Beam current automatic debugging method and system of proton treatment system

Abstract

The invention provides an automatic beam debugging method of a proton treatment system. The method comprises the following steps: fixedly mounting external measurement equipment of a beam on a treatment head; a processor of the automatic debugging work station starts to execute a beam automatic beam adjusting program, and beam adjusting target parameters are set; the accelerator loads the automatic loading parameters and the irradiation scheme for irradiation; the ionization chamber and external measurement equipment are used for measuring the performance parameters of the beam current and sending the performance parameters to the automatic debugging work station; and if the angle is within the required threshold range, storing the parameters and debugging the next rack angle, otherwise, adjusting the magnet parameters and sending the adjusted magnet parameters and the irradiation scheme to the accelerator for next iteration. The invention further provides an automatic beam debugging system of the proton treatment system. According to the invention, efficient and automatic debugging of the beam current under different rack rotation angles is realized, the efficiency of the proton treatment system in initial debugging and daily maintenance is remarkably improved, and the method has important significance in guaranteeing the clinical treatment effect.

Description

Technical Field

[0001] The present invention belongs to the technical field of medical devices, and in particular relates to a beam automatic adjustment method and system for a proton therapy system. Background Art

[0002] Tumor radiotherapy uses high-energy rays, including X-rays, gamma rays, protons, and heavy ion rays, to treat tumors through the killing effect of rays on cells. Protons have become an important radiotherapy method because of their unique Bragg peak, which allows them to concentrate doses on tumors without causing any harm to surrounding healthy tissues. The treatment room of a proton therapy system usually includes components such as a gantry, a treatment head, and a treatment bed. During radiotherapy, the gantry is rotated to different angles to meet the needs of different clinical proton incidence paths.

[0003] During the beam debugging process of the proton therapy system, the beam transport system is required to achieve stable beam transmission for complex working conditions such as different beam energies and different irradiation angles of the rotating gantry. Usually, beam debugging is required based on the beamline beam optical model, and beam adjustment is completed by manual intervention.

[0004] Due to various nonlinear factors of beamline magnets and deviations of magnet parameters under different working conditions, debuggers need to rely on a large amount of beam test data and find the actual working point of each magnet through multiple iterations. This process is not only time-consuming and labor-intensive, but also leads to low efficiency of beam debugging.

[0005] In addition, in the daily operation of the proton therapy system, the beam current will fluctuate, and the beam current fluctuation under the gantry angle and energy needs to be monitored regularly. For beam current parameters that do not meet the requirements, corresponding debugging must be carried out in a timely manner.

[0006] Therefore, beam debugging is not only a phased task, but also a long-term and labor-intensive continuous process.

[0007] In the prior art, beam debugging of proton therapy systems usually relies on manual adjustment and traditional optical models, which has a series of shortcomings. The closest implementation scheme of the present invention usually includes the following aspects:

[0008] (1) Manual debugging solution:

[0009] The current debugging process mainly relies on professionally trained debuggers to manually adjust the various magnet parameters of the beam system based on experience and a series of measured data. This usually involves multiple measurements and observations of the beam, and gradually converges to the optimal working point of the magnet through data analysis. This process is time-consuming and easily affected by human factors. In addition, for complex beam parameter adjustments, debuggers may need to make multiple attempts, resulting in low efficiency.

[0010] (2) Target monitoring system:

[0011] Some existing solutions have adopted target monitoring systems, which can monitor the basic parameters of the beam in real time, such as beam intensity and energy. However, these systems mostly monitor a single parameter and lack comprehensive beam stability analysis and intelligent feedback mechanisms, so that after problems are detected, they still need to rely on manual corrections by debuggers.

[0012] (3) Simplified optical model:

[0013] Although the optical models used in some technologies can guide the debugging process, they often do not take into account a variety of complex factors, such as the changes in the behavior of the beam at different energies and angles, resulting in insufficient debugging accuracy. Therefore, such models are usually not flexible enough to adapt to the needs of different operating conditions.

[0014] (4) Fixed debugging procedure:

[0015] Many proton therapy system commissioning schemes use fixed commissioning procedures and standard processes that lack adaptive capabilities. These fixed procedures do not have the ability to adjust in time when faced with new beam states or operating conditions, thus limiting the adaptability and efficiency of the system.

[0016] Therefore, the existing proton therapy system has the following problems in beam debugging for the rotating gantry:

[0017] (1) Low debugging efficiency:

[0018] Existing beam debugging methods usually rely on manual operation and manual adjustment, which makes the debugging process time-consuming and inefficient, especially when the rotating frame angle needs to be adjusted frequently.

[0019] (2) Lack of flexibility:

[0020] During the process of debugging the beam at different rotating gantry angles, existing technologies may not be able to achieve real-time and automatic adjustments, which limits the flexibility of the system in a dynamic environment.

[0021] (3) Measurement and feedback delay:

[0022] The beam measurement and feedback links in the prior art may have time delays, resulting in the operator being unable to obtain the required beam parameters in real time, thereby affecting the treatment effect and efficiency.

[0023] (4) Untimely response to clinical needs:

[0024] The existing beam debugging system may not be able to respond quickly to changes in clinical needs, resulting in the inability to adjust the beam parameters in time during treatment, which may affect the patient's treatment effect.

[0025] (5) Lack of intelligent and automated functions:

[0026] Traditional debugging methods usually do not have the ability to perform intelligent analysis based on historical data, lack machine learning and adaptive adjustment functions, and thus cannot effectively improve the accuracy and automation level of debugging.

[0027] In summary, the existing beam debugging scheme faces problems such as low efficiency, lack of flexibility and expensive labor costs. Therefore, it is necessary to achieve a more efficient and reliable proton therapy beam debugging system by introducing automation, intelligent monitoring and optimized optical models. Summary of the invention

[0028] The purpose of the present invention is to provide a beam automatic adjustment method and system for a proton therapy system, so as to realize online beam automatic adjustment at different rotating gantry angles, so as to improve the efficiency and flexibility of beam adjustment.

[0029] In order to achieve the above object, the present invention provides a method and system for automatically debugging the beam of a proton therapy system, comprising:

[0030] S1: An external beam measuring device is fixedly installed on the treatment head of the proton therapy system, and data transmission is realized between the external measuring device, the dose ionization chamber and the position ionization chamber of the proton therapy system and an automatic debugging workstation;

[0031] S2: The processor of the automatic debugging workstation starts to execute the beam automatic adjustment program and sets the beam adjustment target parameters;

[0032] S3: After the accelerator is loaded with automatic loading parameters and irradiation scheme, irradiation is performed. The automatic loading parameters include magnet parameters and injector parameters. Subsequently, the performance parameters of the beam are measured using a dose ionization chamber, a position ionization chamber and an external measuring device and sent to the automatic debugging workstation.

[0033] S4: the automatic debugging workstation determines whether the performance parameters of the beam are within a required threshold range according to the performance parameters of the beam;

[0034] S5: If it is within the required threshold range, the current gantry angle and magnet parameters at the target energy are saved and uploaded to the accelerator, and the process returns to step S2 to continue debugging the next gantry angle until all gantry angles are debugged. At this time, the automatic beam adjustment program is executed;

[0035] Otherwise, the magnet parameters are adjusted according to the deviation of the beam performance parameters and based on the beamline beam optical algorithm model, and the adjusted magnet parameters and irradiation plan are sent to the accelerator, and the process returns to step S3 for the next iteration.

[0036] The step S1 comprises:

[0037] S11: a fixing bracket is fixedly mounted on the treatment head, and an external measuring device is mounted on the fixing bracket;

[0038] S12: setting a reference point, wherein the reference point is any point on a straight line from the outlet of the treatment head to the isocenter position of the proton therapy system, and adjusting the fixed support to set the measurement center of the external measurement device at the reference point;

[0039] S13: Connect the cables between the external measuring equipment and the automatic debugging workstation, and realize the data transmission between the accelerator, dose ionization chamber and position ionization chamber of the proton therapy system and the automatic debugging workstation.

[0040] In step S2, setting the beam adjustment target parameters specifically includes:

[0041] S21: Setting a rack angle, where the rack angle is used to rotate the rotating rack to a target angle;

[0042] S22: Setting an irradiation plan with a single or multiple target energies, the irradiation plan being used to be sent to the accelerator.

[0043] In step S3, the performance parameters of the beam are measured using a dose ionization chamber, a position ionization chamber and an external measuring device and sent to the automatic debugging workstation, which specifically includes:

[0044] S31: For single-energy irradiation of the target, the measurement data of the dose ionization chamber, the position ionization chamber and the external measurement equipment are sent to the automatic debugging workstation;

[0045] S32: For irradiation of multiple target energies, the accelerator automatically reduces the energy according to the irradiation plan from high to low target energy and completes the irradiation in one time. The dose ionization chamber, position ionization chamber and external measurement equipment obtain measurement data under the control of the accelerator and the automatic debugging workstation respectively. After the irradiation of all target energies is completed, all measurement data are packaged and sent to the automatic debugging workstation at one time.

[0046] In step S5, the current gantry angle and magnet parameters at the target energy are saved and uploaded to the accelerator, and the process returns to step S2 to continue debugging the next gantry angle until all gantry angles are debugged. At this time, the automatic beam adjustment program is executed, which specifically includes:

[0047] S510: The magnet parameters and beam performance parameters at the current gantry angle and target energy are saved as the optimal debugging result; at the same time, the current magnet parameters are uploaded to the accelerator, so that the accelerator performs irradiation under the condition of loading the current magnet parameters;

[0048] S520: Return to step S2 to continue debugging the next rack angle until all rack angles are debugged, at which point the automatic beam adjustment program is executed.

[0049] In step S5, the magnet parameters are adjusted according to the deviation of the beam performance parameters and based on the beam optical algorithm model, and the adjusted magnet parameters and irradiation scheme are sent to the accelerator, and the process returns to step S3 for the next iteration, which specifically includes:

[0050] S51: According to the beam optical algorithm model, the size of the beam spot is adjusted by adjusting the quadrupole magnet;

[0051] S52: According to the beam optical algorithm model, the position of the beam spot is adjusted by adjusting the correction magnet or the dipole magnet;

[0052] S53: After the automatic beam adjustment procedure adjusts the magnet parameters, return to step S3 to perform the next iteration.

[0053] The step S3 further includes: saving the magnet parameters and beam performance parameters as historical debugging data;

[0054] Furthermore, after step S53, step S54 may be further included: evaluating and optimizing the current beamline beam optical algorithm model according to historical debugging data.

[0055] On the other hand, the present application provides a beam automatic debugging system for a proton therapy system, characterized in that it includes a dose ionization chamber and a position ionization chamber installed at the exit of a treatment head, an external measuring device installed at a reference point, and an automatic debugging workstation connected to the dose ionization chamber, the position ionization chamber, and the external measuring device;

[0056] Among them, the reference point can be any point on the straight line from the outlet of the treatment head to the isocenter position of the proton therapy system; the automatic debugging workstation includes a memory, a processor and a computer-readable beam automatic adjustment program stored in the memory, and the processor executes the beam automatic adjustment program to implement the beam automatic debugging method of the proton therapy system described above.

[0057] The gantry of the proton therapy system is a rotating gantry or a fixed gantry.

[0058] The automatic beam adjustment method of the proton therapy system of the present invention has the following advantages:

[0059] (1) Automatic debugging method:

[0060] The present invention introduces an automatic debugging method, which reduces the reliance on manual intervention and improves debugging efficiency. Compared with the traditional manual debugging scheme, automated debugging significantly improves debugging efficiency and accuracy, can quickly respond to system changes, and reduces debugging time. Specifically, the automatic debugging method reduces manual intervention, achieves rapid response and precise adjustment, significantly shortens the debugging cycle, significantly reduces the long-term operation and maintenance costs of the proton therapy system, achieves efficient use of resources, and improves debugging efficiency. Due to the automation and intelligence of the debugging process, the present invention can significantly reduce the demand for high-quality debugging personnel, thereby reducing labor costs and reducing overall maintenance and operation resource consumption. At the same time, reducing manual operations also correspondingly reduces the probability of errors occurring during the debugging process and improves the overall reliability of the system.

[0061] (2) Beam stability monitoring:

[0062] A real-time monitoring system was established through external measurement equipment. By measuring the fluctuation of beam parameters in real time, it can timely identify and adjust beam parameters that do not meet the requirements, and timely adjust the parameters that do not meet the requirements to ensure the stability of the beam and the treatment effect. The real-time monitoring and adjustment mechanism of the beam ensures the stability of the beam, thereby improving the safety and effectiveness of the treatment process, and can respond quickly after problems occur to avoid potential treatment risks.

[0063] (3)Optimization of optical model:

[0064] The historical debugging data is analyzed by a machine learning algorithm to obtain an optimized beam line beam optical algorithm model, which automatically calculates and adjusts the working point of the magnet during the debugging process, improves the accuracy and reliability of the debugging, and overcomes the problem of inaccurate optical models in existing solutions.

[0065] (4) Adaptive debugging strategy:

[0066] Adopting the adaptive algorithm of machine learning, the debugging strategy is dynamically adjusted according to the changes of different beam energies and gantry irradiation angles. This flexibility enables the system to self-adjust according to real-time conditions, significantly improving the adaptability and flexibility of operation. The present invention combines a machine learning algorithm based on a neural network to analyze and predict the effect of the debugging strategy and optimize the debugging process. This intelligent method makes the beam parameter adjustment more accurate and can reduce the number of iterations.

[0067] (5)Integration of multiple functions:

[0068] The present invention not only realizes the automatic debugging function of the beam current, but also integrates monitoring, feedback and optimization algorithms, effectively integrates multiple functions, and improves the performance of the entire system.

[0069] In summary, the present invention overcomes the shortcomings of the existing technology by introducing technical means such as automation, real-time monitoring, optimization model and adaptive algorithm, significantly improves the efficiency, safety and reliability of proton therapy beam debugging, and shows good application prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] The drawings in the specification which constitute a part of the application are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0071] Figure 1 A structural schematic diagram of a real-time monitoring system of a beam automatic debugging system of a proton therapy system according to an embodiment of the present invention;

[0072] Figure 2 A schematic diagram of the structure of a beam line of a rotating gantry of a typical proton therapy system;

[0073] Figure 3 The figure is a flow chart of a method for automatic beam adjustment of a proton therapy system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0074] The preferred embodiments of the present invention are given below in conjunction with the accompanying drawings and described in detail.

[0075] like Figure 1 The figure shows an automatic beam debugging system of a proton therapy system according to an embodiment of the present invention. The proton therapy system is existing, and mainly includes an accelerator (not shown), a rotating gantry 1, a treatment head 2 mounted on the rotating gantry 1, and a dose ionization chamber 3 and a position ionization chamber 4 mounted at the outlet of the treatment head 2. The rotation angle range of the rotating gantry 1 is 0 to 360°; the treatment head 2 rotates with the random gantry, and the beam is emitted from the outlet of the treatment head 2 to the treatment position; the dose ionization chamber 3 is used to measure the dose at the outlet of the treatment head, and is fixedly installed in the treatment head 2. The position ionization chamber 4 is used to measure the beam spot size and position in the beam at the outlet of the treatment head, and is fixedly installed in the treatment head 2. The dose ionization chamber 3 and the position ionization chamber 4 are key components of the existing proton therapy system. Since the beam can directly pass through the dose ionization chamber 3 and the position ionization chamber 4, the beam will not be affected.

[0076] The beam automatic debugging system of the present invention includes an existing dose ionization chamber 3 and a position ionization chamber 4 installed at the outlet of the treatment head 2, an external measuring device 5 installed at a reference point, and an automatic debugging workstation 6 connected to the dose ionization chamber 3, the position ionization chamber 4, and the external measuring device 5.

[0077] The reference point can be any point on the straight line from the outlet of the treatment head 2 to the isocenter position of the proton therapy system. The main principle is that measuring two points can ensure that the beam incident direction is on the same straight line, that is, the two points are in a straight line. This measurement method can ensure the beam exit direction. The isocenter position of the proton therapy system belongs to a central position defined in the coordinate system of the proton therapy system.

[0078] The external measuring device 5 is used to measure the beam spot size and position in the beam at the reference point, and is fixedly mounted on the treatment head and can rotate with the random bracket. The external measuring device 5 is first fixed to the treatment head 2 through a fixed bracket, and the fixed bracket is adjustable to ensure that the center position of the external measuring device 5 is consistent with the beam position. After the initial adjustment of the position, there is no need to adjust the position of the fixed bracket during subsequent adjustment and actual treatment using the proton therapy system.

[0079] In this embodiment, the external measuring device 5 is a self-developed device, and the hardware mainly includes a plastic scintillator screen, a reflector, a CCD camera and a housing, as well as a data acquisition and processing module. The principle of this external measuring device 5 is similar to the Lynx-2D commonly used on the market. The advantage of using a self-developed device is that the automatic debugging workstation 6 can obtain the data stream of the external measuring device 5. In other embodiments, the external measuring device 5 can also be replaced by an existing product on the market, as long as it can provide a data stream and a control interface to the automatic debugging workstation 6.

[0080] The automatic debugging workstation 6 includes a memory, a processor, and a computer-readable automatic beam adjustment program stored in the memory. The processor executes the automatic beam adjustment program to implement the automatic beam adjustment method, so that the debugging personnel can complete related debugging work through the automatic beam debugging program.

[0081] The automatic beam adjustment method specifically includes: acquiring the performance parameters of the beam in real time, and when the performance parameters of the beam exceed the required threshold range, correcting the magnet parameters of the proton therapy system according to the deviation of the performance parameters of the beam to achieve automatic beam adjustment, effectively improving the accuracy and automation level of debugging, and thus improving the treatment effect and efficiency.

[0082] Therefore, the beam automatic debugging system of the present invention obtains the performance parameters of the beam in real time through the dose ionization chamber, position ionization chamber and external self-developed measuring equipment of the treatment head 2, thereby realizing real-time monitoring of the performance parameters of the beam; and the real-time monitoring results are linked with the automatic debugging workstation 6, wherein the performance parameters of the beam are sent to the automatic debugging workstation 6 in real time, so that the instability or deviation of the beam can be monitored in time, and the automatic debugging workstation 6 can make corrections according to the deviation of the performance parameters of the beam, thereby effectively improving the accuracy and automation level of debugging, and thus improving the treatment effect and efficiency.

[0083] It should be noted that “real-time” in the present invention does not mean that the automatic beam adjustment system of the present invention can monitor and send data during treatment, but means that before treatment, the automatic beam adjustment system of the present invention can automatically perform the next step of beam adjustment according to the current data.

[0084] In some embodiments, the rotating gantry 1 can be replaced by a fixed gantry. Therefore, the application scope of the system described in the present invention is not limited to proton therapy systems with a rotating gantry, but can also be used for proton therapy systems with a fixed gantry, reflecting its wide applicability.

[0085] like Figure 2 Shown is a schematic diagram of the structure of the beam line of the rotating gantry.

[0086] like Figure 2 As shown, the upstream of the rotating gantry 1 is connected to the beam high energy transport line 7. After the beam is accelerated from the accelerator to a specific energy, it is led to the beam high energy transport line 7, and the beam high energy transport line 7 transmits the beam to the rotating gantry 1. The downstream of the rotating gantry 1 is connected to the treatment head 2.

[0087] The rotating gantry 1 specifically includes at least one section of a dipole magnet 11 , at least one section of a quadrupole magnet 12 , a correction magnet 13 , and a scanning magnet 14 arranged along the beam transport path 100 . The scanning magnet 14 is directly disposed upstream of the treatment head 2 .

[0088] The dipole magnet 11 is mainly used for beam deflection, and is mainly used for adjusting the position of the beam in a large range in the X and Y directions. The location of the dipole magnet 11 is determined according to the required beam transport path 100 .

[0089] The quadrupole magnet 12 is mainly used to adjust the beam spot size in the X and Y directions of the beam.

[0090] The correction magnet 13 is mainly used for adjusting the position of the beam in a small range in the X and Y directions. In this embodiment, the correction magnet 13 is arranged between the multi-segment quadruple magnets 12 .

[0091] The scanning magnet 14 is mainly used to scan the beam in the X and Y directions within the treatment field to ensure the uniformity and effectiveness of the irradiation dose.

[0092] The beam high energy transport line 7 comprises a treatment room entrance magnet 71, and the treatment room entrance magnet 71 comprises a dipole magnet, a quadrupole magnet and a correction magnet. The functions of these magnets are the same as those described above.

[0093] Figure 3 The figure shows a flow chart of a method for automatically debugging the beam of a proton therapy system according to an embodiment of the present invention, which includes the following steps:

[0094] Step S1: a beam external measuring device 5 is fixedly installed on the treatment head 2 of the proton therapy system, and data transmission is realized between the external measuring device 5, the dose ionization chamber 3 and the position ionization chamber 4 of the proton therapy system and the automatic debugging workstation 6;

[0095] Thus, the external measuring device 5 can rotate along with the rotating gantry of the proton therapy system.

[0096] The step S1 comprises:

[0097] Step S11: a fixed bracket is fixedly mounted on the treatment head 2, and an external measuring device 5 is mounted on the fixed bracket;

[0098] Step S12: setting a reference point, which is any point on a straight line from the outlet of the treatment head 2 to the isocenter position of the proton therapy system, and adjusting the fixed bracket to set the measurement center of the external measurement device 5 at the reference point;

[0099] Step S13: connecting the cables between the external measuring device 5 and the automatic debugging workstation 6, and realizing data transmission between the accelerator, the dose ionization chamber 3 and the position ionization chamber 4 of the proton therapy system and the automatic debugging workstation 6.

[0100] Among them, the dose ionization chamber 3 and the position ionization chamber 4 of the treatment head 2 can measure the beam spot size and position in the beam at the exit of the treatment head 2. The measurement data of the dose ionization chamber 3 and the position ionization chamber 4 are sent to the automatic beam adjustment workstation in real time, and the measurement instructions are controlled by the proton therapy system. The external measurement device 5 can measure the beam spot size and position in the beam at the reference point. The measurement data of the external measurement device 5 can be sent to the automatic beam adjustment workstation in real time, and the measurement instructions are controlled by the automatic beam adjustment program. Therefore, in the following debugging process, it is necessary to take into account the beam parameters at the ionization chamber and the reference point on the treatment head to ensure that the beam parameters at the two measurement points meet the clinical requirements and ensure that the beam can be accurately irradiated to the center position of the treatment.

[0101] The transmission data sent by the automatic debugging workstation 6 to the accelerator is mainly the irradiation plan, including the following parameters: gantry angle, energy layer, irradiation point number, dose, each position and scanning number, etc. The accelerator of the proton therapy system is based on the irradiation plan, and the accelerator loads automatic loading parameters, which include: parameters of each magnet contained in the accelerator, injector parameters, etc., to achieve corresponding irradiation.

[0102] The automatic debugging workstation 6 does not directly exchange data with the dose ionization chamber 3 and the position ionization chamber 4 of the treatment head 2, but all data are transferred through the accelerator.

[0103] The dose ionization chamber 3 and position ionization chamber 4 of the treatment head 2 are controlled by the accelerator and feed back the measurement data to the proton therapy system. The transmission data sent by the accelerator to the dose ionization chamber 3 and position ionization chamber 4 include: start and end measurement commands, size and position of the beam spot in the beam, dose, number of points, energy layer, etc.

[0104] The transmission data sent via the accelerator to the automatic debugging workstation 6 includes the beam parameters measured by the dose ionization chamber 3 and the position ionization chamber 4 of the treatment head, specifically including: the position and size of the beam spot in the X and Y directions, the gantry angle, the irradiation energy, the number of points, the dose, etc.

[0105] The transmission data sent by the automatic debugging workstation 6 to the external measuring device 5 includes control instructions of the external measuring device 5 . The control instructions of the external measuring device 5 include: start and end measurement commands, background acquisition, background removal, etc.

[0106] The transmission data sent by the external measuring device 5 to the automatic debugging workstation 6 includes: the position and size of the beam spot in the X and Y directions.

[0107] In addition, the step S1 may also include checking the data transmission between the proton therapy system and its dose ionization chamber 3 and position ionization chamber 4 and the automatic debugging workstation 6 to ensure that all relevant data can be transmitted normally.

[0108] Step S2: the processor of the automatic debugging workstation 6 starts to execute the beam automatic adjustment program and sets the beam adjustment target parameters;

[0109] In step S2, setting the beam adjustment target parameters specifically includes:

[0110] Step S21: setting a rack angle, where the rack angle is used to rotate the rotating rack 1 to a target angle;

[0111] Thus, after the setting is completed, the automatic debugging workstation 6 will send the rack angle to the rack control system, and the rack control system will rotate the rotating rack to the rack angle;

[0112] Step S22: Setting an irradiation plan with a single or multiple target energies, wherein the irradiation plan is used to be sent to the accelerator.

[0113] The irradiation plan supports setting a single target energy or multiple target energies. After selecting all target energies for setting the irradiation plan, the corresponding irradiation plan will be set and sent to the accelerator, and the parameters corresponding to the rotating gantry and target energy will be sent to the accelerator;

[0114] Step S3: After the accelerator loads the automatic loading parameters and irradiation plan, irradiation is performed; subsequently, the performance parameters of the beam are measured using the dose ionization chamber 3, the position ionization chamber 4 and the external measurement device 5 and sent to the automatic debugging workstation 6;

[0115] In addition, the step S3 further includes: saving the automatic loading parameters and the performance parameters of the beam as historical debugging data.

[0116] The performance parameters of the beam include the size and position of the beam spot in the beam (such as the size and position in the X and Y directions).

[0117] As mentioned above, the irradiation plan includes: gantry angle, energy layer, number of irradiation points, dose, position (such as position in X and Y directions) and number of scans, etc. Automatic loading parameters include: parameters of each magnet contained in the accelerator, injector parameters, etc. For example, parameters of each beam line magnet, injection extraction static magneto system parameters and slow extraction system parameters, etc.

[0118] In step S3, the performance parameters of the beam are measured by using the dose ionization chamber 3, the position ionization chamber 4 and the external measurement device 5 and sent to the automatic debugging workstation 6, which specifically includes:

[0119] Step S31: for the irradiation of the target single energy, the measurement data of the dose ionization chamber 3, the position ionization chamber 4 and the external measurement device 5 are sent to the automatic debugging workstation 6;

[0120] Step S32: For irradiation of multiple target energies, the accelerator automatically reduces the energy according to the irradiation scheme from high to low target energy and completes the irradiation in one time. The dose ionization chamber 3, the position ionization chamber 4 and the external measurement equipment 5 obtain measurement data under the control of the accelerator and the automatic debugging workstation 6 respectively. After the irradiation of all target energies is completed, all the measurement data are packaged at one time and sent to the automatic debugging workstation 6.

[0121] Step S4: the automatic debugging workstation 6 determines whether the performance parameters of the beam are within the required threshold range according to the performance parameters of the beam;

[0122] Step S5: If it is within the required threshold range, the current gantry angle and magnet parameters at the target energy are saved and uploaded to the accelerator, and the process returns to step S2 to continue debugging the next gantry angle until all gantry angles are debugged. At this time, the automatic beam adjustment program is executed;

[0123] Otherwise, the magnet parameters are adjusted according to the deviation of the beam performance parameters and based on the beamline beam optical algorithm model, and the adjusted magnet parameters and irradiation plan are sent to the accelerator, and the process returns to step S3 for the next iteration.

[0124] Therefore, automatic beam adjustment is achieved by correcting the magnet parameters of the proton therapy system.

[0125] In step S5, the current gantry angle and magnet parameters at the target energy are saved and uploaded to the accelerator, and the process returns to step S2 to continue debugging the next gantry angle until all gantry angles are debugged. At this time, the automatic beam adjustment program is executed, which specifically includes:

[0126] Step S510: The magnet parameters and beam performance parameters at the current gantry angle and target energy are saved as the optimal debugging results, so as to facilitate the subsequent tracing of the optimal debugging results; at the same time, the current magnet parameters are uploaded to the accelerator, so that the accelerator performs irradiation under the condition of loading the current magnet parameters;

[0127] The optimal debugging result is saved in the database, which is located on the server of the accelerator control system, not on the automatic beam adjustment workstation. The server of the accelerator control system is responsible for managing all data related to the operation and control of the accelerator (including historical debugging data).

[0128] Step S520: Return to step S2 to continue debugging the next rack angle until all rack angles are debugged, at which point the automatic beam adjustment program is executed.

[0129] In step S5, the magnet parameters are adjusted according to the deviation of the beam performance parameters and based on the beam optical algorithm model, and the adjusted magnet parameters and irradiation scheme are sent to the accelerator, and the process returns to step S3 for the next iteration, which specifically includes:

[0130] Step S51: adjusting the size of the beam spot by adjusting the quadrupole magnet according to the beam line optical algorithm model;

[0131] The quadrupole magnet includes a beam high energy transport line 7 and a quadrupole magnet on the rotating frame 1 .

[0132] Step S52: adjusting the position of the beam spot by adjusting the correction magnet or the dipole magnet according to the beam line optical algorithm model;

[0133] The correction magnet or dipole magnet includes the correction magnet or dipole magnet on the beam high energy transport line 7 and the rotating frame 1 .

[0134] Step S53: After the automatic beam adjustment procedure adjusts the magnet parameters, return to step S3 to perform the next iteration.

[0135] Specifically, when returning to step S3, the adjusted magnet parameters are sent to the accelerator, the irradiation scheme remains unchanged, the accelerator loads the adjusted magnet parameters for irradiation, and the performance parameters of the beam are obtained and saved as historical debugging data.

[0136] In addition, after step S53, step S54 may be further included: using other algorithms to evaluate and optimize the current beamline beam optical algorithm model according to historical debugging data.

[0137] Among them, the beamline beam optical algorithm model is an existing mature technology. References are as follows:

[0138] [1] C.Xia,

[0139] [2]RRWilson. Radiological use of fast protons. Radiology, 1946, 47(5):487.

[0140] [3] Liu Xu. Design of rotating gantry beam transport line for proton therapy [PhD dissertation]. Wuhan: Huazhong University of Science and Technology, 2018.

[0141] [4] Zhao Zefeng. Research on fringe field effect and high-order aberrations of proton therapy rotating gantry beamline [Master's thesis]. Wuhan: Huazhong University of Science and Technology, 2019.

[0142] [5]Z.Zhao,B.Qin,X.Liu,W.Chen,Q.Chen.Influence of fringing field andsecond-order aberrations on proton therapy.Nuclear Instruments and Methods inPhysics Research Section A:Accelerators,Spectrometers,Detectors andAssociated Equipment,2019,940:479-485.

[0143] [6]R.Roussel,A.Hanuka,A.Edelen.Multiobjective Bayesian optimizationfor online accelerator tuning.Physical Review Accelerators and Beams,2021,24(1).

[0144] [7]B.Naujoks,N.Beume,M.Emmerich.Multiobjective optimization on alimited budget of evaluations using model-assisted s-metric selection,in:Parallel Problem Solving from Nature–PPSN X.Dortmund,Germany,September 13-17,2008,Springer,Berlin,Heidelberg,2008:784-794.

[0145] [8]X.Huang,J.Corbett,J.Safranek,J.Wu.An algorithm for onlineoptimization of accelerators.Nuclear Instruments and Methods in PhysicsResearch Section A:Accelerators,Spectrometers,Detectors and AssociatedEquipment,2013,720:134-139。

[0146] Among them, the beamline beam optical algorithm model is an algorithm specifically used to describe how proton beams propagate and interact with matter in various physical environments. It is based on physical laws (such as electromagnetism and particle dynamics) and is calculated and optimized through mathematical models. In proton therapy systems, the beamline beam optical algorithm model is used to output adjusted magnet parameters based on the deviation of the current beam parameters, mainly focusing on the focusing, transmission and modulation of particle beams.

[0147] Beamline optical algorithm models usually involve the following types of algorithms:

[0148] Beam transport model: Based on Bellman's equations or the transfer matrix approach, the propagation and imaging characteristics of proton beams in various optical elements (such as defocusing lenses, colliders, and quadrupole lenses) are calculated.

[0149] Particle trajectory simulation algorithms: Use Monte Carlo methods or other numerical methods (such as particle trajectory tracking in a box) to simulate the behavior of particles interacting with matter during treatment.

[0150] Other algorithms used in step S54 may be any existing mature algorithms on the market, such as machine learning algorithms, adaptive control algorithms, and the like.

[0151] A machine learning algorithm is an algorithm that learns and improves automatically through data and experience. Machine learning can be applied to a variety of problems, including classification, regression, clustering, etc. It makes predictions or decisions by extracting patterns in data.

[0152] In this embodiment, a neural network-based machine learning algorithm is used to optimize the historical debugging data of the current beamline beam optical algorithm model; specifically, the neural network-based machine learning algorithm is trained according to the historical debugging data to obtain the relationship between different debugging strategies and the corresponding beam performance parameters, and a trained neural network-based machine learning algorithm is obtained. The trained neural network-based machine learning algorithm is used as the optimized beamline beam optical algorithm model and is used to predict the impact of different debugging strategies on the performance parameters of the beam.

[0153] After training, the neural network-based machine learning algorithm can identify and learn complex input and output relationships, and obtain the optimal parameter configuration of the beam by predicting the impact of different debugging strategies on the performance parameters of the beam, so as to improve the predictive ability of the beamline beam optical algorithm model and enhance the treatment effect or beam transmission efficiency.

[0154] Therefore, the optimization of the beamline beam optical algorithm model is achieved through the machine learning algorithm based on the neural network, which improves the efficiency and accuracy of the beamline beam optical algorithm model, and can further reduce the number of iterations and improve the accuracy of magnet parameter adjustment.

[0155] In a neural network-based machine learning algorithm, input parameters can include:

[0156] Real-time data (e.g., current gantry angle, actual beam position, beam characteristics, etc.); historical data (including previous gantry angles, magnet settings, and related beam characteristics); system parameters (e.g., magnet current, strength, polarity, etc.).

[0157] Output parameters: ideal magnet setting parameters (e.g. required current value, magnetic field strength, etc. after adjustment); expected beam performance parameters (e.g. optimized beam trajectory, diameter, etc.).

[0158] The neural network-based machine learning algorithm is trained with historical debugging data and used to predict the expected beam performance parameters corresponding to the adjusted magnet parameters at different gantry angles. The specific process is as follows:

[0159] (1) Data collection and preparation

[0160] Historical data: First, collect historical data related to the beam optics model, including the following:

[0161] 1 Rack Angle: Different rack angle settings.

[0162] 2 Magnet parameters: including current, magnetic field strength, polarity and other parameters related to magnets.

[0163] 3 Beam characteristics: such as beam energy, beam diameter, beam position, beam quality (such as divergence angle), beam trajectory, etc.

[0164] 4. Debugging results: Feedback on beam performance under different adjustments (successful debugging results and failed debugging results).

[0165] Real-time data: During the debugging process, sensors are used to obtain historical debugging data, including but not limited to:

[0166] 1 Magnet parameters and beam performance parameters;

[0167] 2Current rack angle;

[0168] 3. Operating status data (such as temperature, test current).

[0169] (2) Data preprocessing

[0170] Cleaning: Remove missing values ​​and outliers.

[0171] Feature engineering: Selecting and generating important features based on the collected data, such as extracting the main features through principal component analysis (PCA).

[0172] (3) Train machine learning models;

[0173] Choose a model: Depending on the nature of the problem, choose an appropriate machine learning model such as random forest, neural network, etc.

[0174] Training model: The model is trained using a dataset of historical debugging data to enable it to understand the impact of gantry angle and magnet parameter adjustments on beam characteristics.

[0175] At this point, the machine learning model training is complete.

[0176] (4) Real-time prediction process;

[0177] Get real-time data: During the debugging process, quickly get real-time data (such as current gantry angle, actual beam characteristics, etc.).

[0178] Input model: These real-time data are input into the trained machine learning model, and the model gives the output results after processing.

[0179] Based on real-time data, the output of machine learning algorithms includes but is not limited to:

[0180] Ideal magnet setting parameters: recommended magnet current, magnetic field strength and other adjustment parameters.

[0181] Expected beam characteristics: The estimated beam characteristics (such as beam position and size) based on the output magnet setting parameters.

[0182] (5) Adjustment and verification

[0183] Implement adjustment: Adjust the magnet according to the parameters output by the machine learning algorithm.

[0184] Feedback Verification: Use real-time feedback data to verify the adjusted beam characteristics to determine the effectiveness of the adjustment method.

[0185] Through the above process, the neural network-based machine learning algorithm can be used as an optimized beamline beam optical algorithm model to achieve real-time prediction and provide accurate magnet setting parameters for the debugging process. This can not only improve the debugging efficiency, but also reduce the errors caused by human factors during the debugging process. At the same time, this prediction capability based on real-time data enables a deeper understanding and precise regulation of the relationship between beam characteristics and adjustment parameters.

[0186] In other embodiments, in step S54, the current beamline beam optical algorithm model is evaluated and / or optimized, which may also be implemented by using an existing adaptive control algorithm.

[0187] Adaptive control algorithms are mainly used in real-time control systems to adjust parameters during operation to maintain target performance or stability. Adaptive control algorithms can provide real-time dynamic feedback when optimizing beam optical models, making the optimization process more accurate and improving the quality of its control decisions. The adjustment feedback of real-time control can make the optimization model more robust and adaptable.

[0188] Therefore, in the present invention, automatic beam adjustment is firstly realized through a beam line beam flow optical algorithm model, and then a large amount of automatic beam adjustment data is used to train the model (such as an adaptive control algorithm, a neural network, a decision tree, etc.) to obtain an optimized beam line beam flow optical algorithm model, thereby improving the automatic beam adjustment effect and efficiency.

[0189] In summary, the technical solution of the present invention achieves its purpose through the following key components:

[0190] (1) Automatic beam adjustment program:

[0191] The automatic debugging workstation 6 automatically adjusts the various magnet parameters of the beam system based on the beam automatic adjustment program and the real-time measured data, and the debugging efficiency is high. Through the beam measurement equipment, the automatic debugging workstation 6 can monitor the state of the beam in real time, perform data analysis, and achieve accurate debugging.

[0192] (2) Real-time monitoring system:

[0193] The automatic beam debugging system of the present invention obtains the performance parameters of the beam in real time through the dose ionization chamber, position ionization chamber and external self-developed measuring equipment of the treatment head 2, thereby realizing real-time monitoring of the performance parameters of the beam; and the real-time monitoring results are linked with the automatic debugging workstation 6, wherein the performance parameters of the beam are sent to the automatic debugging workstation 6 in real time, so that the instability or deviation of the beam can be monitored in time, and the automatic debugging workstation 6 can make corrections according to the deviation of the performance parameters of the beam, thereby effectively improving the accuracy and automation level of debugging, and thus improving the treatment effect and efficiency.

[0194] (3) Beamline optical algorithm model:

[0195] The present invention realizes automatic beam adjustment through the existing beam optical algorithm model. In addition, the present invention also evaluates and / or optimizes the beam optical algorithm model based on other algorithms, trains the model through historical data, and predicts the change in the performance parameters of the beam corresponding to the magnet parameter adjustment at different rack angles. The introduction of the model enables the ideal magnet setting parameters to be quickly calculated based on the acquired real-time data during the debugging process, thereby guiding accurate debugging and replacing the traditional simplified optical model.

[0196] (4) System integration and compatibility design:

[0197] The automatic beam adjustment workstation of the present invention is designed with integration and compatibility with existing proton therapy equipment in mind, and achieves overall optimization through seamless docking with the accelerator of the existing proton therapy system (i.e., the proton therapy accelerator control system) through a standardized interface. This means that the automatic beam adjustment workstation can communicate through a universal RJ45 interface, exchange data based on the common TCP / IP communication protocol, send irradiation plans to the accelerator, and receive beam performance parameters measured by the ionization chamber on the treatment head: beam spot size and position in the XY direction. The design of the automatic debugging workstation 6 of the present invention also supports future technology upgrades and expansions, ensuring flexibility and maintainability for long-term operation.

[0198] The above is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. The above embodiments of the present invention can also be modified in various ways. All simple, equivalent changes and modifications made according to the claims and the description of the present invention fall within the scope of protection of the claims of the present invention. The contents not described in detail in the present invention are all conventional technical contents.

Claims

1. A method for automatically adjusting the beam current of a proton therapy system, characterized in that: include: Step S1: An external beam measuring device is fixedly installed on the treatment head of the proton therapy system, and data transmission is realized between the external measuring device, the dose ionization chamber and the position ionization chamber of the proton therapy system and an automatic debugging workstation; Step S2: the processor of the automatic debugging workstation starts to execute the beam automatic adjustment program and sets the beam adjustment target parameters; Step S3: After the accelerator is loaded with automatic loading parameters and irradiation scheme, irradiation is performed, wherein the automatic loading parameters include magnet parameters and injector parameters; subsequently, the performance parameters of the beam are measured using a dose ionization chamber, a position ionization chamber and an external measuring device and sent to the automatic debugging workstation; Step S4: the automatic debugging workstation determines whether the performance parameters of the beam are within a required threshold range according to the performance parameters of the beam; Step S5: If it is within the required threshold range, the current gantry angle and magnet parameters at the target energy are saved and uploaded to the accelerator, and the process returns to step S2 to continue debugging the next gantry angle until all gantry angles are debugged. At this time, the automatic beam adjustment program is executed; Otherwise, the magnet parameters are adjusted according to the deviation of the beam performance parameters and based on the beamline beam optical algorithm model, and the adjusted magnet parameters and irradiation plan are sent to the accelerator, and the process returns to step S3 for the next iteration.

2. The method for automatically adjusting the beam of a proton therapy system according to claim 1, characterized in that: The step S1 comprises: Step S11: a fixed bracket is fixedly mounted on the treatment head, and an external measuring device is mounted on the fixed bracket; Step S12: setting a reference point, which is any point on a straight line from the outlet of the treatment head to the isocenter position of the proton therapy system, and adjusting the fixed support to set the measurement center of the external measurement device at the reference point; Step S13: Connect the cables between the external measuring device and the automatic debugging workstation, and realize data transmission between the accelerator, the dose ionization chamber and the position ionization chamber of the proton therapy system and the automatic debugging workstation.

3. The method for automatically adjusting the beam of a proton therapy system according to claim 1, characterized in that: In step S2, setting the beam adjustment target parameters specifically includes: Step S21: setting a rack angle, where the rack angle is used to rotate the rotating rack to a target angle; Step S22: Setting an irradiation plan with a single or multiple target energies, wherein the irradiation plan is used to be sent to the accelerator.

4. The method for automatically adjusting the beam of a proton therapy system according to claim 1, characterized in that: In step S3, the performance parameters of the beam are measured using a dose ionization chamber, a position ionization chamber and an external measuring device and sent to the automatic debugging workstation, which specifically includes: Step S31: for the single energy irradiation of the target, the measurement data of the dose ionization chamber, the position ionization chamber and the external measurement equipment are sent to the automatic debugging workstation; Step S32: For irradiation of multiple target energies, the accelerator automatically reduces the energy according to the irradiation scheme from high to low target energy and completes the irradiation in one time. The dose ionization chamber, position ionization chamber and external measurement equipment obtain measurement data under the control of the accelerator and the automatic debugging workstation respectively. After the irradiation of all target energies is completed, all measurement data are packaged and sent to the automatic debugging workstation at one time.

5. The method for automatic beam adjustment of a proton therapy system according to claim 1, characterized in that: In step S5, the current gantry angle and magnet parameters at the target energy are saved and uploaded to the accelerator, and the process returns to step S2 to continue debugging the next gantry angle until all gantry angles are debugged. At this time, the automatic beam adjustment program is executed, which specifically includes: Step S510: The magnet parameters and beam performance parameters at the current gantry angle and target energy are saved as the optimal debugging results; at the same time, the current magnet parameters are uploaded to the accelerator, so that the accelerator performs irradiation under the condition of loading the current magnet parameters; Step S520: Return to step S2 to continue debugging the next rack angle until all rack angles are debugged, at which point the automatic beam adjustment program is executed.

6. The method for automatically adjusting the beam of a proton therapy system according to claim 1, characterized in that: In step S5, the magnet parameters are adjusted according to the deviation of the beam performance parameters and based on the beam optical algorithm model, and the adjusted magnet parameters and irradiation scheme are sent to the accelerator, and the process returns to step S3 for the next iteration, which specifically includes: Step S51: adjusting the size of the beam spot by adjusting the quadrupole magnet according to the beam line optical algorithm model; Step S52: adjusting the position of the beam spot by adjusting the correction magnet or the dipole magnet according to the beam line optical algorithm model; Step S53: After the automatic beam adjustment procedure adjusts the magnet parameters, return to step S3 to perform the next iteration.

7. The method for automatic beam adjustment of a proton therapy system according to claim 1, characterized in that: The step S3 further includes: saving the magnet parameters and beam performance parameters as historical debugging data; Furthermore, after step S53, step S54 may be further included: evaluating and optimizing the current beamline beam optical algorithm model according to historical debugging data.

8. A proton therapy system beam automatic debugging system, characterized in that: It includes a dose ionization chamber and a position ionization chamber installed at the outlet of the treatment head, an external measuring device installed at a reference point, and an automatic debugging workstation connected to the dose ionization chamber, the position ionization chamber, and the external measuring device; Among them, the reference point can be any point on the straight line from the outlet of the treatment head to the isocenter position of the proton therapy system; the automatic debugging workstation includes a memory, a processor and a computer-readable beam automatic adjustment program stored in the memory, and the processor executes the beam automatic adjustment program to implement the beam automatic adjustment method of the proton therapy system described in any one of claims 1 to 7.

9. The automatic beam adjustment system of the proton therapy system according to claim 8, characterized in that: The gantry of the proton therapy system is a rotating gantry or a fixed gantry.

Images