Radiotherapy plan generation method, apparatus, and electronic device

Abstract

The present disclosure provides a radiotherapy plan generation method, comprising: obtaining object information of a target object, the object information at least comprising medical image information and a treatment target of the target object; calculating a field intensity distribution according to the object information, the field intensity distribution comprising a plurality of dose grids and beam information of a corresponding beam of each dose grid; obtaining an initial weight, the initial weight representing an initial radiation intensity coefficient of each beam, the initial weight being obtained according to a corresponding relative biological effect of each dose grid; taking the initial weight as a starting point of an inverse optimization problem, calculating a target radiation intensity coefficient corresponding to each beam; and generating a radiotherapy plan according to the target radiation intensity coefficient corresponding to each beam.

Description

Technical Field

[0001] This disclosure relates to the field of medical radiation, and more specifically, to a method, apparatus, and electronic device for generating radiotherapy plans. Background Technology

[0002] Radiotherapy is one of the main methods for treating malignant tumors, and intensity-modulated particle therapy (IMPT) is commonly used clinically. This technology modulates the intensity (i.e., weight) of thousands of pencil beams through inverse optimization to generate a highly conformal dose distribution that meets the lethal dose for tumors while maximizing the protection of surrounding organs at risk.

[0003] However, existing inverse optimization methods often use relatively simple physical dose considerations when starting iterative calculations. Inverse optimization usually requires handling a large number of variables and constraints, typically requiring high-performance computers and a lot of memory, and is very time-consuming. Moreover, the results of inverse optimization depend on the design of the objective function, and sometimes the objective function needs to be repeatedly adjusted to obtain the desired result. It has low computational accuracy, is time-consuming, and has a complex process. Summary of the Invention

[0004] In view of this, the present disclosure provides a method for generating a radiotherapy plan and an electronic device.

[0005] One aspect of this disclosure provides a radiotherapy plan generation method, comprising: acquiring object information of a target object, the object information including at least medical imaging information and treatment target of the target object; calculating a radiation field intensity distribution based on the object information, the radiation field intensity distribution including multiple dose grids and beam information of the corresponding beams for each dose grid; acquiring initial weights, the initial weights characterizing the initial radiation intensity coefficients of each beam, the initial weights being obtained based on the relative biological effects corresponding to each dose grid; using the initial weights as the starting point of an inverse optimization problem, calculating the target radiation intensity coefficients corresponding to each beam; and generating a radiotherapy plan based on the target radiation intensity coefficients corresponding to each beam.

[0006] According to embodiments of this disclosure, obtaining initial weights includes: constructing an initial optimization problem based on the target dose values ​​of at least some dose grids in each dose grid; adjusting the initial optimization problem based on the relative biological effects corresponding to the dose grids to obtain a target optimization problem; and solving the initial optimization problem to obtain initial weights.

[0007] According to embodiments of this disclosure, the radiotherapy planning generation method further includes: classifying each dose grid; selecting a target dose grid in each class of dose grids; and constructing an initial optimization problem based on the target dose values ​​of at least some dose grids in each dose grid, including: constructing an initial optimization problem based on the target dose values ​​of each target dose grid.

[0008] According to embodiments of this disclosure, constructing an initial optimization problem includes: using the target dose value corresponding to the dose grid as the optimization objective of the initial optimization problem, and using the radiation intensity coefficient corresponding to each beam as the solution objective to construct the initial optimization problem; adjusting the initial optimization problem includes: obtaining a relative biological effect correction factor based on the relative biological effect corresponding to each target dose grid; and weighting the target dose value in the initial optimization problem based on the relative biological effect to obtain the target optimization problem.

[0009] According to embodiments of this disclosure, the radiotherapy planning method further includes: calculating the dose distribution of each beam based on initial weights; adding dose grids where the error between the dose distribution and the target dose value is greater than an error threshold to the target dose grid, and updating the initial optimization problem; and recalculating the initial weights based on the updated initial optimization problem.

[0010] According to embodiments of this disclosure, the radiotherapy planning method further includes: calculating the dose distribution of each beam based on initial weights; updating the relative biological effect correction factor based on the dose distribution; updating the initial optimization problem based on the updated relative biological effect correction factor; and recalculating the initial weights based on the updated initial optimization problem.

[0011] According to embodiments of this disclosure, the initial weights are recalculated based on the updated initial optimization problem, and then the method further includes updating the initial weights again based on the initial weights before recalculation and the initial weights after recalculation.

[0012] According to embodiments of this disclosure, solving an initial optimization problem to obtain initial weights includes: solving an initial optimization problem based on a calculation method for solving a system of linear equations to obtain initial weights.

[0013] Another aspect of this disclosure provides a radiotherapy planning device, comprising: a first acquisition module for acquiring object information of a target object, the object information including at least medical image information of the target object and a treatment target; a first calculation module for calculating a radiation field intensity distribution based on the object information, the radiation field intensity distribution including multiple dose grids and beam information of the corresponding beams for each dose grid; a second acquisition module for acquiring initial weights, the initial weights characterizing the initial radiation intensity coefficients of each beam, the initial weights being obtained based on the relative biological effects corresponding to each dose grid; a second calculation module for calculating the target radiation intensity coefficients corresponding to each beam using the initial weights as the starting point of an inverse optimization problem; and a first generation module for generating a radiotherapy plan based on the target radiation intensity coefficients corresponding to each beam.

[0014] Another aspect of this disclosure provides an electronic device including: at least one processor; and a memory connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the radiotherapy planning generation method of any of the foregoing embodiments.

[0015] Another aspect of this disclosure provides a computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to perform a radiotherapy planning method according to any of the foregoing embodiments.

[0016] Another aspect of this disclosure provides a computer program product, including a computer program / instructions, characterized in that the computer program / instructions, when executed by a processor, implement the operation of the radiotherapy planning generation method of any of the foregoing embodiments. Attached Figure Description

[0017] The above and other objects, features and advantages of this disclosure will become clearer from the following description of embodiments with reference to the accompanying drawings, in which:

[0018] Figure 1 A flowchart illustrating a radiotherapy plan generation method according to an embodiment of the present disclosure is shown schematically.

[0019] Figure 2 A flowchart illustrating the process of obtaining initial weights in a radiotherapy planning generation method according to an embodiment of the present disclosure is shown schematically.

[0020] Figure 3 This schematically illustrates another flowchart of the radiotherapy planning generation method for obtaining initial weights according to an embodiment of the present disclosure;

[0021] Figure 4 This schematically illustrates another flowchart of the radiotherapy planning generation method for obtaining initial weights according to an embodiment of the present disclosure;

[0022] Figure 5 This schematically illustrates another flowchart of obtaining initial weights in a radiotherapy planning generation method according to an embodiment of the present disclosure;

[0023] Figure 6 This schematically illustrates another flowchart of the radiotherapy planning generation method for obtaining initial weights according to an embodiment of the present disclosure;

[0024] Figure 7 This schematically illustrates another flowchart of the radiotherapy planning generation method for obtaining initial weights according to an embodiment of the present disclosure;

[0025] Figure 8 This schematically illustrates another flowchart of the radiotherapy planning generation method for obtaining initial weights according to an embodiment of the present disclosure;

[0026] Figure 9 A block diagram of a radiotherapy planning generation apparatus according to an embodiment of the present disclosure is illustrated schematically; and

[0027] Figure 10 A block diagram of an electronic device suitable for implementing the methods described above, according to embodiments of the present disclosure, is illustrated schematically. Detailed Implementation

[0028] The embodiments of the present disclosure will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the disclosure. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of the present disclosure for ease of explanation. However, it will be apparent that one or more embodiments may be practiced without these specific details. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concepts of the present disclosure.

[0029] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0030] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0031] When using expressions such as "at least one of A, B and C", they should generally be interpreted in accordance with the meaning that is commonly understood by those skilled in the art (e.g., "a system having at least one of A, B and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B and C, etc.).

[0032] In the embodiments disclosed herein, the collection, updating, analysis, processing, use, transmission, provision, disclosure, and storage of data (e.g., including but not limited to user personal information) comply with relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. In particular, necessary measures have been taken to prevent unauthorized access to user personal information data and to safeguard user personal information security, network security, and national security.

[0033] This disclosure provides a radiotherapy plan generation method, comprising: based on object information of a target object, the object information including at least medical imaging information and treatment target of the target object; calculating a radiation field intensity distribution based on the object information, the radiation field intensity distribution including multiple dose grids and beam information of the corresponding beams for each dose grid; obtaining initial weights, the initial weights characterizing the initial radiation intensity coefficients of each beam, the initial weights being obtained based on the relative biological effects corresponding to each dose grid; using the initial weights as the starting point of an inverse optimization problem, calculating the target radiation intensity coefficients corresponding to each beam; and generating a radiotherapy plan based on the target radiation intensity coefficients corresponding to each beam.

[0034] Figure 1 A flowchart illustrating a radiotherapy planning method according to an embodiment of the present disclosure is shown schematically.

[0035] like Figure 1 As shown, the radiotherapy planning generation method may include at least operations S110 to S150.

[0036] In operation S110, object information of the target object is acquired. This object information includes at least the target object's medical imaging information and treatment goals. The target object's object information refers to the complete set of data related to the individual to be treated with radiotherapy, used to develop a personalized treatment plan. Medical imaging information provides details of the target object's internal anatomical structures, while the treatment goals define the dosimetric outcomes expected for these anatomical structures. Clinical data related to the individual to be treated is also acquired. Medical imaging information is used to determine anatomical structures, such as the geometry and shape of the tumor target area and organs at risk. Treatment goals specify the dosimetric parameters expected for each anatomical structure, such as the minimum dose to be achieved at the target area and the maximum dose limit that organs at risk can tolerate.

[0037] For example, the target is a patient with a brain tumor, the medical imaging information is the patient's computed tomography (CT) image data, and the treatment goal is to apply a bioequivalent dose of 60 grays to the tumor area marked in the image data.

[0038] In operation S120, the radiation field intensity distribution is calculated based on the object information. The radiation field intensity distribution includes multiple dose grids and the beam information corresponding to each dose grid. The radiation field intensity distribution is a mathematical model describing the dose deposition relationship between basic radiation units (beams) and spatial discrete units (dose grids).

[0039] Calculating the intensity distribution of the radiation field involves, for example, constructing a dose influence matrix based on the physical model of the beam and the medical image information of the target object. Each element of this matrix represents the physical dose value deposited by a specific beam of unit intensity at a specific spatial location (i.e., a dose grid). Beam information may include parameters such as the beam's position, direction, and energy.

[0040] For example, the physical dose deposition produced by each of a series of proton pencil beams incident from a specific angle within each grid cell of a three-dimensional dose grid matrix divided from patient CT image data is calculated. This ultimately forms a field intensity distribution matrix describing the dose contribution of all beams to all grid cells.

[0041] In operation S130, initial weights are obtained. These initial weights characterize the initial radiation intensity coefficients of each beam and are derived based on the relative biological effects corresponding to each dose grid. The initial weights provide a biologically meaningful initial solution for the subsequent inverse optimization process. These initial weights are not randomly set or uniformly assigned, but are pre-calculated considering the mechanism of the relative biological effects of proton or heavy ion beams at different tissue locations.

[0042] For example, in proton radiotherapy, it is known that the relative biological effect is higher in the terminal region of the beam with a high linear energy transfer (LET) value. Based on this prior knowledge, and combined with the positional information of each dose grid, a set of initial weights is generated, such that beams that can project high LET regions into the tumor target area are assigned relatively high initial weight values, while beams that mainly affect normal tissues are assigned lower initial weight values.

[0043] In operation S140, the initial weights are used as the starting point for the inverse optimization problem to calculate the target radiation intensity coefficients corresponding to each beam.

[0044] The initial weights are used as input to the optimization algorithm to initiate an iterative optimization process. This process adjusts the radiation intensity coefficients of each beam according to a preset objective function that describes the difference between the desired dose distribution (i.e., the target dose value corresponding to each dose grid) and the actual dose distribution, in order to minimize this difference, and finally determines a set of radiation intensity coefficient combinations that meet clinical requirements.

[0045] For example, gradient descent can be used for inverse optimization. Initial weights are loaded as the initial values ​​of the optimization variables. The gradient between the current dose distribution and the prescribed dose is calculated according to the objective function, and the weights are updated in the reverse direction of the gradient. Since the initial weights already have good biological guidance, the optimization process can more quickly approach or reach a better solution, which is the target radiation intensity coefficient.

[0046] During operation S150, a radiotherapy plan is generated based on the target radiation intensity coefficients corresponding to each beam. The calculated target radiation intensity coefficients are then converted into a set of instructions executable by the treatment device, forming a complete treatment plan that can be implemented clinically.

[0047] For example, the target radiation intensity coefficient of each beam is converted into the corresponding machine unit or particle number, and combined with information such as the position and energy of the beam, a treatment plan file that conforms to the communication protocol of a specific treatment device is generated.

[0048] According to embodiments of this disclosure, by introducing consideration of relative biological effects at the initial weight acquisition stage, the starting point of the inverse optimization process is no longer a blind guess at the physical dose level, but rather a preliminary solution guided by biological effects. This guides subsequent complex optimization processes towards searching a biologically superior solution space, thereby increasing the likelihood of avoiding local optima that only satisfy physical dose constraints but have poor biological effects. The method provided by embodiments of this disclosure can improve the biological conformity of the final generated radiotherapy plan without increasing the complexity of subsequent optimization algorithms. That is, while effectively killing tumor cells, it better protects surrounding normal tissues, improving the precision and effectiveness of treatment.

[0049] Figure 2 A flowchart illustrating the process of obtaining initial weights in a radiotherapy planning method according to an embodiment of the present disclosure is shown.

[0050] like Figure 2 As shown, based on the aforementioned embodiments, operation S130 may include operations S210 to S230.

[0051] In operation S210, an initial optimization problem is constructed based on the target dose values ​​of at least some dose grids in each dose grid. An optimization problem is a mathematical problem that, under a series of constraints, seeks a set of variable values ​​to achieve the optimal value (e.g., minimum or maximum) of one or more predefined objective functions. In embodiments of this disclosure, the variables to be solved are typically the radiation intensity coefficients of each beam, the objective function is used to quantify the difference between the calculated dose distribution and the dose distribution required by the prescription, and the constraints include, for example, dose limits for organs at risk.

[0052] The initial optimization problem is a simplified mathematical model designed for rapid solution. Operation S210 can be understood as selecting a subset from the entire dose grid and using the target dose values ​​corresponding to that subset to construct a smaller initial optimization problem.

[0053] For example, from tens of thousands of dose grids, only a few hundred key dose grids located at the center of the tumor target area, the edge of the target area, and the boundary of adjacent organs at risk are selected. The prescription dose values ​​of these key grids are used as optimization targets to construct a simplified set of equations with the beam weight as the unknown.

[0054] In operation S220, based on the relative biological effects corresponding to the dose grid, the initial optimization problem is adjusted to obtain the objective optimization problem. The relationship based on physical dose in the initial optimization problem is transformed into a relationship based on biological equivalent dose. The mathematical expression in the initial optimization problem is transformed so that its solution objective changes from matching physical dose to matching biological equivalent dose. This transformation is based on the estimated relative biological effect values ​​at each dose grid point.

[0055] For example, for each dose grid selected for the initial optimization problem, a relative biological effect value is estimated based on the linear energy transfer spectrum at its location. Subsequently, the corresponding rows of the dose influence matrix describing the relationship between beam weight and physical dose in the initial optimization problem are modified to reflect the influence of the relative biological effect, thus forming a new objective optimization problem aimed at solving for the biological equivalent dose.

[0056] In operation S230, the initial optimization problem is solved to obtain the initial weights. The aforementioned objective optimization problem is solved to obtain a set of initial weight values. Since this objective optimization problem is a simplified, low-dimensional problem, its solution process can obtain a deterministic or near-optimal solution, providing a high-quality starting point for subsequent full-dimensional optimization.

[0057] For example, the mathematical relationship corresponding to the target optimization problem—namely, the corrected dose influence matrix and the target dose vector of the representative grid—is input into a solver. The solver performs the calculation and outputs a set of beam weights that enable the calculated dose to best match the target dose on the selected representative grid; this set of weights is the initial weights obtained.

[0058] According to embodiments of this disclosure, by selecting a portion of the dose grid to construct the initial optimization problem, the dimensionality of the problem solution is effectively reduced, resulting in a significant improvement in computational efficiency. Furthermore, this simplified problem is adjusted based on relative biological effects, ensuring that the calculated initial weights are not only obtained quickly but also have biological significance. This allows the initial weights to be preliminarily aligned with the treatment target at the biological effect level, maintaining computational speed while providing a higher-quality starting point closer to the final ideal solution for subsequent fine-tuning processes. This improves the efficiency of the entire radiotherapy planning process and the quality of the final plan.

[0059] Figure 3 Another flowchart illustrating the method for obtaining initial weights in a radiotherapy planning generation method according to an embodiment of the present disclosure is shown.

[0060] like Figure 3 As shown, based on the foregoing embodiments, the radiotherapy planning generation method may include operations S310-S320. Operation S210 may include operation S330.

[0061] In operation S310, each dose grid is classified. All dose grids are grouped according to the characteristics of their received dose contribution. A feasible classification criterion is based on the beam that exerts the dominant dose contribution on each dose grid. First, each dose grid is analyzed to identify all beams that produce dose deposition on it; second, the dose contribution values ​​of these beams to the dose grid are compared, and the dose grid is classified into the category corresponding to the beam with the largest contribution value.

[0062] For example, suppose the unit weighted dose contribution of beam j to dose grid i is D(i, j). For dose grid i1, calculate the contributions of all beams to it: D(i1, 1), D(i1, 2), ..., D(i1, N). If D(i1, k) is found to be the maximum value, then dose grid i1 is assigned to the category C corresponding to beam k. k This process is repeated for all dose grids, and eventually each dose grid is assigned to a unique category.

[0063] In operation S320, a target dose grid is selected for each dose grid class. The target dose grid is one or more grids representing all dose grids in its class, used to construct the initial optimization problem after dimensionality reduction.

[0064] When extracting a representative target dose grid from each category, there are several possible methods. One method is to select the dose grid that contributes the most to the dominant beam dose received in that category as the target dose grid. Another method is to mathematically average the field intensity distribution information of all dose grids within a category and use the virtual grid represented by this average as the target dose grid. Yet another method is to randomly select a dose grid from the category as the target dose grid according to a preset probability distribution.

[0065] For example, in category C k The system includes dose grids i1, i2, and i3. If the dose contribution of beam k to these three grids is 10, 8, and 9 units respectively, then grid i1 with a dose contribution of 10 units can be selected as the target dose grid for this category.

[0066] In operation S330, an initial optimization problem is constructed based on the target dose values ​​of each target dose grid. The representative vectors of the field intensity distribution determined for each class in the preceding operations are combined to form a dimension-reduced field intensity distribution matrix. Specifically, the representative vectors f1, f2, ..., f... C Stacked row by row, they form a reduced-dimensional matrix with the number of rows equal to the total number of categories C and the number of columns equal to the total number of beams N, denoted as A. phy It can be represented in the following form:

[0067]

[0068] For example, concatenating C representative vectors into a dimension-reduced field intensity distribution matrix A phy Simultaneously, the target dose value corresponding to each representative vector is obtained to form the target dose vector. target The initial optimization problem can be constructed as a system of linear equations with the beam weight vector (weight) to be solved as the unknown: A phy *weight=dose target .

[0069] According to embodiments of this disclosure, a physically meaningful and structured dimensionality reduction is achieved by classifying the dose grid according to the dominant influence of the beams and calculating a representative dose influence vector for each class. This dimensionality reduction method not only significantly reduces the number of constraints involved in constructing the initial optimization problem, but also ensures that the dimensionality-reduced model can faithfully summarize the core dose deposition characteristics of each beam cluster in the original high-dimensional problem through the generation of representative vectors (e.g., averaging or selecting extrema). Therefore, the constructed initial optimization problem is an efficient and robust approximation of the original problem, and its solution can provide a more accurate and effective starting point for subsequent optimizations, thereby improving optimization efficiency and the quality of the final plan.

[0070] Figure 4 Another flowchart illustrating the method for obtaining initial weights in a radiotherapy planning generation method according to an embodiment of the present disclosure is shown.

[0071] like Figure 4 As shown, based on the aforementioned embodiments, operation S210 may include operation S410, and operation S220 may include S420~S430.

[0072] In operation S410, the target dose value corresponding to the dose grid is used as the optimization objective of the initial optimization problem, and the radiation intensity coefficient corresponding to each beam is used as the solution objective to construct the initial optimization problem. For example, the reduced field intensity distribution matrix is ​​denoted as A. phy The element in the c-th row and j-th column represents the unit-weighted physical dose contribution of the j-th beam to the c-th target dose grid. The radiation intensity coefficients of each beam to be solved are formed into a column vector `weight`. The prescription target dose values ​​corresponding to each target dose grid are formed into a column vector `dose`. target At this point, the initial optimization problem can be expressed as a linear system as follows: A phy *weight=dose target .

[0073] In operation S420, a relative biological effect correction factor is obtained based on the relative biological effect corresponding to each target dose grid. The relative biological effect correction factor is a dimensionless parameter used to quantify the difference in physical dose required by proton or heavy ion beams compared to conventional photon radiotherapy to produce the same biological endpoint event; it is a correction coefficient representing the strength of the biological effect. An initial relative biological effect correction factor is determined for each target dose grid. This determination can be based on prior information such as the grid's location in the anatomical structure, the type and energy of the irradiated particles, and the corresponding linear energy transfer (LET) spectrum, or it can be calculated by consulting standard databases or using simplified biophysical models.

[0074] In operation S430, the target dose value in the initial optimization problem is weighted based on relative biological effects to obtain the target optimization problem. This transforms the initial optimization problem from the physical dose domain to the biological equivalent dose domain. Here, "weighting" refers to adjusting the mathematical relationships describing dose contributions in the initial optimization problem using a relative biological effect correction factor, so that the optimization objective directly points to the biological effect.

[0075] Specifically, for the reduced-dimensional field intensity distribution matrix A in the initial optimization problem... phy Each row is multiplied by the relative biological effect correction factor of the target dose grid corresponding to that row. After this operation, each element of the matrix is ​​transformed from representing the physical dose contribution per unit weight to representing the biological equivalent dose contribution per unit weight, thus yielding the objective optimization problem.

[0076] For example, construct a diagonal matrix diag(rbe_factor) from the relative biological effect correction factors (rbe_factor) of all target dose grids. Multiply this diagonal matrix on the left by matrix A in the initial optimization problem. phy The corrected dose influence matrix A is obtained. rbe =diag(rbe_factor)*A phy The objective optimization problem is now updated to: A rbe *weight=dose target The physical meaning of this equation is to find a set of weights such that the resulting bioequivalent dose is equal to the prescribed target dose.

[0077] According to embodiments of this disclosure, by systematically converting the physical dose model into a biologically equivalent dose model during the initial optimization problem construction phase, the biological relevance of the initial weight solution process is ensured. Compared to methods that only construct simplified problems at the physical dose level, this approach allows the solved initial weights to naturally tend towards a distribution with better biological effects, rather than simply a matching of physical doses. This provides a more biologically advantageous starting point for subsequent full-dimensional inverse optimization, contributing to better achieving efficient tumor killing and effective protection of normal tissues in the final optimization results.

[0078] Figure 5 Another flowchart illustrating the process of obtaining initial weights in a radiotherapy planning method according to an embodiment of the present disclosure is shown.

[0079] like Figure 5 As shown, based on the aforementioned embodiments, the radiotherapy plan generation method may include operations S510~S530.

[0080] In operation S510, the dose distribution of each beam is calculated based on the initial weights. Using the initial weights obtained in the preceding steps, a forward calculation is performed to obtain the complete dose distribution across all dose grids. This calculation uses the undimension-reduced, original field intensity distribution matrix, which is multiplied by the initial weight vector, resulting in a dose vector containing the predicted dose values ​​for each dose grid within the treatment area.

[0081] For example, the original, complete field intensity distribution matrix is ​​denoted as A. full The initial weight vector obtained is denoted as weight0. The complete dose distribution (Dose) is calculated. calc =A full *weight0.

[0082] In operation S520, dose grids with errors greater than a threshold between the dose distribution and the target dose value are added to the target dose grid, updating the initial optimization problem. The error threshold is a preset value used to determine whether the dose deviation is significant. The complete dose distribution calculated in the previous step is compared with the dose distribution required by the prescription at each grid point, identifying dose grids with absolute dose deviations exceeding the preset error threshold. Subsequently, these newly identified dose grids are added to the target dose grid set used to construct the initial optimization problem, and the dimensionality-reduced field intensity distribution matrix and target dose vector are updated accordingly, thus forming a new, expanded, and corrected initial optimization problem.

[0083] For example, set the error threshold to 3% of the prescribed dose. For all dose grids i, calculate the dose error |Dose|. calc(i) -dose target(i) | If dose grid i is found new1 and i new2 If the error exceeds the threshold, then these two grids are added to the target dose grid set. Simultaneously, from the original field intensity distribution matrix A... full Extract i new1 and i new2 The corresponding row vectors are appended to the end of the reduced field intensity distribution matrix to form the updated matrix A. compressed_update .

[0084] In operating S530, the initial weights are recalculated based on the updated initial optimization problem. The updated initial optimization problem, with increased dimensionality, is solved to obtain a new set of optimized initial weights. This solution process can maintain the same methodology as the previous initial weight solution, but it solves for an expanded and modified mathematical model.

[0085] According to embodiments of this disclosure, by introducing an iterative correction mechanism, this method can proactively identify and compensate for the accuracy loss caused by the initial simplified model. After obtaining the initial weights, its effectiveness across the entire treatment area is verified through a full dose distribution calculation, and the "weakest link" regions with the largest dose deviations are precisely located. The dose grids of these "weakest link" regions are then specifically added to the initial optimization problem, which is equivalent to a targeted correction of the simplified model.

[0086] Figure 6 Another flowchart illustrating the radiotherapy planning generation method for obtaining initial weights according to an embodiment of the present disclosure is shown.

[0087] like Figure 6 As shown, based on the aforementioned embodiments, the radiotherapy plan generation method may include operations S610~S640.

[0088] In operation S610, the dose distribution of each beam is calculated based on the initial weights. This operation is similar to the aforementioned operation S510 and will not be described in detail here.

[0089] In operation S620, the relative biological effect correction factor is updated based on the dose distribution. The value of the relative biological effect correction factor is related not only to physical parameters such as particle type and energy, but also to the magnitude of the physical dose received by each dose grid. This step uses the dose distribution calculated in the previous step to iteratively update the previously estimated relative biological effect correction factor to obtain a more accurate assessment of the biological effect at the current dose level.

[0090] For example, for a target dose grid i, its initial correction factor rbe_factor 0(i) This is based on empirical or simplified model estimates. Now, let's calculate the actual physical dose (Dose) from this grid. calc(i) As input, this is substituted into a more accurate biophysical model that considers dose dependence, to calculate a new, updated correction factor, rbe_factor. 1(i) Perform this update operation on all target dose grids.

[0091] In operation S630, the initial optimization problem is updated based on the updated relative biological effect correction factor. The previously constructed objective optimization problem used to solve the initial weights is revised using the updated relative biological effect correction factor, so that the mathematical model of the optimization problem can more accurately reflect the biological effects under the current dose distribution.

[0092] For example, the updated correction factors rbe_factor1 for all target dose grids are used to construct a new diagonal matrix diag(rbe_factor1). This new matrix replaces the old matrix in the original objective optimization problem, resulting in an updated dose influence matrix A. rbe_update =diag(rbe_factor1)*A phy The initial optimization issues were subsequently updated.

[0093] When operating the S640, the initial weights are recalculated based on the updated initial optimization problem. The updated initial optimization problem, which is more accurate for the biological model, is solved to obtain a new set of optimized initial weights.

[0094] According to embodiments of this disclosure, by introducing iterative updates to the relative biological effect correction factor, a feedback loop between physical dose and biological effect is established, correcting the limitations of the initial RBE estimation. This makes the calculation of initial weights no longer a static, unidirectional process, but a dynamic, self-improving one. This method of iteratively optimizing the biological model during the simplified model solution stage can significantly improve the accuracy of the initial weights in a biological sense, thus providing a high-quality starting point for subsequent full-dimensional inverse optimization and helping the final plan converge more quickly to a solution with better biological effects.

[0095] Figure 7 Another flowchart illustrating the radiotherapy planning generation method for obtaining initial weights according to an embodiment of the present disclosure is shown.

[0096] like Figure 7 As shown, based on the aforementioned embodiments, operation S640 may include operation S710.

[0097] In operation S710, the initial weights are updated again based on the initial weights before and after recalculation. This update is an incremental correction, not a simple replacement. The initial weights before recalculation are considered a baseline solution, and the recalculation process aims to find a weight increment to correct this baseline solution. The final updated initial weights are the vector sum of the baseline solution and the weight increment.

[0098] Specifically, the deviation between the dose distribution and the prescribed target dose caused by the initial weights (e.g., weight0) before recalculation is considered. residual The new optimization objective is to construct and solve a new initial optimization problem, where the objective is no longer the complete weights, but the weight residuals that produce the dose bias. residualAfter solving the problem and obtaining the weight residuals, add them to the initial weights before recalculation to obtain the final updated initial weights.

[0099] For example, the initial weight before recalculation is denoted as weight0. The dose deviation is calculated based on weight0. residual Construct a new optimization problem, such as A compressed_update weight residual =dose residual And solve for the weight residuals. residual Finally, the updated initial weights are calculated as weight = weight0 + weight residual This weight will serve as a better starting point for subsequent full-dimensional reverse optimization.

[0100] According to embodiments of this disclosure, by updating the initial weights using an incremental correction method, this method achieves stable and efficient iterative optimization of the initial solution. This method retains the reasonable parts already existing in the previous calculation (reflected in weight0) and performs targeted correction (solving for weight) on this basis. residual To compensate for the dose residual This avoids the drastic oscillations that may result from resolving from scratch, making the optimization process of the initial weights smoother and more convergent. It can quickly iterate the initial solution to a state that is closer to the final ideal solution with less computational cost.

[0101] Figure 8 Another flowchart illustrating the method for obtaining initial weights in a radiotherapy planning generation method according to an embodiment of the present disclosure is shown.

[0102] like Figure 8 As shown, based on the aforementioned embodiments, operation S230 may include operation S810.

[0103] In operating the S810, based on the computational method of solving linear equation systems, the initial optimization problem is solved to obtain the initial weights. A linear equation system is a set of linear equations containing multiple unknowns, and its general form can be expressed as A*x=b, where A is a known coefficient matrix, b is a known constant vector, and x is the vector of unknowns to be solved. In this technical solution, the aforementioned initial optimization problem can be expressed as or approximated as a linear equation system. Due to the dimensionality reduction processing of classification and selection of representative grids, the coefficient matrix in the initial optimization problem (i.e., the dimensionality-reduced field intensity distribution matrix A) is... compressedThe number of rows (representing the number of grid cells) and the number of columns (representing the number of beams) are on roughly the same scale. This matrix structure characteristic makes this optimization problem very suitable for obtaining a solution directly or quickly using computationally efficient linear equation solving methods.

[0104] For example, computational methods for solving linear equation systems include, but are not limited to, the conjugate gradient method, the minimum residual method (MINRES), and iterative least squares methods. Let the initial optimization problem A... compressed *weight=dose target Using any of the above methods as input, the initial weight vector weight0 can be calculated efficiently.

[0105] According to embodiments of this disclosure, by limiting the solution of the initial optimization problem to a computational method using linear equations, the advantages of the mathematical structure of the dimensionality-reduced problem are fully utilized. Compared with general optimization algorithms that may require a large number of iterations and have uncertain convergence, linear equation solving methods typically have faster computation speeds and better convergence properties, and can directly or quickly obtain a deterministic solution.

[0106] Figure 9 A block diagram of a radiotherapy planning device according to an embodiment of the present disclosure is shown schematically.

[0107] like Figure 9 As shown, the radiotherapy planning generation device 900 may include a first acquisition module 910, a first calculation module 920, a second acquisition module 930, a second calculation module 940, and a first generation module 950.

[0108] The first acquisition module 910 is used to acquire object information of the target object, the object information including at least the medical image information and treatment target of the target object. In some embodiments, the first acquisition module 910 can be used to perform operation S110 in the radiotherapy plan generation method described above, which will not be elaborated here.

[0109] The first calculation module 920 is used to calculate the radiation field intensity distribution based on the object information. The radiation field intensity distribution includes multiple dose grids and beam information of the corresponding beams for each dose grid. In some embodiments, the first calculation module 920 can be used to perform operation S120 in the radiotherapy planning method described above, which will not be elaborated here.

[0110] The second acquisition module 930 is used to acquire initial weights, which characterize the initial radiation intensity coefficients of each beam. These initial weights are obtained based on the relative biological effects corresponding to each dose grid. In some embodiments, the second acquisition module 930 can be used to perform operation S130 in the radiotherapy planning method described above, which will not be elaborated upon here.

[0111] The second calculation module 940 is used to calculate the target radiation intensity coefficient corresponding to each of the beams, using the initial weights as the starting point of the inverse optimization problem. In some embodiments, the second calculation module 940 can be used to perform operation S140 in the radiotherapy planning method described above, which will not be elaborated here.

[0112] The first generation module 950 is used to generate a radiotherapy plan based on the target radiation intensity coefficients corresponding to each of the beams. In some embodiments, the first generation module 950 may be used to perform operation S150 in the radiotherapy plan generation method described above, which will not be elaborated here.

[0113] According to embodiments of this disclosure, the second acquisition module may include a first construction module, a first adjustment module, and a first solution module.

[0114] The first construction module is used to construct an initial optimization problem based on the target dose values ​​of at least some dose grids in each dose grid. In some embodiments, the first construction module can be used to perform operation S210 in the radiotherapy planning method described above, which will not be elaborated here.

[0115] The first adjustment module is used to adjust the initial optimization problem based on the relative biological effects corresponding to the dose grid to obtain the target optimization problem. In some embodiments, the first adjustment module can be used to perform operation S220 in the radiotherapy planning method described above, which will not be elaborated here.

[0116] The first solution module is used to solve the initial optimization problem and obtain the initial weights. In some embodiments, the first solution module can be used to perform operation S230 in the radiotherapy planning method described above, which will not be elaborated here.

[0117] According to embodiments of this disclosure, the radiotherapy planning generation device may include a first classification module and a first selection module, and the first construction module may include a second construction module.

[0118] The first classification module is used to classify the various dose grids. In some embodiments, the first classification module can be used to perform operation S310 in the radiotherapy planning method described above, which will not be elaborated here.

[0119] The first selection module is used to select the target dose grid in each type of dose grid. In some embodiments, the first selection module can be used to perform operation S320 in the radiotherapy planning method described above, which will not be elaborated here.

[0120] The second construction module is used to construct an initial optimization problem based on the target dose values ​​of each target dose grid. In some embodiments, the second construction module can be used to perform operation S330 in the radiotherapy planning method described above, which will not be elaborated here.

[0121] According to embodiments of this disclosure, the first building module may include a third building module, and the first adjustment module may include a fifth obtaining module and a weighting module.

[0122] The third construction module is used to construct the initial optimization problem by taking the target dose value corresponding to the dose grid as the optimization objective and the radiation intensity coefficient corresponding to each beam as the solution objective. In some embodiments, the third construction module can be used to perform operation S410 in the radiotherapy planning method described above, which will not be elaborated here.

[0123] The fifth obtaining module is used to obtain a relative biological effect correction factor based on the relative biological effect corresponding to each target dose grid. In some embodiments, the fifth obtaining module can be used to perform operation S420 in the radiotherapy planning generation method described above, which will not be elaborated here.

[0124] The weighting module is used to weight the target dose values ​​in the initial optimization problem based on relative biological effects, thereby obtaining the target optimization problem. In some embodiments, the weighting module can be used to perform operation S430 in the radiotherapy planning method described above, which will not be elaborated here.

[0125] According to embodiments of this disclosure, the radiotherapy plan generation device may include a fourth calculation module, a first addition module, and a first recalculation module.

[0126] The fourth calculation module is used to calculate the dose distribution of each beam based on the initial weights. In some embodiments, the fourth calculation module can be used to perform operation S510 in the radiotherapy planning method described above, which will not be elaborated here.

[0127] The first adding module is used to add dose grids where the error between the dose distribution and the target dose value is greater than an error threshold to the target dose grid, thus updating the initial optimization problem. In some embodiments, the first adding module can be used to perform operation S520 in the radiotherapy planning generation method described above, which will not be elaborated here.

[0128] The first-level calculation module is used to recalculate the initial weights based on the updated initial optimization problem. In some embodiments, the first-level calculation module can be used to perform operation S530 in the radiotherapy planning method described above, which will not be elaborated here.

[0129] According to embodiments of this disclosure, the radiotherapy planning generation device may include a fifth calculation module, a second update module, a third update module, and a second calculation module.

[0130] The fifth calculation module is used to calculate the dose distribution of each beam based on the initial weights. In some embodiments, the fifth calculation module can be used to perform operation S610 in the radiotherapy planning method described above, which will not be elaborated here.

[0131] The second update module is used to update the relative biological effect correction factor according to the dose distribution. In some embodiments, the second update module can be used to perform operation S620 in the radiotherapy planning method described above, which will not be elaborated here.

[0132] The third update module is used to update the initial optimization problem based on the updated relative biological effect correction factor. In some embodiments, the third update module can be used to perform operation S630 in the radiotherapy planning method described above, which will not be elaborated here.

[0133] The second calculation module is used to recalculate the initial weights based on the updated initial optimization problem. In some embodiments, the second calculation module can be used to perform operation S640 in the radiotherapy planning method described above, which will not be elaborated here.

[0134] According to embodiments of this disclosure, the second calculation module may include a recalculation submodule.

[0135] The recalculation submodule is used to update the initial weights again based on the initial weights before recalculation and the initial weights after recalculation. In some embodiments, the recalculation submodule can be used to perform operation S710 in the radiotherapy planning method described above, which will not be elaborated here.

[0136] According to an embodiment of this disclosure, the first solving module may include a solving submodule.

[0137] The solver submodule is used to solve the initial optimization problem and obtain the initial weights based on the computational method for solving a system of linear equations. In some embodiments, the solver submodule can be used to perform operation S810 in the radiotherapy planning generation method described above, which will not be elaborated here.

[0138] Any one or more of the modules, submodules, units, and subunits according to embodiments of the present disclosure, or at least part of the functions of any one or more of them, can be implemented in one module. Any one or more of the modules, submodules, units, and subunits according to embodiments of the present disclosure can be implemented by dividing them into multiple modules. Any one or more of the modules, submodules, units, and subunits according to embodiments of the present disclosure can be at least partially implemented as hardware circuitry, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a System-on-Chip, a System-on-a-Substrate, a System-on-Package, an Application-Specific Integrated Circuit (ASIC), or implemented in hardware or firmware by any other reasonable means of integrating or packaging circuitry, or implemented in software, hardware, or firmware, or in any suitable combination of any of these three implementation methods. Alternatively, one or more of the modules, submodules, units, and subunits according to embodiments of the present disclosure can be at least partially implemented as computer program modules, which, when run, can perform corresponding functions.

[0139] For example, any plurality of the first acquisition module 910, the first calculation module 920, the second acquisition module 930, the second calculation module 940, and the first generation module 950 can be combined into one module / unit / subunit, or any one of these modules / units / subunits can be split into multiple modules / units / subunits. Alternatively, at least part of the functionality of one or more of these modules / units / subunits can be combined with at least part of the functionality of other modules / units / subunits and implemented in one module / unit / subunit. According to embodiments of this disclosure, at least one of the first acquisition module 910, the first calculation module 920, the second acquisition module 930, the second calculation module 940, and the first generation module 950 can be at least partially implemented as hardware circuitry, such as a field-programmable gate array (FPGA), a programmable logic array (PLA), a system-on-a-chip, a system-on-a-substrate, a system-on-package, an application-specific integrated circuit (ASIC), or any other reasonable means of integrating or packaging the circuitry, or implemented in software, hardware, or firmware, or in any suitable combination of any of these three implementation methods. Alternatively, at least one of the first acquisition module 910, the first calculation module 920, the second acquisition module 930, the second calculation module 940, and the first generation module 950 can be at least partially implemented as a computer program module, which can perform corresponding functions when the computer program module is run.

[0140] It should be noted that the data processing system part in the embodiments of this disclosure corresponds to the data processing method part in the embodiments of this disclosure. The specific description of the data processing system part is referred to in the data processing method part, and will not be repeated here.

[0141] Figure 10 A block diagram of an electronic device suitable for implementing the methods described above, according to embodiments of the present disclosure, is illustrated schematically. Figure 10 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0142] like Figure 10 As shown, an electronic device 1000 according to an embodiment of the present disclosure includes a processor 1001, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage portion 1008 into a random access memory (RAM) 1003. The processor 1001 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 1001 may also include onboard memory for caching purposes. The processor 1001 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0143] RAM 1003 stores various programs and data required for the operation of electronic device 1000. Processor 1001, ROM 1002, and RAM 1003 are interconnected via bus 1004. Processor 1001 performs various operations of the method flow according to embodiments of the present disclosure by executing programs in ROM 1002 and / or RAM 1003. It should be noted that the programs may also be stored in one or more memories other than ROM 1002 and RAM 1003. Processor 1001 may also perform various operations of the method flow according to embodiments of the present disclosure by executing programs stored in said one or more memories.

[0144] According to embodiments of this disclosure, the electronic device 1000 may further include an input / output (I / O) interface 1005, which is also connected to a bus 1004. The electronic device 1000 may also include one or more of the following components connected to the input / output (I / O) interface 1005: an input section 1006 including a keyboard, mouse, etc.; an output section 1007 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 1008 including a hard disk, etc.; and a communication section 1009 including a network interface card such as a LAN card, modem, etc. The communication section 1009 performs communication processing via a network such as the Internet. A drive 1010 is also connected to the input / output (I / O) interface 1005 as needed. A removable medium 1011, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 1010 as needed so that computer programs read from it can be installed into the storage section 1008 as needed.

[0145] According to embodiments of this disclosure, the method flow according to embodiments of this disclosure can be implemented as a computer software program. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable storage medium, the computer program containing program code for performing the methods shown in the flowchart. In such embodiments, the computer program can be downloaded and installed from a network via communication section 1009, and / or installed from removable medium 1011. When the computer program is executed by processor 1001, it performs the functions defined in the system of embodiments of this disclosure. According to embodiments of this disclosure, the systems, devices, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0146] This disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs that, when executed, implement the method according to the embodiments of this disclosure.

[0147] According to embodiments of this disclosure, the computer-readable storage medium can be a non-volatile computer-readable storage medium. Examples include, but are not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this disclosure, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0148] For example, according to embodiments of this disclosure, a computer-readable storage medium may include ROM 1002 and / or RAM 1003 and / or one or more memories other than ROM 1002 and RAM 1003 as described above.

[0149] Embodiments of this disclosure also include a computer program product comprising a computer program containing program code for performing the methods provided in the embodiments of this disclosure. When the computer program product is run on an electronic device, the program code is used to enable the electronic device to implement the radiotherapy plan generation method provided in the embodiments of this disclosure.

[0150] When the computer program is executed by the processor 1001, it performs the functions defined in the system / apparatus of this disclosure embodiments. According to embodiments of this disclosure, the systems, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0151] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices or magnetic storage devices. In another embodiment, the computer program may also be transmitted and distributed in the form of signals over a network medium, and downloaded and installed via communication section 1009, and / or installed from removable medium 1011. The program code contained in the computer program can be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination thereof. According to embodiments of this disclosure, program code for executing the computer programs provided in embodiments of this disclosure can be written in any combination of one or more programming languages. Specifically, these computational programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C", or similar programming languages. The program code may be executed entirely on a user computing device, partially on a user device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing devices can be connected to user computing devices via any type of network, including local area networks (LANs) or wide area networks (WANs), or they can be connected to external computing devices (e.g., via the Internet using an Internet service provider).

[0152] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions. Those skilled in the art will understand that the features described in the various embodiments of the present disclosure can be combined and / or combined in various ways, even if such combinations are not explicitly described in the present disclosure. In particular, the features described in the various embodiments of this disclosure may be combined and / or combined in various ways without departing from the spirit and teachings of this disclosure. All such combinations and / or combinations fall within the scope of this disclosure.

[0153] The embodiments of this disclosure have been described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of this disclosure. Although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be used advantageously in combination. Various substitutions and modifications can be made by those skilled in the art without departing from the scope of this disclosure, and all such substitutions and modifications should fall within the scope of this disclosure.

Claims

1. A method for generating a radiotherapy plan, characterized in that, include: Obtain object information of the target object, wherein the object information includes at least the medical image information and treatment target of the target object; Based on the object information, the field intensity distribution is calculated, which includes multiple dose grids and the beam information of the beam corresponding to each dose grid. An initial weight is obtained, which characterizes the initial radiation intensity coefficient of each beam and is obtained based on the relative biological effects corresponding to each dose grid. Using the initial weights as the starting point of the inverse optimization problem, calculate the target radiation intensity coefficient corresponding to each of the beams; A radiotherapy plan is generated based on the target radiation intensity coefficient corresponding to each of the aforementioned beams; The process of obtaining the initial weights includes: The dose grids are classified. Select the target dose grid in each type of dose grid, and each type of target dose grid corresponds to a field intensity distribution representative vector to form a dimension-reduced field intensity distribution matrix. An initial optimization problem is constructed based on the target dose values ​​of at least some of the dose grids in each of the dose grids; Based on the relative biological effects corresponding to the dose grid, the initial optimization problem is adjusted to obtain the target optimization problem; Solve the objective optimization problem to obtain the initial weights; The step of constructing an initial optimization problem based on the target dose values ​​of at least a portion of the dose grids in each of the dose grids includes: An initial optimization problem is constructed based on the target dose values ​​of each target dose grid, wherein the target dose value corresponding to each target dose grid is used as the optimization objective of the initial optimization problem, and the radiation intensity coefficient corresponding to each beam is used as the solution objective; wherein the reduced field intensity distribution matrix is ​​denoted as A. phy The radiation intensity coefficients of each of the beams to be solved are used to form a column vector weight, and the target dose values ​​corresponding to each target dose grid are used to form a column vector dose. target Then the initial optimization problem is expressed as: A phy *weight=dose target ; The process of adjusting the initial optimization problem based on the relative biological effects corresponding to the dose grid to obtain the target optimization problem includes: Based on the relative biological effects corresponding to each of the target dose grids, the relative biological effect correction factor rbe_factor is obtained; Construct a diagonal matrix diag(rbe_factor) from the relative biological effect correction factors rbe_factor of all target dose grids, and then multiply this diagonal matrix on the left by the A. phy The corrected dose influence matrix A is obtained. rbe =diag(rbe_factor) *A phy ; The objective optimization problem is updated to: A rbe *weight=dose target .

2. The method according to claim 1, characterized in that, Also includes: The dose distribution of each of the beams is calculated based on the initial weights; The dose grids whose error between the dose distribution and the target dose value is greater than the error threshold are added to the target dose grid, thus updating the initial optimization problem; The initial weights are recalculated based on the updated initial optimization problem.

3. The method according to claim 1, characterized in that, Also includes: The dose distribution of each of the beams is calculated based on the initial weights; The relative biological effect correction factor is updated based on the dose distribution; The initial optimization problem is updated based on the updated relative biological effect correction factor. The initial weights are recalculated based on the updated initial optimization problem.

4. The method according to claim 3, characterized in that, The process of recalculating the initial weights based on the updated initial optimization problem further includes: The initial weights are updated again based on the initial weights before and after recalculation.

5. The method according to claim 1, characterized in that, Solving the initial optimization problem to obtain the initial weights includes: The initial optimization problem is solved using a computational method for solving linear equations to obtain the initial weights.

6. A radiotherapy planning device, characterized in that, include: The first acquisition module is used to acquire object information of the target object, wherein the object information includes at least the medical image information and treatment target of the target object; The first calculation module is used to calculate the field intensity distribution based on the object information. The field intensity distribution includes multiple dose grids and the beam information of the beam corresponding to each dose grid. The second acquisition module is used to acquire initial weights, which characterize the initial radiation intensity coefficients of each beam and are obtained based on the relative biological effects corresponding to each dose grid. The second calculation module is used to calculate the target radiation intensity coefficient corresponding to each of the beams, using the initial weights as the starting point of the inverse optimization problem. The first generation module is used to generate a radiotherapy plan based on the target radiation intensity coefficient corresponding to each of the beams; The process of obtaining the initial weights includes: The dose grids are classified. Select the target dose grid in each type of dose grid, and each type of target dose grid corresponds to a field intensity distribution representative vector to form a dimension-reduced field intensity distribution matrix. An initial optimization problem is constructed based on the target dose values ​​of at least some of the dose grids in each of the dose grids; Based on the relative biological effects corresponding to the dose grid, the initial optimization problem is adjusted to obtain the target optimization problem; Solve the objective optimization problem to obtain the initial weights; The step of constructing an initial optimization problem based on the target dose values ​​of at least a portion of the dose grids in each of the dose grids includes: An initial optimization problem is constructed based on the target dose values ​​of each target dose grid, wherein the target dose value corresponding to each target dose grid is used as the optimization objective of the initial optimization problem, and the radiation intensity coefficient corresponding to each beam is used as the solution objective; wherein the reduced field intensity distribution matrix is ​​denoted as A. phy The radiation intensity coefficients of each of the beams to be solved are used to form a column vector weight, and the target dose values ​​corresponding to each target dose grid are used to form a column vector dose. target Then the initial optimization problem is expressed as: A phy *weight=dose target ; The process of adjusting the initial optimization problem based on the relative biological effects corresponding to the dose grid to obtain the target optimization problem includes: Based on the relative biological effects corresponding to each of the target dose grids, the relative biological effect correction factor rbe_factor is obtained; Construct a diagonal matrix diag(rbe_factor) from the relative biological effect correction factors rbe_factor of all target dose grids, and then multiply this diagonal matrix on the left by the A. phy The corrected dose influence matrix A is obtained. rbe =diag(rbe_factor) *A phy ; The objective optimization problem is updated to: A rbe *weight=dose target .

7. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 5.

Images