Particle implantation preoperative planning method and system

Abstract

The embodiment of the invention provides a preoperative planning method and system for particle implantation. The method comprises the following steps: acquiring image data of a segmented target region and a tissue region of a target object; initial puncture needle distribution is determined based on a representation model associated with particle implantation, the representation model comprises a puncture needle candidate position representation and a particle candidate position representation associated with the image data, and one or more particle candidate positions correspond to the puncture needle candidate positions; based on the initial puncture needle distribution, optimizing the puncture needle distribution through a first optimization algorithm to obtain a candidate particle implantation plan; and based on the candidate particle implantation plan, optimizing the particle distribution through a second optimization algorithm to obtain a target particle implantation plan.

Description

Technical Field

[0001] The present invention relates to the field of particle implantation technology, and in particular to a particle implantation preoperative planning method and system. Background Art

[0002] 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 for tumor treatment is: through imaging guidance technology (such as CT, ultrasound, etc.), puncture is performed 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.

[0003] In order to improve the efficacy and local control rate of tumors and ensure the smooth progress of the operation, before the implementation of the particle implantation operation, a corresponding particle implantation plan must be formulated according to the particle implantation treatment plan in order to smoothly implement the particle implantation.

[0004] At present, the preoperative plan for seed implantation is mainly made through manual trial and error, and the number and position of puncture needles and seeds are adjusted manually until the distribution of seeds in the target area meets the clinical dose requirements. This method is time-consuming, prolongs the treatment cycle of seed implantation surgery, and is highly dependent on subjective experience, which introduces more uncertainties into seed implantation surgery.

[0005] Therefore, a particle implantation preoperative planning method and system are provided to alleviate the deficiencies of existing preoperative planning systems and achieve more efficient acquisition of accurate particle implantation plans. Summary of the invention

[0006] One of the embodiments of the present specification provides a method for preoperative planning of particle implantation, comprising: acquiring image data of a segmented target area and a tissue area of ​​a target object; determining an initial puncture needle distribution based on a representation model associated with the particle implantation, the representation model comprising a puncture needle candidate position representation and a particle candidate position representation associated with the image data, wherein the puncture needle candidate position corresponds to one or more particle candidate positions; based on the initial puncture needle distribution, optimizing the puncture needle distribution by a first optimization algorithm to obtain a candidate particle implantation plan; based on the candidate particle implantation plan, optimizing the particle distribution by a second optimization algorithm to obtain a target particle implantation plan.

[0007] One of the embodiments of the present specification provides a particle implantation preoperative planning system, comprising: an acquisition module, used to acquire image data of a segmented target area and tissue area of ​​a target object; a determination module, used to determine an initial puncture needle distribution based on a representation model associated with the particle implantation, the representation model comprising a puncture needle candidate position representation and a particle candidate position representation associated with the image data, wherein the puncture needle candidate position corresponds to one or more of the particle candidate positions; a first optimization module, used to optimize the puncture needle distribution by a first optimization algorithm based on the initial puncture needle distribution to obtain a candidate particle implantation plan; a second optimization module, used to optimize the particle distribution by a second optimization algorithm based on the candidate particle implantation plan to obtain a target particle implantation plan.

[0008] One of the embodiments of the present specification provides a particle implantation preoperative planning device, including a processor, wherein the processor is used to execute the above-mentioned particle implantation preoperative planning method. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] 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:

[0010] Figure 1 It is a schematic diagram of an application scenario of a particle implantation preoperative planning method according to some embodiments of this specification.

[0011] Figure 2 is an exemplary schematic diagram of the modules of a particle implantation preoperative planning system according to some embodiments of the present specification.

[0012] Figure 3a is an exemplary flow chart of a method for preoperative planning of particle implantation according to some embodiments of the present specification.

[0013] Figure 3b is an exemplary schematic diagram of the initial puncture needle distribution according to some embodiments of the present specification.

[0014] Figure 3c is an exemplary schematic diagram showing candidate positions of a puncture needle according to some embodiments of the present specification.

[0015] Figure 3d is an exemplary schematic diagram of the representation of candidate positions of particles according to some embodiments of the present specification.

[0016] Figure 4a is an exemplary flow chart of a method for determining an initial puncture needle distribution according to some embodiments of the present specification.

[0017] Figure 4bis an exemplary schematic diagram of puncture needle insertion according to preoperative planning of particle implantation as shown in some embodiments of the present specification.

[0018] Figure 5a is an exemplary flow chart of optimizing a particle implantation plan by using an optimization algorithm according to some embodiments of the present specification.

[0019] Figure 5b is an exemplary schematic diagram of the first transformation process shown in some embodiments of the present specification.

[0020] Figure 5c is an exemplary schematic diagram of a target particle implantation plan for particle implantation according to some embodiments of the present specification.

[0021] Figure 6 is an exemplary flow chart of another method for preoperative planning of target seed implantation according to some embodiments of the present specification.

[0022] Figure 7 is an exemplary schematic diagram of a particle implantation preoperative planning device according to some embodiments of the present specification. DETAILED DESCRIPTION

[0023] 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.

[0024] 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.

[0025] 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 "include" and "comprise" 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.

[0026] 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.

[0027] Figure 1 It is a schematic diagram of an application scenario of a particle implantation preoperative planning system according to some embodiments of this specification.

[0028] like Figure 1 As shown, the application scenario 100 of the particle implantation preoperative planning system may include a medical scanning device 110 (exemplarily, Figure 1 CT scanner in the example), network 120, terminal 130, processing device 140 and storage device 150. The components in application scenario 100 can be connected in various ways. For example, Figure 1 As shown in , the medical scanning device 110 can be connected to the processing device 140 via the network 120. The medical scanning device 110 can be directly connected to the processing device 140 (as shown by the double-headed arrow in the dashed line connecting the medical scanning device 110 and the processing device 140). The storage device 150 can be connected to the processing device 140 directly or via the network 120.

[0029] The medical scanning device 110 can scan a scanned object and / or generate multiple data about the scanned object. In this specification, the scanned object may also be referred to as a scanned object, a target object, a target, or a detected object. In some embodiments, the scanned object may be a patient, an animal, etc. When the scanned person needs to be scanned, after the scanned object enters the scanning area 115, the medical scanning device 110 may perform tube anode exposure based on a preset scanning protocol to emit radiation (e.g., an X-ray beam), and the radiation is irradiated on the scanned object to obtain a corresponding medical image. In some embodiments, the medical image may include information such as the contour of the target area, the organs or tissue areas around the target area, etc.

[0030] The network 120 may include any suitable network that facilitates information and / or data exchange of the application scenario 100. In some embodiments, one or more components of the application scenario 100 (e.g., the medical scanning device 110, the terminal 130, the processing device 140, or the storage device 150) may transmit information and / or data to one or more other components of the application scenario 100 via the network 120. For example, the processing device 140 may obtain a medical image of a scanned object from the medical scanning device 110 via the network 120. In some embodiments, the network 120 may be any one or more of a wired network or a wireless network. In some embodiments, the network may be a point-to-point, shared, centralized, or other topological structure or a combination of multiple topological structures.

[0031] The terminal 130 may include a mobile device 130-1, a tablet computer 130-2, a laptop computer 130-3, etc., or any combination thereof. In some embodiments, the terminal 130 may interact with other components in the application scenario 100 through the network 120. For example, the terminal 130 may receive data such as medical images sent by the medical scanning device 110. In some embodiments, the terminal 130 may receive information and / or instructions input by a user (e.g., a user of the medical scanning device 110, such as a doctor), and send the received information and / or instructions to the medical scanning device 110 or the processing device 140 via the network 120. For example, a doctor may input operating instructions for the medical scanning device 110 through the terminal 130. In some embodiments, the terminal 130 may display a report of a particle implantation plan for the user to view and / or select.

[0032] The processing device 140 may process data and / or information obtained from the medical scanning device 110, the terminal 130 and / or the storage device 150. For example, the processing device 140 may acquire a medical image of a scanned person.

[0033] In some embodiments, the processing device 140 can be a single server or a server group. The server group can be centralized or distributed. In some embodiments, the processing device 140 can be local or remote. The processing device 140 can be directly connected to the medical scanning device 110, the terminal 130 and the storage device 150 to access the stored or acquired information and / or data. In some embodiments, the processing device 140 can be implemented on a cloud platform. By way of example only, the cloud platform can include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-layer cloud, etc. or any combination thereof.

[0034] The storage device 150 may store data and / or instructions. In some embodiments, the storage device 150 may store data obtained from the medical scanning device 110, the terminal 130, and / or the processing device 140. For example, the storage device 150 may store medical images obtained by the user scanning device, reports of particle implantation plans, etc. In some embodiments, the storage device 150 may store data and / or instructions that the processing device 140 may execute or use to execute the exemplary methods described in this specification. For example, the storage device 150 may store instructions for the processing device 140 to execute the methods shown in the various flow charts. In some embodiments, the storage device 150 may include a mass storage device, a removable storage device, a volatile read-write memory, a read-only memory (ROM), etc., or any combination thereof. In some embodiments, the storage device 150 may be implemented on a cloud platform.

[0035] In some embodiments, the storage device 150 may be connected to the network 120 to communicate with one or more components of the application scenario 100 (e.g., the medical scanning device 110, the terminal 130, the processing device 140, etc.). One or more components of the application scenario 100 may access data or instructions stored in the storage device 150 via the network 120. In some embodiments, the storage device 150 may be directly connected to or communicate with one or more components of the application scenario 100. In some embodiments, the storage device 150 may be part of the processing device 140.

[0036] The above description is for illustrative purposes only, and actual application scenarios may vary.

[0037] It should be noted that the application scenario 100 is provided for illustrative purposes only and is not intended to limit the scope of the present application. For those of ordinary skill in the art, various modifications or variations can be made according to the description of this specification. For example, the application scenario 100 may also include a display device. However, these variations and modifications will not deviate from the scope of the present application.

[0038] Figure 2 is an exemplary schematic diagram of the modules of a particle implantation preoperative planning system according to some embodiments of the present specification.

[0039] like Figure 2 As shown, the particle implantation preoperative planning system 200 (hereinafter referred to as the planning system 200 ) may include an acquisition module 210 , a determination module 220 , a first optimization module 230 , and a second optimization module 240 .

[0040] The acquisition module 210 may be used to acquire image data of the segmented target area and tissue area of ​​the target object.

[0041] The determination module 220 can be used to determine the initial puncture needle distribution based on a representation model associated with particle implantation, wherein the representation model includes a puncture needle candidate position representation and a particle candidate position representation associated with the image data, wherein the puncture needle candidate position corresponds to one or more of the particle candidate positions.

[0042] In some embodiments, the determination module 220 can also be used to preprocess the candidate puncture needle positions based on the representation model, and the preprocessing includes one or more of the following: eliminating the candidate puncture needle positions that do not meet the preset conditions of the puncture needle, and eliminating the candidate particle positions that do not meet the preset conditions of the particles; based on the preprocessed candidate puncture needle positions, determine the initial puncture needle distribution.

[0043] The first optimization module 230 may be used to optimize the puncture needle distribution based on the initial puncture needle distribution by using a first optimization algorithm to obtain a candidate particle implantation plan.

[0044] In some embodiments, the first optimization module 230 can also be used to: optimize the puncture needle distribution through a first optimization algorithm with the goal of making the candidate particle implantation plan satisfy the first constraint and reducing the function value of the first objective function, so as to obtain a candidate particle implantation plan; wherein, in the puncture needle distribution, particles are placed at any particle candidate position on the puncture needle candidate position; and, the first constraint is related to the target area dose coverage, and the first objective function is related to the total number of puncture needles and the total number of particles.

[0045] In some embodiments, the first optimization module 230 can also be used to: perform optimization processing based on at least one round of iterative processing, wherein one round of iterative processing includes: obtaining an initial population, the initial population including multiple individuals, each individual corresponding to a particle implantation plan; based on the initial population, generating a new population through a preset deduction algorithm; based on constraints or based on constraints and objective functions, screening target individuals from the initial population and the new population to form a target population, and the initial population in the next round of iterative processing is the target population; determining the target result in the target population obtained after the optimization processing; wherein, for optimizing the puncture needle distribution through the first optimization algorithm, the constraint condition is the first constraint condition, the objective function is the first objective function, the initial population of the first round of iteration is obtained based on the initial puncture needle distribution, and the target result is a candidate particle implantation plan.

[0046] The second optimization module 240 may be used to optimize the particle distribution based on the candidate particle implantation plan by using a second optimization algorithm to obtain a target particle implantation plan.

[0047] In some embodiments, the second optimization module 240 can also be used to optimize the particle distribution through a second optimization algorithm with the goal of making the target particle implantation plan satisfy the second constraint and reducing the function value of the second objective function, so as to obtain a target particle implantation plan; wherein the second constraint is related to the target area dose coverage and the total number of puncture needles and / or the total number of particles; and the second objective function is related to the particle dose conformity and / or the uniformity of the particle dose distribution.

[0048] In some embodiments, the second optimization module 240 can also be used to: during the optimization process, obtain the difference particles in the particle distribution of the candidate particle implantation plan corresponding to the optimized particle implantation plan and the optimized particle implantation plan; when the number of difference particles is less than the preset total number of particles, determine the dose at the difference particles.

[0049] In some embodiments, the first optimization module 240 can also be used to: perform optimization processing based on at least one round of iterative processing, wherein one round of iterative processing includes: obtaining an initial population, the initial population including multiple individuals, each individual corresponding to a particle implantation plan; based on the initial population, generating a new population through a preset deduction algorithm; based on constraints or based on constraints and objective functions, screening target individuals from the initial population and the new population to form a target population, and the initial population at the next round of iterative processing is the target population; determining the target result in the target population obtained after the optimization processing; wherein, for optimizing the particle distribution through the second optimization algorithm, the constraints are the second constraints, the objective function is the second objective function, the initial population of the first round of iteration is obtained based on the candidate particle implantation plan, and the target result is the target particle implantation plan.

[0050] In some embodiments, the particle implantation preoperative planning system 200 may further include an output module 250. The output module 250 may be used to output a report corresponding to the candidate particle implantation plan and / or the target particle implantation plan.

[0051] It should be noted that the above description of the particle implantation preoperative planning system 200 and its modules is for convenience of description only and does not limit this specification to the scope of the embodiments cited. It is understandable that for those skilled in the art, after understanding the principle of the system, it is possible to arbitrarily combine the various modules, or form a subsystem to connect with other modules without deviating from this principle. The various modules can be different modules in a system, or a module can implement the functions of two or more of the above-mentioned modules. For example, the modules can share a storage device, and each component can also have its own storage device. Such variations are within the scope of protection of this specification.

[0052] Figure 3ais an exemplary flow chart of a method for preoperative planning of particle implantation according to some embodiments of the present specification.

[0053] In some embodiments, process 300 may be performed by planning system 200. Figure 3a As shown, process 300 includes the following steps:

[0054] Step 310: Acquire image data of the segmented target area and tissue area of ​​the target object.

[0055] The target object may refer to an individual who needs to undergo particle implantation, which may be a human patient, an animal, or the like.

[0056] The target area may refer to the area of ​​the body of the target object where the particle implantation surgery is required. For example, the target area may include an area of ​​the body where abnormal lesions occur, such as a tumor area in the chest cavity.

[0057] The tissue region may refer to a body region related to the current seed implantation. For example, the tissue region may include organs (such as the heart), bones, blood vessels, etc. around the target area. In some embodiments, the tissue region may include a first preset tissue and a second preset tissue.

[0058] The first preset tissue refers to non-puncturable tissue, which can be determined based on the actual situation of this particle implantation. For example, the degree of negative effects on the target object after puncture of the tissue area (such as the possibility of serious complications, heavy bleeding, etc.) can be evaluated. The greater the degree of impact, the more likely it is to be marked as the first preset tissue; for another example, for tissue areas that do not require puncture (such as bones, calcified tissue), the difficulty of puncture can also be evaluated. The greater the difficulty, the greater the possibility of marking it as the first preset tissue.

[0059] The second preset tissue refers to the tissue that needs to be limited in particle dose. Among them, the particle dose limitation can include dose limit indicators such as volume dose and point dose of the tissue area (such as maximum volume dose, maximum point dose, etc.). It should be understood that the particle dose values ​​of different tissue areas are different. When the particle dose value is exceeded, the possibility of negative effects on the target object (such as causing serious complications, etc.) is greater. The second preset tissue can be determined according to the actual situation of this particle implantation, for example, according to the physique of different target objects, the location of the target area and the type of surrounding tissue.

[0060] It should be noted that the first preset tissue and the second preset tissue are determined according to the actual scenario of the particle implantation. In different types of particle implantations (such as liver cancer, gastric cancer, and lung cancer), the first preset tissue and the second preset tissue may be different. In addition, a certain tissue area may be both the first preset tissue and the second preset tissue (for example, a non-puncturable heart also has dose limit constraints). In some embodiments of the present specification, by marking different tissue areas in the planning of particle implantation and taking into account their non-puncturability and particle dose limitations, the particle implantation plan can be made more accurate.

[0061] The image data may include but is not limited to medical image data such as CT images and ultrasound images, which may be one or more pictures, or one or more frames of images in video data. In some embodiments, the image data may be obtained by scanning the target object with a medical scanning device (such as a CT device).

[0062] The image data contains information about the target area and / or tissue area. For example, the image data may include information such as the location (such as the chest, neck, abdomen, etc.), shape, outline, size, etc. of the target area in the target object. It may also include information such as whether there are important organs or body tissues (such as the heart, carotid artery, lungs, etc.) around the target area and their shapes, outlines, etc.

[0063] The planning system 200 can process the acquired image data to outline the target area and tissue area, thereby obtaining processed image data of the segmented target area and tissue area. In some embodiments, when performing a particle implantation operation, different target areas require different implantation doses, and tissue areas related to the target area (such as a second preset tissue around the target area) also need to meet dose limit conditions.

[0064] In some embodiments, the planning system 200 may analyze grayscale changes, color distortion, etc. of a single-frame image, and may also extract features of the target area and / or tissue area (such as the type of tissue) in the single-frame image.

[0065] In some embodiments, the planning system 200 may process the image data through an image processing algorithm. For example, the image data may be segmented using methods including but not limited to a threshold method, a region growing method, etc. to obtain the above image data.

[0066] In some embodiments, the planning system 200 may also process the image data using a trained machine learning or deep learning model. For example, the image data may be segmented using a U-Net-based segmentation model to obtain target image data.

[0067] It can be understood that segmenting the target area and tissue area in the image can be achieved through various feasible methods.

[0068] In some embodiments of the present specification, by segmenting the target area and tissue area, the contours of the target area and surrounding important tissues or organs can be accurately obtained, which helps the puncture needle of the particle implantation surgery avoid important organs and reduce the negative impact of the dose.

[0069] Step 320, determining an initial puncture needle distribution based on a representation model associated with particle implantation, wherein the representation model includes a puncture needle candidate position representation and a particle candidate position representation associated with the image data, wherein a puncture needle candidate position corresponds to one or more particle candidate positions.

[0070] The initial puncture needle distribution may refer to the spatial distribution information of the candidate puncture needles. The candidate puncture needles may be used to characterize the feasible puncture paths of the puncture needles. The spatial distribution information of the candidate puncture needles may include the number of candidate puncture needles and the information of the candidate puncture needles such as the needle insertion point, needle tip point, needle insertion depth, needle direction, etc.

[0071] The initial puncture needle distribution may also include spatial distribution information of candidate particles, wherein the candidate particles may be used to characterize the distribution source and dose information of the implanted particles, and the spatial distribution information of the candidate particles may include information such as the position and quantity of the candidate particles.

[0072] In some embodiments, the initial puncture needle distribution can be represented by a representation model associated with particle implantation. The representation model can refer to a method for representing and analyzing the initial puncture needle distribution information, which can include a puncture needle candidate position representation and a particle candidate position representation, wherein a puncture needle candidate position corresponds to one or more particle candidate positions.

[0073] In some embodiments, the planning system 200 can determine the representation model through mathematical modeling or computer simulation methods based on the image data of the segmented target area and tissue area. For example, the representation model can be obtained by analyzing and processing the information such as the location, outline, size, etc. of the target area in the image data, as well as the types of important organs around the target area and their requirements for particle doses. The representation of the candidate positions of the puncture needle and the candidate positions of the particles in the representation model can be represented in various ways such as numerical values, symbols, and codes.

[0074] In some embodiments, the representation model may include a representation model based on a coplanar needle group, and the puncture needle candidate position representation and / or the particle candidate position representation are binary representations. Binary representation refers to a representation with only two possible output results. Among them, the binary representation of the puncture needle candidate position is determined based on whether the puncture needle candidate position is placed at the puncture needle candidate position, and the binary representation of the particle candidate position is determined based on whether the particle is placed at the particle candidate position. Exemplarily, the binary representation of the puncture needle candidate position and the particle candidate position may include one or a combination of binary representation forms such as A / B, Y / N, + / -. In some embodiments, the binary representation can be represented by a binary number (i.e., 0 / 1). Among them, when the puncture needle candidate position is placed at the puncture needle candidate position and the particle candidate position is placed at the particle candidate position, it can be represented by 1 respectively, otherwise it can be represented by 0.

[0075] The coplanar needle group may refer to puncture needles determined based on a particle implantation template, the puncture needles are parallel, and the particle implantation template is a plane. Exemplarily, the particle implantation template may be a rectangular area, which is the range of the initial puncture needle distribution. The initial puncture needle distribution is adjusted by adjusting the center position of the particle implantation template and the angle or direction of the template, wherein the particle implantation template includes holes that can be used to indicate candidate positions of the puncture needles, and the needle insertion direction can be perpendicular to the template plane.

[0076] refer to Figure 3b , Figure 3b is an exemplary schematic diagram of the initial puncture needle distribution according to some embodiments of the present specification.

[0077] like Figure 3b As shown, the rectangular grid area is a particle implantation template 321, the elliptical area represents a target area 322, each black solid dot represents a candidate puncture needle position 323, and the two dotted circular areas represent non-puncture areas 324.

[0078] The particle implantation template 321 may be pre-set and may include a plurality of preset holes (such as the intersection of a grid). The contours, relative positions and other related information of the target area 322 and the non-punctureable area 324 may be determined based on the image data of the segmented target area and tissue area.

[0079] The particle implantation template 321 can determine multiple candidate puncture needle positions 323 according to the relevant information of the target area 322 and the non-puncture area 324 by adjusting the center position (such as translation along the x-axis and y-axis directions) and rotating the angle (such as rotating along the XY-axis plane and the XZ-axis plane based on the center position point). Figure 3bAs shown, the number of candidate puncture needle positions 323 is 22, and each candidate puncture needle position 323 corresponds to a candidate puncture needle, wherein the candidate puncture needle is within the target area 322 and does not pass through any non-punctureable area 324. The multiple candidate puncture needles corresponding to the multiple candidate puncture needle positions 323 are a coplanar needle group, that is, a candidate needle group.

[0080] It should be noted that the representation model may also include a representation model based on an eccentric needle group. An eccentric needle group may mean that the puncture needles may not be parallel. For example, a feasible needle insertion area may be drawn on the body surface corresponding to the target area of ​​the target object, wherein the feasible needle insertion area avoids the non-puncture area. A needle insertion point is randomly selected in the feasible needle insertion area and paired with a random point in the target area to generate a candidate puncture needle; after repeating the above operations many times, an eccentric needle group may be generated, and based on the eccentric needle group, the initial puncture needle distribution is determined.

[0081] This manual mainly uses the coplanar needle group as an example to illustrate the preoperative planning method for particle implantation.

[0082] In some embodiments, the candidate position of the puncture needle may be represented in the form of a binary number, which may be represented as 0 or 1. 0 indicates that the candidate position of the puncture needle does not have a puncture needle placed therein; 1 indicates that the candidate position of the puncture needle has a puncture needle placed therein, and the puncture needle is the recommended puncture needle, and the candidate position is the recommended puncture needle position.

[0083] Combination Figure 3c , Figure 3c is an exemplary schematic diagram showing candidate positions of a puncture needle according to some embodiments of the present specification.

[0084] like Figure 3c The representation of the candidate positions of the puncture needles corresponding to the candidate needle group is shown, which can be represented as a binary sequence (or array) with n elements, wherein the value of n is determined based on the number of candidate positions of the puncture needles (eg, 22).

[0085] For example, Figure 3c As shown in the figure, the value of the first candidate puncture needle position is 0, indicating that the puncture needle is not placed at this position; the value of the second candidate puncture needle position is 1, indicating that the puncture needle is placed at this position. Based on this principle, a binary sequence corresponding to n candidate puncture needle positions can be obtained. Among them, the candidate puncture needle position corresponding to the binary value of 1 in the sequence is the recommended puncture needle position.

[0086] In some embodiments, whether the candidate puncture needle position is used as the recommended puncture needle position, or whether the candidate puncture needle is used as the recommended puncture needle, needs to meet the puncture needle preset conditions. For relevant content about the puncture needle preset conditions, see Figure 4a and its description.

[0087] In some embodiments, one or more particle candidate positions may correspond to a puncture needle candidate position. It is understandable that one puncture needle candidate position corresponds to one candidate puncture needle. In some embodiments, the puncture needle is engraved with equally spaced scales, and each scale corresponds to a particle candidate position. It should be noted that when performing particle implantation, the puncture needle will first pass through the target area, and then gradually withdraw the needle and place the particles according to the scale. Exemplarily, a puncture needle is engraved with m (such as 10) equally spaced scales, for example, scale 1, scale 2...scale m, which indicates that there are m particle candidate positions corresponding to the puncture needle where particles can be placed.

[0088] In some embodiments, the particle candidate position representation may be in the form of a binary number representation, which may be represented as 0 or 1. 0 indicates that the particle candidate position does not place a particle; 1 indicates that the particle candidate position places a particle.

[0089] Combination Figure 3d , Figure 3d is an exemplary schematic diagram of the representation of candidate positions of particles according to some embodiments of the present specification.

[0090] Figure 3d The figure shows the representation of the particle candidate positions corresponding to k puncture needles. The representation of the particle candidate position of a certain puncture needle (such as puncture needle 1, puncture needle k) can be represented as a binary sequence (or array) with m elements. The value of m is determined based on the number of puncture needle scales (such as 10), and the value of k is the number of recommended puncture needles in the candidate needle group, which is less than or equal to the total number of puncture needle candidate positions or candidate puncture needles n.

[0091] For example, Figure 3d As shown, in the puncture needle 1, m (such as 10) scales correspond to m candidate particle positions, the binary value corresponding to scale 1 is 0, indicating that the particle candidate position does not place a particle; the binary value corresponding to scale 2 is 1, indicating that the particle candidate position needs to place a particle. According to this principle, based on the binary values ​​of the m candidate particle positions, the representation of the candidate particle position of puncture needle 1 can be obtained. Similarly, the representation of the candidate particle positions of k puncture needles can be obtained, which can be a matrix of binary values ​​with k rows and m columns.

[0092] In some embodiments, whether a particle candidate position is to be placed, or whether a particle candidate position is to be used as a recommended particle position, needs to satisfy a particle preset condition. For more information about particle preset conditions, see Figure 4a and its description.

[0093] Step 330 , based on the initial puncture needle distribution, the puncture needle distribution is optimized by a first optimization algorithm to obtain a candidate particle implantation plan.

[0094] In some embodiments, the planning system 200 can determine one or more initial puncture needle distributions and particle distributions based on the representation model. An initial puncture needle distribution and particle distribution can represent an initial particle implantation plan. Exemplarily, the above-mentioned matrix of binary values ​​of k rows and m columns can be represented as an initial particle implantation plan.

[0095] The candidate particle implantation plan may refer to a particle implantation plan that meets preset conditions.

[0096] In some embodiments, the candidate particle implantation plan obtained through the optimization in step 330 can be used as a feasible solution for particle implantation, which can meet the preoperative planning requirements for particle implantation to a certain extent. For example, see Figure 6 The method shown.

[0097] In some embodiments, the planning system 200 may determine a candidate particle implantation plan based on prior knowledge or medical experience. For example, based on the image data of the target area and the tissue area, historical particle implantation plans of similar historical cases may be obtained, and one or more historical particle implantation plans with good treatment effects (such as patient feedback, evaluation results of postoperative medical observation) may be used as candidate particle implantation plans.

[0098] In some embodiments, the planning system 200 can adjust the candidate puncture needle distribution parameters (such as the position and number of puncture needles) and the parameters of the particle candidate position distribution (such as the placement position and number of particles) in the initial particle implantation plan. When the adjusted initial particle implantation plan meets the preset conditions, the candidate particle implantation plan is obtained.

[0099] In some embodiments, in the optimization stage of step 330 (which may be referred to as the first optimization stage), particles may be placed at all candidate particle positions on each puncture needle in the determined initial puncture needle distribution. Thus, in the optimization stage of step 330, the puncture needle distribution may be optimized and a candidate particle implantation plan may be obtained.

[0100] In some embodiments, the planning system 200 can optimize the puncture needle distribution through the first optimization algorithm to obtain a candidate particle implantation plan. Figure 5a and its description.

[0101] Step 340 , based on the candidate particle implantation plan, optimize the particle distribution by a second optimization algorithm to obtain a target particle implantation plan.

[0102] The target seed implantation plan may refer to a seed implantation plan that is ultimately used to perform seed implantation surgery.

[0103] The optimization stage of step 340 may be referred to as a second optimization stage. In some embodiments, the planning system 200 may compare and analyze multiple candidate particle implantation plans, and select a candidate particle implantation plan that meets preset conditions from the multiple candidate particle implantation plans as a target particle implantation plan.

[0104] In some embodiments, the planning system 200 can optimize the particle distribution based on the candidate particle implantation plan by using the second optimization algorithm to obtain the target particle implantation plan. Figure 5a and its description.

[0105] In some embodiments of the present specification, the target particle implantation plan is automatically determined by the planning system, so as to efficiently obtain an accurate particle implantation plan and avoid the uncertainty caused by the particle implantation plan determined by subjective experience. In addition, through the separate optimization of two stages (first optimization algorithm optimization and second optimization algorithm optimization), the problem that the optimization effect of the number of needles and the number of particles may be weakened when the puncture needle distribution and the particle distribution are optimized at the same time can be avoided (for example, the number of puncture needles and the number of particles are both used as optimization targets, and since the optimization target also includes the optimization of dosage and other aspects, the optimization of the number of needles and the number of particles may be weakened), so that the optimization direction of the particle implantation plan has stronger pertinence and better stability, and thus a more reliable and more practical particle implantation plan can be obtained.

[0106] Figure 4a is an exemplary flow chart of a method for determining an initial puncture needle distribution according to some embodiments of the present specification.

[0107] In some embodiments, process 400 may be performed by planning system 200. Figure 4a As shown, process 400 includes the following steps:

[0108] Step 410 , preprocessing the candidate puncture needle positions based on the representation model.

[0109] In some embodiments, the planning system 200 can obtain a binary representation of the candidate puncture needle positions based on the representation model, which includes a binary representation of the candidate puncture needle positions and a binary representation of the candidate particle positions corresponding to each candidate puncture needle position. For relevant content about the representation model, the candidate puncture needle positions, and the binary representation of the candidate particle positions, see Figure 3a and its description.

[0110] In some embodiments, the planning system 200 may initialize the binary representation of the candidate puncture needle positions, for example, generating binary numbers that are all 0, or all 1, or a random combination of 0 and 1.

[0111] In some embodiments, the preprocessing may include the following steps 411 and 412:

[0112] Step 411, remove the candidate puncture needle positions that do not meet the preset conditions of the puncture needle. The preset conditions of the puncture needle include one or more of the following: the puncture needle at the candidate puncture needle position cannot penetrate the target tissue, and the insertion depth of the puncture needle at the candidate puncture needle position is less than the instrument length of the puncture needle.

[0113] The target tissue may be a first preset tissue around the target area. For example, blood vessels, bones, etc. near the target area. For more information about the first preset tissue, see Figure 3a and its description.

[0114] In some embodiments, the puncture needle at the puncture needle candidate position cannot pass through the target tissue and may also include expanding the boundary of the current contour of the target tissue based on a preset safety distance (e.g., 10 mm, etc.), and the puncture needle at the puncture needle candidate position cannot pass through the target tissue after the boundary expansion.

[0115] In some embodiments of the present specification, by introducing a preset safety distance, the distribution of the pre-treated puncture needles can be made safer.

[0116] The insertion depth of the puncture needle may include the first depth from the insertion point of the puncture needle on the body surface to the first time the needle tip of the puncture needle touches the target area. When the instrument length (physical length) of the puncture needle is less than the first depth, it indicates that the candidate position of the puncture needle does not meet the preset conditions of the puncture needle.

[0117] The insertion depth of the puncture needle may also include a second depth from the body surface insertion point to a preset needle tip point (such as the last voxel in the target area). When the instrument length of the puncture needle is less than the second depth, it indicates that the candidate position of the puncture needle does not meet the preset conditions of the puncture needle.

[0118] The first depth and the second depth can be determined based on actual conditions (such as the shape and size of the target area). The planning system 200 can determine the distance between the body surface needle entry point and the point where the needle tip first touches the target area and the preset needle tip point based on the contour of the target area and the voxels on the contour, as well as the puncture direction of the puncture needle and other information, and then compare the aforementioned distances with the instrument length of the puncture needle to determine whether the candidate position of the puncture needle meets the preset conditions of the puncture needle.

[0119] In some embodiments, the puncture needle candidate positions that do not meet the puncture needle preset conditions may be eliminated by: when a puncture needle candidate position does not meet the puncture needle preset conditions, the planning system 200 may set the binary number of the puncture needle candidate position to 0; otherwise, it is set to 1.

[0120] Step 412: Eliminate candidate particle positions that do not meet the particle preset conditions. The particle preset conditions include one or more of the following: the particle candidate position is inside the target area, and the distance between the particle candidate position and the first puncture voxel or the last puncture voxel of the target area is less than a preset value.

[0121] The first puncture voxel of the target area refers to the voxel point where the puncture needle contacts the target area for the first time; the last puncture voxel refers to the voxel point corresponding to the position of the needle tip after the puncture needle is inserted.

[0122] In some embodiments, the candidate particle positions that do not meet the particle preset conditions may be eliminated by: when a candidate particle position does not meet the particle preset conditions, the planning system 200 may set the binary number of the candidate particle position to 0; otherwise, it is set to 1.

[0123] Figure 4b is an exemplary schematic diagram of puncture needle insertion according to preoperative planning of particle implantation as shown in some embodiments of the present specification.

[0124] like Figure 4b As shown, for the human body region (indicated by dotted lines in the figure), the puncture needle 4121 is an exemplary candidate puncture needle in the preoperative planning of particle implantation, and the voxel points (indicated by hollow points in the figure) after the puncture needle 4121 penetrates the target area 4120 include: the body surface needle entry point 412-1, the first puncture voxel 412-2 of the target area, the last puncture voxel 412-3 of the target area, and the last puncture voxel 412-4. Among them, the last puncture voxel 412-4 can correspond to the needle tip position of the puncture needle 4121. In some embodiments, the planning system 200 can place the needle tip at a preset extension distance (such as 5mm) along the direction of the puncture path after the puncture needle 4121 reaches the last puncture voxel 412-3 of the target area to determine the last puncture voxel 412-4. If the puncture needle 4121 is extended to pass through the first preset tissue and / or the second preset tissue, the needle tip retreats to the surface of the target area 4120. At this time, the last puncture voxel 412-4 overlaps with the last puncture voxel 412-3 of the target area.

[0125] In some embodiments, the planning system 200 can respectively determine the distance between the body surface needle entry point 412-1 and the first puncture voxel 412-2 of the target area, and the distance between the body surface needle entry point 412-1 and the last puncture voxel 412-4 to obtain the first depth and the second depth, and determine whether the puncture needle 4121 needs to be eliminated based on the processing of step 411. The planning system can also determine whether the particle candidate position (the scale on the needle, not shown in the figure) is located inside the target area 4120, and determine whether the distance between the particle candidate position outside the target area 4120 and the first puncture voxel 412-2 and the last puncture voxel 412-4 of the target area is less than a preset value (such as 5mm), and then determine whether each particle candidate position needs to be eliminated.

[0126] Step 420: Determine the initial puncture needle distribution based on the preprocessed candidate puncture needle positions.

[0127] In some embodiments, the planning system 200 may traverse the preprocessed binary sequence of candidate puncture needle positions, and obtain candidate puncture needle positions with a binary value of 1 in the binary sequence as one or more recommended puncture needle positions in the initial puncture needle distribution.

[0128] At the same time, for the recommended puncture needle position, the planning system 200 can traverse the binary sequence of particle candidate positions corresponding to each recommended puncture needle position, and obtain the particle candidate position with a binary value of 1 in the binary sequence as one or more particle placement positions on each recommended puncture needle in the initial puncture needle distribution, which specifically is one or more scales of the recommended puncture needle.

[0129] Based on the processing of step 420 above, the planning system 200 can obtain the initial puncture needle distribution.

[0130] In some embodiments of the present specification, the candidate puncture needle positions and candidate particle positions are screened by preprocessing, so that the candidate puncture needle positions and candidate particle positions that do not meet the conditions can be quickly eliminated, providing a good foundation for subsequent optimization.

[0131] Figure 5a is an exemplary flow chart of optimizing a particle implantation plan by using an optimization algorithm according to some embodiments of the present specification.

[0132] In some embodiments, process 500 may be performed by planning system 200 .

[0133] In some embodiments, the method flow of optimizing the puncture needle distribution by the first optimization algorithm and optimizing the particle distribution by the second optimization algorithm described in some embodiments of this specification can be similarly implemented according to process 500.

[0134] In some embodiments, the planning system 200 can perform optimization processing based on at least one round of iterative processing, optimizing the puncture needle distribution by a first optimization algorithm or optimizing the particle distribution by a second optimization algorithm. Figure 5a As shown, process 500 includes the following steps:

[0135] Step 510, obtaining an initial population, the initial population including a plurality of individuals, each individual corresponding to a particle implantation plan.

[0136] The initial population may refer to a set of one or more particle implantation plans before being optimized by the first optimization algorithm or the second optimization algorithm.

[0137] With respect to optimizing the puncture needle distribution by the first optimization algorithm, individuals in the initial population of the first round of iteration can be obtained based on the initial puncture needle distribution.

[0138] For optimizing the particle distribution by the second optimization algorithm, the initial population of the first round of iteration can be obtained based on the candidate particle implantation plan. The candidate particle implantation plan at this time can be a plurality of candidate particle implantation plans obtained after being optimized by the first optimization algorithm.

[0139] Each individual in the initial population can be a binary representation of the candidate particle implantation plan, which can be a binary matrix with k rows and m columns. For relevant content about the binary representation of the candidate particle implantation plan, see Figure 3a and its description.

[0140] In some embodiments, for optimizing the puncture needle distribution by the first optimization algorithm, the planning system 200 can determine one or more individuals based on the preprocessed initial puncture needle distribution and form an initial population. Exemplarily, in the preprocessed puncture needle distribution, all particle candidate positions on any puncture needle candidate position are set to place particles (the value of the binary bit corresponding to the particle candidate position that meets the preset particle condition is set to 1), thereby forming an individual. For relevant content about preprocessing, initial puncture needle distribution and particle preset conditions, see Figure 4a and its description.

[0141] Exemplarily, for the binary number matrix corresponding to each individual, the planning system 200 can randomly set the value of one or more binary bits on the puncture needle (such as puncture needle 1, puncture needle, etc.) in a certain individual to 0 or 1 according to a preset random probability (such as 0.5), and generate one or more new individuals. Based on the generated new individuals, they are combined into an initial population. In some embodiments, the number of individuals in the initial population can be a preset number of individuals (such as 10, 30).

[0142] It should be noted that, when the value of one or more binary bits is set from 0 to 1, the particle position corresponding to the binary bit needs to meet the particle preset condition.

[0143] In some embodiments, the preset random probability is related to the number of recommended puncture needles and the number of recommended particles. The preset random probability p can be determined based on the following formula (1):

[0144] Where p in formula (1) is the random probability, N rn and N rs Respectively represent the number of recommended puncture needles and the number of recommended particles, N pn and Nps Respectively represent the number of candidate puncture needles and the number of candidate particles. The number of recommended particles can be determined based on prior knowledge or medical experience. As an example, the number of recommended particles can be based on the medical experience formula: N rs =4.674×V 0.562 / A is determined, where V(cm 3 ) represents the target volume, A (mCi) represents the particle activity; the number of candidate particles can be determined based on the number of candidate particle positions in the initial puncture needle distribution. The planning system 200 can adjust the value of the binary bit in the initial puncture needle distribution based on the preset random probability to generate an initial population of a preset number of individuals (such as 30). For more information about candidate particle positions, see Figure 3a and its description.

[0145] In some embodiments of the present specification, a preset random probability is determined by introducing the relationship between the number of recommended puncture needles and the number of recommended particles, which is conducive to obtaining a good initial population, can improve the efficiency of subsequent optimization processing, and reduce the workload and time consumption of calculations.

[0146] Step 520: Generate a new population based on the initial population by using a preset deduction algorithm.

[0147] The preset inference algorithm may refer to an algorithm used to perform inference on an initial population to generate new individuals.

[0148] In some embodiments, the preset deduction algorithm may include the following steps S1 to S3:

[0149] Step S1, determining the first individual based on the initial population.

[0150] The first individual may refer to at least two individuals selected from the initial population. In some embodiments, for multiple individuals in the initial population, the planning system 200 may determine the first individual based on a preset individual ratio. The preset individual ratio may be set according to actual needs.

[0151] In some embodiments, the preset individual ratio is related to the total number of individuals in the initial population. The planning system 200 can determine the ratio of the first individual based on the total number of individuals in the initial population. For example, when the total number of individuals in the initial population is less than 40, the preset individual ratio can be 100%; when the total number of individuals in the initial population is greater than 100, the preset individual ratio can be 50%, etc.

[0152] By presetting the individual ratio to determine the number of the first individuals, the load of each round of iterative processing can be balanced.

[0153] In some embodiments, the planning system 200 may determine the first individual through a preset selection function based on the evaluation values ​​of the individuals in the initial population.

[0154] The evaluation value can represent the quality of an individual.

[0155] In some embodiments, for optimizing the puncture needle distribution by the first optimization algorithm, the evaluation value can be determined based on the function value of the first objective function; for optimizing the particle distribution by the second optimization algorithm, the evaluation value can be determined based on the function value of the second objective function.

[0156] The selection function may be any preset selection operator, such as a roulette selection operator, an expected value selection operator, a uniform sorting operator, etc. The larger the evaluation value of an individual is, the greater the probability that the individual is selected as the first individual by the selection function.

[0157] The first objective function is related to the total number of puncture needles and the total number of particles. For example, the function value of the first objective function can be the sum of the total number of puncture needles and the total number of particles corresponding to an individual. When the sum is smaller, the evaluation value corresponding to the individual is higher, indicating that the individual is better. The first objective function is only used as an example here, and the total number of puncture needles and the total number of particles can have different weight coefficients.

[0158] The second objective function is related to particle dose conformity and / or particle dose distribution uniformity.

[0159] The particle dose conformity can characterize the degree of influence of the particle dose of the particle implantation on the tissue around the target area. In some embodiments, the particle dose conformity can be determined based on the following formula (2):

[0160] In the above formula (2), CN represents the particle dose conformity, V T,ref It represents the volume of the area within the target area that is higher than the reference dose (PD), V T represents the target volume, V ref Indicates the volume that receives a dose higher than the reference dose (PD). The larger the CN value, the less dose leakage and the smaller the impact on the tissues around the target area. The higher the evaluation value of the individual, the better the individual.

[0161] In some embodiments of the present specification, by introducing particle dose conformity to evaluate the individual's quality, it is possible to avoid high doses to tissues around the target area and protect organs around the target area while ensuring the efficacy of particle implantation.

[0162] The particle dose distribution uniformity can characterize the uniformity of the dose distribution inside the target area. In some embodiments, the particle dose distribution uniformity can be determined based on the following formula (3):

[0163] In the above formula (3), DNR represents the uniformity of particle dose distribution, V ref represents the volume receiving dose higher than the reference dose (PD), V 1.5ref It indicates the volume that receives a dose higher than 1.5 times the reference dose (1.5×PD). The smaller the DNR value, the more uniform the dose distribution, the fewer local high-dose areas in the target area, the higher the evaluation value of the individual, and the better the individual.

[0164] In some embodiments of the present specification, by introducing the uniformity of particle dose distribution to evaluate the quality of an individual, it is possible to avoid the occurrence of uneven local high doses or local low doses in the target area and improve the treatment effect.

[0165] In some embodiments, the function value of the second objective function can be determined based on the particle dose conformity (CN value) and the particle dose distribution uniformity (DNR value). As an example only, the function value of the second objective function can be determined by the sum of the inverse of the CN value and the DNR value. When the CN value is larger and the DNR value is smaller, the function value of the second objective function is smaller, and the individual evaluation value is larger, that is, the individual is better.

[0166] Step S2, performing a first transformation process on the first individual to generate a second individual.

[0167] The first transformation process may refer to a process of pairing and processing the first individual to generate a new individual. The second individual may refer to a set of multiple new individuals generated by the first transformation process.

[0168] In some embodiments, the planning system 200 may randomly pair any two individuals in the first individual and adjust the puncture needle distribution and / or particle distribution of the two individuals.

[0169] In some embodiments, the first transformation process may include exchanging the particle distribution on the same puncture needle of two individuals.

[0170] Combination Figure 5b , Figure 5b is an exemplary schematic diagram of the first transformation process shown in some embodiments of the present specification.

[0171] For example only, Figure 5bAs shown, for the two first individuals, individual 521 and individual 522 respectively include 3 puncture needles (one row represents one puncture needle), and the distribution of particles on each puncture needle (1 represents placement of particles, and 0 represents no placement of particles).

[0172] The planning system 200 can exchange the particle distribution conditions in the puncture needle 1 of the individual 521 and the puncture 1 of the individual 522. Two second individuals are generated, namely Figure 5b Individual 521-1 and individual 522-1 are shown.

[0173] It is understandable that by exchanging the particle distribution conditions on the same puncture needles of two individuals, the generated second individual also satisfies the particle preset conditions. For relevant content about the particle preset conditions, see Figure 4a and its description.

[0174] In some embodiments, with the goal of increasing the evaluation value of an individual, the planning system 200 can traverse the puncture needles in the two paired individuals respectively, and obtain the number of binary bits with a value of 1 in each puncture needle (hereinafter referred to as the number of particles), and then use the particle distribution of the puncture needle corresponding to the maximum number of particles for the first transformation process. Figure 5b For the three puncture needles in individual 521, the numbers of particles are 8, 2 and 3 respectively; for the three puncture needles in individual 522, the numbers of particles are 5, 3 and 4 respectively. Among them, the number of particles in puncture needle 1 of individual 521 is the largest, and the particle distribution of puncture needle 1 can be used for the first transformation process mentioned above.

[0175] It can be understood that the first transformation process is conducive to retaining the puncture needles with fewer particles in the individual; at the same time, exchanging the particle distribution of the puncture needle with the largest number of particles with the particle distribution of the puncture needle corresponding to the paired individual is conducive to reducing the number of particles on the puncture needle, thereby optimizing the particle distribution of the individual in the direction of reducing the function value of the first objective function. In addition, optimizing the particle distribution through the first transformation process at the puncture needle level is conducive to quickly expanding the individual search space and improving the speed and efficiency of obtaining the optimal individual.

[0176] The first transformation process is only used as an example. For example, the first transformation process may be to exchange the distribution of particles on one or more puncture needles. In some embodiments, the first transformation process may also perform an exchange process of the particle placement state (0 or 1) on one or more particles (such as particles at the same particle candidate position) on the corresponding puncture needles (such as puncture needles at the same puncture needle candidate position) in two paired individuals to generate a new individual. Exemplarily, the particle placement states corresponding to multiple particle candidate positions on one or more puncture needles may be obtained randomly or according to a preset probability to form a combination for performing the first transformation process.

[0177] In some embodiments of the present specification, the speed of acquiring new individuals can be accelerated through the first transformation processing, which is beneficial to the expansion of the population and the speed of obtaining excellent individuals.

[0178] Step S3, performing a second transformation process on the individuals in the initial population and / or the second individual to generate a third individual.

[0179] The second transformation process may refer to a process of adjusting the particle distribution of a single individual to generate a new individual. The third individual may refer to a set of one or more new individuals generated by the second transformation process.

[0180] In some embodiments, the planning system 200 may select one or more individuals from the initial population and / or the second individual and adjust the particle distribution on the puncture needle of each individual. Figure 5b The particle distribution in the puncture needle (such as puncture needle 1, puncture needle 2, etc.) of the individual 521-1 shown in the figure can be adjusted. For example, the value of the first binary bit in the puncture needle 1 of the individual 521-1 can be set from 1 to 0; the value of the second binary bit can also be set from 0 to 1; or the combination of multiple (such as 2, 3, etc.) binary bits can be adjusted. Then one or more third individuals are generated.

[0181] It should be noted that, during the second transformation process, when the value of a binary bit is set from 0 to 1, the particle position corresponding to the binary bit needs to meet the particle preset condition.

[0182] In some embodiments of the present specification, the second transformation processing is used to achieve local optimization of the particle distribution of the individual at the particle level, and at the same time, the diversity of the particle distribution of the individual is increased, which is conducive to obtaining individuals with higher evaluation values.

[0183] Step 530 , based on the constraint condition or based on the constraint condition and the objective function, select target individuals from the initial population and the new population to form a target population, and the initial population in the next round of iterative processing is the target population.

[0184] Wherein, for optimizing the puncture needle distribution by the first optimization algorithm, the constraint condition is the first constraint condition, and the objective function is the first objective function;

[0185] For optimizing the particle distribution by the second optimization algorithm, the constraint condition is the second constraint condition, and the objective function is the second objective function.

[0186] The new population may refer to a population composed of new individuals obtained through the first transformation process and / or the second transformation process, and may include a second individual generated through the first transformation process and / or a third individual generated through the second transformation process.

[0187] In some embodiments, with respect to optimizing the puncture needle distribution through a first optimization algorithm, the planning system 200 may screen individuals in the initial population and the new population based on a first constraint condition so that the candidate particle implantation plan satisfies the first constraint condition and the function value of the first objective function gradually decreases with the optimization (the individual evaluation value gradually increases).

[0188] With respect to optimizing the particle distribution through the second optimization algorithm, the planning system 200 can screen the individuals in the initial population and the new population based on the second constraint condition so that the target particle implantation plan satisfies the second constraint condition and the function value of the second objective function gradually decreases with the optimization (the individual evaluation value gradually increases).

[0189] For the convenience of the following description, the optimization of the puncture needle distribution by the first optimization algorithm can be referred to as the first stage optimization; the optimization of the particle distribution by the second optimization algorithm can be referred to as the second stage optimization.

[0190] The first constraint condition or the second constraint condition may refer to a discriminant condition for screening individuals in the initial population and the new population, and may be set according to actual needs.

[0191] In some embodiments, the first constraint is related to the target dose coverage. The target dose coverage can be used to characterize that the dose at the target needs to reach a certain level to ensure the treatment effect. The target dose coverage needs to reach a preset target dose coverage. The preset target dose coverage can be determined according to clinically relevant needs or requirements, for example, it can be related to D90. D90 represents the dose level of the isodose line within the target area that contains 90% of the volume of the target area.

[0192] In some embodiments, the first constraint condition may be determined based on the following expression (4): c=δ[D90 <PD]×(D90-PD) (4)

[0193] Among them, δ[x] is an indicator function that returns 1 when x is true and 0 otherwise. In the above expression (4), PD represents the reference dose (or prescribed dose), which can be determined based on scientific research institutions or medical experience. c represents the discrimination value of the second constraint condition. Expression (4) means that when the value of D90 is lower than the reference dose PD (i.e., D90 < PD), the constraint discrimination value c takes the value of the part (c90 - PD), that is, the difference between D90 and PD. At this time, the discrimination value c is negative, indicating that the individual does not meet the first constraint condition; otherwise, it is 0, indicating that the individual meets the first constraint condition. That is to say, the first constraint condition can be that the dose level of the isodose line containing 90% of the volume of the target area in the target area (i.e., D90) needs to be higher than the reference dose PD.

[0194] In some embodiments, the first constraint condition is also related to the dose limit of the second preset tissue. For example, the second constraint condition may further include that the volume dose and point dose of the second preset tissue around the target area are respectively less than the preset maximum volume dose and preset maximum point dose. Among them, the preset maximum volume dose and preset maximum point dose can be determined according to the type of the second preset tissue, and they can be obtained based on medical prior knowledge. For example, the second preset tissue around the target area is the spinal cord, and its corresponding maximum volume dose is 10 Gy and the maximum point dose is 14.0 Gy. Another example is that the second preset tissue around the target area is the main bronchus, and its corresponding maximum volume dose is 10.5 Gy and the maximum point dose is 16.0 Gy. For more content about the second preset tissue and its dose limit, see Figure 3a And its description.

[0195] In some embodiments, the planning system 200 can respectively obtain the D90 values of each individual in the initial population and the new population, and according to the discrimination value of the above expression (4), obtain the target individuals that meet the first constraint condition, form a target population, and use this target population as the initial population for the next round of iterative processing.

[0196] In some embodiments, the second constraint condition is related to the dose coverage rate of the target area and the total number of puncture needles and / or the total number of particles. Among them, the total number of puncture needles here is related to the increment threshold of the total number of puncture needles of the individual before and after the second-stage optimization; the total number of particles is related to the increment threshold of the total number of particles of the individual before and after the second-stage optimization. In other words, after the second-stage optimization, the change situation of the total number of puncture needles and the total number of particles of the individual needs to meet the second constraint condition.

[0197] The increment threshold of the total number of puncture needles and the increment threshold of the total number of particles can be determined based on the actual situation. For example, it can be determined according to the actual size of the target area, the type of tissue around the target area (such as the heart, lungs), etc.

[0198] In some embodiments, by way of example, the incremental threshold of the total number of puncture needles can be set to 3, and the incremental threshold of the total number of particles can be set to 5. The second constraint condition can be determined based on the following expression (5): c = δ[D90 < PD]×(D90 - PD)+δ[N n > N n,0 + 3]×(N n,0 + 3 - N n )+δ[N s > N s,0 + 5]×(N s,0 + 5 - N s ) (5)

[0199] In the above expression (5), δ[x] is an indicator function. If x is true, it returns 1; otherwise, it returns 0. N n,0 and N a,0 respectively represent the number of needles and the number of particles corresponding to the individual (target particle implantation plan) obtained after the second-stage optimization. For example, the number of needles of an individual is 10 and the number of particles is 20.

[0200] The first part δ[D90 < PD]×(D90 - PD) of the above expression (5) means that when the D90 of this individual is lower than the reference dose PD, the constraint discrimination value of the first part is the difference between the two, which is a negative value; otherwise, it is 0;

[0201] The second part δ[N n > N n,0 + 3]×(N n,0 + 3 - N n ) In this part, N n represents the number of needles of the individual before optimization, and N n,0 represents the number of needles of this individual after optimization. The second part means that when the incremental number of needles N n - N n,0 exceeds 3, the constraint discrimination value of the second part is N n,0 + 3 - N n , and the score is a negative value; otherwise, it is 0;

[0202] The third part δ[N s > N s,0 + 5]×(N s,0 + 5 - N s ) In this part, N s represents the number of particles of the individual before optimization, and N s,0 represents the number of particles of this individual after optimization. The third part means that when the incremental number of particles N s - N s,0 exceeds 5, the constraint discrimination value of the third part is N s,0 + 5 - Ns , that is, a negative number; otherwise, it is 0.

[0203] The c in the above expression (5) represents the discriminant value of the entire expression (5), which is determined based on the sum of the discriminant values ​​of the first part, the second part, and the second part of the expression (5). If the value of c is negative, it means that the individual does not satisfy the second constraint condition, otherwise the value of c is 0, which means that the individual satisfies the second constraint condition.

[0204] It should be noted that the puncture needle increment threshold 3 and the particle increment threshold 5 are only used as examples, and they can be set according to actual conditions (for example, the puncture needle increment threshold is 4, the particle increment threshold is 6, etc.), and the above formula expression (5) is modified accordingly.

[0205] In some embodiments of the present specification, by introducing a puncture needle increment threshold and a particle increment threshold, the second stage optimization can appropriately limit the number of puncture needles and the number of particles while satisfying the first constraint condition, thereby avoiding the situation where the number of puncture needles and / or the number of particles is too large in the individuals generated by the deduction of the second optimization stage.

[0206] In some embodiments, the second constraint is also related to the dose limit of the second preset tissue. Similar to the first constraint, the second constraint may include that the volume dose and point dose of the second preset area around the target area are respectively less than the preset maximum volume dose and the preset maximum point dose.

[0207] In some embodiments, during the optimization process of the second optimization stage, the planning system 200 may also obtain the difference particles of the particle distribution of the optimized particle implantation plan and the candidate particle implantation plan corresponding to the optimized particle implantation plan, and determine the dose at the difference particle when the number of difference particles is less than the preset total number of particles. The optimized particle implantation plan refers to the second individual or the third individual generated by the second stage optimization. It can be understood that there is a change in the particle distribution of the two individuals of a candidate particle implantation plan (i.e., the individual before the second stage optimization) and the optimized particle implantation plan (i.e., the individual after the second stage optimization) obtained after the second stage optimization. The preset total number of particles can be determined based on the maximum number of current particles in the two individuals. The number of difference particles can be determined based on the number of inconsistent particle placement states (0 or 1) of the same particle candidate position in the two individuals. For example, the particle placement states of the first particle candidate position on a puncture needle in individual A and individual B are different (such as the former is 0 and the latter is 1), and the others are consistent, then the number of difference particles is 1.

[0208] It should be noted that after the first stage of optimization, during the optimization process of the second optimization stage, the particle distribution of each individual obtained by optimizing through the above-mentioned preset deduction algorithm (such as the second individual or the third individual generated in the second optimization stage) is smaller than the particle distribution of the individual before optimization. By comparing the difference in particle distribution of the individual before and after optimization, when the difference value is less than the preset total number of particles, the dose at the difference particle can be directly calculated, thereby accelerating the dose calculation (such as the calculation of spatial dose distribution), and then accelerating the optimization process.

[0209] As an example, for a candidate particle implantation plan (such as individual A) and individual B obtained after the second stage optimization, the particle distributions of the two individuals are 1100 and 1110 respectively, and the number of difference particles between the two is 1 (i.e., individual B places one more particle at the third position, and the other positions are the same), which is less than the maximum number of particles of the two individuals, 3 (i.e., the number of particles of individual B). At this time, the planning system 200 can directly calculate the dose at the difference particle (the third position of individual B). The difference in particle distribution of multiple puncture needles and the determination of the dose at the difference particle are similar.

[0210] It should be noted that before calculating the CN value and DNR value of an individual, it is necessary to calculate the spatial dose distribution (such as the dose at multiple particles). In some embodiments of this specification, by calculating the dose at the difference particle, it is possible to avoid recalculating the dose of all particles in the individual particle distribution, thereby reducing the time spent on calculation. While accelerating the dose calculation, it is possible to improve the efficiency of optimization.

[0211] In some embodiments, the planning system 200 may also sort the target populations that meet the first constraint and / or the second constraint. This may be an algorithm preset according to actual conditions. For example, the populations may be sorted according to the size of the evaluation values ​​(e.g., in descending order), and the top ranked individuals may be selected.

[0212] In some embodiments, the sorting process may include available algorithms with similar functions such as non-dominated sorting algorithms. As an example, through the processing of the non-dominated sorting algorithm, the target population is stratified to obtain non-dominated individuals in the stratified levels. The higher the level of the individual, the higher the non-dominated state of the individual, and the greater the probability of being screened out to enter the next round of iteration. At the same time, the crowding degree of the individuals in each dominant level can also be calculated. When the crowding distance between an individual and its adjacent individuals is larger, it indicates that the surroundings of the individual are sparser and the crowding degree of the individual is greater. The larger the crowding degree, the lower the similarity between the individual and other individuals, and the greater the probability of being screened out to enter the next round of iteration.

[0213] In some embodiments of the present specification, individuals selected by a non-dominated sorting algorithm are used as a target population, and the target population is used as the initial population for the next round of iterative processing, so that the individuals in the population have diversity, which is conducive to obtaining a better particle implantation plan during the optimization process.

[0214] Step 540, determining a target result in the target population obtained after at least one round of iterative processing.

[0215] In some embodiments, the planning system 200 may repeat the iterative processing of step 520 and step 530 above until the iterative processing is terminated when a preset termination condition is met, thereby obtaining the target population. The preset termination condition may include but is not limited to reaching a preset number of iterations and the number of individuals in the target population reaching a preset number of individuals.

[0216] The planning system 200 may determine a target outcome based on the target population.

[0217] For the first optimization stage, the target result can be used as a candidate particle implantation plan, which can be used as the initial population for the second optimization stage. For the second optimization stage, the target result can be used as a target particle implantation plan. It should be noted that the above target result can be multiple candidate particle implantation plans and / or target particle implantation plans, which can also be used for selection or adjustment by the user. For example, the user can make appropriate adjustments based on experience.

[0218] In some embodiments, the target particle implantation plan generated by the planning system 200 can be used to guide a user (eg, a medical staff) to perform particle implantation on a target object. Figure 5c , Figure 5c is an exemplary schematic diagram of a target particle implantation plan for particle implantation according to some embodiments of the present specification.

[0219] like Figure 5cAs shown, the cylinder represents the target area 322 in the target object (organs and other tissues around the target area are not shown). For a certain target particle implantation plan, the user can determine the multiple recommended puncture needles 541 (indicated by the vertical lines perpendicular to the particle implantation template 321 in the figure, such as 5 recommended puncture needles) actually inserted into the target area 322 according to the multiple recommended puncture needle positions in the particle implantation template 321 (the value of the binary bit corresponding to the candidate puncture needle position is 1), and determine the placement of particles based on the particle distribution information on each puncture needle in the target particle implantation plan. For example only, for the recommended puncture needle 541, among the five candidate particle positions corresponding to the five scales on the needle (indicated by black solid points and hollow points), each black solid point 542-1 corresponds to the position where the value of the binary bit on the puncture needle is 1, indicating that the position needs to place particles, and the hollow point 543-1 corresponds to the position where the value of the binary bit on the puncture needle is 0, indicating that particles are not placed. The same is true for other recommended puncture needles, so as to achieve treatment of the target object.

[0220] In some implementations, the planning system 200 can also generate a particle implantation plan report corresponding to one or more individuals based on the target result. The particle implantation plan report may include, but is not limited to: basic information of the target object (such as a patient); image data (such as the outline of the target area and tissue area); instrument information (such as puncture needle length, scale, particle type, particle activity, particle implantation template information, etc.); position and direction of the puncture needle; particle distribution on the puncture needle (such as the number and position of particles); visualization of the puncture needle track and particle spatial distribution; isodose line display of the dose distribution generated by the particles; DVH curve display of the dose distribution generated by the particles; quantitative evaluation results of the dose distribution, including indicators such as particle dose conformity and particle dose distribution uniformity.

[0221] In some embodiments of this specification, the optimized target particle implantation plan can be automatically obtained through the first optimization algorithm and / or the second optimization algorithm, which can reduce the manpower and time costs caused by manual deduction. At the same time, the combination of the first optimization algorithm and the second optimization algorithm, based on the individual obtained by the optimization of the first optimization algorithm, the optimization of the second optimization algorithm can make the individual optimization direction more targeted, stable and reliable, thereby achieving a more accurate target particle implantation plan that better meets actual needs.

[0222] It should be noted that the first optimization algorithm and / or the second optimization algorithm may also be other feasible optimization algorithms or search algorithms.

[0223] In some embodiments, the optimization strategy of the first optimization algorithm and / or the second optimization algorithm may be related to the time complexity and / or space complexity of the optimization process. Exemplarily, when the target area is small (such as a small cross-sectional area, a small volume, etc.), the number of puncture needles required for particle implantation is small, and / or the number of particles is small, then the number of particle implantation plans is small. At this time, the time complexity and / or space complexity of the optimization process is low. The first optimization algorithm and / or the second optimization algorithm may be a set composed of enumerating different combinations of 0 or 1 (a combination of binary values ​​corresponding to all candidate particle positions is an individual) to determine the candidate particle implantation plan and / or the target particle implantation plan; otherwise, the first optimization algorithm and / or the second optimization algorithm may be such as Figure 5a The strategy shown can also be implemented by other combinatorial optimization algorithms (such as simulated annealing algorithm, etc.).

[0224] The planning system 200 can determine the optimization strategy of the first optimization algorithm and / or the second optimization algorithm based on the actual situation (such as parameter configuration), and optimize the puncture needle distribution through the first optimization algorithm with the goal of making the candidate particle implantation plan satisfy the first constraint and reducing the function value of the first objective function to obtain the candidate particle implantation plan; at the same time, with the goal of making the target particle implantation plan satisfy the second constraint and reducing the function value of the second objective function, the particle distribution is optimized through the second optimization algorithm to obtain the target particle implantation plan.

[0225] Figure 6 is an exemplary flow chart of another method for preoperative planning of target seed implantation according to some embodiments of the present specification.

[0226] In some embodiments, process 600 may be performed by planning system 200. Figure 6 As shown, process 600 includes the following steps:

[0227] Step 610: Acquire image data of the segmented target area and tissue area of ​​the target object.

[0228] For details about step 610, see Figure 3a Step 310 and its description.

[0229] Step 620, determining an initial puncture needle distribution based on a representation model associated with particle implantation, wherein the representation model includes a puncture needle candidate position representation and a particle candidate position representation associated with the image data, wherein a puncture needle candidate position corresponds to one or more particle candidate positions.

[0230] For details about step 620, please refer to Figure 3a . Step 320 and its description in .

[0231] Step 630: Based on the initial puncture needle distribution, the puncture needle distribution is optimized by a first optimization algorithm to obtain a target particle implantation plan.

[0232] For more information about the first optimization algorithm to optimize the distribution of puncture needles, see Figure 5a and its description.

[0233] In some embodiments, for one or more candidate particle implantation plans obtained by optimizing the puncture needle distribution through the first optimization algorithm, the planning system 200 can determine whether the candidate particle implantation plan meets the preset clinical conditions. The preset clinical conditions may include the second constraint condition and / or the second objective function.

[0234] For more information about the second constraint and the second objective function, see Figure 5a and its description.

[0235] In response to the existence of a candidate seed implantation plan that meets the preset clinical condition, the candidate seed implantation plan may be used as a target seed implantation plan.

[0236] In some embodiments of the present specification, the puncture needle distribution is optimized by a first optimization algorithm. When a candidate particle implantation plan meets clinical conditions, the candidate particle implantation plan is used as a target particle implantation plan without the need for a second optimization stage, thereby reducing computational and time costs.

[0237] Figure 7 is an exemplary schematic diagram of a particle implantation preoperative planning device according to some embodiments of the present specification.

[0238] like Figure 7 As shown, the particle implantation pre-operative planning device 700 includes a processor 710 and a memory 720 coupled to the processor 710 .

[0239] The memory 720 stores program instructions for implementing the method of any of the above embodiments; the processor 710 is used to execute the program instructions stored in the memory 720 to implement the steps of the above method embodiments. The processor 710 may also be referred to as a CPU (Central Processing Unit). The processor 710 may be an integrated circuit chip with signal processing capabilities. The processor 710 may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0240] It should be noted that the above description of the relevant 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 the process under the guidance of this specification. However, these modifications and changes are still within the scope of this specification.

[0241] 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.

[0242] 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 method for preoperative planning of particle implantation, characterized in that: include: Acquire image data of segmented target areas and tissue areas of the target object; Determining an initial puncture needle distribution based on a representation model associated with the particle implantation, the representation model comprising a puncture needle candidate position representation and a particle candidate position representation associated with the image data, wherein the puncture needle candidate position corresponds to one or more of the particle candidate positions; Based on the initial puncture needle distribution, optimizing the puncture needle distribution by a first optimization algorithm to obtain a candidate particle implantation plan; Based on the candidate particle implantation plan, the particle distribution is optimized by a second optimization algorithm to obtain a target particle implantation plan.

2. The method according to claim 1, characterized in that The representation model includes a representation model based on a coplanar needle group, and the puncture needle candidate position representation and / or the particle candidate position representation are binary representations.

3. The method according to claim 1, characterized in that The determining of the initial puncture needle distribution based on the representation model associated with the particle implantation further comprises: Based on the representation model, the candidate positions of the puncture needle are preprocessed, and the preprocessing includes one or more of the following: eliminating the candidate positions of the puncture needle that do not meet the preset conditions of the puncture needle, and eliminating the candidate particle positions that do not meet the preset conditions of the particle; wherein, The puncture needle preset conditions include one or more of the following: the puncture needle at the puncture needle candidate position cannot penetrate the target tissue, the insertion depth of the puncture needle at the puncture needle candidate position is less than the instrument length of the puncture needle; The particle preset conditions include one or more of the following: the particle candidate position is inside the target area, the distance between the particle candidate position and the first puncture voxel or the last puncture voxel of the target area is less than a preset value; and The initial puncture needle distribution is determined based on the preprocessed candidate puncture needle positions.

4. The method according to claim 1, characterized in that: The optimizing the puncture needle distribution by a first optimization algorithm based on the initial puncture needle distribution to obtain a candidate particle implantation plan includes: The candidate particle implantation plan is optimized by the first optimization algorithm to satisfy the first constraint condition and reduce the function value of the first objective function, thereby obtaining the candidate particle implantation plan; wherein, In the puncture needle distribution, particles are placed at all particle candidate positions on any of the puncture needle candidate positions; and the first constraint condition is related to the target area dose coverage, and the first objective function is related to the total number of puncture needles and the total number of particles.

5. The method according to claim 1, characterized in that The step of optimizing the particle distribution based on the candidate particle implantation plan by a second optimization algorithm to obtain a target particle implantation plan comprises: The target particle implantation plan is optimized by the second optimization algorithm to satisfy the second constraint condition and reduce the function value of the second objective function, thereby obtaining the target particle implantation plan; wherein, The second constraint condition is related to the target area dose coverage, the total number of puncture needles and / or the total number of particles; the second objective function is related to the particle dose conformity and / or the particle dose distribution uniformity.

6. The method according to claim 5, characterized in that Further including: In the optimization process, obtaining difference particles of the particle distribution between the optimized particle implantation plan and the candidate particle implantation plan corresponding to the optimized particle implantation plan; When the number of the difference particles is less than the preset total number of particles, the dose at the difference particles is determined.

7. The method according to claim 4 or 5, characterized in that: The optimizing of the puncture needle distribution by the first optimization algorithm or the optimizing of the particle distribution by the second optimization algorithm comprises: The optimization process is performed based on at least one round of iterative processing, wherein the round of iterative processing includes: Acquire an initial population, wherein the initial population includes a plurality of individuals, each individual corresponding to a particle implantation plan; Based on the initial population, a new population is generated by a preset deduction algorithm; Based on the constraint condition or based on the constraint condition and the objective function, target individuals are selected from the initial population and the new population to form a target population, and the initial population in the next round of iterative processing is the target population; Determine the target result in the target population obtained after the optimization process; wherein, For optimizing the puncture needle distribution by the first optimization algorithm, the constraint condition is the first constraint condition, the objective function is the first objective function, the initial population of the first round of iteration is obtained based on the initial puncture needle distribution, and the target result is the candidate particle implantation plan; With respect to optimizing the particle distribution by using the second optimization algorithm, the constraint condition is the second constraint condition, the objective function is the second objective function, the initial population of the first round of iteration is obtained based on the candidate particle implantation plan, and the target result is the target particle implantation plan.

8. A method for preoperative planning of particle implantation, characterized in that: include: Acquire image data of segmented target areas and tissue areas of the target object; Determining an initial puncture needle distribution based on a representation model associated with the particle implantation, the representation model comprising a puncture needle candidate position representation and a particle candidate position representation associated with the image data, wherein the puncture needle candidate position corresponds to one or more of the particle candidate positions; Based on the initial puncture needle distribution, the puncture needle distribution is optimized by a first optimization algorithm to obtain a target particle implantation plan.

9. A particle implantation preoperative planning system, characterized in that: include: An acquisition module, used for acquiring image data of the segmented target area and tissue area of ​​the target object; A determination module, configured to determine an initial puncture needle distribution based on a representation model associated with the particle implantation, wherein the representation model includes a puncture needle candidate position representation and a particle candidate position representation associated with the image data, wherein the puncture needle candidate position corresponds to one or more of the particle candidate positions; A first optimization module, configured to optimize the puncture needle distribution based on the initial puncture needle distribution by a first optimization algorithm to obtain a candidate particle implantation plan; The second optimization module is used to optimize the particle distribution based on the candidate particle implantation plan by a second optimization algorithm to obtain a target particle implantation plan.

10. A particle implantation preoperative planning device, characterized in that: The method comprises a processor, wherein the processor is used to execute the particle implantation preoperative planning method according to any one of claims 1 to 8.

Images