Multi-center radiotherapy plan generation method and device, electronic equipment and computer readable storage medium

Abstract

The invention provides a multi-center radiotherapy plan generation method and device, electronic equipment and a computer readable storage medium, and the method comprises the steps: receiving coordinates, radiation field parameters, positioning modes and unified dose constraints of a plurality of treatment centers, and receiving a medical image, a target region and an organ-at-risk contour of a patient; establishing a multi-center collaborative optimization model; according to the unified dose constraint optimization multi-center collaborative optimization model, generating a radiotherapy total plan including three-dimensional dose distribution; splitting the total plan into a plurality of sub-plans; and performing dose verification on the sub-plans, and outputting the sub-plans passing the dose verification as executable sub-plans to the treatment equipment. According to the method, the multi-center collaborative optimization model is optimized according to the unified dose constraint to generate the radiotherapy total plan containing the three-dimensional dose distribution, and the dose constraint does not need to be repeatedly set and the placement verification does not need to be implemented for multiple times in the plan generation process, so that the radiotherapy time is shortened, and the dose deviation risk is reduced. Besides, the plurality of treatment centers are uniformly optimized, so that the dose interference risk of each treatment center can be reduced, and the situation that cold and hot spots are formed due to non-uniform dose superposition and the safety of organs is affected is avoided.

Description

Technical Field

[0001] The present invention belongs to the technical field of medical radiotherapy, and specifically relates to a multi-center radiotherapy plan generation method, device, electronic equipment and computer-readable storage medium, which realizes global dose control, automated plan splitting and efficient execution through multi-center collaborative optimization. Background Art

[0002] In radiotherapy, multi-center treatment plans are required for cases with multiple or long target volumes. Common multi-center treatment plans mainly include manual split planning, step-by-step superposition optimization, and treatment range segmentation under mechanical constraints, among which:

[0003] Manually splitting plans requires physicists to design a separate treatment plan for each isocenter, setting target dose constraints and organ-at-risk protection parameters. This process requires repeated adjustments to field parameters (such as gantry angle and MLC sequence), taking hours or even days. For example, in the treatment of bilateral breast cancer, independent intensity-modulated radiation plans must be designed for the left and right target volumes before dose stacking is performed, resulting in complex and inefficient operations.

[0004] In conventional radiotherapy, step-by-step optimization involves first optimizing a single isocenter plan and then superimposing the dose contributions of other isocenters. For example, Monte Carlo algorithms can be used to optimize field parameters for different target volumes in stages. However, step-by-step optimization can easily lead to dose interference risks. For example, uneven dose superposition can create hot and cold spots, impacting the safety of organs at risk.

[0005] Mechanically constrained treatment range segmentation is limited by device hardware (e.g., gantry rotation angle ≤ 180°, treatment table movement accuracy ±1mm). A single treatment cannot cover extremely long target volumes or multiple spatially dispersed target volumes (e.g., total spinal irradiation requires three centers: intracranial, upper, and lower spine). Furthermore, multiple plans require multiple setup verifications, which can lead to setup errors (e.g., craniocaudal deviation ±3mm), significantly affecting dose distribution.

[0006] In summary, existing multicenter treatment technologies suffer from the following technical issues: 1. Inefficiency: Manual splitting requires repeated dose constraint setting, lacks global optimization algorithm support, and multiple treatment plan executions require multiple setup verifications, significantly increasing execution time and the risk of dose deviation. 2. Uneven dose distribution: Step-by-step optimization leads to overlapping hot and cold spots in the target area. 3. Inadequate protection of organs at risk: Cumulative doses can easily exceed target values when multiple plans are independently optimized. Summary of the Invention

[0007] In order to solve at least one of the above-mentioned technical problems existing in the existing multi-center radiotherapy technology, the first aspect of the present invention provides a multi-center radiotherapy plan generation method, the detailed technical solution of which is as follows:

[0008] A multicenter radiation therapy plan generation method, comprising:

[0009] Receive coordinates, field parameters, positioning methods, and unified dose constraints from multiple treatment centers, as well as medical images, target volumes, and outlines of organs at risk from patients;

[0010] Establish a multi-center collaborative optimization model;

[0011] A multi-center collaborative optimization model is optimized based on a unified dose constraint to generate a total radiotherapy plan including a three-dimensional dose distribution.

[0012] Split the overall plan into several sub-plans;

[0013] The sub-plan is dose verified and the sub-plan that passes the dose verification is output to the treatment device as an executable sub-plan.

[0014] In some embodiments, the field parameters include field angle, ray energy, field size, field weight, gantry angle, and MLC sequence;

[0015] Medical images include CT images, MRI images, and PET images;

[0016] The multi-center collaborative optimization model calculates the total dose distribution based on the following formula:

[0017]

[0018] Where n is the number of radiation fields generated by all treatment centers, w i is the weight of the i-th field, D i is the dose distribution of the i-th field;

[0019] Optimize the multi-center collaborative optimization model, the objective function is:

[0020]

[0021] Where m is the number of target areas, k j is the weight coefficient of the jth target area, D PTV,j is the dose of the jth target area, D prescribed，j is the dose limit of the jth target, p is the number of organs at risk, k o is the weight coefficient of the oth organ at risk, D OAR,o is the dose to the oth organ at risk, D tolorance,o is the dose limit of the jth organ at risk, λ1 is the L1 regularization term, n is the number of radiation fields, λ2 is the group regularization term, C is the number of treatment centers, and n l is the number of radiation fields in the lth treatment center.

[0022] In some embodiments, optimizing the multi-center collaborative optimization model includes:

[0023] The L-BFGS-B optimization engine was used to optimize the multi-center collaborative optimization model. During the optimization process, the radiation field parameters of each treatment center were dynamically adjusted through Pareto frontier analysis.

[0024] GPU-accelerated dose calculation updates the 3D dose distribution in real time.

[0025] In some embodiments, optimizing the multi-center collaborative optimization model includes automatically reducing the weight of the treatment center associated with the organ at risk when the cumulative dose of the organ at risk exceeds a preset threshold.

[0026] In some embodiments, splitting the overall plan into several sub-plans includes: splitting the overall plan into several sub-plans according to mechanical parameters of the equipment.

[0027] In some embodiments, dose verification of several sub-plans includes: verifying the sub-plan dose using a GPU-accelerated Monte Carlo algorithm, comparing the gamma pass rate of the planned dose with the actual delivered dose, and the executable sub-plan is the sub-plan with a gamma pass rate (3% / 3mm) exceeding 95%.

[0028] In some embodiments, the medical image is a multimodal image. After receiving the patient's medical image, target volume, and outline of organs at risk, the multicenter radiotherapy plan generation method further includes: fusing the multimodal images through rigid and / or non-rigid registration technology.

[0029] A second aspect of the present invention provides a multi-center radiotherapy plan generating device, comprising:

[0030] A receiving module is used to receive the coordinates, field parameters, positioning methods and unified dose constraints of multiple treatment centers, as well as the patient's medical images, target areas and outlines of organs at risk;

[0031] Modeling module, used to establish multi-center collaborative optimization model;

[0032] The plan generation module is used to optimize the multi-center collaborative optimization model according to the unified dose constraint and generate the radiotherapy master plan including the three-dimensional dose distribution;

[0033] Plan splitting module, used to split the overall plan into several sub-plans;

[0034] The verification module is used to perform dose verification on the sub-plan and output the sub-plan that passes the dose verification as an executable sub-plan to the treatment device.

[0035] A third aspect of the present invention provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any of the above-described methods for generating a multicenter radiotherapy plan when executing the program.

[0036] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the computer program implements any of the above-mentioned interactive radiotherapy plan generation methods.

[0037] This method optimizes a multi-center collaborative optimization model based on unified dose constraints to generate a master radiotherapy plan that includes a three-dimensional dose distribution. This eliminates the need for repeated dose constraint settings and setup verification during plan generation, thereby shortening radiotherapy treatment time and reducing the risk of dose deviation. Furthermore, unified optimization across multiple treatment centers reduces the risk of dose interference across centers, avoiding the formation of hotspots and cold spots caused by uneven dose addition, which can impact organ safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 Schematic diagram of a single or multiple target area with multiple treatment centers;

[0039] Figure 2 is a flowchart of an execution method of a multi-center radiotherapy plan generation method in an embodiment of the present invention;

[0040] Figure 3 is a flowchart of an execution method of a multi-center radiotherapy plan generation method in an embodiment of the present invention;

[0041] Figure 4 FIG. 4 is a block diagram of a multi-center radiotherapy plan generation apparatus according to an embodiment of the present invention. DETAILED DESCRIPTION

[0042] It should be pointed out that the contents of the following detailed description are exemplary and are intended to provide an indicative description of the contents of the present invention. It should be noted that all technical and scientific terms used in the present invention have the same meaning as commonly understood by ordinary technicians in the technical field to which the invention belongs.

[0043] The following will provide a clear and complete description of the system architecture in the embodiments of the present invention and the solutions in the prior art, in conjunction with the accompanying drawings of the embodiments of the present invention. It should be noted that the described embodiments are only for the purpose of explaining and illustrating the present invention, and are not exhaustive. Based on the embodiments provided by the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts are within the scope of protection of the present invention.

[0044] Example 1

[0045] like Figure 2 and Figure 3 As shown, a multi-center radiotherapy plan generation method of the present invention includes the following steps:

[0046] S1. Receive the coordinates, field parameters, positioning methods and unified dose constraints of multiple treatment centers, as well as the patient's medical images, target areas and outlines of organs at risk.

[0047] S2. Establish a multi-center collaborative optimization model.

[0048] S3. Optimize the multi-center collaborative optimization model based on a unified dose constraint to generate a total radiotherapy plan including three-dimensional dose distribution.

[0049] S4. Split the overall plan into several sub-plans.

[0050] S5. Perform dose verification on the sub-plan, and output the sub-plan that passes the dose verification as an executable sub-plan to the treatment device.

[0051] The positioning method of the treatment center in step S1 may include, for example, bone positioning, gold marker positioning, soft tissue positioning, etc. The dose constraint is the dose limit of the target volume (PTV) and the organ at risk.

[0052] For example, in whole-spine irradiation, the dose constraint is set as: PTV D95 ≥60 Gy, spinal cord D max ≤35 Gy. That is, at least 95% of the PTV volume receives a radiation dose of no less than 60 Gy, and the dose received by any point in the spinal cord must not exceed 35 Gy.

[0053] For example, in the treatment of nasopharyngeal carcinoma with primary invasion of the skull base and bilateral cervical lymph node metastasis, both the intracranial and cervical target volumes need to be treated simultaneously. Dose limits are set for the target volume and organs at risk. Dose limit rings are set for each target volume, with distances of 0.2 cm, 0.5 cm, and 0.9 cm, respectively, and a uniform inner diameter of 0.2 cm. Gradually decreasing dose limits are set to control the rate of dose drop.

[0054] As can be seen, the multicenter radiotherapy plan generation method of the present invention optimizes the multicenter collaborative optimization model based on unified dose constraints to generate a master radiotherapy plan that includes a three-dimensional dose distribution. This eliminates the need for repeated dose constraint setting and multiple setup verifications during the plan generation process, thereby shortening radiotherapy treatment time and reducing the risk of dose deviation. Furthermore, unified optimization across multiple treatment centers reduces the risk of dose interference across treatment centers and avoids the formation of hot and cold spots due to uneven dose superposition, which can affect organ safety.

[0055] Example 2

[0056] like Figure 2 and Figure 3 As shown, a multi-center radiotherapy plan generation method of the present invention includes the following steps:

[0057] S1. Receive the coordinates, field parameters, positioning methods and unified dose constraints of multiple treatment centers, as well as the patient's medical images, target areas and outlines of organs at risk.

[0058] S2. Establish a multi-center collaborative optimization model.

[0059] S3. Optimize the multi-center collaborative optimization model based on a unified dose constraint to generate a total radiotherapy plan including three-dimensional dose distribution.

[0060] S4. Split the overall plan into several sub-plans.

[0061] S5. Perform dose verification on the sub-plan, and output the sub-plan that passes the dose verification as an executable sub-plan to the treatment device.

[0062] The difference between this embodiment and embodiment 1 is that:

[0063] In step S1 above, the radiation field parameters include radiation field angle, radiation energy, radiation field size (e.g., length and width), and MLC sequence. The patient's medical image can be one or more medical images acquired by various existing medical imaging devices, such as CT images, MRI images, and PET images. CT images focus on displaying anatomical structures, MRI images focus on displaying the boundaries of the target volume (PTV), and PET images focus on displaying metabolically active areas. Fusion of these three images can further improve the accuracy of target delineation.

[0064] Therefore, when the received medical image of the patient is a multimodal image including two or more of CT images, MRI images, and PET images, the multimodal images can be fused through rigid and / or non-rigid registration technology.

[0065] Before implementing radiotherapy, doctors or physicists generally outline the target area and organs at risk on medical images. In addition, they may also draw one or more customized auxiliary radiotherapy structures on the medical image, such as the dose drop zone near the target area.

[0066] The multi-center collaborative optimization model in step S2 calculates the total dose distribution based on the following formula:

[0067]

[0068] Where n is the number of radiation fields generated by all treatment centers, w iis the dose weight of the target area corresponding to the i-th field, D i is the dose distribution of the ith field.

[0069] The objective function of the optimized multi-center collaborative optimization model in step S3 is:

[0070]

[0071] Where m is the number of target areas, k j is the weight coefficient of the jth target area, D PTV,j is the dose of the jth target area, D prescribed，j is the dose limit of the jth target, p is the number of organs at risk, k o is the weight coefficient of the oth organ at risk, D OAR,o is the dose to the oth organ at risk, D tolorance,o is the dose limit of the jth organ at risk, λ1 is the L1 regularization term, n is the number of radiation fields, λ2 is the group regularization term, C is the number of treatment centers, and n l is the number of radiation fields in the lth treatment center.

[0072] In other words, the objective function is to minimize the sum of the target dose excess and the organ-at-risk dose excess. The L1 regularization term is used to compress the weights of low-contribution fields to zero, thereby automatically eliminating redundant fields. Low-contribution fields are, for example, fields with a dose weight less than 0.01. The group regularization term is used to reduce the number of treatment centers.

[0073] The optimization of the multi-center collaborative optimization model in step S3 specifically includes:

[0074] The L-BFGS-B optimization engine was used to optimize the multi-center collaborative optimization model. During the optimization process, the radiation field parameters (radiation field angle, radiation energy, and radiation field size) of each treatment center were dynamically adjusted through Pareto frontier analysis.

[0075] The three-dimensional dose distribution is updated in real time through GPU-accelerated calculations.

[0076] Specifically, the L-BFGS-B optimization engine combines L-BFGS (Limited Memory BFGS) with boundary constraint processing technology. It offers numerous advantages, including low memory usage, support for explicit boundary constraints, and rapid convergence. This reduces iterations and allows for rapid optimization of multi-center collaborative optimization models. Pareto front analysis is a mathematical tool for multi-objective optimization problems that can find the optimal balance between multiple conflicting objectives. In the dynamic adjustment of radiotherapy field parameters (such as field angle, radiation energy, and field size), it can balance multiple conflicting objectives in field parameter optimization. Adjustment requires balancing multiple clinical objectives. For example, the goal of tumor control is to maximize dose coverage and uniformity within the tumor target volume; the goal of organ-at-risk protection is to minimize the dose to organs at risk (such as the heart and spinal cord); and the goal of dose distribution conformality is to optimize the match between the field shape and the tumor geometry. These objectives are often conflicting (e.g., increasing the tumor dose may increase the risk of organ-at-risk damage), and Pareto front analysis is needed to find the optimal compromise.

[0077] Compared with CPU calculations, GPU accelerated computing can increase the speed of Monte Carlo dose simulation by 50-200 times, thereby supporting real-time dynamic adjustment of radiotherapy plans.

[0078] In order to further improve the safety of organs at risk, in this embodiment, the optimization multi-center collaborative optimization model in step S3 further includes:

[0079] When the cumulative dose of an organ at risk exceeds a preset threshold, the weight of the treatment center related to the organ at risk is automatically reduced, that is, the radiation dose of the organ at risk is reduced.

[0080] Example 3

[0081] like Figure 2 and Figure 3 As shown, a multi-center radiotherapy plan generation method of the present invention includes the following steps:

[0082] S1. Receive the coordinates, field parameters, positioning methods and unified dose constraints of multiple treatment centers, as well as the patient's medical images, target areas and outlines of organs at risk.

[0083] S2. Establish a multi-center collaborative optimization model.

[0084] S3. Optimize the multi-center collaborative optimization model based on a unified dose constraint to generate a total radiotherapy plan including three-dimensional dose distribution.

[0085] S4. Split the overall plan into several sub-plans.

[0086] S5. Perform dose verification on the sub-plan, and output the sub-plan that passes the dose verification as an executable sub-plan to the treatment device.

[0087] The difference between this embodiment and embodiment 1 is that:

[0088] Step S4 divides the overall plan into several sub-plans, including:

[0089] The overall plan is divided into several sub-plans according to the mechanical parameters of the equipment.

[0090] For example, the total plan for full central spinal irradiation is divided into several three-sub-plans based on the movement range of the treatment bed (±40 cm), and the three sub-plans cover the cervical spine, thoracic spine, and lumbar spine respectively.

[0091] The dose verification of the sub-plan in step S5 includes:

[0092] A GPU-accelerated Monte Carlo algorithm was used to verify the sub-plan doses. The gamma pass rates of the planned doses and the actual delivered doses were compared, and sub-plans with a gamma pass rate exceeding 95% were considered executable sub-plans.

[0093] In this embodiment, in step S5, before outputting the sub-plan that has passed the dose verification to the treatment device as an executable sub-plan, the step further includes: optimizing the execution order of the executable sub-plan.

[0094] Optional optimization methods include:

[0095] Mechanical motion optimization: The execution order of sub-plans is restricted according to the gantry angle to avoid the cumulative error caused by frequent movement of the treatment table (for example, the cranial and caudal direction error is reduced from ±3mm to ±1mm);

[0096] A path optimization algorithm is used to automatically generate the shortest path for the treatment bed to improve the efficiency and accuracy of multiple treatment plan execution.

[0097] After the dose-verified sub-plan is exported to the treatment device as an executable sub-plan, formal radiotherapy can be carried out on the patient according to the execution order of the executable sub-plan. The radiotherapy process is as follows:

[0098] Secure the patient to the treatment bed. Automatically position the patient according to the positioning method for Sub-Plan 1, and then execute Sub-Plan 1 using the pre-set tracking method. After Sub-Plan 1 is completed, the system automatically moves the patient to the positioning position for Sub-Plan 2, and executes Sub-Plan 2 using the pre-set tracking method. Continue following these steps to execute all sub-plans.

[0099] To enable those skilled in the art to more clearly understand the execution process of the multi-center radiotherapy plan generation method of the present invention, the execution process of the multi-center radiotherapy plan generation method of the present invention will be described in more detail below through Examples 4 and 5.

[0100] Example 4

[0101] Case characteristics: Nasopharyngeal carcinoma, primary lesion invades skull base, bilateral cervical lymph node metastasis, requiring simultaneous treatment of intracranial target area and cervical target area.

[0102] During the data acquisition (input) phase, submillimeter registration is achieved through multimodal image fusion (such as 1-mm slice-thickness CT, T1-weighted / T2-weighted MRI, and PET-CT). The operator delineates the target volume (GTV / CTV / PTV) and organs at risk on the computer system and evaluates the delineation results. MRI / PET-CT is used to correct complex boundaries such as the skull base invasion area.

[0103] Bone tracking is used for positioning in the skull area, and soft tissue tracking is used for positioning of lymph node metastases in the neck. The positioning center, positioning mode and different treatment node modes are set respectively.

[0104] Set dose limits for the target area and organs at risk, and set dose limit rings for each target area with distances of 0.2 cm, 0.5 cm, and 0.9 cm, respectively. The inner diameter of the ring is uniformly 0.2 cm, and gradually decreasing dose limits are set for them to control the dose drop rate.

[0105] The treatment plan is optimized to obtain a total radiotherapy plan, and the total radiotherapy plan is divided into several sub-plans.

[0106] After treatment evaluation, the total radiotherapy plan is split into three sub-plans based on the established positioning center and the remaining radiation fields. A path optimization algorithm (such as a genetic algorithm) is then used to plan the movement path of the treatment couch and determine the execution order of the three sub-plans: Sub-Plan 1, Sub-Plan 2, and Sub-Plan 3.

[0107] Sub-plan 1, sub-plan 2, and sub-plan 3 are sent to the treatment device for implementation. The operator only needs to initially position the patient for sub-plan 1 and perform treatment for sub-plan 1. The system then automatically positions the patient for sub-plan 2 and performs treatment for sub-plan 2. Subsequently, the system automatically positions the patient for sub-plan 3 and performs treatment for sub-plan 3.

[0108] Example 5

[0109] The patient required full-spine irradiation, targeting the cervical, thoracic, and lumbar spine, a total length exceeding the conventional single-center treatment range. Traditional approaches require three treatment centers (intracranial, upper spine, and lower spine), with multiple treatment plans and individual treatments resulting in low treatment efficiency. Sequential treatments and multiple positioning procedures can lead to cumulative errors (±2 mm). The implementation process of this embodiment is as follows.

[0110] Data input:

[0111] Receive the coordinates and radiation field parameters of the three treatment centers, some of which are:

[0112] The initial values of the field weights are: 0.2 for treatment center 1, 0.2 for treatment center 2, 0.2 for treatment center 3, 0.2 for treatment center 4, and 0.2 for treatment center 5.

[0113] The patient's CT / MRI fusion images are imported to outline the target area (cervical spine, thoracic spine, lumbar spine) and organs at risk (spinal cord, lungs, kidneys).

[0114] Multi-center collaborative optimization:

[0115] A global optimization model is established, and the objective function is the same as in Example 2 above.

[0116] Dose constraints: At least 95% of the target volume receives a radiation dose of no less than 60 Gy, and the dose received by any point in the spinal cord must not exceed 35 Gy.

[0117] L1 regularization term (λ1=0.1): Automatically compresses most of the field weights in the treatment center to 0 (dose contribution < 0.01), reducing redundancy and increasing treatment efficiency.

[0118] Group regularization term (λ2 = 0.5): Reduce the number of fields in treatment center 3 from 5 to 3 to simplify the execution process.

[0119] Plan splitting and verification:

[0120] According to the movement range of the treatment bed (±10cm), the overall plan is divided into three sub-plans:

[0121] Sub-plan 1: Cervical spine (center 2),

[0122] Sub-plan 2: Thoracic spine (center 4),

[0123] Sub-plan 3: Lumbar spine (center 5).

[0124] GPU-accelerated Monte Carlo validation:

[0125] The gamma pass rate (3% / 3mm) of sub-plan 1 was 97.2%, that of sub-plan 2 was 96.8%, and that of sub-plan 3 was 98.1%, all of which were greater than 95%.

[0126] Sub-plan 1, sub-plan 2, and sub-plan 3 are sent to the treatment device for implementation. The operator only needs to initially position the patient for sub-plan 1 and perform treatment for sub-plan 1. The system then automatically positions the patient for sub-plan 2 and performs treatment for sub-plan 2. Subsequently, the system automatically positions the patient for sub-plan 3 and performs treatment for sub-plan 3.

[0127] Technical Results: Single-session optimization time was shortened from the traditional 4 hours to 40 minutes (GPU acceleration), the cumulative spinal cord dose was reduced from the traditional 32 Gy to 28.5 Gy (below the limit), and positioning errors were reduced by 50% (in a single treatment). Treatment plan execution time was reduced from 150 minutes to 90 minutes due to a reduction in the number of treatment centers.

[0128] Example 6

[0129] like Figure 4 As shown, a multi-center radiotherapy plan generating device of the present invention comprises:

[0130] Receiving module 1, used to receive the coordinates, field parameters, positioning methods and unified dose constraints of multiple treatment centers, as well as medical images, target areas and contours of organs at risk of patients;

[0131] Modeling module 2, used to establish a multi-center collaborative optimization model;

[0132] Plan generation module 3, used to optimize the multi-center collaborative optimization model according to the unified dose constraint and generate a total radiotherapy plan including three-dimensional dose distribution;

[0133] Plan splitting module 4 is used to split the overall plan into several sub-plans;

[0134] The verification module 5 is used to perform dose verification on the sub-plan and output the sub-plan that passes the dose verification as an executable sub-plan to the treatment device.

[0135] Since the processing procedures of the functional modules of the multi-center radiotherapy plan generation apparatus of the embodiment are consistent with the processing procedures of the multi-center radiotherapy plan generation methods provided in the aforementioned method embodiments, the detailed processing procedures of the functional modules of the interactive radiotherapy plan generation apparatus will not be repeated in this embodiment. The relevant contents in the aforementioned method embodiments may be directly referred to.

[0136] Example 7

[0137] An electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor and the memory are connected, for example, via a bus. When the processor executes the program, the multicenter radiation therapy plan generation method according to any of the above embodiments is implemented.

[0138] Example 8

[0139] A computer-readable storage medium is provided. The computer-readable storage medium stores a computer program. When the program is executed by a processor, the multi-center radiotherapy plan generation method provided in the above method embodiment is implemented.

[0140] The present invention has been described above in sufficient detail with certain particularities. Those skilled in the art will appreciate that the descriptions in the embodiments are merely illustrative, and that all modifications that do not depart from the true spirit and scope of the invention are intended to be within the scope of protection of the present invention. The scope of protection claimed in the present invention is defined by the appended claims, not by the foregoing description of the embodiments.

Claims

1. A method for generating a multi-center radiotherapy plan, characterized in that: The multi-center radiotherapy plan generation method comprises: Receive coordinates, field parameters, positioning methods, and unified dose constraints from multiple treatment centers, as well as medical images, target volumes, and outlines of organs at risk from patients; Establish a multi-center collaborative optimization model; A multi-center collaborative optimization model is optimized based on a unified dose constraint to generate a total radiotherapy plan including a three-dimensional dose distribution. Split the overall plan into several sub-plans; The sub-plan is dose verified and the sub-plan that passes the dose verification is output to the treatment device as an executable sub-plan.

2. The multicenter radiotherapy plan generation method according to claim 1, wherein: The field parameters include field angle, ray energy, field size, field weight, gantry angle and MLC sequence; The medical images include CT images, MRI images and PET images; The multi-center collaborative optimization model calculates the total dose distribution based on the following formula: Where n is the number of radiation fields generated by all treatment centers, w i is the dose weight of the target area corresponding to the i-th field, D i is the dose distribution of the i-th field; Optimize the multi-center collaborative optimization model, the objective function is: Where m is the number of target areas, k j is the weight coefficient of the jth target area, D PTV,j is the dose of the jth target area, D prescribed，j is the dose limit of the jth target, p is the number of organs at risk, k o is the weight coefficient of the oth organ at risk, D OAR,o is the dose to the oth organ at risk, D tolorance,o is the dose limit of the jth organ at risk, λ1 is the L1 regularization term, n is the number of radiation fields, λ2 is the group regularization term, C is the number of treatment centers, and n l is the number of radiation fields in the lth treatment center.

3. The multicenter radiotherapy plan generation method according to claim 2, wherein: The optimization multi-center collaborative optimization model includes: The L-BFGS-B optimization engine was used to optimize the multi-center collaborative optimization model. During the optimization process, the radiation field parameters of each treatment center were dynamically adjusted through Pareto frontier analysis. GPU-accelerated dose calculation updates the 3D dose distribution in real time.

4. The multicenter radiotherapy plan generation method according to claim 2, wherein: The establishing of the multi-center collaborative optimization model further includes: when the cumulative dose of the endangered organ exceeds a preset threshold, automatically reducing the weight of the treatment center related to the endangered organ.

5. The multi-center radiotherapy plan generation method according to claim 1, wherein: The optimization multi-center collaborative optimization model includes: The overall plan is divided into several sub-plans according to the mechanical parameters of the equipment.

6. The multi-center radiotherapy plan generation method according to claim 1, wherein: The performing of dose verification on the plurality of sub-plans includes: The GPU-accelerated Monte Carlo algorithm was used to verify the sub-plan doses, and the gamma pass rates of the planned doses and the actual delivered doses were compared. The executable sub-plans were those with a gamma pass rate (3% / 3mm) exceeding 95%.

7. The multicenter radiotherapy plan generation method according to claim 1, wherein: The medical image is a multimodal image. After receiving the medical image of the patient, the target volume, and the outline of the organ at risk, the multicenter radiotherapy plan generation method further includes: Multimodal images are fused via rigid and / or non-rigid registration techniques.

8. A multi-center radiotherapy plan generating device, characterized in that: The multi-center radiotherapy plan generating device comprises: A receiving module is used to receive the coordinates, field parameters, positioning methods and unified dose constraints of multiple treatment centers, as well as the patient's medical images, target areas and outlines of organs at risk; Modeling module, used to establish multi-center collaborative optimization model; The plan generation module is used to optimize the multi-center collaborative optimization model according to the unified dose constraint and generate the radiotherapy master plan including the three-dimensional dose distribution; A plan splitting module, used for splitting the overall plan into several sub-plans; The verification module is used to perform dose verification on the sub-plan and output the sub-plan that passes the dose verification as an executable sub-plan to the treatment device.

9. An electronic device, characterized in that: The electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the multicenter radiotherapy plan generation method according to any one of claims 1 to 7 when executing the program.

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

Images