Proton radiotherapy plan robust optimization device and method based on adaptive scenario

Abstract

The invention discloses a proton radiotherapy plan robust optimization device and method based on adaptive scenario, and relates to the field of medical science and technology. The device is used for generating N robust scene images based on a radiotherapy plan of a target object, calculating a dose distribution diagram of each robust scene image through a dose calculation engine to obtain N dose distribution diagrams corresponding to the N robust scene images; determining a first dose distribution diagram and a second dose distribution diagram according to the N dose distribution diagrams; and the adjusting unit is used for adjusting the radiotherapy plan according to the first dose distribution diagram and the second dose distribution diagram. The technical problems that in the prior art, in order to cope with the positions, shapes and densities of tumor target regions and surrounding normal tissues, the positions, shapes and densities may change due to body position changes and physiological states of patients or changes of tumors, and a conventional robust optimization method is long in time consumption and poor in effect are solved.

Description

Technical Field

[0001] This application relates to the field of medical technology. Specifically, it relates to a proton radiotherapy plan robust optimization device and method based on adaptive scenario. Background Art

[0002] In radiotherapy, the positions, shapes, and densities of tumor target areas and surrounding normal tissues may change due to patient body position changes, physiological states, or changes in the tumors themselves. These changes affect the propagation path and dose distribution of radiation, which may lead to reduced treatment effectiveness or damage to normal tissues. To address these uncertainties, radiotherapy uses robust optimization methods. For example, by adding an outer expansion boundary to the tumor, possible deviations and changes are incorporated into the treatment plan formulation process. This ensures that the treatment plan can effectively cover the tumor area under various possible actual situations while maximizing the protection of normal tissues.

[0003] However, using the method of adding an outer expansion boundary to the tumor to improve the robustness of the radiotherapy plan easily causes normal tissues to receive excessive irradiation, and dose calculations also need to be performed for the outer expansion boundary, resulting in the technical problems of long optimization time and poor effect for proton radiotherapy plans.

[0004] To address the above problems, no effective solutions have been proposed yet. Summary of the Invention

[0005] This application provides a proton radiotherapy plan robust optimization device and method based on adaptive scenario to at least solve the technical problems in the prior art that, in order to cope with the changes in the positions, shapes, and densities of tumor target areas and surrounding normal tissues due to patient body position changes, physiological states, or changes in the tumors themselves, conventional robust optimization methods are time-consuming and have poor effects.

[0006] According to one aspect of the present application, a proton radiotherapy plan robust optimization device based on adaptive sceneization is provided, including: a first processing unit configured to generate N robust scene images based on the radiotherapy plan of a target object, wherein the N robust scene images are used to simulate the change information of M regions of interest of the target object, and both N and M are integers greater than 1; a second processing unit configured to calculate the dose distribution map of each robust scene image through a dose calculation engine to obtain N dose distribution maps corresponding to the N robust scene images; a determination unit configured to determine a first dose distribution map and a second dose distribution map according to the N dose distribution maps, wherein the first dose distribution map is used to record the maximum dose value of the N dose distribution maps at each grid point, and the second dose distribution map is used to record the minimum dose value of the N dose distribution maps at each grid point, and each grid point corresponds to a beam spot in radiotherapy; an adjustment unit configured to adjust the radiotherapy plan according to the first dose distribution map and the second dose distribution map.

[0007] Optionally, the adjustment unit includes: a first determination subunit configured to determine a first sequence number matrix according to the sequence numbers of the robust scene images corresponding to the dose values of each grid point in the first dose distribution map; a second determination subunit configured to determine a second sequence number matrix according to the sequence numbers of the robust scene images corresponding to the dose values of each grid point in the second dose distribution map; an adjustment subunit configured to adjust the radiotherapy plan according to the first dose distribution map, the second dose distribution map, the first sequence number matrix, and the second sequence number matrix.

[0008] Optionally, the adjustment subunit includes: a first determination module configured to determine the maximum dose distribution matrix of each region of interest based on the first dose distribution map; and determine the minimum dose distribution matrix of each region of interest based on the second dose distribution map; a first processing module configured to use the sub-matrix corresponding to each region of interest in the first sequence number matrix as the first sub-matrix of the region of interest; a second processing module configured to use the sub-matrix corresponding to each region of interest in the second sequence number matrix as the second sub-matrix of the region of interest; an adjustment module configured to adjust the plan content regarding each region of interest in the radiotherapy plan according to the minimum dose distribution matrix, the maximum dose distribution matrix, the first sub-matrix, and the second sub-matrix of each region of interest.

[0009] Optionally, the adjustment module includes: a detection sub-module configured to detect N dose distribution sub-maps corresponding to each region of interest in the N dose distribution maps; a determination sub-module configured to determine the N dose volume histograms of the region of interest according to the N dose distribution sub-maps corresponding to the region of interest; a first adjustment sub-module configured to adjust the plan content regarding each region of interest in the radiotherapy plan according to the N dose volume histograms, the minimum dose distribution matrix, the maximum dose distribution matrix, the first sub-matrix, and the second sub-matrix of each region of interest.

[0010] Optionally, the adjustment module includes: a second adjustment sub-module, configured to adjust the plan content of the radiotherapy plan for the i-th region of interest according to the maximum dose distribution matrix and the second sub-matrix of the i-th region of interest when the constraint condition set for the i-th region of interest is to reduce the dose, where i is an integer greater than or equal to 1; a third adjustment sub-module, configured to adjust the plan content of the radiotherapy plan for the j-th region of interest according to the minimum dose distribution matrix and the first sub-matrix of the j-th region of interest when the constraint condition set for the j-th region of interest is to increase the dose, where j is an integer greater than or equal to 1.

[0011] Optionally, the second adjustment sub-module includes: a first processing sub-module, configured to determine the dose constraint matrix of the i-th region of interest according to the maximum dose distribution matrix and the constraint condition of the i-th region of interest; a first calculation sub-module, configured to calculate the matrix product of the dose constraint matrix of the i-th region of interest and the second sub-matrix of the i-th region of interest to obtain the iterative constraint matrix of the i-th region of interest; a second processing sub-module, configured to adjust the plan content of the radiotherapy plan for the i-th region of interest according to the iterative constraint matrix of the i-th region of interest.

[0012] Optionally, the second processing sub-module includes: a third processing sub-module, configured to determine the gradient matrix of the i-th region of interest according to the iterative constraint matrix of the i-th region of interest; a second calculation sub-module, configured to calculate the matrix product of the gradient matrix of the i-th region of interest and the first sub-matrix of the i-th region of interest to obtain the iterative gradient matrix of the i-th region of interest; a fourth processing sub-module, configured to adjust the plan content of the radiotherapy plan for the i-th region of interest according to the iterative gradient matrix of the i-th region of interest.

[0013] Optionally, the second processing unit includes: a first processing subunit, configured to calculate an initial dose matrix for each robust scenario image based on a dose calculation engine, obtaining N initial dose matrices corresponding to the N robust scenario images; a second processing subunit, configured to, for each region of interest of the target object, sample the N initial dose matrices according to the dose constraint conditions set for each region of interest, obtaining the dose information corresponding to each region of interest in each initial dose matrix; a third processing subunit, configured to determine N intermediate dose matrices according to the dose information corresponding to each region of interest in each initial dose matrix, where the N intermediate dose matrices correspond one-to-one to the N robust scenario images, and each intermediate dose matrix includes the dose information corresponding to M regions of interest in one initial dose matrix; a fourth processing subunit, configured to determine N dose distribution maps corresponding to the N robust scenario images according to the N intermediate dose matrices and the weights set for each beam spot.

[0014] Optionally, the fourth processing subunit includes: a resampling module, configured to resample the N intermediate dose matrices respectively according to the parameter information of the radiation particles, obtaining N target dose matrices corresponding one-to-one to the N intermediate dose matrices; a generation module, configured to generate a dose distribution map corresponding to the target dose matrix according to each target dose matrix and the weights set for each beam spot, obtaining N dose distribution maps corresponding to the N target dose matrices.

[0015] Optionally, the proton radiotherapy plan robust optimization device based on adaptive scenario also includes: a sampling correction unit, configured to determine sampling correction information through a dose calculation engine according to the radiotherapy plan of the target object and the weights set for each beam spot; a dose adjustment unit, configured to adjust the dose information of the N dose distribution maps according to the sampling correction information.

[0016] According to another aspect of the present application, there is also provided a proton radiotherapy plan robust optimization method based on adaptive scenario, including: generating N robust scenario images based on the radiotherapy plan of the target object, where the N robust scenario images are used to simulate the change information of M regions of interest of the target object, and both N and M are integers greater than 1; calculating the dose distribution map of each robust scenario image through a dose calculation engine, obtaining N dose distribution maps corresponding to the N robust scenario images; determining a first dose distribution map and a second dose distribution map according to the N dose distribution maps, where the first dose distribution map is used to record the maximum dose value of the N dose distribution maps at each grid point, and the second dose distribution map is used to record the minimum dose value of the N dose distribution maps at each grid point, and each grid point corresponds to a beam spot in radiotherapy; adjusting the radiotherapy plan according to the first dose distribution map and the second dose distribution map.

[0017] As can be seen from the above, by generating N robust scenario images for the target object, the present application effectively simulates the changes of the tumor target area and its surrounding tissues under different conditions. Compared with the method of simply using a fixed external expansion boundary in the prior art, the present application can more accurately predict the influence of dose distribution caused by body position changes, physiological states or tumor changes. By calculating the dose distribution of each robust scenario through a dose calculation engine, the N dose distribution maps obtained cover all possible dose distribution situations, which provides a comprehensive data basis for subsequent robust optimization.

[0018] Secondly, the generation of the first dose distribution map and the second dose distribution map respectively records the maximum and minimum dose values of the target area under various scenarios. This processing method can intuitively reflect the uncertainty range of the dose distribution. Based on these two maps, the adjustment of the radiotherapy plan can be targeted to reduce the overlap between the external expansion boundary of the tumor and normal tissues, avoid excessive irradiation of normal tissues, and ensure full coverage of the tumor area.

[0019] In addition, during the iterative optimization process of the present application, through precise calculation and constraint adjustment, fast and effective dose optimization is achieved, overcoming the problems of slow optimization speed and poor effect in the prior art. The processes of iterative dose and iterative constraints ensure that adjustments can be made according to the latest dose distribution information and constraint conditions in each optimization cycle, so as to achieve the optimal robust plan within limited calculation time. In addition, the parallel processing ability of the algorithm further shortens the optimization time and improves the efficiency.

[0020] In summary, the present application not only solves the technical problems of long time consumption and poor effect of the robust optimization method in the prior art, but also can more accurately and flexibly respond to the changes of the tumor target area and its surrounding tissues, providing a safer and more effective dose distribution solution for radiotherapy. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The schematic embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation to the present application. In the drawings:

[0022] Figure 1 is a schematic diagram of a robust optimization device for proton radiotherapy plan based on adaptive scenario according to an embodiment of the present application;

[0023] Figure 2 is a schematic diagram of an optional N robust scenario images according to an embodiment of the present application;

[0024] Figure 3 is an example diagram of an optional N dose distribution maps according to an embodiment of the present application;

[0025] Figure 4 It is an example diagram of an optional first dose distribution map according to an embodiment of the present application;

[0026] Figure 5 It is an example diagram of an optional second dose distribution map according to an embodiment of the present application;

[0027] Figure 6 It is a schematic diagram of an optional first serial number matrix according to an embodiment of the present application;

[0028] Figure 7 It is a flowchart of a method for robust optimization of a proton radiotherapy plan based on adaptive scenario according to an embodiment of the present application;

[0029] Figure 8 It is an architecture diagram of a method for robust optimization of a proton radiotherapy plan based on adaptive scenario according to an embodiment of the present application. Detailed implementation manners

[0030] In order to enable those skilled in the art to better understand the solution of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the protection scope of the present application.

[0031] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present application described here can be implemented in an order other than those illustrated or described here. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units does not necessarily need to be limited to those clearly listed steps or units, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0032] In an optional embodiment, the device for robust optimization of a proton radiotherapy plan based on adaptive scenario can be a software system or an embedded system combining software and hardware. For the convenience of description, the device for robust optimization of a proton radiotherapy plan based on adaptive scenario will be simplified to a system for description below.

[0033] According to an embodiment of the present application, an embodiment of a device for robust optimization of a proton radiotherapy plan based on adaptive scenario is provided, wherein,Figure 1 Schematic diagram of a proton radiotherapy plan robust optimization device based on adaptive sceneization according to an embodiment of the present application, as Figure 1 shown, the device includes: a first processing unit 101, a second processing unit 102, a determination unit 103, and an adjustment unit 104.

[0034] Optionally, the first processing unit 101 is configured to generate N robust scene images based on the radiotherapy plan of the target object, where the N robust scene images are used to simulate the change information of M regions of interest of the target object, and both N and M are integers greater than 1.

[0035] Optionally, in the field of radiotherapy, the target object usually refers to a patient receiving treatment. The radiotherapy plan includes all parameters and details of radiotherapy, such as the position, intensity, irradiation angle, time of the radiation source, and patient-specific anatomical structure information. In the embodiments of the present application, the radiotherapy plan may be a proton radiotherapy plan.

[0036] Optionally, the robust scene images may be multiple image scenes simulated according to the patient's radiotherapy plan and possible physiological changes, position changes, or anatomical changes (such as respiratory movement, position flipping, tumor growth, etc.). Each scene represents the possible state of the target area and surrounding tissues under different change conditions. The creation of these scenes is to evaluate the robustness of the treatment plan to these changes in actual application, that is, the treatment plan can still be effectively and safely executed under various possible changes. N represents the number of generated robust scene images, and N being greater than 1 means that at least two or more scenes are created, which ensures that enough possible changes are covered, improving the robustness and adaptability of the radiotherapy plan.

[0037] Optionally, in radiotherapy, the region of interest (ROI) usually refers to the tumor region (target area) and surrounding normal organs or tissues that need to be protected (also called organs at risk). M being greater than 1 indicates that multiple different regions are considered, which may include multiple parts of the tumor or multiple normal tissues that need to be considered, ensuring the comprehensiveness and complexity management of the treatment plan.

[0038] In an alternative embodiment, the second processing unit 102 is configured to calculate the dose distribution map of each robust scene image through a dose calculation engine, obtaining N dose distribution maps corresponding to the N robust scene images.

[0039] Optionally, the dose calculation engine is a software component in a radiotherapy planning system responsible for calculating the dose distribution of radiation passing through a patient's body. The dose calculation engine can accurately predict the deposited dose of radiation at various locations in the patient's body based on physical models and biological effect models, taking into account factors such as radiation attenuation, scattering, and tissue heterogeneity. The core task of the dose calculation engine is to predict the dose distribution of the radiation beam on the robust scenario image under the given radiotherapy plan parameters.

[0040] Optionally, the dose distribution map is a visual representation of the dose values of radiation exposure at various locations in the patient's body. The dose distribution map shows the distribution of dose in three-dimensional space, usually using different colors or gray levels to distinguish different dose levels. The dose distribution map is an important part of radiotherapy planning. Doctors and physicists will evaluate the safety and effectiveness of the treatment plan based on the dose distribution map to ensure that the tumor area receives a sufficient dose of radiation while minimizing damage to surrounding healthy tissues.

[0041] It should be noted that the N dose distribution maps can be the original dose distribution maps (also called initial dose matrices) calculated by the dose calculation engine based on N robust scenario images, or the N dose distribution maps obtained by sampling each of the N original dose distribution maps at least once. Among them, the conditions for each sampling can be custom-set.

[0042] In an optional embodiment, the determination unit 103 is configured to determine a first dose distribution map and a second dose distribution map according to the N dose distribution maps, where the first dose distribution map is used to record the maximum dose value of the N dose distribution maps at each grid point, and the second dose distribution map is used to record the minimum dose value of the N dose distribution maps at each grid point, and each grid point corresponds to a beam spot in radiotherapy.

[0043] Optionally, in the robust optimization method of radiotherapy, the "first dose distribution map" and the "second dose distribution map" are used to quantify and characterize the dose distribution uncertainty under N robust scenario images. Specifically: The first dose distribution map (also called the maximum dose distribution map) records the highest dose value that each beam spot (i.e., a specific small area where radiation irradiates the patient's body, often represented by a grid point in the image) can receive under all N robust scenarios. This means that for each grid point, by comparing the dose distributions in N scenarios, the maximum dose value is selected as the first dose distribution value at that point. This can identify areas that may receive excessive doses under any scenario, especially normal tissues, during the optimization process, thereby avoiding or reducing possible side effects.

[0044] In contrast, the second dose distribution map (which can also be referred to as the minimum dose distribution map) records the lowest dose value that each beam spot can receive under N robust scenarios. For each grid point, the minimum dose value among the N scenarios is selected. This map is mainly used to ensure that the tumor region can receive sufficient treatment dose under all possible scenarios and achieve the treatment goal even under the most unfavorable conditions.

[0045] Optionally, Figure 2 is a schematic diagram of an optional N robust scenario images according to an embodiment of the present application. As Figure 2 shown, when N = 3, it includes three robust scenario images, namely Image 1, Image 2, and Image 3. Each image includes two regions of interest, namely Region A and Region B. In different scenario images, the shapes and / or positions of the regions of interest are different. It should be noted that N = 3 and M = 2 are only examples. In practical applications, N and M are any integers greater than 1.

[0046] Optionally, Figure 3 is an example diagram of an optional N dose distribution maps according to an embodiment of the present application. Among them, as Figure 3 shown, the dose distribution Figure 1 is the dose distribution map obtained based on Image 1 (including dose values 1, 2, 3, 4); the dose distribution Figure 2 is the dose distribution map obtained based on Image 2 (including doses 0.5, 1.5, 5, 3); the dose distribution Figure 3 is the dose distribution map obtained based on Image 3 (including doses 2, 3, 4, 1). It should be noted that Figure 3 is only an example for the purpose of making it easier for those skilled in the art to understand the technical solution of the embodiment of the present application. In practical applications, the matrix distribution of the dose distribution map can be various forms of distribution.

[0047] Optionally, the second processing unit is further configured to detect the dose value recorded at the x-th grid point of each dose distribution map, where x is an integer greater than or equal to 1; and determine the maximum dose value recorded at the x-th grid point of the N dose distribution maps as the value at the x-th grid point of the first dose distribution map according to the dose value recorded at the x-th grid point of each dose distribution map.

[0048] Optionally, Figure 4 is an example diagram of an optional first dose distribution map according to an embodiment of the present application. As Figure 4 shown, based on the dose distribution Figure 1 、the dose distribution Figure 2 and the dose distribution Figure 3For example, if the lattice points in the upper left corner are 1, 0.5, and 2 respectively, then the maximum dose value at the lattice points in the upper left corner of the three dose distribution maps can be determined to be 2 (from dose distribution Figure 3 ); similarly, the maximum dose value at the lattice points in the upper right corner of the three dose distribution maps is 5 (from dose distribution Figure 2 ), the maximum dose value at the lattice points in the lower left corner of the three dose distribution maps is 3 (from dose distribution Figure 3 ), and the maximum dose value at the lattice points in the lower right corner of the three dose distribution maps is 4 (from dose distribution Figure 1 ).

[0049] Optionally, the second processing unit is further configured to detect the dose value recorded at the y-th lattice point of each dose distribution map, where y is an integer greater than or equal to 1; and determine the minimum dose value recorded at the y-th lattice point of the N dose distribution maps as the value of the second dose distribution map at the y-th lattice point.

[0050] Optionally, Figure 5 is an example diagram of an optional second dose distribution map according to an embodiment of the present application. As Figure 5 shown, based on dose distribution Figure 1 , dose distribution Figure 2 , and dose distribution Figure 3 , the minimum dose value at the lattice points in the upper left corner of the three dose distribution maps is 0.5 (from dose distribution Figure 2 ), the minimum dose value at the lattice points in the upper right corner of the three dose distribution maps is 3 (from dose distribution Figure 1 ), the minimum dose value at the lattice points in the lower left corner of the three dose distribution maps is 1.5 (from dose distribution Figure 2 ), and the minimum dose value at the lattice points in the lower right corner of the three dose distribution maps is 1 (from dose distribution Figure 3 ).

[0051] As can be seen from the above, the first dose distribution map and the second dose distribution map provide key information for the robust design of radiotherapy by recording the upper and lower limits of the dose distribution in N robust scenarios, helping to achieve safer and more effective radiotherapy plan dose optimization.

[0052] In an optional embodiment, the adjustment unit 104 is configured to adjust the radiotherapy plan according to the first dose distribution map and the second dose distribution map.

[0053] Optionally, in the robust optimization process of radiotherapy, the adjustment of the radiotherapy plan based on the "first dose distribution map" and the "second dose distribution map" ensures the effectiveness and safety of the treatment plan in the face of uncertainties. This adjustment process aims to narrow the fluctuation range of the dose distribution, especially in the tumor target area and the surrounding normal tissues, to ensure the accuracy of the treatment and reduce side effects.

[0054] Optionally, regarding how to adjust the radiotherapy plan according to the first dose distribution map and the second dose distribution map, the present application provides at least the following two implementation manners:

[0055] The first implementation manner: Identify the parts of the normal tissues that are most likely to receive excessive radiation, which correspond to the regions with higher dose values in the first dose distribution map. For these regions, the radiotherapy plan needs to be adjusted to reduce radiation exposure; identify the positions in the second dose distribution map where the dose values of the tumor target area are lower than the treatment threshold, which means that in the most adverse scenarios, these parts may not receive sufficient treatment doses.

[0056] According to the above analysis, adjust the direction and intensity of the beam. For example, for the regions of excessive exposure of normal tissues, avoid direct irradiation by changing the beam direction or reducing the beam intensity. For the parts with insufficient dose in the tumor area, increase the beam intensity or find more effective multi-beam irradiation angles to ensure the necessary treatment dose is reached.

[0057] The second implementation manner: Provide an adaptive dose compensation strategy based on the regions with uneven dose distributions identified in the first dose distribution map and the second dose distribution map. For example, use additional shielding materials or adjustable dose compensators to dynamically adjust during radiotherapy implementation to achieve the goal of uniform dose distribution.

[0058] Design or adjust the shape and density distribution of the dose compensator according to the information in the first dose distribution map and the second dose distribution map. This requires the compensator to accurately correspond to the high-dose regions and low-dose regions shown in the dose distribution map to reduce the excessive irradiation of normal tissues and increase the dose in the tumor area.

[0059] During the radiotherapy implementation process, real-time monitoring technology can also be used to monitor the actual situation of the dose distribution in the patient's body. If a significant deviation is found between the dose distribution and the first or second dose distribution map, immediately enable the adaptive dose compensation strategy for adjustment to ensure the robustness during the treatment process and the precise control of the dose.

[0060] Both of the above two embodiments reflect the guiding role of using the first dose distribution map and the second dose distribution map. By adjusting the specific parameters of radiotherapy or introducing auxiliary tools, the robustness of the treatment plan is enhanced, ensuring that the best treatment effect can still be achieved under various possible uncertainty scenarios, while maximizing the protection of the patient's physical health.

[0061] It should be noted that this application also allows further analysis based on the first dose distribution map and the second dose distribution map. For example, analyzing the sub - maps corresponding to each region of interest in the first dose distribution map and the sub - maps corresponding to each region of interest in the second dose distribution map, and combining the robust scenario images corresponding to the sub - maps of each region of interest and the N dose distribution sub - maps corresponding to each region of interest in the N dose distribution maps, so as to adjust the planned content regarding each region of interest in the radiotherapy plan.

[0062] As can be seen from the above, by generating N robust scenario images for the target object, this application effectively simulates the changes of the tumor target area and its surrounding tissues under different conditions. Compared with the method of simply using a fixed outer expansion boundary in the prior art, this application can more accurately predict the dose distribution impact caused by changes in body position, physiological state or tumor changes. By calculating the dose distribution of each robust scenario through the dose calculation engine, the N dose distribution maps obtained cover all possible dose distribution situations, which provides a comprehensive data basis for subsequent robust optimization.

[0063] Secondly, the generation of the first dose distribution map and the second dose distribution map respectively records the maximum and minimum dose values of the target area under various scenarios. This processing method can intuitively reflect the uncertainty range of the dose distribution. Based on these two maps, the adjustment of the radiotherapy plan can be targeted to reduce the overlap between the outer expansion boundary of the tumor and normal tissues, avoid excessive irradiation of normal tissues, and ensure sufficient coverage of the tumor area.

[0064] In addition, during the iterative optimization process of this application, through precise calculation and constraint adjustment, fast and effective dose optimization is achieved, overcoming the problems of slow optimization speed and poor effect in the prior art. The process of iterative dose and iterative constraint ensures that adjustments can be made according to the latest dose distribution information and constraint conditions in each optimization cycle, so as to achieve the optimal robust plan within limited calculation time. In addition, the parallel processing ability of the algorithm further shortens the optimization time and improves the efficiency.

[0065] In an alternative embodiment, the adjustment unit 104 includes: a first determination subunit, configured to determine a first sequence number matrix according to the sequence numbers of the robust scenario images corresponding to the dose values of each grid point in the first dose distribution map; a second determination subunit, configured to determine a second sequence number matrix according to the sequence numbers of the robust scenario images corresponding to the dose values of each grid point in the second dose distribution map; and an adjustment subunit, configured to adjust the radiotherapy plan according to the first dose distribution map, the second dose distribution map, the first sequence number matrix, and the second sequence number matrix.

[0066] Optionally, in the embodiments of the present application, the "first sequence number matrix" and the "second sequence number matrix" further provide the "source" information of the extreme values of the dose distribution, that is, which robust scenario generates the maximum dose at each grid point in the first dose distribution map and the minimum dose at each grid point in the second dose distribution map. This enables the adjustment of the radiotherapy plan not only to simply adjust the dose, but also to specifically optimize the dose distribution under specific scenarios, improving the personalization and robustness of the treatment.

[0067] Optionally, the adjustment device of the radiotherapy plan further includes: a sequence number determination unit, configured to use the sequence number of the robust scenario image corresponding to the dose value of the x-th grid point in the first dose distribution map as the value at the x-th matrix position in the first sequence number matrix.

[0068] Optionally, Figure 6 is a schematic diagram of an alternative first sequence number matrix according to the embodiments of the present application. As Figure 6 shown, since the dose distribution Figure 1 , the dose distribution Figure 2 , and the dose distribution Figure 3 of the three dose distribution maps have a maximum dose value of 2 at the grid point in the upper left corner (from the dose distribution Figure 3 ), a maximum dose value of 5 at the grid point in the upper right corner (from the dose distribution Figure 2 ), a maximum dose value of 3 at the grid point in the lower left corner (from the dose distribution Figure 3 ), and a maximum dose value of 4 at the grid point in the lower right corner (from the dose distribution Figure 1 ). Then, the upper left corner of the first sequence number matrix is "3" (representing the dose distribution Figure 3 ), the upper right corner is 2 (representing the dose distribution Figure 2 ), the lower left corner is 3 (representing the dose distribution Figure 3 ), and the lower right corner is 1 (representing the dose distribution Figure 1 ).

[0069] Optionally, the radiotherapy plan adjustment device further includes: a serial number determination unit, configured to use the serial number of the robust scenario image corresponding to the dose value of the y-th grid point in the second dose distribution map as the value at the y-th matrix position in the second serial number matrix.

[0070] The determination process of the second serial number matrix can refer to the determination process of the first serial number matrix. The principles of the two are similar and will not be elaborated here.

[0071] Optionally, regarding how to adjust the radiotherapy plan according to the first dose distribution map, the second dose distribution map, the first serial number matrix, and the second serial number matrix. The embodiments of the present application provide at least the following two implementation manners.

[0072] Method 1: Adjust the beam current to adapt to the most unfavorable scenario. For example, find out which robust scenarios the maximum dose and the minimum dose of each grid point correspond to through the "first serial number matrix" and the "second serial number matrix". Identify those scenarios that are most likely to cause excessive irradiation of normal tissues and insufficient dose in the tumor region. For the grid points in the first dose distribution map where normal tissues may be excessively irradiated, find the serial number of the most unfavorable scenario corresponding to them in the first serial number matrix, and adjust the direction or intensity of the beam current to avoid directly irradiating these areas. For the grid points with low dose in the tumor region in the second dose distribution map, find the serial number of the most unfavorable scenario corresponding to them in the second serial number matrix, and specifically enhance the beam current to ensure that the tumor region can reach the required dose for treatment in all scenarios.

[0073] Method 2: Introduce a dose adaptive control mechanism. For example, based on the "first serial number matrix" and the "second serial number matrix", design an adaptive dose control system that can dynamically adjust the beam current parameters during the radiotherapy implementation according to the actual changes of the patient to cope with the most unfavorable dose distribution scenario. During the treatment process, use real-time image guidance technology (such as CBCT or EPID) to monitor the changes in the patient's tumor position and surrounding tissues. The system quickly searches the first and second serial number matrices according to the monitoring results, identifies the robust scenario closest to the current change, and then immediately adjusts the beam current intensity and direction to match the optimal dose distribution in this scenario. During the treatment, the adaptive control system continuously calculates the dose distribution based on the current change scenario and compares it with the first dose distribution map and the second dose distribution map. If it is found that the actual dose distribution is close to the first dose distribution map (risk of excessive irradiation) or the second dose distribution map (risk of insufficient dose), the system will automatically adjust the beam current parameters to ensure that the dose distribution can cover the tumor region and will not cause excessive damage to normal tissues.

[0074] Both of these two embodiments focus on using the first dose distribution map, the second dose distribution map, and the first and second serial number matrices to provide a depth adjustment strategy for the radiotherapy plan. This method not only considers the numerical changes of the dose, but also combines the scenario information that generates these changes, making the adjustment of the treatment plan more accurate and personalized, being able to effectively cope with various uncertainties in the treatment process, and improving the treatment effect and patient safety.

[0075] In an alternative embodiment, the adjustment subunit includes: a first determination module, configured to determine the maximum dose distribution matrix of each region of interest based on the first dose distribution map; and determine the minimum dose distribution matrix of each region of interest based on the second dose distribution map; a first processing module, configured to use the sub-matrix corresponding to each region of interest in the first serial number matrix as the first sub-matrix of the region of interest; a second processing module, configured to use the sub-matrix corresponding to each region of interest in the second serial number matrix as the second sub-matrix of the region of interest; an adjustment module, configured to adjust the planned content of each region of interest in the radiotherapy plan according to the minimum dose distribution matrix, the maximum dose distribution matrix, the first sub-matrix, and the second sub-matrix of each region of interest.

[0076] Optionally, the first dose distribution map records the maximum dose values that all beam spots may receive under N robust scenarios. For each region of interest (ROI), the maximum dose values of all beam spots in this region can be extracted from the first dose distribution map to construct the maximum dose distribution matrix of this ROI. This matrix intuitively shows the upper limit of the dose that this ROI can receive under the most unfavorable scenario. For example, in Figure 4 the first dose distribution map shown, the matrix composed of the two dose values (2 and 3) on the left is the maximum dose distribution matrix corresponding to region of interest A; the matrix composed of the two dose values (5 and 4) on the right is the maximum dose distribution matrix corresponding to region of interest B.

[0077] Similarly, the second dose distribution map records the minimum dose values that all beam spots may receive under N robust scenarios. For each region of interest (ROI), the minimum dose values of all beam spots in this region are extracted from the second dose distribution map to construct the minimum dose distribution matrix of this ROI. This matrix helps to identify the lower limit of the dose that this ROI can receive in any scenario, especially ensuring that the tumor region can obtain sufficient treatment dose even under the most unfavorable conditions. For example, in Figure 5 the second dose distribution map shown, the matrix composed of the two dose values (0.5 and 1.5) on the left is the minimum dose distribution matrix corresponding to region of interest A; the matrix composed of the two dose values (3 and 1) on the right is the minimum dose distribution matrix corresponding to region of interest B.

[0078] In addition, the first sequence number matrix and the second sequence number matrix label from which robust scenario the maximum dose and the minimum dose of each beam spot originate. For each region of interest (ROI), a sub-matrix corresponding to the ROI is extracted from the first sequence number matrix, i.e., the first sub-matrix, which reveals the scenario information that leads to the maximum dose of the ROI beam spot. For example, in Figure 6 In the first sequence number matrix shown, the sub-matrix formed by the two sequence numbers (3 and 3) on the left is the first sub-matrix corresponding to region of interest A; the sub-matrix formed by the two sequence numbers (2 and 1) on the right is the first sub-matrix corresponding to region of interest B. Similarly, a sub-matrix corresponding to the ROI is extracted from the second sequence number matrix, i.e., the second sub-matrix, which reveals the scenario information that leads to the minimum dose of the ROI beam spot.

[0079] Finally, based on the maximum dose distribution matrix, the minimum dose distribution matrix, the first sub-matrix, and the second sub-matrix of each ROI, the dose distribution related to each region of interest in the radiotherapy plan can be optimized and adjusted. For example, by analyzing the first sub-matrix and the maximum dose distribution matrix, it is possible to identify the excessive irradiation that normal tissues may receive under the most unfavorable scenarios, and accordingly adjust the beam direction and intensity to reduce the dose of normal tissues and protect them from damage. At the same time, based on the second sub-matrix and the minimum dose distribution matrix, to ensure that the tumor region can still receive sufficient treatment dose under the most favorable scenarios, it may be necessary to enhance the beam or optimize the beam path to overcome the dose insufficiency under unfavorable scenarios. This adjustment process is an iterative optimization process and may require multiple cycles until an optimal radiotherapy plan that can meet the dose limits and treatment goals under all robust scenarios is found.

[0080] Through the above steps, the present application provides a robust optimization method based on quantitative analysis, which not only considers the numerical changes of the dose distribution, but also combines the sequence number information of the changing scenarios, realizes the precise adjustment of the radiotherapy plan, improves the efficiency and safety of treatment, especially when dealing with complex cases with significant uncertainties during the treatment process.

[0081] In an alternative embodiment, the adjustment module includes: a detection sub-module for detecting N dose distribution sub-graphs respectively corresponding to each region of interest in N dose distribution graphs; a determination sub-module for determining the N dose volume histograms of the region of interest according to the N dose distribution sub-graphs corresponding to each region of interest; a first adjustment sub-module for adjusting the planned content regarding each region of interest in the radiotherapy plan according to the N dose volume histograms, the minimum dose distribution matrix, the maximum dose distribution matrix, the first sub-matrix, and the second sub-matrix of each region of interest.

[0082] Optionally, first, for the N dose distribution maps obtained from N robust scenario simulations, the proton radiotherapy plan robust optimization device can automatically detect and extract the dose distribution information of each region of interest (including the tumor target area and critical normal tissues) under each scenario, forming N dose distribution sub-maps. These sub-maps provide the dose change trends of the ROI under different scenarios and are the basis for subsequent analysis and adjustment.

[0083] Optionally, the dose-volume histogram (DVH) is a statistical tool used to describe the volume of tissue irradiated within a certain dose range. Based on the N dose distribution sub-maps of each ROI, the corresponding N DVH maps can be generated. This step is essentially quantifying the dose range and frequency received by different parts of the ROI under each scenario.

[0084] Optionally, the adjustment of the radiotherapy plan is based on the comprehensive evaluation of the dose distribution of the ROI under N scenarios. By analyzing the N DVHs, it is possible to determine the doses received by the tumor and normal tissues under all potential physical change conditions, and identify the limit values and high-risk areas of the dose distribution. In addition, the minimum dose distribution matrix and the maximum dose distribution matrix provide the lower and upper limits of the ROI dose distribution, while the first sub-matrix and the second sub-matrix respectively identify the scenarios that result in these limit dose distributions. The combination of this matrix information and the data of the N DVHs provides a multi-dimensional perspective for adjusting beam parameters, optimizing dose distribution, reducing the dose to normal tissues, and ensuring tumor dose coverage.

[0085] For example, for normal tissues, by analyzing the maximum dose distribution matrix and the first sub-matrix, the risk of possible over-irradiation is identified, and then the beam direction, dose rate, or shielding means are adjusted to reduce the radiation received by these tissues. For the tumor area, referring to the minimum dose distribution matrix and the second sub-matrix, ensure that even in the most unfavorable scenario, the tumor can reach the required dose level for treatment. This may mean increasing the intensity of certain beams or optimizing the beam path to overcome the problem of insufficient dose in certain scenarios.

[0086] Based on the analysis of the N DVHs, the radiotherapy plan can be iteratively adjusted multiple times as needed until the dose distributions of all ROIs meet the established clinical criteria and the robustness is improved. In each iteration, the system will recalculate the DVH and evaluate the effect of the adjustment until an optimal solution is found.

[0087] In an alternative embodiment, the adjustment module includes: a second adjustment sub-module, configured to, when it is detected that the constraint condition set for the i-th region of interest is to reduce the dose, adjust the plan content regarding the i-th region of interest in the radiotherapy plan according to the maximum dose distribution matrix and the second sub-matrix of the i-th region of interest, where i is an integer greater than or equal to 1; a third adjustment sub-module, configured to, when it is detected that the constraint condition set for the j-th region of interest is to increase the dose, adjust the plan content regarding the j-th region of interest in the radiotherapy plan according to the minimum dose distribution matrix and the first sub-matrix of the j-th region of interest, where j is an integer greater than or equal to 1.

[0088] In an alternative embodiment, the adjustment module includes: a second adjustment sub-module, configured to, when it is detected that the constraint condition set for the i-th region of interest is to reduce the dose, adjust the plan content regarding the i-th region of interest in the radiotherapy plan according to the maximum dose distribution matrix and the first sub-matrix of the i-th region of interest, where i is an integer greater than or equal to 1; a third adjustment sub-module, configured to, when it is detected that the constraint condition set for the j-th region of interest is to increase the dose, adjust the plan content regarding the j-th region of interest in the radiotherapy plan according to the minimum dose distribution matrix and the second sub-matrix of the j-th region of interest, where j is an integer greater than or equal to 1.

[0089] Optionally, when the constraint condition set for the i-th region of interest is to reduce the dose: for the i-th ROI, first locate its maximum dose distribution matrix. This is because the constraint of reducing the dose is intended to avoid the region from receiving excessive radiation dose, and the maximum dose distribution matrix exactly contains the highest dose values that may be reached under all robust scenarios. Additionally, the first sub-matrix provides information on the robust scenarios where the dose contribution at each beam spot (i.e., the beam incidence point) in the maximum dose distribution matrix is the largest. In other words, the first sub-matrix can help the system identify which beams or scenarios cause the highest dose to the i-th ROI, thereby locating the beams or scenarios that need to be adjusted.

[0090] Based on the analysis results of the maximum dose distribution matrix and the first sub-matrix, the system will adjust the part of the radiotherapy plan related to the i-th ROI. The adjustment strategies include: reducing the intensity of certain beams, adjusting the direction of the beams, introducing beam shielding, or adjusting the irradiation time to ensure that the i-th ROI does not exceed the set dose limit under all possible scenarios.

[0091] Optionally, when it is detected that the constraint condition set for the j-th region of interest is to increase the dose, the system can lock the minimum dose distribution matrix of the j-th ROI to ensure that this region can receive sufficient dose under all robust scenarios, thus ensuring the effectiveness of the treatment. Secondly, the second sub-matrix of the j-th ROI indicates which beams contribute the least dose to the j-th ROI in the minimum dose distribution matrix. This helps the algorithm identify the beams that need to increase intensity or be optimized to improve the radiation dose to the j-th ROI.

[0092] Optionally, based on the analysis of the minimum dose distribution matrix and the second sub-matrix, the system will correspondingly increase the intensity of certain beams, optimize the beam directions, or extend the irradiation time when necessary to ensure that the j-th ROI can reach or approach the lower limit of the dose required for treatment under the most adverse robust scenarios.

[0093] It should be noted that whether the dose is reduced or increased, the key to the above process is to accurately locate the beams and scenarios to be adjusted through the maximum or minimum dose distribution matrix and the associated first or second sub-matrix. The system automatically adjusts the specific parameters of the radiotherapy plan based on this information to adapt to the dose constraint requirements of different ROIs, ensuring that the radiotherapy plan can still achieve safe and effective tumor coverage and normal tissue protection in the face of patient individual differences and uncertainties during the treatment process. This dynamic adjustment mechanism based on the dose distribution matrix and sub-matrix provides an efficient and intelligent solution for the robust optimization of radiotherapy.

[0094] It should also be noted that the above process can also improve the optimization speed of radiotherapy technology. For example, if N dose values are obtained for the target area under N scenarios, according to the existing technology solutions, regardless of which constraint condition, it is necessary to perform optimization calculations for each dose value separately, that is, it needs to be calculated N times. However, under specific constraint conditions, in fact, not every dose value needs to be concerned. Taking the target area as an example, when the target area is usually set with the constraint condition of increasing the dose, in this case, according to the technical solution of the present application, only the minimum dose value among the N dose values will be concerned, and then the dose increase optimization will be carried out for this minimum dose value in combination with the constraint condition. For the larger dose values among the N dose values, there is no need to perform optimization calculations anymore. This is equivalent to reducing N - 1 calculations, thus improving the calculation efficiency and saving calculation resources. Moreover, calculating the N dose values simultaneously will actually introduce errors. For example, it is easy to cause the neural network model to have "hallucinations" because even though the larger dose values already meet the constraint conditions, they are still optimized, which will mislead the judgment direction of the neural network model. However, by adopting the technical solution of the present application, this problem can be avoided.

[0095] In an alternative embodiment, the second adjustment sub-module includes: a first processing sub-module for determining a dose constraint matrix for the i-th region of interest according to the maximum dose distribution matrix of the i-th region of interest and the constraint conditions of the i-th region of interest; a first calculation sub-module for calculating the matrix product of the dose constraint matrix of the i-th region of interest and the first sub-matrix of the i-th region of interest to obtain an iterative constraint matrix for the i-th region of interest; and a second processing sub-module for adjusting the plan content regarding the i-th region of interest in the radiotherapy plan according to the iterative constraint matrix of the i-th region of interest.

[0096] Optionally, generally, a radiotherapy plan sets a dose upper limit for each ROI to avoid over-irradiation of normal tissues or critical organs, and also sets a dose lower limit to ensure that the tumor region receives sufficient dose. For the constraint conditions of reducing dose, the main concern is the dose upper limit. According to the dose upper limit constraint of the ROI, the system generates a dose constraint matrix for this ROI. This matrix is a threshold matrix, and each element in it represents the dose constraint value corresponding to the beam spot position, that is, the maximum allowable dose value at this position.

[0097] Optionally, by performing a matrix product operation on the dose constraint matrix and the first sub-matrix, it is possible to identify those beam spot positions that exceed the dose constraint in the most adverse scenario. Through the matrix product, an iterative constraint matrix can be obtained, which highlights the beam spot positions that need to be adjusted to meet the dose constraint.

[0098] Optionally, the basis for the system to adjust the radiotherapy plan is the iterative constraint matrix. This matrix indicates which beam spots or beam parameters need to be modified to reduce the over-irradiation of the i-th ROI. Possible adjustments include: reducing the beam intensity, adjusting the beam angle or the incident point, increasing beam shielding, using a shield to reduce the dose in a specific area, or adjusting the irradiation sequence or time to reduce the impact on sensitive areas.

[0099] Optionally, the above adjustment process can be iterative until a preset optimization criterion is reached. After each adjustment, the maximum dose distribution matrix is recalculated and the iterative constraint matrix is updated until the dose distribution of the i-th ROI stabilizes within the dose constraint range, achieving the goal of robust optimization.

[0100] Through the above process, the present application can accurately identify the beams or beam spots that need to be adjusted for the dose constraint conditions of a specific ROI in the radiotherapy plan. Through iterative optimization, it ensures that the dose distribution effectively covers the tumor region and does not cause unnecessary damage to normal tissues or critical organs. This robust optimization method based on matrix operations significantly improves the safety and personalization level of radiotherapy.

[0101] Optionally, the third adjustment sub-module is further configured to determine the dose constraint matrix of the j-th region of interest according to the minimum dose distribution matrix of the j-th region of interest and the constraint condition of the j-th region of interest; calculate the matrix product of the dose constraint matrix of the j-th region of interest and the second sub-matrix of the j-th region of interest to obtain the iterative constraint matrix of the j-th region of interest; and adjust the plan content regarding the j-th region of interest in the radiotherapy plan according to the iterative constraint matrix of the j-th region of interest.

[0102] In an optional embodiment, the second processing sub-module includes: a third processing sub-module, configured to determine the gradient matrix of the i-th region of interest according to the iterative constraint matrix of the i-th region of interest; a second calculation sub-module, configured to calculate the matrix product of the gradient matrix of the i-th region of interest and the first sub-matrix of the i-th region of interest to obtain the iterative gradient matrix of the i-th region of interest; and a fourth processing sub-module, configured to adjust the plan content regarding the i-th region of interest in the radiotherapy plan according to the iterative gradient matrix of the i-th region of interest.

[0103] Optionally, the iterative constraint matrix highlights the beam spot positions where the dose needs to be adjusted to ensure that the dose constraints of the ROI are not violated. Based on this matrix, the system can calculate the gradient of the dose constraint change at each beam spot position, that is, for each beam spot position, how much the dose should be reduced to meet the constraint conditions. The gradient matrix reflects the spatial change rate of the dose and is crucial for optimizing the beam path and intensity. In the context of robust optimization, the gradient matrix helps identify which parameters in the treatment plan can be slightly adjusted to effectively reduce or control the dose received by a specific ROI.

[0104] Optionally, the system performs a matrix multiplication operation on the gradient matrix of the i-th ROI and the first sub-matrix. The result of the matrix multiplication is the iterative gradient matrix, which contains the recommended gradient values for dose adjustment at each beam spot in the most adverse robust scenario. These gradient values guide the adjustment direction of beam parameters (such as intensity, direction) to effectively reduce the dose of the i-th ROI and achieve the purpose of reducing the dose constraint condition.

[0105] Based on the iterative gradient matrix, the system can determine which beam parameters need to be adjusted and how to adjust them to reduce the dose to the i-th ROI. Possible adjustments include: reducing the beam intensity, especially at those beam spot positions that contribute the most to the ROI dose; adjusting the beam direction or the incident point to avoid or reduce the irradiation of the sensitive ROI; introducing or adjusting beam shielding, using shielding materials to reduce the dose of a specific beam spot to the ROI.

[0106] It should be noted that the above adjustment process is iterative, that is, after the adjustment, the dose distribution will be recalculated to generate a new iterative constraint matrix and the first sub-matrix, and the iterative gradient matrix will be calculated again until the dose distribution of the i-th ROI is stable and all dose constraint conditions are met. This process continuously approaches the treatment goal, ensuring the robustness and effectiveness of the dose distribution.

[0107] Through the above technical process, the present application provides a method for precisely adjusting beam parameters to optimize the dose distribution of a specific ROI, which can not only effectively control the dose received by the sensitive area, but also improve the adaptability and safety of the treatment plan in the face of patient individual differences and treatment uncertainties.

[0108] Optionally, the proton radiotherapy plan robust optimization device is further configured to determine the gradient matrix of the j-th region of interest according to the iterative constraint matrix of the j-th region of interest; calculate the matrix product of the gradient matrix of the j-th region of interest and the second sub-matrix of the j-th region of interest to obtain the iterative gradient matrix of the j-th region of interest; and adjust the plan content of the radiotherapy plan regarding the j-th region of interest according to the iterative gradient matrix of the j-th region of interest.

[0109] In an optional embodiment, the second processing unit includes: a first processing subunit, configured to calculate the initial dose matrix of each robust scenario image based on a dose calculation engine to obtain N initial dose matrices corresponding to N robust scenario images; a second processing subunit, configured to sample the N initial dose matrices according to the dose constraint conditions set for each region of interest of the target object to obtain the dose information corresponding to each region of interest in each initial dose matrix; a third processing subunit, configured to determine N intermediate dose matrices according to the dose information corresponding to each region of interest in each initial dose matrix, where the N intermediate dose matrices correspond to the N robust scenario images one by one, and each intermediate dose matrix includes the dose information corresponding to M regions of interest in one initial dose matrix; and a fourth processing subunit, configured to determine N dose distribution maps corresponding to the N robust scenario images according to the N intermediate dose matrices and the weights set for each beam spot.

[0110] Optionally, first, a dose calculation engine (such as an AI-based dose prediction model, Monte Carlo simulation, convolutional neural network, etc.) is used to predict the dose distribution of the images in N robust scenarios, obtaining N initial dose matrices. Each dose matrix contains the dose information of the radiation beam at all beam spot positions in the patient's body under a specific scenario. Then, dose constraint conditions are set for each region of interest (ROI) of the target object. Among them, each ROI (such as the tumor target area, critical organs, etc.) has its specific dose constraint conditions, which are designed to ensure that the tumor area receives sufficient dose while the dose of the surrounding normal tissues is kept within a safe range. The constraint conditions include dose lower limit, upper limit or dose mean, etc.

[0111] Optionally, the system applies the dose constraint conditions for each ROI to the N initial dose matrices, and extracts the dose distribution of each ROI in each robust scenario through sampling. For example, sampling can be to statistically analyze or average the dose values in a specific region (ROI) of the matrix to obtain the dose information of the ROI in a specific scenario. Optionally, based on the dose information of each region of interest in each initial dose matrix, the system constructs N intermediate dose matrices. Each intermediate dose matrix contains the dose distribution data of M regions of interest in a certain robust scenario, where M represents the number of ROIs. The role of the intermediate dose matrix is to expand the single beam spot dose to the dose description of the entire ROI, providing more comprehensive information for the subsequent generation of the dose distribution map.

[0112] Optionally, through the intermediate dose matrix and the weight (W), the system can generate the final N dose distribution maps. The weight reflects the magnitude of the contribution of each beam spot in the plan to the overall treatment, and can be set based on physical parameters (such as beam current intensity, beam direction) or clinical parameters (such as dose optimization target). The calculation process involves multiplying the dose value at each beam spot position in the intermediate dose matrix by its corresponding weight, and then summing up the dose values of all beam spots to obtain the overall dose distribution in each robust scenario.

[0113] In an optional embodiment, the fourth processing subunit includes: a resampling module, configured to resample the N intermediate dose matrices respectively according to the parameter information of the radiation particles, obtaining N target dose matrices corresponding to the N intermediate dose matrices one by one; a generation module, configured to generate a dose distribution map corresponding to the target dose matrix according to each target dose matrix and the weight set for each beam spot, obtaining N dose distribution maps corresponding to the N target dose matrices.

[0114] Optionally, in radiotherapy, different types of radiation particles (such as photons, protons, electrons, etc.) have different physical properties, such as penetration power, scattering characteristics, range, etc. These properties directly affect the distribution pattern of the dose in the patient's body. The system will resample the previously generated N intermediate dose matrices, and this process will consider the specific parameters of the radiation particles. Resampling includes adjusting the resolution of the dose matrix, recalculating the dose distribution according to the penetration depth of the particles, or correcting the dose distribution based on the particle range and scattering effect to ensure that the dose calculation more accurately reflects the true behavior of the particles in the patient's body.

[0115] Optionally, after resampling, the intermediate dose matrix in each robust scenario is converted into a target dose matrix that more accurately reflects the dose distribution of the radiation particles. These matrices contain the dose values of each beam spot in a specific scenario, taking into account the particle characteristics, providing a basis for the generation of subsequent dose distribution maps.

[0116] Optionally, the weight (W) of each beam spot reflects its contribution to the overall dose distribution. The setting of the weight is usually based on physical parameters (such as beam current intensity, beam direction) and clinical requirements (such as tumor coverage and normal tissue protection). The system can multiply the beam spot dose value in each target dose matrix by its corresponding weight, and then sum up the weighted dose values of all beam spots to generate the dose distribution map for this robust scenario. The dose distribution map visually shows which areas in the patient's body receive higher or lower doses, as well as the uniformity and coverage of the dose distribution, considering the radiation particle parameters and beam spot weights.

[0117] Repeat the above steps to generate the corresponding dose distribution maps for each of the N robust scenarios one by one, and finally obtain a set of N dose distribution maps. These maps not only reflect the dose distribution of each beam spot in each scenario, but also consider the influence of radiation particle characteristics and beam spot weights, providing a comprehensive perspective on the robustness of the treatment plan.

[0118] It should be noted that in the embodiments of this application, the sampling process is not a necessary process, and the purpose of sampling is to improve the optimization speed of the radiotherapy plan. On this basis, even if sampling is performed, the number of sampling times can be set customarily, for example, sampling once or sampling twice.

[0119] In an alternative embodiment, the radiotherapy plan adjustment device further includes: a sampling correction unit for determining sampling correction information through a dose calculation engine according to the radiotherapy plan of the target object and the weight set for each beam spot; a dose adjustment unit for adjusting the dose information of the N dose distribution maps according to the sampling correction information.

[0120] Optionally, the advantage of sampling is to improve the optimization speed of radiotherapy planning. However, sampling also introduces errors. To correct the errors caused by sampling, a computer or dose calculation engine will compare the N initially generated dose distribution maps with the treatment target, identify the differences between the dose distribution and the expected target, and form sampling correction information. Such information may include specific descriptions and quantifications of issues such as high or low dose deviations, non-uniformity of dose distribution, insufficient dose coverage of the ROI, or over-irradiation. Then the system will adjust the dose information in the N initially generated dose distribution maps based on the sampling correction information. For example, recalculate the beam spot dose, adjust the beam angle or intensity, change the irradiation time, etc., to correct the deviations in the initially generated dose distribution maps.

[0121] For example, the dose calculation engine can extract all necessary parameters from the radiotherapy plan, including but not limited to the specific information of the patient, the delineation data of tumors and normal tissues, the angles and intensities of the beams, the irradiation time, and the dose constraints for each region of interest (ROI). Secondly, the beam spot refers to the beam incident point designated as a specific dose distribution in the treatment plan, which is usually predefined in the plan file. The weight reflects the importance of each beam spot in the total dose distribution and is used to adjust the dose contribution of the beam spot. The weight is usually set based on the physical parameters of the beam spot (such as beam intensity, incident angle) and clinical requirements (such as tumor dose coverage and normal tissue protection).

[0122] Optionally, based on the radiotherapy plan parameters and beam spot weights obtained in the data preparation stage, the dose calculation engine simulates the initial distribution of radiation dose in the patient's body. The calculations at this stage may be rough or fast, for a preliminary estimate of the dose distribution. Subsequently, the dose calculation engine compares the initially generated dose distribution map with the treatment target, where the targets include dose constraints for each ROI, such as dose upper limit, lower limit, or average dose, etc. Through analysis, identify the beam spots or regions that do not meet the expected dose target, as well as the non-uniformity or deviation of the dose distribution. Finally, use mathematical methods to quantify the difference between the initially generated dose distribution and the treatment target, generating an error matrix or error distribution map. This may include calculating metrics such as the average error, root mean square error, or maximum deviation of the dose distribution.

[0123] Based on the results of the error analysis, determine the beam spots or dose distribution regions that need to be corrected, as well as the specific correction methods. For example, it may be necessary to adjust the beam intensity to reduce the high-dose area, or increase beam shielding to protect normal tissues. Finally, combined with the correction strategy, generate sampling correction information for each beam spot or region. This can be a list containing the parameter changes of each beam spot before and after correction, or guidance information for fine-tuning the input parameters of the dose calculation engine.

[0124] In an alternative embodiment, Figure 7is a flowchart of a proton radiotherapy plan robust optimization method based on adaptive sceneization according to an embodiment of the present application. Among them, as Figure 7 shown, the method includes the following steps:

[0125] Step S701, generating N robust scene images based on the radiotherapy plan of the target object.

[0126] Among them, the N robust scene images are used to simulate the change information of M regions of interest of the target object, and both N and M are integers greater than 1;

[0127] Step S702, calculating the dose distribution map of each robust scene image through a dose calculation engine to obtain N dose distribution maps corresponding to the N robust scene images.

[0128] Step S703, determining a first dose distribution map and a second dose distribution map according to the N dose distribution maps.

[0129] Among them, the first dose distribution map is used to record the maximum dose value of the N dose distribution maps at each grid point, and the second dose distribution map is used to record the minimum dose value of the N dose distribution maps at each grid point. Each grid point corresponds to a beam spot in radiotherapy.

[0130] Step S704, adjusting the radiotherapy plan according to the first dose distribution map and the second dose distribution map.

[0131] Optionally, Figure 8 is an architecture diagram of a proton radiotherapy plan robust optimization method based on adaptive sceneization according to an embodiment of the present application. As Figure 8 shown, the entire architecture includes four stages: "before optimization start", "iterative dose", "iterative constraint", and "calculate gradient".

[0132] In the stage of "before optimization start", the following steps are included:

[0133] Obtaining the CT image of the target object and the corresponding contour file;

[0134] Generating an initial radiotherapy plan for the target object;

[0135] Generating a robust scene based on the initial radiotherapy plan of the target object. It includes: images in the non-robust scene and N robust scene images, where the HU value and / or position of each pixel of the N robust scene images have uncertainties;

[0136] Based on a dose calculation engine (optional AI engine, Monte Carlo engine, convolution engine, etc.) to calculate the dose influence matrix corresponding to the N robust images (corresponding to the above-mentioned initial dose matrix, that is Figure 8 in ), each ROI obtains N initial dose matrices (ROI1, ROI2... ROIN) based on N robust scenario images;

[0137] Sample the N dose impact matrices based on M ROI regions with overdose constraints set. The sampling of each ROI is performed in parallel under the GPU (for example, sampling N millimeters below the Bragg peak position, sampling the entire image as a hammer shape along the central axis of the light spot, and Only sample the areas where the ROI exists during sampling);

[0138] Merge the dose impact matrices sampled in parallel;

[0139] Further sample the N dose impact matrices after sampling for M ROIs based on the characteristics of the radioactive particles. The parameters that can be set include but are not limited to: truncation distance, truncation position, sampling shape, etc.;

[0140] Set the weight W corresponding to each beam spot in the dose impact matrix.

[0141] After the above steps, the dose distribution map in the non-robust scenario after two samplings can be obtained (i.e., Figure 8 the non-robust scenario in ), as well as the N dose distribution maps in N robust scenarios (i.e., Figure 8 the robust scenarios in ... robust scenarios ).

[0142] Optionally, in the iterative dose stage, the following steps are included:

[0143] Obtain the weight w corresponding to each point in the current dose impact matrix;

[0144] Calculate the dose distribution in N scenarios based on the weight w and the sampled dose impact matrix;

[0145] Call the dose calculation engine to perform a complete dose calculation and correct the dose distribution calculated after sampling (i.e., Figure 8 the intermediate dose correction in

[0146] Obtain the maximum value in each grid point of the N dose distributions to get the maximum dose distribution (i.e., obtain the first dose distribution map mentioned above).

[0147] Take the minimum value in each grid point of the N dose distributions to get the minimum dose distribution (i.e., obtain the second dose distribution map mentioned above);

[0148] Calculate which nth robust scenario the dose in each grid point of the maximum dose distribution comes from to obtain the maximum sequence number image (i.e., obtain the first sequence number matrix mentioned above), such as Figure 8As shown, the mask of the maximum existing dose in the non-robust scenario and the masks of the maximum existing dose in N robust scenarios can be obtained;

[0149] Calculate that the dose in each grid point in the minimum dose distribution comes from the nth robust scenario, and obtain the minimum sequence number image (that is, obtain the above-mentioned second sequence number matrix), as Figure 8 As shown, the mask of the minimum existing dose in the non-robust scenario and the masks of the minimum existing dose in N robust scenarios can be obtained;

[0150] Crop the N dose distributions to obtain the N dose distributions corresponding to each ROI, including obtaining the maximum dose distribution and the minimum dose distribution corresponding to each ROI;

[0151] Calculate the DVH of each ROI in the N dose distributions;

[0152] Crop the maximum sequence number images corresponding to the M ROIs (that is, Figure 8 the ROI maximum dose sequence number Mask in);

[0153] Crop the minimum sequence number images corresponding to the M ROIs (that is, Figure 8 the ROI minimum dose sequence number Mask in).

[0154] Optionally, in the iterative constraint stage, the following steps are included:

[0155] Based on the non-robust scenario and N robust scenarios, obtain the ROI matrix of the current constraint: for the constraint of reducing the dose class, obtain the maximum dose matrix (for example, the maximum dose distribution matrix of the ith region of interest); for the constraint of increasing the dose class, obtain the minimum dose matrix (for example, the minimum dose distribution matrix of the jth region of interest). For the mean class constraint, obtain the dose matrix under N robust scenarios.

[0156] Calculate the FGAP matrix under the corresponding dose matrix constraints, including: calculating the FGAP matrix under the minimum dose matrix constraint and calculating the FGAP matrix under the maximum dose matrix constraint.

[0157] Determine the ROI sequence number image, including: for the constraint of reducing the dose class, obtain the ROI maximum sequence number Mask (for example, the first sub-matrix of the ith region of interest), for the constraint of increasing the dose class, obtain the ROI minimum sequence number Mask (for example, the second sub-matrix of the jth region of interest). For the mean class constraint, there is no need to obtain the sequence number image.

[0158] Multiply the FGAP matrix by the corresponding ROI sequence number Mask to obtain the FGAP matrix under the corresponding constraint (including the FGAP matrix of the minimum dose under the constraint and the FGAP of the maximum dose under the constraint). For the mean class constraint, skip this step and directly obtain the FGAP of the dose in each scenario.

[0159] Optionally, in the stage of calculating the gradient, the following steps are included:

[0160] Calculate the gradient matrix of each constraint.

[0161] For the dose-increasing type constraint, multiply the gradient matrix of the ROI by the minimum serial number Mask of the ROI. For the dose-decreasing type constraint, multiply the gradient matrix of the ROI by the maximum serial number Mask of the ROI. Skip the mean type constraint.

[0162] Superimpose all the gradients into a complete matrix.

[0163] The above four stages can be repeatedly executed in a loop until the optimizer converges and stops.

[0164] The serial numbers of the embodiments of the present application above are only for description and do not represent the advantages or disadvantages of the embodiments.

[0165] In the above embodiments of the present application, the descriptions of the respective embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0166] In several embodiments provided by the present application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only illustrative. For example, the division of the units can be a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point, the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the units or modules can be in an electrical or other form.

[0167] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0168] In addition, the functional units in each embodiment of the present application can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0169] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), mobile hard disks, magnetic disks, or optical discs.

[0170] The above are only the preferred embodiments of this application. It should be noted that for those of ordinary skill in the art, without departing from the principle of this application, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of this application.

Claims

1. An adaptive scenario-based robust optimization device for proton radiotherapy planning, characterized in that, Comprising: A first processing unit for generating N robust scenario images based on a radiotherapy plan of a target object, wherein the N robust scenario images are used to simulate variation information of M regions of interest of the target object, and both N and M are integers greater than 1; A second processing unit for calculating a dose distribution map of each robust scenario image through a dose calculation engine to obtain N dose distribution maps corresponding to the N robust scenario images; A determination unit for determining a first dose distribution map and a second dose distribution map according to the N dose distribution maps, wherein the first dose distribution map is used to record the maximum dose value of the N dose distribution maps at each grid point, and the second dose distribution map is used to record the minimum dose value of the N dose distribution maps at each grid point, and each grid point corresponds to a beam spot in radiotherapy; An adjustment unit for adjusting the radiotherapy plan according to the first dose distribution map and the second dose distribution map.

2. The proton radiotherapy plan robust optimization device based on adaptive sceneization according to claim 1, wherein, The adjustment unit includes: A first determination subunit for determining a first sequence number matrix according to the sequence numbers of the robust scenario images corresponding to the dose values of each grid point in the first dose distribution map; A second determination subunit for determining a second sequence number matrix according to the sequence numbers of the robust scenario images corresponding to the dose values of each grid point in the second dose distribution map; An adjustment subunit for adjusting the radiotherapy plan according to the first dose distribution map, the second dose distribution map, the first sequence number matrix, and the second sequence number matrix.

3. The proton radiotherapy plan robust optimization device based on adaptive scene is characterized in that, according to claim 2 The adjustment subunit includes: A first determination module for determining a maximum dose distribution matrix of each region of interest based on the first dose distribution map; and determining a minimum dose distribution matrix of each region of interest based on the second dose distribution map; A first processing module for using the sub-matrix corresponding to each region of interest in the first sequence number matrix as the first sub-matrix of the region of interest; A second processing module for using the sub-matrix corresponding to each region of interest in the second sequence number matrix as the second sub-matrix of the region of interest; An adjustment module for adjusting the plan content of the radiotherapy plan regarding each region of interest according to the minimum dose distribution matrix, the maximum dose distribution matrix, the first sub-matrix, and the second sub-matrix of each region of interest.

4. The proton radiotherapy plan robust optimization device based on adaptive sceneization according to claim 3, characterized in that, The adjustment module includes: A detection sub-module for detecting N dose distribution sub-maps respectively corresponding to each region of interest in the N dose distribution maps; A determination sub-module for determining N dose volume histograms of the region of interest according to the N dose distribution sub-maps corresponding to each region of interest; A first adjustment sub-module for adjusting the plan content of the radiotherapy plan regarding each region of interest according to the N dose volume histograms, the minimum dose distribution matrix, the maximum dose distribution matrix, the first sub-matrix, and the second sub-matrix of each region of interest.

5. The proton radiotherapy plan robust optimization device based on adaptive scenario according to claim 3, wherein The adjustment module includes: The second adjustment sub-module is used to adjust the plan content regarding the $i$-th region of interest in the radiotherapy plan according to the maximum dose distribution matrix and the first sub-matrix of the $i$-th region of interest when the constraint condition set for the $i$-th region of interest is to reduce the dose, where $i$ is an integer greater than or equal to 1; The third adjustment sub-module is used to adjust the plan content regarding the $j$-th region of interest in the radiotherapy plan according to the minimum dose distribution matrix and the second sub-matrix of the $j$-th region of interest when the constraint condition set for the $j$-th region of interest is to increase the dose, where $j$ is an integer greater than or equal to 1.

6. The proton radiotherapy plan robust optimization device based on adaptive scenario according to claim 5, wherein, The second adjustment sub-module includes: The first processing sub-module is used to determine the dose constraint matrix of the $i$-th region of interest according to the maximum dose distribution matrix of the $i$-th region of interest and the constraint condition of the $i$-th region of interest; The first calculation sub-module is used to calculate the matrix product of the dose constraint matrix of the $i$-th region of interest and the first sub-matrix of the $i$-th region of interest to obtain the iterative constraint matrix of the $i$-th region of interest; The second processing sub-module is used to adjust the plan content regarding the $i$-th region of interest in the radiotherapy plan according to the iterative constraint matrix of the $i$-th region of interest.

7. The proton radiotherapy plan robust optimization device based on adaptive sceneization according to claim 6, characterized in that, The second processing sub-module includes: The third processing sub-module is used to determine the gradient matrix of the $i$-th region of interest according to the iterative constraint matrix of the $i$-th region of interest; The second calculation sub-module is used to calculate the matrix product of the gradient matrix of the $i$-th region of interest and the first sub-matrix of the $i$-th region of interest to obtain the iterative gradient matrix of the $i$-th region of interest; The fourth processing sub-module is used to adjust the plan content regarding the $i$-th region of interest in the radiotherapy plan according to the iterative gradient matrix of the $i$-th region of interest.

8. The proton radiotherapy plan robust optimization device based on adaptive scenario according to claim 1, wherein The second processing unit includes: The first processing sub-unit is used to calculate the initial dose matrix of each robust scenario image based on the dose calculation engine to obtain $N$ initial dose matrices corresponding to the $N$ robust scenario images; The second processing sub-unit is used to sample the $N$ initial dose matrices according to the dose constraint conditions set for each region of interest of the target object to obtain the dose information corresponding to each region of interest in each initial dose matrix; The third processing sub-unit is used to determine $N$ intermediate dose matrices according to the dose information corresponding to each region of interest in each initial dose matrix, where the $N$ intermediate dose matrices correspond to the $N$ robust scenario images one by one, and each intermediate dose matrix includes the dose information corresponding to the $M$ regions of interest in an initial dose matrix; The fourth processing sub-unit is used to determine $N$ dose distribution maps corresponding to the $N$ robust scenario images according to the $N$ intermediate dose matrices and the weights set for each beam spot.

9. The proton radiotherapy plan robust optimization device based on adaptive sceneization according to claim 8, characterized in that, The fourth processing sub-unit includes: A resampling module, configured to resample each of the N intermediate dose matrices according to parameter information of radioactive particles, so as to obtain N target dose matrices corresponding one by one to the N intermediate dose matrices; A generation module, configured to generate a dose distribution map corresponding to each target dose matrix according to each target dose matrix and a weight set for each beam spot, so as to obtain N dose distribution maps corresponding to the N target dose matrices.

10. The proton radiotherapy plan robust optimization device based on adaptive scenario according to claim 8 or 9, characterized in that, The proton radiotherapy plan robust optimization device based on adaptive scenario further includes: A sampling correction unit, configured to determine sampling correction information through the dose calculation engine according to the radiotherapy plan of the target object and the weight set for each beam spot; A dose adjustment unit, configured to adjust dose information of the N dose distribution maps according to the sampling correction information.

11. A proton radiotherapy plan robust optimization method based on adaptive sceneization, characterized in that, Comprising: Generating N robust scenario images based on the radiotherapy plan of the target object, wherein the N robust scenario images are used to simulate variation information of M regions of interest of the target object, and both N and M are integers greater than 1; Calculating a dose distribution map of each robust scenario image through a dose calculation engine, so as to obtain N dose distribution maps corresponding to the N robust scenario images; Determining a first dose distribution map and a second dose distribution map according to the N dose distribution maps, wherein the first dose distribution map is used to record the maximum dose value of the N dose distribution maps at each grid point, and the second dose distribution map is used to record the minimum dose value of the N dose distribution maps at each grid point, and each grid point corresponds to a beam spot in radiotherapy; Adjusting the radiotherapy plan according to the first dose distribution map and the second dose distribution map.

Images