System, method and device for optimizing particle implantation plan

Abstract

The embodiment of the invention provides a particle implantation plan optimization system, method and device, and the system comprises a processor which is used for executing the following operations: obtaining a particle implantation plan of a target object; the particle implantation plan comprises a puncture needle sequence and particle distribution corresponding to each puncture needle in the puncture needle sequence; determining an optimization object and an optimization target based on the particle implantation plan; the optimization object comprises a puncture needle in the puncture needle sequence and / or particle distribution corresponding to the puncture needle; and based on the optimization object and the optimization target, performing optimization processing on the particle implantation plan, and determining a target particle implantation plan.

Description

Technical Field

[0001] The present specification relates to the field of radiotherapy, and in particular to a particle implantation plan optimization system, method and device. Background Art

[0002] Seed implantation is a close-range radiotherapy technique that is suitable for the treatment of a variety of tumors. In order to improve the efficacy and local control rate of tumors and ensure the smooth progress of the operation, a seed implantation plan must be formulated before the seed implantation operation is performed.

[0003] This specification provides a particle implantation plan optimization system, method and device, which improves the accuracy of the existing preoperative planning system by optimizing the preoperative particle implantation plan, thereby providing the possibility for better therapeutic effects. Summary of the invention

[0004] One or more embodiments of the present specification provide a particle implantation plan optimization system, the system comprising a processor, the processor being configured to perform the following operations: obtaining a particle implantation plan for a target object; the particle implantation plan comprising a puncture needle sequence and a particle distribution corresponding to each puncture needle in the puncture needle sequence; determining an optimization object and an optimization target based on the particle implantation plan; the optimization object comprising the puncture needles in the puncture needle sequence and / or the particle distribution corresponding to the puncture needles; optimizing the particle implantation plan based on the optimization object and the optimization target to determine a target particle implantation plan.

[0005] One or more embodiments of the present specification provide a particle implantation plan optimization method, the method comprising: obtaining a particle implantation plan for a target object; the particle implantation plan comprising a puncture needle sequence and a particle distribution corresponding to each puncture needle in the puncture needle sequence; determining an optimization object and an optimization target based on the particle implantation plan; the optimization object comprises the puncture needles in the puncture needle sequence and / or the particle distribution corresponding to the puncture needles; based on the optimization object and the optimization target, optimizing the particle implantation plan to determine a target particle implantation plan.

[0006] One or more embodiments of the present specification provide a particle implantation plan optimization device, including a processor, wherein the processor is used to execute a particle implantation plan optimization method.

[0007] One or more embodiments of the present specification provide a computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes a particle implantation plan optimization method. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0009] Figure 1 is a schematic diagram of an application scenario of a particle implantation plan optimization system according to some embodiments of this specification;

[0010] Figure 2 is an exemplary flow chart of a particle implantation plan optimization method according to some embodiments of the present specification;

[0011] Figure 3 is an exemplary flow chart for optimizing the puncture parameters of the puncture needle according to some embodiments of this specification;

[0012] Figure 4 is an exemplary flow chart for optimizing position parameters of particles according to some embodiments of this specification;

[0013] Figure 5 is an exemplary flow chart for optimizing puncture parameters and position parameters according to some embodiments of this specification;

[0014] Figure 6 is an exemplary schematic diagram of a DVH curve according to some embodiments of this specification;

[0015] Figure 7 is an exemplary schematic diagram of particle position modeling according to some embodiments of this specification;

[0016] Figure 8 is an exemplary schematic diagram of particle quantity modeling according to some embodiments of this specification;

[0017] Fig. 9 It is an exemplary schematic diagram of target area dose coverage according to some embodiments of the present specification. DETAILED DESCRIPTION

[0018] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0019] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0020] As shown in this specification and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprise" and "include" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0021] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0022] The full name of particle implantation is "radioactive particle implantation therapy technology". It belongs to the close-range radiotherapy technology and is a local treatment method that can accurately destroy tumor cells. The working mechanism of particle implantation to treat tumors is to puncture through imaging guidance technology (such as CT, ultrasound, etc.) to implant particles carrying radioactive nuclides (such as I-125) into the tumor or around the tumor. Radioactive nuclides continuously release low-energy gamma rays inside the tumor, which have a strong killing effect on tumor cells and little damage to adjacent cancerous tissues, thereby achieving the effect of local tumor treatment.

[0023] In order to improve the efficacy and local control rate of tumors and ensure the smooth progress of the operation, a particle implantation plan needs to be formulated before the particle implantation operation is performed. Particle implantation plans are divided into manual planning and automatic planning. Manual planning requires doctors to manually arrange the puncture needle based on their experience, and the quality of the plan depends largely on the physician's experience; automatic planning relies less on the physician's experience and can provide a time-consuming and acceptable plan. During the planning process, the search space often needs to be limited and downsampled. Both of the above methods can give feasible planning results, but there is still much room for improvement in the quality of the plan.

[0024] In order to improve the quality of particle implantation plans, some embodiments of this specification provide a particle implantation plan optimization system, method and device, which can improve the accuracy of existing preoperative planning systems by performing post-processing optimization on the planned particle implantation plans, thereby providing the possibility for better therapeutic effects.

[0025] Figure 1It is a schematic diagram of an application scenario of a particle implantation plan optimization system according to some embodiments of this specification.

[0026] like Figure 1 As shown, the particle implantation plan optimization system 100 may include a surgical robot device 110 , a network 120 , a terminal 130 , a processing device 140 , and a storage device 150 .

[0027] In some embodiments, the seed implantation plan optimization system 100 can be used to further optimize the completed seed implantation surgery plan to better assist doctors in performing seed implantation surgery.

[0028] The surgical robot device 110 can be used to perform corresponding operations according to the received instructions (e.g., control signal instructions). In some embodiments, the surgical robot device 110 includes a surgical robot, a medical device, and a mobile bed. When the surgical robot device 110 receives data or instructions sent by other devices or system components, the mobile bed can carry the patient to the position indicated by the instruction, the medical device starts the working state according to the instruction, and the surgical robot performs surgery based on the instruction (e.g., performing particle implantation surgery). In some embodiments, the surgical robot includes a mechanical arm and an end instrument (e.g., including end clamps, puncture needles and other surgical instruments). When the surgical robot receives data or instructions sent by other devices or system components, the mechanical arm on the surgical robot moves to move the end instrument to the position indicated by the instruction and perform surgical actions (e.g., inserting the puncture needle into the patient's body). In some embodiments, the surgical robot can be integrated with the medical device or can be separated. For example, the bottom of the surgical robot includes a bottom cart, and the surgical robot can be moved to a suitable position by the bottom cart to perform interventional surgery. In some embodiments, the surgical robot may also be provided with a sensor to detect kinematic parameters (e.g., position, angle, speed, etc.) when the connecting rod moves, and feed the kinematic parameters back to the processing device 140 or the terminal 130. In some embodiments, the surgical robot may also be provided with a camera to obtain an image of the surgical robot and its environment, and send the image to the processing device 140 or the terminal 130.

[0029] The network 120 includes any suitable network capable of facilitating information and / or data exchange of the surgical robot device 110. In some embodiments, at least one component of the particle implantation plan optimization system 100 (e.g., the surgical robot device 110, the terminal 130, the processing device 140, the storage device 150) can exchange information and / or data with at least one other component in the particle implantation plan optimization system 100 through the network 120. For example, the processing device 140 can obtain a medical image of a target object from the terminal 130 through the network 120. For another example, the processing device 140 can perform particle implantation planning based on the obtained medical image of the target object, and send the results of the particle implantation planning (e.g., the particle implantation plan) to other components in the system, such as to the terminal 130 for display, etc. In some embodiments, the processing device 140 can also optimize the obtained particle implantation plan to obtain a target particle implantation plan. In some embodiments, the network 120 includes at least one network access point. For example, the network 120 includes wired and / or wireless network access points (eg, base stations and / or Internet exchange points), and at least one component of the particle implantation planning optimization system 100 can be connected to the network 120 through the access points to exchange data and / or information.

[0030] The terminal 130 can communicate and / or connect with the surgical robot device 110, the processing device 140 and / or the storage device 150. In some embodiments, the terminal 130 includes a mobile device 131, a tablet computer 132, a laptop computer 133, etc. or any combination thereof. For example, the mobile device 131 includes a mobile control handle, a personal digital assistant (PDA), a smart phone, etc. or any combination thereof. In some embodiments, the terminal 130 includes a display device, such as a display. The display device can be used to display information or images related to the interventional surgery, such as a particle implantation plan, prompt information, a target particle implantation plan, a medical image of a patient, a three-dimensional model, or an operation panel related to the interventional surgery. In some embodiments, the terminal 130 is part of the processing device 140.

[0031] The processing device 140 can process data and / or information obtained from the surgical robot device 110, the terminal 130, the storage device 150, or other components of the particle implantation plan optimization system 100. For example, the processing device 140 can obtain a particle implantation plan for a target object; determine an optimization object and an optimization target based on the particle implantation plan; and optimize the particle implantation plan based on the optimization object and the optimization target to determine a target particle implantation plan. In some embodiments, the processing device 140 can be a single server or a server group, or it can be centralized or distributed. In some embodiments, the processing device 140 can be local or remote. For example, the processing device 140 can access information and / or data from the surgical robot device 110, the storage device 150, and / or the terminal 130 through the network 120. For another example, the processing device 140 can be directly connected to the surgical robot device 110, the terminal 130, and / or the storage device 150 to access information and / or data. For another example, the processing device 140 can be installed on the surgical robot device 110. In some embodiments, the processing device 140 can be implemented on a cloud platform. For example, the cloud platform includes private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, cloud-to-cloud, multi-cloud, etc. or any combination thereof.

[0032] The storage device 150 can be used to store data, instructions and / or any other information. For example, the storage device 150 can store data obtained from the surgical robot device 110, the terminal 130 and / or the processing device 140. In some embodiments, the storage device 150 can store data and / or instructions used by the processing device 140 to execute or use to complete the exemplary methods described in this specification. In some embodiments, the storage device 150 includes a large-capacity memory, a removable memory, a volatile read-write memory, a read-only memory (ROM), etc. or any combination thereof. In some embodiments, the storage device 150 is implemented on a cloud platform.

[0033] In some embodiments, the storage device 150 is connected to the network 120 to communicate with at least one other component (e.g., the processing device 140, the terminal 130) in the particle implantation plan optimization system 100. At least one component in the particle implantation plan optimization system 100 accesses data stored in the storage device 150 through the network 120. In some embodiments, the storage device 150 is part of the processing device 140. In some embodiments, the processing device 140 and the storage device 150 are integrated in the surgical robot device 110.

[0034] It should be noted that the above description is provided for illustrative purposes only and is not intended to limit the scope of this specification. For those of ordinary skill in the art, various changes and modifications can be made under the guidance of the contents of this specification. The features, structures, methods and other features of the exemplary embodiments described in this specification can be combined in various ways to obtain additional and / or alternative exemplary embodiments. For example, the storage device 150 is a data storage device 150 including a cloud computing platform, such as a public cloud, a private cloud, a community and a hybrid cloud. However, these changes and modifications will not deviate from the scope of this specification.

[0035] Figure 2 FIG. 1 is an exemplary flow chart of a particle implantation plan optimization method according to some embodiments of the present specification. Figure 2 As shown, the process 200 includes the following steps. In some embodiments, the process 200 may be executed by a particle implantation plan optimization system or a processing device (eg, the processing device 140).

[0036] Step 210: Obtain a particle implantation plan for the target object.

[0037] The target object includes the whole or part of the biological object and / or non-biological object involved. For example, the target object can be living or non-living organic and / or inorganic matter, such as the head, ears, nose, mouth, neck, chest, abdomen, liver, gallbladder, pancreas, spleen, kidneys, spine, etc.

[0038] Particle implantation planning refers to the process of using imaging techniques (such as CT, MRI, etc.) to assist in determining the position and angle of the puncture needle before the particle implantation surgery so that the particles in the puncture needle can be accurately positioned in the target area. In some embodiments, the particle implantation plan includes a puncture needle sequence and the particle distribution corresponding to each puncture needle in the puncture needle sequence.

[0039] In some embodiments, the particle implantation plan is divided into coplanar planning and non-coplanar planning. Coplanar planning refers to planning a set of parallel puncture needles so that the particle distribution therein can meet the dose requirements. Non-coplanar planning means that the planned puncture needles may not be parallel in space.

[0040] The puncture needle sequence is a set of multiple planned puncture needles. The planned puncture needles include the puncture path, needle spacing, needle insertion angle and needle insertion depth of the puncture needle. The puncture path of the puncture needle refers to the path that the puncture needle passes through when it enters the target area from the skin surface during puncture. The puncture path can be represented by the needle entry point of the puncture needle on the skin surface and its corresponding target point on the target area surface. The needle spacing refers to the spacing between the puncture needles, the needle insertion angle refers to the angle between the puncture needle and the skin surface normal vector of the target object when the puncture needle is inserted, and the needle insertion depth refers to the length of the puncture needle entering the target object after puncture.

[0041] Particle distribution refers to the placement of particles within the puncture needle.

[0042] In some embodiments, the processing device can obtain a particle implantation plan by executing particle implantation planning, for example, obtaining the particle implantation plan by manual planning or automatic planning. Manual planning refers to the physician placing needles in the treatment planning system based on clinical experience and arranging particles in the needles so that the target dose coverage meets the standard. Automatic planning is to optimize the puncture needle and particle spatial distribution according to pre-set optimization goals (such as target dose coverage, maximizing the target conformity of the dose distribution, and meeting the maximum dose limit of important organs, etc.) using planning algorithms (for example, simulated annealing algorithms and genetic algorithms, etc.). In some embodiments, the two can also be combined, such as obtaining a particle implantation plan by combining manual planning with automatic planning. This specification does not limit the specific planning method of the particle implantation plan.

[0043] In some embodiments, the processing device can also obtain the particle implantation plan by reading a pre-stored particle implantation plan from a storage device or a database.

[0044] Step 220: Determine the optimization object and optimization goal based on the particle implantation plan.

[0045] The optimization object is an abstract description of the object to be adjusted in the particle implantation plan. In some embodiments, the optimization object includes the puncture needles in the puncture needle sequence and / or the particle distribution corresponding to the puncture needles.

[0046] The optimization goal refers to the preset goal that you want to achieve by optimizing the optimization object.

[0047] In some embodiments, the optimization target includes an overall optimization target and / or a local optimization target. For example, the optimization target may include only the overall optimization target or the local optimization target, or may include both the overall optimization target and the local optimization target.

[0048] In some embodiments, the overall optimization goal includes target dose coverage of seed implantation and / or organ dose irradiation.

[0049] Target dose coverage refers to the degree of coverage of the target area by the dose released by the radioactive particles. Taking the target dose coverage as the overall optimization goal can ensure that the dose released by the radioactive particles can cover the entire target area to fully damage the tumor tissue and ensure the efficacy. In some embodiments, the dose coverage can be evaluated by a dose distribution map. The dose distribution map shows the distribution of the energy released by the radioactive particles in the tissue. Organ dose radiation refers to the dose generated in the surrounding organs after the rays of particle radiation pass through the target area.

[0050] In some embodiments, the processing device can evaluate the particle implantation plan and determine the optimization object and the optimization target based on the evaluation result. For example, the processing device can quantitatively evaluate the particle implantation plan and determine the plan risk information; issue a prompt to the user based on the plan risk information; and receive confirmation information input by the user, and determine the optimization object and the optimization target based on the confirmation information and the plan risk information.

[0051] Quantitative evaluation refers to the process of using quantitative methods and data to evaluate or measure. Through quantitative evaluation, the possible risks in the current particle implantation plan can be determined. These possible risks are the plan risk information. In some embodiments, the plan risk information includes the presence of cold spots and / or hot spots in the dose space corresponding to the target area, the distance between the puncture needle and the target tissue is less than the safe distance, and the degree of dispersion of the puncture needle layout. For more information about plan risk information, please refer to the following text Figure 3 Related description in .

[0052] In some embodiments, the particle implantation optimization system issues corresponding prompts to the user based on the planned risk information in a manner including pop-up windows, voice, and text. The user can interact with the issued prompts or within the system (if the user does not recognize the risk, the particle implantation plan may not be optimized). For example, by interactively inputting confirmation information, indicating that the user recognizes the planned risk information, the system can determine the optimization object and the optimization target based on the planned risk information. For example, when there are hot spots and / or cold spots in the dose space corresponding to the target area, the system can confirm that the optimization object is the particle distribution in the puncture needle, and the optimization target includes the overall optimization target (overall optimization) and / or the local optimization target (optimization for hot spots and cold spots). This embodiment does not limit the input determination information of the user interaction method. For example, the interaction method includes clicking, sliding, or pull-down selection, and the user input method includes external device input (for example, mouse and keyboard, etc.), voice input, and gesture input.

[0053] In some embodiments, the overall optimization goal can be determined based on a preset treatment plan, for example, the dose coverage of the entire target area should reach a certain value, the organ dose radiation should be less than a certain value, etc.

[0054] In some embodiments, the local optimization target includes the local dose coverage of the target area of ​​the particle implantation. The local dose coverage of the target area refers to the dose coverage of a certain area or part in the target area.

[0055] In some embodiments, the processing device can determine a local optimization target based on the dose space corresponding to the target area. For example, the processing device can determine hot spots and / or cold spots in the dose space corresponding to the target area, and determine the local optimization target based on the dose requirements of the areas corresponding to the hot spots and / or cold spots. The hot spots are used to characterize the local high dose points in the dose space, and the cold spots are used to characterize the local low dose points in the dose space.

[0056] In some embodiments, the hot spot corresponds to an area in the dose space where the dose is higher than a first preset threshold, and the cold spot corresponds to an area in the dose space where the dose is lower than a second preset threshold. The first preset threshold and the second preset threshold can be determined based on expert experience. For example, assuming that the target area is a prostate tumor and the prescribed dose given by the doctor is 160Gy, the first preset threshold can be set to 1.5 times the prescribed dose (here in the example, 240Gy), and the second preset threshold can be set to be equal to the prescribed dose (here in the example, 160Gy).

[0057] Dose space is the space used to describe the radiation therapy dose in particle implantation planning. After the particle distribution is planned, the dose distribution at different locations in the target area can be calculated. The calculated data is used to draw a three-dimensional dose space model. In the dose space model, different colors can be used to represent the radiation dose in different areas. For example, the darker the color, the greater the dose.

[0058] The dose requirement refers to the condition that the dose index should meet. For example, the dose in the dose space should not be higher than a first preset threshold and not lower than a second preset threshold.

[0059] In some embodiments, the processing device can set corresponding local optimization targets based on the dose requirements corresponding to the hot spots and / or cold spots. For example, for a hot spot area, its local optimization target is to optimize the dose of the area to be less than a first preset threshold.

[0060] In some embodiments, the processing device can determine a region of interest within a target area; calculate the dose distribution within the region of interest and obtain a corresponding dose-volume histogram; determine an indicator to be optimized based on the dose-volume histogram; and determine the local optimization target based on the indicator to be optimized.

[0061] The region of interest refers to the target area, organs and some important tissue parts, which are predetermined areas that need attention.

[0062] A dose-volume histogram (DVH) is a three-dimensional calculation and description of the radiation dose distribution of an organ or tissue volume at different dose levels for a given treatment plan. In some embodiments, a dose-volume histogram is also referred to as a DVH curve. For example, a DVH curve can be as follows: Figure 6 As shown, Figure 6 It is an exemplary schematic diagram of the DVH curve shown in some embodiments of this specification, wherein the horizontal axis represents the dose and the vertical axis represents the volume percentage. The dose volume histogram can be obtained by separating the target area (such as a tumor) from the surrounding normal tissue, and then calculating the volume percentage of the target area, the surrounding normal tissue, and other specific organs (or tissues) in different dose ranges, and plotting them into a dose volume histogram. The dose volume histogram can help doctors and radiologists better understand the impact of the treatment plan on the patient, so as to optimize the treatment plan and reduce the occurrence of side effects.

[0063] In some embodiments, the user can determine the optimization index by observing the index on the DVH curve. For example, if the index of a local position on the DVH curve does not meet the requirements (that is, the tissue coverage of the corresponding isodose line does not meet the standard), the local position can be used as a region of interest. Specifically, when observing the DVH curve, you can pay attention to points at specific positions on the curve, such as V100, V150, V200, D90, D95, etc. on the tumor DVH curve, and D10, D30, etc. of the organ. Among them, V(*) represents the ratio of the volume in the target area that exceeds *% of the prescription dose to the total volume of the target area. For example, V100 represents the ratio of the volume in the target area that exceeds 100% of the prescription dose to the total volume of the target area; D(*) represents the dose value corresponding to the volume of *% of the prescription dose in the target area.

[0064] By observing the values ​​corresponding to these points, it is judged whether the requirements are met. For example, the values ​​corresponding to these points are compared with the size of the limit value to judge whether the requirements are met. If the requirements are not met, a corresponding optimization target is formulated. For example, when the value of a point on the DVH curve is less than the limit value, the corresponding optimization target can be specified as the index value corresponding to the point on the DVH curve reaches the limit value. The size of the limit value can be determined according to expert consensus, and can also be adjusted according to actual conditions, which is not limited in this embodiment.

[0065] Step 230: Optimize the particle implantation plan based on the optimization object and the optimization target to determine a target particle implantation plan.

[0066] Optimization refers to the process of adjusting and optimizing the puncture needle group and the particle distribution in the puncture needle in the particle implantation plan. In some embodiments, the optimization is the optimization of the puncture needle group and the particle distribution in the puncture needle. For example, for the puncture needle, the optimization includes adjusting one or more of the puncture path, needle insertion angle, needle tip distance and needle insertion depth of the puncture needle; for the particle distribution in the puncture needle, the optimization includes adjusting the spacing between particles in the puncture needle (particle position) and the number of particles.

[0067] The target particle implantation plan refers to the particle implantation plan obtained after optimization processing.

[0068] In some embodiments, the processing device can optimize the particle implantation plan based on the optimization object and the optimization target by using a preset optimization algorithm to determine a target particle implantation plan.

[0069] For example, the processing device can optimize the puncture parameters of one or more puncture needles in the particle implantation plan based on the optimization object and the optimization target. The puncture parameters refer to parameters that affect the spatial position of the puncture needle. In some embodiments, the puncture parameters include at least one of the puncture path, inter-needle spacing, needle insertion angle, and needle insertion depth of the puncture needle.

[0070] For another example, the processing device can optimize the position parameters of one or more particles in the puncture needle based on the optimization object and the optimization target, and the position parameters affect the parameters of the position distribution of the particles in the puncture needle. In some embodiments, the position parameters include at least one of the particle position in the puncture needle and the spacing between adjacent particles. For another example, the processing device can optimize the puncture parameters of one or more puncture needles in the particle implantation plan and the position parameters of one or more particles in the puncture needle based on the optimization object and the optimization target. In some embodiments, the optimization (optimization processing) of the puncture parameters and / or position parameters can be implemented based on a preset optimization algorithm, for example, based on at least one of a simulated annealing algorithm, a genetic algorithm, and a particle swarm optimization algorithm.

[0071] For detailed information on optimization processing, see Figure 3 The description is not repeated here.

[0072] Step 240: output the target particle implantation plan and the difference between the target particle implantation plan and the particle implantation plan.

[0073] The difference refers to the difference between the target particle implantation plan and the particle implantation plan. In some embodiments, the difference includes the offset of the center position of each puncture needle between the target particle implantation plan and the particle implantation plan, the rotation amount of the angle, the displacement of the particles in the needle, the increase or decrease in the number of particles in the needle, the DVH comparison chart, the dose distribution difference chart, the comparison of the newly added local optimization index values, the difference between the needle tip coordinates and the needle tail coordinates, etc. Among them, the comparison of the newly added local optimization index values ​​refers to the comparison of the values ​​of the local optimization objective function before and after the particle implantation plan is adjusted. For an explanation of the value of the objective function, please refer to the following text. Figure 3 The description is not repeated here.

[0074] In some embodiments, after completing the optimization of the particle implantation plan, the particle implantation optimization system can output a complete target particle implantation plan report for user reference. In some embodiments, the specific content of the report may include: basic information of the patient; imaging data of the patient, such as medical imaging near the target area, and the contours of the target area and organs; instrument information, such as puncture needle length, scale, particle type and particle activity, etc., and template information can also be provided if a template is used; position and direction of the puncture needle; distribution of particles inside the needle channel; visualization of the needle channel and particle spatial distribution; isodose line display of the dose distribution generated by the particles, which is a line connecting points with equal doses; DVH curve display of the dose distribution generated by the particles, which is the focus of clinical attention and can reflect the encirclement of the isodose line on the target area and organs; and quantitative evaluation results of dose distribution, including indicators such as conformity and uniformity.

[0075] The output method of the target particle implantation plan report may be output through a display device or other methods, which are not limited in this embodiment. In addition, step 240 is an optional step and may be omitted in some embodiments.

[0076] In some embodiments of the present specification, by optimizing and adjusting the puncture needle group and the particle distribution in the puncture needle in the particle implantation plan, the overall and / or local dose distribution can be optimized, thereby improving the quality of the particle implantation plan. In addition, the disclosed particle implantation optimization method provides subsequent optimization processing on the basis of the existing particle implantation plan, quickly improves the quality of the plan, and the optimization processing method is also applicable to a wide range of areas, for example, it is applicable to both manual and automatic planning results, and also to coplanar and non-coplanar (non-coplanar) planning results. For example, for a coplanar template planning plan, the equidistant template holes can be optimized to non-equidistant ones, which has better conformity to the tumor and better obstacle avoidance effect on the organ; for another example, for a particle implantation plan that is manually planned or non-coplanar, the position, angle and puncture depth of the puncture needle can be quickly adjusted to achieve plan correction and improve the effectiveness and safety of the plan. In addition, the particles can be arranged in non-equidistant intervals in the puncture needle, and the plan optimization is flexible (the optimization target setting is flexible, which can be global optimization, local optimization, or a combination of the two), and a better dose distribution can be obtained.

[0077] In some embodiments, in order to increase the user's interactive experience and combine the user's experience to better optimize the particle implantation plan, the particle implantation optimization system can also perform the following steps: obtain a particle implantation plan for the target object; the particle implantation plan includes a puncture needle sequence and one or more particles corresponding to each puncture needle in the puncture needle sequence; quantitatively evaluate the particle implantation plan, determine the plan risk information, and issue a prompt to the user based on the plan risk information; receive confirmation information input by the user, and determine the optimization object and optimization target based on the confirmation information and the plan risk information; the optimization object includes the puncture needles in the puncture needle sequence and / or one or more particles corresponding to the puncture needles; based on the optimization object and the optimization target, optimize the particle implantation plan to determine the target particle implantation plan.

[0078] In some embodiments, the particle implantation optimization system can also perform the following steps: obtaining a particle implantation plan for a target object; the particle implantation plan includes a puncture needle sequence and one or more particles corresponding to each puncture needle in the puncture needle sequence; based on the particle implantation plan, determining an optimization object and an optimization target; the optimization object includes the puncture needles in the puncture needle sequence and / or one or more particles corresponding to the puncture needles, and the optimization target includes an overall optimization target and / or a local optimization target; based on the optimization object and the optimization target, the particle implantation plan is optimized to determine a target particle implantation plan. In this embodiment, by setting an overall optimization target and / or a local optimization target, the overall and / or local dose distribution can be optimized to improve the quality of the particle implantation plan.

[0079] In some embodiments, the particle implantation optimization system can also perform the following steps: obtaining a particle implantation plan for the target object; the particle implantation plan includes a puncture needle sequence and one or more particles corresponding to each puncture needle in the puncture needle sequence; determining the overall optimization target and / or local optimization target of the particle implantation plan; the overall optimization target includes the target area dose coverage and / or organ dose radiation of the particle implantation, and the local optimization target includes the local dose coverage of the target area of ​​the particle implantation; based on the overall optimization target and / or local optimization target, the particle implantation plan is optimized to determine the target particle implantation plan. In this embodiment, by setting the overall optimization target and / or local optimization target, the overall and / or local dose distribution can be optimized to improve the quality of the particle implantation plan.

[0080] Detailed descriptions of the steps in the above embodiments may be found in other parts of this specification, for example, Figures 2 to 5 The relevant description will not be repeated here.

[0081] Figure 3 is an exemplary flow chart for optimizing the puncture parameters of the puncture needle according to some embodiments of the present specification. In some embodiments, process 300 may be executed by a particle implantation plan optimization system or a processing device (eg, the processing device 140).

[0082] Step 310: construct a needle objective function for optimizing puncture parameters based on the puncture needles in the puncture needle sequence and the optimization target.

[0083] The objective function is a function set to determine whether the adjustment of the optimization object reaches the optimization goal. For example, the optimization object includes the puncture needles in the puncture needle sequence and / or one or more particles corresponding to the puncture needles. Then the objective function can be a needle objective function, a particle objective function, or an object objective function (for the description of particle objective function and object objective function, please refer to the following text) Figure 4 and Figure 5 ). The needle objective function refers to a function used to determine whether the optimization of the puncture needle has reached the optimization goal. The needle objective function can be used in the scenario where only the puncture needles in the puncture needle sequence are optimized. The particle objective function refers to a function used to determine whether the optimization of one or more particles corresponding to the puncture needle has reached the optimization goal. The particle objective function can be used in the scenario where only the one or more particles corresponding to the puncture needles in the puncture needle sequence are optimized. The object objective function refers to a function used to determine whether the optimization of the puncture needles in the puncture needle sequence and the optimization of one or more particles corresponding to the puncture needles have reached the optimization goal. The object objective function can be used in the scenario where the puncture needles in the puncture needle sequence and the one or more particles corresponding to them are optimized.

[0084] In some embodiments, the objective function is constructed by adding function terms corresponding to the optimization object and the optimization target to the objective function. The objective function is used to characterize at least one of the needle objective function, the particle objective function and the object objective function.

[0085] In some embodiments, the function items include function items corresponding to the overall optimization target and / or function items corresponding to the local optimization target. Exemplarily, taking the construction of the target function for characterizing the needle target function as an example, the specific method is to add the function items corresponding to the puncture needles in the puncture needle sequence and the optimization target in the needle target function corresponding to the puncture parameter optimization. The needle target function includes function items corresponding to the overall optimization target and / or function items corresponding to the local optimization target. For example, taking the optimization target including at least one of the local dose optimization target, the puncture needle and tissue distance optimization target and the puncture needle layout optimization target as an example, when constructing the needle target function, the function items corresponding to the local dose optimization target, the function items corresponding to the puncture needle and tissue distance optimization target and the function items corresponding to the puncture needle layout optimization target can be added to the needle target function of the puncture parameter optimization. The construction method of the particle target function and the object target function is similar to the above method, which will not be repeated here.

[0086] In some embodiments, in order to better perform iterative optimization, the optimization of particles can be bound to the puncture needle, and the particle distribution (including optimization of particle position and quantity) can be optimized within the puncture needle.

[0087] In some embodiments, the position of the particle in the puncture needle is modeled before iterative optimization. For example, a particle can be represented by the center position S of the particle. C (The particle has a certain volume, so the center of gravity or mass of the particle can be determined as the center position) and the direction of the particle. Since the particle is optimized in conjunction with the puncture needle, the direction of the puncture needle is the direction of the particle. Therefore, the optimization of the particle position in the puncture needle only needs to optimize the center position S C Considering that the actual length of the particle is about 5 mm, the center position S of each particle is directly optimized. C This may cause particles to collide in physical space. In this embodiment, the spacing between particles is optimized. The specific modeling method is as follows: Figure 7 As shown, Figure 7 is an exemplary schematic diagram of particle position modeling according to some embodiments of the present specification, wherein the gray square inside the needle represents an example of placement, S N represents the Nth particle in the puncture needle from the needle tip to the needle tail. The optimization variable of the particle spacing can be expressed as Δ = {Δ 1 ,…,Δ k ,…,Δ N-1}, where Δ krepresents the distance between the kth particle and the k+1th particle from the needle tip to the needle end. The distance between the center position of the ith particle and the needle tip is expressed by formula (1).

[0088] Among them, L S represents the particle length, Δ k represents the distance between the kth particle and the k+1th particle from the needle tip to the needle tail, S i represents the i-th particle, Represents the distance between the center position of the ith particle and the needle tip.

[0089] In some embodiments, the number of particles in the puncture needle can also be modeled. In the above example, position modeling can optimize the position of the particles, but the number of particles remains unchanged. When calculating the dose, only the particles in the target area are considered. For example, when optimizing the particle spacing, if S i After that, all particles are adjusted outside the target area, and it is considered that S i The subsequent particles are no longer used, and the optimization result is a decrease in the number of particles. In order to achieve the optimization of increasing the number of particles under the same rule, when initializing the particle distribution in the puncture needle, two more particles (S N+1 and S N+2 ), these two particles also participate in the optimization. If one (or two) of these two particles is adjusted to the target area when optimizing the particle spacing, the optimization result is an increase in the number of particles. It should be noted that more than two particles can be placed outside the target area at the needle tail end, and this embodiment does not limit this. Figure 8 As shown, Figure 8 is an exemplary schematic diagram of particle number modeling according to some embodiments of this specification, which shows the situation where two more particles are placed outside the target area, for example, particle S N+1 and S N+2 Located outside the target area.

[0090] After the optimization object is modeled, a corresponding objective function can be established according to the optimization target for iterative optimization. In some embodiments, the optimization process based on the objective function can be implemented based on a preset optimization algorithm. The preset optimization algorithm includes at least one of a simulated annealing algorithm, a genetic algorithm, and a particle swarm optimization algorithm.

[0091] For the overall optimization goal, the objective function is defined as an indicator on the entire target area or organ. For example, for a manually planned particle implantation plan, optimization goals can be set for target area dose coverage and organ dose radiation to obtain a better particle implantation plan through iteration. For example, an example of the objective function of the overall optimization goal is shown in formula (2).

[0092] in, w 1 and w 2 Represents the weights of the two function terms of the objective function, which correspond to the target area dose coverage optimization objective and the organ dose radiation optimization objective respectively; represents the dose distribution in the i-th important organ, Represents the maximum dose value in the i-th important organ set by the user. The objective function can be interpreted as V100 must exceed 90%, and the dose in the organ must be less than the maximum dose value set by the user. V100 represents the ratio of the target volume surrounded by the isodose line with a dose level of 100%*prescription dose in the target area to the total volume of the target area, which can be used to characterize the target dose coverage.

[0093] For the automatically planned particle implantation plan, the objective function of the algorithm used for planning the particle implantation plan can be used (which can be similar in form to the above formula (2)), or the above formula (2) can be used. A new objective function can also be set according to the optimization goal, which is not limited in this embodiment.

[0094] For local optimization targets, the objective function is defined as an indicator on a part of the target area or organ. The local optimization target is an optimization target set for the situation where the overall dose requirement is met but the local dose does not meet the requirement. By adding the corresponding local optimization target, the overall and local doses can be met at the same time.

[0095] In some embodiments, local optimization includes local spatial optimization and / or local DVH optimization.

[0096] Local spatial optimization means that when there is a situation where the local dose in space does not meet the requirements, such as the presence of hot spots and / or cold spots, a separate objective function can be set for the corresponding local area (or a function term of the local optimization objective can be added to the overall optimization objective function) to optimize the local dose. For example, Fig. 9 As shown, Fig. 9 This is an exemplary schematic diagram of target area dose coverage according to some embodiments of this specification. It shows that in the planned particle implantation plan, the overall target area dose coverage is good, but there is an over-dose area outside the target area in the lower left corner (the area in the white circle).

[0097] In some embodiments, the area in the target area where the dose is too high or too low can be interactively selected by the user, and the system can add an optimization target for the dose of this area. Exemplarily, the objective function constructed after adding the optimization target is shown in the following formula (3). L = ReLU(D max -PD) (3)

[0098] Among them, D max represents the maximum dose in the area, PD represents the prescribed dose, This objective function indicates that a penalty is imposed when the maximum dose in the region exceeds the prescribed dose. During optimization, the dose in the region can be reduced by optimizing the distribution of particles and needles.

[0099] Local DVH optimization refers to determining the indicators to be optimized based on the DVH curve, and setting corresponding optimization targets for optimization. In the report corresponding to the particle implantation plan output by the system, in addition to the spatial dose distribution, a DVH (Dose and Volume Histogram) curve is usually included. During preoperative planning, the DVH curve is also a focus of clinical attention, which can reflect the encirclement of the target area and organs by the isodose line. If the indicators of a local position on the DVH curve do not meet the requirements (that is, the coverage of the corresponding isodose line does not meet the standard), the corresponding optimization target can be added to the optimization function.

[0100] like Figure 6 As shown in the figure, assuming that the prescription dose PD = 160Gy, then V150 in the figure should be equal to the ordinate value of the point with a horizontal coordinate of 240Gy (150%*160); D90 should be equal to the horizontal coordinate value of the point with a vertical coordinate of 90%. In DVH, the indicator D x (dose level of the isodose line enclosing x% of tissue volume) and V x (The ratio of the volume of the area enclosed by the isodose lines with a dose level of x% × PD to the total volume). For example, if V150 is observed to be too large, V150 can be added to the objective function to optimize the needle and particles in the direction of decreasing the value of the objective function. It should be noted that for the dose distribution in an area, a series of isodose lines are drawn according to different dose values ​​(similar to the contour lines in a topographic map), and each isodose line contains a certain volume. x First, calculate the volume value of x%*region volume, and then find the isodose line that can just contain this much volume. The dose value of this isodose line is D x About V x First, calculate the dose value of x%*prescription dose, then draw isodose lines based on this dose value, and then calculate the volume of the area surrounded by the isodose lines. The ratio of this volume to the target volume is V x Since the horizontal axis of DVH corresponds to the dose and the vertical axis corresponds to the volume, each point on the DVH represents the volume ratio of the area contained in the isodose line exceeding a certain dose value in the target area, which is related to D x and V x correspond.

[0101] Illustratively, the following embodiments illustrate how to determine optimization objectives and construct corresponding objective functions in different scenarios.

[0102] In some embodiments, after quantitatively evaluating the manually planned particle implantation plan, it is determined that the planned risk information is the presence of local cold spots or hot spots in the target area or organ in the dose distribution. After prompting the user based on the planned risk information, the user interactively outlines the cold spot area R in the target area of ​​the particle implantation plan according to the prompt. 1 and hotspot area R 2 , and the hotspot region R in the organ 3 And input the confirmation information. Based on the confirmation information and the planned risk information, the system adds the optimization target to the function corresponding to the optimization process. The optimization target is to optimize the needle and particles to optimize the spatial dose distribution, realize the plan deviation correction, and improve the effectiveness and safety of the plan. The optimization object is the puncture needle and the particles in the needle, and based on the optimization target, the function term is added to the function to determine the object objective function. The determined object objective function is shown in the following formula (4).

[0103] in, PD stands for prescribed dose, D max,OAR represents the maximum dose limit in an organ, D min,R and D max,R Respectively represent the minimum and maximum dose values ​​in region R, w i Represents the weight of the optimization item.

[0104] Then, according to the optimization goal, the position and angle of the needle and the spacing of the particles inside the needle are optimized.

[0105] In some embodiments, after quantitatively evaluating the particle implantation plan of the coplanar template automatically planned by the system, it is determined that the planned risk information is that the puncture needle is too close to the important organ. After prompting the user based on the planned risk information, the user sets the safe distance L of the organ according to the prompt. OAR , and input confirmation information; based on the confirmation information and the planned risk information, the system adds a local optimization target to the function corresponding to the optimization process. The optimization target is to optimize the position of the needle, and optimize the coplanar equidistant template to a coplanar non-equidistant template, so that the distribution of the puncture needle is more conformal to the target area and has a better obstacle avoidance effect on the organ. The optimization object is the puncture needle. Based on the local optimization target, a function term is added to the needle objective function to determine the needle objective function. The determined needle objective function is shown in the following formula (5).

[0106] L=∑ i ReLU(L OAR -L i,OAR ) (5)

[0107] Among them, L i,OAR Represents the distance from the i-th puncture needle to the organ.

[0108] Then, optimize the position of the puncture needle according to the optimization target. If the distance is still too close after optimization, prompt the user to increase the safety distance L OAR , and optimize again.

[0109] In some embodiments, after quantitatively evaluating the particle implantation plan of the eccentric template automatically planned by the system, it is determined that the overall layout of the puncture needles is relatively scattered, which makes clinical practice difficult. The overall layout of the puncture needles is relatively scattered, mainly because the restriction on the angle between needles is relatively loose during eccentric planning. Therefore, after prompting the user based on the plan risk information, the user sets the maximum angle between the needles to θ according to the prompt. max , and input the confirmation information; based on the confirmation information and the planned risk information, the system adds the overall optimization goal to the objective function corresponding to the optimization process. The optimization goal is to restrict the optimization process of the non-planar planning results so that the puncture needles are gathered together to facilitate clinical operation. The optimization object is the puncture needle. Based on the overall optimization goal, a function term is added to the needle objective function to determine the needle objective function. The determined needle objective function is shown in the following formula (6): L=∑ i ∑ j ReLU(θ i,j -θ max ) (6)

[0110] Among them, θ i,j represents the angle between the i-th needle and the j-th needle.

[0111] Then, according to the optimization goal, optimize the position and angle of the needle. If the overall puncture needle distribution is still scattered after optimization, prompt the user to reduce θ max , and optimize again.

[0112] It should be noted that the above examples are only for illustrative purposes. For example, the objective function can simultaneously represent the above-mentioned needle objective function and object objective function, and this specification does not limit this. The specific process of optimization can be found in the description of each step below.

[0113] Step 320: Based on the needle objective function, the puncture parameters of the one or more puncture needles are optimized by performing multiple rounds of iterations.

[0114] Multiple iterations refer to a series of gradual improvement cycles to achieve the ultimate goal. For example, in each iteration, the puncture parameters of the puncture needle can be optimized by calculating the value of the needle objective function, and the next iteration is optimized based on the puncture parameters of the puncture needle optimized in the previous iteration.

[0115] In some embodiments, the operation of each round of iterations includes the following steps 321-325.

[0116] Step 321, obtaining the first function value of the objective function.

[0117] The first function value can be understood as the initial function value of the needle objective function in the current iteration. For example, in this embodiment, it is the value of the needle objective function before the puncture parameters in the puncture needle are optimized in the current iteration.

[0118] In some embodiments, the first function value corresponding to the first round of iteration is calculated based on the initial puncture parameters of the puncture needle, and the first function value corresponding to the subsequent round of iteration is the second function value of the previous round of iteration.

[0119] The initial puncture parameters of the puncture needle refer to the puncture parameters before the puncture needle is optimized in the current round of iteration. For the first function value of the first round of iteration, the processing device can calculate the dose volume of the particles in the puncture needle in the target area based on the initial puncture parameters of the puncture needle in the particle implantation plan, for example, at least one of the puncture path of the initial puncture needle, the initial needle spacing, the initial needle insertion direction and the initial needle insertion depth, and substitute the dose volume into the needle objective function to calculate the first function value. For the first function value of the subsequent round of iteration, the processing device can directly obtain the second function value of the previous round of iteration and use it as the first function value of the current round of iteration. For an explanation of the second function value, see the description in step 323 below.

[0120] Step 322: Based on the preset optimization range, the puncture parameters of the one or more puncture needles are adjusted to determine the current puncture parameters of the one or more puncture needles.

[0121] The preset optimization range refers to a preset limit range for adjusting the puncture parameters of the puncture needle.

[0122] In some embodiments, the processing device can optimize the initial puncture parameters of the puncture needle based on a preset optimization range, for example, within the preset range, the perturbation needle tip coordinate N T and needle tail coordinate N S , the adjusted puncture needle puncture parameters are the current puncture needle puncture parameters. For another example, for the needle tip coordinate N T and needle tail coordinate N SGenerally speaking, the needle tail will not enter the patient's body, that is, it is still outside the body. When adjusting the puncture parameters, the needle can be regarded as a straight line. The position parameters of the straight line (needle) can be adjusted by adjusting the positions of two points on the straight line. These two points can be the needle tip and the needle tail, or the target point and the needle entry point corresponding to the puncture needle. The needle tip can be considered to be the same point as the target point, but the needle tail is actually on the extension line from the needle tip to the needle entry point. However, when adjusting the puncture parameters, the target point and the needle entry point can also be adjusted. This embodiment does not limit this.

[0123] When optimizing the planned coplanar template, the direction of the puncture needle is fixed (for example, the direction is the normal vector of the template plane), so only the needle tip N needs to be adjusted. T When optimizing the needle tip coordinate N of each needle T When the preset optimization range is set, it can be determined based on at least one of the following conditions: optimization within a certain radius of the initial position (the radius can be customized, for example, the radius is 1 mm or 2 mm, etc.); needle collision detection: the distance between needles must be greater than the collision distance; organ collision detection: the optimized needle cannot collide with the organ; the puncture depth can reach: the puncture depth of the optimized needle is less than the needle length; within the template range: N T The projection on the template plane must be within the template rectangle.

[0124] When optimizing the planned eccentric template, the direction of the puncture needle is uncertain and N needs to be optimized at the same time. T and N S . In optimizing the needle tip coordinate N of each needle T and needle tail coordinate N T When the preset optimization range is set, it can be determined based on at least one of the following conditions: optimization within a certain radius of the initial position (the radius can be customized, for example, the radius is 1 mm or 2 mm, etc.); needle collision detection: the distance between needles must be greater than the collision distance; organ collision detection: the optimized needle cannot collide with the organ; the puncture depth can reach: the puncture depth of the optimized needle is less than the needle length; within the template range: N T The projection on the template plane must be within the template rectangle; limitation of puncture angle: the angle between the puncture path and the skin surface normal vector is less than a certain range, for example, the angle is less than 15 degrees or less than 10 degrees, etc.

[0125] Step 323: Calculate a second function value of the needle objective function based on the current puncture parameters of the one or more puncture needles.

[0126] Using the above example, we can perturb the tip coordinate N T and needle tail coordinate N SAfter the adjustment, the position of the puncture needle in the target area has changed, and accordingly, the dose distribution of the puncture needle in the target area has also changed. For example, after the puncture needle position is offset, it may be closer to another puncture needle. Then, the area between the two puncture needles is covered by the two needles, and the dose in this area will be higher than before the adjustment. After calculating the dose volume of the particles in the needle in the target area based on the current puncture parameters of the puncture needle, substitute the dose volume into the needle objective function to calculate the second function value.

[0127] Step 324: determine whether to update the puncture parameters of the one or more puncture needles based on the first function value and the second function value.

[0128] In some embodiments, the processing device can determine whether to update the puncture parameters of one or more puncture needles by comparing the first function value and the second function value.

[0129] Exemplarily, the processing device may determine whether to update the puncture parameters of one or more puncture needles through the process described in the following embodiments.

[0130] Determine the magnitude relationship between the second function value and the first function value. In some embodiments, the processing device can directly compare the second function value with the first function value to determine the magnitude relationship between the second function value and the first function value.

[0131] If the second function value is less than the first function value, the puncture parameters of the one or more puncture needles are updated. It can be understood that if the second function value is less than the first function value, it means that the current puncture parameters of the currently adjusted puncture needles are closer to the optimization target, and the initial puncture parameters of the puncture needles are updated.

[0132] If the second function value is greater than or equal to the first function value, then whether to update the puncture parameters of the one or more puncture needles is determined based on a preset probability. In some embodiments, the preset probability can be determined based on the following formula (7).

[0133] Among them, p is the preset probability value, T is the current temperature in the simulated annealing algorithm used, f is the second function value, and f t In this embodiment, by setting a preset probability to accept a suboptimal solution (a case where the second function value is less than the first function value), it helps to avoid the optimization algorithm from falling into a local optimum.

[0134] Step 325: If yes, the current puncture parameters of the one or more puncture needles are used to replace the puncture parameters of the one or more puncture needles.

[0135] Figure 4is an exemplary flow chart for optimizing the position parameters of particles according to some embodiments of the present specification. In some embodiments, process 400 may be executed by a particle implantation plan optimization system or processing device (eg, processing device 140).

[0136] Step 410: construct a particle objective function for position parameter optimization based on one or more particles corresponding to the puncture needle and the optimization target.

[0137] For detailed description of step 410, please refer to the description of step 310, which will not be repeated here.

[0138] Step 420 , based on the particle objective function, optimize the position parameters of one or more particles in the puncture needle by performing multiple rounds of iterations.

[0139] In some embodiments, the operation of each round of iterations includes the following steps 421-425.

[0140] Step 421, obtaining a third function value of the particle objective function.

[0141] In some embodiments, the third function value corresponding to the first round of iteration is calculated based on the initial position parameters of one or more particles in the puncture needle, and the third function value corresponding to the subsequent round of iteration is the fourth function value of the previous round of iteration.

[0142] The initial position parameters of one or more particles refer to the position parameters before the positions of the particles in the puncture needle are optimized in the current iteration. The position parameters refer to the distribution positions of the particles in the puncture needle.

[0143] The third function value is the initial function value of the particle objective function in the current iteration. That is, the value of the particle objective function before optimizing the particle position in the puncture needle in this iteration. The initial position parameters of one or more particles corresponding to the first iteration are the position parameters of one or more particles in the puncture needle in the acquired particle implantation plan, and the initial position parameters of one or more particles corresponding to the subsequent iterations are the position parameters after optimizing the particle position in the puncture needle in the previous iteration.

[0144] For the third function value of the first iteration, the processing device can calculate the dose volume of the particles in the puncture needle in the target area based on the initial position parameters of one or more particles in the puncture needle in the particle implantation plan, and substitute the dose volume into the particle objective function to calculate the third function value. For the third function value of the subsequent iteration, the processing device can directly obtain the fourth function value of the previous iteration and use it as the third function value of the current iteration. For an explanation of the fourth function value, see the description in step 423 below.

[0145] Step 422: Adjust the position parameters of the one or more particles to determine the current position parameters of the one or more particles.

[0146] For example, the interval between particles set in each puncture needle is adjusted, and the one or more particles in the adjusted puncture needle are the current position parameters of the one or more particles.

[0147] Step 423: Calculate a fourth function value of the particle objective function based on the current position parameters of the one or more particles.

[0148] After the adjustment, the position of the particles in the puncture needle changes, and accordingly, the dose distribution of the puncture needle in the target area will also change. For example, if the distance between two particles in the puncture needle becomes smaller, the dose in the area between the two particles will be higher than before the adjustment.

[0149] After calculating the dose volume of the particles in each puncture needle in the target area based on the current position parameters of one or more particles, the dose volume is substituted into the particle objective function to calculate the fourth function value.

[0150] Step 424: determine whether to update the position parameters of the one or more particles based on the third function value and the fourth function value.

[0151] In some embodiments, the processing device is capable of determining the magnitude relationship between the fourth function value and the third function value; if the fourth function value is less than the third function value, updating the position parameters of the one or more particles; if the fourth function value is greater than or equal to the third function value, determining whether to update the position parameters of the one or more particles based on a preset probability.

[0152] The determination method of step 424 is the same as that of step 324 , and reference may be made to the description of step 324 , which will not be repeated here.

[0153] Step 425: If yes, the position parameters of the one or more particles are replaced with the current position parameters of the one or more particles.

[0154] Figure 5 is an exemplary flow chart for optimizing puncture parameters and position parameters according to some embodiments of the present specification. In some embodiments, process 500 may be executed by a particle implantation plan optimization system or processing device (eg, processing device 140).

[0155] Step 510: constructing an object objective function for puncture parameter optimization and position parameter optimization based on the puncture needles in the puncture needle sequence, one or more particles corresponding to the puncture needles, and the optimization target.

[0156] Step 520 , based on the object objective function, optimize the puncture parameters of the one or more puncture needles and the position parameters of the one or more particles in the puncture needles by performing multiple rounds of iterations.

[0157] In some embodiments, the operation of each round of iterations includes the following steps 521-5210.

[0158] Step 521, obtaining the fifth function value of the object objective function; wherein the fifth function value corresponding to the first round of iteration is calculated based on the initial puncture parameters of the one or more puncture needles and the initial position parameters of one or more particles in the puncture needles, and the fifth function value corresponding to the subsequent round of iteration is the eighth function value of the previous round of iteration.

[0159] Step 522: Based on the preset optimization range, the puncture parameters of the one or more puncture needles are adjusted to determine the current puncture parameters of the one or more puncture needles.

[0160] Step 523: Calculate the sixth function value of the object objective function based on the current puncture parameters of the one or more puncture needles and the position parameters of the one or more particles obtained in the previous iteration.

[0161] Step 524: determine whether to update the puncture parameters of the one or more puncture needles based on the fifth function value and the sixth function value.

[0162] Step 525: If yes, the current puncture parameters of the one or more puncture needles are used to replace the puncture parameters of the one or more puncture needles.

[0163] Step 526, obtaining the seventh function value of the object objective function; wherein the seventh function value is the sixth function value of the current round of iteration.

[0164] Step 527: Adjust the position parameters of the one or more particles to determine the current position parameters of the one or more particles.

[0165] Step 528: Calculate an eighth function value of the object objective function based on the current position parameters of the one or more particles and the puncture parameters of the one or more puncture needles obtained in the current round of iterations.

[0166] Step 529: Determine whether to update the position parameters of the one or more particles based on the seventh function value and the eighth function value.

[0167] Step 5210: If yes, the position parameters of the one or more particles are replaced with the current position parameters of the one or more particles.

[0168] For detailed description of steps 521-5210, see Figure 3 and Figure 4 The relevant description will not be repeated here.

[0169] In some embodiments, the particle implantation optimization system may iterate the following steps (corresponding to steps 521-525) in each of the above iterations (to avoid confusion, it may be referred to as the first iteration): obtain the fifth function value of the object objective function; adjust the puncture parameters of the one or more puncture needles based on a preset optimization range to determine the current puncture parameters of the one or more puncture needles; calculate the sixth function value of the object objective function based on the current puncture parameters of the one or more puncture needles and the position parameters of one or more particles obtained in the previous iteration; determine whether to update the puncture parameters of the one or more puncture needles based on the fifth function value and the sixth function value; if so, replace the puncture parameters of the one or more puncture needles with the current puncture parameters of the one or more puncture needles. Wherein, when performing the first iteration, the fifth function value of the object objective function obtained is to assign the value of the sixth function value of the previous iteration in the first iteration as the fifth function value.

[0170] In some embodiments, the particle implantation optimization system may also iterate the following steps (corresponding to steps 526-5210) in each of the above iterations (to avoid confusion, it may be referred to as the second iteration): obtaining the seventh function value of the object objective function; adjusting the position parameters of the one or more particles to determine the current position parameters of the one or more particles; calculating the eighth function value of the object objective function based on the current position parameters of the one or more particles and the puncture parameters of the one or more puncture needles obtained in the current iteration; determining whether to update the position parameters of the one or more particles based on the seventh function value and the eighth function value; if so, replacing the position parameters of the one or more particles with the current position parameters of the one or more particles. Wherein, when performing the second iteration, the seventh function value of the object objective function obtained is assigned the value of the eighth function value of the previous iteration in the second iteration as the seventh function value.

[0171] It should be noted that the above iterations can be performed simultaneously or on one of them. For example, the first iteration of steps 521-525 and the second iteration of steps 526-5210 can be performed simultaneously, or it can be an iteration of steps 521-525 or steps 526-5210.

[0172] In order to better understand the technical solution disclosed in this specification, the following takes the simulated annealing algorithm as an example to illustrate the process of setting the optimization target, and optimizing the particle implantation plan by adjusting the particles and needles in a way that the preset optimization algorithm (i.e., the simulated annealing algorithm) can reduce the value of its objective function. The specific steps can be as follows.

[0173] S1: Initialize the parameters of the simulated annealing algorithm: set the initial temperature T 0 , termination temperature T f , cooling rate R∈(0,1);

[0174] S2: Setting optimization target: The optimization target may include an overall optimization target and / or a local optimization target. In some embodiments, the optimization target only includes an overall optimization target. In some embodiments, the optimization target only includes a local optimization target. This example setting takes the optimization target including the overall optimization target and the local optimization target as an example. The objective function after adding the optimization target is shown in the following formula (8). minf t =w G ∑ i w G,i L G,i +w L ∑ j w L,j L L,j (8)

[0175] Among them, L G,i represents the i-th overall optimization goal, w G,i Indicates L G,i The weight of L L,j represents the jth local optimization objective, w L,j Indicates L L,j The weight of G and w L Respectively represent the weights of the overall optimization goal and the local optimization goal. It should be noted that there can be multiple overall optimization goals. The overall optimization reflects the overall indicator for the planning result calculation, without paying attention to the specific situation of each individual involved in the calculation. For example, calculating the average dose of the entire target area and limiting the average dose without considering the dose situation of each position involved in the calculation of the average dose is the optimization of the overall target area dose. For another example, optimizing the distribution of the entire puncture needle and limiting the average distance between all puncture needles and organs is also an overall optimization. Conversely, if a limit is placed on the distance between a certain needle and a certain organ, it is a local optimization.

[0176] S3: Initialize state distribution: Initialize the state distribution of particles and puncture needles according to the obtained particle implantation plan, and calculate the value of the current objective function f 0(corresponding to the first function value or the fifth function value), and set the current temperature T = T 0 ;

[0177] S4: Update time t=t+1, initialize f t =f t-1 ;

[0178] S5: Randomly update the state distribution of the needle, and perturb the needle tip coordinate N within the preset optimization range. T and needle tail coordinate N S , and calculate the value f of the current objective function (corresponding to the second function value or the sixth function value);

[0179] S6: Determine whether to update the current needle distribution:

[0180] If f <f t , then update the state distribution of the needle and let f t =f;

[0181] If f ≥ f t , then update with a certain probability, the probability is

[0182] Return S4 to iterate a certain number of times.

[0183] S7: Update time t=t+1, initialize f t =f t-1 (corresponding to the third function value or the seventh function value);

[0184] S8: Randomly update the state distribution of particles: For each puncture needle, optimize the interval Δ of particles in the needle separately i , and calculate the current objective function f (corresponding to the fourth function value or the eighth function value);

[0185] S9: Determine whether to update the distribution of the current particle:

[0186] If f <f t , then update the state distribution of the particle and let f t =f;

[0187] If f ≥ f t , then update with a certain probability, the probability is

[0188] Return to S7 to iterate a certain number of times.

[0189] S10: If T>T f , then the temperature drop T=T×R, and return to S4; otherwise, the optimization ends; where T>T in the first round of iteration f T=T 0 , when cooling, T=T 0×R, T in the subsequent iterations is the cooling result of the previous iteration. For example, T in the second iteration is T 0 ×R, T in the third iteration is T×(T 0 ×R);

[0190] S11: Restore the variables back to the spatial coordinates of the puncture needle and particles, and remove particles outside the target area in each needle.

[0191] In some embodiments, when optimizing the particle implantation plan using a preset optimization algorithm, all needles and particles may be optimized, or some of the needles or particles may be specified for optimization, which is not limited in this specification.

[0192] It should be noted that, in some embodiments, the first function value and the fifth function value may be the same. In some embodiments, the first function value and the fifth function value may also be different. Similarly, in some embodiments, the second function value and the sixth function value may be the same. In some embodiments, the second function value and the sixth function value may be different. And, in some embodiments, the third function value and the seventh function value may be the same. In some embodiments, the third function value and the seventh function value may also be different. In some embodiments, the fourth function value and the eighth function value may be the same. In some embodiments, the fourth function value and the eighth function value may also be different.

[0193] It should be noted that the above description of each process is only for example and explanation, and does not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to each process under the guidance of this specification. However, these modifications and changes are still within the scope of this specification. For example, a storage step is added between each process step, etc.

[0194] It should be understood that the system and its modules involved in this specification can be implemented in various ways. For example, in some embodiments, the system and its modules can be implemented by hardware, software, or a combination of software and hardware. Among them, the hardware part can be implemented using dedicated logic; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or a dedicated design hardware. Those skilled in the art will understand that the above methods and systems can be implemented using computer executable instructions and / or included in processor control codes, such as such as carrier media such as disks, CDs or DVD-ROMs, programmable memories such as read-only memories (firmware), or data carriers such as optical or electronic signal carriers. Such codes are provided on the system and its modules of this specification. Not only can the hardware circuits such as ultra-large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc. be implemented, they can also be implemented with software such as executed by various types of processors, and can also be implemented by a combination of the above hardware circuits and software (e.g., firmware).

[0195] It should be noted that the above description of the particle implantation plan optimization system and its modules is only for convenience of description and does not limit the present specification to the scope of the embodiments. It is understandable that, after understanding the principle of the system, those skilled in the art may arbitrarily combine the modules or form a subsystem connected with other modules without deviating from the principle.

[0196] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0197] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0198] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0199] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0200] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0201] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this specification are hereby incorporated by reference in their entirety. Except for application history documents that are inconsistent with or conflicting with the contents of this specification, documents that limit the broadest scope of the claims of this specification (currently or later attached to this specification) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the materials attached to this specification are inconsistent or conflicting with the contents described in this specification, the descriptions, definitions, and / or use of terms in this specification shall prevail.

[0202] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A particle implantation plan optimization system, the system comprising a processor, the processor being configured to perform the following operations: Acquire a particle implantation plan for the target object; the particle implantation plan includes a puncture needle sequence and a particle distribution corresponding to each puncture needle in the puncture needle sequence; Based on the particle implantation plan, determining an optimization object and an optimization target; the optimization object includes the puncture needles in the puncture needle sequence and / or the particle distribution corresponding to the puncture needles; Based on the optimization object and the optimization target, the particle implantation plan is optimized to determine a target particle implantation plan.

2. The system according to claim 1, wherein the step of optimizing the particle implantation plan based on the optimization object and the optimization target to determine a target particle implantation plan comprises: Optimizing the particle implantation plan based on the optimization object and the optimization goal; Based on the optimized puncture needle and particle distribution, the target particle implantation plan is determined.

3. The system according to claim 2, wherein the optimizing process for the particle implantation plan based on the optimization object and the optimization goal comprises: Based on the puncture needles in the puncture needle sequence and the optimization target, optimizing the puncture parameters of one or more puncture needles in the particle implantation plan, wherein the puncture parameters are parameters that affect the spatial position of the puncture needles; and / or Based on the one or more particles corresponding to the puncture needle and the optimization target, the position parameters of the one or more particles in the puncture needle are optimized, and the position parameters are parameters that affect the position distribution of the particles in the puncture needle.

4. The system according to claim 3, wherein the optimizing the puncture parameters of one or more puncture needles in the particle implantation plan based on the puncture needles in the puncture needle sequence and the optimization target comprises: Constructing a needle objective function for optimizing puncture parameters based on the puncture needles in the puncture needle sequence and the optimization target; Based on the needle objective function, optimizing the puncture parameters of the one or more puncture needles by performing multiple rounds of iterations; Each round of iteration includes: Obtaining a first function value of the needle objective function; wherein the first function value corresponding to the first round of iteration is calculated based on the initial puncture parameters of the one or more puncture needles, and the first function value corresponding to the subsequent round of iteration is the second function value of the previous round of iteration; Based on a preset optimization range, adjusting the puncture parameters of the one or more puncture needles to determine current puncture parameters of the one or more puncture needles; Calculating a second function value of the needle objective function based on current puncture parameters of the one or more puncture needles; Determining whether to update the puncture parameters of the one or more puncture needles based on the first function value and the second function value; If so, the current puncture parameters of the one or more puncture needles are used to replace the puncture parameters of the one or more puncture needles.

5. The system according to claim 3, wherein the step of optimizing the position parameters of one or more particles in the puncture needle based on the one or more particles corresponding to the puncture needle and the optimization target comprises: Constructing a particle objective function for position parameter optimization based on one or more particles corresponding to the puncture needle and the optimization target; Based on the particle objective function, optimizing the position parameters of one or more particles in the puncture needle by performing multiple rounds of iterations; Each round of iteration includes: Obtaining a third function value of the particle objective function; wherein the third function value corresponding to the first round of iteration is calculated based on the initial position parameters of one or more particles in the puncture needle, and the third function value corresponding to the subsequent round of iteration is the fourth function value of the previous round of iteration; Adjusting the position parameters of the one or more particles to determine the current position parameters of the one or more particles; Calculating a fourth function value of the particle objective function based on current position parameters of the one or more particles; Determining whether to update position parameters of the one or more particles based on the third function value and the fourth function value; If so, the position parameters of the one or more particles are replaced with the current position parameters of the one or more particles.

6. The system according to claim 3, wherein the processor is further configured to: Constructing an object objective function for puncture parameter optimization and position parameter optimization based on the puncture needles in the puncture needle sequence, one or more particles corresponding to the puncture needles, and the optimization target; Based on the object objective function, optimizing the puncture parameters of the one or more puncture needles and the position parameters of the one or more particles in the puncture needles by performing multiple rounds of iterations; in, Each iteration includes: Obtaining a fifth function value of the object objective function; wherein the fifth function value corresponding to the first round of iteration is calculated based on the initial puncture parameters of the one or more puncture needles and the initial position parameters of one or more particles in the puncture needles, and the fifth function value corresponding to the subsequent round of iteration is the eighth function value of the previous round of iteration; Based on a preset optimization range, adjusting the puncture parameters of the one or more puncture needles to determine current puncture parameters of the one or more puncture needles; Calculating a sixth function value of the object objective function based on current puncture parameters of the one or more puncture needles and position parameters of the one or more particles obtained in the previous iteration; Determining whether to update the puncture parameters of the one or more puncture needles based on the fifth function value and the sixth function value; If so, replacing the puncture parameters of the one or more puncture needles with the current puncture parameters of the one or more puncture needles; Obtaining a seventh function value of the object objective function; wherein the seventh function value is the sixth function value of the current round of iteration; Adjusting the position parameters of the one or more particles to determine the current position parameters of the one or more particles; Calculating an eighth function value of the object objective function based on the current position parameters of the one or more particles and the puncture parameters of the one or more puncture needles obtained in the current round of iterations; Determining whether to update position parameters of the one or more particles based on the seventh function value and the eighth function value; If so, the position parameters of the one or more particles are replaced with the current position parameters of the one or more particles.

7. According to the system according to any one of claims 4 to 6, constructing the objective function comprises: Function terms corresponding to the optimization object and the optimization target are added to the objective function, and the objective function is used to characterize at least one of the needle objective function, the particle objective function and the object objective function.

8. The system according to claim 1, wherein determining an optimization object and an optimization goal based on the particle implantation plan comprises: Performing a quantitative evaluation on the seed implantation plan to determine plan risk information; Prompt the user based on the plan risk information; Receive confirmation information input by the user, and determine the optimization object and the optimization goal based on the confirmation information and the plan risk information.

9. According to the system of claim 8, the optimization target includes an overall optimization target and / or a local optimization target; the overall optimization target includes the target area dose coverage of particle implantation and / or organ dose radiation, and the local optimization target includes the local dose coverage of the target area of ​​particle implantation.

10. The system according to claim 9, wherein determining the local optimization target comprises: Determine a hot spot and / or a cold spot in a dose space corresponding to the target area, wherein the hot spot corresponds to an area in the dose space where the dose is higher than a first preset threshold, and the cold spot corresponds to an area in the dose space where the dose is lower than a second preset threshold; The local optimization target is determined based on the dose requirement of the area corresponding to the hot spot and / or the cold spot.

11. The system according to claim 9, wherein determining the local optimization target comprises: determining a region of interest within the target area; Calculating the dose distribution in the region of interest and obtaining a corresponding dose volume histogram; Determining an indicator to be optimized based on the dose-volume histogram; Based on the indicator to be optimized, the local optimization target is determined.

12. The system of claim 1, wherein the processor is further configured to: The target particle implantation plan and the difference between the target particle implantation plan and the particle implantation plan are output.

13. A method for optimizing a particle implantation plan, the method comprising: Obtaining a particle implantation plan for a target object; The particle implantation plan includes a puncture needle sequence and a particle distribution corresponding to each puncture needle in the puncture needle sequence; Based on the particle implantation plan, determining an optimization object and an optimization target; the optimization object includes the puncture needles in the puncture needle sequence and / or the particle distribution corresponding to the puncture needles; Based on the optimization object and the optimization target, the particle implantation plan is optimized to determine a target particle implantation plan.

14. A particle implantation plan optimization device, comprising a processor, wherein the processor is used to execute the particle implantation plan method described in claim 13.

Images