Method, device and electronic equipment for determining error of accelerator

Abstract

The present application discloses an error determination method, device and electronic device for an accelerator, and relates to the field of medical technology. The method includes: obtaining a preset plan and a target radiotherapy plan for a target object, wherein the preset plan is used to test the accelerator device through pre-set accelerator device parameters; executing the preset plan on the accelerator device to obtain the target execution result of the accelerator device for the preset plan; determining the target error of the accelerator device according to the target execution result; determining the estimated dose information according to the target error, wherein the estimated dose information represents the dose information generated by the accelerator device when executing the target radiotherapy plan in the presence of a target error. The present application solves the technical problem in the prior art that the device status of the accelerator cannot be verified before the treatment of each patient, resulting in poor controllability of the radiotherapy effect for the patient.

Description

Technical Field

[0001] The present application relates to the field of medical technology, and in particular, to an accelerator error determination method, device and electronic equipment. Background Art

[0002] The principle of photon therapy is to use light energy of a specific wavelength to penetrate the skin and enter the human tissue, where the light energy interacts with the pigments and cells in the tissue. This interaction can transfer energy to the cells, thereby changing the function and metabolic process of the cells.

[0003] Traditional radiotherapy is a type of photon therapy that uses rays. Photon therapy is generally performed through a linear accelerator and a multi-page collimator to conform to the target area. Precision treatment needs to be based on the precise operation of the accelerator equipment. Whether the patient's radiotherapy plan is accurately executed depends on the status of the accelerator equipment before the patient's treatment.

[0004] However, existing technical solutions usually involve performing a morning inspection of the accelerator equipment on each treatment day, and do not set up an independent accelerator quality control link for each patient, which leads to technical problems such as poor controllability of the radiotherapy effect on the patient.

[0005] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0006] The present application provides an accelerator error determination method, device and electronic device to at least solve the technical problem in the prior art that the device status of the accelerator cannot be verified before treatment of each patient, resulting in poor controllability of the radiotherapy effect on the patient.

[0007] According to one aspect of the present application, a method for determining an error of an accelerator is provided, comprising: before each target object receives radiotherapy, obtaining a preset plan and a target radiotherapy plan of the target object, wherein the preset plan is used to test the accelerator device through preset accelerator device parameters; executing the preset plan on the accelerator device to obtain a target execution result of the accelerator device for the preset plan; determining a target error of the accelerator device according to the target execution result; determining estimated dose information according to the target error, wherein the estimated dose information represents dose information generated by the accelerator device when executing the target radiotherapy plan in the presence of a target error.

[0008] Optionally, the error determination method for the accelerator also includes: inputting the target execution result into the target model, and determining the target error of the accelerator device according to the target execution result through prior knowledge of the target model, wherein the prior knowledge is used to characterize the correlation between the execution result output by the accelerator device when executing the error plan and the known device error of the accelerator device.

[0009] Optionally, the error determination method for the accelerator also includes: modifying the parameter values ​​of the accelerator device parameters in the preset plan to obtain an error plan; recording the parameter difference values ​​between the accelerator device parameters in the error plan and the accelerator device parameters in the preset plan; executing the error plan on the accelerator device to obtain the execution result of the error plan by the accelerator device; and training to obtain the target model based on the parameter difference values ​​and the execution result of the error plan.

[0010] Optionally, the error determination method for the accelerator also includes: inputting the execution results of the error plan, the parameter difference value and the preset plan into the neural network; iteratively training the neural network to learn the relationship between the execution results of the error plan, the parameter difference value and the preset plan, until the similarity between the plan execution results predicted and output by the neural network based on the parameter difference value and the preset plan and the execution results of the error plan is greater than a first preset similarity, and / or the similarity between the device error value of the accelerator device predicted and output by the neural network based on the execution results of the error plan and the parameter difference value is greater than a second preset similarity.

[0011] Optionally, the error determination method for the accelerator further includes: adjusting accelerator equipment parameters included in the target radiotherapy plan according to the target error, and using the adjusted target radiotherapy plan as the target error plan; determining estimated dose information according to the target error plan, wherein the estimated dose information represents dose information generated by the accelerator equipment when executing the target radiotherapy plan in the presence of the target error.

[0012] Optionally, the error determination method for the accelerator also includes: after determining the estimated dose information according to the target error plan, detecting the similarity between the estimated dose information and the target dose information, wherein the target dose information represents the dose information generated by the accelerator device when executing the target radiotherapy plan in the absence of errors; when it is detected that the similarity between the estimated dose information and the target dose information is greater than a preset threshold, prohibiting the use of the accelerator device to execute the target radiotherapy plan; when it is detected that the similarity between the estimated dose information and the target dose information is less than or equal to the preset threshold, allowing the accelerator device to execute the target radiotherapy plan.

[0013] Optionally, the error determination method for the accelerator also includes: after allowing the accelerator device to execute the target radiotherapy plan when detecting that the similarity between the estimated dose information and the target dose information is less than or equal to a preset threshold, obtaining a log file generated by the accelerator device when executing the target radiotherapy plan; using the device parameters actually executed by the accelerator device recorded in the log file as the first parameter; using the accelerator device parameters included in the target radiotherapy plan as the second parameter; detecting the difference between the first parameter and the second parameter; and allowing the accelerator device to execute the radiotherapy plan for the object for which radiotherapy has not been completed when detecting that the difference between the first parameter and the second parameter is a value within a preset interval.

[0014] Optionally, the error determination method for the accelerator further includes: after detecting the difference value between the first parameter and the second parameter, when it is detected that the difference value between the first parameter and the second parameter is a value outside a preset interval, adjusting the accelerator device according to the difference value between the first parameter and the second parameter; and determining the device error of the accelerator device after the adjustment through a preset plan and a target model.

[0015] Optionally, the accelerator device parameters included in the preset plan include at least the following parameters: a gantry angle parameter, used to characterize the gantry angle set for the accelerator device in the preset plan; an accelerator beam output parameter, used to characterize the number of hops set for the accelerator device in the preset plan; a multi-leaf grating parameter, used to characterize the blade motion law set for the accelerator device according to the multi-leaf grating system in the preset plan; and a target parameter, used to characterize the motion law set for multiple tungsten gates of the accelerator device in the preset plan.

[0016] According to another aspect of the present application, an error determination device for an accelerator is also provided, wherein the error determination device for an accelerator further includes: an acquisition unit, used to acquire a preset plan and a target radiotherapy plan for the target object before each target object receives radiotherapy, wherein the preset plan is used to test the accelerator device through pre-set accelerator device parameters; a plan execution unit, used to execute the preset plan on the accelerator device to obtain a target execution result of the accelerator device for the preset plan; a first determination unit, used to determine a target error of the accelerator device according to the target execution result; and a second determination unit, used to determine estimated dose information according to the target error, wherein the estimated dose information represents dose information generated by the accelerator device when executing the target radiotherapy plan in the presence of a target error.

[0017] Optionally, the first determination unit includes: a first determination sub-unit, used to input the target execution result into the target model, and determine the target error of the accelerator device according to the target execution result through prior knowledge of the target model, wherein the prior knowledge is used to characterize the correlation between the execution result output by the accelerator device when executing the error plan and the known device error of the accelerator device.

[0018] Optionally, the error determination device for the accelerator further includes: a parameter modification unit, a recording unit, an error plan execution unit, and a model training unit. The parameter modification unit is used to modify the parameter values ​​of the accelerator device parameters in the preset plan to obtain the error plan; the recording unit is used to record the parameter difference values ​​between the accelerator device parameters in the error plan and the accelerator device parameters in the preset plan; the error plan execution unit is used to execute the error plan on the accelerator device to obtain the execution result of the error plan by the accelerator device; the model training unit is used to train and obtain the target model according to the parameter difference value and the execution result of the error plan.

[0019] Optionally, the model training unit includes: a first processing subunit and a second processing subunit. The first processing subunit is used to input the execution result of the error plan, the parameter difference value and the preset plan into the neural network; the second processing subunit is used to iteratively train the neural network to learn the relationship between the execution result of the error plan, the parameter difference value and the preset plan, until the similarity between the plan execution result output by the neural network based on the parameter difference value and the preset plan prediction and the execution result of the error plan is greater than a first preset similarity, and / or the similarity between the device error value of the accelerator device output by the neural network based on the execution result of the error plan prediction and the parameter difference value is greater than a second preset similarity.

[0020] Optionally, the second determination unit includes: a parameter adjustment subunit and a third processing subunit. The parameter adjustment subunit is used to adjust the accelerator device parameters included in the target radiotherapy plan according to the target error, and use the adjusted target radiotherapy plan as the target error plan; the third processing subunit is used to determine the estimated dose information according to the target error plan.

[0021] Optionally, the error determination device for the accelerator further includes: a detection unit, a first processing unit, and a second processing unit. The detection unit is used to detect the similarity between the estimated dose information and the target dose information, wherein the target dose information represents the dose information generated by the accelerator device when the target radiotherapy plan is executed without error; the first processing unit is used to prohibit the use of the accelerator device to execute the target radiotherapy plan when it is detected that the similarity between the estimated dose information and the target dose information is greater than a preset threshold; the second processing unit is used to allow the accelerator device to execute the target radiotherapy plan when it is detected that the similarity between the estimated dose information and the target dose information is less than or equal to the preset threshold.

[0022] Optionally, the error determination device for the accelerator further includes: a third processing unit, a fourth processing unit, a fifth processing unit, a sixth processing unit, and a seventh processing unit. The third processing unit is used to obtain a log file generated by the accelerator device when executing the target radiotherapy plan; the fourth processing unit is used to use the device parameters actually executed by the accelerator device recorded in the log file as the first parameter; the fifth processing unit is used to use the accelerator device parameters included in the target radiotherapy plan as the second parameter; the sixth processing unit is used to detect the difference between the first parameter and the second parameter; the seventh processing unit is used to allow the accelerator device to execute the radiotherapy plan for the object that has not completed the radiotherapy when it is detected that the difference between the first parameter and the second parameter is a value within a preset interval.

[0023] Optionally, the error determination device for the accelerator further includes: an eighth processing unit and a ninth processing unit. The eighth processing unit is used to adjust the accelerator device according to the difference value of the first parameter and the second parameter when it is detected that the difference value of the first parameter and the second parameter is a value outside the preset interval; and the ninth processing unit is used to determine the device error of the accelerator device after the adjustment through a preset plan and a target model.

[0024] According to another aspect of the present application, an electronic device is also provided, wherein the electronic device includes one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by one or more processors, the one or more processors execute any one of the above-mentioned error determination methods for an accelerator.

[0025] In the present application, a preset plan and a target radiotherapy plan for a target object are first obtained, wherein the preset plan includes preset accelerator device parameters. Then, the preset plan is executed on the accelerator device to obtain the target execution result of the accelerator device on the preset plan, the target error of the accelerator device is determined according to the target execution result, and the estimated dose information is determined according to the target error, wherein the estimated dose information represents the dose information generated by the accelerator device when executing the target radiotherapy plan in the presence of the target error.

[0026] From the above content, it can be seen that before using the accelerator device to execute the target radiotherapy plan of the target object, the present application first obtains the target execution result of the accelerator device for the preset plan, and then determines the possible target error of the accelerator device based on the target execution result. This method does not require human intervention and can be implemented repeatedly, thereby reducing the cost of manual inspection of the status of the accelerator device.

[0027] In addition, after obtaining the target error, the dose information generated by the accelerator device when executing the target radiotherapy plan in the presence of the target error can be estimated based on the target error. This is equivalent to verifying the state of the accelerator device before formal radiotherapy of the target object, and estimating the treatment effect of the accelerator device in this state when executing the target radiotherapy plan, which is beneficial to enhancing the controllability of the treatment effect on the target object.

[0028] It can be seen that through the technical solution of the present application, the purpose of quality inspection of the accelerator equipment can be achieved before each patient is treated, thereby achieving the technical effect of improving the stability and controllability of the radiotherapy effect, and further solving the technical problem in the prior art that the equipment status of the accelerator cannot be verified before each patient is treated, resulting in poor controllability of the radiotherapy effect for the patient. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0030] Figure 1 is a flow chart of an optional error determination method for an accelerator according to an embodiment of the present application;

[0031] Figure 2 is a flow chart of training an optional target model according to an embodiment of the present application;

[0032] Figure 3 It is a schematic diagram of an optional error determination device for an accelerator according to an embodiment of the present application. DETAILED DESCRIPTION

[0033] 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.

[0034] 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.

[0035] It should also be noted that the information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) collected by this application are information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data are in compliance with the relevant laws, regulations and standards of the relevant regions, necessary confidentiality measures are taken, and public order and good customs are not violated, and corresponding operation portals are provided for users to choose to authorize or refuse. For example, an interface is set up between this system and relevant users or institutions. Before obtaining relevant information, it is necessary to send an acquisition request to the aforementioned user or institution through the interface, and obtain relevant information after receiving the consent information fed back by the aforementioned user or institution.

[0036] According to an embodiment of the present application, a method embodiment of an error determination method for an accelerator is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0037] In an optional embodiment, an accelerator quality inspection system can be used as the execution subject of the error determination method for the accelerator in the embodiment of the present application, wherein the accelerator quality inspection system can be a software system or an embedded system combining software and hardware. In addition, those skilled in the art can understand that in addition to using the above-mentioned accelerator quality inspection system as the execution subject, the execution subject of the error determination method for the accelerator can also be other devices or equipment, and the embodiment of the present application does not specifically limit this. For the convenience of description, the accelerator quality inspection system is used as the execution subject below.

[0038] Figure 1 is a flow chart of an optional method for determining an error of an accelerator according to an embodiment of the present application, such as Figure 1 As shown, the method comprises the following steps:

[0039] Step S101, obtaining a preset plan and a target radiotherapy plan for a target object.

[0040] In step S101 , the preset plan is used to test the accelerator device by using preset accelerator device parameters.

[0041] Optionally, there may be multiple preset plans, which may also be referred to as morning inspection plans. The preset plans are stored in a morning inspection plan library, wherein the morning inspection plan library is a database connected to the accelerator quality inspection system.

[0042] Optionally, the preset plan includes pre-set accelerator device parameters, wherein the accelerator device parameters include but are not limited to the following device parameters:

[0043] A gantry angle parameter is used to characterize the gantry angle set for the accelerator device in a preset plan;

[0044] Accelerator beam output parameters, used to characterize the number of hops set for the accelerator device in the preset plan;

[0045] Multileaf grating parameters, used to characterize the leaf motion law set for the accelerator equipment according to the multileaf grating system in the preset plan;

[0046] The target parameters are used to characterize the motion patterns of multiple tungsten gates set for the accelerator equipment in the preset plan.

[0047] It should be noted that for each accelerator device parameter, multiple sub-plans can be pre-set. For example, the morning inspection plan library can include the following modules:

[0048] The rack angle verification module is used to feedback the rack angle accuracy of the accelerator device, that is, the rack angle verification module is used to detect whether there is an error in the rack angle parameter of the accelerator device. The rack angle verification module is correspondingly provided with N rack angle plans with an angle interval of X (which can be recorded as N first sub-plans), where X ranges from 1 to 5, and N=360 / X.

[0049] The accelerator beam verification module is used to feedback the beam stability of the accelerator device, that is, the accelerator beam verification module is used to detect the accelerator beam parameters of the accelerator device. The accelerator beam verification module is correspondingly provided with M sub-plans with different hop numbers of the accelerator device when the rack angle is 0 degrees (which can be recorded as M second sub-plans), where M is an integer greater than 1.

[0050] The multi-leaf grating (MLC) in-place accuracy verification module is used to detect the multi-leaf grating parameters of the accelerator device. The multi-leaf grating (MLC) in-place accuracy verification module is correspondingly provided with K sub-plans including all leaves moving from left to right in sequence and all leaves moving from right to left (which can be recorded as K third sub-plans), where K is an integer greater than 1.

[0051] The tungsten gate position accuracy verification module is used to detect the target parameters of the accelerator equipment. The tungsten gate position accuracy verification module is correspondingly provided with a sub-plan including S tungsten gates moving from left to right in sequence and all blades moving from right to left (which can be recorded as S fourth sub-plans), where S is an integer greater than 1.

[0052] It can be seen from the above content that the preset plan may include: N first sub-plans, M second sub-plans, K third sub-plans and S fourth sub-plans.

[0053] It should be noted that, in addition to the above-mentioned rack angle parameters, accelerator beam output parameters, multi-leaf grating parameters and target parameters, the accelerator device parameters may also include other parameters of the accelerator device. Those skilled in the art can select the accelerator device parameters according to the actual scenario to formulate a preset plan.

[0054] Optionally, the target object is a subject to be treated with radiotherapy using an accelerator device, and the target radiotherapy plan is a radiotherapy plan prepared by a doctor for the target object.

[0055] Step S102: executing a preset plan on the accelerator device to obtain a target execution result of the preset plan by the accelerator device.

[0056] Optionally, if an accelerator device is used to execute a target radiotherapy plan to treat a target object when there is an error in the accelerator device, the expected radiotherapy effect may not be achieved due to the error of the accelerator device, and even medical accidents may occur when the accelerator error is large. Therefore, it is necessary to perform quality inspection on the accelerator device.

[0057] However, in the prior art, the accelerator equipment is usually only inspected once in the morning on each treatment day, and then the accelerator equipment will not be inspected in the morning if it is not necessary on the same day. This is because in the prior art, the process of accelerator quality inspection is actually to use a patient's radiotherapy plan to control the accelerator for dry irradiation verification, that is, the accelerator equipment executes a patient's radiotherapy plan, but the patient does not receive actual radiation exposure. The doctor will manually judge whether there is an error in the accelerator based on the EPID (Electronic Portal Imaging Device) image generated when the accelerator equipment executes the patient's radiotherapy plan, combined with the patient's radiotherapy plan.

[0058] However, it should be noted that the cost of controlling the accelerator to execute the radiotherapy plan to obtain EPID images is relatively high. Therefore, for cost control reasons, the accelerator is usually only verified once during a treatment day, which leads to the problem that the accelerator's equipment status is not verified before each patient's treatment. In addition, the existing accelerator quality inspection process will also introduce new errors caused by EPID images, resulting in the problem that the final error assessment results of the accelerator may not be accurate.

[0059] In order to solve the above problems, the present application proposes a new accelerator quality inspection method, which does not require the use of the patient's radiotherapy plan to perform air-shot verification of the accelerator equipment, but instead uses a preset plan to determine the accelerator error. By executing the preset plan on the accelerator equipment, the target execution result of the accelerator equipment for the preset plan is obtained.

[0060] It should be noted that compared with the patient's radiotherapy plan, the content of the preset plan is simpler. The preset plan usually only includes the pre-set accelerator equipment parameters. Therefore, the preset plan can be regarded as a personalized plan specially formulated to test the specific parameters of the accelerator equipment. It does not need to include various complex data such as patient data and field data in the radiotherapy plan. Therefore, the cost of the accelerator equipment to execute the preset plan is lower, and there is no need to generate EPID images. Generally speaking, by combining the measurement results of the third-party water tank hardware, the EPID results of the accelerator itself, and the execution log, the target execution results of the accelerator equipment for the preset plan can be determined.

[0061] Step S103: determining a target error of the accelerator device according to the target execution result.

[0062] Optionally, after obtaining the target execution result of the accelerator device for the preset plan, the accelerator quality inspection system may determine the target error of the accelerator device in a variety of ways.

[0063] For example, since the preset plan is a manually preset plan, an execution result-error mapping table corresponding to the preset plan can also be created when creating the preset plan, wherein the execution result-error mapping table is used to record the accelerator errors corresponding to different execution results of the preset plan. As shown in Table 1:

[0064] Table 1

[0065]

[0066] It can be seen that the accelerator quality inspection system can determine the target error of the accelerator device by referring to the execution result-error mapping table.

[0067] In addition, the accelerator quality inspection system can also use a pre-trained target model to determine the target error of the accelerator device according to the target execution result of the accelerator device for the preset plan. The target model can be a neural network model, for example, a model trained using a deep learning algorithm.

[0068] Step S104: determining estimated dose information according to the target error.

[0069] In step S104, the estimated dose information represents the dose information generated by the accelerator device when executing the target radiotherapy plan in the presence of a target error.

[0070] Optionally, the accelerator quality inspection system can apply the determined target error of the accelerator device to the target radiotherapy plan of the target object, and then use the dose calculation engine software or the neural network model to calculate the estimated dose information generated when the accelerator device executes the target radiotherapy plan under the current target error, and then determine whether the accelerator device in the current state can be used to execute the target radiotherapy plan to perform radiotherapy on the target object based on the estimated dose information.

[0071] In addition, when there are G preset plans, the G preset plans can be executed on the accelerator device, and then the target execution results of the accelerator device for the G preset plans can be obtained. According to the target execution results, the G target errors of the accelerator device can be determined (the target error can be 0, which means that there is actually no error), where G is an integer greater than 1. Finally, the accelerator quality inspection system can determine G estimated dose information according to the G target errors, and use the G estimated dose information as a dose interval. By judging whether the dose interval meets the preset dose error interval, it is judged whether to use the accelerator device in the current state to execute the target radiotherapy plan.

[0072] Based on the contents of the above steps S101 to S104, it can be known that in the present application, the preset plan and the target radiotherapy plan of the target object are first obtained, wherein the preset plan includes the preset accelerator device parameters. Then, the preset plan is executed on the accelerator device to obtain the target execution result of the accelerator device on the preset plan, the target error of the accelerator device is determined according to the target execution result, and the estimated dose information is determined according to the target error, wherein the estimated dose information represents the dose information generated by the accelerator device when executing the target radiotherapy plan in the presence of the target error.

[0073] As can be seen from the above content, before using the accelerator device to execute the target radiotherapy plan of the target object, the present application first obtains the target execution result of the accelerator device for the preset plan, and then determines the target error that may exist in the accelerator device based on the target execution result. This method does not require manual intervention and can be implemented repeatedly, so the cost of manually inspecting the state of the accelerator device can be reduced. In addition, after obtaining the target error, the dose information generated by the accelerator device when executing the target radiotherapy plan in the presence of the target error can be estimated based on the target error, which is equivalent to verifying the state of the accelerator device before formal radiotherapy of the target object, and estimating the treatment effect of the accelerator device in this state when executing the target radiotherapy plan, which is conducive to enhancing the controllability of the treatment effect on the target object.

[0074] It can be seen that through the technical solution of the present application, the purpose of quality inspection of the accelerator equipment can be achieved before each patient is treated, thereby achieving the technical effect of improving the stability and controllability of the radiotherapy effect, and further solving the technical problem in the prior art that the equipment status of the accelerator cannot be verified before each patient is treated, resulting in poor controllability of the radiotherapy effect for the patient.

[0075] In an optional embodiment, the present application provides an embodiment of using a target model to determine the target error of an accelerator device based on a target execution result of a preset plan, including: the accelerator quality inspection system can input the target execution result into the target model, and determine the target error of the accelerator device based on the target execution result through prior knowledge of the target model, wherein the prior knowledge is used to characterize the correlation between the execution result output by the accelerator device when executing the error plan and the known device error of the accelerator device.

[0076] Optionally, after the accelerator quality inspection system inputs the target execution result into the target model, the target model can extract the feature vector of the target execution result, and then predict the target error of the accelerator device based on the extracted feature vector combined with the prior knowledge learned by the target model during the training phase.

[0077] From the above content, it can be seen that the present application adopts the method of introducing the target model, and uses the prior knowledge of the target model to predict the target error of the accelerator device. Compared with the existing technology and the above-mentioned method of using the execution result-error mapping table, as long as a sufficient number of training samples that meet the quality requirements are ensured to participate in the model training, a target model with good fitting effect and high prediction accuracy can be obtained. Moreover, the use of the target model to predict the error of the accelerator is not restricted by manual experience and the degree of detail of the execution result-error mapping table. It not only has a wider applicability, but also can ensure the accuracy of the prediction results.

[0078] In an optional embodiment, Figure 2 is a training flow chart of an optional target model according to an embodiment of the present application, such as Figure 2 As shown, the following steps are included:

[0079] Step S201, modifying the parameter values ​​of the accelerator device parameters in the preset plan to obtain an error plan.

[0080] Optionally, the accelerator equipment parameters in the preset plan may be modified by the accelerator quality inspection system to obtain an error plan.

[0081] For example, if the preset plan is "the rack angle is specified to execute 5 degrees", the plan can be modified to "the rack angle is executed at 5.5 degrees", and the modified plan is used as an error plan.

[0082] Optionally, when the above-mentioned preset plan may include N first sub-plans, M second sub-plans, K third sub-plans and S fourth sub-plans, the error plan may also be multiple.

[0083] For example, an error plan can be randomly generated based on the gantry angle parameters. Assuming that the gantry angle parameters are randomly modified L1 times, N*L1 error plans related to the gantry angle parameters can be obtained. An error plan can also be randomly generated based on the accelerator beam output parameters. Assuming that the accelerator beam output parameters are randomly modified L2 times, M*L2 error plans related to the accelerator beam output parameters can be obtained.

[0084] For another example, an error plan can be randomly generated based on the multi-leaf grating parameters. Assuming that the multi-leaf grating parameters are randomly modified L3 times, K*L3 error plans related to the multi-leaf grating parameters can be obtained; an error plan can also be randomly generated based on the target parameters. Assuming that the target parameters are randomly modified L4 times, L4*S error plans can be obtained.

[0085] The above L1, L2, L3, and L4 are all integers greater than or equal to 1.

[0086] Step S202 , recording the parameter difference between the accelerator device parameters in the error plan and the accelerator device parameters in the preset plan.

[0087] Optionally, assuming that the preset plan is "rack angle is specified to execute 5 degrees" and the error plan is "rack angle is executed 5.5 degrees", the parameter difference value is "rack angle deviation 0.5 degrees".

[0088] Step S203, executing the error plan on the accelerator device to obtain the execution result of the error plan by the accelerator device.

[0089] Step S204: training and obtaining a target model according to the parameter difference value and the execution result of the error plan.

[0090] Optionally, the accelerator quality inspection system can use the execution result of the accelerator device on the error plan as training data, and the parameter difference value between the error plan and the preset plan as training labels, and train the neural network using the training data and training labels to obtain the target model.

[0091] In an optional embodiment, in the process of training to obtain the target model based on the parameter difference value and the execution result of the error plan, the execution result of the error plan, the parameter difference value and the preset plan can be input into the neural network, and then the neural network is iteratively trained to learn the relationship between the execution result of the error plan, the parameter difference value and the preset plan until the similarity between the plan execution result predicted and output by the neural network based on the parameter difference value and the preset plan and the execution result of the error plan is greater than a first preset similarity, and / or the similarity between the device error value of the accelerator device predicted and output by the neural network based on the execution result of the error plan and the parameter difference value is greater than a second preset similarity.

[0092] Optionally, during the model training process, in addition to inputting parameter difference values ​​and the execution results of the error plan into the neural network, a preset plan can also be input into the neural network, thereby improving the learning efficiency of the neural network when learning the correlation between parameter difference values ​​and the execution results of the error plan. This is because the execution results generated by the accelerator when executing the error plan are not only affected by the parameter difference values, but also greatly affected by the preset plan, because in fact, the execution results of the error plan should essentially be the deviation results of the execution results of the preset plan after being affected by the parameter difference values. On this basis, adding a preset plan to let the neural network learn can allow the neural network to learn the correlation between the parameter difference values ​​and the execution results of the error plan more quickly, which is conducive to improving the convergence speed of the neural network.

[0093] Optionally, the convergence condition of the neural network may be that the similarity between the plan execution result output by the neural network based on the parameter difference value and the preset plan prediction and the execution result of the error plan is greater than a first preset similarity, and / or the similarity between the device error value of the accelerator device output by the neural network based on the execution result prediction of the error plan and the parameter difference value is greater than a second preset similarity. Both the first preset similarity and the second preset similarity can be custom set.

[0094] In an optional embodiment, when determining the estimated dose information according to the target error, the accelerator quality inspection system may adjust the accelerator device parameters included in the target radiotherapy plan according to the target error, and use the adjusted target radiotherapy plan as the target error plan. Then, the accelerator quality inspection system may determine the estimated dose information according to the target error plan, wherein the estimated dose information represents the dose information generated by the accelerator device when executing the target radiotherapy plan in the presence of the target error.

[0095] Optionally, assuming that the target error of the accelerator device is a gantry angle deviation of 0.5 degrees, the accelerator quality inspection system can also adjust the gantry angle included in the target radiotherapy plan to deviate from 0.5, and use the adjusted target radiotherapy plan as the target error plan. Subsequently, the accelerator quality inspection system performs dose calculation on the target error plan through a dose calculation engine to obtain estimated dose information.

[0096] It can be seen from the above content that the technical solution of the present application can not only determine the error information of the accelerator device, but also determine the dose information when the accelerator device executes the target radiotherapy plan under the current error condition.

[0097] In an optional embodiment, after determining the estimated dose information according to the target error plan, the accelerator quality inspection system may further detect the similarity between the estimated dose information and the target dose information, wherein the target dose information represents the dose information generated by the accelerator device when executing the target radiotherapy plan in the absence of an error. When it is detected that the similarity between the estimated dose information and the target dose information is greater than a preset threshold, the accelerator device is prohibited from executing the target radiotherapy plan; when it is detected that the similarity between the estimated dose information and the target dose information is less than or equal to the preset threshold, the accelerator device is allowed to execute the target radiotherapy plan.

[0098] Optionally, the accelerator quality inspection system can also use the dose calculation engine to calculate the dose of the target radiotherapy plan, so as to obtain the target dose information. It can be understood that the target dose information is the radiotherapy dose information that the doctor wants to achieve for the target object. Therefore, if it is detected that the similarity between the estimated dose information and the target dose information is greater than the preset threshold, it means that the target error of the accelerator has a great influence on the process of generating doses, which will cause a large dose error. Therefore, it is necessary to prohibit the use of the accelerator device in the current state to execute the target radiotherapy plan, and the accelerator device needs to perform error correction. Of course, if it is detected that the similarity between the estimated dose information and the target dose information is less than or equal to the preset threshold, it means that the target error of the accelerator has little influence on the process of generating doses and will not cause a large dose error. Therefore, the accelerator device in the current state can be used to execute the target radiotherapy plan.

[0099] In an optional embodiment, after the accelerator device is allowed to execute the target radiotherapy plan, the accelerator quality inspection system may obtain the log file generated by the accelerator device when executing the target radiotherapy plan, and then use the device parameters actually executed by the accelerator device recorded in the log file as the first parameter; and use the accelerator device parameters included in the target radiotherapy plan as the second parameter. The accelerator quality inspection system may detect the difference between the first parameter and the second parameter, and when it is detected that the difference between the first parameter and the second parameter is a value within a preset interval, the accelerator device is allowed to execute the radiotherapy plan for the object that has not completed radiotherapy.

[0100] Optionally, the present application also provides another scheme for detecting the error of the accelerator using a log file. For example, after the accelerator device executes the target radiotherapy plan, the accelerator quality inspection system can read the log file generated by the accelerator device when executing the target radiotherapy plan, and determine the error of the accelerator by analyzing the difference between the device parameters (i.e., the first parameters) actually executed by the accelerator device recorded in the log file and the accelerator device parameters (i.e., the second parameters) included in the target radiotherapy plan. For example, if the gantry angle actually executed by the accelerator is recorded as 7 degrees in the log file, but the gantry angle specified in the target radiotherapy plan is 5 degrees, it can be determined that there is an error of 2 degrees in the gantry angle of the accelerator. If the error of 2 degrees is within the preset range, the accelerator device is allowed to execute the radiotherapy plan of the object that has not completed the radiotherapy, that is, the radiotherapy plan of other objects can continue to be executed.

[0101] It should be noted that by using the log file to detect the error of the accelerator, the accelerator device may no longer be started to execute the preset plan, thereby further saving the use cost of the accelerator device.

[0102] In addition, after using the log file to determine the accelerator error, estimated dose information can also be calculated based on the accelerator error for the radiotherapy plan of the object that has not completed radiotherapy, and then it can be determined whether to execute the radiotherapy plan of the object that has not completed radiotherapy based on the calculated estimated dose information.

[0103] In an optional embodiment, after detecting the difference value between the first parameter and the second parameter, when it is detected that the difference value between the first parameter and the second parameter is a value outside a preset interval, the accelerator quality inspection system may adjust the accelerator device according to the difference value between the first parameter and the second parameter, and then determine the device error of the accelerator device after the adjustment through a preset plan and a target model.

[0104] Optionally, after the accelerator device is adjusted according to the difference between the first parameter and the second parameter, it is impossible to determine whether the adjusted accelerator device still has an error, so it is impossible to continue to use the log to make an error determination. At this time, an optional method is to continue to detect whether the accelerator device has an error after the adjustment through a preset plan. The specific execution steps are consistent with the content described above, and no unnecessary details are given here.

[0105] In an optional embodiment, in order to save the use cost of the accelerator, the method of determining the accelerator error using a preset plan and the method of determining the accelerator error using a log file can be used in combination. For example, for the first patient treated daily, the accelerator error is determined using a preset plan, and for the non-first patient treated daily, the accelerator error is determined using the accelerator log file after the treatment of the previous patient. If after determining the accelerator error using the accelerator log file after the treatment of the i-th patient, it is detected that the accelerator error at this time is large, and the accelerator needs to be error corrected, and after the accelerator completes the error correction, the preset plan is used to perform an error check on the corrected accelerator to determine the result of the error correction, where i is an integer greater than 1.

[0106] It can be seen that through the technical solution of the present application, the purpose of quality inspection of the accelerator equipment can be achieved before each patient is treated, thereby achieving the technical effect of improving the stability and controllability of the radiotherapy effect, and further solving the technical problem in the prior art that the equipment status of the accelerator cannot be verified before each patient is treated, resulting in poor controllability of the radiotherapy effect for the patient.

[0107] According to another aspect of the embodiment of the present application, there is also provided an error determination device for an accelerator, wherein: Figure 3 is a schematic diagram of an optional error determination device for an accelerator according to an embodiment of the present application, such as Figure 3 As shown, the error determination device for the accelerator includes: an acquisition unit 301 , a plan execution unit 302 , a first determination unit 303 and a second determination unit 304 .

[0108] Optionally, an acquisition unit 301 is used to acquire a preset plan and a target radiotherapy plan for the target object before each target object receives radiotherapy, wherein the preset plan is used to test the accelerator device through pre-set accelerator device parameters; a plan execution unit 302 is used to execute the preset plan on the accelerator device to obtain a target execution result of the accelerator device for the preset plan; a first determination unit 303 is used to determine a target error of the accelerator device according to the target execution result; and a second determination unit 304 is used to determine estimated dose information according to the target error, wherein the estimated dose information represents dose information generated by the accelerator device when executing the target radiotherapy plan in the presence of a target error.

[0109] Optionally, the first determination unit 303 includes: a first determination subunit, used to input the target execution result into the target model, and determine the target error of the accelerator device according to the target execution result through prior knowledge of the target model, wherein the prior knowledge is used to characterize the correlation between the execution result output by the accelerator device when executing the error plan and the known device error of the accelerator device.

[0110] Optionally, the error determination device for the accelerator further includes: a parameter modification unit, a recording unit, an error plan execution unit, and a model training unit. The parameter modification unit is used to modify the parameter values ​​of the accelerator device parameters in the preset plan to obtain the error plan; the recording unit is used to record the parameter difference values ​​between the accelerator device parameters in the error plan and the accelerator device parameters in the preset plan; the error plan execution unit is used to execute the error plan on the accelerator device to obtain the execution result of the error plan by the accelerator device; the model training unit is used to train and obtain the target model according to the parameter difference value and the execution result of the error plan.

[0111] Optionally, the model training unit includes: a first processing subunit and a second processing subunit. The first processing subunit is used to input the execution result of the error plan, the parameter difference value and the preset plan into the neural network; the second processing subunit is used to iteratively train the neural network to learn the relationship between the execution result of the error plan, the parameter difference value and the preset plan, until the similarity between the plan execution result output by the neural network based on the parameter difference value and the preset plan prediction and the execution result of the error plan is greater than a first preset similarity, and / or the similarity between the device error value of the accelerator device output by the neural network based on the execution result of the error plan prediction and the parameter difference value is greater than a second preset similarity.

[0112] Optionally, the second determination unit 304 includes: a parameter adjustment subunit and a third processing subunit. The parameter adjustment subunit is used to adjust the accelerator device parameters included in the target radiotherapy plan according to the target error, and use the adjusted target radiotherapy plan as the target error plan; the third processing subunit is used to determine the estimated dose information according to the target error plan.

[0113] Optionally, the error determination device for the accelerator further includes: a detection unit, a first processing unit, and a second processing unit. The detection unit is used to detect the similarity between the estimated dose information and the target dose information, wherein the target dose information represents the dose information generated by the accelerator device when the target radiotherapy plan is executed without error; the first processing unit is used to prohibit the use of the accelerator device to execute the target radiotherapy plan when it is detected that the similarity between the estimated dose information and the target dose information is greater than a preset threshold; the second processing unit is used to allow the accelerator device to execute the target radiotherapy plan when it is detected that the similarity between the estimated dose information and the target dose information is less than or equal to the preset threshold.

[0114] Optionally, the error determination device for the accelerator further includes: a third processing unit, a fourth processing unit, a fifth processing unit, a sixth processing unit, and a seventh processing unit. The third processing unit is used to obtain a log file generated by the accelerator device when executing the target radiotherapy plan; the fourth processing unit is used to use the device parameters actually executed by the accelerator device recorded in the log file as the first parameter; the fifth processing unit is used to use the accelerator device parameters included in the target radiotherapy plan as the second parameter; the sixth processing unit is used to detect the difference between the first parameter and the second parameter; the seventh processing unit is used to allow the accelerator device to execute the radiotherapy plan for the object that has not completed the radiotherapy when it is detected that the difference between the first parameter and the second parameter is a value within a preset interval.

[0115] Optionally, the error determination device for the accelerator further includes: an eighth processing unit and a ninth processing unit. The eighth processing unit is used to adjust the accelerator device according to the difference value of the first parameter and the second parameter when it is detected that the difference value of the first parameter and the second parameter is a value outside the preset interval; and the ninth processing unit is used to determine the device error of the accelerator device after the adjustment through a preset plan and a target model.

[0116] Optionally, the accelerator device parameters included in the preset plan include at least the following parameters: a gantry angle parameter, used to characterize the gantry angle set for the accelerator device in the preset plan; an accelerator beam output parameter, used to characterize the number of hops set for the accelerator device in the preset plan; a multi-leaf grating parameter, used to characterize the blade motion law set for the accelerator device according to the multi-leaf grating system in the preset plan; and a target parameter, used to characterize the motion law set for multiple tungsten gates of the accelerator device in the preset plan.

[0117] According to another aspect of the present application, an error determination device for an accelerator is also provided, wherein the error determination device for an accelerator further includes: an acquisition unit, used to acquire a preset plan and a target radiotherapy plan for a target object, wherein the preset plan includes pre-set accelerator device parameters; a plan execution unit, used to execute the preset plan on the accelerator device to obtain a target execution result of the accelerator device for the preset plan; a first determination unit, used to determine a target error of the accelerator device according to the target execution result; and a second determination unit, used to determine estimated dose information according to the target error, wherein the estimated dose information represents dose information generated by the accelerator device when executing the target radiotherapy plan in the presence of a target error.

[0118] According to another aspect of the present application, an electronic device is also provided, wherein the electronic device includes one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by one or more processors, the one or more processors execute any one of the above-mentioned error determination methods for an accelerator.

[0119] The serial numbers of the embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0120] 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.

[0121] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0122] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0123] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0124] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk, etc., which can store program code.

[0125] 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 method for determining an error of an accelerator, characterized in that: include: Before each target object receives radiotherapy, a preset plan and a target radiotherapy plan of the target object are obtained, wherein the preset plan is used to test the accelerator device through preset accelerator device parameters; Executing the preset plan on the accelerator device to obtain a target execution result of the preset plan by the accelerator device; determining a target error of the accelerator device according to the target execution result; Determining estimated dose information according to the target error, wherein the estimated dose information represents dose information generated by the accelerator device when executing the target radiotherapy plan in the presence of the target error; Wherein, determining the target error of the accelerator device according to the target execution result includes: inputting the target execution result into a target model, and determining the target error of the accelerator device according to the target execution result through prior knowledge of the target model, wherein the prior knowledge is used to characterize the correlation between the execution result output by the accelerator device when executing the error plan and the known device error of the accelerator device; The target model is trained by the following steps: The parameter values ​​of the accelerator device parameters in the preset plan are modified to obtain an error plan; the parameter difference values ​​between the accelerator device parameters in the error plan and the accelerator device parameters in the preset plan are recorded; the error plan is executed on the accelerator device to obtain the execution result of the error plan by the accelerator device; and the target model is trained according to the parameter difference value and the execution result of the error plan.

2. The error determination method for an accelerator according to claim 1, characterized in that: According to the parameter difference value and the execution result of the error plan, the target model is trained, including: Inputting the execution result of the error plan, the parameter difference value and the preset plan into a neural network; The neural network is iteratively trained to learn the relationship between the execution result of the error plan, the parameter difference value and the preset plan, until the similarity between the plan execution result output by the neural network based on the parameter difference value and the preset plan and the execution result of the error plan is greater than a first preset similarity, and / or the similarity between the device error value of the accelerator device output by the neural network based on the execution result of the error plan and the parameter difference value is greater than a second preset similarity.

3. The error determination method for an accelerator according to claim 1, characterized in that: Determining estimated dose information according to the target error includes: adjusting the accelerator device parameters included in the target radiotherapy plan according to the target error, and using the adjusted target radiotherapy plan as a target error plan; The estimated dose information is determined according to the target error plan.

4. The error determination method for an accelerator according to claim 3, characterized in that: After determining the estimated dose information according to the target error plan, the error determination method for the accelerator further includes: detecting a similarity between the estimated dose information and target dose information, wherein the target dose information represents dose information generated by the accelerator device when executing the target radiotherapy plan without errors; When it is detected that the similarity between the estimated dose information and the target dose information is greater than a preset threshold, prohibiting the use of the accelerator device to execute the target radiotherapy plan; When it is detected that the similarity between the estimated dose information and the target dose information is less than or equal to the preset threshold, the accelerator device is allowed to execute the target radiotherapy plan.

5. The error determination method for an accelerator according to claim 4, characterized in that: In the case where it is detected that the similarity between the estimated dose information and the target dose information is less than or equal to the preset threshold, after allowing the accelerator device to execute the target radiotherapy plan, the error determination method for the accelerator further includes: Obtaining a log file generated by the accelerator device when executing the target radiotherapy plan; Using the device parameter actually executed by the accelerator device recorded in the log file as the first parameter; using the accelerator equipment parameters included in the target radiotherapy plan as second parameters; Detecting a difference between the first parameter and the second parameter; When it is detected that the difference between the first parameter and the second parameter is a value within a preset interval, the accelerator device is allowed to execute a radiotherapy plan for the object for which radiotherapy has not been completed.

6. The error determination method for an accelerator according to claim 5, characterized in that: After detecting the difference between the first parameter and the second parameter, the error determination method for the accelerator further includes: When it is detected that the difference between the first parameter and the second parameter is a value outside the preset interval, adjusting the accelerator device according to the difference between the first parameter and the second parameter; The device error of the accelerator device after adjustment is determined through the preset plan and the target model.

7. The error determination method for an accelerator according to claim 1, characterized in that: The accelerator equipment parameters included in the preset plan include at least the following parameters: A gantry angle parameter, used to characterize the gantry angle set for the accelerator device in the preset plan; An accelerator beam output parameter, used to characterize the number of hops set for the accelerator device in the preset plan; Multileaf grating parameters, used to characterize the leaf motion law set for the accelerator device according to the multileaf grating system in the preset plan; The target parameter is used to characterize the motion law of the multiple tungsten gates set for the accelerator device in the preset plan.

8. An error determination device for an accelerator, characterized in that: include: an acquisition unit, used for acquiring a preset plan and a target radiotherapy plan of each target object before each target object receives radiotherapy, wherein the preset plan is used for testing the accelerator device by using preset accelerator device parameters; A plan execution unit, configured to execute the preset plan on the accelerator device to obtain a target execution result of the preset plan by the accelerator device; A first determining unit, configured to determine a target error of the accelerator device according to the target execution result; A second determining unit is used to determine estimated dose information according to the target error, wherein the estimated dose information represents dose information generated by the accelerator device when executing the target radiotherapy plan in the presence of the target error; The first determination unit includes: a first determination subunit, which is used to input the target execution result into the target model, and determine the target error of the accelerator device according to the target execution result through the prior knowledge of the target model, wherein the prior knowledge is used to characterize the correlation between the execution result output by the accelerator device when executing the error plan and the known device error of the accelerator device; The error determination device for the accelerator also includes: a parameter modification unit, used to modify the parameter values ​​of the accelerator device parameters in the preset plan to obtain an error plan; a recording unit, used to record the parameter difference values ​​between the accelerator device parameters in the error plan and the accelerator device parameters in the preset plan; an error plan execution unit, used to execute the error plan on the accelerator device to obtain the execution result of the error plan by the accelerator device; according to the parameter difference value and the execution result of the error plan, the target model is trained to obtain.

9. An electronic device, characterized in that: The invention comprises one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors execute the error determination method for an accelerator as described in any one of claims 1 to 7.

Images