Dynamic adjustable radiotherapy multi-objective optimization method and system

Abstract

The invention discloses a dynamic adjustable radiotherapy multi-objective optimization method and system, and the method comprises the steps: receiving the clinical diagnosis and treatment information and constraint information of a patient, and dynamically generating a Pareto leading edge through a multi-objective optimization model; intensity optimization is carried out on the Pareto leading edge, and multiple groups of intensity optimization radiotherapy plans are generated; and providing a navigation interface to guide the user to select a final radiotherapy plan, and generating machine parameters of radiotherapy based on the final radiotherapy plan. According to the dynamic adjustable radiotherapy multi-objective optimization method, the intensity optimization radiotherapy plan is generated by using the intensity optimization Pareto leading edge, the plan result guides the user to balance the plan in a navigation interface mode, and after the final radiotherapy plan is screened, the machine parameters of radiotherapy are generated through the DVH constraint, so that the quality of the generated plan is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of radiotherapy, and in particular to a dynamically adjustable radiotherapy multi-objective optimization method and system. Background Art

[0002] Radiotherapy planning systems model the radiation source and patient, and perform inverse optimization and calculation of the absorbed dose distribution within the patient's body. This allows the radiation intensity within the target area to be modulated to achieve a sufficient lethal dose for tumor cells while minimizing the radiation dose to normal tissue surrounding the target area. However, traditional radiotherapy methods require different parameters for different constraints, making it impossible to simultaneously analyze dose changes to multiple organs within a limited timeframe. Multi-objective optimization systems, in addition to generating multiple Pareto plans, must combine user guidance to generate plans that are no less effective than traditional intensity-modulated plans. This also addresses challenges such as the lengthy multi-objective optimization process.

[0003] In view of this, the present invention patent is proposed. Summary of the Invention

[0004] In order to solve the above problems, the present invention provides a dynamically adjustable multi-objective optimization method and system for radiotherapy. Specifically, the following technical solutions are adopted:

[0005] A dynamically adjustable multi-objective optimization method for radiotherapy, characterized by comprising:

[0006] Receive the patient's clinical diagnosis and treatment information and constraint information, and dynamically generate the Pareto frontier through a multi-objective optimization model;

[0007] Perform intensity optimization on the Pareto frontier and generate multiple sets of intensity-optimized radiotherapy plans;

[0008] A navigation interface is provided to guide the user to select the final radiotherapy plan and generate the machine parameters for radiotherapy based on the final radiotherapy plan.

[0009] As an optional embodiment of the present invention, in a dynamically adjustable radiotherapy multi-objective optimization method of the present invention, the Pareto frontier is based on the patient's clinical diagnosis and treatment information and constraint information, and is determined by the initial multi-objective optimization model function.

[0010]

[0011] The Pareto solution of the surface in space is formed, where Ψ is the radiation intensity, f i is a constraint function, n represents the number of constraints, and the constraint function includes a DVH function and an EUD function.

[0012] As an optional embodiment of the present invention, in a dynamically adjustable multi-objective optimization method for radiotherapy of the present invention, performing intensity optimization on the Pareto front to generate multiple sets of intensity-optimized radiotherapy plans includes:

[0013] According to a set of predefined constraint weights w i ≥0,w1+…+w n =1, by optimizing the multi-objective optimization model function

[0014]

[0015] An optimal radiotherapy intensity solution is calculated, where the optimal radiotherapy intensity solution corresponds to a Pareto solution of the initial multi-objective optimization model function.

[0016] As an optional embodiment of the present invention, in a dynamically adjustable radiotherapy multi-objective optimization method of the present invention, the optimal radiotherapy intensity solution corresponds to a Pareto solution of the initial multi-objective optimization model function, and the objective function value of the Pareto solution [f1; ...; f n ] is the Pareto vertex on the Pareto front.

[0017] As an optional embodiment of the present invention, in a dynamically adjustable multi-objective optimization method for radiotherapy of the present invention, performing intensity optimization on the Pareto front to generate multiple sets of intensity-optimized radiotherapy plans includes:

[0018] Calculate n groups of anchor plans, each anchor plan uses a weight w i =1,w j =∈,j≠i,∈>0, and calculate the maximum value of the different constraint objective functions in the anchor plan and the minimum value Where i represents the current constraint parameter index;

[0019] Determine whether it is satisfied If the judgment result is yes, the corresponding constraint parameter is deleted from the constraint parameter list, and the target plan screening is re-performed on the remaining constraint parameters; if the judgment result is no, a weight search is performed.

[0020] As an optional embodiment of the present invention, in a dynamically adjustable multi-objective optimization method for radiotherapy of the present invention, performing intensity optimization on the Pareto front to generate multiple sets of intensity-optimized radiotherapy plans includes:

[0021] Use the selected target plan to construct the Pareto approximate frontier and the Pareto outer approximate surface Z out and inner approximate surface Z inThe inner approximate surface and the outer approximate surface are used to measure the upper limit and the lower limit of the Pareto frontier respectively;

[0022] The weight search algorithm is used to find the next set of optimal target weights w i So that Z in And Z out The Hausdorff distance d Haus (Z in , Z out ) is minimized;

[0023] When the weight search is completed, the target weights w i are used to perform intensity optimization on the Pareto frontier to generate multiple sets of intensity-optimized radiotherapy plans.

[0024] As an optional embodiment of the present application, in the dynamic adjustable radiotherapy multi-objective optimization method, the generating multiple sets of intensity-optimized radiotherapy plans comprises:

[0025] Step S1: generating n sets of anchor plans;

[0026] Step S2: screening target constraints, deleting constraints that meet the screening conditions, taking the remaining constraints as multi-objective optimization sub-targets, and re-executing step S1;

[0027] Step S3: generating a set of trade-off plans, each trade-off plan being an intensity-optimized radiotherapy plan with weights ;

[0028] Step S4: obtaining the next round of intensity-optimized weights according to the weight search method;

[0029] Step S5: performing intensity optimization using the search weights;

[0030] Step S6: repeatedly executing steps S4-S5 until a preset number of intensity-optimized radiotherapy plans is generated.

[0031] As an optional embodiment of the present application, in the dynamic adjustable radiotherapy multi-objective optimization method, the providing a navigation interface to guide the user to select a final radiotherapy plan comprises:

[0032] The navigation interface provides a slider for each constraint target for screening the corresponding plan, the position of the slider representing the satisfaction degree of the current constraint, and the path passed by the slider corresponding to a smooth curve connecting the worst point to the optimal point of the current target on the Pareto frontier;

[0033] When the user completes the final radiotherapy plan confirmation, the mapping relationship between the dose and the beam is calibrated.

[0034] As an optional embodiment of the present invention, in a dynamically adjustable multi-objective optimization method for radiotherapy of the present invention, generating radiotherapy machine parameters based on the final radiotherapy plan includes:

[0035] Generate machine parameters based on the DVH of the final radiotherapy plan, using slider-guided DVH constraints:

[0036]

[0037] in is the reference dose DVH, where the reference dose is the DVH of the organ selected for the user's plan, d is the optimized dose distribution, D(v,d) is the DVH function of dose d, v represents the DVH volume quantile, PTV represents the target volume, OAR represents the organ at risk, and F represents the machine parameters. Slider-guided DVH constraints are used to ensure that the newly generated dose results are non-inferior to the dose results observed during navigation.

[0038] The present invention also provides a dynamically adjustable radiotherapy multi-objective optimization system, comprising:

[0039] The multi-objective intensity optimization module receives the patient's clinical diagnosis and treatment information and constraint information, dynamically generates the Pareto frontier through the multi-objective optimization model, optimizes the intensity based on the Pareto frontier, and generates multiple sets of intensity-optimized radiotherapy plans;

[0040] The Pareto planning guidance module provides a navigation interface to guide users in selecting the final radiotherapy plan;

[0041] The deliverable plan generation module generates machine parameters for radiotherapy based on the final radiotherapy plan.

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] The present invention provides a dynamically adjustable multi-objective optimization method for radiotherapy. It uses the intensity-optimized Pareto front to generate an intensity-optimized radiotherapy plan. The plan results guide the user to weigh the plan in a navigation interface. After the final radiotherapy plan screening is completed, the DVH constraints guided by the slider generate the radiotherapy machine parameters to ensure that the newly generated dose is not inferior to the dose seen by navigation.

[0044] Therefore, the present invention provides a dynamically adjustable multi-objective optimization method for radiotherapy, which can generate multiple sets of intensity-optimized radiotherapy plans at one time within a custom constraint range. The DVH guidance method further improves the plan quality based on the guided plan, shortens the user's planning time while meeting the plan quality, and improves the planning efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1A flowchart of a dynamically adjustable multi-objective optimization method for radiotherapy according to an embodiment of the present invention. DETAILED DESCRIPTION

[0046] To make the purpose, technical solutions and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them.

[0047] Therefore, the following detailed description of the embodiments of the present invention is not intended to limit the scope of the claimed invention, but merely represents some embodiments of the present invention. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without creative effort shall fall within the scope of protection of the present invention.

[0048] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features and technical solutions therein may be combined with each other.

[0049] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings.

[0050] In the description of the present invention, it should be noted that the terms "upper" and "lower" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, or the orientations or positional relationships in which the inventive product is typically placed when in use, or the orientations or positional relationships commonly understood by those skilled in the art. Such terms are intended solely to facilitate the description of the present invention and simplify the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, be constructed, or operate in a specific orientation. Therefore, they should not be construed as limitations on the present invention. Furthermore, the terms "first" and "second" and the like are used solely for distinction and should not be construed as indicating or implying relative importance.

[0051] See also Figure 1 As shown, a dynamically adjustable multi-objective optimization method for radiotherapy of this embodiment includes:

[0052] Receive the patient's clinical diagnosis and treatment information and constraint information, and dynamically generate the Pareto frontier through a multi-objective optimization model;

[0053] Perform intensity optimization on the Pareto frontier and generate multiple sets of intensity-optimized radiotherapy plans;

[0054] A navigation interface is provided to guide the user to select the final radiotherapy plan and generate the machine parameters for radiotherapy based on the final radiotherapy plan.

[0055] This embodiment provides a dynamically adjustable multi-objective optimization method for radiotherapy. This method utilizes the intensity-optimized Pareto front to generate an intensity-optimized radiotherapy plan. The plan results guide the user through a navigation interface to weigh the plan. After the final radiotherapy plan is screened, the machine parameters for radiotherapy are generated using DVH constraints to ensure the quality of the generated plan.

[0056] Therefore, a dynamically adjustable radiotherapy multi-objective optimization method in this embodiment can generate multiple sets of intensity-optimized radiotherapy plans at one time within a custom constraint range. The DVH guidance method further improves the plan quality based on the guided plan, shortens the user's plan-making time while meeting the plan quality, and improves plan efficiency.

[0057] In a dynamically adjustable multi-objective optimization method for radiotherapy of this embodiment, the Pareto frontier is based on the patient's clinical diagnosis and treatment information and constraint information, and is determined by the initial multi-objective optimization model function.

[0058] The Pareto solution of the surface in space is formed, where Ψ is the radiation intensity, f i is a constraint function, n represents the number of constraints, and the constraint function includes a DVH function and an EUD function.

[0059] In radiotherapy plan optimization, obtaining the Pareto optimal solution for different constraints is a multi-objective optimization problem that requires balancing multiple clinical objectives (such as target coverage, organ-at-risk protection, and dose uniformity). In this embodiment, the patient's clinical diagnosis and treatment information and constraint information are included. The clinical diagnosis and treatment information includes the radiation field template, delineation information, CT scan, etc. The constraint information includes constraint parameters and trade-off parameters. Constraint parameters are constraints that must be met, and trade-off parameters are constraints that require user selection.

[0060] In a dynamically adjustable multi-objective optimization method for radiotherapy of this embodiment, performing intensity optimization on the Pareto front to generate multiple sets of intensity-optimized radiotherapy plans includes:

[0061] According to a set of predefined constraint weights w i ≥0,w1+…+w n =1, by optimizing the multi-objective optimization model function

[0062]

[0063] An optimal radiotherapy intensity solution is calculated, where the optimal radiotherapy intensity solution corresponds to a Pareto solution of the initial multi-objective optimization model function.

[0064] In a dynamically adjustable radiotherapy multi-objective optimization method of this embodiment, the optimal radiotherapy intensity solution corresponds to a Pareto solution of the initial multi-objective optimization model function, and the objective function value of the Pareto solution [f1; ...; f n ] is the Pareto vertex on the Pareto frontier, and the newly added Pareto vertex is used to perform the subsequent weight search process.

[0065] In a dynamically adjustable multi-objective optimization method for radiotherapy of this embodiment, performing intensity optimization on the Pareto front to generate multiple sets of intensity-optimized radiotherapy plans includes:

[0066] Calculate n groups of anchor plans, each anchor plan uses a weight w i =1,w j =∈,j≠i,∈>0, and calculate the maximum value of the different constraint objective functions in the anchor plan and the minimum value Where i represents the current constraint parameter index;

[0067] Determine whether it is satisfied If the judgment result is yes, the corresponding constraint parameter is deleted from the constraint parameter list, and the target plan screening is re-performed on the remaining constraint parameters; if the judgment result is no, a weight search is performed.

[0068] Furthermore, in a dynamically adjustable multi-objective optimization method for radiotherapy of this embodiment, performing intensity optimization on the Pareto front to generate multiple sets of intensity-optimized radiotherapy plans includes:

[0069] Use the selected target plan to construct the Pareto approximate frontier and the Pareto outer approximate surface Z out and inner approximate surface Z in , the inner approximation surface and the outer approximation surface are used to measure the upper and lower bounds of the Pareto front respectively;

[0070] The weight search algorithm used to find the next set of optimal target weights w i Make Z in and Z out The Hausdorff distance d Haus (Z in ,Z out ) minimum;

[0071] After completing the weight search, use the target weight w i Intensity optimization is performed on the Pareto frontier to generate multiple sets of intensity-optimized radiotherapy plans.

[0072] Specifically, in a dynamically adjustable multi-objective optimization method for radiotherapy of this embodiment, generating multiple sets of intensity-optimized radiotherapy plans includes:

[0073] Step S1: Generate n groups of anchor plans;

[0074] Step S2: Filter the target constraints, delete the constraints that meet the filtering conditions, use the remaining constraints as the multi-objective optimization sub-goals, and re-execute step S1;

[0075] Step S3: Generate a set of trade-off plans, each of which adopts a weight of intensity-optimized radiotherapy planning;

[0076] Step S4: Obtain the next round of strength optimization weights according to the weight search method;

[0077] Step S5: Optimize the strength using the search weight;

[0078] Step S6: Repeat steps S4-S5 until a preset number of intensity-optimized radiotherapy plans are generated.

[0079] In a dynamically adjustable radiotherapy multi-objective optimization method of this embodiment, providing a navigation interface to guide the user in selecting a final radiotherapy plan includes:

[0080] The navigation interface provides a slider for each constraint target to filter the corresponding plan. The position of the slider indicates the degree of satisfaction of the current constraint. The path of dragging the slider corresponds to the smooth curve connecting the worst point to the best point of the current target on the Pareto front.

[0081] After the user completes the final radiotherapy plan confirmation, the mapping relationship between dose and beam is calibrated.

[0082] Furthermore, in a dynamically adjustable multi-objective optimization method for radiotherapy of this embodiment, generating the radiotherapy machine parameters based on the final radiotherapy plan includes:

[0083] Generate machine parameters based on the DVH of the final radiotherapy plan, using slider-guided DVH constraints:

[0084]

[0085] in is the reference dose DVH, where the reference dose is the DVH of the organ selected for the user's plan, d is the optimized dose distribution, D(v,d) is the DVH function of dose d, v represents the DVH volume quantile, PTV represents the target volume, OAR represents the organ at risk, and F represents the machine parameters. Slider-guided DVH constraints are used to ensure that the newly generated dose results are non-inferior to the dose results observed during navigation.

[0086] This embodiment also provides a dynamically adjustable radiotherapy multi-objective optimization system, including:

[0087] The multi-objective intensity optimization module receives the patient's clinical diagnosis and treatment information and constraint information, dynamically generates the Pareto frontier through a multi-objective optimization model, performs intensity optimization based on the Pareto frontier, and generates multiple sets of intensity-optimized radiotherapy plans;

[0088] The Pareto planning guidance module provides a navigation interface to guide users in selecting the final radiotherapy plan;

[0089] The deliverable plan generation module generates machine parameters for radiotherapy based on the final radiotherapy plan.

[0090] In this embodiment, a dynamically adjustable multi-objective optimization system for radiotherapy is described. The multi-objective intensity optimization module generates an intensity-optimized radiotherapy plan using the intensity-optimized Pareto front. The plan results are used in a navigation interface of the Pareto plan guidance module to guide the user in weighing the plan. After the final radiotherapy plan screening is completed, the Pareto plan guidance module generates radiotherapy machine parameters using DVH constraints to ensure the quality of the generated plan.

[0091] Therefore, a dynamically adjustable radiotherapy multi-objective optimization system in this embodiment can generate multiple sets of intensity-optimized radiotherapy plans at one time within a custom constraint range. The DVH guidance method further improves the plan quality based on the guided plan, shortens the user's plan-making time while meeting the plan quality, and improves plan efficiency.

[0092] In this embodiment, a dynamically adjustable radiotherapy multi-objective optimization system is provided, wherein the optimization steps include:

[0093] Step 1: Import clinical diagnosis and treatment data, including radiation field templates, outline information, CT, etc.

[0094] Step 2: Set constraints and trade-off parameters. Constraints are constraints that must be met, and trade-offs are constraints that require user selection.

[0095] Step 3: Execute the multi-objective strength optimization module;

[0096] Step 4: Execute the Pareto planning guidance module;

[0097] Step 5: Execute the deliverable plan generation module;

[0098] Step 6: Confirm the plan information, otherwise go to Step 2.

[0099] This embodiment provides a dynamically adjustable multi-objective optimization system for radiotherapy. It uses an interactive method to select appropriate plans and a DVH constraint method to ensure the quality of deliverable plan generation. This method includes a multi-objective optimization module, a Pareto plan guidance module, and a deliverable plan generation module.

[0100] The Multi-Objective Intensity Optimization Module utilizes user-imported beam field, contouring, CT information, and constraint information to simultaneously generate multiple plans. The Multi-Objective Intensity Optimization Module includes an intensity optimization module, a plan target screening module, a weight search module, and a Pareto plan generation module.

[0101] The strength optimization module generates multiple sets of strength plans for fitting the Pareto frontier. The Pareto frontier is a multi-objective optimization problem.

[0102]

[0103] The Pareto solution of the surface in space is formed, where Ψ is the intensity, f i is the constraint function, n represents the number of constraints, including DVH function and EUD function.

[0104] The strength optimization described in this embodiment is based on a set of predefined constraint weights w i ≥0,w1+…+w n =1 optimization problem

[0105]

[0106] The optimal strength solution corresponds to a Pareto solution in (1). The optimization target value obtained from the strength optimization result is used to supplement the Pareto vertex on the Pareto frontier. The Pareto vertex is the objective function value of the current Pareto solution [f1; ...; f n ], the newly added Pareto vertex is used to execute the weight search module.

[0107] The plan target screening module first calculates n groups of anchor plans, each of which uses a weight of w i =1,w j =∈,j≠i,∈>0 strength plan, calculate the maximum value of different constraint objective functions in the anchor plan and the minimum value Where i represents the current constraint index. If The corresponding constraint is deleted from the constraint parameter list, and the remaining constraints are re-screened for planning objectives; otherwise, the weight search module is executed.

[0108] The weight search module uses the previously generated plan to construct the Pareto approximate frontier and the Pareto outer approximate surface Z out and inner approximate surface Z in The inner approximation surface and the outer approximation surface are used to measure the upper and lower bounds of the Pareto front respectively. The weight search algorithm used to find the next set of optimal target weights w i Make Z in and Z out The Hausdorff distance d Haus (Z in ,Z out ) is minimum. After completing the weight search, use the target weight w i Execute the strength optimization module.

[0109] The Pareto plan generation module generates multiple sets of strength optimization solutions according to the following steps:

[0110] Step S1: Generate n groups of anchor plans;

[0111] Step S2: Filter the target constraints. If there are certain constraints that meet the constraint conditions, delete them, use the remaining constraints as the sub-goals of the multi-objective optimization, and re-execute step 1;

[0112] Step S3: Generate a set of trade-off plans, each of which uses a weight of intensity plan;

[0113] Step S4: Obtain the next round of strength optimization weights according to the weight search method;

[0114] Step S5: Optimize the strength using the search weight;

[0115] Step S6: Repeat steps S4-S5 until a preset planned quantity is generated.

[0116] The Pareto Plan Guidance module provides an interactive plan interpolation method using multiple plans generated by the multi-objective optimization module. The slider guidance module within this module provides a navigation interface to guide the user in selecting an appropriate plan. This navigation interface provides a slider for selecting the corresponding plan for each constraint objective. The position of the slider indicates the degree of satisfaction of the current constraint, and the path of the slider corresponds to a smooth curve on the Pareto front connecting the worst point to the best point of the current objective. Once the user completes plan confirmation, the dose-beam mapping relationship is calibrated, and the DVH constraint module is executed.

[0117] The deliverable plan generation module directly generates the deliverable plan by using the plan information obtained by the Pareto plan guidance module. The slider-guided DVH constraint module in the module uses the user-guided plan DVH to perform the next step of direct machine parameter generation. The slider-guided DVH constraint is:

[0118]

[0119] wherein is the reference dose DVH, the reference dose is the user-selected plan organ DVH, d is the optimized dose distribution, D(v,d) is the DVH function of the dose d, v represents the DVH volume percentile, PTV represents the target region, OAR represents the organ at risk, and F represents the machine parameter. The slider-guided DVH constraint is used to ensure that the newly generated dose result is not worse than the dose result seen in the navigation process.

[0120] The embodiment also provides a computer readable storage medium storing a computer executable program, and the computer executable program is executed to implement the dynamic adjustable radiotherapy multi-objective optimization method.

[0121] The computer readable storage medium in the embodiment can include a data signal propagating in a baseband or as a part of a carrier wave, and the data signal carries the readable program code. The propagating data signal can adopt various forms, including but not limited to an electromagnetic signal, an optical signal or any suitable combination of the above. The computer readable storage medium can also be any readable medium other than the readable storage medium, which can send, propagate or transmit the program for use by or in combination with an instruction execution system, device or apparatus. The program code included in the computer readable storage medium can be transmitted by any suitable medium, including but not limited to wireless, wired, optical cable, RF and the like, or any suitable combination of the above.

[0122] The embodiment also provides an electronic device including a processor and a memory, and the memory is used to store a computer executable program, and the processor executes the computer program to implement the dynamic adjustable radiotherapy multi-objective optimization method.

[0123] The electronic device is in the form of a general computing device. The processor can be one or multiple and work cooperatively. The present application also does not exclude distributed processing, that is, the processor can be dispersed in different entity devices. The electronic device of the present application is not limited to a single entity, and can also be the sum of multiple entity devices.

[0124] The memory stores a computer executable program, typically a machine-readable code, which can be executed by the processor to enable the electronic device to perform the method of the present invention, or at least some of the steps in the method.

[0125] The memory includes a volatile memory, such as a random access memory unit (RAM) and / or a cache memory unit, and may also be a non-volatile memory, such as a read-only memory unit (ROM).

[0126] It should be understood that the electronic devices of the present invention may also include elements or components not shown in the above examples. For example, some electronic devices also include display units such as screens, and some electronic devices also include human-computer interaction elements such as buttons and keyboards. As long as the electronic device can execute a computer-readable program stored in its memory to implement the method of the present invention or at least some of the steps of the method, it can be considered an electronic device covered by the present invention.

[0127] Through the above description of the implementation mode, it is easy for those skilled in the art to understand that the present invention can be implemented by hardware capable of executing a specific computer program, such as the system of the present invention, and the electronic processing unit, server, client, mobile phone, control unit, processor, etc. contained in the system. The present invention can also be implemented by computer software that executes the method of the present invention, such as control software executed by a microprocessor, an electronic control unit, a client, a server, etc. However, it should be noted that the computer software that executes the method of the present invention is not limited to being executed by one or a specific hardware entity, and it can also be implemented in a distributed manner by unspecified specific hardware. For computer software, the software product can be stored in a computer-readable storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), or it can be distributed and stored on a network, as long as it enables an electronic device to execute the method according to the present invention.

[0128] The above embodiments are only used to illustrate the present invention and are not intended to limit the technical solutions described in the present invention. Although this specification has described the present invention in detail with reference to the above embodiments, the present invention is not limited to the above specific implementation methods. Therefore, any modification or equivalent replacement of the present invention; and all technical solutions and improvements thereof that do not depart from the spirit and scope of the invention are included in the scope of the claims of the present invention.

Claims

1. A dynamically adjustable multi-objective optimization method for radiotherapy, characterized in that: include: Receive the patient's clinical diagnosis and treatment information and constraint information, and dynamically generate the Pareto frontier through a multi-objective optimization model; Perform intensity optimization on the Pareto frontier and generate multiple sets of intensity-optimized radiotherapy plans; A navigation interface is provided to guide the user to select the final radiotherapy plan and generate the machine parameters for radiotherapy based on the final radiotherapy plan.

2. A dynamically adjustable multi-objective optimization method for radiotherapy according to claim 1, characterized in that: The Pareto frontier is based on the patient's clinical diagnosis and treatment information and constraint information, and is determined by the initial multi-objective optimization model function The Pareto solution of the surface in space is formed, where Ψ is the radiation intensity, f i is a constraint function, n represents the number of constraints, and the constraint function includes a DVH function and an EUD function.

3. The method for dynamically adjustable multi-objective optimization of radiotherapy according to claim 2, characterized in that: The intensity optimization for the Pareto frontier and generation of multiple sets of intensity-optimized radiotherapy plans include: According to a set of predefined constraint weights w i ≥0,w1+…+w n =1, by optimizing the multi-objective optimization model function An optimal radiotherapy intensity solution is calculated, where the optimal radiotherapy intensity solution corresponds to a Pareto solution of the initial multi-objective optimization model function.

4. A dynamically adjustable multi-objective optimization method for radiotherapy according to claim 3, characterized in that: The optimal radiotherapy intensity solution corresponds to a Pareto solution of the initial multi-objective optimization model function, and the objective function value of the Pareto solution [f1; ...; f n ] is the Pareto vertex on the Pareto front.

5. The method for dynamically adjustable multi-objective optimization of radiotherapy according to claim 3, characterized in that: The intensity optimization for the Pareto frontier and generation of multiple sets of intensity-optimized radiotherapy plans include: Calculate n groups of anchor plans, each anchor plan uses a weight w i =1,w j =∈, j≠i,∈>0, and calculate the maximum value f of the different constraint objective functions in the anchor plan. i max =max n f i n and the minimum value f i min =min n f i n , where i represents the current constraint parameter index; Determine whether f is satisfied i max =f i min =0, if the judgment result is yes, the corresponding constraint parameter is deleted from the constraint parameter list, and the target plan screening is re-performed for the remaining constraint parameters; if the judgment result is no, a weight search is performed.

6. The method for dynamically adjustable multi-objective optimization of radiotherapy according to claim 5, characterized in that: The intensity optimization for the Pareto frontier and generation of multiple sets of intensity-optimized radiotherapy plans include: Use the selected target plan to construct the Pareto approximate frontier and the Pareto outer approximate surface Z out and inner approximate surface Z in , the inner approximation surface and the outer approximation surface are used to measure the upper and lower bounds of the Pareto front respectively; The weight search algorithm used to find the next set of optimal target weights w i Make Z in and Z out The Hausdorff distance d Haus (Z in ,Z out ) minimum; After completing the weight search, use the target weight w i Intensity optimization is performed on the Pareto frontier to generate multiple sets of intensity-optimized radiotherapy plans.

7. The method for dynamically adjustable multi-objective optimization of radiotherapy according to claim 6, characterized in that: Generating multiple sets of intensity-optimized radiotherapy plans includes: Step S1: Generate n groups of anchor plans; Step S2: Filter the target constraints, delete the constraints that meet the filtering conditions, use the remaining constraints as the multi-objective optimization sub-goals, and re-execute step S1; Step S3: Generate a set of trade-off plans, each of which adopts a weight of intensity-optimized radiotherapy planning; Step S4: Obtain the next round of strength optimization weights according to the weight search method; Step S5: Optimize the strength using the search weight; Step S6: Repeat steps S4-S5 until a preset number of intensity-optimized radiotherapy plans are generated.

8. The method for dynamically adjustable multi-objective optimization of radiotherapy according to claim 1, characterized in that: Providing a navigation interface to guide the user to select a final radiotherapy plan includes: The navigation interface provides a slider for each constraint target to filter the corresponding plan. The position of the slider indicates the degree of satisfaction of the current constraint. The path of dragging the slider corresponds to the smooth curve connecting the worst point to the best point of the current target on the Pareto front. After the user completes the final radiotherapy plan confirmation, the mapping relationship between dose and beam is calibrated.

9. The method for dynamically adjustable multi-objective optimization of radiotherapy according to claim 1, characterized in that: The machine parameters for generating radiotherapy based on the final radiotherapy plan include: Generate machine parameters based on the DVH of the final radiotherapy plan, using slider-guided DVH constraints: in is the reference dose DVH, where the reference dose is the DVH of the organ selected for the user's plan, d is the optimized dose distribution, D(v,d) is the DVH function of dose d, v represents the DVH volume quantile, PTV represents the target volume, OAR represents the organ at risk, and F represents the machine parameters. Slider-guided DVH constraints are used to ensure that the newly generated dose results are non-inferior to the dose results observed during navigation.

10. A dynamically adjustable multi-objective optimization system for radiotherapy, characterized in that: include: The multi-objective intensity optimization module receives the patient's clinical diagnosis and treatment information and constraint information, dynamically generates the Pareto frontier through the multi-objective optimization model, optimizes the intensity based on the Pareto frontier, and generates multiple sets of intensity-optimized radiotherapy plans; The Pareto planning guidance module provides a navigation interface to guide users in selecting the final radiotherapy plan; The deliverable plan generation module generates machine parameters for radiotherapy based on the final radiotherapy plan.

Images