BNCT treatment plan generation method and device based on barrier algorithm, medium and terminal

Abstract

The invention provides a BNCT treatment plan generation method and device based on a barrier algorithm, a medium and a terminal. The method comprises the following steps: acquiring a plurality of irradiation fields; respectively calculating dose distribution per unit time of each irradiation field; taking the irradiation time combination of the plurality of irradiation fields as a generation target, and determining an evaluation index and a constraint condition of the generation target; obtaining the generation target of the minimum value of the evaluation index under the limitation of the constraint condition based on a barrier algorithm so as to obtain an optimal irradiation time combination of the plurality of irradiation fields; and determining the irradiation time of each irradiation field based on the optimal irradiation time combination so as to generate a BNCT treatment plan based on the irradiation time of all the irradiation fields and the corresponding unit time dose distribution. According to the method and the device, the BNCT treatment plan with relatively high dose uniformity can be generated, the damage to surrounding healthy tissues can be reduced while sufficient radiation dose is ensured to be received, and the safety of radiotherapy is effectively improved.

Description

Technical Field

[0001] This application belongs to the field of radiation technology, and relates to a BNCT treatment plan generation method, device, medium and terminal based on a barrier algorithm. Background Art

[0002] BNCT (Boron Neutron Capture Therapy) is a precise radiotherapy that combines targeted drugs with neutron irradiation, which can selectively kill tumor cells and preserve normal cells. Compared with photon radiotherapy, BNCT effectively reduces the radiation to normal cells and reduces the side effects of radiotherapy. And photon radiotherapy usually requires the dose to be divided into multiple irradiations, with a long treatment cycle, while BNCT only needs 1-2 irradiations to reach the dose required to kill tumors. The treatment time is very friendly to patients and reduces the treatment burden of patients. Compared with other radiotherapy techniques, BNCT has obvious advantages in treatment time, accuracy and side effect control, and has broad application prospects.

[0003] In BNCT treatment, evaluation indicators are helpful for effectively evaluating the treatment of BNCT treatment plans. For example, when the dose uniformity is used as an evaluation indicator, this evaluation indicator is crucial for the radiotherapy effect, which may affect the tumor control rate and the side effects of radiotherapy. A uniform dose distribution helps to ensure complete elimination of tumors, reduce the risk of recurrence, and can reduce the high-dose areas in the patient's body, thereby reducing damage to normal tissues, such as side effects like dermatitis or urethral toxicity, and improving the safety of radiotherapy. This is very important in the treatment of breast cancer, prostate cancer and head and neck cancer. Therefore, how to efficiently obtain a BNCT treatment plan that meets the evaluation indicators is a technical problem that those skilled in the art urgently need to solve. Summary of the Invention

[0004] The purpose of this application is to provide a BNCT treatment plan generation method, device, storage medium and terminal based on a barrier algorithm, which is used to solve the technical problem of how to efficiently obtain a BNCT treatment plan that meets the evaluation indicators.

[0005] In a first aspect, this application provides a BNCT treatment plan generation method based on a barrier algorithm, and the method includes: Obtain multiple irradiation fields; Calculate the dose distribution per unit time of each of the irradiation fields respectively; Take the combination of the irradiation times of the multiple irradiation fields as a generation target, and determine the evaluation indicators and constraints of the generation target; Based on the barrier algorithm, obtain the generation target with the minimum value of the evaluation indicator under the limitation of the constraints, so as to obtain the optimal irradiation time combination of the multiple irradiation fields; Determine the irradiation time for each irradiation field based on the optimal irradiation time combination, so as to generate a BNCT treatment plan based on the irradiation times of all irradiation fields and the corresponding unit time dose distributions.

[0006] In an embodiment of the present application, the constraint conditions include tumor target area radiation constraints, critical organ radiation constraints, and irradiation time constraints: among them, the tumor target area radiation constraints and the critical organ radiation constraints are determined by the average radiation dose.

[0007] In an embodiment of the present application, obtaining the generation target with the minimum evaluation index value under the limitation of the constraint conditions based on the barrier algorithm includes: Obtain a generation model based on the barrier algorithm, where the generation model is used to obtain the generation target with the minimum value of the evaluation index that satisfies the constraint conditions; Iteratively solve the generation model until the solution approximation error is not less than a preset threshold, and obtain the optimal irradiation time combination of the multiple irradiation fields; Wherein, the preset threshold is the comparison result of the number of the constraint conditions and the hyperparameters of the barrier algorithm.

[0008] In an embodiment of the present application, the method further includes: When the solution approximation error is less than the preset threshold, update the hyperparameters of the barrier algorithm to update the preset threshold, and update the generation model based on the updated hyperparameters of the barrier algorithm to re-iteratively solve; wherein, use the comparison result of the hyperparameters of the barrier algorithm and the update parameters as the updated hyperparameters of the barrier algorithm.

[0009] In an embodiment of the present application, the method includes: if the generation model has no feasible solution, adjust the constraint conditions to re-obtain the generation model and continue to iteratively solve.

[0010] In an embodiment of the present application, generating a BNCT treatment plan based on the irradiation times of all irradiation fields and the corresponding unit time dose distributions includes: Obtain the minimum value of the tumor target area radiation and the maximum value of the critical organ radiation based on the irradiation times of all irradiation fields and the corresponding unit time dose distributions; Perform a generation judgment operation based on the minimum value of the tumor target area radiation and the maximum value of the critical organ radiation; When the generation judgment operation passes, generate a BNCT treatment plan based on the irradiation times of all irradiation fields and the corresponding unit time dose distributions; [[ID=3l]] When the generation judgment operation fails, adjust the constraint conditions to re-obtain the generation model and continue to iteratively solve.

[0011] In an embodiment of the present application, the generation judgment operation includes: judging whether the maximum value of the radiation of the organ at risk is less than the maximum tolerance dose. If not, the generation judgment operation fails; if so, continue to judge whether the minimum value of the radiation of the tumor target area is not less than the prescribed dose; If so, the generation judgment operation passes; if not, the generation judgment operation fails.

[0012] In a second aspect, the present application further provides a BNCT treatment plan generation device based on a barrier algorithm. The device includes: An acquisition module for acquiring a plurality of irradiation fields; A calculation module for respectively calculating the dose distribution per unit time of each of the irradiation fields; A target module for taking the irradiation time combination of the plurality of irradiation fields as a generation target, and determining the evaluation index and constraint conditions of the generation target; A search module for searching for the generation target with the minimum value of the evaluation index under the limitation of the constraint conditions based on the barrier algorithm to obtain the optimal irradiation time combination of the plurality of irradiation fields; A generation module for determining the irradiation time of each irradiation field based on the optimal irradiation time combination, so as to generate a BNCT treatment plan based on the irradiation times of all irradiation fields and the corresponding dose distribution per unit time.

[0013] In a third aspect, the present application further provides a storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the above-mentioned BNCT treatment plan generation method based on a barrier algorithm.

[0014] In a fourth aspect, the present application further provides a terminal, including a processor and a memory, which are communicatively connected between the memory and the processor; the memory is used for storing a computer program, and the processor is used for executing the computer program stored in the memory, so that the terminal executes the above-mentioned BNCT treatment plan generation method based on a barrier algorithm.

[0015] As described above, the BNCT treatment plan generation method, device, medium and terminal based on the barrier algorithm of the present application have the following beneficial effects: This application takes the combination of irradiation times of multiple irradiation fields as the generation target, sets evaluation indicators and constraint conditions, and thus obtains the generation target that meets the constraint conditions and the minimum value of the evaluation indicators, that is, the optimal irradiation time combination, and generates a BNCT treatment plan that meets the evaluation indicators based on this, improving the treatment effect and reducing the side effects of radiotherapy. At the same time, this application introduces the barrier algorithm into the BNCT treatment plan generation scenario, blocks the solutions that do not meet the constraints outside the barrier by obtaining the generation model, iteratively solves to quickly obtain the optimal irradiation time combination, and efficiently generates a BNCT treatment plan that meets the evaluation indicators based on this, so as to ensure that the tumor receives the prescribed dose while making the dose distribution as uniform as possible. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 FIG. shows a schematic diagram of the principle of BNCT treatment described in the embodiments of this application.

[0017] Figure 2 FIG. shows a schematic flowchart of the BNCT treatment plan generation method based on the barrier algorithm described in the embodiments of this application.

[0018] Figure 3 FIG. shows a schematic flowchart of the BNCT treatment plan generation method based on the barrier algorithm described in the embodiments of this application.

[0019] Figure 4 FIG. shows a schematic diagram of the images of logarithmic barrier functions with different hyperparameter values described in the embodiments of this application.

[0020] Figure 5 FIG. shows a schematic diagram of the process of obtaining the optimal solution of the generation model described in the embodiments of this application.

[0021] Figure 6 FIG. shows a schematic diagram of the logical judgment for generating a BNCT treatment plan described in the embodiments of this application.

[0022] Figure 7 FIG. shows a schematic structural diagram of the BNCT treatment plan generation device based on the barrier algorithm described in the embodiments of this application.

[0023] Figure 8 FIG. shows a schematic structural diagram of the terminal described in the embodiments of this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] The following describes the implementation modes of the present application through specific examples. Those skilled in the art can easily understand other advantages and effects of the present application from the content disclosed in this specification. The present application can also be implemented or applied through other different specific implementation modes. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that, without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0025] It should be noted that in the following description, reference is made to the accompanying drawings, which describe several embodiments of the present application. It should be understood that other embodiments can also be used, and mechanical composition, structure, electrical, and operational changes can be made without departing from the spirit and scope of the present application. The following detailed description should not be considered restrictive, and the scope of the embodiments of the present application is only defined by the claims of the published patent. The terms used herein are only for describing specific embodiments and are not intended to limit the present application. Spatially related terms, such as "upper", "lower", "left", "right", "below", "beneath", "lower part", "above", "upper part", etc., can be used in the text to facilitate the description of the relationship between one element or feature shown in the figure and another element or feature.

[0026] Furthermore, as used herein, the singular forms "a", "an", and "the" are also intended to include the plural forms unless the context indicates otherwise. It should be further understood that the terms "comprise", "include" indicate the presence of the described features, operations, elements, components, items, types, and / or groups, but do not exclude the presence, occurrence, or addition of one or more other features, operations, elements, components, items, types, and / or groups. The terms "or" and "and / or" used herein are interpreted as inclusive, or meaning either one or any combination.

[0027] BNCT is a targeted particle therapy method that selectively kills tumor cells and preserves normal cells. Its principle is shown in Figure 1. During the treatment process, first, a targeting drug carrying 10 B, such as BPA (Boronophenylalanine) or BSH (Sodium Borocaptate), is introduced into the patient's body by intravenous injection. At this time, the targeting drug will selectively accumulate in tumor cells. When the tumor cells accumulate a sufficient number of 10 B atoms, the tumor is irradiated with a beam of epithermal neutrons (0.5 eV < En < 10 keV) or thermal neutrons (En < 0.5 eV). The 10 B (n,α)7Li fission reaction in the tumor cells will produce α particles (4He) and recoil 7Li+ atomic nuclei. The reaction formula is shown in (1):

[0028] As can be seen from Equation (1), 10 After the target nucleus B absorbs neutrons, the excited compound nucleus ¹¹B is formed, and then it directly splits into lithium (Li) and helium nucleus (α particle), and de-excites by releasing γ rays. In fact, the linear energy transfer (LET) of α particles and 7 Li+ atomic nuclei is very high, 164 keV / μm and 151 keV / μm respectively, and the ranges of α particles and 7 Li+ atomic nuclei are very short, 9 μm and 5 μm respectively, which are smaller than the diameters of most cells (about 10 μm). This shows that the fission reaction occurring in tumor cells hardly affects the cells of surrounding tissues, and BNCT can kill tumor cells without accidentally injuring surrounding normal cells.

[0029] In the process of generating a BNCT treatment plan, the treatment of the treatment plan can be effectively evaluated by setting reasonable evaluation indicators. Therefore, how to efficiently generate a BNCT treatment plan that meets the evaluation indicators is a technical problem that needs to be solved urgently by those skilled in the art.

[0030] To at least solve the above technical problems, the embodiments of the present application provide a method, device, medium and terminal for generating a BNCT treatment plan based on a barrier algorithm, which can quickly generate a BNCT treatment plan that meets the evaluation indicators and improve the BNCT treatment effect.

[0031] Figure 2 The flow chart of the method for generating a BNCT treatment plan based on the barrier algorithm according to the embodiments of the present application is shown. As Figure 2 shown, the method for generating a BNCT treatment plan based on the barrier algorithm provided by the embodiments of the present application includes steps S1 to S5.

[0032] S1. Obtain a plurality of irradiation fields.

[0033] In some embodiments, after determining the tumor target area, the contour points of the tumor target area can be outlined through a DICOM-RT Struct file, and the arithmetic mean of the sums of these positions is used as the geometric center point A of the tumor target area. Then, the distance between the contour points of the skin outlined in the DICOM-RT Struct file and point A is calculated. The point with the smallest distance is used as the starting point, and the vector pointing to point A is the irradiation angle on the skin surface closest to the geometric center point A. Rotate this irradiation angle 360° around point A in the horizontal plane, and record any angle selected therefrom as the irradiation angle of an irradiation field, so that irradiation fields with multiple different irradiation angles can be selected.

[0034] Furthermore, since the irradiation field usually needs to be selected on the side where the skin is closer to the tumor and the treatment couch needs to be avoided, these unreasonable angles can be removed to obtain the final multiple irradiation fields.

[0035] S2. Calculate the dose distribution per unit time for each of the irradiation fields respectively.

[0036] In some embodiments, the dose distribution per unit time for each irradiation field can be simulated and calculated by the Monte Carlo method. For example, the DICOM-RT Image file obtained from CT scanning is converted into a voxel model that can be used for Monte Carlo calculation, and the corresponding boron concentration is added to the voxel model according to the organs outlined in the DICOM-RT Struct file to simulate the boron distribution in the patient's body after injection of BSA or BSH. Then, according to the multiple irradiation fields selected in step S1, the angles and positions of the corresponding sources are added to the input card to perform a Monte Carlo simulation calculation for each irradiation field per unit time, obtain the physical doses of different radiation components, and after the calculation is completed, the physical doses of different radiation components in each voxel grid are weighted and summed respectively according to RBE (Relative Biological Effectiveness) and CBE (Comparative Biological Effectiveness) to obtain the equivalent photon dose distribution, that is, the dose distribution per unit time for each irradiation field.

[0037] S3. Take the irradiation time combination of the multiple irradiation fields as the generation target, and determine the evaluation index and constraint conditions of the generation target.

[0038] In fact, this application generates a suitable BNCT treatment plan by determining the irradiation time of multiple irradiation fields. Therefore, the embodiments of this application take the irradiation time combination as the generation target and set evaluation indexes in order to generate a BNCT treatment plan that meets the evaluation indexes.

[0039] In fact, dose uniformity is one of the important indicators for evaluating the quality of treatment plans. A uniform dose distribution ensures that all regions within the gross tumor volume (GTV) receive sufficient radiation dose, thereby maximizing the tumor control probability (TCP). Increasing the radiation dose received by the GTV can improve its tumor control rate, and the uniform distribution of the dose is the basis for achieving this goal. At the same time, it can also reduce normal tissue damage. By restricting the high-dose region within the GTV, the radiation dose to the surrounding normal tissue can be minimized, thus reducing the side effects related to radiotherapy. That is, a good diagnosis and treatment plan needs to ensure that the target volume receives sufficient dose while reducing the radiation to normal tissues.

[0040] However, when using the BNCT technique for treatment, if the tumor is located deep, the neutron flux at the tumor site is low, and the total dose is consequently low. To ensure that all tumor cells can receive the prescribed dose, the irradiation time needs to be extended. If a single irradiation field is used, not only is the dose distribution within the tumor region very uneven, but the normal tissue between the tumor and the neutron source will also receive a high dose due to the increased irradiation time, which may lead to serious complications. If the number of irradiation fields is increased and the neutron beam is irradiated from different directions, more normal tissues can "share" the dose, reducing the maximum dose and average dose within the normal tissue and decreasing the probability of complications.

[0041] Therefore, in order to reduce the side effects of radiotherapy, it is necessary to improve the dose uniformity as much as possible. Thus, when the average dose of each voxel grid within the tumor target area is the same, a BNCT treatment plan with better dose uniformity can increase the minimum dose of the tumor target area, ensure that all voxel grids within the tumor target area receive sufficient radiation dose, and reduce the radiation to normal tissues, thereby better protecting the patient and reducing the probability of radiotherapy complications.

[0042] To this end, in some embodiments, the present application sets the evaluation index as the variance of the radiation dose of each voxel grid within the tumor target area, and improves the dose uniformity of the BNCT treatment plan by minimizing this evaluation index, so as to be able to reduce the side effects on normal tissues while ensuring the radiation dose of the tumor target area.

[0043] Among them, the evaluation index can be expressed by Equation (2):

[0044] Among them, is the number of voxel grids in the tumor target area; , representing the radiation dose / Gy transferred by all irradiation fields in the BNCT treatment plan to the i-th voxel grid within the tumor target area; n is the number of irradiation fields; Denoted as the dose rate delivered by the j-th irradiation field to the i-th voxel grid in the tumor target area / Gy·min -1 ; Denoted as the irradiation time of the j-th irradiation field / min; Denoted as the average radiation dose of the voxel grid in the tumor target area / Gy. By minimizing the variance of the radiation dose of each voxel grid in the tumor target area, the dose uniformity can be improved.

[0045] Furthermore, in the process of generating a BNCT treatment plan, it is necessary to achieve evaluation indicators and treatment effects while observing many treatment principles. For example, in order to kill all tumor cells to ensure the treatment effect, within the total irradiation time, all voxel grids in the tumor target area should receive the prescribed dose. Another example is that in order to protect critical organs and avoid the impact of excessive radiation dose on such organs, the maximum value of the radiation dose received by each critical organ should not be greater than the maximum tolerance dose. In addition, the treatment time also needs to be determined in advance to avoid the impact of too long treatment time on the patient's body. Therefore, in the process of obtaining a BNCT treatment plan that meets the evaluation indicators, it is also necessary to set constraint conditions to achieve the generation goal that meets various treatment principles and treatment effects.

[0046] In some embodiments, the present application sets tumor target area radiation constraints, critical organ radiation constraints, and irradiation time constraints as constraint conditions.

[0047] In some embodiments, the irradiation time constraint includes: the irradiation time constraint is that the sum of the irradiation times of all the irradiation fields should not be greater than a preset total irradiation time, and the irradiation time of each irradiation field should not be less than zero.

[0048] It should be noted that, since the BNCT treatment plan is actually a priori, while the tumor target area radiation and critical organ radiation are actually a posteriori. That is, only after generating the BNCT treatment plan can the specific dose distribution results be obtained based on the treatment plan. Therefore, the tumor target area radiation constraint and the critical organ radiation constraint are approximately determined by the average radiation dose.

[0049] In some embodiments, the tumor target area radiation constraint set by average dose approximation is: the minimum value of the average radiation dose of each voxel grid in the tumor target area under all the irradiation fields should not be less than the prescribed dose.

[0050] In some embodiments, the critical organ radiation constraint set by average dose approximation is: the average radiation dose of each critical organ under all the irradiation fields should not be greater than the maximum tolerance dose.

[0051] In some embodiments, the above-set constraint conditions are as shown in Equation (3):

[0052] wherein, represents the average dose rate vector of all voxel grids in the tumor target area under n different irradiation fields; represents the average dose rate / Gy·min of all voxel grids in the tumor target area under the j-th irradiation field -1 ; represents the irradiation time of the irradiation field; represents the prescribed dose / Gy; represents the average dose rate matrix of the irradiation field to the organs at risk; represents the average dose rate / Gy·min of the j-th irradiation field to the k-th organ at risk -1 ; represents the dose rate / Gy·min transferred by the j-th irradiation field to the i-th voxel grid in the k-th organ at risk -1 ; N represents the number of voxel grids of the organs at risk; t lim represents the upper limit of the total irradiation time of all irradiation fields / min; represents the maximum tolerable dose / Gy of the organs at risk.

[0053] In order to ensure that the dose can be accurately delivered to the tumor target area and the patient cannot move randomly during irradiation, the total irradiation time of the treatment plan cannot be set too long. In some embodiments, t lim is set to 60 min.

[0054] Furthermore, it should be noted that the above embodiments only illustrate one implementation manner of the constraint conditions. That is, in fact, the constraint conditions can be set according to the treatment objectives and actual situations. For example, the average dose of the tumor target area and the average dose of the organs at risk can be used as constraints, or the threshold value that the specific dose of a certain special organ at risk needs to reach can be used as a constraint, etc. The present application does not make any restrictions on this.

[0055] S4. Based on the barrier algorithm, obtain the generation target of the minimum value of the evaluation index under the limitation of the constraint conditions, so as to obtain the optimal irradiation time combination of the multiple irradiation fields.

[0056] As described above, the present application sets the evaluation index and the constraint conditions, thereby obtaining the generation target that satisfies both, and generating the BNCT treatment plan based on this. That is, in fact, the present application needs to solve an optimization problem with constraints. That is, under the limitation of the constraint conditions, the generation target of the minimum value of the evaluation index is the required optimal irradiation time combination. In the above embodiments, the optimal irradiation time combination should be able to achieve the optimal dose uniformity.

[0057] In this regard, the present application introduces a barrier algorithm to obtain the generation target of the minimum value of the evaluation index under the limitation of the constraint conditions. In some embodiments, the generation target of obtaining the minimum value of the evaluation index under the limitation of the constraint conditions based on the barrier algorithm can be expressed by Equation (4) as follows:

[0058] wherein, represents the irradiation time of j irradiation fields, that is, the irradiation time combination of the irradiation fields, ; is the evaluation index shown in Equation 2, that is, the objective function to be minimized; represents the w-th constraint condition, and there are m constraint conditions in total. For example, in the above embodiment, actually 4 constraint conditions are set in total.

[0059] Actually, due to the existence of inequality constraints in Equation (4), the gradient of the objective function cannot be directly calculated using the Newton method and iteratively solved. Therefore, in some embodiments, the present application introduces a logarithmic barrier algorithm to convert Equation (4) into an unconstrained approximate problem, and then uses the Newton method to solve and gradually approach the optimal solution, that is, to obtain the optimal irradiation time combination of multiple irradiation fields. Figure 3 shows a schematic flowchart of the BNCT treatment plan generation method based on the barrier algorithm according to the embodiment of the present application. As Figure 3 shown, obtaining the generation target with the minimum value of the evaluation index value under the limitation of the constraint conditions based on the barrier algorithm includes steps S41 to S42.

[0060] S41. Obtain a generation model based on the barrier algorithm, where the generation model is used to obtain the generation target of the minimum value of the evaluation index that satisfies the constraint conditions.

[0061] The barrier algorithm usually needs to meet the following several conditions:

[0062] (1) When within the domain of definition of the original problem of Equation (4), the value of the barrier function is small enough and basically does not affect the size of the objective function in Equation (4), and the deviation caused by the approximate conversion is minimized as much as possible. The size of, and the deviation caused by the approximate conversion is minimized as much as possible.

[0063] (2) When at the boundary or outside the domain of definition of the original problem of Equation (4), the value of the barrier function is large enough. When the solution iterated by the Newton method approaches the boundary of the domain of definition or goes outside the domain of definition, the value of the objective function will become very large, ensuring that the iteration is carried out within the domain of definition.

[0064] For this reason, in some embodiments, a logarithmic barrier function is used to obtain the generation model. Among them, the standard form of the logarithmic barrier function is shown in Equation (5):

[0065] Among them, \(t\) represents a hyperparameter of the barrier algorithm and \(t>0\).

[0066] Among them, the generation model obtained based on the barrier algorithm can be represented by Equation (6):

[0067] It can be seen that the generation model actually fuses the evaluation index of the generation target with the constraint conditions, converts the constraint conditions into a part of the whole, so as to convert Equation (4) with inequality constraints into Equation (6) without constraints, thereby realizing the solution of the generation model, and then the generation target with the minimum value of the evaluation index satisfying the constraint conditions can be obtained.

[0068] Furthermore, actually, the logarithmic barrier function images for different \(t\) values are shown in Figure 4. When \(t\) is relatively large (see the black curve in Figure 4 ), the value of the logarithmic barrier function within the domain is small enough and basically does not affect the original problem of Equation (4); while when \(t\) is relatively small (see the blue curve in Figure 4), the value of the logarithmic barrier function within the domain is larger, making the optimal solution of the approximately transformed Equation (6) far from the boundary of the domain, resulting in a deviation. Therefore, the \(t\) value will cause a deviation between the optimal solutions of Equation (6) and Equation (4), so it is necessary to continuously update \(t\) in the subsequent steps to be able to use the optimal solution of the generation model as the optimal solution of Equation (4).

[0069] S42. Iteratively solve the generation model until the solution approximation error is not less than the preset threshold, and obtain the optimal irradiation time combination of the multiple irradiation fields.

[0070] Among them, the preset threshold is the comparison result of the number of the constraint conditions and the hyperparameter of the barrier algorithm.

[0071] According to the Slater condition, if the objective function in Equation (4) is a convex function and has a strictly feasible solution, then the optimization problem has the strong duality property. If there is only one feasible solution instead of a strictly feasible solution, it indicates that Equation (4) has one and only one solution, and then there is no need to discuss its optimal solution and optimal value. In addition, if there is no feasible solution, it indicates that Equation (4) has no solution, and thus there is no optimal solution and optimal value. For the sake of clear representation, the case of no optimal solution in the following text refers to the case of no feasible solution.

[0072] Furthermore, if equation (4) has an optimal solution, it must satisfy the Karush-Kuhn-Tucker (KKT) conditions, which mainly include the following four parts:

[0073] (1) Stationarity. At the optimal solution, the derivative of the Lagrangian function of equation (4) is 0, indicating that it is an extreme value.

[0074] (2) Primal Feasibility. All the constraint conditions in equation (4) must be satisfied, and the inequality constraints require to be within their feasible regions.

[0075] (3) Dual Feasibility. The Lagrange multipliers of the inequality constraints of the Lagrangian function of equation (4) must be non-negative because the Lagrange multipliers are the solutions of the dual problem, and the dual problem variables are non-negative.

[0076] (4) Complementary Slackness. At , each inequality constraint is "tight" ( ) or "slack" ( ).

[0077] Then, due to the existence of inequality constraint conditions in equation (4), the KKT conditions satisfied by the optimal solution of equation (4) can be expressed by equation (7):

[0078] where, is the stationarity condition; is the primal feasibility condition; is the dual feasibility condition; is the complementary slackness condition.

[0079] Furthermore, the Lagrange dual function of the optimal solution of equation (4) is as shown in (8):

[0080] where, is the Lagrangian function of equation (4); is the solution of the dual problem of equation (4).

[0081] Similarly, if equation (6) has an optimal solution, it should also satisfy the KKT conditions, as shown in equation (9): ​​

[0082] Among them, is the optimal solution of Equation (6) at time t.

[0083] Then, due to Then, according to Equations (7) and (8), it can be obtained that is a feasible solution to the dual problem of Equation (4).

[0084] Then, when strong duality holds, the optimal solution and optimal value of Equation (4) are the same as those of the dual problem of Equation (4). Then, the dual gap of Equation (4) can be scaled to obtain Equation (10):

[0085] Then, combining Equation (8) gives Equation (11):

[0086] Equation (12) can be derived from Equation (11):

[0087] Then, let the solution approximation error be , and the preset threshold is set to , that is, the ratio of the number of constraint conditions m to the barrier algorithm hyperparameter t. If [[ID=3,3]] , according to (12), the optimal solution of Equation (6) at t can be considered as the optimal solution of Equation (4). Solving the optimal solution of Equation (6) through the Newton method, that is, the optimal solution of the generation model. At this time, this solution is actually the optimal irradiation time combination of multiple irradiation fields required by Equation (4). If , then at this time, t needs to be updated. The common method is to divide by the update parameter to increase t, and update the generation model based on the updated t to re-iteratively solve for the optimal solution. Then, compare and , until the condition is satisfied and the optimal solution is output. That is, when the solution approximation error is less than the preset threshold, update the barrier algorithm hyperparameter to update the preset threshold, and update the generation model based on the updated barrier algorithm hyperparameter to re-iteratively solve; where, the ratio result of the barrier algorithm hyperparameter to the update parameter is used as the updated barrier algorithm hyperparameter. Figure 5 Shows the process of obtaining the optimal solution of the generation model in the embodiments of the present application.

[0088] It should be noted that, as described above, there may be a situation where Equation (4) has no feasible solution, that is, there is no optimal solution. This means that the generation target for obtaining the minimum value of the evaluation index cannot be achieved based on the barrier algorithm under the limitations of the said constraint conditions. This indicates that the constraint conditions need to be readjusted to re-obtain the generation model and continue the iterative solution. In some embodiments, the fact that the generation target for obtaining the minimum value of the evaluation index cannot be achieved under the limitations of the said constraint conditions means that when the radiation constraint of the critical organ is satisfied, the radiation constraint of the tumor target area cannot be satisfied. Then, at this time, it is necessary to reduce the radiation constraint of the tumor target area and reset the radiation constraint of the critical organ to re-obtain the generation model, and perform iterative solution to obtain the optimal solution. Among them, resetting the radiation constraint of the critical organ is to restore the domain of definition reduced by the radiation constraint of the critical organ.

[0089] It should be noted that, in the optimal time combination obtained through the generation model, there may be a radiation field with an irradiation time of 0, which indicates that the radiation field at this angle is actually not needed.

[0090] S5. Determine the irradiation time of each radiation field based on the optimal irradiation time combination, so as to generate a BNCT treatment plan based on the irradiation times of all radiation fields and the corresponding unit-time dose distributions.

[0091] As described above, the BNCT treatment plan is a priori. Only after obtaining the optimal irradiation time combination, that is, obtaining the irradiation times of different radiation fields, can the dose distributions of the tumor target area and critical organs in the patient's body be calculated based on this. That is, based on the irradiation times of the multiple radiation fields and the corresponding unit-time dose distributions, the dose distribution of the patient is inversely deduced, and the dose distributions of the tumor target area and critical organs are statistically analyzed to determine whether it is necessary to re-generate the optimal solution, and then iterate repeatedly to obtain a good BNCT treatment plan.

[0092] In some embodiments, generating a BNCT treatment plan based on the irradiation times of all radiation fields and the corresponding unit-time dose distributions includes: obtaining the minimum value of the tumor target area radiation and the maximum value of the critical organ radiation based on the irradiation times of all radiation fields and the corresponding unit-time dose distributions; performing a generation judgment operation based on the minimum value of the tumor target area radiation and the maximum value of the critical organ radiation. When the generation judgment operation passes, a BNCT treatment plan is generated based on the irradiation times of all radiation fields and the corresponding unit-time dose distributions; when the generation judgment operation fails, the constraint conditions are adjusted to re-obtain the generation model and continue the iterative solution.

[0093] Among them, the generation judgment operation includes: judging whether the maximum value of the radiation of the organ at risk is less than the maximum tolerance dose; if not, the generation judgment operation fails; if so, continue to judge whether the minimum value of the radiation of the tumor target area is not less than the prescription dose; if so, the generation judgment operation passes; if not, the generation judgment operation fails.

[0094] Figure 6 It is shown as the schematic diagram of logical judgment for generating the BNCT treatment plan in the embodiment of the present application. As Figure 6 shown, judge whether there is an optimal solution. If there is, based on the irradiation time of the multiple irradiation fields and the corresponding dose distribution per unit time, obtain the minimum value of the radiation of the tumor target area and the maximum value of the radiation of the organ at risk. If not, reduce the radiation constraint of the tumor target area and reset the radiation constraint of the organ at risk to re-iterate and solve the generation model.

[0095] If there is an optimal solution, perform the generation judgment operation. First, judge whether the maximum value of the radiation of the organ at risk is less than the maximum tolerance dose. If it is not less than, the generation judgment operation fails. At this time, adjust the constraint conditions, that is, reduce the radiation constraint of the organ at risk to re-obtain the generation model and continue to iterate and solve. If it is less than the maximum tolerance dose, further judge whether the minimum value of the radiation of the tumor target area is not less than the prescription dose. If it is not less than the prescription dose, the generation judgment operation passes, and generate the BNCT treatment plan, that is, perform BNCT treatment according to the irradiation time of the currently determined multiple irradiation fields. If it is less than the prescription dose, adjust the constraint conditions. At this time, it is necessary to further judge whether the radiation constraint of the tumor target area has been reduced during the process of obtaining the optimal solution. If the radiation constraint of the tumor target area has been reduced, reduce the radiation constraint of the tumor target area again. If the radiation constraint of the tumor target area has not been reduced, increase the radiation constraint of the tumor target area.

[0096] It should be noted that in the above embodiment, reducing the radiation constraint of the tumor target area means reducing the prescription dose, and increasing the radiation constraint of the tumor target area means increasing the prescription dose. In addition, reducing the radiation constraint of the organ at risk means reducing the maximum tolerance dose, and increasing the radiation constraint of the organ at risk means increasing the maximum tolerance dose.

[0097] After obtaining the generation target of the minimum value of the evaluation index that meets the constraint conditions, that is, the optimal irradiation time combination, at this time, after neutron beam irradiation according to the irradiation time of the multiple irradiation fields, the dose distribution in the patient's body can obtain the optimal result in terms of the evaluation index.

[0098] Therefore, the BNCT treatment plan generation method based on the barrier algorithm provided by the embodiment of the present application can, while ensuring that the tumor receives sufficient radiation dose, minimize the harm to surrounding healthy tissues as much as possible, improve the treatment effect and reduce the side effects of radiotherapy.

[0099] The protection scope of the BNCT treatment plan generation method based on the barrier algorithm in the embodiments of the present application is not limited to the execution order of the steps listed in this embodiment. Any solution achieved by adding or subtracting steps of the prior art and replacing steps according to the principle of the present application is included in the protection scope of the present application.

[0100] The embodiments of the present application further provide a BNCT treatment plan generation device based on the barrier algorithm. The BNCT treatment plan generation device based on the barrier algorithm can implement the BNCT treatment plan generation method described in the present application. However, the implementation devices of the BNCT treatment plan generation device based on the barrier algorithm described in the present application include, but are not limited to, the structure of the BNCT treatment plan generation device based on the barrier algorithm listed in this embodiment. Any structural deformation and replacement of the prior art made according to the principle of the present application are included in the protection scope of the present application.

[0101] Figure 7 The structural schematic diagram of the BNCT treatment plan generation device based on the barrier algorithm described in the embodiments of the present application is shown as Figure 7 shown. The BNCT treatment plan generation device based on the barrier algorithm includes an acquisition module 41, a calculation module 42, a target module 43, a search 44, and a generation module 45. Among them, The acquisition module 41 is used to acquire a plurality of irradiation fields; The calculation module 42 is used to calculate the dose distribution per unit time of each of the irradiation fields respectively; The target module 43 is used to take the irradiation time combination of the plurality of irradiation fields as the generation target, and determine the evaluation index and constraint conditions of the generation target; The second calculation module 44 is used to search for the generation target with the minimum value of the evaluation index under the limitation of the constraint conditions based on the barrier algorithm, so as to obtain the optimal irradiation time combination of the plurality of irradiation fields; The generation module 45 is used to determine the irradiation time of each irradiation field based on the optimal irradiation time combination, so as to generate a BNCT treatment plan based on the irradiation time of all irradiation fields and the corresponding dose distribution per unit time.

[0102] It should be noted that the structures and principles of the acquisition module 41, the calculation module 42, the target module 43, the search module 44, and the generation module 45, as well as the beneficial effects obtained by this device, are the same as those in the above embodiments, and will not be elaborated herein.

[0103] The embodiments of the present application further provide a storage medium, on which a computer program is stored. The feature is that when the program is executed by a processor, all steps of the BNCT treatment plan generation method based on the barrier algorithm in the embodiment are implemented.

[0104] Among them, the specific steps of the BNCT treatment plan generation method based on the barrier algorithm and the beneficial effects obtained by using the readable storage medium provided in the embodiments of the present application are the same as those in the above embodiments, and will not be elaborated herein.

[0105] Those of ordinary skill in the art can understand that all or part of the steps in the methods of the above embodiments can be completed by instructing a processor through a program. The program can be stored in a computer-readable storage medium, and the storage medium is a non-transitory medium, such as random access memory, read-only memory, flash memory, hard disk, solid state drive, magnetic tape, floppy disk, optical disc, and any combination thereof. The above storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., digital video disc (DVD)), or a semiconductor medium (e.g., solid state disk (SSD)), etc.

[0106] The embodiments of the present application also provide a terminal. Figure 8 The structural schematic diagram of the terminal described in the embodiments of the present application is shown, as Figure 8 shown, the terminal 700 in the embodiments of the present application includes: at least one processor 701, a memory 702, at least one network interface 704, and a user interface 706. Moreover, the various components in the terminal 700 are coupled together through a bus system 705. It can be understood that the bus system 705 is used to realize the connection and communication between these components. In addition to including a data bus, the bus system 705 also includes a power bus, a control bus, and a status signal bus. However, for the sake of clarity, in Figure 7 all the various buses are labeled as the bus system. The user interface 706 may include a display, a keyboard, a mouse, a trackball, a click gun, a key, a button, a touchpad, or a touch screen, etc.

[0107] It can be understood that the memory 702 can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. This application does not specifically limit it. The memory 702 in the embodiments of this application is used to store various types of data to support the operation of the terminal 700. Examples of these data include: any executable programs for operating on the terminal 700, such as the operating system 7021 and the application program 7022; the operating system 7021 includes various system programs, such as the framework layer, the core library layer, the driver layer, etc., for implementing various basic services and processing hardware-based tasks. The application program 7022 can include various application programs, such as the MediaPlayer, the Browser, etc. Implementing the BNCT treatment plan generation method based on the barrier algorithm provided in the embodiments of this application can be included in the application program 7022.

[0108] The BNCT treatment plan generation method based on the barrier algorithm disclosed in the above embodiments of this application can be applied to the processor 701 or implemented by the processor 701. The processor 701 may be an integrated circuit chip with the ability to process signals. During the implementation process, each step of the above method can be completed by the integrated logic circuit in the hardware of the processor 701 or by instructions in the form of software. The above-mentioned processor 701 can be a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 701 can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor 701 can be a microprocessor or any conventional processor, etc.

[0109] In an exemplary embodiment, the terminal 700 can be an application-specific integrated circuit (ASIC), a DSP, a programmable logic device (PLD), or a complex programmable logic device (CPLD) for executing the foregoing method.

[0110] Those of ordinary skill in the art can understand that all or part of the steps for implementing the above method embodiments can be completed by hardware related to a computer program. The foregoing computer program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps including the above method embodiments; and the foregoing storage medium includes: various media such as ROM, RAM, magnetic disks, or optical discs that can store program codes.

[0111] The above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed in this application can easily think of changes or substitutions, which should all be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

[0112] The above embodiments are only illustrative of the principles and effects of the present application and are not intended to limit the present application. Any person familiar with this technology can modify or change the above embodiments without departing from the spirit and scope of the present application. Therefore, all equivalent modifications or changes made by those with ordinary knowledge in the technical field without departing from the spirit and technical idea disclosed in the present application should still be covered by the claims of the present application.

Claims

1. A BNCT treatment plan generation method based on a barrier algorithm, characterized in that The method includes: Obtaining a plurality of irradiation fields; Calculating the dose distribution per unit time of each of the irradiation fields respectively; Taking the irradiation time combination of the plurality of irradiation fields as a generation target, and determining the evaluation index and constraint conditions of the generation target; Based on the barrier algorithm, obtaining the generation target with the minimum value of the evaluation index under the limitation of the constraint conditions, so as to obtain the optimal irradiation time combination of the plurality of irradiation fields; Determining the irradiation time of each irradiation field based on the optimal irradiation time combination, so as to generate a BNCT treatment plan based on the irradiation time of all irradiation fields and the corresponding dose distribution per unit time.

2. The BNCT treatment plan generation method based on the barrier algorithm according to claim 1, wherein The constraint conditions include tumor target area radiation constraint, organ at risk radiation constraint and irradiation time constraint: among them, the tumor target area radiation constraint and the organ at risk radiation constraint are determined by the average radiation dose.

3. The BNCT treatment plan generation method based on the barrier algorithm according to claim 1, characterized in that Obtaining the generation target with the minimum value of the evaluation index value under the limitation of the constraint conditions based on the barrier algorithm includes: Obtaining a generation model based on the barrier algorithm, where the generation model is used to obtain the generation target with the minimum value of the evaluation index that satisfies the constraint conditions; Iteratively solving the generation model until the solution approximation error is not less than a preset threshold, and obtaining the optimal irradiation time combination of the plurality of irradiation fields; Wherein, the preset threshold is the comparison result of the number of the constraint conditions and the hyperparameters of the barrier algorithm.

4. The BNCT treatment plan generation method based on the barrier algorithm according to claim 3, wherein The method further includes: When the solution approximation error is less than the preset threshold, updating the hyperparameters of the barrier algorithm to update the preset threshold, and updating the generation model based on the updated hyperparameters of the barrier algorithm to re-iteratively solve; wherein, taking the comparison result of the hyperparameters of the barrier algorithm and the update parameters as the updated hyperparameters of the barrier algorithm.

5. The BNCT treatment plan generation method based on the barrier algorithm according to claim 3, characterized in that, The method includes: If the generation model has no feasible solution, adjusting the constraint conditions to re-obtain the generation model and continue to iteratively solve.

6. The BNCT treatment plan generation method based on the barrier algorithm according to claim 1, wherein, Generating a BNCT treatment plan based on the irradiation time of all irradiation fields and the corresponding dose distribution per unit time includes: Obtaining the minimum value of tumor target area radiation and the maximum value of organ at risk radiation based on the irradiation time of all irradiation fields and the corresponding dose distribution per unit time; Performing a generation judgment operation based on the minimum value of the tumor target area radiation and the maximum value of the organ at risk radiation; When the generation judgment operation passes, generating a BNCT treatment plan based on the irradiation time of all irradiation fields and the corresponding dose distribution per unit time; When the generation judgment operation fails, adjusting the constraint conditions to re-obtain the generation model and continue to iteratively solve.

7. The BNCT treatment plan generation method based on the barrier algorithm according to claim 6, wherein, The generation judgment operation includes: Judging whether the maximum value of the organ at risk radiation is less than the maximum tolerance dose, if not, the generation judgment operation fails; if so, continuing to judge whether the minimum value of the tumor target area radiation is not less than the prescription dose; If so, the generation judgment operation passes; if not, the generation judgment operation fails.

8. A BNCT treatment plan generation device based on a barrier algorithm, characterized in that, The device includes: An acquisition module, configured to acquire a plurality of irradiation fields; A calculation module, configured to calculate the dose distribution per unit time of each of the irradiation fields respectively; A target module, configured to use the irradiation time combinations of the multiple irradiation fields as a generation target, and determine an evaluation index and constraints for the generation target; A search module, configured to search for the generation target with the minimum value of the evaluation index under the limitation of the constraints based on a barrier algorithm, so as to obtain an optimal irradiation time combination of the multiple irradiation fields; A generation module, configured to determine the irradiation time of each irradiation field based on the optimal irradiation time combination, so as to generate a BNCT treatment plan based on the irradiation times of all irradiation fields and the corresponding unit time dose distributions; 9. A storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the program implements the BNCT treatment plan generation method based on a barrier algorithm according to any one of claims 1 to 7.

10. A terminal, characterized in that, It includes a processor and a memory, and the memory is communicatively connected to the processor; the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the terminal executes the BNCT treatment plan generation method based on a barrier algorithm according to any one of claims 1 to 7.

Images