Radiotherapy plan optimization method, equipment, system and medium

Abstract

The invention provides a radiotherapy plan optimization method, equipment, a system and a medium, and belongs to the technical field of radiotherapy. The method comprises the following steps: generating an initial radiotherapy plan for a tumor target region in a medical image; wherein the initial radiotherapy plan at least comprises a high-dose lattice dot matrix and a beam direction corresponding to each high-dose lattice in the high-dose lattice dot matrix; at least one of the beam direction in the initial radiotherapy plan and the rotation attitude of the high-dose lattice lattice relative to the tumor target region is optimized, so that a plurality of high-dose lattices exist in at least one beam direction, and an optimized radiotherapy plan is obtained.

Description

Technical Field

[0001] This disclosure relates to the field of radiotherapy technology, and in particular to a method, equipment, system and medium for optimizing radiotherapy plans. Background Technology

[0002] Spatially Fractionated Radiation Therapy (SFRT) is a technique that creates a non-uniform radiation dose distribution within the tumor to control or kill tumor cells while avoiding unacceptable radiation damage to surrounding healthy tissues and organs at risk (OARs).

[0003] High-dose lattice radiotherapy (LRT) is a technique that achieves spatially segmented radiotherapy in three-dimensional space. LRT constructs a three-dimensional high-dose lattice array within the tumor target volume (GTV) consisting of multiple discrete quasi-spherical or spherical high-dose lattices. It provides a high radiation dose within each high-dose lattice and a low radiation dose in the regions between the high-dose lattices within the tumor target volume (i.e., the regions outside the high-dose lattices), thereby delivering a three-dimensional non-uniform radiation dose to the tumor target volume with a high peak-valley dose ratio (PVDR).

[0004] In lattice radiotherapy protocols, all high-dose lattices are irradiated sequentially. Since lattice radiotherapy treatment plans typically involve dozens or even more high-dose lattices, each irradiation requires mechanical movement and repositioning of the patient positioning system. This results in a significant amount of treatment time being consumed in the non-irradiated, purely mechanical movement and positioning phases, leading to an exceptionally lengthy treatment process. Summary of the Invention

[0005] This disclosure provides a method, equipment, system, and medium for optimizing radiotherapy planning; it can reduce unnecessary mechanical movement time during radiotherapy and shorten the overall treatment time of the radiotherapy process.

[0006] The technical solution disclosed herein is implemented as follows: In a first aspect, this disclosure provides a method for optimizing radiotherapy planning, the method comprising: An initial radiotherapy plan is generated for the tumor target area in a medical image; wherein the initial radiotherapy plan includes at least a high-dose lattice and the beam direction corresponding to each high-dose lattice in the high-dose lattice; An optimized radiotherapy plan is obtained by optimizing at least one of the beam direction and the rotational orientation of the high-dose lattice relative to the tumor target region in the initial radiotherapy plan, such that there are multiple high-dose lattices in at least one beam direction.

[0007] Secondly, this disclosure provides an apparatus for optimizing radiotherapy plans, comprising: a generation section and an optimization section; wherein, The generation section is configured to generate an initial radiotherapy plan for the tumor target area in the medical image; wherein the initial radiotherapy plan includes at least a high-dose lattice and the beam direction corresponding to each high-dose lattice in the high-dose lattice. The optimization portion is configured to optimize at least one of the beam direction and the rotational orientation of the high-dose lattice relative to the tumor target region in the initial radiotherapy plan, such that there are multiple high-dose lattices in at least one beam direction, to obtain an optimized radiotherapy plan.

[0008] Thirdly, this disclosure provides a radiotherapy planning device, comprising: Memory that stores executable instructions for a computer; And at least one processing unit configured to execute the computer-executable instructions to cause the radiotherapy planning device to implement the radiotherapy planning optimization method described in the first aspect.

[0009] Fourthly, this disclosure provides a radiotherapy system, comprising: a radiotherapy planning device and a radiotherapy device that communicate bidirectionally with each other; wherein the radiotherapy planning device is the radiotherapy planning device described in the third aspect, for generating an optimized radiotherapy plan; and the radiotherapy device is used to perform radiotherapy on a target subject according to the optimized radiotherapy plan.

[0010] Fifthly, this disclosure provides a computer-readable storage medium storing at least one instruction that is executed by a processor to implement the method for optimizing a radiotherapy plan as described in the first aspect.

[0011] In a sixth aspect, this disclosure provides a computer program product that, when run on a computer, causes the computer to perform the steps of the method for optimizing a radiotherapy plan as described in the first aspect.

[0012] This disclosure provides a method, device, system, and medium for optimizing radiotherapy planning; by optimizing at least one of the beam direction and the rotational attitude of the high-dose lattice relative to the tumor target area, multiple high-dose lattices exist in at least one beam direction, thereby reducing unnecessary mechanical movement time during radiotherapy and shortening the overall treatment time of the radiotherapy process. Attached Figure Description

[0013] Figure 1 This is a schematic diagram of a system composition for performing radiotherapy, as provided in this disclosure.

[0014] Figure 2 This is a schematic diagram of a medical image including a tumor site provided in this disclosure.

[0015] Figure 3 This is a schematic diagram of a method for optimizing a radiotherapy plan provided in this disclosure.

[0016] Figure 4 This is a schematic diagram of the beam path after the beam direction has been optimized, as provided in this disclosure.

[0017] Figure 5 This is a schematic diagram of the beam path after rotating a high-dose lattice, as provided in this disclosure.

[0018] Figure 6 This is a schematic diagram of the components of an optimization device for radiotherapy planning provided in this disclosure. Detailed Implementation

[0019] The technical solutions of this disclosure will now be clearly and completely described with reference to the accompanying drawings. Obviously, the embodiments described in this disclosure are merely some embodiments, not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without creative effort are within the protection scope of this disclosure.

[0020] In this disclosure, the terms “one or more” and “at least one” are used interchangeably; the terms “first” and “second” are used to distinguish different objects or to distinguish different treatments of the same object, rather than to describe a particular order of objects.

[0021] In this disclosure, radiotherapy may also be referred to as radiation therapy or radiotherapy. Furthermore, a radiotherapy plan may also be referred to as a radiotherapy plan, a radiotherapy treatment plan, a treatment plan, or a plan.

[0022] It should be understood that the various embodiments in this disclosure can be used in combination.

[0023] Figure 1 This is a schematic diagram of a system for performing radiotherapy provided in this disclosure. The system 100 includes a radiotherapy planning device 110 and a radiotherapy device 120 that communicate bidirectionally with each other.

[0024] The radiotherapy planning device 110 is used to generate, optimize, and evaluate treatment plans for target subjects, and to produce a final optimized treatment plan. Specifically, the radiotherapy planning device 110 includes at least one processing unit 112, a memory 114, and a communication connector 116 that enables the radiotherapy planning device 110 to communicate with other devices (such as the radiotherapy device 120).

[0025] exist Figure 1 In this context, memory 114 includes computer-readable instructions, data structures, program modules, etc., associated with the Treatment Planning System (TPS) 115. Processing unit 112 is configured to generate, optimize, and evaluate treatment plans by executing the computer-readable instructions, data structures, program modules, etc., associated with TPS 115, and to produce a final optimized treatment plan.

[0026] In addition, memory 114 is also used to store data transmitted from other devices to radiotherapy planning device 110 by communication connector 116, as well as the final optimized plan generated by processing unit 112.

[0027] After the processing unit 112 generates the final optimized treatment plan, it transmits the final optimized treatment plan to the radiotherapy device 120 via the communication connector 116, so that the radiotherapy device 120 can perform radiotherapy on the target object according to the final optimized treatment plan.

[0028] See Figure 1 The system 100 for administering radiotherapy also includes an imaging scanning device 130 that communicates bidirectionally with the radiotherapy planning device 110, such as a cone-beam computed tomography (CBCT) device, a computed tomography (CT) device, an emission computed tomography (ECT) device, a magnetic resonance imaging (MRI) device, a positron emission tomography (PET) device, and an ultrasound examination device. The imaging scanning device 130 is used to scan and display the tumor site and surrounding normal tissue of the target object, and to generate a medical image of the target object. This medical image is a 3D representation of the tumor site and the surrounding normal tissue.

[0029] After obtaining the medical image of the target object, the imaging scanning device 130 uploads the medical image to the radiotherapy planning device 110, so that the radiotherapy planning device 110 can generate, optimize and evaluate the treatment plan for the target object based on the medical image of the target object, and generate the final treatment plan.

[0030] Figure 2 This is a schematic medical image illustrating a tumor site provided in this disclosure. Figure 2 In the medical image 200 shown, an irregular solid-line frame 210 illustrates the outline of the region where the tumor is located, i.e., the tumor target volume (GTV) 220. Outside this outline are adjacent healthy organs or tissues that are radiosensitive to the tumor target volume, i.e., organs at risk (OARs) 230. In this disclosure, the outline of the tumor target volume 220 is formed by the radiotherapy planning device 110 in the medical image.

[0031] After obtaining the outline 210 of the tumor target region 220, the physician can determine a prescription dose for treating the tumor site by considering the size and shape of the tumor and its positional relationship with organs at risk. In this disclosure, for lattice radiotherapy, the prescription dose includes at least: the radiation dose covering the tumor target region 220, the dose required for the high-dose lattice (also referred to as the high-dose lattice prescription dose), and the tolerable dose for organs at risk. It is understood that the above-mentioned prescription dose is used when lattice radiotherapy is applied to… Figure 2 The target dose that should be met during radiotherapy to the tumor site shown.

[0032] In this disclosure, after obtaining the outline 210 of the tumor target region 220 and the prescribed dose, the radiotherapy planning device 110, in particular the processing unit 112, is configured to perform the process of generating a lattice radiotherapy treatment plan.

[0033] Specifically, the processing unit 112, according to the prescribed dosage requirements, sets multiple high-dose lattices within the tumor target region 220 to form a high-dose lattice array. In this high-dose lattice array, each high-dose lattice includes at least one of the following layout parameters: high-dose lattice position, size, and high-dose lattice spacing. For example... Figure 2 As shown, each solid circle represents a high-dose lattice, labeled 260-1, 260-2, 260-3, 260-4, and 260-5 respectively. After these high-dose lattices are deployed, the deployment parameters, such as the position and size of each high-dose lattice and the distance between each high-dose lattice, are also set.

[0034] Taking Gamma Knife radiotherapy as an example, the processing unit 112 generates a target point within each high-dose lattice. For instance, a corresponding target point can be generated at the center of each high-dose lattice. Figure 2As shown, the black dots within each high-dose lattice are the target points corresponding to that high-dose lattice. In addition to setting the target points, the processing unit 112 also sets the weight of each target point, the collimator size corresponding to the target point, and the beam angle of the target point, so that the area covered by the isodose percentage curve (e.g., the 50% isodose percentage curve) corresponding to the prescription dose of each target point is consistent with the area covered by the high-dose lattice corresponding to that target point. This ensures that the irradiation dose received by the high-dose lattice corresponding to each target point meets the prescription dose requirements of the high-dose lattice, thereby generating a lattice radiotherapy treatment plan.

[0035] Taking accelerator radiotherapy as an example, the processing unit 112, based on a high-dose lattice array formed by multiple high-dose lattices, optimizes the radiation parameters corresponding to each high-dose lattice in the high-dose lattice array with the prescription dose as the target, in order to generate a lattice radiotherapy treatment plan. The radiation parameters include radiation intensity, radiation shape, etc.

[0036] After generating the lattice radiotherapy treatment plan, the lattice radiotherapy treatment plan is transmitted to the radiotherapy equipment 120. According to the lattice radiotherapy treatment plan, the radiotherapy equipment 120 irradiates the high-dose lattices one by one in sequence. Moreover, after each high-dose lattice is irradiated, the radiotherapy equipment 120 moves the treatment bed through the patient positioning system to align the beam with the next high-dose lattice. This cycle is repeated until all high-dose lattices have been irradiated in sequence, thus completing the lattice radiotherapy for the target.

[0037] During lattice radiotherapy, the duration of irradiation of a single high-dose lattice is less than the time spent moving the treatment bed. In other words, during lattice radiotherapy, more of the total treatment time is consumed in the mechanical movement process, which greatly occupies valuable equipment time and reduces the work efficiency of medical institutions and the patient throughput.

[0038] To reduce the duration of a single treatment session in lattice radiotherapy, this disclosure optimizes the treatment plan to achieve co-path irradiation of multiple high-dose lattices, resulting in multiple high-dose lattices existing in a single beam direction. In this disclosure, Figure 3 This is a schematic diagram of a method for optimizing radiotherapy planning. The process is implemented by the radiotherapy planning equipment 110, and more particularly by the processing unit 112.

[0039] See Figure 3 In step S302, an initial radiotherapy plan is generated for the tumor target area in the medical image.

[0040] In this disclosure, after receiving the medical image transmitted by the imaging scanning device 130 and obtaining the three-dimensional contour 210 of the tumor target region 220 based on the medical image, the processing unit 112 deploys multiple high-dose lattices within the tumor target region 220 to form a high-dose lattice array, and sets corresponding beam parameters for each high-dose lattice. These beam parameters include beam shape, beam intensity, and beam direction, etc., to generate an initial treatment plan. The process of generating the initial treatment plan can be found in the above description of the process of generating lattice radiotherapy treatment plans using Gamma Knife and accelerators, and will not be repeated here. Thus, the initial radiotherapy plan includes at least the high-dose lattice array and the beam direction corresponding to each high-dose lattice in the high-dose lattice array.

[0041] In step S304, at least one of the beam direction and the rotational orientation of the high-dose lattice relative to the tumor target area in the initial radiotherapy plan is optimized such that there are multiple high-dose lattices in at least one beam direction, so as to obtain an optimized radiotherapy plan.

[0042] Specifically, in Figure 2 In the image, the arrow indicates that in the initial radiotherapy plan, a high-dose beam 271 of lattice 260-1 is irradiated, the direction of which is... Figure 2 The angle between the horizontal direction indicated by the midpoint line is... As shown by the dashed line, only the high-dose lattice 260-1 exists in the direction of beam 271.

[0043] In this disclosure, Figure 4 This is a schematic diagram showing the optimized beam direction of beam 271. Figure 4 In the process, processing unit 112 optimizes the beam direction of beam 271 using a random optimization algorithm, such that the optimized beam direction has an angle of θ with the horizontal direction. .from Figure 4 As can be seen, in addition to irradiating the high-dose lattice 260-1 according to the optimized beam direction, beam 271 also irradiates the high-dose lattice 260-2. That is to say, after optimizing the beam direction of beam 271, the beam 271 irradiates two high-dose lattices (260-1 and 260-2) in the high-dose lattice. Thus, during the treatment, there is no need to spend time moving the treatment bed to align the beam with the high-dose lattice 260-2, nor is it necessary to irradiate the high-dose lattice 260-2 separately, which reduces the total treatment time and improves efficiency.

[0044] In addition to optimizing the beam direction, this disclosure also treats the high-dose lattice as a rigid monolithic structure and rotates the high-dose lattice relative to the tumor target area in three-dimensional space. Figure 5 This is a schematic diagram showing the high-dose crystal lattice rotated relative to the tumor target region. Figure 5 In this process, the processing unit rotates the high-dose lattice 260 using the geometric center 280 as the rotation center. After rotation, the direction of the beam 271 irradiating the high-dose lattice 260-1 still makes an angle with the horizontal direction. However, as shown by the dashed line, after the high-dose lattice rotation is completed, beam 271 irradiates not only 260-1 but also high-dose lattice 260-2. In other words, after optimizing the rotation state of the high-dose lattice relative to the tumor target area using a stochastic optimization algorithm, beam 271 irradiates two high-dose lattices (260-1 and 260-2) within the high-dose lattice. This is only based on... Figure 5 Taking the rotation of a high-dose lattice as an example, it can be understood that when a high-dose lattice is rotated relative to the tumor target area in three-dimensional space, the center of rotation can be the geometric center of the high-dose lattice, or it can be a point located inside or outside the tumor target area.

[0045] In this disclosure, in addition to optimizing the beam direction and the rotation state of the high-dose lattice relative to the tumor target area separately, the processing unit 112 also optimizes the beam direction and the rotation state of the high-dose lattice relative to the tumor target area in a stochastic optimization algorithm. That is, the processing unit 112 optimizes the beam direction and the rotation state of the high-dose lattice relative to the tumor target area at the same time, so that in the optimized radiotherapy plan, there are multiple high-dose lattices in at least one beam direction.

[0046] During the optimization process by the processing unit 112 of at least one of the beam direction and the rotational attitude of the high-dose lattice relative to the tumor target area in the initial radiotherapy plan using a stochastic optimization algorithm, a time cost function is formed based on the overall execution time of the treatment plan, and a penalty function is formed by using the tolerance dose of the organs at risk and the dose coverage of the high-dose lattice as constraint objectives. Subsequently, the processing unit 112 forms the objective function of the stochastic optimization algorithm based on the time cost function and the penalty function. Next, the processing unit 112 takes the beam direction of each high-dose lattice in the initial radiotherapy plan, or the rotational attitude of the high-dose lattice relative to the tumor target area, or the beam direction of each high-dose lattice and the rotational attitude of the high-dose lattice relative to the tumor target area, as input to the stochastic optimization algorithm, and performs iterative calculation with the objective function minimization as the goal, thereby outputting the optimized beam direction of each high-dose lattice, or the optimized rotational attitude of the high-dose lattice relative to the tumor target area, or the optimized beam direction of each high-dose lattice and the rotational attitude of the high-dose lattice relative to the tumor target area, respectively.

[0047] For example, the objective function can be defined as follows:

[0048] in, The solution vector of the objective function includes all variables to be optimized, such as the beam direction of each high-dose lattice point, or the rotation angle of the high-dose lattice, or the beam direction and the rotation angle of the high-dose lattice.

[0049] The time cost function is used to represent the overall execution time of the treatment plan. In this disclosure, the overall execution time is characterized by the number of independent beam paths. The number of high-dose lattices is set to... , and the plan Achieved If the striped beam path is used to irradiate these high-dose lattices, then the time cost function is... It is directly proportional to, or inversely proportional to, the number of high-dose lattice cells irradiated per beam path on average. For example, or ,in, Indicates the first The number of high-dose lattices irradiated by the stripe beam path. Therefore, the optimization objective is to minimize... .

[0050] This represents a penalty function for organs at risk, used to punish excessive doses to those organs. It is typically constructed based on clinical constraints of the dose-volume histogram (DVH). For example, for the [missing information - likely a specific organ or organ]... For each OAR, clinical requirements dictate that the received dose exceeds the safety limit. The volume cannot exceed The penalty function is the sum of penalty terms for all OARs that violate the constraints, and takes the following form:

[0051] in, Indicating in the plan Next, the The dose received by the OAR exceeded the safety limit. The size of the volume Represented as the first The OAR setting is able to withstand The maximum volume to be irradiated. For example, the first... For an OAR (Organic Acid Reduction) targeting the brainstem, clinical requirements stipulate that the volume of the brainstem receiving a dose of 20 Gy or higher must be less than 5 cc. 20 Gy It is 5cc, if planned If a dose exceeding 20 Gy is administered to a 6.5 cc volume of the brainstem, then the penalty score for the brainstem as an organ would be: .

[0052] This is a penalty function representing the dose coverage of high-dose lattices, used to penalize insufficient dose coverage of high-dose lattices. For example, if a dose prescription specifies that 95% of the volume of a high-dose lattice should receive a set radiation dose, then this penalty function is the sum of penalty terms for all high-dose lattices that fail to meet the dose coverage requirement. It takes the following form:

[0053] in, Represents all high-dose lattices, Indicates the high-dose lattice prescription dose. Indicates the first k The lowest dose received by 95% of the volume within a high-dose lattice is also used to measure whether the dose coverage of a high-dose lattice is adequate. For example, the prescribed dose requires each high-dose lattice point to... Reaching 18Gy, then That would be 18Gy. If the plan... Next, the k A high-dose lattice With only 17.2 Gy, the penalty for this high-dose lattice is divided into... .

[0054] In the objective function, , as well as The weighting factors represent time cost, organs at risk, and dose coverage of high-dose lattices, respectively, and are used to balance the priorities among different optimization objectives.

[0055] In addition to the constraints of the objective function mentioned above, other constraints can be set, such as the maximum dose of all OARs must not exceed their tissue tolerance limit.

[0056] After setting the input, objective function, and other constraints of the stochastic optimization algorithm, the processing unit 112 iteratively calculates the stochastic optimization algorithm until the objective function is minimized, thereby outputting the optimized beam direction of each high-dose lattice, or the rotational attitude of the optimized high-dose lattice relative to the tumor target area, or the optimized beam direction of each high-dose lattice and the rotational attitude of the high-dose lattice relative to the tumor target area.

[0057] pass Figure 3The technical solution shown optimizes at least one of the beam direction and the rotational attitude of the high-dose lattice relative to the tumor target area, so that there are multiple high-dose lattices in at least one beam direction, thereby reducing unnecessary mechanical movement time during radiotherapy and shortening the overall treatment time of radiotherapy.

[0058] exist Figure 3 The technical solutions shown include stochastic optimization algorithms such as simulated annealing, particle swarm optimization, or genetic algorithms. This disclosure illustrates implementation examples of these three stochastic optimization algorithms.

[0059] In this disclosure, taking the beam direction as an example of the optimization target, the process of optimizing using a simulated annealing algorithm while keeping the rotational orientation of the high-dose lattice relative to the tumor target region fixed, i.e., the rotational orientation of the initial radiotherapy plan, includes: First, the initialization process is executed: the beam direction in the initial radiotherapy plan is defined as the current state, and... Figure 3 The objective function described in the technical solution is used as an energy function to evaluate the energy of the current state, and the initial temperature and cooling coefficient are set.

[0060] Next, the iterative search process is executed: at the current temperature, the following iteration steps are performed L times: The current state is randomly and slightly perturbed to generate a new state. For example, one of several beam directions can be randomly selected, and the angle of the selected beam direction can be randomly changed by a small range, such as 5°.

[0061] Calculate the energy of the new state and obtain the energy change compared to the previous state; If the energy of the new state is less than the energy of the previous state, it means that the new state is better, and the new state is used as the current state for the next iteration. Otherwise, it means the new state is worse, so it will proceed according to the set probability, for example... Accept this worse situation; among them, This represents the energy difference between the new state and the previous state. Indicates temperature.

[0062] Subsequently, a cooling process is performed: after completing the above L iterations of search, the temperature is decreased according to the cooling coefficient. Understandably, the lower the temperature, the lower the probability of accepting a poor solution, and the algorithm's search behavior gradually shifts from a global coarse search to a local fine search.

[0063] Next, the iterative search and cooling process is repeated based on the attenuated temperature until the temperature T drops to a very small value (close to 0), or the optimal solution remains unchanged during multiple cooling processes. In this way, the optimal beam direction is obtained through simulated annealing algorithm.

[0064] In this disclosure, taking the optimization objective as the rotational orientation of a high-dose lattice relative to the tumor target region as an example, while keeping the beam direction fixed, i.e., the beam direction in the initial radiotherapy plan, the optimization process using a particle swarm optimization algorithm includes: First, the initial particle swarm process is executed: multiple particle swarms are randomly generated based on the rotational attitude of the high-dose lattice relative to the tumor target area according to the initial radiotherapy plan, where the position of each particle represents a three-dimensional rotational attitude.

[0065] Next, the fitness of all particles is evaluated. For each particle, its representative rotational attitude is applied to the high-dose lattice points, and then the number of high-dose lattice points that the beam direction can cover under that rotational attitude is calculated, and the fitness is calculated accordingly. This can be understood as... Figure 3 The fitness of the objective function described in the technical solution shown is calculated.

[0066] Then, the velocity of each particle is updated based on its own historical best position (pBest) and the historical best position of the entire particle swarm (gBest), and the position of each particle is updated based on the updated velocity. When the maximum number of iterations is reached or the change in the optimal solution of the particle swarm is less than a certain threshold, the rotational attitude represented by the current optimal position of the entire particle swarm is taken as the optimal solution. In this way, the optimal rotational attitude is obtained through particle swarm optimization.

[0067] In this disclosure, taking the optimization objectives as the beam direction and the rotational attitude of the high-dose lattice relative to the tumor target region, the optimization process using a genetic algorithm includes: First, the process of initializing the population is performed: the initial radiotherapy plan is treated as an individual whose chromosome consists of the beam direction and the rotational orientation of the high-dose lattice relative to the tumor target area, and multiple individuals are randomly generated from this individual to form a population.

[0068] Next, assess the fitness of each individual in the population: for each individual, according to Figure 3 The objective function described in the technical solution illustrates the fitness calculation to evaluate the merits of each individual.

[0069] Then, the individuals in the population were subjected to multi-generational evolution by simulating natural selection, crossover, and mutation. After a set number of generations, the individual with the highest fitness during the multi-generational evolution was selected as the optimal solution, along with its corresponding beam direction and the rotational attitude of the high-dose lattice relative to the tumor target region.

[0070] In the implementation of the above-mentioned stochastic optimization algorithm, the rotation of the high-dose lattice includes: rotating the high-dose lattice with its geometric center as the rotation center so that the high-dose lattice remains centered within the tumor target area after rotation; rotating a high-dose lattice within the high-dose lattice with its rotation center as the rotation center to avoid endangered organs near the rotation center in the high-dose lattice; and rotating a virtual point outside the tumor target area with its rotation center to provide a composite motion of translation and rotation of the high-dose lattice.

[0071] Understandably, after obtaining the optimized radiotherapy plan through the above-mentioned stochastic optimization algorithm, the radiotherapy device 120 can irradiate all high-dose lattices completely with the fewest number of irradiations, reducing the mechanical movement time during the radiotherapy process and shortening the overall treatment time of the radiotherapy process.

[0072] To balance the precision and efficiency of spatially fractionated radiotherapy, in this disclosure, the size (diameter of the high-dose lattice) of the high-dose lattice in the high-dose lattice ranges from 9 mm to 20 mm.

[0073] In this disclosure, at least two high-dose lattices in the high-dose lattice are of different sizes.

[0074] In this disclosure, the high-dose lattice is either a uniform lattice or a non-uniform lattice. When the high-dose lattice is a non-uniform lattice, at least two high-dose lattices have different center-to-center spacings. For example, such as... Figure 2 As shown, the distance between high-dose lattices 260-1 and 260-2 is different from the distance between high-dose lattices 260-4 and 260-5. This effectively improves the peak-to-trough dose ratio (PVDR) of the treatment plan.

[0075] In this disclosure, in order to avoid radiation exposure to sensitive areas (such as blood vessels) within the tumor target region or to reduce radiation exposure to normal tissues (organs at risk) surrounding the tumor target region, Figure 3 The technical solution shown also includes: optimizing the arc range of the ray beam corresponding to each target point to avoid irradiation of the preset sensitive area.

[0076] In this disclosure, there are subregions with special biological characteristics within the tumor target volume, such as hypoxic areas or hyperproliferative areas. This disclosure targets these biologically characteristic subregions within the tumor target volume. Figure 3The technical solution shown also includes: forming a uniform high-dose irradiation in the biological feature subregion, and setting the high-dose lattice in the remaining region of the tumor target area after removing the biological feature subregion, and spatially segmenting the remaining region for irradiation.

[0077] Specifically, tumors are usually treated as homogeneous bodies for radiotherapy. However, tumors are heterogeneous bodies, and there may be some biological characteristic sub-regions such as hypoxic areas / high-proliferation areas inside the tumor. Different radiotherapy methods are required. In this disclosure, after the processing unit 112 identifies the above-mentioned biological characteristic sub-regions in the tumor target area of ​​the medical image, it generates a radiotherapy plan for uniform high-dose irradiation of the biological characteristic sub-regions. The radiotherapy plan also includes: generating an optimized radiotherapy plan in the remaining area of ​​the tumor target area after removing the biological characteristic sub-regions according to the technical solution of the aforementioned embodiment, and performing radiotherapy.

[0078] In this disclosure, at least two high-dose lattices are irradiated in different ways, including gamma irradiation and X-ray irradiation.

[0079] Specifically, different types of radiation can damage tumor cells in different ways, thereby exposing different tumor antigens, or activating downstream immune signaling pathways with different intensities and modes. Based on this, this disclosure sets different irradiation methods for different high-dose lattices. For example, lattices in the tumor core region with strong radioresistance are irradiated with gamma rays; while lattices in the periphery of the tumor and in the more actively proliferating region are irradiated with X-rays.

[0080] Based on the same inventive concept as the aforementioned technical solution, see [link to inventive concept]. Figure 6 This illustration shows a schematic diagram of the composition of a radiotherapy planning optimization device 600 provided in this disclosure. The radiotherapy planning optimization device 600 includes a generation section 602 and an optimization section 604; wherein, The generation section 602 is configured to generate an initial radiotherapy plan for a tumor target region in a medical image; wherein the initial radiotherapy plan includes at least a high-dose lattice and the beam direction corresponding to each high-dose lattice in the high-dose lattice. The optimization section 604 is configured to optimize at least one of the beam direction and the rotational orientation of the high-dose lattice relative to the tumor target region in the initial radiotherapy plan, such that there are multiple high-dose lattices in at least one beam direction, to obtain an optimized radiotherapy plan.

[0081] In this disclosure, the optimization of part 604 is configured as follows: A time cost function is formed based on the overall execution time of the treatment plan, and a penalty function is formed by taking the tolerance dose of the organs at risk and the dose coverage of the high-dose lattice as constraint targets. The objective function of the stochastic optimization algorithm is formed based on the time cost function and the penalty function; The beam direction of each high-dose lattice in the initial radiotherapy plan, or the rotational orientation of the high-dose lattice relative to the tumor target area, or the beam direction of each high-dose lattice and the rotational orientation of the high-dose lattice relative to the tumor target area, are used as inputs to a stochastic optimization algorithm. The algorithm iteratively calculates the algorithm with the objective function minimization as the goal, and outputs the optimized beam direction of each high-dose lattice, or the optimized rotational orientation of the high-dose lattice relative to the tumor target area, or the optimized beam direction of each high-dose lattice and the rotational orientation of the high-dose lattice relative to the tumor target area.

[0082] In this disclosure, the size of the high-dose lattice in the optimized radiotherapy plan is 9 mm to 20 mm.

[0083] In this disclosure, in the optimized radiotherapy plan, at least two high-dose lattices in the high-dose lattice are of different sizes.

[0084] In this disclosure, in the optimized radiotherapy plan, at least two high-dose lattice centers have different spacings.

[0085] In this disclosure, the optimization of part 604 is also configured as follows: Optimize the arc range of the X-ray beam corresponding to each high-dose lattice to avoid irradiation of the preset sensitive areas.

[0086] In this disclosure, the tumor target region includes subregions with specific biological characteristics, and in the optimized radiotherapy plan, the high-dose lattice is located in the region of the tumor target region excluding the subregions with specific biological characteristics.

[0087] In this disclosure, at least two high-dose lattices in the high-dose lattice are irradiated in different ways.

[0088] This disclosure also provides a computer-readable storage medium storing at least one instruction that is executed by a processor to implement the radiotherapy planning optimization method as described in the various embodiments above.

[0089] This disclosure also provides a computer program product including computer instructions stored in a computer-readable storage medium; a processor of a computing device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computing device to perform the method for optimizing the radiotherapy plan as described in the various embodiments above.

[0090] Those skilled in the art will recognize that the functions described in this disclosure in one or more of the examples above can be implemented using hardware, software, firmware, or any combination thereof. When implemented in software, these functions can be stored in a computer-readable medium or transmitted as one or more instructions or code on a computer-readable medium. Computer-readable media include computer storage media and communication media, wherein communication media include any medium that facilitates the transfer of a computer program from one place to another. Storage media can be any available medium accessible to a general-purpose or special-purpose computer.

[0091] It should be noted that the technical solutions described in this disclosure can be combined arbitrarily as long as they do not conflict.

[0092] The above description is merely a specific embodiment of this disclosure, but the scope of protection of this disclosure is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for optimizing radiotherapy planning, characterized in that, The method includes: An initial radiotherapy plan is generated for the tumor target area in a medical image; wherein the initial radiotherapy plan includes at least a high-dose lattice and the beam direction corresponding to each high-dose lattice in the high-dose lattice; An optimized radiotherapy plan is obtained by optimizing at least one of the beam direction and the rotational orientation of the high-dose lattice relative to the tumor target region in the initial radiotherapy plan, such that multiple high-dose lattices exist in at least one beam direction.

2. The optimization method according to claim 1, characterized in that, The optimized radiotherapy plan is obtained by optimizing at least one of the beam direction and the rotational orientation of the high-dose lattice relative to the tumor target region in the initial radiotherapy plan, such that multiple high-dose lattices exist in at least one beam direction. This includes: A time cost function is formed based on the overall execution time of the treatment plan, and a penalty function is formed by taking the tolerance dose of the organs at risk and the dose coverage of the high-dose lattice as constraint targets. The objective function of the stochastic optimization algorithm is formed based on the time cost function and the penalty function; The beam direction of each high-dose lattice in the initial radiotherapy plan, or the rotational orientation of the high-dose lattice relative to the tumor target area, or the beam direction of each high-dose lattice and the rotational orientation of the high-dose lattice relative to the tumor target area, are used as inputs to a stochastic optimization algorithm. The algorithm iteratively calculates the algorithm with the objective function as the minimum, and outputs the optimized beam direction of each high-dose lattice, or the optimized rotational orientation of the high-dose lattice relative to the tumor target area, or the optimized beam direction of each high-dose lattice and the rotational orientation of the high-dose lattice relative to the tumor target area.

3. The optimization method according to claim 2, characterized in that, The stochastic optimization algorithm includes simulated annealing, particle swarm optimization, or genetic algorithm.

4. The optimization method according to claim 1, characterized in that, The size of the high-dose lattice in the high-dose lattice is 9 mm to 20 mm.

5. The optimization method according to claim 1, characterized in that, At least two high-dose lattices in the high-dose lattice are of different sizes.

6. The optimization method according to claim 1, characterized in that, At least two high-dose lattice points have different center-to-center spacings.

7. The optimization method according to claim 1, characterized in that, The method further includes: Optimize the arc range of the X-ray beam corresponding to each high-dose lattice to avoid irradiation of the preset sensitive areas.

8. The optimization method according to claim 1, characterized in that, The tumor target region includes subregions with specific biological characteristics, and the high-dose lattice is located in the region of the tumor target region excluding the subregions with specific biological characteristics.

9. The optimization method according to claim 1, characterized in that, At least two high-dose lattices in the high-dose lattice have different irradiation methods.

10. A radiotherapy planning device, characterized in that, The radiotherapy planning equipment includes: Memory that stores executable instructions for a computer; And at least one processing unit configured to execute the computer-executable instructions to cause the radiotherapy planning device to implement the radiotherapy planning optimization method according to any one of claims 1 to 9.

11. A radiotherapy system, characterized in that, The system includes: a radiotherapy planning device and a radiotherapy device that communicate bidirectionally with each other; wherein the radiotherapy planning device is the radiotherapy planning device of claim 10, for generating an optimized radiotherapy plan; and the radiotherapy device is used to perform radiotherapy on a target subject according to the optimized radiotherapy plan.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one instruction, which is executed by a processor to implement the method for optimizing a radiotherapy plan as described in any one of claims 1 to 9.

Images