is described using N=5 as an example. Other values ​​may be used in other embodiments and are not specifically limited in this embodiment. When the number of frequency changes with the smallest difference from L1 is less than N, as many frequency changes with the smallest difference as possible are considered. The difference here refers to the absolute value of the difference.

[0100] The difference between the reference frequency change and L1 is small, so the temperature characteristics of the patient's body tissue (ie, the temperature change rate) corresponding to the reference frequency change can better reflect the distribution ratio a. i Is the increased frequency L1 appropriate, which reflects the distribution ratio a i The adjustment range.

[0101] As an example, the adjusted allocation ratio of each normal RF source is obtained according to the temperature change rate corresponding to all reference frequency changes, including the following method:

[0102] The temperature change rate is the absolute value of the average slope of the temperature over time after each frequency change, which indicates the magnitude of the effect of the frequency change on the temperature. The larger the mean value of the temperature change rate, the more likely the frequency change will cause a larger temperature change; the smaller the mean value of the temperature change rate, the more likely the frequency change will cause a smaller temperature change.

[0103] It should be noted that the average slope of the temperature over time after each frequency change refers to the average slope of the temperature over time during a period between each frequency change and the next frequency change.

[0104] The average of the temperature change rates corresponding to all reference frequency changes is recorded as k1, and k1 is used as the allocation index w of each normal RF source. The larger w is, the higher the allocation ratio a is. i The more the frequency L1 is increased, the more likely it is to cause a significant temperature change. Therefore, when an abnormal RF source appears, it is necessary to reduce a. i , to avoid the normal RF source from sharing more frequencies. When w= is smaller, it means that according to the last allocation ratio a i The more the frequency L1 is increased, the less likely it is to cause a significant temperature change. Therefore, the more a i , so that the normal RF source can share more frequencies.

[0105] The allocation index w of all normal RF sources is linearly normalized to obtain the normalized allocation index w1, which is in the range of 0 to 1. According to the allocation ratio a of each normal RF source, i And the normalized allocation index w1 obtains the adjusted allocation ratio a of each normal RF source i+1 The formula is: i+1 =a i (1-w1).

[0106] In other embodiments,

[0107] In this embodiment, only a i+1 It only needs to be negatively correlated with w1, and the specific calculation model is not limited.

[0108] It should be noted that in order to ensure that the sum of the adjusted allocation ratios of all normal radio frequency sources is equal to 1, it is also necessary to adjust the adjusted allocation ratio a of each normal radio frequency source. i+1 Normalization is performed again. This time, the normalization method uses the Softmax function. The Softmax function is a well-known technology and will not be described in detail in this embodiment.

[0109] Example 3:

[0110] As an example, the frequency-heat model is constructed as follows:

[0111] During each radiofrequency tumor hyperthermia treatment in history, the tumor location, the location of each radiofrequency source, and the average frequency of each radiofrequency source during the entire hyperthermia treatment process are recorded and used as a sample; the heat at the tumor location during each radiofrequency tumor hyperthermia treatment process is used as a label for the sample;

[0112] Then all the radiofrequency tumor hyperthermia treatment processes in the history correspond to multiple samples and their labels.

[0113] Considering that the heat at the tumor location cannot be directly obtained, but the heat at the tumor location is negatively correlated with the tumor ablation time, that is, the higher the heat, the shorter the tumor ablation time, this embodiment uses the inverse of the tumor ablation time as the label of each sample. However, it can still be considered that the label can represent the heat at the tumor location.

[0114] The tumor location can be obtained by magnetic resonance imaging (MRI) or CT technology, which will not be described in detail in this embodiment.

[0115] A frequency-heat model is trained using all samples and labels. The input of this model is the tumor location contained in each sample, the location of each RF source, and the average frequency of each RF source during the entire thermal therapy process. The output is the heat at the tumor location. It should be noted that the heat at the tumor location output by the frequency-heat model is expressed as the inverse of the tumor ablation time, and it is not necessary to output the actual and accurate heat at the tumor location.

[0116] Taking into account that the number of RF sources used in each thermal therapy process in history may be different, which leads to the non-uniform dimension of the input data of the frequency-heat model, then this embodiment fills the missing dimensions with 0, that is, the position and average frequency of the missing RF source are replaced with 0. This is a commonly used sample data preprocessing method and will not be described in detail in this embodiment.

[0117] The frequency-heat model of this embodiment is a 5th-order polynomial model containing parameters to be learned. In other embodiments, a Gaussian mixture model or a fully connected neural network model can be used. The method for updating the parameters to be learned during training is the stochastic gradient descent algorithm, and the loss function is the mean square error loss function. Whether it is a 5th-order polynomial model or a fully connected neural network model, the training method is the same and well-known, and will not be described in detail in this embodiment. The 5th-order polynomial model in other embodiments can also obtain the parameters to be learned by the least squares method, and the specific process will not be described in detail in this embodiment.

[0118] It should be noted that the aforementioned frequency-heat model is not an accurate measure of the frequency domain and heat of an RF source. This is because, firstly, the tissue structures of different patients undergoing hyperthermia vary, making it difficult to obtain a simple and accurate frequency-heat model. Secondly, tumors are located within the human body, making it impossible to measure the heat loss at the tumor's location. Considering that the purpose of all embodiments of the present invention is to assign frequencies to different RF sources, the heat loss measurement required in this embodiment is only an intermediate variable and is not used to measure actual physical laws. Therefore, this embodiment uses the aforementioned method to construct a frequency-heat model that can roughly estimate the amount of heat loss.

[0119] As an example, the heat loss amount is obtained based on the frequency and location of the abnormal RF source after frequency reduction, the location of the tumor, and the frequency-heat model, including the following methods:

[0120] The frequency and position of the abnormal RF source after frequency reduction, the frequency and position of the normal RF source, and the position of the tumor are substituted into the trained frequency-heat model, and the model output result is recorded as R1.

[0121] The frequency and position of the abnormal RF source before frequency reduction, the frequency and position of the normal RF source, and the position of the tumor are substituted into the trained frequency-heat model, and the model output result is recorded as R2.

[0122] R2-R1 is the heat loss.

[0123] As an example, the frequency that needs to be increased for each normal RF source is obtained based on the amount of heat loss allocated to each normal RF source, the location of the tumor, and a frequency-heat model of the location of each normal RF source, including the following methods:

[0124] When an abnormal RF source appears for the i-th time:

[0125] For all RF sources at this time, including the reduced abnormal RF sources and normal RF sources, the frequencies and locations of all RF sources and the location of the tumor are substituted into the trained frequency-heat model, and the model output result is recorded as R3;

[0126] The heat loss amount allocated to the jth normal RF source is recorded as p j .

[0127] The frequency that needs to be increased by the j-th normal RF source is recorded as the parameter to be solved x j , the frequency of the jth normal RF source is recorded as X j ; x j +X j , the frequencies of all RF sources other than the jth normal RF source, the positions of all RF sources, and the position of the tumor are substituted into the trained frequency-heat model to solve x jMake the frequency-heat model output equal to R3+p j .

[0128] The solved x j The frequency that needs to be increased for the j-th normal radio frequency source is used, and the frequencies that need to be increased for other normal radio frequency sources are obtained similarly.

[0129] Similarly, when an abnormal radio frequency source appears for the (i+1)th time, the same method is used to obtain the frequency that needs to be increased for each normal radio frequency source.

[0130] It should be noted that when the frequency-heat model is a polynomial model, the function analytical method can be used to solve x j ; This embodiment uses the stochastic gradient descent method to solve x j In other embodiments, when a fully connected neural network is used, the stochastic gradient descent method can also be used to solve x j ; Among them, the stochastic gradient descent method is not only a commonly used and well-known algorithm for training models, but also an optimization algorithm for solving the optimal parameters. Their essence is the same, and this embodiment will not repeat the specific process of the stochastic gradient descent method.

[0131] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A radio frequency tumor hyperthermia system with an adjustable radio frequency source, characterized in that: The system includes a radio frequency source, a body temperature sensor, and a radio frequency source controller; The number of radio frequency sources is greater than or equal to 2, and a body temperature sensor is installed at each radio frequency source position; The RF source controller includes the following modules: The body temperature detection module is used to collect and record the temperature of each RF source location at each moment during hyperthermia treatment, and to determine in real time whether the temperature exceeds the upper limit of the tolerance temperature. The RF source at the location exceeding the upper limit of the tolerance temperature is recorded as an abnormal RF source, and the RF source at the location not exceeding the upper limit of the tolerance temperature is recorded as a normal RF source; A radio frequency control module is used to reduce the frequency of an abnormal radio frequency source when an abnormal radio frequency source appears, and change the frequency of a normal radio frequency source according to the amount of heat loss generated by the abnormal radio frequency source after the frequency reduction and the distribution ratio; When the abnormal RF source appears again, the frequency of the abnormal RF source is reduced again, the allocation ratio is adjusted according to the temperature change of the normal RF source after the frequency is changed in the historical moment, and the frequency of the normal RF source is changed according to the heat loss generated by the abnormal RF source after the frequency is reduced again and the adjusted allocation ratio; The specific method for obtaining the heat loss is: The amount of heat loss is estimated based on the frequency of the abnormal RF source after frequency reduction and the location of the tumor; Changing the frequency of the normal radio frequency source includes the following steps: Allocate the heat loss to each normal radio frequency source according to the distribution characteristics, and obtain the frequency that each normal radio frequency source needs to increase; The frequency of each normal radio frequency source is changed according to the frequency that needs to be increased; the allocation characteristics include the allocation ratio and the adjusted allocation ratio, and each normal radio frequency source corresponds to one allocation characteristic.

2. The radio frequency tumor hyperthermia system with an adjustable radio frequency source according to claim 1, characterized in that: The step of estimating the amount of heat loss based on the frequency of the abnormal radio frequency source after frequency reduction and the location of the tumor comprises the following steps: The frequency of the abnormal RF source after frequency reduction and the location of the tumor are substituted into the frequency-heat model to estimate the amount of heat loss.

3. The radio frequency tumor hyperthermia system with an adjustable radio frequency source according to claim 1, characterized in that: The step of allocating the heat loss to each normal RF source according to the distribution characteristics to obtain the frequency that each normal RF source needs to increase includes the following specific steps: The product of the heat loss amount and the allocation characteristics of each normal RF source is recorded as the heat loss amount allocated to each normal RF source. The allocated heat loss amount and the location of the tumor are substituted into the frequency-heat model to obtain the frequency that each normal RF source needs to increase.

4. The radio frequency tumor hyperthermia treatment system with an adjustable radio frequency source according to claim 1, characterized in that: The specific steps of adjusting the allocation ratio according to the temperature change of the normal radio frequency source after the frequency is changed at a historical moment are as follows: The heat loss generated by the abnormal RF source after the frequency is reduced again is recorded as P, and the heat loss P is distributed to each normal RF source according to the distribution ratio to obtain the frequency that each normal RF source needs to increase, which is recorded as L1; For each frequency change amount of each normal RF source at each frequency change in a historical moment, the adjusted allocation ratio of each normal RF source is obtained according to the difference between L1 and the frequency change amount at each frequency change and the temperature change after each frequency change.

5. The radio frequency tumor hyperthermia treatment system with an adjustable radio frequency source according to claim 4, characterized in that: The step of obtaining the adjusted distribution ratio of each normal RF source according to the difference between L1 and the frequency change amount at each frequency change and the temperature change after each frequency change is as follows: Several frequency changes with the smallest difference from L1 are obtained and recorded as reference frequency changes. The temperature change rate is obtained based on the change in temperature after each frequency change. Each reference frequency change corresponds to a temperature change rate. The adjusted distribution ratio of each normal RF source is obtained based on the temperature change rates corresponding to all reference frequency changes. The adjusted distribution ratio is negatively correlated with the temperature change rate.

6. The radio frequency tumor hyperthermia treatment system with an adjustable radio frequency source according to claim 2 or 3, characterized in that: The specific steps for obtaining the frequency-heat model are as follows: During each radiofrequency tumor hyperthermia treatment in history, the tumor location, the location of each radiofrequency source, and the average frequency of each radiofrequency source during the entire treatment process were recorded and used as a sample. The inverse of the tumor ablation time during each radiofrequency tumor hyperthermia treatment process was used as the sample label. The input of the frequency-heat model is the tumor location contained in each sample, the location of each RF source, and the frequency of each RF source, and the output is the heat at the tumor location; The frequency-heat model is trained using samples and labels obtained from all historical radiofrequency tumor hyperthermia treatment processes.

7. The radio frequency tumor hyperthermia treatment system with an adjustable radio frequency source according to claim 5, characterized in that: The temperature change rate is the absolute value of the average slope of the temperature over time after each frequency change.

8. The radio frequency tumor hyperthermia treatment system with an adjustable radio frequency source according to claim 5, characterized in that: The step of obtaining the adjusted distribution ratio of each normal RF source according to the temperature change rate corresponding to all reference frequency changes includes the following specific steps: The average of the temperature change rates corresponding to all reference frequency changes is used as the allocation index w of each normal RF source. The allocation index w of the normal RF source is linearly normalized to obtain w1. The allocation ratio of each normal RF source is recorded as a. The adjusted allocation ratio of each normal RF source is negatively correlated with w1 and positively correlated with a.

9. The radio frequency tumor hyperthermia treatment system with an adjustable radio frequency source according to claim 1, characterized in that: It also includes a tumor positioning module for obtaining the tumor position according to the magnetic resonance imaging device.

10. The radio frequency tumor hyperthermia treatment system with an adjustable radio frequency source according to claim 1, characterized in that: Each RF source contains two electrodes, and a body temperature sensor is installed at each electrode position. When the temperature value output by any temperature sensor at the two electrode positions exceeds the upper limit of the tolerance temperature, the RF sources corresponding to the two electrodes are recorded as abnormal RF sources; when the temperature values ​​output by all temperature sensors at the two electrode positions do not exceed the upper limit of the tolerance temperature, the RF sources corresponding to the two electrodes are recorded as normal RF sources.

Images