Beam pulse dose prediction method, device, equipment and storage medium

By setting sensors outside the beam flow pipeline of the medical accelerator to obtain signals and perform prediction model processing, the problem of inaccurate beam pulse dose recognition is solved, and more accurate and simple prediction is achieved, improving the accuracy and safety of treatment.

CN118915117APending Publication Date: 2024-11-08ZHONGJIU FLASH MEDICAL TECHNOLOGY CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411000862.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-25
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

In the use scenarios of medical accelerators, the dose identification of beam pulses is inaccurate. The prior art requires opening holes in the beam pipeline to affect stability and uniformity, and the method based on simulation calculation is complex and inaccurate enough.

Method used

By setting sensors outside the beam pipeline to obtain the beam signal and input it into a preset dose prediction model for processing, avoiding the impact of openings and simplifying the calculation process.

Benefits of technology

Achieve more accurate and simple beam pulse dose prediction, ensuring treatment effect and patient safety, improving the response speed and accuracy of dose monitoring, and reducing the complexity of simulation-based computing.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118915117A_ABST
    Figure CN118915117A_ABST
Patent Text Reader

Abstract

The invention provides a beam pulse dose prediction method and device, equipment and a storage medium. The method comprises the following steps: firstly, acquiring a beam signal in a beam pipeline; the beam signal is obtained through a sensor arranged outside the beam pipeline; the beam signal is used for representing the real-time change of the charge quantity of a charged particle beam in the beam pipeline, and the charged particle beam is generated by a particle accelerator; and inputting the beam signal into a preset dose prediction model for processing to obtain the dose of the beam pulse in the beam pipeline. According to the method, on one hand, the defect that in the prior art, a hole needs to be formed in a beam pipeline, so that the beam pulse prediction accuracy is affected is overcome, and on the other hand, the beam signal is directly and continuously processed through the preset dosage prediction model, so that the beam pulse dosage corresponding to the beam signal is obtained; compared with a method based on analog computation in the prior art, the method is simpler and more accurate in computation.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of particle accelerators, and in particular to a beam pulse dose prediction method, device, equipment and storage medium. Background Art

[0002] A medical accelerator is a medical device specifically used for radiotherapy. It accelerates charged particles (such as electrons, protons, heavy ions, etc.) to produce high-energy rays for the treatment of cancer and other diseases. A medical accelerator can include two parts: the accelerator body and the beam transmission system.

[0003] In the prior art, in the use scenario of a medical accelerator, there is a technical problem of inaccurate dose identification of the beam pulse output by the medical accelerator. Summary of the invention

[0004] The purpose of the present invention is to overcome the above technical deficiencies and provide a beam pulse dose prediction method, device, equipment and storage medium to solve the technical problem in the prior art of inaccurate dose identification of beam pulses output by a medical accelerator in the use scenario of a medical accelerator.

[0005] In order to achieve the above technical objectives, the present invention adopts the following technical solutions:

[0006] In a first aspect, the present invention provides a beam pulse dose prediction method, the method comprising:

[0007] Acquire a beam signal in the beam pipeline; wherein the beam signal is acquired by a sensor arranged outside the beam pipeline; wherein the beam signal is a signal used to characterize the real-time change of the charge amount of the charged particle beam in the beam pipeline, and the charged particle beam is generated by a particle accelerator;

[0008] The beam signal is input into a preset dose prediction model for processing to obtain the dose of the beam pulse in the beam pipeline.

[0009] In a second aspect, the present invention provides a device for predicting beam pulse dose, the device comprising:

[0010] An acquisition module is used to acquire a beam signal in a beam pipeline; wherein the beam signal is acquired by a sensor arranged outside the beam pipeline; wherein the beam signal is a signal used to characterize the real-time change of the charge amount of a charged particle beam in the beam pipeline, and the charged particle beam is generated by a particle accelerator;

[0011] A processing module is used to input the beam signal into a preset dose prediction model for processing to obtain the dose of the beam pulse in the beam pipeline.

[0012] The third aspect proposes an electronic device, comprising: a memory, and one or more processors communicatively connected to the memory; the memory stores instructions executable by the one or more processors, and the instructions are executed by the one or more processors so that the one or more processors implement the above-mentioned method.

[0013] A fourth aspect provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program implements the above method when executed by a processor.

[0014] Beneficial effects:

[0015] The present invention first obtains a beam signal in a beam pipe; wherein the beam signal is obtained by a sensor disposed outside the beam pipe; wherein the beam signal is a signal used to characterize the real-time change of the charge amount of a charged particle beam in the beam pipe, and the charged particle beam is generated by a particle accelerator; and then the beam signal is input into a preset dose prediction model for processing to obtain the dose of the beam pulse in the beam pipe. On the one hand, this method avoids the defect of the prior art that a hole needs to be opened in the beam pipe, thereby affecting the accuracy of beam pulse prediction. On the other hand, the beam signal is directly processed through a preset dose prediction model to obtain the beam pulse dose corresponding to the beam signal. Compared with the method based on simulation calculation in the prior art, this method is simpler and more accurate in calculation. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a schematic diagram of a beam pulse dose prediction method used in an embodiment of the present invention;

[0017] Figure 2 is a schematic diagram of a beam pulse dose prediction method used in an embodiment of the present invention;

[0018] Figure 3 is a schematic diagram of a beam pulse dose prediction method used in an embodiment of the present invention;

[0019] Figure 4 is a block diagram of a beam pulse dose prediction device used in an embodiment of the present invention;

[0020] Figure 5 It is a block diagram of an electronic device used in an embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0022] Overview:

[0023] In the relevant technology, radiotherapy is an important treatment method, which mainly uses high-energy rays (such as X-rays, gamma rays, electron beams, etc.) to irradiate diseased tissues to kill cancer cells or inhibit their growth. In this process, accurate control of radiation dose is the key to ensuring treatment effect and patient safety. Therefore, dose monitoring technology is of great significance in radiotherapy. Particle accelerators are important equipment in radiotherapy, which can generate high-energy rays by accelerating charged particles. However, due to the complex working principle of particle accelerators and the influence of various factors, the dose of the beam pulses it outputs is often difficult to accurately control. Therefore, how to monitor the dose of the beam pulses output by the accelerator in real time to ensure the treatment effect and protect the safety of patients is an important issue facing current radiotherapy technology.

[0024] In some technical solutions, it is necessary to open holes in the beam pipeline to set up corresponding sensors, but the openings will affect the stability and uniformity of the beam, and then affect the detection accuracy of the beam, and accordingly, will also affect the treatment effect. Secondly, the response speed of these sensors is slow and cannot reflect the changes in the beam in real time, which is not conducive to the precise control of the dose. In some technical solutions, the dose of the beam is predicted according to the working parameters of the accelerator by adopting a method based on simulation calculation. Specifically, the method based on simulation calculation is a method that uses computer simulation and numerical calculation technology to study and predict the behavior of complex systems. This method usually requires the establishment of complex mathematical models and calculation models, and the model is solved by numerical methods to obtain the behavior and performance prediction results of the system. For example, certain assumptions and simplifications are required when establishing the model, and these assumptions may affect the accuracy of the simulation results. Secondly, the parameter selection and sensitivity analysis in the model have a great impact on the results, and different parameter values ​​may lead to different simulation results. Finally, complex models and large-scale calculations require a lot of computing resources and time, which may limit the accuracy and efficiency of the simulation.

[0025] In summary, in the prior art, in the use scenario of a medical accelerator, there is a technical problem of inaccurate dose identification of the beam pulse output by the medical accelerator.

[0026] In response to the technical problem, the present invention first obtains the beam signal in the beam pipe; wherein the beam signal is obtained by a sensor arranged outside the beam pipe; wherein the beam signal is a signal used to characterize the real-time change of the charge amount of the charged particle beam in the beam pipe, and the charged particle beam is generated by a particle accelerator; and then the beam signal is input into a preset dose prediction model for processing to obtain the dose of the beam pulse in the beam pipe. On the one hand, this method avoids the defect of the prior art that a hole needs to be opened in the beam pipe, thereby affecting the accuracy of the beam pulse prediction. On the other hand, the beam signal is directly processed through the preset dose prediction model to obtain the beam pulse dose corresponding to the beam signal. Compared with the method based on simulation calculation in the prior art, the calculation of this method is simpler and more accurate.

[0027] According to an embodiment of the present invention, a beam pulse dose prediction method is provided. Figure 1 ,include:

[0028] Step S102: Acquire a beam signal in the beam pipe; wherein the beam signal is acquired by a sensor arranged outside the beam pipe; wherein the beam signal is a signal for characterizing a real-time change in the charge amount of a charged particle beam in the beam pipe, and the charged particle beam is generated by a particle accelerator.

[0029] In this embodiment, the acquisition action is represented by obtaining a beam signal through a sensor disposed outside the beam pipeline, and the signal is used to characterize the real-time change of the charge amount of the charged particle beam in the beam pipeline. The sensor can be used to detect and record the change of the charge amount of the charged particle beam in the beam pipeline, and transmit the data to the system for subsequent processing.

[0030] In this embodiment, the beam signal can be a voltage signal or a current signal, and its magnitude and change reflect the change of the charge amount of the charged particle beam in the beam pipe over time. By measuring and recording the change of this signal, the charge information of the beam can be obtained in real time, providing a basis for real-time monitoring of the dose.

[0031] In this embodiment, the beam pipe is a part of the medical accelerator, which is used to guide and transmit the charged particle beam. The beam pipe is usually composed of a vacuum pipe and a magnetic field system, which can ensure that the charged particle beam remains stable and focused during the transmission process.

[0032] In this embodiment, the placement of the sensor is very critical because it affects the accuracy and real-time performance of dose monitoring. Specifically, the sensor is arranged around the beam pipe in a non-invasive manner to avoid affecting the stability and uniformity of the beam. Specifically, the sensor can be placed on a specially designed bracket or fixture that can ensure that the sensor maintains a certain distance from the beam pipe while maintaining a stable and fixed relative position.

[0033] In this embodiment, the number of sensors depends on the length of the beam pipeline, the accuracy required for monitoring, and the specific configuration of the particle accelerator. Specifically, sensors need to be set at least at key positions in the beam pipeline to ensure that changes in the beam can be fully monitored. For longer beam pipelines or situations where high-precision monitoring is required, multiple sensor arrays can be set. More specifically, the position of the sensor can be selected in an area that can capture the changes in the electromagnetic field caused by the particle beam to the greatest extent. It is understandable that this area should be an area outside the beam pipeline, rather than an area inside the beam pipeline. The area can be determined by preliminary simulation or experiment. The sensors can be evenly distributed along the beam pipeline, or they can be concentrated in one or more target areas, which can be where the beam is most likely to change or where precise control is most needed.

[0034] In a specific embodiment, the sensor model used can be HMC5883L, which is a three-axis magnetoresistive sensor with high sensitivity and low power consumption, suitable for accurately measuring changes in magnetic fields, including those caused by particle beams. The operating frequency is 1MHz and the inductance is 1μH, which ensures that the sensor can respond quickly and accurately to charge changes in particle beams.

[0035] Step S104: inputting the beam signal into a preset dose prediction model for processing to obtain the dose of the beam pulse in the beam pipeline.

[0036] In this embodiment, the dose prediction model can be a pre-trained machine learning model. Specifically, it can be a machine learning model capable of performing regression analysis. For example, it can be a linear regression model and a decision tree model. It is understandable that in medical applications, especially in the field of radiotherapy, it is very critical to predict the beam pulse dose in the beam pipeline. Real-time monitoring and adjustment of the dose are required to ensure that the patient receives accurate treatment. Therefore, the dose prediction model needs to be able to quickly process the beam signal and quickly output the dose prediction result. Although the dose needs to be predicted quickly, the accuracy of dose prediction in medical applications is also very high. Therefore, in this embodiment, a machine learning model capable of performing regression analysis is used. On the one hand, its computational complexity is low, and it is suitable for quickly processing beam signals and performing dose prediction in real time. This ensures that accurate dose prediction results can be obtained in a timely manner in medical applications. On the other hand, in the case of pre-training, this can ensure accuracy and provide fast dose prediction results.

[0037] In summary, in this embodiment, firstly, the beam signal in the beam pipe is obtained; wherein, the beam signal is obtained by a sensor arranged outside the beam pipe; wherein, the beam signal is a signal used to characterize the real-time change of the charge amount of the charged particle beam in the beam pipe, and the charged particle beam is generated by a particle accelerator; and then the beam signal is input into a preset dose prediction model for processing to obtain the dose of the beam pulse in the beam pipe. On the one hand, this method avoids the defect of the prior art that a hole needs to be opened in the beam pipe, thereby affecting the accuracy of the beam pulse prediction. On the other hand, the beam signal is directly processed through the preset dose prediction model to obtain the beam pulse dose corresponding to the beam signal. Compared with the method based on simulation calculation in the prior art, the calculation of this method is simpler and more accurate.

[0038] In some embodiments, in the above method, the sensor is arranged outside the beam pipe in a preset distance. In this embodiment, the preset distance can be determined by experiments or tests, and can be several centimeters or tens of centimeters. In this embodiment, by arranging the sensor outside the beam pipe, it is possible to avoid the sensor from interfering with the transmission and focusing of the charged particle beam inside the beam pipe. In this way, the transmission quality and stability of the charged particle beam can be ensured, and will not be affected by the sensor.

[0039] In some embodiments, the sensors are arranged outside the beam pipe at even intervals in the circumferential direction. In this embodiment, by arranging the sensors at even intervals in the circumferential direction, it is possible to ensure that the entire area around the beam pipe is fully monitored. In this way, beam signals can be obtained more comprehensively, and the understanding of beam characteristics and the accuracy of monitoring can be improved.

[0040] In some embodiments, the sensor is an inductive sensor or a capacitive sensor. In this embodiment, the inductive sensor and the capacitive sensor do not need to directly contact the monitored object, and can achieve monitoring through the induction principle. This can avoid direct contact between the sensor and the beam pipeline, reduce the impact on the beam pipeline, and also facilitate installation and maintenance.

[0041] In some embodiments, before the step of inputting the beam signal into a preset dose prediction model for processing to obtain the dose of the beam pulse, Figure 2 As shown, the method also includes:

[0042] Step S202: construct a data set; wherein the data set includes a plurality of dose monitoring data, each dose monitoring data includes a beam pulse dose value and a beam signal in a corresponding beam pipe. It is understandable that the beam pulse dose value is also a label in the data set. In some embodiments, the corresponding sensor can be directly configured in the beam pipe to collect the beam pulse dose value and the beam signal at multiple moments as a data set. In some embodiments, the data set can also be generated by simulation calculation or simulation software. For example, a physical model is used to calculate the beam signal and the corresponding beam pulse dose value under different conditions.

[0043] In this embodiment, the dose monitoring data of the data set may be preprocessed, such as denoising and normalization.

[0044] In this embodiment, before step S204, some preprocessing may be performed on the beam signal, for example, denoising or normalization may be performed on the beam signal, so as to optimize the accuracy of model training.

[0045] Step S204: Divide the data set into a training set and a test set according to a certain ratio.

[0046] In this implementation, the training set and the test set may be divided into a ratio of 5:1.

[0047] Step S206: Use the training set to train the initial dose prediction model to obtain a trained dose prediction model.

[0048] In this embodiment, the initial dose prediction model can be a linear regression model, a decision tree model, a random forest model or a support vector machine model.

[0049] Step S208: Use the test set to test the trained dose prediction model.

[0050] Step S210: When the test set passes the test, the preset dose prediction model is obtained.

[0051] In this embodiment, if the test fails, the model can be trained multiple times using the training set so that the model can learn the feature distribution in the training set, thereby enabling the model to pass the test of the test set.

[0052] In some embodiments, the initial dose prediction model is a linear regression model, a decision tree model, a random forest model or a support vector machine model. In this embodiment, the above model is used. On the one hand, its computational complexity is low, which is suitable for fast processing of beam signals and dose prediction in real time. This ensures that accurate dose prediction results can be obtained in a timely manner in medical applications. On the other hand, in the case of pre-training, this can ensure accuracy and provide fast dose prediction results.

[0053] In some embodiments, in the above method, before the step of obtaining the beam signal in the beam pipeline, as Figure 3 As shown, the method also includes:

[0054] Step S302: determining a target area of ​​the beam pipeline; the target area is used to characterize an area that can capture the electromagnetic field changes caused by the particle beam to the greatest extent.

[0055] In this embodiment, the target area can be determined by a variety of methods. For example, during the use of the medical accelerator, sensors can be placed at multiple locations outside the beam pipe, and the charge amount change of the charged particle beam can be observed to determine which areas are the most suitable target areas for placing sensors. It is also possible to set a sensor and change different positions for measurement to determine the target area. It is also possible to directly use computer simulation software to simulate the electromagnetic field distribution of the charged particle beam in the space around the beam pipe. Through simulation calculation, it is possible to predetermine in which areas the charge amount change of the charged particle beam is most significant, thereby determining the target area.

[0056] Step S304: Setting at least one sensor in the target area.

[0057] In this embodiment, one sensor or a plurality of sensors may be arranged in the target area, and the sensors may be evenly arranged in the target area.

[0058] In this embodiment, by arranging sensors at key positions of the beam pipeline, it is possible to ensure that changes in the beam, including changes in the electromagnetic field, are fully monitored, so that beam signals can be acquired more accurately, thereby improving the accuracy and real-time performance of dose prediction.

[0059] In summary, the beam pulse dose prediction method provided in the above-mentioned multiple embodiments can, firstly, realize real-time monitoring of the dose of the beam pulse output by the accelerator, which is of great significance for improving the accuracy and safety of radiotherapy. Secondly, the present invention can avoid opening holes in the beam pipe, thereby ensuring the stability and uniformity of the beam and improving the treatment effect. In addition, the method of the present invention can also improve the response speed of dose monitoring, realize real-time feedback of beam changes, and facilitate precise control of dose. Finally, the present invention can also reduce the demand for complex models and a large amount of computing resources for methods based on simulation calculations, simplify the process of dose prediction, and improve the accuracy of prediction results. Therefore, the present invention has broad market demand and good application prospects.

[0060] According to an embodiment of the present invention, a device for predicting beam pulse dose is provided, such as Figure 4 As shown, the method device includes:

[0061] An acquisition module is used to acquire a beam signal in a beam pipeline; wherein the beam signal is acquired by a sensor arranged outside the beam pipeline; wherein the beam signal is a signal used to characterize the real-time change of the charge amount of a charged particle beam in the beam pipeline, and the charged particle beam is generated by a particle accelerator;

[0062] A processing module is used to input the beam signal into a preset dose prediction model for processing to obtain the dose of the beam pulse in the beam pipeline.

[0063] According to an embodiment of the present invention, an electronic device is provided. Figure 5 The electronic device in this embodiment may include one or more of the following components: a processor, a network interface, a memory, a non-volatile memory, and one or more applications, wherein the one or more applications may be stored in the non-volatile memory and configured to be executed by one or more processors, and the one or more programs are configured to execute the method described in the aforementioned method embodiment.

[0064] According to an embodiment of the present invention, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a computer, the computer executes the method described in any of the above embodiments.

[0065] According to an embodiment of the present invention, a computer program product including instructions is also provided. When the instructions are executed by a computer, the computer executes the method described in any one of the above embodiments.

[0066] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0067] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and this embodiment will not be described in detail here.

[0068] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0069] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0070] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A beam pulse dose prediction method, characterized in that: The method comprises: Acquire a beam signal in the beam pipeline; wherein the beam signal is acquired by a sensor arranged outside the beam pipeline; wherein the beam signal is a signal used to characterize the real-time change of the charge amount of the charged particle beam in the beam pipeline, and the charged particle beam is generated by a particle accelerator; The beam signal is input into a preset dose prediction model for processing to obtain the dose of the beam pulse in the beam pipeline.

2. The method according to claim 1, characterized in that The sensor is arranged outside the beam pipe at a preset distance.

3. The method according to claim 1, characterized in that The sensors are arranged outside the beam pipe at even intervals in the circumferential direction. The method according to claim 1 , wherein the sensor is an inductive sensor or a capacitive sensor.

5. The method according to claim 1, before the step of inputting the beam signal into a preset dose prediction model for processing to obtain the dose of the beam pulse, the method further comprises: Constructing a data set; wherein the data set includes a plurality of dose monitoring data, each dose monitoring data includes a beam pulse dose value and a beam signal in a corresponding beam pipeline; Performing data preprocessing on the beam signal; wherein the data preprocessing includes denoising processing or normalization processing; Dividing the data set into a training set and a test set according to a certain ratio; Using the training set to train an initial dose prediction model to obtain a trained dose prediction model; Using the test set to test the trained dose prediction model; When the test set passes the test, the preset dose prediction model is obtained.

6. The method according to claim 5, wherein the initial dose prediction model is a linear regression model, a decision tree model, a random forest model or a support vector machine model.

7. The method according to claim 1, before the step of acquiring the beam signal in the beam pipeline, the method further comprises: Determine the target area of ​​the beam pipeline; The target region is used to characterize a region that can capture the electromagnetic field changes caused by the particle beam to the greatest extent; At least one sensor is arranged in the target area.

8. A device for predicting beam pulse dose, characterized in that: The device comprises: An acquisition module is used to acquire a beam signal in a beam pipeline; wherein the beam signal is acquired by a sensor arranged outside the beam pipeline; wherein the beam signal is a signal used to characterize the real-time change of the charge amount of a charged particle beam in the beam pipeline, and the charged particle beam is generated by a particle accelerator; A processing module is used to input the beam signal into a preset dose prediction model for processing to obtain the dose of the beam pulse in the beam pipeline.

9. An electronic device, characterized in that: include: a memory, and one or more processors communicatively coupled to the memory; The memory stores instructions that can be executed by the one or more processors. The instructions are executed by the one or more processors to enable the one or more processors to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Citation Information

Cited By

  • Induced radioactivity assessment method suitable for particle accelerator beam tube

    CN120686303A