Radiotherapy plan optimization method and device, electronic equipment, storage medium and product

Abstract

The invention provides a radiotherapy plan optimization method and device, electronic equipment, a storage medium and a product, and relates to the technical field of medical treatment. According to the specific implementation scheme, multiple first parameter sets corresponding to an initial radiotherapy plan are determined, the initial radiotherapy plan comprises parameter sets of multiple target spots, each first parameter set comprises the target spot weight of each target spot in the multiple target spots, and the parameter set of each target spot comprises the target spot position and the target spot size; based on the dose field corresponding to each first parameter group, determining a radiotherapy plan treatment duration corresponding to each first parameter group; determining a second parameter group from the plurality of first parameter groups based on the radiotherapy plan treatment duration corresponding to each first parameter group; and obtaining an optimized radiotherapy plan based on the second parameter group. Therefore, by determining the target weight of each target in the plurality of targets, the treatment duration in the radiotherapy plan is optimized to obtain the optimized radiotherapy plan, so that the treatment effect of each target can be improved.

Description

Technical Field

[0001] The present disclosure relates to the field of medical technology, and in particular to a method, device, electronic equipment, storage medium and product for optimizing a radiotherapy plan. Background Art

[0002] With the development of radiotherapy technology, automatic treatment planning technology based on reinforcement learning algorithms has become more and more mature. In the algorithm process of Gamma Knife automatic planning, a set of Gamma Knife treatment plans can be obtained based on the input target area information through algorithm calculation. The treatment plan includes the number, location, and size of the targets. However, the current reinforcement learning algorithm does not fully consider the impact of each target weight on the treatment plan when it is designed. Therefore, after obtaining preliminary reinforcement learning results, it is hoped that the quality of the treatment plan can be optimized by optimizing the target weights. Summary of the invention

[0003] The present disclosure provides a method, device, electronic device, storage medium and product for optimizing a radiotherapy plan. By determining the target weight of each target among multiple targets, the treatment duration in the radiotherapy plan is optimized to obtain an optimized radiotherapy plan, thereby accurately determining the treatment duration for each target, improving the treatment effect for each target, and improving the quality of the radiotherapy plan.

[0004] According to one aspect of the present disclosure, a method for optimizing a radiotherapy plan is provided, the method comprising:

[0005] Determine a plurality of first parameter groups corresponding to an initial radiotherapy plan, the initial radiotherapy plan comprising parameter sets of a plurality of targets, each first parameter group comprising a target weight of each target in the plurality of targets, and the parameter set of each target comprising a target position and a target size;

[0006] Determine the treatment duration of the radiotherapy plan corresponding to each first parameter group based on the dose field corresponding to each first parameter group;

[0007] Determining a second parameter group from the plurality of first parameter groups based on the radiotherapy plan treatment duration corresponding to each first parameter group;

[0008] Based on the second parameter group, an optimized radiotherapy plan is obtained.

[0009] In some embodiments, determining the treatment duration of the radiotherapy plan corresponding to each first parameter group based on the dose field corresponding to each first parameter group includes:

[0010] Determine the maximum dose value of the dose field corresponding to each first parameter group;

[0011] Based on the prescription dose and the maximum dose value of the dose field corresponding to each first parameter group, the treatment duration of the radiotherapy plan corresponding to each first parameter group is determined.

[0012] In some embodiments, determining a second parameter group from a plurality of first parameter groups based on the radiotherapy plan treatment duration corresponding to each first parameter group includes:

[0013] Determine a quality evaluation index for each first parameter group based on the dose field corresponding to each first parameter group, the quality evaluation index is used to evaluate the quality of the radiotherapy plan corresponding to the parameter group, and the quality evaluation index includes coverage and selectivity;

[0014] Based on the radiotherapy plan treatment duration and quality assessment index corresponding to each first parameter group, a second parameter group is determined from the multiple first parameter groups.

[0015] In some embodiments, based on the radiotherapy plan treatment duration and quality assessment index corresponding to each first parameter group, determining the second parameter group from the plurality of first parameter groups includes:

[0016] Determine at least one third parameter group from the plurality of first parameter groups, wherein the coverage rate and the selectivity rate corresponding to each third parameter group meet the index requirements, and the index requirements are used to indicate the preset quality of the radiotherapy plan;

[0017] A third parameter group with the shortest treatment duration is determined from the at least one third parameter group as the second parameter group.

[0018] In some embodiments, determining a quality assessment indicator for each first parameter group based on a dose field corresponding to each first parameter group includes:

[0019] Based on the dose field corresponding to each first parameter group, the coverage and selectivity corresponding to each first parameter group are determined. The coverage is used to indicate the proportion of the target volume within the radiotherapy target area that reaches the prescription dose to the total volume of the radiotherapy target area. The selectivity is used to indicate the proportion of the target volume within the radiotherapy target area that reaches the prescription dose to the dose volume indicated by the prescription dose.

[0020] In some embodiments, determining a plurality of first parameter groups corresponding to the initial radiotherapy plan includes:

[0021] Determine N initial parameter groups corresponding to the initial radiotherapy plan, each initial parameter group includes an initial target weight of each target among a plurality of randomly determined targets, and N is a positive integer greater than 1;

[0022] Based on the radiotherapy plan treatment time and quality evaluation index corresponding to each initial parameter group, the N initial parameter groups are iteratively optimized through a genetic algorithm to obtain multiple first parameter groups. The quality evaluation index includes fitness, which is determined based on coverage and selection rate.

[0023] In some embodiments, based on the radiotherapy plan treatment duration and quality assessment index corresponding to each initial parameter group, the N initial parameter groups are iteratively optimized by a genetic algorithm to obtain multiple first parameter groups, including:

[0024] Sorting the N initial parameter groups in order of fitness from small to large; wherein, if the fitness of at least two initial parameter groups is the same, sorting the at least two initial parameter groups in order of radiotherapy plan treatment duration from small to large;

[0025] Determine the top M initial parameter groups from the N initial parameter groups according to the sorting, where M is a positive integer greater than 1;

[0026] In the process of iteratively optimizing the M initial parameter groups by the genetic algorithm, cross-processing the M initial parameter groups by at least one cross-over algorithm to obtain M cross-processed parameter groups;

[0027] Based on the M initial parameter groups and the M cross-processed parameter groups, multiple first parameter groups are obtained.

[0028] In some embodiments, based on the M initial parameter groups and the M cross-processed parameter groups, multiple first parameter groups are obtained, including:

[0029] Performing mutation processing on the M cross-processed parameter groups to obtain M mutated parameter groups, the mutation processing comprising: for at least one cross-processed parameter group randomly determined from the M cross-processed parameter groups, randomly adjusting the target weight of each target included in each cross-processed parameter group in the at least one cross-processed parameter group;

[0030] Based on the M initial parameter groups and the M mutated parameter groups, multiple first parameter groups are obtained.

[0031] In some embodiments, based on the radiotherapy plan treatment duration and quality assessment index corresponding to each initial parameter group, the N initial parameter groups are iteratively optimized by a genetic algorithm to obtain multiple first parameter groups, including:

[0032] Dividing the N initial parameter groups into a plurality of initial populations, each initial population including at least one initial parameter group;

[0033] For each of the multiple initial populations, based on the radiotherapy plan treatment duration and fitness corresponding to each initial parameter group, at least one initial parameter group included in each initial population is iteratively optimized by a genetic algorithm to obtain at least one optimized parameter group corresponding to each initial population;

[0034] After each iterative optimization, a migration operation is performed on multiple initial populations containing the optimized parameter group to obtain multiple initial populations after migration;

[0035] Based on multiple initial populations after immigration, the elite population corresponding to each iterative optimization is determined, and one elite population is obtained after one iterative optimization;

[0036] The optimized parameter groups included in each of the multiple elite populations obtained through multiple iterations of optimization are determined as multiple first parameter groups.

[0037] According to another aspect of the present disclosure, there is provided a radiotherapy plan optimization device, the radiotherapy plan optimization device comprising: a processing module;

[0038] A processing module, configured to determine a plurality of first parameter groups corresponding to an initial radiotherapy plan, the initial radiotherapy plan comprising parameter sets of a plurality of targets, each first parameter group comprising a target weight of each target in the plurality of targets, and the parameter set of each target comprising a target position and a target size;

[0039] The processing module is further used to determine the treatment duration of the radiotherapy plan corresponding to each first parameter group based on the dose field corresponding to each first parameter group;

[0040] The processing module is further used to determine a second parameter group from the plurality of first parameter groups based on the radiotherapy plan treatment duration corresponding to each first parameter group;

[0041] The processing module is further used to obtain an optimized radiotherapy plan based on the second parameter group.

[0042] In some embodiments, the processing module is specifically configured to determine a maximum dose value of a dose field corresponding to each first parameter group;

[0043] The processing module is specifically used to determine the treatment duration of the radiotherapy plan corresponding to each first parameter group based on the prescription dose and the maximum dose value of the dose field corresponding to each first parameter group.

[0044] In some embodiments, the processing module is specifically used to determine a quality assessment indicator for each first parameter group based on a dose field corresponding to each first parameter group, the quality assessment indicator being used to assess the quality of the radiotherapy plan corresponding to the parameter group, the quality assessment indicator including coverage and selectivity;

[0045] The processing module is specifically used to determine the second parameter group from multiple first parameter groups based on the radiotherapy plan treatment time and quality evaluation index corresponding to each first parameter group.

[0046] In some embodiments, the processing module is specifically used to determine at least one third parameter group from the plurality of first parameter groups, the coverage rate and the selectivity rate corresponding to each third parameter group satisfy the index requirement, and the index requirement is used to indicate the preset quality of the radiotherapy plan;

[0047] The processing module is specifically used to determine the third parameter group with the shortest treatment time from at least one third parameter group as the second parameter group.

[0048] In some embodiments, the processing module is specifically used to determine the coverage and selectivity corresponding to each first parameter group based on the dose field corresponding to each first parameter group, the coverage is used to indicate the proportion of the target volume within the radiotherapy target area that reaches the prescription dose to the total volume of the radiotherapy target area, and the selectivity is used to indicate the proportion of the target volume within the radiotherapy target area that reaches the prescription dose to the dose volume indicated by the prescription dose.

[0049] In some embodiments, the processing module is specifically used to determine N initial parameter groups corresponding to the initial radiotherapy plan, each initial parameter group includes an initial target weight of each target among a plurality of randomly determined targets, and N is a positive integer greater than 1;

[0050] The processing module is specifically used to iteratively optimize N initial parameter groups through a genetic algorithm based on the radiotherapy plan treatment time and quality evaluation indicators corresponding to each initial parameter group to obtain multiple first parameter groups. The quality evaluation indicators include fitness, which is determined based on coverage and selection rate.

[0051] In some embodiments, the processing module is specifically used to sort the N initial parameter groups in order of fitness from small to large; wherein, when the fitness of at least two initial parameter groups is the same, the at least two initial parameter groups are sorted in order of radiotherapy plan treatment duration from small to large;

[0052] A processing module, specifically used to determine the top M initial parameter groups from the N initial parameter groups according to the sorting, where M is a positive integer greater than 1;

[0053] A processing module, specifically used for performing crossover processing on the M initial parameter groups by at least one crossover algorithm in the process of iteratively optimizing the M initial parameter groups by the genetic algorithm, so as to obtain M crossover-processed parameter groups;

[0054] The processing module is specifically used to obtain multiple first parameter groups based on the M initial parameter groups and the M cross-processed parameter groups.

[0055] In some embodiments, the processing module is specifically used to perform variation processing on the M cross-processed parameter groups to obtain M variation-processed parameter groups, wherein the variation processing includes: for at least one cross-processed parameter group randomly determined from the M cross-processed parameter groups, randomly adjusting the target weight of each target included in each cross-processed parameter group in the at least one cross-processed parameter group;

[0056] The processing module is specifically used to obtain multiple first parameter groups based on the M initial parameter groups and the M parameter groups after mutation processing.

[0057] In some embodiments, the processing module is specifically configured to divide the N initial parameter groups into a plurality of initial populations, each initial population including at least one initial parameter group;

[0058] The processing module is specifically used to iteratively optimize at least one initial parameter group included in each initial population through a genetic algorithm for each initial population among the multiple initial populations based on the radiotherapy plan treatment duration and fitness corresponding to each initial parameter group, so as to obtain at least one optimized parameter group corresponding to each initial population;

[0059] The processing module is specifically used to perform migration operations on multiple initial populations including the optimized parameter group after each iteration optimization to obtain multiple initial populations after migration;

[0060] The processing module is specifically used to determine the elite population corresponding to each iterative optimization based on multiple initial populations after immigration, and obtain an elite population in one iterative optimization;

[0061] The processing module is specifically used to determine the optimized parameter groups included in each of the multiple elite populations obtained by multiple iterative optimizations as multiple first parameter groups.

[0062] According to another aspect of the present disclosure, there is provided an electronic device, comprising:

[0063] processor;

[0064] a memory configured to store processor-executable instructions;

[0065] The processor is configured to execute instructions to implement the radiotherapy plan optimization method provided by the present disclosure.

[0066] According to another aspect of the present disclosure, a non-volatile storage medium is provided, on which a computer program is stored. When the computer program is read and executed, the method for optimizing the radiotherapy plan provided by the present disclosure is implemented.

[0067] According to another aspect of the present disclosure, a computer program product is provided. The computer program product includes computer instructions. When the computer instructions are executed on an electronic device, the method for optimizing the radiotherapy plan provided by the present disclosure is implemented.

[0068] The technical solution provided by the present disclosure can first obtain multiple parameter groups based on the initial radiotherapy plan including the parameter set of multiple targets, and then determine the radiotherapy treatment duration corresponding to each parameter group based on the dose field corresponding to each parameter group. Thus, based on the radiotherapy treatment duration corresponding to each parameter group, a parameter group is determined from the multiple parameter groups to obtain an optimized radiotherapy plan.

[0069] Since the initial radiotherapy plan does not fully consider the impact of target weight on the quality of the treatment plan, based on this, the present application optimizes the treatment plan through a target weight optimization algorithm. At the same time, when optimizing the target weight, the treatment duration of the treatment plan is introduced to achieve a shorter treatment time and obtain a better radiotherapy effect.

[0070] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0072] Figure 1 is a schematic diagram of an implementation environment of a radiotherapy plan optimization method shown in an embodiment of the present disclosure;

[0073] Figure 2 is a flow chart of a method for optimizing a radiotherapy plan shown in an embodiment of the present disclosure;

[0074] Figure 3 is a flow chart of another method for optimizing radiotherapy plan shown in an embodiment of the present disclosure;

[0075] Figure 4 is a structural schematic diagram of a radiotherapy plan optimization device shown in an embodiment of the present disclosure;

[0076] Figure 5 It is a schematic block diagram of an electronic device used to implement the method for optimizing radiotherapy plan according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0077] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0078] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0079] First, the application scenarios involved in the embodiments of the present disclosure are described. The optimization method of radiotherapy plan provided in the embodiments of the present disclosure can be applied in the field of medical technology, and specifically can be applied in the scenario of radiotherapy (abbreviated as radiotherapy).

[0080] In some embodiments, with the rapid development of computer and imaging technology, radiotherapy technology has continued to mature. The optimization method of radiotherapy plan provided in the embodiments of the present disclosure can be applied to precise radiotherapy technologies such as adaptive radiotherapy (Adaptive Radiation Therapy, ART), three-dimensional conformal radiotherapy (Three dimensional conformal Radiation Therapy, 3D-CRT), intensity modulated radiotherapy (Intensity Modulated Radio Therapy, IMRT) and image guided radiotherapy (Image Guide Radio Therapy, IGRT).

[0081] With the development of radiotherapy technology, how to quickly generate qualified medical records (radiotherapy plans) before radiotherapy has become an important issue in radiotherapy. In the algorithm process of automatic planning, a set of gamma knife plans can be obtained according to the information of the input target area and the algorithm. The radiotherapy plan includes the number, position, and collimator model of the targets. However, the current reinforcement learning algorithm does not fully consider the impact of the weight of each target on the treatment plan when it is designed. Therefore, after obtaining the preliminary reinforcement learning results (radiotherapy plan), it is hoped that the weight of the target can be changed without changing the position, number, and collimator model of the target to optimize the quality of the radiotherapy plan and find a better radiotherapy treatment plan. In the process of automatic planning, it is a very critical process to adjust the weight of the target to find the optimal target weight in the current target set.

[0082] Based on this, the embodiment of the present disclosure provides a method for optimizing a radiotherapy plan, which can first obtain multiple parameter groups based on an initial radiotherapy plan including a parameter set of multiple targets, and then determine the treatment duration of the radiotherapy plan corresponding to each parameter group based on the dose field corresponding to each parameter group. Thus, based on the treatment duration of the radiotherapy plan corresponding to each parameter group, a parameter group is determined from multiple parameter groups to obtain an optimized radiotherapy plan.

[0083] Since the initial radiotherapy plan does not fully consider the impact of target weight on the quality of the treatment plan, based on this, the present application optimizes the treatment plan through a target weight optimization algorithm. At the same time, when optimizing the target weight, the treatment duration of the treatment plan is introduced to achieve a shorter treatment time and obtain a better radiotherapy effect.

[0084] Figure 1 Schematic diagram of an implementation environment of a radiotherapy plan optimization method shown in an embodiment of the present disclosure. Figure 1 The implementation environment includes an image scanning device 101, a radiotherapy planning device 102 and a radiotherapy device 103.

[0085] The image scanning device 101 is a device for scanning and displaying the tumor site and surrounding normal tissue of the object to be radiotherapy. In some embodiments, the image scanning device 101 can be at least one of a cone beam computed tomography (CBCT) device, a computed tomography (CT) device, an emission computed tomography (ECT) device, a magnetic resonance imaging (MRI) device, a positron emission tomography (PET) device, and an ultrasound examination device.

[0086] In the disclosed embodiment, the image scanning device 101 is used to scan and obtain a planned image of the object to be radiotherapy, and then, the planned image of the object to be radiotherapy can be uploaded to the radiotherapy planning device 102, so that the radiotherapy planning device 102 can perform a subsequent radiotherapy plan optimization process based on the planned image of the object to be radiotherapy.

[0087] The radiotherapy planning device 102 is a device for generating and optimizing radiotherapy plans. In some embodiments, the radiotherapy planning device 102 may be at least one of a smart phone, a smart watch, a desktop computer, a laptop computer, a virtual reality terminal, an augmented reality terminal, a wireless terminal, and a laptop computer. Further, in some embodiments, the radiotherapy planning device 102 may run a radiotherapy planning system (TPS), which provides the function of generating and optimizing radiotherapy plans.

[0088] In the disclosed embodiment, the radiotherapy planning device 102 is used to determine multiple first parameter groups corresponding to an initial radiotherapy plan, the initial radiotherapy plan includes parameter sets for multiple targets, each first parameter group includes a target weight for each target in the multiple targets, and the parameter set for each target includes a target position and a target size; based on the dose field corresponding to each first parameter group, the treatment duration of the radiotherapy plan corresponding to each first parameter group is determined; based on the treatment duration of the radiotherapy plan corresponding to each first parameter group, a second parameter group is determined from the multiple first parameter groups; based on the second parameter group, an optimized radiotherapy plan is obtained.

[0089] In some embodiments, the radiotherapy planning device 102 is specifically used to determine the maximum dose value of the dose field corresponding to each first parameter group; based on the prescription dose and the maximum dose value of the dose field corresponding to each first parameter group, determine the radiotherapy plan treatment duration corresponding to each first parameter group.

[0090] In some embodiments, the radiotherapy planning device 102 is specifically used to determine the quality assessment index of each first parameter group based on the dose field corresponding to each first parameter group, the quality assessment index is used to evaluate the quality of the radiotherapy plan corresponding to the parameter group, and the quality assessment index includes coverage and selectivity; based on the treatment duration and quality assessment index of the radiotherapy plan corresponding to each first parameter group, determine the second parameter group from multiple first parameter groups.

[0091] In some embodiments, the radiotherapy planning device 102 is specifically used to determine at least one third parameter group from multiple first parameter groups, and the coverage and selectivity corresponding to each third parameter group meet the index requirements, and the index requirements are used to indicate the preset quality of the radiotherapy plan; determine the third parameter group with the shortest treatment time from at least one third parameter group as the second parameter group.

[0092] In some embodiments, the radiotherapy planning device 102 is specifically used to determine the coverage and selectivity corresponding to each first parameter group based on the dose field corresponding to each first parameter group, the coverage is used to indicate the proportion of the target volume within the radiotherapy target area that reaches the prescribed dose to the total volume of the radiotherapy target area, and the selectivity is used to indicate the proportion of the target volume within the radiotherapy target area that reaches the prescribed dose to the dose volume indicated by the prescription dose.

[0093] In some embodiments, the radiotherapy planning device 102 is specifically used to determine N initial parameter groups corresponding to the initial radiotherapy plan, each initial parameter group includes an initial target weight for each of a plurality of randomly determined targets, and N is a positive integer greater than 1; based on the radiotherapy plan treatment duration and quality evaluation index corresponding to each initial parameter group, the N initial parameter groups are iteratively optimized through a genetic algorithm to obtain multiple first parameter groups, and the quality evaluation index includes fitness, which is determined based on coverage and selection rate.

[0094] In some embodiments, the radiotherapy planning device 102 is specifically used to sort the N initial parameter groups in order of fitness from small to large; wherein, when the fitness of at least two initial parameter groups is the same, at least two initial parameter groups are sorted in order of radiotherapy plan treatment duration from small to large; according to the sorting, the top M initial parameter groups are determined from the N initial parameter groups, where M is a positive integer greater than 1; in the process of iteratively optimizing the M initial parameter groups through a genetic algorithm, the M initial parameter groups are cross-processed through at least one crossover algorithm to obtain M cross-processed parameter groups; based on the M initial parameter groups and the M cross-processed parameter groups, multiple first parameter groups are obtained.

[0095] In some embodiments, the radiotherapy planning device 102 is specifically used to perform variation processing on M cross-processed parameter groups to obtain M variation-processed parameter groups, and the variation processing includes: for at least one cross-processed parameter group randomly determined from the M cross-processed parameter groups, randomly adjusting the target weight of each target included in each cross-processed parameter group in at least one cross-processed parameter group; based on the M initial parameter groups and the M variation-processed parameter groups, obtaining multiple first parameter groups.

[0096] In some embodiments, the radiotherapy planning device 102 is specifically used to divide N initial parameter groups into multiple initial populations, each initial population including at least one initial parameter group; for each initial population in the multiple initial populations, based on the radiotherapy plan treatment duration and fitness corresponding to each initial parameter group, at least one initial parameter group included in each initial population is iteratively optimized through a genetic algorithm to obtain at least one optimized parameter group corresponding to each initial population; after each iterative optimization, the multiple initial populations containing the optimized parameter groups are migrated to obtain multiple initial populations after migration; based on the multiple initial populations after migration, an elite population corresponding to each iterative optimization is determined; based on the elite population corresponding to each iteration, multiple first parameter groups are obtained.

[0097] In some embodiments, the radiotherapy planning device 102 is specifically configured to determine P optimized parameter groups with the smallest fitness from the elite population corresponding to each iteration as the multiple first parameter groups.

[0098] The radiotherapy device 103 is a device used for radiotherapy. In some embodiments, the radiotherapy device 103 can be at least one of a gamma knife, a linear accelerator, a neutron knife, an X-ray therapy machine, and the like.

[0099] In the disclosed embodiment, the radiotherapy device 103 is used to receive the radiotherapy plan from the radiotherapy planning device 102, and perform radiotherapy on the subject to be treated according to the radiotherapy plan.

[0100] In some embodiments, the implementation environment further includes a server 104. In some embodiments, the server 104 is used to provide background communication services for the above-mentioned image scanning device 101, radiotherapy planning device 102 and radiotherapy device 103.

[0101] Among them, the server 104 can be an independent physical server, or a server cluster or distributed file system composed of multiple physical servers, or at least one of the cloud servers that provide basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content distribution networks, and big data or artificial intelligence platforms, etc., which is not limited in the embodiments of the present disclosure. In some embodiments, the number of the above-mentioned servers 104 can be more or less, which is not limited in the embodiments of the present disclosure. Of course, the server 104 can also include other functions to provide more comprehensive and diversified services.

[0102] The following is based on Figure 1 The implementation environment shown is used to introduce the method provided by the embodiment of the present disclosure.

[0103] Figure 2 1 is a flow chart of a method for optimizing a radiotherapy plan shown in an embodiment of the present disclosure. In some embodiments, the method for optimizing a radiotherapy plan is executed by an electronic device. For example, the electronic device may be the above-mentioned Figure 1 The radiotherapy planning equipment shown. Figure 2 As shown, the method includes the following steps.

[0104] S201. The radiotherapy planning device determines a plurality of first parameter groups corresponding to an initial radiotherapy plan.

[0105] The initial radiotherapy plan includes parameter sets of multiple targets, each first parameter group includes a target weight of each target in the multiple targets, and the parameter set of each target includes a target position and a target size.

[0106] In the disclosed embodiment, the radiotherapy plan is a file used to control the radiotherapy equipment to deliver radiation, and the initial radiotherapy plan is a preliminary treatment plan generated based on the planned image of the object to be radiotherapy obtained by scanning the imaging scanning device. The initial radiotherapy plan needs to be further optimized to obtain an optimized radiotherapy plan.

[0107] In some embodiments, the initial radiotherapy plan may include parameter sets of multiple targets, each of which is obtained based on the planning image, and each of which may include: target position (such as position coordinates), target size (also known as collimator size), target weight, etc. By optimizing the target weight of the initial radiotherapy plan (for example, by genetic algorithm), an optimized radiotherapy plan may be obtained.

[0108] It can be understood that the multiple first parameter groups corresponding to the initial radiotherapy plan are parameter groups obtained after the target weight optimization of the initial radiotherapy plan, that is, the optimized radiotherapy plan.

[0109] S202. The radiotherapy planning device determines the radiotherapy plan treatment duration corresponding to each first parameter group based on the dose field corresponding to each first parameter group.

[0110] It should be noted that the dose field is used to characterize the dose distribution at different positions in the target area of ​​the object to be radiotherapy.

[0111] For example, the dose field can be expressed in the form of an image, a table, or a curve. For example, in the form of an image, the dose field can be a three-dimensional dose distribution diagram. The embodiment of the present disclosure does not limit the form of expression of the dose distribution.

[0112] In this way, through the dose field corresponding to each first parameter group and according to the data information contained in the dose field, the treatment duration of the radiotherapy plan corresponding to each first parameter group can be determined.

[0113] S203. The radiotherapy planning device determines a second parameter group from multiple first parameter groups based on the radiotherapy plan treatment duration corresponding to each first parameter group.

[0114] In the disclosed embodiment, after determining the treatment duration of the radiotherapy plan corresponding to each first parameter group, a group of first parameter groups (i.e., the second parameter group) corresponding to the optimal (shortest) treatment duration can be determined, and based on the parameters included in this group of first parameter groups, an optimized radiotherapy plan can be obtained.

[0115] S204: The radiotherapy planning device obtains an optimized radiotherapy plan based on the second parameter group.

[0116] The technical solution provided by the embodiment of the present disclosure can first obtain multiple parameter groups according to the initial radiotherapy plan including the parameter set of multiple targets, and then determine the radiotherapy treatment time corresponding to each parameter group based on the dose field corresponding to each parameter group. Thus, based on the radiotherapy treatment time corresponding to each parameter group, a parameter group is determined from the multiple parameter groups to obtain an optimized radiotherapy plan.

[0117] Since the initial radiotherapy plan does not fully consider the impact of target weight on the quality of the treatment plan, based on this, the present application optimizes the treatment plan through a target weight optimization algorithm. At the same time, when optimizing the target weight, the treatment duration of the treatment plan is introduced to achieve a shorter treatment time and obtain a better radiotherapy effect.

[0118] Above Figure 2 This is an embodiment of the present disclosure. The following describes the method for optimizing the radiotherapy plan provided by the present disclosure based on a specific embodiment. Figure 3 1 is a flow chart of a method for optimizing a radiotherapy plan shown in an embodiment of the present disclosure. In some embodiments, the method for optimizing a radiotherapy plan is executed by an electronic device. For example, the electronic device may be the above-mentioned Figure 1 The radiotherapy planning equipment shown. Figure 3 As shown, with the radiotherapy planning device as the execution subject, the method includes the following steps:

[0119] S301. The radiotherapy planning device determines N initial parameter groups corresponding to the initial radiotherapy plan.

[0120] Each initial parameter group includes an initial target weight of each target among a plurality of randomly determined targets, and N is a positive integer greater than 1.

[0121] In some embodiments, after the radiotherapy planning device acquires the planning image of the object to be radiotherapy, the gamma knife automatic planning algorithm based on reinforcement learning can be used to calculate a preliminary gamma knife automatic plan (i.e., initial radiotherapy plan) based on the planning image. Specifically, the initial radiotherapy plan includes: the number of targets, the size of the target (i.e., the collimator model), and the position of the target.

[0122] It should be noted that when randomly determining the initial target weight of each target, the collimator model corresponding to each target can be referred to. The larger the collimator model, the larger the initial target weight assigned to the target.

[0123] It should be understood that the initial radiotherapy plan is completed before the implementation of this program. The following is a brief description of the process of making the initial radiotherapy plan: First, the medical staff uses the image scanning equipment to scan and locate the object to be radiotherapy, and obtains the scanned image (such as a CT image or an MRI image) of the object to be radiotherapy. After that, the medical staff outlines the acquired scanned image to outline the target area and its surrounding tissues that need to be radiotherapy, and gives the prescribed dose (such as the minimum radiation dose and the maximum radiation dose) of the target area and the organs at risk. Finally, the medical staff combines the outlined image and the prescribed dose, and uses the radiotherapy planning system provided by the radiotherapy planning equipment to complete the preparation of the initial radiotherapy plan.

[0124] In some embodiments, when performing the plan optimization of the current object to be radiotherapy, the medical staff may upload the initial radiotherapy plan of the current object to be radiotherapy to the radiotherapy planning device. The corresponding process may be: the radiotherapy planning device receives the upload operation (or import operation) of the initial radiotherapy plan by the medical staff, and in response to the upload operation (or import operation) of the initial radiotherapy plan, obtains the initial radiotherapy plan of the object to be radiotherapy.

[0125] Alternatively, in other embodiments, the radiotherapy planning device may pre-maintain one or more initial radiotherapy plans for the objects to be radiotherapy, and when performing plan optimization for the current object to be radiotherapy, the initial radiotherapy plan for the current object to be radiotherapy is obtained from the one or more initial radiotherapy plans for the objects to be radiotherapy.

[0126] In the above embodiments, two implementation methods are provided for the radiotherapy planning device to obtain the initial radiotherapy plan for the object to be radiotherapy, thereby improving the flexibility of obtaining the initial radiotherapy plan.

[0127] It is worth noting that, in other embodiments, the radiotherapy planning device may also use other implementations to perform the above process of obtaining the initial radiotherapy plan for the object to be radiotherapy. The embodiments of the present disclosure are not limited to this.

[0128] Exemplarily, as shown in Table 1, there are N initial parameter groups corresponding to the initial radiotherapy plan, each of which includes an initial target weight corresponding to each of the multiple targets (e.g., 10 targets) of the initial radiotherapy plan. The N initial parameter groups can be understood as the first generation of seeds in the genetic algorithm (e.g., N is 30, i.e., the first generation of seeds includes 30 seeds), and each seed represents a set of target weights (i.e., the initial target weight of each of the multiple targets).

[0129] Table 1

[0130]

[0131] It can be understood that the initial parameter group shown in Table 1 can be considered as 30 10-dimensional seeds, each seed is a 1*10 vector (ie, the initial treatment plan includes 10 targets, and each seed includes initial target weights corresponding to the 10 targets).

[0132] S302. The radiotherapy planning device iteratively optimizes N initial parameter groups through a genetic algorithm based on the radiotherapy plan treatment duration and quality assessment index corresponding to each initial parameter group to obtain multiple first parameter groups.

[0133] Among them, the quality assessment index includes fitness, which is determined based on coverage and selectivity. Fitness is used to characterize the quality of the radiotherapy plan corresponding to the initial parameter group. It should be understood that the smaller the value of fitness, the smaller the gap between the radiotherapy plan corresponding to the initial parameter group and the preset requirement of the quality assessment index (that is, the smaller the difference between the coverage and selectivity of the radiotherapy plan and the threshold), indicating that the effect of the radiotherapy plan is better.

[0134] The following is an explanation of how to determine fitness:

[0135] Fitness is proposed to measure the quality of each result of the genetic algorithm. Fitness describes the evaluation score of the solution of the current genetic algorithm compared with the coverage index (for example: 95%) and the selection rate index (for example: 80%). When the selection rate is constant, the smaller the coverage rate is than the coverage rate index, the greater the fitness; when the coverage rate is constant, the smaller the selection rate is than the selection rate index, the greater the fitness.

[0136] It should be noted that the coverage rate refers to the ratio of the volume of the target area that reaches the prescribed dose to the total volume of the target area. For example, the calculation formula of the coverage rate can refer to the following formula 1.

[0137]

[0138] The selectivity refers to the ratio of the target volume that reaches the prescribed dose to the volume required by the prescribed dose. For example, the formula for calculating the selectivity can refer to the following formula 2.

[0139]

[0140] Further, the radiotherapy planning device can determine the first function parameter De1 based on the coverage and the preset coverage threshold. The preset coverage threshold refers to a pre-set coverage index, such as 95% (95 is used for calculation during the calculation process). It should be understood that when the coverage reaches 95%, it means that the ratio of the target volume that reaches the prescribed dose to the total volume of the target area meets the clinical index requirements.

[0141] Exemplarily, the first function parameter De1 may be determined by the following formula three based on the coverage and a preset coverage threshold.

[0142]

[0143] Among them, α is a coefficient greater than 1 (for example, 5, 10 or 20, etc.), round() is a rounding function, and the first function parameter De1 is expressed as the difference between a preset coverage threshold (95%) and the coverage. When the coverage is less than or equal to the preset coverage threshold (95%), the first function parameter De1 is also numerically increased based on α, that is, multiplied by the preset value α.

[0144] It should be noted that the numerical value increase process may be multiplication by a preset value, addition by a preset value, squaring, etc. The embodiment of the present disclosure does not limit the specific implementation of the numerical value increase process.

[0145] It can be understood that when the coverage rate is greater than the preset coverage rate threshold, the first function parameter De1 is a negative value, and when the coverage rate is less than or equal to the preset coverage rate threshold, the first function parameter De1 is a value greater than or equal to 0.

[0146] In the disclosed embodiment, the first function parameter De1 is negatively correlated with the target area coverage. The first function parameter De1 indicates the deviation between the current coverage and the preset coverage threshold (for example, 95%). If the current coverage is less than or equal to the preset coverage threshold (for example, 95%), the deviation is expanded by α.

[0147] And, the radiotherapy planning device can determine the second function parameter De2 based on the selectivity and the preset selectivity threshold. The preset selectivity threshold refers to a preset selectivity index, such as 80% (80 is used for calculation during the calculation process). It should be understood that when the target area selectivity reaches 80%, it means that the ratio of the target area volume that reaches the prescription dose to the target area volume required by the prescription dose meets the clinical index requirement.

[0148] Exemplarily, the second function parameter De2 may be determined by the following formula 4 based on the selection rate and a preset selection rate threshold.

[0149]

[0150] Among them, α is a coefficient greater than 1 (for example, 5, 10 or 20, etc.), round() is a rounding function, and the second function parameter De2 is expressed as the difference between a preset selectivity threshold value (80%) and the selectivity. When the selectivity is less than or equal to the preset selectivity threshold value (80%), the second function parameter De2 is also numerically increased based on α, that is, multiplied by the preset value α.

[0151] It should be noted that the numerical value increase process may be multiplication by a preset value, addition by a preset value, squaring, etc. The embodiment of the present disclosure does not limit the specific implementation of the numerical value increase process.

[0152] It can be understood that when the selection rate is greater than the preset selection rate threshold, the second function parameter De2 is a negative value, and when the selection rate is less than or equal to the preset selection rate threshold, the second function parameter De2 is a value greater than or equal to 0.

[0153] In the embodiment of the present disclosure, the second function parameter De2 is negatively correlated with the selectivity, and the second function parameter De2 indicates the deviation between the current selectivity and a preset selectivity threshold (e.g., 80%). If the current selectivity is less than or equal to the preset selectivity threshold (e.g., 80%), the deviation is expanded by α.

[0154] Based on this, the radiotherapy planning device obtains fitness (Fitness) based on the first function parameter De1 and the second function parameter De2.

[0155] Exemplarily, the fitness (Fitness) may be determined by the following formula 5 based on the first function parameter De1 and the second function parameter De2.

[0156] Fitness=De1+De2Formula 5

[0157] It can be understood that when the coverage rate is greater than the preset coverage rate threshold, the first function parameter De1 is a negative value, and when the coverage rate is less than or equal to the preset coverage rate threshold, the first function parameter De1 is a value greater than or equal to 0; and when the selection rate is greater than the preset selection rate threshold, the second function parameter De2 is a negative value, and when the selection rate is less than or equal to the preset selection rate threshold, the second function parameter De2 is a value greater than or equal to 0. Therefore, when the fitness is the smallest, it corresponds to the optimal solution of the genetic algorithm.

[0158] In the disclosed embodiment, the fitness (Fitness) is positively correlated with the first function parameter De1 and the second function parameter De2, respectively. Specifically, the fitness (Fitness) can be expressed as the sum of the first function parameter De1 and the second function parameter De2. Alternatively, the fitness (Fitness) can be expressed as the product of the first function parameter De1 and the second function parameter De2. Of course, other methods can also be used to determine the fitness (Fitness) number. The disclosed embodiment will be described later using the sum as an example to illustrate the solution.

[0159] The following is an explanation of how to determine the duration of radiotherapy treatment:

[0160] First, the radiotherapy planning device calculates the initial dose value of each target in the dose field according to the initial target weight of each target included in each initial parameter group, and then sums the initial dose value of each target by voxel position to obtain the maximum dose value of the dose field corresponding to the entire target area (i.e., each initial parameter group).

[0161] Furthermore, by calculating the ratio between the prescribed dose and the maximum dose value of the dose field corresponding to each initial parameter group, the treatment duration of the radiotherapy plan corresponding to each initial parameter group can be determined.

[0162] In this way, after determining the radiotherapy plan treatment duration and quality assessment index (ie, fitness) corresponding to each initial parameter group, the N initial parameter groups can be iteratively optimized through a genetic algorithm to obtain multiple first parameter groups.

[0163] In some embodiments, the N initial parameter groups may be iteratively optimized by using a genetic algorithm in combination with the parameter of the radiotherapy plan treatment duration to obtain multiple first parameter groups. The above step S302 may specifically include the following steps:

[0164] S401. The radiotherapy planning device sorts N initial parameter groups in order of fitness from small to large.

[0165] Wherein, when the fitness of at least two initial parameter groups is the same, the at least two initial parameter groups are sorted in ascending order of the treatment duration of the radiotherapy plan.

[0166] In the disclosed embodiment, during each iterative optimization process, the seeds (i.e., N initial parameter groups, or parameter groups selected during subsequent iterations) are first sorted according to fitness. When the fitness is the same, they are sorted in ascending order according to the treatment duration of the radiotherapy plan.

[0167] S402: The radiotherapy planning device determines M initial parameter groups with the highest ranking from the N initial parameter groups according to the ranking.

[0168] Wherein, M is a positive integer greater than 1.

[0169] Exemplarily, the 30 seeds (ie, N initial parameter groups) are sorted according to the fitness and treatment duration sorting rule from small to large, and the top 30 seeds (ie, the top M initial parameter groups) are determined as parent seeds.

[0170] It should be noted that when the N initial parameter groups (30 seeds) are iterated for the first time, the top 30 seeds selected from the sorting are the N initial parameter groups. In the subsequent iterations, since the child seeds can be obtained based on the parent seeds, the parent seeds and the child seeds are sorted, and the top M seeds can be selected.

[0171] S403. In the process of iteratively optimizing the M initial parameter groups by using the genetic algorithm, the radiotherapy planning device performs cross processing on the M initial parameter groups by using at least one crossover algorithm to obtain M cross-processed parameter groups.

[0172] In some embodiments, two initial parameter groups can be randomly selected from the M initial parameter groups (i.e., parent seeds), and a probability value (e.g., a value between 0 and 1) is randomly generated for the two initial parameter groups. If the randomly generated probability value is less than the preset reference probability, the target weights in the two initial parameter groups are cross-processed (any cross-over algorithm) to obtain two cross-processed parameter groups (i.e., offspring seeds). If the randomly generated probability value is greater than or equal to the preset reference probability, there is no need to cross-process the target weights in the two initial parameter groups, and the two initial parameter groups are directly used as offspring seeds.

[0173] It should be noted that for the two initial parameter groups that need to be cross-processed, multiple cross-processing algorithms can be used to cross-process the target weights in the two initial parameter groups. Thus, two cross-processed parameter groups are obtained by each cross-processing algorithm. That is, assuming that three cross-processing algorithms are used to cross-process the target weights in the two initial parameter groups, six cross-processed parameter groups can be obtained.

[0174] Then, multiple cross-processed parameter groups (such as the 6 cross-processed parameter groups mentioned above) obtained by multiple cross-processing algorithms are screened, and the two best cross-processed parameter groups (for example, they can be selected based on quality assessment indicators and treatment duration) with target weights within a reasonable range (such as a preset limit range) are selected as offspring seeds.

[0175] In this way, two initial parameter groups are randomly selected from the M initial parameter groups for crossover processing, until M parameter groups after crossover processing are selected as offspring seeds.

[0176] In some embodiments, the crossover algorithm may specifically be an algorithm such as arithmetic crossover, uniform crossover, excellent seed crossover, or two-point crossover.

[0177] Exemplarily, arithmetic crossover specifically includes: for the two selected initial parameter groups (for example, the target weights included are a1(i) and a2(i)), two corresponding random numbers (for example, r1 and r2) are randomly generated, so that two cross-processed parameter groups can be calculated through the target weights a1(i) and a2(i), and the random numbers r1 and r2, for example, A1(i)=0.5*(a1(i)*(1+r1)+(1-r2)*a2(i)) and A2(i)=0.5*(a2(i)*(1+r2)+(1-r1)*a1(i)). Wherein, A1(i) or A2(i) is the target weight included in the cross-processed parameter group, and a1(i) or a2(i) is the target weight included in the initial parameter group.

[0178] Another exemplary embodiment of uniform crossover is as follows: for the two selected initial parameter groups (for example, the target weights included are a1(i) and a2(i)), a random number u is randomly generated. If u is less than or equal to 0.5, the crossover parameter b is determined to be equal to (2*u) to the (1 / 11)th power. If u is greater than 0.5, b is equal to 1 / (2*(1-u) to the (1 / 11)th power. In this way, based on these parameters, two crossover parameter groups can be obtained, for example, A1(i)=0.5*(a1(i)*(1-b)+(1+b)*a2(i)) and A2(i)=0.5*(a1(i)*(1+b)+(1-b)*a2(i)). Wherein, A1(i) or A2(i) is the target weight included in the crossover parameter group, and a1(i) or a2(i) is the target weight included in the initial parameter group.

[0179] Another exemplary method is that the excellent seed crossover is as follows: for the two selected initial parameter groups (for example, the target weights included are a1(i) and a2(i)), two corresponding random numbers (for example, c1 and c2) are randomly generated, so that two cross-processed parameter groups can be calculated by the target weights a1(i) and a2(i), and the random numbers c1 and c2, for example, A1(i)=0.5*(a1(i)*(1+c1)+(1-c2)*a1(i)) and A2(i)=0.5*(a1(i)*(1+c2)+(1-c1)*a2(i)). Wherein, A1(i) or A2(i) is the target weight included in the cross-processed parameter group, and a1(i) or a2(i) is the target weight included in the initial parameter group.

[0180] S404: The radiotherapy planning device obtains multiple first parameter groups based on the M initial parameter groups and the M cross-processed parameter groups.

[0181] It can be understood that after cross-processing the M initial parameter groups to obtain M cross-processed parameter groups, the M cross-processed parameter groups can be further mutated, or the M cross-processed parameter groups can be not mutated and subsequent steps (such as determining the quality assessment index of each first parameter group) can be directly executed.

[0182] In some embodiments, the M initial parameter groups may be optimized for multiple iterations, and at the end of any iteration, it is determined whether the current iteration satisfies a preset iteration condition, and if the current iteration satisfies the preset iteration condition, the iteration is stopped. The preset iteration condition may be that the number of iterations reaches a preset number of iterations, such as 100, 1000, or other times.

[0183] Specifically, when it is necessary to further perform mutation processing on the M cross-processed parameter groups, the above step S404 may include:

[0184] S4041. The radiotherapy planning device performs variation processing on the M cross-processed parameter groups to obtain M variation-processed parameter groups.

[0185] The mutation processing includes: for at least one cross-processed parameter group randomly determined from the M cross-processed parameter groups, randomly adjusting the target weight of each target included in each cross-processed parameter group in the at least one cross-processed parameter group.

[0186] In some embodiments, for each of the M cross-processed parameter groups, a probability value (e.g., a value between 0 and 1) can be randomly generated. If the probability value is less than a preset mutation probability, the weight of each target point included in the cross-processed parameter group is randomly adjusted (e.g., adding or subtracting a random value); if the probability value is greater than or equal to the preset mutation probability, mutation processing may not be performed, and M mutation-processed parameter groups are ultimately obtained.

[0187] S4042. The radiotherapy planning device obtains multiple first parameter groups based on the M initial parameter groups and the M parameter groups after variation processing.

[0188] In this way, after further performing mutation processing on the M cross-processed parameter groups to obtain M mutated parameter groups, multiple first parameter groups can be obtained based on the M initial parameter groups and the M mutated parameter groups.

[0189] In some embodiments, after obtaining M parameter groups after variation processing (or M parameter groups after crossover processing), the target weights included in the M parameter groups after variation processing (or M parameter groups after crossover processing) can also be normalized, that is, for each parameter group after variation processing (or each parameter group after crossover processing), all target weights included in the parameter group can be added together to obtain the total weight, and each target weight can be divided by the total weight to obtain the normalized target weight in each parameter group after variation processing (or each parameter group after crossover processing).

[0190] Further, for each parameter group in the M initial parameter groups and each parameter group in the M mutated parameter groups, the fitness and radiotherapy plan treatment duration corresponding to each parameter group are calculated again. For the method of determining the fitness and radiotherapy plan treatment duration, reference can be made to the above-mentioned related description, which will not be repeated here.

[0191] In this way, the M initial parameter groups are used as parent seeds, and the M parameter groups after mutation processing (or M parameter groups after crossover processing) are used as child seeds, so that the parent seeds and the child seeds are merged to obtain 2M seeds, and M seeds are selected from the 2M seeds as parent seeds for the next iteration, and steps S401 to S404 are repeated until the preset iteration conditions are met to obtain multiple first parameter groups.

[0192] Specifically, the 2M seeds obtained by merging the parent seed and the child seed can be sorted in order from small to large according to the fitness of each seed, and the top M seeds are determined from the 2M seeds according to the sorting as the parent seeds for the next iteration. In the case where the fitness of multiple seeds is the same, the multiple seeds are sorted in order from small to large according to the treatment duration of the radiotherapy plan.

[0193] In some embodiments, the N initial parameter groups may be iteratively optimized by combining a genetic algorithm with multiple populations and an elite strategy to obtain multiple first parameter groups. The above step S302 may specifically include the following steps:

[0194] S501. The radiotherapy planning device divides N initial parameter groups into multiple initial populations.

[0195] Each initial population includes at least one initial parameter group.

[0196] In some embodiments, N initial parameter groups (i.e., parent seeds) may be randomly divided into multiple initial populations, for example, N initial parameter groups may be divided into 5 initial populations, each of which may include N / 5 initial parameter groups. It should be noted that the number of initial parameter groups included in each initial population may be the same or different.

[0197] S502. For each of the multiple initial populations, the radiotherapy planning device iteratively optimizes at least one initial parameter group included in each initial population through a genetic algorithm based on the radiotherapy plan treatment duration and fitness corresponding to each initial parameter group, to obtain at least one optimized parameter group corresponding to each initial population.

[0198] In some embodiments, for each of the multiple initial populations, it is also necessary to sort at least one initial parameter group included in each initial population in order from small to large according to the fitness corresponding to each initial parameter group included in each initial population, and determine the top-ranked initial parameter group from the at least one initial parameter group included in each initial population according to the sorting (the number of selected parameter groups is consistent with the number of at least one initial parameter group included in each initial population). Then, the at least one initial parameter group included in each initial population is iteratively optimized through a genetic algorithm to obtain at least one optimized parameter group corresponding to each initial population. It should be noted that this process can be specifically referred to the relevant description in the above steps S401-S403, which will not be repeated here.

[0199] It can be understood that when the N initial parameter groups (30 seeds) are iterated for the first time, the top 30 seeds selected from the sorting are the N initial parameter groups. In the subsequent iterations, since the child seeds can be obtained based on the parent seeds, the parent seeds and the child seeds are merged and sorted, and the top M seeds can be selected as the parent seeds for the next iteration.

[0200] It should be noted that when performing crossover and mutation processing on at least one initial parameter group included in each initial population, it is necessary to perform processing based on the parameters corresponding to each initial population (such as a preset restriction range, a preset mutation probability, etc.).

[0201] In addition, the target weights included in the parameter group after the variation processing (or the parameter group after the cross processing) can also be normalized, and the fitness and radiotherapy plan treatment duration corresponding to each parameter group can be calculated. For the normalization processing and the method for determining the fitness and radiotherapy plan treatment duration, reference can be made to the above-mentioned related descriptions, which will not be repeated here.

[0202] S503 . After each iterative optimization, perform an immigration operation on multiple initial populations including the optimized parameter group to obtain multiple initial populations after immigration.

[0203] It can be understood that in each iterative optimization process, each initial population can be subjected to crossover and mutation processing, and then immigration processing can be performed between the multiple initial populations after the crossover and mutation processing to obtain multiple initial populations after immigration.

[0204] S504: Based on the multiple initial populations after immigration, determine the elite population corresponding to each iterative optimization.

[0205] Among them, one iterative optimization obtains an elite population.

[0206] In some embodiments, after performing an iterative optimization on at least one initial parameter group included in each initial population, an immigration process may be performed between multiple initial populations after crossover and mutation processing to obtain multiple initial populations after immigration. Then, the multiple initial populations after immigration are merged, and each seed in the multiple initial populations is sorted in order from small to large in fitness. When the fitness is the same, the seeds are sorted in order from small to large in the treatment duration of the radiotherapy plan, and based on the elite population selection rule, the top N seeds are selected as the elite population after this iterative optimization.

[0207] It should be noted that after each iterative optimization, migration operations and elite population selection are required. That is, in the process of one iterative optimization, an elite population will be obtained from multiple initial populations after migration. When N iterations are performed, N elite populations will be generated. Therefore, the parameter groups included in these N elite populations are subsequently determined as multiple first parameter groups.

[0208] Specifically, the immigration process requires exchanging the better partially optimized parameter groups included in each initial population (i.e. the partially optimized parameter groups with the smallest fitness) with the worse optimized parameter groups included in other initial populations (i.e. the partially optimized parameter groups with the largest fitness), so as to realize information exchange between the initial populations, which helps to improve the convergence speed of the algorithm and avoid premature convergence.

[0209] In some embodiments, two initial populations (including a source population and a target population) can be selected from multiple initial populations, and then the half of the optimized parameter groups ranked higher in the source population are determined according to the fitness ranking (i.e., the parameter groups for immigrants are selected), and the half of the optimized parameter groups ranked lower in the target population are determined according to the fitness ranking (i.e., the parameter groups for immigrants are selected). Thus, the half of the optimized parameter groups ranked higher in the source population are used to replace the half of the optimized parameter groups ranked lower in the target population, and the immigration process is completed.

[0210] In some embodiments, the migration rules between multiple initial populations can be specifically as follows: randomly selecting two initial populations from multiple initial populations as the source population and the target population; or, grouping the multiple initial populations, each group including two initial populations (i.e., a source population and a target population); or, sorting the multiple initial populations, and according to the sorting sequence, the two initial populations corresponding to each two adjacent sequence numbers are used as the source population and the target population (i.e., assuming there are 3 initial populations, half of the parameter groups with a higher sorting in the second initial population can be migrated to the first initial population, half of the parameter groups with a higher sorting in the third initial population can be migrated to the second initial population, and half of the parameter groups with a higher sorting in the first initial population can be migrated to the third initial population).

[0211] In this way, after the optimized multiple initial populations are subjected to immigration processing, multiple initial populations after immigration processing can be obtained.

[0212] S505. The radiotherapy planning device determines the optimized parameter groups included in each of the multiple elite populations obtained through multiple iterations of optimization as multiple first parameter groups.

[0213] In some embodiments, the optimized parameter groups included in the elite population obtained in each iterative optimization may be merged to determine all the merged parameter groups as a plurality of first parameter groups.

[0214] In this way, by combining the genetic algorithm with multiple populations and elite strategies, the N initial parameter groups are iteratively optimized to determine the optimal multiple first parameter groups.

[0215] S303. The radiotherapy planning device determines the maximum dose value of the dose field corresponding to each first parameter group.

[0216] Finally, after performing multiple iterations on the initial parameter group and determining the final multiple first parameter groups, the maximum dose value of the dose field corresponding to each first parameter group can be constructed.

[0217] S304. The radiotherapy planning device determines the radiotherapy plan treatment duration corresponding to each first parameter group based on the prescription dose and the maximum dose value of the dose field corresponding to each first parameter group.

[0218] Furthermore, by calculating the ratio between the prescribed dose and the maximum dose value of the dose field corresponding to each first parameter group, the treatment duration of the radiotherapy plan corresponding to each first parameter group can be determined.

[0219] S305. The radiotherapy planning device determines a quality assessment index for each first parameter group based on the dose field corresponding to each first parameter group.

[0220] Among them, the quality assessment indicators are used to evaluate the quality of the radiotherapy plan corresponding to the parameter group, and the quality assessment indicators include coverage rate and selection rate.

[0221] In some embodiments, the above step S305 may specifically include the following steps:

[0222] S3051. The radiotherapy planning device determines the coverage and selectivity corresponding to each first parameter group based on the dose field corresponding to each first parameter group.

[0223] Among them, the coverage rate is used to indicate the proportion of the target volume within the radiotherapy target area that reaches the prescribed dose to the total volume of the radiotherapy target area, and the selectivity rate is used to indicate the proportion of the target volume within the radiotherapy target area that reaches the prescribed dose to the dose volume indicated by the prescription dose.

[0224] It should be noted that, based on the dose field corresponding to each first parameter group, the coverage and selectivity of each first parameter group are determined. The above-mentioned determination of fitness may be referred to, and will not be elaborated here.

[0225] S306. The radiotherapy planning device determines a second parameter group from multiple first parameter groups based on the radiotherapy plan treatment duration and quality assessment index corresponding to each first parameter group.

[0226] In some embodiments, the above step S306 may specifically include the following steps:

[0227] S3061. The radiotherapy planning device determines at least one third parameter group from the multiple first parameter groups.

[0228] Among them, the coverage rate and the selectivity rate corresponding to each third parameter group meet the index requirements, and the index requirements are used to indicate the preset quality of the radiotherapy plan.

[0229] In some embodiments, after determining the coverage, selectivity and radiotherapy plan treatment duration corresponding to each first parameter group, a qualified parameter group (i.e., at least one third parameter group, for example, a coverage greater than or equal to 95%, a selectivity greater than or equal to 80%) can be determined from multiple first parameter groups.

[0230] S3062. The radiotherapy planning device determines, from at least one third parameter group, a third parameter group with the shortest treatment duration as the second parameter group.

[0231] In some embodiments, if the plurality of first parameter groups include a parameter group that meets the standard, a parameter group with the shortest radiotherapy plan treatment time is selected from the parameter groups that meet the standard (ie, at least one third parameter group) as the second parameter group.

[0232] Furthermore, if there is no parameter group that meets the standard among the multiple first parameter groups, a parameter group with the same coverage and selectivity and the shortest radiotherapy plan treatment time is selected from the multiple first parameter groups as the second parameter group.

[0233] In this way, it can be ensured that when there is a standard parameter group in the optimized solution set (i.e., multiple first parameter groups), the result output with the shortest treatment time is selected, and when there is no standard parameter group, the result output with basically the same coverage rate and selection rate and the shortest treatment time is selected.

[0234] S307: The radiotherapy planning device obtains an optimized radiotherapy plan based on the second parameter group.

[0235] Finally, the radiotherapy planning device determines an optimized radiotherapy plan for the object to be radiotreated based on the weight of each target included in the second parameter group and in combination with the target quantity parameter, target location parameter, and target size parameter in the initial treatment plan.

[0236] The above mainly introduces the solution provided by the embodiment of the present application from the perspective of the method. In order to achieve the above functions, the power determination device or electronic device includes a hardware structure and / or software module corresponding to the execution of each function. It should be easily appreciated by those skilled in the art that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0237] The embodiments of the present disclosure may divide the functional modules of the communication device according to the above method embodiments. For example, each functional module may be divided corresponding to each function, or two or more functions may be integrated into one functional module. The above integrated modules may be implemented in the form of hardware or software. It should be noted that the division of modules in the embodiments of the present disclosure is schematic and is only a logical function division. There may be other division methods in actual implementation. The following is an example of dividing each functional module corresponding to each function.

[0238] Figure 4 Schematic diagram of a radiotherapy plan optimization device provided in an embodiment of the present disclosure, which is applied to electronic equipment. The radiotherapy plan optimization device 400 can execute the above method embodiment. Figure 2 and Figure 3 The optimization method of radiotherapy plan shown in Figure 4As shown, the radiotherapy plan optimization device 400 includes: a processing module 401.

[0239] A processing module 401 is used to determine a plurality of first parameter groups corresponding to an initial radiotherapy plan, the initial radiotherapy plan comprising parameter sets of a plurality of targets, each first parameter group comprising a target weight of each target in the plurality of targets, and the parameter set of each target comprising a target position and a target size;

[0240] The processing module 401 is further used to determine the treatment duration of the radiotherapy plan corresponding to each first parameter group based on the dose field corresponding to each first parameter group;

[0241] The processing module 401 is further configured to determine a second parameter group from the plurality of first parameter groups based on the radiotherapy plan treatment duration corresponding to each first parameter group;

[0242] The processing module 401 is further configured to obtain an optimized radiotherapy plan based on the second parameter group.

[0243] In some embodiments, the processing module 401 is specifically used to determine the maximum dose value of the dose field corresponding to each first parameter group;

[0244] The processing module 401 is specifically configured to determine the treatment duration of the radiotherapy plan corresponding to each first parameter group based on the prescription dose and the maximum dose value of the dose field corresponding to each first parameter group.

[0245] In some embodiments, the processing module 401 is specifically used to determine a quality evaluation index of each first parameter group based on a dose field corresponding to each first parameter group, the quality evaluation index is used to evaluate the quality of the radiotherapy plan corresponding to the parameter group, and the quality evaluation index includes coverage and selectivity;

[0246] The processing module 401 is specifically configured to determine a second parameter group from a plurality of first parameter groups based on the radiotherapy plan treatment duration and quality assessment index corresponding to each first parameter group.

[0247] In some embodiments, the processing module 401 is specifically used to determine at least one third parameter group from the plurality of first parameter groups, the coverage rate and the selectivity rate corresponding to each third parameter group satisfy the index requirement, and the index requirement is used to indicate the preset quality of the radiotherapy plan;

[0248] The processing module 401 is specifically configured to determine a third parameter group with the shortest treatment duration from at least one third parameter group as the second parameter group.

[0249] In some embodiments, the processing module 401 is specifically used to determine the coverage and selectivity corresponding to each first parameter group based on the dose field corresponding to each first parameter group, the coverage is used to indicate the proportion of the target volume within the radiotherapy target area that reaches the prescription dose to the total volume of the radiotherapy target area, and the selectivity is used to indicate the proportion of the target volume within the radiotherapy target area that reaches the prescription dose to the dose volume indicated by the prescription dose.

[0250] In some embodiments, the processing module 401 is specifically used to determine N initial parameter groups corresponding to the initial radiotherapy plan, each initial parameter group includes an initial target weight of each target among a plurality of randomly determined targets, and N is a positive integer greater than 1;

[0251] Processing module 401 is specifically used to iteratively optimize N initial parameter groups through a genetic algorithm based on the radiotherapy plan treatment duration and quality evaluation index corresponding to each initial parameter group to obtain multiple first parameter groups. The quality evaluation index includes fitness, which is determined based on coverage and selection rate.

[0252] In some embodiments, the processing module 401 is specifically used to sort the N initial parameter groups in order of fitness from small to large; wherein, when the fitness of at least two initial parameter groups is the same, the at least two initial parameter groups are sorted in order of radiotherapy plan treatment duration from small to large;

[0253] The processing module 401 is specifically used to determine the top M initial parameter groups from the N initial parameter groups according to the ranking, where M is a positive integer greater than 1;

[0254] The processing module 401 is specifically used to perform crossover processing on the M initial parameter groups by at least one crossover algorithm in the process of iteratively optimizing the M initial parameter groups by the genetic algorithm to obtain M crossover-processed parameter groups;

[0255] The processing module 401 is specifically configured to obtain a plurality of first parameter groups based on the M initial parameter groups and the M cross-processed parameter groups.

[0256] In some embodiments, the processing module 401 is specifically used to perform mutation processing on the M cross-processed parameter groups to obtain M mutation-processed parameter groups, wherein the mutation processing includes: for at least one cross-processed parameter group randomly determined from the M cross-processed parameter groups, randomly adjusting the target weight of each target included in each cross-processed parameter group in the at least one cross-processed parameter group;

[0257] The processing module 401 is specifically configured to obtain a plurality of first parameter groups based on the M initial parameter groups and the M mutated parameter groups.

[0258] In some embodiments, the processing module 401 is specifically configured to divide the N initial parameter groups into a plurality of initial populations, each initial population including at least one initial parameter group;

[0259] The processing module 401 is specifically configured to iteratively optimize at least one initial parameter group included in each initial population through a genetic algorithm for each initial population among the multiple initial populations based on the radiotherapy plan treatment duration and fitness corresponding to each initial parameter group, so as to obtain at least one optimized parameter group corresponding to each initial population;

[0260] The processing module 401 is specifically used to perform migration operations on multiple initial populations including the optimized parameter group after each iteration optimization to obtain multiple initial populations after migration;

[0261] The processing module 401 is specifically used to determine an elite population corresponding to each iterative optimization based on multiple initial populations after immigration, and obtain an elite population in one iterative optimization;

[0262] The processing module 401 is specifically configured to determine the optimized parameter groups included in each of the multiple elite populations obtained through multiple iterations of optimization as multiple first parameter groups.

[0263] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0264] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, including a processor; a memory configured to store processor executable instructions; wherein the processor is configured to execute the instructions to implement the radiotherapy plan optimization method provided by the present disclosure.

[0265] According to an embodiment of the present disclosure, the present disclosure further provides a non-volatile storage medium, wherein a computer program is stored on the storage medium, and when the computer program is read and executed, the method for optimizing the radiotherapy plan provided by the present disclosure is implemented.

[0266] According to an embodiment of the present disclosure, the present disclosure further provides a computer program product, which includes computer instructions. When the computer instructions are executed on an electronic device, the method for optimizing the radiotherapy plan provided by the present disclosure is implemented.

[0267] In some embodiments, the electronic device may be the above Figure 1 The radiation therapy planning device shown in . Figure 5A schematic block diagram of an example electronic device 500 that can be used to implement an embodiment of the present disclosure is shown. The electronic device 500 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device 500 can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0268] like Figure 5 As shown, the electronic device 500 includes a computing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 to a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the electronic device 500 can also be stored. The computing unit 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0269] Multiple components in the electronic device 500 are connected to the I / O interface 505, including: an input unit 506, such as a keyboard, a mouse, etc.; an output unit 507, such as various types of displays, speakers, etc.; a storage unit 508, such as a disk, an optical disk, etc.; and a communication unit 509, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 509 allows the electronic device 500 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0270] The computing unit 501 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSP), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 501 performs the various methods and processes described above, such as the optimization method of the radiotherapy plan. For example, in some embodiments, the optimization method of the radiotherapy plan may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 508. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 500 via the ROM 502 and / or the communication unit 509. When the computer program is loaded into the RAM 503 and executed by the computing unit 501, one or more steps of the optimization method of the radiotherapy plan described above may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to execute the optimization method for radiotherapy planning in any other appropriate manner (eg, by means of firmware).

[0271] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard parts (ASSPs), system on chip systems (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0272] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0273] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0274] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user, such as a cathode ray tube (CRT) or a liquid crystal display (LCD) monitor; and a keyboard and a pointing device (e.g., a mouse or a trackball), through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and the input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0275] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: Local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.

[0276] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0277] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of this disclosure can be achieved, and this document is not limited here.

[0278] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for optimizing a radiotherapy plan, characterized in that: include: Determine a plurality of first parameter groups corresponding to an initial radiotherapy plan, wherein the initial radiotherapy plan includes parameter sets of a plurality of targets, each of the first parameter groups includes a target weight of each of the plurality of targets, and each of the parameter sets of the target includes a target position and a target size; Determining the treatment duration of the radiotherapy plan corresponding to each of the first parameter groups based on the dose field corresponding to each of the first parameter groups; Determining a second parameter group from the plurality of first parameter groups based on the radiotherapy plan treatment duration corresponding to each of the first parameter groups; Based on the second parameter group, an optimized radiotherapy plan is obtained.

2. The method according to claim 1, characterized in that The step of determining the treatment duration of the radiotherapy plan corresponding to each of the first parameter groups based on the dose field corresponding to each of the first parameter groups includes: Determine a maximum dose value of the dose field corresponding to each of the first parameter groups; Based on the prescription dose and the maximum dose value of the dose field corresponding to each of the first parameter groups, the treatment duration of the radiotherapy plan corresponding to each of the first parameter groups is determined.

3. The method according to claim 1, characterized in that The determining of a second parameter group from the plurality of first parameter groups based on the radiotherapy plan treatment duration corresponding to each of the first parameter groups comprises: Determine a quality evaluation index for each of the first parameter groups based on the dose field corresponding to each of the first parameter groups, wherein the quality evaluation index is used to evaluate the quality of the radiotherapy plan corresponding to the parameter group, and the quality evaluation index includes coverage and selectivity; Based on the radiotherapy plan treatment duration and the quality assessment index corresponding to each of the first parameter groups, a second parameter group is determined from the multiple first parameter groups.

4. The method according to claim 3, characterized in that: The determining of a second parameter group from the plurality of first parameter groups based on the radiotherapy plan treatment duration and the quality assessment index corresponding to each of the first parameter groups comprises: Determine at least one third parameter group from the plurality of first parameter groups, the coverage rate and the selectivity rate corresponding to each third parameter group both satisfy an index requirement, and the index requirement is used to indicate a preset quality of a radiotherapy plan; A third parameter group with the shortest treatment duration is determined from the at least one third parameter group as the second parameter group.

5. The method according to claim 3, characterized in that: The determining, based on the dose field corresponding to each of the first parameter groups, a quality assessment index of each of the first parameter groups comprises: Based on the dose field corresponding to each of the first parameter groups, the coverage rate and the selectivity corresponding to each of the first parameter groups are determined, the coverage rate is used to indicate the proportion of the target volume within the radiotherapy target area that reaches the prescription dose to the total volume of the radiotherapy target area, and the selectivity is used to indicate the proportion of the target volume within the radiotherapy target area that reaches the prescription dose to the dose volume indicated by the prescription dose.

6. The method according to any one of claims 1 to 5, characterized in that The step of determining a plurality of first parameter groups corresponding to the initial radiotherapy plan includes: Determine N initial parameter groups corresponding to the initial radiotherapy plan, each of the initial parameter groups includes an initial target weight of each of the multiple targets determined randomly, and N is a positive integer greater than 1; Based on the radiotherapy plan treatment duration and quality evaluation index corresponding to each initial parameter group, the N initial parameter groups are iteratively optimized through a genetic algorithm to obtain the multiple first parameter groups. The quality evaluation index includes fitness, and the fitness is determined based on coverage and selection rate.

7. The method according to claim 6, characterized in that The step of iteratively optimizing the N initial parameter groups based on the radiotherapy plan treatment duration and quality assessment index corresponding to each initial parameter group by a genetic algorithm to obtain the multiple first parameter groups includes: The N initial parameter groups are sorted in the order of the fitness from small to large; wherein, when the fitness of at least two initial parameter groups is the same, the at least two initial parameter groups are sorted in the order of the treatment duration of the radiotherapy plan from small to large; Determine the top M initial parameter groups from the N initial parameter groups according to the ranking, where M is a positive integer greater than 1; In the process of iteratively optimizing the M initial parameter groups by the genetic algorithm, cross-processing the M initial parameter groups by at least one cross-processing algorithm to obtain M cross-processed parameter groups; The multiple first parameter groups are obtained based on the M initial parameter groups and the M cross-processed parameter groups.

8. The method according to claim 7, characterized in that The obtaining the plurality of first parameter groups based on the M initial parameter groups and the M cross-processed parameter groups comprises: Performing mutation processing on the M cross-processed parameter groups to obtain M mutated parameter groups, the mutation processing comprising: for at least one cross-processed parameter group randomly determined from the M cross-processed parameter groups, randomly adjusting the target weight of each target included in each cross-processed parameter group in the at least one cross-processed parameter group; The multiple first parameter groups are obtained based on the M initial parameter groups and the M mutated parameter groups.

9. The method according to claim 6, characterized in that The step of iteratively optimizing the N initial parameter groups based on the radiotherapy plan treatment duration and quality assessment index corresponding to each initial parameter group by a genetic algorithm to obtain the multiple first parameter groups includes: Dividing the N initial parameter groups into a plurality of initial populations, each initial population including at least one initial parameter group; For each of the multiple initial populations, based on the radiotherapy plan treatment duration and the fitness corresponding to each initial parameter group, iteratively optimize the at least one initial parameter group included in each initial population by using the genetic algorithm to obtain at least one optimized parameter group corresponding to each initial population; After each iterative optimization, a migration operation is performed on multiple initial populations containing the optimized parameter group to obtain multiple initial populations after migration; Based on the multiple initial populations after the migration, an elite population corresponding to each iterative optimization is determined, and one elite population is obtained after one iterative optimization; The optimized parameter groups included in each of the multiple elite populations obtained through multiple iterations of optimization are determined as the multiple first parameter groups.

10. A radiotherapy plan optimization device, characterized in that: The radiotherapy plan optimization device comprises: a processing module, configured to determine a plurality of first parameter groups corresponding to an initial radiotherapy plan, wherein the initial radiotherapy plan includes parameter sets of a plurality of targets, each of the first parameter groups includes a target weight of each of the plurality of targets, and each of the parameter sets of the target includes a target position and a target size; The processing module is further used to determine the treatment duration of the radiotherapy plan corresponding to each of the first parameter groups based on the dose field corresponding to each of the first parameter groups; The processing module is further configured to determine a second parameter group from the plurality of first parameter groups based on the radiotherapy plan treatment duration corresponding to each of the first parameter groups; The processing module is further used to obtain an optimized radiotherapy plan based on the second parameter group.

11. An electronic device, characterized in that: The electronic device comprises: processor; a memory configured to store instructions executable by the processor; The processor is configured to execute the instructions to implement the method according to any one of claims 1 to 9.

12. A non-volatile storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is read and executed, the method according to any one of claims 1 to 9 is implemented.

13. A computer program product, characterized in that The computer program product comprises computer instructions, and when the computer instructions are executed on an electronic device, the method according to any one of claims 1 to 9 is implemented.

Images