A method and system for optimizing the delivery direction of radiotherapy robots based on genetic algorithms

Abstract

The present application provides a method and system for optimizing the delivery direction of a radiotherapy robot based on a genetic algorithm, the method comprising: establishing a quasi-periodic respiratory motion model of a tumor based on a particle swarm algorithm, thereby obtaining characteristics such as tumor motion amplitude, phase, and frequency; integrating the tumor respiratory motion characteristics and the expected delivery dose distribution constraints to establish an objective function, optimizing the delivery dose while considering the constraints of tumor motion compensation; designing a genetic algorithm strategy to optimize the selection of a set of radiation spherical delivery directions. Compared with existing methods, the present application takes into account the impact of tumor respiratory motion on delivery direction optimization, while optimizing the spatial distribution of delivery nodes; after optimization, the error between the actual delivery dose and the expected dose can be reduced, and the irradiation dose of the beam to risk tissues can be reduced, providing a more accurate treatment accuracy for the radiotherapy robot.

Description

Technical Field

[0001] The present application relates to the field of medical robot technology, and in particular to a method and system for optimizing the delivery direction of a radiotherapy robot based on a genetic algorithm, which can solve the problem of selecting the beam delivery direction of a stereotactic radiotherapy robot. Background Art

[0002] The selection of beam delivery direction is an important part of the treatment plan made by radiotherapy robots. For tumors with a lot of risk tissue (OAR) around them, traditional coplanar beam delivery will pose a serious threat to the risk tissue. During radiotherapy, the use of non-coplanar beam delivery and the selection and optimization of the beam delivery direction can significantly reduce the difference between the actual delivered dose and the target dose in the target area, while meeting the dose constraints of the risk tissue, ensuring the safety of important tissues around the tumor, and improving the quality of the treatment plan.

[0003] Currently, there are two strategies: manual beam angle selection (BAS) and automatic BAS. With the improvement of the intelligence of the equipment, the scheme of manually performing beam selection based on the geometric structure of the patient's tumor, repeated trials and the experience of the physician has been basically eliminated, and intelligent BAS strategies have begun to emerge in large numbers. Automatic BAS can also be divided into two categories: the first category separates the BAS problem from the flux map optimization (FMO), which is to optimize the weights of beams in different directions so that the actual delivery dose of the selected delivery direction set is closer to the expected value. This type of method first solves the BAS problem based on the dose measurement of the geometric distribution or potential beam set, and then solves the FMO problem through mathematical optimization methods. The second category solves BAS and FMO at the same time, that is, the objective functions of the two are merged, and the FMO problem is solved while selecting the delivery direction according to a total objective function. Beam angle selection optimization is a combinatorial optimization problem, which selects n best delivery directions from N candidate sets, but there is currently no effective algorithm that can solve the BAS problem within polynomial time complexity, that is, BAS is an NP-hard problem, and it is impractical to use enumeration search in clinical practice. So all current solutions can be seen as heuristics that explore only a small part of the search space.

[0004] Although many effective solutions have been proposed for BAS, most of them are BAS methods for static tumors, and few researchers have taken into account clinical scenarios that require compensation for tumor respiratory motion during delivery. Therefore, studying a delivery direction optimization method that can take tumor respiratory motion into account is of great significance for improving the accuracy of radiotherapy robots. Summary of the invention

[0005] In view of this, the purpose of this application is to provide a method for optimizing the delivery direction of a radiotherapy robot based on a genetic algorithm, so as to solve the problem of selecting the beam delivery direction of a stereotactic radiotherapy robot.

[0006] The technical solution of the present application is: a method for optimizing the delivery direction of a radiotherapy robot based on a genetic algorithm, comprising the following steps:

[0007] Step 1: construct a radiation sphere on the body surface according to the spatial accessibility of using a robotic arm to drive the beam to compensate for respiratory motion during radiotherapy, wherein the candidate delivery nodes are within the upper half of the radiation sphere, and select a set of candidate delivery nodes within the upper half of the radiation sphere;

[0008] Step 2: According to the expected delivered dose distribution constraints, formulate the dose distribution objective function for delivery direction optimization;

[0009] Step 3: Analyze the constraints of tumor respiratory motion and fit the quasi-periodic characteristics of tumor respiratory motion based on particle swarm algorithm;

[0010] Step 4, according to the influence of tumor respiratory motion on dose delivery, the quasi-periodic characteristics of the tumor respiratory motion and the expected delivered dose distribution constraint are integrated to establish an optimized objective function;

[0011] Step 5: Design a delivery direction optimization scheme based on the genetic algorithm and optimize the selection of beam direction according to the objective function.

[0012] Furthermore, in step 1, on the upper half of the spherical surface, the direction angle represents any point on the sphere, where θ∈[0°,90°), then The candidate delivery node sets are selected every 6° in the direction and every 5° in the θ direction, and a total of 1080 candidate node sets are selected.

[0013] Furthermore, in step 2, an optimization function h(ω) is set to optimize the dose weight ω of each node; the dose distribution objective function f(X) is set to the value of h(ω) after iterative optimization:

[0014]

[0015] Where X represents the set of radiation angles during the delivery process The set contains n delivery nodes of the radial sphere, and the delivery nodes are determined by the direction angle Denotes that ω is the dose weight at each delivery node;

[0016] The optimization function is defined as:

[0017]

[0018] And: ω ≥ 0

[0019] Among them, human tissues exposed to radiation are divided into N s For different organizations S, different objective functions p are selected. k (ω),λ k represents the weight of the optimization function of the kth organization.

[0020] Furthermore, in step 3, the quasi-periodic motion model of the quasi-periodic characteristics of the tumor respiratory motion is expressed by the following formula:

[0021]

[0022] In the above formula, C 0 , C 1 , A and They represent the baseline position, baseline drift speed, oscillation amplitude and phase offset of the posture parameters respectively, and the values ​​corresponding to different parameters are different; f i Represents the oscillation frequency and period. All posture parameters have the same oscillation frequency. N determines the steepness and flatness of the model shape.

[0023] Furthermore, in step 4, the spatial positions of the candidate delivery nodes are distributed at the peaks and valleys of the respiratory movement.

[0024] Furthermore, in step 4, when the speed of the beam movement is constant during the delivery process, the spacing between two nodes is controlled to be close to half a respiratory motion cycle, so that the spatial distribution of the nodes is close to the peak and valley of the tumor respiratory motion;

[0025] The optimization objective function ensures that the node distribution spacing is close to The delivery is completed within a respiratory cycle, and the tumor motion frequency is obtained according to the quasi-periodic characteristics of the tumor respiratory motion fitted in step 3, and the The movement distance of the beam in each breathing cycle is calculated, and the movement distance is used as the constraint threshold in the optimization objective function to ensure that the distribution spacing of the delivery nodes is close to the constraint threshold.

[0026] Furthermore, in step 5, a delivery node optimization scheme is designed based on a genetic algorithm, and n delivery directions are selected from the candidate delivery node set in step 1 according to the objective function; the objective function established in step 4 is optimized using a genetic algorithm; the radiation sphere is evenly divided according to the number of beams, and an optimization node is selected in the plane of each direction to obtain the optimal delivery node set.

[0027] Based on the above purpose, the present application also proposes a radiotherapy robot delivery direction optimization system based on genetic algorithm, including:

[0028] A node set module, for constructing a radiation sphere on the body surface according to the spatial accessibility of compensating for respiratory motion using a robotic arm to drive the beam during radiotherapy, with candidate delivery direction nodes within the upper half of the radiation sphere, and selecting a candidate node set within the upper half of the radiation sphere;

[0029] Function building module, used to formulate the dose distribution objective function for delivery direction optimization according to the expected delivered dose distribution constraints;

[0030] Feature fitting module, used to analyze the constraints of tumor respiratory motion and fit the quasi-periodic characteristics of tumor respiratory motion based on particle swarm algorithm;

[0031] A function optimization module is used to establish an optimized objective function based on the influence of tumor respiratory motion on dose delivery and integrating the quasi-periodic characteristics of tumor respiratory motion and the constraints of expected delivered dose distribution;

[0032] The direction optimization module is used to design a delivery direction optimization scheme based on a genetic algorithm and optimize the selection of beam direction according to the objective function.

[0033] In general, the advantages of this application and the experience it brings to users are: this application provides a method for solving the optimization of the delivery direction of radiotherapy robots, combining the delivery direction selection and flux map optimization problems, optimizing the weights of beams in each direction while optimizing the node distribution, and taking the influence of tumor respiratory motion into account, and formulating an optimization objective function that integrates the respiratory motion characteristics of the tumor and the constraints of the expected delivery dose distribution; to solve the NP-hard combinatorial optimization problem, this application proposes an optimization strategy based on a genetic algorithm, and at the same time, in order to ensure that the beam can fully irradiate all directions of the tumor, the radiation sphere is evenly divided according to the number of beams, and a node is selected in each plane in each direction to ensure that the tumor can be fully irradiated. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the multiple drawings represent the same or similar parts or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings only depict some embodiments disclosed in the present application and should not be regarded as limiting the scope of the present application.

[0035] Figure 1 This is a flow chart of the method for optimizing the delivery direction of a radiotherapy robot based on a genetic algorithm according to the first embodiment of the present application.

[0036] Figure 2 This is the candidate node set of embodiment 1 of the present application.

[0037] Figure 3 A set of delivery directions selected based on the method proposed in this application.

[0038] Figure 4 A structural diagram of a radiotherapy robot delivery direction optimization system based on a genetic algorithm according to an embodiment of the present application is shown.

[0039] Figure 5 A schematic structural diagram of an electronic device provided in one embodiment of the present application is shown.

[0040] Figure 6 A schematic diagram of a storage medium provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0041] The present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the relevant invention, rather than to limit the invention. It is also necessary to explain that, for ease of description, only the parts related to the relevant invention are shown in the accompanying drawings.

[0042] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0043] In order to achieve the purpose of this application, Figure 1 As shown, in one embodiment of the present application, a method for optimizing the delivery direction of a radiotherapy robot based on a genetic algorithm comprises the following steps:

[0044] In step 1, the robotic arm is used to drive the beam to compensate for the respiratory movement of the tumor. In order to prevent the influence of the medical bed on the beam dose and the obstacle avoidance of the robotic arm movement, the delivery direction is considered to be on the upper part of the patient's body surface. At the same time, considering that the distance from the radiation source to the center of the tumor (source wheelbase) is constant, the candidate delivery direction node set is selected in the upper half of the radiation sphere centered on the tumor.

[0045] On the upper half of the radiation sphere centered on the tumor, the direction angle represents any point on the sphere, where θ∈[0°,90°), then The candidate delivery node set is selected every 6° in the direction and every 5° in the θ direction. The final candidate node set is as follows Figure 2 shown.

[0046] In step 2, an evaluation function for node selection is formulated according to the target delivered dose, which ensures that the distribution of delivery directions can meet the target dose requirements while satisfying the dose constraints of risk tissues (OARs).

[0047] The objective function f(X) that ensures that the beam dose distribution is close to the expected value involves the flux map optimization (FMO) problem, that is, after dose calculation and FMO optimization, the difference between the actual delivered dose and the expected delivered dose of the currently selected set of delivery nodes X can be evaluated, and the dose constraints of the risk tissue (OAR) can be taken into account to evaluate the impact of this group of nodes on the OAR tissue. In the FMO optimization process, an optimization function h(ω) is set to optimize the dose weight ω of each node so that the difference between the dose accumulation and the expected dose in the actual delivery process is minimized, and the constraints of the risk tissue are taken into account.

[0048] The size of h(ω) after iterative optimization will be affected by the spatial distribution position of the nodes. The better the node distribution position, the smaller the value of the final optimization function h(ω). Therefore, the objective function f(X) that ensures that the beam dose distribution is close to the expected value can be set to the value of h(ω) after iterative optimization:

[0049]

[0050] Where X represents the set of radiation angles during the delivery process The set contains n delivery nodes of the radial sphere, and the spherical delivery nodes are determined by the direction angle Denotes , and ω is the dose weight at each delivery node.

[0051] The FMO optimization function is defined as:

[0052]

[0053] And: ω ≥ 0

[0054] Human tissues exposed to radiation can be divided into N s For different tissues S, different objective functions p can be selected. k (ω),λ k represents the weight of the optimization function for the kth tissue, with higher λ for target and high-risk tissues and lower weight for non-high-risk tissues. The positivity constraint ω ≥ 0 ensures that only positive radiation effects are considered.

[0055] The target area objective function in tissue S is defined as:

[0056]

[0057] where k∈S Target Indicates p k is the target area objective function; is the expected dose of tissue S; the tissue S is divided into many voxel blocks to calculate the dose, d ij represents the delivered dose of the jth beam to the i-th voxel block, ω jis the weight of the jth beam; Θ(·) is the Heaviside function.

[0058] The maximum dose constraint is used for OAR tissue, and its constraint function is defined as:

[0059]

[0060] and:

[0061] where k∈S OAR Indicates p k is the OAR constraint function, d max It is the maximum confined dose that the OAR tissue can withstand. and represents the kth constraint function p k (ω) is the lower and upper bounds, κ is the parameter of the LSE (LogSumExp) function, and κ can be taken as 10 -3 .

[0062] Ordinary tissues use mean dose constraints, and their constraint function is defined as:

[0063]

[0064] and:

[0065] where k∈S others Indicates p k is a general organizational constraint function, and represents the kth constraint function p k The lower and upper bounds of (ω), n s is the number of voxel blocks into which tissue S is segmented.

[0066] In step 3, in order to consider the impact of tumor respiratory motion on dose delivery, the periodic characteristics of tumor respiratory motion were fitted based on the particle swarm algorithm (PSO), and the amplitude, phase and frequency of tumor motion were analyzed.

[0067] Taking one dimension of the tumor posture as an example, considering the influence of its baseline drift, its quasi-periodic motion model can be expressed as follows:

[0068]

[0069] In the above formula, C 0 , C 1 , A and They represent the baseline position, baseline drift speed, oscillation amplitude and phase offset of the posture parameters respectively, and the values ​​corresponding to different parameters are different; f iRepresents the oscillation frequency and period, and all posture parameters have the same oscillation frequency; N represents the number of sin functions with different frequencies and phases contained in the motion model, and its value represents the steepness and flatness of the model shape. In the example, the quasi-periodic motion model of the tumor is fitted by the particle swarm optimization (PSO) with adaptive inertia factor.

[0070] In step 4, the problems existing in the prediction of tumor respiratory motion during the delivery process are analyzed, and the defects in tumor position prediction are compensated by optimizing the spatial distribution of delivery nodes. In order to compensate for the respiratory motion of the tumor during radiotherapy, it is usually practiced to establish a correlation model of tumor motion through external signals and predict the movement position of the tumor in real time. However, when the correlation model predicts the tumor position, the prediction accuracy at the peak and valley of the tumor motion is low. On the contrary, the prediction accuracy of the tumor movement between the peak and valley is higher. Therefore, it is considered to distribute the spatial position of the nodes at the peak and valley of the respiratory motion, so as to ensure a more accurate delivery dose during the delivery process of compensating for the respiratory motion.

[0071] Considering the influence of tumor respiratory motion, the evaluation function of the spatial distribution of delivery nodes is formulated. The delivery dose distribution constraint and the spatial distribution constraint of delivery nodes in step 2 are integrated to formulate the objective function for optimizing the final delivery direction. In order to make the spatial position of delivery nodes distributed at the peak and valley of tumor respiratory motion, when the speed of beam motion is constant during delivery, the spatial distribution of nodes can be made close to the peak and valley of tumor respiratory motion by controlling the distance between two nodes to be close to half a respiratory motion cycle. Ensure that the node distribution spacing is close to The objective function of delivering within a breathing cycle is set as g(X). According to step 3, the quasi-periodic motion characteristics of the tumor are fitted to obtain the tumor motion frequency and calculate The movement distance d of the beam in one breathing cycle c , and use this distance as the constraint threshold in the objective function to ensure that the distribution distance of delivery nodes is close to this threshold.

[0072]

[0073] in is the beam projection on Angular velocity in the direction, f t is the frequency of tumor respiratory motion fitting. The function of g(X) is to control the distance between two nodes to be closer to the threshold d c , then g(X) is defined as:

[0074]

[0075] Finally, the overall objective function integrating the tumor respiratory motion characteristics and the desired delivered dose distribution constraints is defined as:

[0076]

[0077] Where α and β are the weights of the objective function.

[0078] In step 5, a delivery node optimization scheme is designed based on a genetic algorithm, and according to the objective function, n delivery directions are selected from the set of candidate delivery nodes in step 1. In clinical applications, 20 delivery directions are usually selected for dose delivery, so this embodiment selects 20 of the 1080 candidate nodes as optimization targets. The objective function established in step 4 is optimized using a genetic algorithm. At the same time, in order to ensure that all directions of the tumor can be irradiated by the beam, the radiation sphere is evenly divided according to the number of beams, and a better node is selected in each direction of the plane to eventually plan the optimal set of delivery nodes. This application was experimented on the open source simulation platform matRad, and a set of delivery directions was selected such as Figure 3 shown.

[0079] The application embodiment provides a radiotherapy robot delivery direction optimization system based on genetic algorithm, which is used to execute the radiotherapy robot delivery direction optimization method based on genetic algorithm described in the above embodiment, such as Figure 4 As shown, the system includes:

[0080] A node set module 501 is used to construct a radiation sphere on the body surface according to the spatial accessibility of compensating for respiratory motion using a robotic arm to drive the beam during radiotherapy, wherein the candidate delivery direction nodes are within the upper half of the radiation sphere, and select a candidate node set within the radiation sphere;

[0081] Function construction module 502, for formulating a dose distribution objective function for delivery direction optimization according to the expected delivered dose distribution constraints;

[0082] A feature fitting module 503 is used to analyze the tumor respiratory motion constraints and fit the quasi-periodic features of the tumor respiratory motion based on a particle swarm algorithm;

[0083] A function optimization module 504 is used to establish an optimized objective function based on the effect of tumor respiratory motion on dose delivery, integrating the quasi-periodic characteristics of tumor respiratory motion and the constraints of expected delivered dose distribution;

[0084] The direction optimization module 505 is used to design a delivery direction optimization scheme based on a genetic algorithm and optimize the selection of the beam direction according to the objective function.

[0085] The genetic algorithm-based radiotherapy robot delivery direction optimization system provided in the above-mentioned embodiments of the present application and the genetic algorithm-based radiotherapy robot delivery direction optimization method provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0086] The embodiment of the present application also provides an electronic device corresponding to the method for optimizing the delivery direction of a radiotherapy robot based on a genetic algorithm provided in the above embodiment, so as to execute the method for optimizing the delivery direction of a radiotherapy robot based on a genetic algorithm. The embodiment of the present application is not limited.

[0087] Please refer to Figure 5 , which shows a schematic diagram of an electronic device provided by some embodiments of the present application. Figure 5 As shown, the electronic device 20 includes: a processor 200, a memory 201, a bus 202 and a communication interface 203, and the processor 200, the communication interface 203 and the memory 201 are connected via the bus 202; the memory 201 stores a computer program that can be run on the processor 200, and when the processor 200 runs the computer program, it executes the genetic algorithm-based radiotherapy robot delivery direction optimization method provided in any of the aforementioned embodiments of the present application.

[0088] The memory 201 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk memory. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 203 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.

[0089] The bus 202 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The memory 201 is used to store a program, and the processor 200 executes the program after receiving an execution instruction. The method for optimizing the delivery direction of a radiotherapy robot based on a genetic algorithm disclosed in any of the embodiments of the present application may be applied to the processor 200, or implemented by the processor 200.

[0090] The processor 200 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 200. The above processor 200 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a readily available programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware decoding processor to be executed, or the hardware and software modules in the decoding processor can be executed. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 201, and the processor 200 reads the information in the memory 201 and completes the steps of the above method in combination with its hardware.

[0091] The electronic device provided in the embodiment of the present application and the method for optimizing the delivery direction of a radiotherapy robot based on a genetic algorithm provided in the embodiment of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, operated or implemented therein.

[0092] The present application also provides a computer-readable storage medium corresponding to the method for optimizing the delivery direction of a radiotherapy robot based on a genetic algorithm provided in the above-mentioned embodiment. Figure 6 The computer-readable storage medium shown is a CD 30 on which a computer program (i.e., a program product) is stored. When the computer program is run by the processor, it will execute the genetic algorithm-based radiotherapy robot delivery direction optimization method provided in any of the aforementioned embodiments.

[0093] It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical or magnetic storage media, which are not listed here one by one.

[0094] The computer-readable storage medium provided in the above-mentioned embodiments of the present application and the genetic algorithm-based radiotherapy robot delivery direction optimization method provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0095] It should be noted that:

[0096] The algorithms and displays provided herein are not inherently related to any particular computer, virtual system or other device. Various general purpose systems may also be used together with the teachings based thereon. It is apparent from the above description that the structure required for constructing such systems is not intended for any particular programming language. In addition, the present application is not intended for any particular programming language either. It should be understood that the content of the present application described herein may be implemented using various programming languages, and the description of the particular language above is intended to disclose the best mode of implementation of the present application.

[0097] In the description provided herein, a large number of specific details are described. However, it is understood that the embodiments of the present application can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0098] Similarly, it should be understood that in order to streamline the present application and help understand one or more of the various inventive aspects, in the above description of the exemplary embodiments of the present application, the various features of the present application are sometimes grouped together into a single embodiment, figure, or description thereof. However, the disclosed method should not be interpreted as reflecting the following intention: the claimed application requires more features than the features clearly stated in each claim. More specifically, as reflected in the claims below, the inventive aspects are less than all the features of the single embodiment disclosed above. Therefore, the claims following the specific embodiment are hereby expressly incorporated into the specific embodiment, wherein each claim itself serves as a separate embodiment of the present application.

[0099] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and in addition they may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this manner may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0100] In addition, those skilled in the art will appreciate that, although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present application and form different embodiments. For example, in the claims below, any one of the claimed embodiments may be used in any combination.

[0101] The various component embodiments of the present application can be implemented in hardware, or implemented in software modules running on one or more processors, or implemented in a combination thereof. It should be understood by those skilled in the art that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all functions of some or all components in the creation system of the virtual machine according to the embodiment of the present application. The application can also be implemented as a device or system program (for example, a computer program and a computer program product) for performing a part or all of the methods described herein. Such a program implementing the present application can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0102] It should be noted that the above embodiments illustrate the present application rather than limit the present application, and that those skilled in the art may design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets should not be constructed as a limitation to the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of multiple such elements. The present application may be implemented by means of hardware including several different elements and by means of appropriately programmed computers. In a unit claim that lists several systems, several of these systems may be embodied by the same hardware item. The use of the words first, second, and third, etc. does not indicate any order. These words may be interpreted as names.

[0103] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for optimizing the delivery direction of radiotherapy robots based on genetic algorithms, It is characterized in that The steps include: Step 1: construct a radiation sphere on the body surface according to the spatial accessibility of using a robotic arm to drive the beam to compensate for respiratory motion during radiotherapy, wherein the candidate delivery nodes are within the upper half of the radiation sphere, and select a set of candidate delivery nodes within the upper half of the radiation sphere; Step 2: According to the expected delivered dose distribution constraints, formulate the dose distribution objective function for delivery direction optimization; Step 3: Analyze the constraints of tumor respiratory motion and fit the quasi-periodic characteristics of tumor respiratory motion based on particle swarm algorithm; Step 4, according to the influence of tumor respiratory motion on dose delivery, the quasi-periodic characteristics of the tumor respiratory motion and the expected delivered dose distribution constraint are integrated to establish an optimized objective function; Step 5: Design a delivery direction optimization scheme based on a genetic algorithm and optimize the selection of beam direction according to the objective function; In step 4, the spatial positions of the candidate delivery nodes are distributed at the peaks and valleys of the respiratory motion; when the speed of the beam motion is constant during the delivery process, the distance between the two nodes is controlled to be close to half a respiratory motion cycle, so that the spatial distribution of the nodes is close to the peaks and valleys of the tumor respiratory motion; The optimization objective function ensures that the node distribution spacing is close to The delivery is completed within a respiratory cycle, and the tumor motion frequency is obtained according to the quasi-periodic characteristics of the tumor respiratory motion fitted in step 3, and the The movement distance of the beam in each breathing cycle is calculated, and the movement distance is used as the constraint threshold in the optimization objective function to ensure that the distribution spacing of the delivery nodes is close to the constraint threshold.

2. The method for optimizing the delivery direction of a radiotherapy robot based on a genetic algorithm according to claim 1, Features: In step 1, on the upper half of the spherical surface, the direction angle represents any point on the sphere, where Then press The candidate delivery node sets are selected every 6° in the direction and every 5° in the θ direction, and a total of 1080 candidate node sets are selected.

3. The method for optimizing the delivery direction of a radiotherapy robot based on a genetic algorithm according to claim 1 or 2, Features: In step 2, an optimization function h(ω) is set to optimize the dose weight ω of each node; the dose distribution objective function f(X) is set to the value of h(ω) after iterative optimization: Where X represents the set of radiation angles during the delivery process The set contains n delivery nodes of the radial sphere, and the delivery nodes are determined by the direction angle Denotes that ω is the dose weight at each delivery node; The optimization function is defined as: And: ω ≥ 0 Among them, human tissues exposed to radiation are divided into N s For different organizations S, different objective functions p are selected. k (ω),λ k represents the weight of the optimization function of the kth organization.

4. The method for optimizing the delivery direction of a radiotherapy robot based on a genetic algorithm according to claim 3, Features: In step 3, the quasi-periodic motion model of the quasi-periodic characteristics of the tumor respiratory motion is expressed by the following formula: In the above formula, C 0 , C 1 , A and They represent the baseline position, baseline drift speed, oscillation amplitude and phase offset of the posture parameters respectively, and the values ​​corresponding to different parameters are different; f i Represents the oscillation frequency and period, all posture parameters have the same oscillation frequency; N determines the steepness and flatness of the model shape.

5. The method for optimizing the delivery direction of a radiotherapy robot based on a genetic algorithm according to claim 1, Features: In step 5, a delivery node optimization scheme is designed based on a genetic algorithm. According to the objective function, n delivery directions are selected from the candidate delivery node set in step 1. The objective function established in step 4 is optimized using a genetic algorithm. The radiation sphere is evenly divided according to the number of beams, and an optimization node is selected in the plane of each direction to obtain the optimal delivery node set.

6. A radiotherapy robot delivery direction optimization system based on genetic algorithm, using the method described in any one of claims 1 to 5, It is characterized in that include: A node set module, for constructing a radiation sphere on the body surface according to the spatial accessibility of compensating for respiratory motion using a robotic arm to drive the beam during radiotherapy, wherein the candidate delivery nodes are within the upper half of the radiation sphere, and selecting a set of candidate delivery nodes within the upper half of the radiation sphere; Function building module, used to formulate the dose distribution objective function for delivery direction optimization according to the expected delivered dose distribution constraints; Feature fitting module, used to analyze the constraints of tumor respiratory motion and fit the quasi-periodic characteristics of tumor respiratory motion based on particle swarm algorithm; A function optimization module is used to establish an optimized objective function based on the influence of tumor respiratory motion on dose delivery and integrating the quasi-periodic characteristics of tumor respiratory motion and the constraints of expected delivered dose distribution; The direction optimization module is used to design a delivery direction optimization scheme based on a genetic algorithm and optimize the selection of beam direction according to the objective function.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, It is characterized in that The processor runs the computer program to implement the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, It is characterized in that The program is executed by a processor to implement the method according to any one of claims 1 to 5.

Images