Particle implantation planning system, method and device

Abstract

The embodiment of the invention provides a particle implantation planning system, method and device, and the system comprises a processor which is used for executing the following operations: obtaining medical image data of a target object; determining object features of the target object based on the medical image data; the object feature comprises a target region; determining a needle insertion path of a reference puncture needle based on the object characteristics of the target object; determining a candidate puncture needle group meeting a preset condition at least based on the needle entering path of the reference puncture needle; particle distribution optimization and needle group optimization are carried out on puncture needles in the candidate puncture needle group, and a target puncture needle group is determined; the target puncture needle group comprises a puncture path of a target puncture needle and particle distribution in the target puncture needle.

Description

Technical Field

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

[0002] Particle implantation is a brachytherapy technique that is suitable for the treatment of a variety of tumors. During particle implantation, radioactive particles are delivered to the target area through a puncture needle to kill tumor cells from the inside. The puncture technique is one of the key factors that determine the efficacy of particle implantation.

[0003] This specification provides a particle implantation planning system, method and device for planning particle implantation before surgery to ensure accurate puncture during surgery. Summary of the invention

[0004] One or more embodiments of the present specification provide a particle implantation planning system, the system including a processor, the processor being configured to perform the following operations: acquiring medical imaging data of a target object; determining object features of the target object based on the medical imaging data; the object features including a target area; determining a needle entry path of a reference puncture needle based on the object features of the target object; determining a candidate puncture needle group that meets preset conditions based at least on the needle entry path of the reference puncture needle; performing particle distribution optimization and needle group optimization on the puncture needles in the candidate puncture needle group to determine a target puncture needle group; the target puncture needle group includes the puncture path of the target puncture needle and the particle distribution in the target puncture needle.

[0005] One or more embodiments of the present specification provide a particle implantation planning method, the method comprising: acquiring medical imaging data of a target object; determining object features of the target object based on the medical imaging data; the object features comprising a target area; determining a needle entry path of a reference puncture needle based on the object features of the target object; determining a candidate puncture needle group that meets preset conditions based at least on the needle entry path of the reference puncture needle; performing particle distribution optimization and needle group optimization on the puncture needles in the candidate puncture needle group to determine a target puncture needle group; the target puncture needle group comprises the puncture path of the target puncture needle and the particle distribution in the target puncture needle.

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

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

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

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

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

[0011] Figure 3 is an exemplary flow chart for determining the needle insertion path of a reference puncture needle according to some embodiments of this specification;

[0012] Figure 4 is an exemplary flow chart for determining a candidate puncture needle group according to some embodiments of this specification;

[0013] Figure 5 is an exemplary schematic diagram of an iterative determination method according to some embodiments of this specification;

[0014] Figure 6 is an exemplary flow chart of calculating target area coverage according to some embodiments of this specification;

[0015] Figure 7 is an exemplary flow chart for determining a target puncture needle set according to some embodiments of this specification;

[0016] Figure 8 is an exemplary flow chart of a particle distribution optimization method according to some embodiments of this specification;

[0017] Fig. 9 is an exemplary flow chart of updating the punctured particle distribution according to some embodiments of the present specification;

[0018] Fig.10 is an exemplary schematic diagram of the length and angle of the puncture needle according to some embodiments of this specification;

[0019] Fig.11 is an exemplary schematic diagram of a reference puncture needle according to some embodiments of the present specification;

[0020] Fig.12 is an exemplary schematic diagram of a preset range according to some embodiments of this specification;

[0021] Fig.13 is an exemplary schematic diagram of target area coverage according to some embodiments of this specification;

[0022] Fig.14 is an exemplary schematic diagram of updating target area coverage according to some embodiments of this specification;

[0023] Fig.15 is an exemplary schematic diagram of a candidate puncture needle group according to some embodiments of this specification;

[0024] Fig.16 is an exemplary schematic diagram of preset equally spaced scales in a puncture needle according to some embodiments of this specification;

[0025] Fig.17 is an exemplary schematic diagram of a non-coplanar template according to some embodiments of the present specification. DETAILED DESCRIPTION

[0026] 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.

[0027] 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.

[0028] As shown in this specification and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprise" and "include" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0029] 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.

[0030] In particle implantation, templates are often used to limit the position and direction of the puncture needle (referred to as the needle). The templates used in particle implantation are divided into two categories: coplanar templates and non-coplanar templates. The puncture needles determined by the coplanar template are parallel, that is, the directions of all puncture needles are consistent. For specific parts, due to the obstruction of important organs (such as the obstruction of a large number of ribs and blood vessels in the chest and abdomen), it is difficult to plan a dose coverage plan using a coplanar template. The puncture needles determined by the non-coplanar template can be skewed, and the puncture needles can be punctured from any angle, which is highly flexible and can effectively alleviate the above-mentioned problem of non-compliant dose coverage while avoiding dangerous organs.

[0031] Although the puncture of the puncture needle is highly flexible and can solve the problem of target area dose coverage, it will also cause the search space and the amount of calculation when planning the puncture path of the puncture needle to expand dramatically, which will reduce the efficiency and increase the difficulty of particle implantation planning. There are few studies on the puncture needle puncture needle puncture planning algorithm for particle implantation in related technologies, and a large amount of manual interaction is required (such as repeated manual adjustment of the number of needles and particles), which is more dependent on subjective experience.

[0032] In view of this, some embodiments of the present specification provide a particle implantation planning system and method, which can quickly and accurately plan a non-planar puncture needle group and the particle distribution within the puncture needle.

[0033] Figure 1 It is a schematic diagram of an exemplary application scenario of a particle implantation planning system according to some embodiments of this specification.

[0034] In some embodiments, Figure 1 As shown, the particle implantation planning system 100 includes a surgical robot device 110 , a network 120 , a terminal 130 , a processing device 140 , and a storage device 150 .

[0035] In some embodiments, the particle implantation planning system 100 is applied to medical fields that require complex operations, such as completing the surgical planning of particle implantation and the execution of interventional surgery (including particle implantation surgery and other interventional surgery). Particle implantation planning refers to determining the puncture needle and the particle distribution in the puncture needle through imaging before surgery, so that the puncture needle can avoid important tissues and implant into the target area, and the implanted particles can minimize the radiation to surrounding important tissues when radiating the target area, thereby obtaining better therapeutic effects. In some embodiments, the puncture needle group and the particle distribution in the needle planned by the particle implantation planning system can also be applied to the execution of manual surgery, which is not limited in this specification.

[0036] The surgical robot device 110 can perform corresponding operations according to the received instructions (e.g., control signal instructions). In some embodiments, the surgical robot device 110 includes a surgical robot, a medical device, and a mobile bed. When the surgical robot device 110 receives data or instructions sent by other devices or system components, the mobile bed can carry the patient to the position indicated by the instruction, the medical device starts the working state according to the instruction, and the surgical robot performs surgery based on the instruction (e.g., performing particle implantation surgery). In some embodiments, the surgical robot includes a robotic arm, an end instrument (e.g., an end clamp, a puncture needle, and other surgical instruments, etc.). When the surgical robot receives data or instructions sent by other devices or system components, the robotic arm on the surgical robot moves to move the end instrument to the position indicated by the instruction and perform surgical actions (e.g., inserting the puncture needle into the patient's body). In some embodiments, the surgical robot can be integrated with the medical device or can be separated. For example, the bottom of the surgical robot includes a bottom cart, and the surgical robot can be moved to a suitable position by the bottom cart to perform interventional surgery. In some embodiments, the surgical robot may also be provided with a sensor to detect kinematic parameters (e.g., position, angle, speed, etc.) when the connecting rod moves, and feed the kinematic parameters back to the processing device 140 or the terminal 130. In some embodiments, the surgical robot may also be provided with a camera to obtain an image of the surgical robot and its environment, and send the image to the processing device 140 or the terminal 130.

[0037] The network 120 includes any suitable network that can facilitate information and / or data exchange of the surgical robot device 110. In some embodiments, at least one component of the particle implantation planning system 100 (e.g., the surgical robot device 110, the terminal 130, the processing device 140, and the storage device 150) can exchange information and / or data with at least one other component in the particle implantation planning system 100 through the network 120. For example, the processing device 140 obtains a medical image of the target object from the terminal 130 through the network 120. For another example, the processing device 140 performs particle implantation planning based on the obtained medical image of the target object, and sends the result of the particle implantation planning to other components in the system, such as to the terminal 130 for display, for user confirmation, etc. In some embodiments, the network 120 includes at least one network access point. For example, the network 120 includes a wired and / or wireless network access point (e.g., a base station and / or an Internet exchange point), and at least one component of the particle implantation planning system 100 can be connected to the network 120 through the access point to exchange data and / or information.

[0038] The terminal 130 is capable of communicating and / or connecting with the surgical robot device 110, the processing device 140 and / or the storage device 150. In some embodiments, the terminal 130 includes a mobile device 131, a tablet computer 132, a laptop computer 133, etc. or any combination thereof. For example, the mobile device 131 includes a mobile control handle, a personal digital assistant (PDA), a smart phone, etc. or any combination thereof. In some embodiments, the terminal 130 includes a display device, such as a display. The display device is used to display information or images related to the particle implantation surgery, such as particle implantation planning results, medical images of patients, three-dimensional models, or operation panels related to the particle implantation surgery. In some embodiments, the terminal 130 is part of the processing device 140.

[0039] The processing device 140 can be used to process data and / or information obtained from the surgical robot device 110, the terminal 130, the storage device 150, or other components of the particle implantation planning system 100. For example, the processing device 140 can obtain medical imaging data of the target object; based on the medical imaging data, determine the object characteristics of the target object; the object characteristics include the target area based on the object characteristics of the target object, determine the reference puncture needle entry path; at least based on the reference puncture needle entry path, determine the candidate puncture needle group that meets the preset conditions; perform particle distribution optimization and needle group optimization on the puncture needles in the candidate puncture needle group to determine the target puncture needle group. In some embodiments, the processing device 140 is a single server or a server group. The server group is centralized or distributed. In some embodiments, the processing device 140 is local or remote. For example, the processing device 140 can access information and / or data from the surgical robot device 110, the storage device 150, and / or the terminal 130 through the network 120. For another example, the processing device 140 can be directly connected to the surgical robot device 110, the terminal 130 and / or the storage device 150 to access information and / or data. For another example, the processing device 140 can be installed on the surgical robot device 110. In some embodiments, the processing device 140 can be implemented on a cloud platform. For example, the cloud platform includes a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, a cloud-to-cloud cloud, a multi-cloud, etc. or any combination thereof.

[0040] The storage device 150 can be used to store data, instructions and / or any other information. For example, the storage device 150 stores data obtained from the surgical robot device 110, the terminal 130 and / or the processing device 140. In some embodiments, the storage device 150 stores data and / or instructions used by the processing device 140 to execute or use to complete the exemplary methods described in this specification. In some embodiments, the storage device 150 includes a large-capacity memory, a removable memory, a volatile read-write memory, a read-only memory (ROM), etc. or any combination thereof. In some embodiments, the storage device 150 is implemented on a cloud platform.

[0041] In some embodiments, the storage device 150 can be connected to the network 120 to communicate with at least one other component (e.g., the processing device 140, the terminal 130) in the particle implantation planning system 100. At least one component in the particle implantation planning system 100 can access data stored in the storage device 150 through the network 120. In some embodiments, the storage device 150 is part of the processing device 140. In some embodiments, the processing device 140 and the storage device 150 can be integrated in the surgical robot device 110.

[0042] It should be noted that the above description is provided for illustrative purposes only and is not intended to limit the scope of this specification. For those of ordinary skill in the art, under the guidance of the contents of this specification, various changes and modifications can be made, and the features, structures, methods and other features of the exemplary embodiments described in this specification can be combined in various ways to obtain additional and / or alternative exemplary embodiments. For example, the storage device 150 is a data storage device 150 including a cloud computing platform, such as a public cloud, a private cloud, a community and a hybrid cloud. However, these changes and modifications will not deviate from the scope of this specification.

[0043] Figure 2 FIG. 1 is an exemplary flow chart of a particle implantation planning method according to some embodiments of the present specification. Figure 2 As shown, the process 200 includes the following steps. In some embodiments, the process 200 may be executed by a particle implantation planning system (eg, a processor included in the particle implantation planning system).

[0044] Step 210: Acquire medical image data of the target object.

[0045] The target object includes the whole or part of the biological object and / or non-biological object involved in the scanning process. For example, the target object is a living or non-living organic and / or inorganic substance, such as the head, ears, nose, mouth, neck, chest, abdomen, liver, gallbladder, pancreas, spleen, kidneys, spine, etc.

[0046] Medical imaging data refers to images obtained by scanning and imaging a target object through an imaging device. In some embodiments, the medical imaging data includes CT (Computed Tomography) images, MRI (Magnetic Resonance Imaging, MRI) images, and the like.

[0047] In some embodiments, the medical imaging data can be obtained by scanning the target object using an imaging device (e.g., a CT device, an MRI device, etc.) before the particle implantation surgery is performed, and then reconstructing the image based on the scanning data. It can also be pre-scanned and stored in a database, storage device, or imaging device, and the medical imaging data can be obtained by reading the data.

[0048] Step 220 , determining object features of the target object based on the medical image data.

[0049] The object characteristic refers to the property, feature or characteristic of the target object. In some embodiments, the object characteristic includes the target area of ​​the target object and the adjacent tissue of the target area.

[0050] In a particle implantation procedure, a target area refers to a part or tissue that needs to be treated with particle implantation. In some embodiments, the target area can be any location that needs to be treated, such as the brain, spine, lungs, or a specific area (such as a tumor). Before performing a particle implantation procedure, a doctor can determine the location and size of the target area through various imaging techniques to ensure the accuracy and effectiveness of the treatment, for example, by determining the target area from the medical imaging data.

[0051] Adjacent tissue refers to tissue adjacent to the target region, for example, tissue whose distance from the target region is less than a certain value (e.g., 1 mm, 2 mm, or 5 mm, etc.). In some embodiments, the adjacent tissue includes organs, such as the heart, lungs, stomach, kidneys, skin, and liver, etc., and an organ is usually composed of two or more tissues.

[0052] In some embodiments, the adjacent tissues vary depending on the target area. For example, for seed implantation of brain tumors, the adjacent tissues of the target area include brain tissue, optic nerve, auditory nerve, pituitary gland, carotid artery, etc. For another example, for seed implantation of prostate cancer, the adjacent tissues of the target area include rectum, bladder, urethra, etc.

[0053] In some embodiments, the processing device can segment the target area of ​​the target object and the adjacent tissues of the target area from the medical image data by image segmentation. For example, the image segmentation can segment the target area lesion, adjacent important organs, skin, bones, and some blood vessels from the medical image data.

[0054] In some embodiments, the image segmentation method includes manual segmentation, semi-automatic segmentation and automatic segmentation. The manual segmentation method includes using interactive software (such as ITK-SNAP, etc.) to outline the region; the semi-automatic segmentation method includes manually setting parameters and using traditional image processing algorithms to segment the target region. The specific algorithms include but are not limited to threshold method, region growing method and level set; the automatic segmentation method includes using trained machine learning or deep learning models to segment the target region in the image, such as a segmentation model based on U-Net. This embodiment does not limit the specific segmentation method, as long as it can achieve the corresponding function.

[0055] In this embodiment, obtaining the object features of the target object can be used to assist in the execution of subsequent particle implantation planning steps. For example, if certain important organs are punctured, it will cause serious complications (such as pneumothorax caused by puncturing the lung), and the puncture needle should be avoided from passing through these organs when planning the needle placement; for another example, in the particle implantation plan, a certain dose level needs to be achieved in the target area (such as a minimum limit, etc.), and certain dose limits (such as a maximum limit) must also be met in important organs. Segmenting the contours of the target area and adjacent tissues can help to count the dose distribution within it, and can also help to avoid passing through important tissues when planning the puncture needle.

[0056] Step 230: Determine the insertion path of the reference puncture needle based on the object features of the target object.

[0057] A puncture needle is a medical device that can be used to inject high-energy particles (such as metal particles containing radionuclides such as I125 and Pd103) into a target area in the patient's body. The puncture needle has different specifications, such as size (diameter), length, etc. Different specifications of puncture needles can reach different parts of the patient's body to adapt to different treatment scenarios.

[0058] The reference puncture needle refers to a puncture needle that can be used as a reference for puncture needle planning. In some embodiments, the reference puncture needle is the first puncture needle planned in the puncture needle group planning. In the puncture needle planning process, it is usually necessary to select the best entry point and puncture angle based on the location and size of the target area, taking into account multiple factors (such as the location of the surrounding tissue, the puncture needle entry angle and depth, etc.).

[0059] The reference puncture needle entry path refers to the entry point of the first puncture needle on the skin surface determined during the particle implantation planning process. Assuming that the reference puncture needle passes through the center of the target area, the reference puncture needle's puncture path can be expressed by its entry point on the skin surface and the center of the target area. For the sake of simplicity, the reference puncture needle's puncture path is described as the reference puncture needle's entry path.

[0060] In some embodiments, the reference puncture needle will pass through the center of the target area. Considering that when the reference puncture needle punctures the edge of the target area (e.g., a tumor), the mobility of the tumor may affect the precise puncture during the subsequent needle puncture process, the reference puncture needle is set to pass through the center of the target area (such as the centroid, geometric center, or a certain point in the specified target area, etc.) in this embodiment, and the puncture path of the reference puncture needle can be determined by connecting the needle entry point and the center of the target area.

[0061] In some embodiments, the processing device can screen the needle entry points on the surface of the target object based on the object characteristics of the target object through a preset first constraint condition to determine the needle entry path of the reference puncture needle. For detailed information on determining the needle entry path of the reference puncture needle, see Figure 3 Description.

[0062] In some embodiments, the insertion path of the reference puncture needle may also be directly specified by the user, which is not limited in this embodiment.

[0063] Step 240, determining a candidate puncture needle group that meets a preset condition based at least on the needle insertion path of the reference puncture needle.

[0064] The candidate puncture needle group refers to a set of puncture needles that may be selected as planning results from multiple screenings. In some embodiments, the candidate puncture needle group includes a reference puncture needle and one or more candidate puncture needles determined at least based on the reference puncture needle. The candidate puncture needle refers to a puncture needle determined after the reference puncture needle is determined. In some embodiments, the candidate puncture needle group may only include one or more candidate puncture needles determined at least based on the reference puncture needle. For example, the candidate puncture needle group for planning is further optimized in the future (see below). Figure 7 ), the reference puncture needle may be removed from the candidate puncture needle group.

[0065] In some embodiments, each candidate puncture needle (abbreviated as puncture needle or needle) in the candidate puncture needle group includes a needle entry point and a target point. The puncture path of the candidate puncture needle can be determined by connecting the needle entry point and the target point.

[0066] In some embodiments, the processing device can screen and gradually acquire candidate puncture needles based on at least the acquired reference puncture needle insertion path according to preset conditions. The preset conditions include a preset needle set acquisition strategy and a preset second constraint condition.

[0067] The preset needle group acquisition strategy refers to the pre-set assumptions for acquiring the puncture needle group. For example, in order to allow the puncture needle to gradually cover the target area, it is assumed that the next needle is within a certain range of the currently acquired needle group. The currently acquired needle group is a collection of puncture needles with determined puncture paths. For example, when acquiring the 6th needle, the currently acquired needle group is the 1st to 5th needles (a total of five puncture needles) that have been acquired. A certain range is an area determined at the needle tip of each needle in the acquired needle group, such as a circular area, and the area is used as the neighboring range of the needle, and the union of the neighboring ranges of multiple acquired needles is used as the range where the needle tip of the next needle to be acquired is located.

[0068] The preset second constraint condition refers to a screening condition when obtaining candidate puncture needles.

[0069] For detailed description of the preset second constraint and determination of candidate puncture needle groups, see Figure 4 Description.

[0070] Step 250 , performing particle distribution optimization and needle group optimization on the puncture needles in the candidate puncture needle group to determine the target puncture needle group.

[0071] The target puncture needle group refers to a set of puncture needles that are intended to be obtained for particle implantation planning. In some embodiments, the target puncture needle group includes the puncture path of the target puncture needle and the particle distribution in the target puncture needle. The particle distribution refers to the spatial position of the particle in the puncture needle.

[0072] Particle distribution optimization refers to adjusting the spatial position of particles in the puncture needle so that the particles in the puncture needle can better cover the target area.

[0073] Needle group optimization refers to further screening of the puncture needles in the candidate puncture needle group, for example, removing redundant puncture needles from the candidate puncture needle group.

[0074] In some embodiments, the processing device can optimize the particle distribution in the puncture needles based on the candidate puncture needle group by using a preset particle distribution optimization algorithm, and screen the puncture needles in the candidate puncture needle group based on the particle distribution optimization results to determine the target puncture needles. For example, in the particle distribution optimization results, there may be some candidate puncture needles with empty particles, and these part of the puncture needles can be removed from the candidate puncture needle group, and the remaining set of puncture needles is the target puncture needle group.

[0075] Detailed instructions for determining the target puncture needle group can be found in Figures 7 to 9 The description is not repeated here.

[0076] In some embodiments, after completing the particle implantation planning, the particle implantation planning system can output a complete plan report for user reference. The specific contents of the report include: basic information of the patient, such as name, age, occupation, gender, etc.; imaging data of the patient, including medical imaging near the target area, target area and tissue contours, etc.; instrument information, including puncture needle length, scale, particle type, particle activity, etc. If a template is used, template information can also be provided, such as whether a coplanar template or a non-coplanar template is used; the insertion point and target point of the puncture needle; the distribution of particles inside the needle channel; visual display of the needle channel and particle spatial distribution; isodose lines of the dose distribution generated by the particles; DVH (dose volume histogram, DVH) curve display of the dose distribution generated by the particles, the DVH curve can reflect the surrounding situation of the isodose lines on the target area and organs; quantitative evaluation results of dose distribution, including indicators such as conformality and uniformity.

[0077] In some embodiments of the present specification, the target area can be extracted from the medical imaging data of the target object, and a candidate puncture needle group (including the insertion path of the reference puncture needle and the puncture path of the subsequent needle) can be adaptively determined according to the morphology and position of the target area, and an optimization algorithm can be used to plan the target puncture needle group within the potential needle group to provide a reference for subsequent precise puncture.

[0078] In some embodiments of the present specification, by planning the first puncture needle separately and planning subsequent needles at least on the basis of the planning of the first puncture needle, it can be applied to more complex clinical scenarios, for example, particle implantation surgery for tumors of different locations, sizes, and shapes. Since the scheme screens the puncture needles based on the preset first constraint and preset conditions, it can automatically avoid obstacles according to the customized non-puncturable areas, and plan out potential needle groups on different surfaces according to the morphology and position of the target area. The scheme also uses an optimization algorithm to plan the distribution of needles and particles within the potential needle group, further improving the effect of puncture needle group planning, and the scheme is easy to implement. For example, the number of puncture needles and the number of particles do not need to be manually defined, and the scheme is not restricted by the model of the puncture needle.

[0079] The above description of each process is only for example and explanation, and is not intended to limit the specific steps of the particle implantation planning disclosed in this specification. For example, in some embodiments, the particle implantation planning can be carried out according to the following steps: based on the medical imaging data, determine the object characteristics of the target object; based on the object characteristics of the target object, determine the candidate puncture needle group that meets the preset conditions; perform particle distribution optimization and needle group optimization on the puncture needles in the candidate puncture needle group to determine the target puncture needle group. In this embodiment, based on the object characteristics of the target object, a candidate puncture needle group that meets the preset conditions is planned, and needle group optimization and particle distribution optimization are performed based on the candidate puncture needle group, which further improves the effect of puncture needle group planning, and the scheme is easy to implement. For another example, in some embodiments, the particle implantation planning can also be carried out according to the following steps: obtain medical imaging data of the target object; based on the medical imaging data, determine the object characteristics of the target object; based on the object characteristics of the target object, determine the needle entry path of the reference puncture needle; at least based on the needle entry path of the reference puncture needle, determine the candidate puncture needle group that meets the preset conditions. In this embodiment, by separating the planning of the first puncture needle and planning subsequent needles at least based on the planning of the first puncture needle, it can be applied to more complex clinical scenarios and meet the needs of needle group planning in complex scenarios. Figure 2 can be found in the description of , and will not be repeated here.

[0080] Figure 3 FIG. 1 is an exemplary flow chart of determining the needle insertion path of a reference puncture needle according to some embodiments of this specification. Figure 3 As shown, the process 300 includes the following operations. In some embodiments, the process 300 may be performed by a particle implantation planning system or processing device.

[0081] Step 310: discretize the target body surface area of ​​the target object into a plurality of body surface units.

[0082] The surface unit refers to the small blocks or units into which the target object's skin surface is divided. Each small block or unit is called a surface unit. By discretizing the target surface area into multiple surface units, the search space for determining the needle insertion point can be reduced, and the algorithm processing speed can be improved.

[0083] Since there are a huge number of voxels on the surface of the target object, traversing all of them requires a lot of time and computing resources, which will greatly reduce the efficiency of the algorithm. At the same time, using adjacent voxels as needle entry points may result in similar planning results, which may lead to some unnecessary repeated calculations. This problem can be alleviated by discretizing the surface.

[0084] The target body surface area refers to a potential needle insertion position area on the body surface of the target object. For example, the target body surface area is the skin surface adjacent to the target area (eg, when the target area is the heart, the target body surface area is the chest area of ​​the target object).

[0085] In some embodiments, the processing device can discretize the target body surface area into triangular facets through a variety of discretization algorithms, such as marching cube algorithm, etc. Each triangular facet can be used as a body surface unit, wherein the discretization interval can be set based on experience, for example, set to 5mm, 6mm, etc. In some embodiments, the discretized body surface unit can also be other shapes, such as quadrilaterals, hexagons, or irregular polygons, etc., which is not limited in this embodiment.

[0086] In some embodiments, a plurality of body surface units may be used to construct a plurality of candidate needle entry points. A candidate needle entry point refers to a body surface unit that may be a needle entry point of a puncture needle on the body surface of a target object.

[0087] Step 320: Screening multiple candidate needle entry points based on a preset first constraint condition.

[0088] In some embodiments, the preset first constraint condition includes a puncture needle length constraint, a puncture angle constraint, and a tissue collision detection constraint.

[0089] The puncture needle length constraint is used to constrain the puncture path length (insertion depth) of the puncture needle. For example, in order to ensure that the needle tip can reach the corresponding planned target point during the subsequent puncture process, the puncture depth and needle length of the needle need to be compared, and the insertion points where the puncture depth is greater than the needle length need to be removed.

[0090] The puncture angle constraint is used to constrain the entry angle of the puncture needle so that the puncture needle enters the skin surface as perpendicularly as possible. For example, constrain the angle between the puncture needle and the skin surface normal vector when the puncture needle enters the body. Constraining the puncture angle can reduce the deformation of the tissue during puncture and improve the puncture accuracy to ensure that the puncture needle accurately enters the target area.

[0091] See also Fig.10 , Fig.10 1010 represents the target area in the body of the target object, 1020 represents the surface skin of the target object, and the puncture depth is L. ST (the distance between S and T), S is the point of needle entry on the body surface, T is the target point, and θ represents the normal vector between the puncture needle and the body surface , O is a point inside the target area through which the reference puncture needle passes. For example, if this point is the reference puncture needle, O can be the center point of the target area (such as the center of mass or center of gravity, etc.).

[0092] Tissue collision detection constraints refer to the regulation of the spatial position of the puncture needle to avoid collision with sensitive tissues in adjacent tissues. Sensitive tissues refer to tissues that need special attention to avoid being squeezed or punctured by the puncture needle. Collision detection can ensure that the puncture needle will not squeeze or puncture sensitive tissues, such as nerves and blood vessels, during puncture. In particle implantation, multiple puncture needles will be implanted at the same time. The puncture needles themselves have a certain volume and will occupy a certain space. Collision detection constraints can avoid physical collisions between puncture needles.

[0093] In some embodiments, when performing collision detection, the organ boundary may be expanded to set a certain safety distance for the organ.

[0094] One or more needle entry points that meet the conditions can be screened out from multiple candidate needle entry points through the preset first constraint condition. For example, the processing device screens multiple candidate needle entry points by performing puncture needle length detection, puncture angle detection, and collision detection, and removes candidate needle entry points that do not meet the preset first constraint condition, thereby obtaining the screened candidate needle entry points. For example, if the puncture path passes through an important organ, the candidate needle entry point corresponding to the puncture needle should be eliminated.

[0095] Step 330, based on the preset first optimization goal and the screened candidate needle entry points, determine the needle entry path of the reference puncture needle.

[0096] The preset first optimization goal refers to the optimization goal set for the selected candidate needle insertion points according to the surgical requirements. In some embodiments, the preset first optimization goal includes at least one of minimizing the needle insertion depth, maximizing the distance from the tissue, and minimizing the puncture angle. For example, the preset first optimization goal can be minimizing the needle insertion depth, or a combination of minimizing the needle insertion depth and maximizing the distance from the tissue.

[0097] In some embodiments, the processing device can further screen the candidate needle insertion points after screening based on the preset first optimization goal, and use the puncture needle that meets the preset first optimization goal as the reference puncture needle. For example, the needle insertion path of the reference puncture needle is the one with the shortest needle insertion depth.

[0098] When the preset first optimization goal is a combination of multiple optimization goals, a weight can be assigned to each optimization goal, and the scores of the candidate needle entry points under each optimization goal can be calculated respectively. Then, the scores of each puncture needle under each optimization goal are weighted, and the needle entry point of the reference puncture needle is determined according to the final weighted score. For example, the candidate needle entry point with the highest weighted score is used as the needle entry point of the reference puncture needle.

[0099] In some embodiments, when determining the first puncture needle, it is assumed that the first puncture needle passes through a preset point in the target area. The preset point is a point in the target area determined according to a preset rule. For example, the preset point can be a point in the central area of ​​the target area (such as within 1-5 mm around the central area of ​​the target area), or it can be the center point of the target area (such as the center of mass or center of gravity, etc.), or it can be any point in the target area. Preferably, the puncture path of the reference puncture needle passes through the center point of the target area, and the puncture path of the reference puncture needle can be determined based on the needle entry point and the center point of the target area (which can be represented by the needle entry path of the reference puncture needle). The needle tip of the puncture needle steps along the direction from the needle entry point to the center of the target area, and the farthest point in the target area that can be reached is the needle tip position of the reference puncture needle.

[0100] For example, the planned reference puncture needle is as follows Fig.11 As shown, Fig.11 This is an exemplary schematic diagram of a reference puncture needle according to some embodiments of the present specification, wherein 1110 represents the reference puncture needle, 1120 represents the target area, and the needle tip of the reference puncture needle passes through a preset point in the target area.

[0101] Figure 4 is an exemplary flow chart for determining a candidate puncture needle set according to some embodiments of this specification. Figure 4 As shown, the process 400 includes the following operations. In some embodiments, the process 400 may be performed by a particle implantation planning system or processing device.

[0102] Step 410: discretize the target body surface area of ​​the target object into a plurality of body surface units.

[0103] In some embodiments, the plurality of discretized body surface units are used to construct a plurality of candidate needle entry points. Figure 3 The discretization method in step 310 is the same and will not be repeated here.

[0104] In some embodiments, the candidate needle entry point at this location may be the same as or different from the candidate needle entry point obtained discretely when planning the first needle.

[0105] Step 420 , based on the uncovered area of ​​the target area, multiple candidate needle entry points are screened to obtain multiple screened candidate needle entry points.

[0106] For the coverage of the target area, it is assumed that the puncture needle is regarded as a cylinder, and the cylindrical area represents the area that the puncture needle can cover (corresponding to the area that the particles in the needle can radiate). The uncovered area of ​​the target area refers to the area in the target area that is not covered by the determined puncture needle. For example, when the puncture needle is regarded as a cylinder, the uncovered area of ​​the target area refers to the area outside the cylinder of the puncture needle in the target area (the cylindrical areas of the needles may intersect).

[0107] In some embodiments, the processing device can pre-set the coverage range of each puncture needle based on the radiation range of the particles. For example, a circle is drawn with the puncture needle as the center and a certain distance is set. The entire puncture needle will form a cylinder, and the area corresponding to the cylinder in the target area is considered to be the area covered by the puncture needle.

[0108] In some embodiments, the uncovered area of ​​the target area is determined based on the determined puncture needle set. The position of the determined puncture needle set in the target area is determined, and when the coverage area of ​​each puncture needle is determined, the other areas in the target area except the covered area are the uncovered areas.

[0109] In some embodiments, the processing device can screen multiple candidate needle entry points based on the uncovered area of ​​the target area and the preset first constraint condition. The specific method of screening can be found in Figure 3 The description of step 320 of the present invention is the same in the specific screening method. The difference is that in step 320, multiple candidate needle entry points in the entire target area are screened based on the first preset condition, while here, multiple candidate needle entry points in the uncovered area of ​​the target area are screened, and the purposes of the two are the same, which is to reduce the search space and improve the processing efficiency of the algorithm.

[0110] Step 430, discretize the surface of the target area to determine a plurality of candidate target points.

[0111] The target point refers to the position on the surface of the target area that the puncture needle aims at during the puncture process. In some embodiments, the target point can also be understood as the position that the needle tip of the puncture needle needs to reach. The candidate target point refers to the surface block obtained after discretization of the surface of the target area. A surface block can be used as a candidate target point.

[0112] In some embodiments, the discretization process for the surface of the target area can be performed in the same manner as Figure 3 The method of discretizing the body surface area of ​​the target object in step 310 may be the same, so it will not be repeated here.

[0113] Step 440, at least based on the needle insertion path of the reference puncture needle, the preset conditions and multiple candidate target points, determine a candidate puncture needle group that meets the preset conditions through multiple rounds of iterations.

[0114] Multiple iterations refer to achieving the ultimate goal through a series of gradually improved cyclic processes. In some embodiments, multiple iterations can be used to determine the next puncture needle based on the puncture needles that have determined the puncture path. For example, the acquisition of the third puncture needle (the second subsequent needle) should be based on the first puncture needle (reference puncture needle) and the second puncture needle (candidate puncture needle), that is, the third puncture needle is acquired based on the information of the first puncture needle and the second puncture needle.

[0115] In some embodiments, the operation of each round of iteration in the multiple rounds of iterations includes the following steps 441-443.

[0116] Step 441, screening the multiple candidate targets based on preset conditions.

[0117] The preset conditions include a preset second constraint condition and a preset needle group acquisition strategy.

[0118] The preset second constraint conditions include a puncture needle length constraint, a puncture angle constraint, a tissue collision detection constraint, a collision detection constraint of an acquired puncture needle, and an angle constraint with a reference puncture needle.

[0119] The puncture needle length constraint is used to constrain the puncture path length (insertion depth) of the puncture needle. For example, in order to ensure that the needle tip can reach the corresponding planned target point during the subsequent puncture process, the puncture depth and needle length of the needle need to be compared, and the insertion points where the puncture depth is greater than the needle length need to be removed.

[0120] The puncture angle constraint is used to constrain the entry angle of the puncture needle so that the puncture needle enters the skin surface as perpendicularly as possible. For example, constrain the angle between the puncture needle and the skin surface normal vector when the puncture needle enters the body. Constraining the puncture angle can reduce the deformation of the tissue during puncture and improve the puncture accuracy to ensure that the puncture needle accurately enters the target area.

[0121] Tissue collision detection constraints refer to the spatial position of the puncture needle to avoid collision with adjacent tissues. Collision detection can ensure that the puncture needle will not squeeze or pierce adjacent tissues or sensitive tissues, such as nerves and blood vessels, during puncture. In particle implantation, multiple puncture needles are implanted at the same time. The puncture needle itself has a certain volume and occupies a certain space. Tissue collision detection constraints can avoid physical collisions between puncture needles.

[0122] The collision detection constraint of the acquired puncture needles is to limit the distance between the candidate puncture needles and the acquired puncture needles to avoid collision between the puncture needles in the planned plan.

[0123] The angle constraint with the reference puncture needle refers to limiting the angle between the candidate puncture needle and the reference puncture needle to avoid the distribution of the puncture needles in the planned plan being too dispersed. For example, when planning a subsequent needle, the angle between the subsequent needle and the reference puncture needle (such as the reference puncture needle) is limited to be less than a certain threshold (such as an angle less than 30°).

[0124] The preset needle group acquisition strategy includes that the candidate puncture needle is within the preset range of the acquired puncture needle group. In the embodiment of this specification, the scheme for acquiring the puncture needle group is to gradually expand the puncture needles outward from the first needle. Therefore, when planning the next needle, it is necessary to be within a certain range around the currently acquired needle group. For example, when screening targets, targets that are more than a certain distance away from the acquired needle group can be eliminated. This operation can narrow the search space and improve the efficiency of the algorithm. For example, see Fig.12 , Fig.12 It is an exemplary schematic diagram of the preset range shown in some embodiments of this specification. Among them, 1210 represents the first puncture needle that has been acquired, 1220 represents the second puncture needle that has been acquired, 1211 represents the area that the first puncture needle can cover, 1221 represents the area that the second puncture needle can cover, 1230 is the target range of the acquired puncture needle group, and the candidate target is selected from the surrounding of this part of the area (for example, the distance from the area is less than a certain value). In some embodiments, the preset range can be manually set or automatically calculated based on machine learning, neural network or big data algorithm, which is not limited in this embodiment.

[0125] Using preset conditions to screen multiple candidate targets can filter out some targets, reduce the search space in subsequent planning, and improve the processing efficiency of the algorithm.

[0126] Step 442, based on the screened multiple candidate needle entry points and the screened multiple candidate target points, the target area coverage rate of the puncture needle is calculated to determine multiple first candidate puncture needles and corresponding target area coverage rates.

[0127] Under the premise of unknown particle distribution in the needle (currently in the planning stage of the puncture needle group, the particle position has not been planned yet), the coverage rate of the puncture needle is calculated, assuming that a particle source is placed at each position in the puncture needle. Under this assumption, the puncture needle can be regarded as a cylinder, and the area inside the cylinder represents the area that the puncture needle can cover. Fig.13 As shown, Fig.13 It is an exemplary schematic diagram of target area coverage according to some embodiments of this specification. Among them, 1310 represents the needle entry point on the body surface, 1320 represents the puncture needle, 1330 is the cylindrical coverage range of the puncture needle, 1340 is the target area illustrated in the form of a point cloud, 1350 is the needle tip position of the puncture needle 1320, the gray range at 1320 represents the skin surface of the target object, and the gray square at 1350 represents the boundary of the target area (the actual target area boundary is mostly a curved surface, and here it is a plane quadrilateral for convenience). The target area coverage rate of the puncture needle can be expressed as the ratio of the target area volume in the cylinder of the puncture needle to the total volume of the target area. In some embodiments, the volume is represented by the number of point clouds within the cylindrical range and the number of point clouds in the entire target area.

[0128] In some embodiments, the processing device can calculate the puncture needle with the largest target coverage rate based on the multiple selected candidate needle entry points and the multiple selected candidate target points. The target coverage rate can be calculated based on the puncture path of the puncture needle, wherein a candidate needle entry point and a candidate target point can form a puncture path. Therefore, for one of the multiple selected candidate needle entry points (using S i Assume that the puncture needle passes through S i , the needle passes through S i Finally, when the needle tip reaches different screened candidate targets, multiple puncture paths will be formed, and each puncture path has a corresponding target area coverage.

[0129] In some embodiments, the processing device determines the target area coverage by using a preset target area coverage calculation method, for example, by calculating the ratio of the number of point clouds of the puncture needle in the target area to the total number of point clouds in the target area.

[0130] After calculating the target area coverage of the puncture needle for each selected candidate needle entry point, multiple first candidate puncture needles and their corresponding target area coverage can be determined. The first candidate puncture needle refers to the puncture needle corresponding to the puncture path with the largest target area coverage among the puncture paths composed of the selected candidate needle entry points and their corresponding target points. For example, the puncture needle corresponding to the puncture path with the largest target area coverage among the puncture paths composed of each candidate needle entry point and multiple candidate target points is determined as the first candidate puncture needle.

[0131] In some embodiments, dose information and target area dose coverage can also be introduced when calculating the target area coverage. For example, for each puncture needle, its particle radiation dose gradually decreases in the direction away from the puncture needle. For each target point in the target area, its corresponding dose is the radiation dose of multiple puncture needles at the target point. The dose of the target point can be obtained by superimposing the radiation doses of multiple puncture needles. The dose is compared with a preset threshold. If it exceeds the threshold, it is considered to be covered. After calculating all target points within the radiation range of the puncture needle, the coverage of the puncture needle can be determined.

[0132] For more information on target coverage calculation, see Figure 6 The description is not repeated here.

[0133] Step 443: Add the first candidate puncture needle with the largest target area coverage rate to the current candidate puncture needle group.

[0134] In the above step 442, the target area coverage rate of each first candidate puncture needle has been calculated. After sorting or comparing the target area coverage rates of multiple first candidate puncture needles, the first candidate puncture needle with the largest target area coverage rate can be determined.

[0135] The current candidate puncture needle group refers to the set of first candidate puncture needles with the largest target area coverage calculated in each round of iteration. Since the determination of subsequent needles is carried out through multiple rounds of iterations, each round of iteration will calculate the first candidate puncture needle with the largest target area coverage in the uncovered area of ​​the current target area. Therefore, after each round of iteration, the first candidate puncture needle with the largest target area coverage corresponding to the current round of iteration can be added to the current candidate puncture needle group.

[0136] The puncture needles in the current candidate puncture needle group will participate in subsequent planning, for example, particle distribution optimization and needle group optimization, so as to obtain the target puncture needle group.

[0137] In some embodiments, a goal of puncture needle planning can be set, for example, to achieve complete coverage of the target area with as few puncture needles as possible. Under this optimization goal, puncture needles can be added one by one in a greedy manner (such as gradually acquiring the next needle based on the determined puncture needle as described in the embodiments of this specification), so that each added puncture needle can cover as much of the remaining target area as possible.

[0138] Illustratively, the method of adding puncture needles one by one in a greedy manner is shown in the following embodiment.

[0139] Before iterating to obtain the candidate puncture needle set, the parameters involved in the iteration can be initialized, for example, the candidate puncture needle set N = {} ({} represents an empty set), the target area coverage rate CR = 0, and the uncovered target area point set is P NC , the point corresponding to the entire target area is P T , initialize P Nc =P T .

[0140] After obtaining the puncture needles, the parameters are gradually updated. For example, after obtaining the first needle n1, N={n1} is updated, and the target area coverage CR is updated. For example, if the target area coverage of the first needle is 5%, CR=5% is updated, and the target area coverage of the first needle is 5%. NC Remove the points covered by n1; after obtaining the second needle n2, update N = {n1, n2}, the target area coverage of the second needle is 5%, then update CR = 10%, and further from the point set P NC Remove the points covered by n2.

[0141] The iterative process is as follows Fig.14 As shown, Fig.14 is an exemplary schematic diagram of updating target area coverage according to some embodiments of the present specification.

[0142] First, obtain the first needle N = {n1}; the first needle is also the reference puncture needle, and its acquisition process is shown in Figure 3 Description of

[0143] Update target coverage CR;

[0144] Determine whether the target area is fully covered;

[0145] If the target area is not fully covered, do the following: Preprocessing; the preprocessing includes the operations described in steps 410 to 430; Get next stitch n i ; Obtaining the next needle includes the operations of step 441 and step 443; Add the next needle obtained to the needle group N = N + {n i};

[0146] If the target area is completely covered, the candidate puncture needle group is output.

[0147] In some embodiments, the specific operation of determining whether the target area is completely covered is as follows: Figure 5 shown.

[0148] Figure 5 is an exemplary schematic diagram of an iterative judgment method according to some embodiments of this specification. Figure 5 As shown, the process 500 includes the following operations. In some embodiments, the process 500 may be performed by a particle implantation planning system or processing device.

[0149] Step 510: remove the point corresponding to the puncture path with the maximum target area coverage from the target area point set.

[0150] The target area point set refers to a set of point clouds obtained by discretizing the target area. In some embodiments, the target area point set includes target points obtained by discretizing the surface of the target area and points discretized inside the target area.

[0151] As described in the above embodiment, the puncture path can be represented by the needle entry point on the body surface and the target point on the target area surface. After determining the puncture path with the maximum target area coverage, the corresponding points inside the target area and the target point on the target area surface of the puncture path can be determined, and the points corresponding to the puncture path can be removed from the target area point set. NC Remove the points covered by n2, where n2 corresponds to the puncture needle corresponding to the puncture path with the largest target area coverage determined in the first round of iteration.

[0152] Step 520, determining whether the coverage of the target area reaches a preset value.

[0153] The preset value is a preset threshold value of the target area coverage rate in the optimization objective, for example, a preset value of 99%, 98% or 97%.

[0154] In some embodiments, the processing device determines whether the preset value is reached by comparing the updated target coverage with the preset value. For example, in the above example, the target coverage of the second needle is 5%, and the updated target coverage is CR=10%, which does not reach the preset value of 99% by comparison.

[0155] After the points corresponding to the puncture paths with the largest target area coverage are removed from the target area point set, the remaining points in the target area are the target area uncovered areas. The method for determining whether the target area coverage reaches the preset value may be to determine whether the number of points removed from the target area point set reaches a certain ratio of the total number of points in the target area point set, for example, whether it reaches the preset value, or to determine whether the remaining target area uncovered area is less than a threshold, for example, whether it is less than 1%, 2% or 3%, etc.

[0156] In some embodiments, after determination, if the preset value is not reached, step 540 is executed; if the preset value is reached, step 530 is executed.

[0157] Step 530: output the current candidate puncture needle group.

[0158] For example, the current candidate puncture needle group N is output, which may include multiple candidate puncture needles.

[0159] In some embodiments, the output candidate puncture needle group can be as follows: Fig.15 As shown, Fig.15 1510 is an exemplary schematic diagram of a candidate puncture needle group according to some embodiments of the present specification. 1510 is an exemplary multiple candidate puncture needles, and 1520 is an enlarged view of the area shown in 1510. The numbers in 1520, #1, #2, #3, etc., are the marked puncture needle numbers, for example, #1 represents the first puncture needle determined.

[0160] Step 540: Perform the next round of iteration based on the puncture needles in the current candidate puncture needle group.

[0161] For example, based on the puncture needles in the current candidate puncture needle group, the uncovered area of ​​the target area is determined, and the preset second constraint condition detection is performed based on the puncture needles in the current candidate puncture needle group. The iterative process can be referred to Figure 4 Description.

[0162] Figure 6 is an exemplary flow chart of calculating target coverage according to some embodiments of the present specification. In some embodiments, process 600 may be executed by a particle implantation planning system or processing device.

[0163] In some embodiments, for each screened candidate needle entry point, the processing device may calculate its target area coverage by executing the following steps 610 - 630 .

[0164] Step 610, determining a plurality of potential target sites from the plurality of screened candidate target sites.

[0165] Potential target points refer to candidate target points that may be combined with the screened candidate needle entry points to form a puncture path.

[0166] In some embodiments, screening is performed using preset conditions to determine multiple potential target sites from multiple screened candidate targets.

[0167] Step 620, calculate the target area coverage based on multiple potential target points, and determine the potential target point with the largest target area coverage.

[0168] In some embodiments, S i The candidate needle entry point is calculated, and the potential target point T with the largest target area coverage can be calculated from multiple potential target points. Exemplarily, the calculation method is shown in formula (1) and formula (2).

[0169] Wherein, T in formula (1) represents the potential target point with the largest target area coverage, S i represents the i-th candidate needle entry point, T j represents the jth potential target, S i T j represents the puncture path determined by two points, Indicates adding puncture path S i T j The target coverage after . S in formula (2) i represents the i-th candidate needle entry point, T j represents the jth potential target, S i T j represents the puncture path determined by two points, Indicates that the current candidate puncture needle group (the puncture needles that have been added + the current puncture needle S i T j ) is the target area point set covered by .

[0170] Step 630, based on the potential target point with the largest target coverage, determine the first candidate puncture needle of the screened candidate needle entry point and the corresponding target coverage.

[0171] For the candidate needle entry point S i , the potential target point with the largest target coverage has been calculated to be T, and the corresponding first candidate puncture needle can be expressed as S i T, and its target area coverage can be expressed as (CR represents target coverage, subscript S i T represents puncture needle).

[0172] For ease of understanding, the following example illustrates an embodiment of determining a candidate puncture needle group in a greedy manner with the optimization goal of achieving complete coverage of the target area with as few puncture needles as possible. The complete steps are shown in the following example.

[0173] S1: Initialization, set the candidate puncture needle group to {}, target area coverage CR = 0, and the uncovered target area point set P NC =PT (PT in initialization is the set of points in the entire target area, including the target points on the target surface and the points inside the target area);

[0174] S2: Add the first needle (reference puncture needle) to the candidate puncture needle group and update the needle group to {n1}; update the coverage of the first needle; NC Remove the points covered by n1;

[0175] S3: Assume that the newly added needle (e.g., the second needle) passes through P NC The center of the target area is the center of the remaining part after removing the covered target area (the center needs to be in P NC The center can be the center of a geometric shape or other forms of center (such as the center of mass).

[0176] S4: Traverse the selected candidate needle entry points, for each candidate needle entry point S i :Put the puncture needle through S i , determine the potential target points to narrow the search space of the target points; then calculate the target point T with the largest target area coverage, and the calculation method can be the same as the above formula (1) and will not be repeated here.

[0177] S5: Calculate the needle with the maximum target area coverage. Exemplarily, the calculation method is as shown in formula (3).

[0178] Among them, ST represents the puncture needle with the largest target coverage, S i represents the i-th candidate needle entry point, Indicates the candidate needle entry point S i The target area coverage of the puncture path corresponding to the target point T.

[0179] S6: Add needle N=N+{ST} to the needle group;

[0180] S7: Update the uncovered target point set P NC , from P NC Remove the points covered by ST;

[0181] S8: Determine whether the target area is completely covered: If the coverage ratio CR ST >99%, it is considered to be fully covered and the candidate puncture needle group N can be output, otherwise it returns to S3 for the next round of iteration to obtain the next subsequent needle.

[0182] After the candidate puncture needle group is obtained, particle distribution optimization and needle group optimization may be performed on the puncture needles in the candidate puncture needle group to obtain the target puncture needle group.

[0183] Figure 7 is an exemplary flow chart for determining a target puncture needle set according to some embodiments of this specification. Figure 7 As shown, the process 700 includes the following steps. In some embodiments, the process 700 can be performed by a particle implantation planning system or processing equipment.

[0184] Step 710, based on the preset equally spaced scales on the puncture needle, determine the initial particle distribution of each candidate puncture needle in the candidate puncture needle group.

[0185] The preset equally spaced scale refers to marks with equal spacing that are pre-set on the puncture needle. For example, if the puncture needle is 5 cm long, the preset equally spaced scale may be a scale with equal spacing of 10 mm.

[0186] The preset equally spaced scales are used to indicate the potential particle positions of the particles in the puncture needle. For example, in order to facilitate the subsequent optimization of the distribution of particles in the puncture needle, a binary variable can be set for each scale to store whether the position corresponding to the scale is finally placed. For example, a value of 1 indicates that the particle is placed, and a value of 0 indicates that the particle is not placed. For example, the schematic diagram is as follows: Fig.16 As shown, Fig.16 This is an exemplary schematic diagram of the preset equally spaced scales in the puncture needle shown in some embodiments of this specification. Among them, the horizontal 10-->0 are the set equally spaced scales, the gray squares represent the particles placed at the scale positions in the puncture needle, and the vertical 1-13 are the numbers of the puncture needles. The binary variables are shown below the arrows in the figure, 1-K respectively represent the number of binary variables to be optimized, and (M, N) represents the Nth potential particle of the Mth puncture needle.

[0187] Step 720 , optimizing the particle distribution based on the initial particle distribution on the candidate puncture needle.

[0188] The initial particle distribution refers to randomly selecting a certain number of positions from all potential particle positions of the puncture needle to place particles.

[0189] In some embodiments, the processing device can perform particle distribution optimization by using a preset particle distribution optimization algorithm, which includes a simulated annealing algorithm, a genetic algorithm, or a binary integer linear programming algorithm.

[0190] In some embodiments, the processing device can optimize the particle distribution of the initial particle distribution on the candidate puncture needle by performing multiple rounds of iterations.

[0191] In some embodiments, the processing device can also perform the multiple rounds of iterations in combination with a preset particle distribution algorithm to optimize the particle distribution on the candidate puncture needle. For example, the steps of multiple rounds of iterations are embedded in the process of the preset particle distribution algorithm.

[0192] For a detailed description of the specific distribution optimization process, see Figure 8 The description is not repeated here.

[0193] Step 730, optimizing the needle set based on the result of the particle distribution optimization, and determining the target puncture needle set according to the needle set optimization result.

[0194] The result of particle distribution optimization refers to the position distribution after the particle positions in the puncture needle are adjusted.

[0195] Needle group optimization refers to optimizing the puncture needles in the candidate puncture needle group. For example, according to the result of particle distribution optimization, the candidate puncture needles with empty particles (the number of particles is 0) are removed. Specifically, the processing device can restore the binary variables after particle optimization to the particle distribution in the puncture needles, and determine whether there are puncture needles with a particle number of 0 based on the restored puncture needles.

[0196] The set of candidate puncture needles remaining after needle group optimization is the target puncture needle group.

[0197] Figure 8 is an exemplary flow chart of a particle distribution optimization method according to some embodiments of this specification. Figure 8 As shown, the process 800 includes the following operations. In some embodiments, the process 800 may be performed by a particle implantation planning system or processing device.

[0198] Step 810 , optimizing the particle distribution of the initial particle distribution on the candidate puncture needle by executing multiple rounds of iterations.

[0199] Each round of iteration may include operations as shown in steps 811 to 815.

[0200] Step 811, obtaining a first objective function value of an objective function for particle distribution optimization.

[0201] The objective function is a function set to reflect whether the particle distribution optimization has achieved the optimization goal. For example, the optimization goals include V100 exceeding 90% and V150 being as small as possible. V100 and V150 are indicators used to evaluate dose distribution in particle implantation planning, which respectively represent the ratio of the volume in the target area exceeding 100% of the prescription dose and the volume exceeding 150% of the prescription dose to the total volume of the target area. In some embodiments, when using its optimization algorithm, for example, using a genetic algorithm or a binary integer linear programming, the optimization goal reflected by its objective function can be the number of particles used (the fewer the better), the number of puncture needles (the fewer the better), or the conformality of the dose field (the higher the better).

[0202] Exemplarily, the objective function is shown in the following formula (4). minf t =w1×ReLU(90%-V100)+w2×V150 (4)

[0203] in, w1 and w2 represent the weights of two function terms (expressed in the form of V100 and V150), f t is the objective function value, minf t Indicates that the optimization goal is to minimize the objective function value. The weight value can be set according to actual needs. For example, the weights of the two function items can be 0.5 and 0.5, or 0.7 and 0.3, respectively.

[0204] The first objective function value can be understood as the initial function value of the objective function in the current iteration. That is, the objective function value before optimizing the particle distribution in the puncture needle in this iteration. Among them, the first objective function value corresponding to the first iteration is calculated based on the initial particle distribution of the candidate puncture needle, and the first objective function value corresponding to the subsequent iteration is the first objective function value of the previous iteration. It can be understood that the initial objective function value in the subsequent iteration is the objective function value after optimizing the particle distribution in the puncture needle in the previous iteration.

[0205] For the first objective function value of the first iteration, the processing device can calculate the dose volume of the particles in the needle in the target area based on the initial distribution of the particles in the candidate puncture needle group, and substitute the dose volume into the above formula (4) to calculate the first objective function value. For the first objective function value of the subsequent iteration, the processing device can directly obtain the second objective function value of the previous iteration and use it as the first objective function value of the current iteration. For the description of the second objective function value, please refer to the description in step 814 below.

[0206] Step 812, adjusting the current particle distribution of the candidate puncture needle to determine the random particle distribution of the candidate puncture needle.

[0207] In some embodiments, the adjustment method is to randomly select a certain number (e.g., 1-3) of all potential particle positions in the current particle distribution of the candidate puncture needle to change the state, such as 0→1 or 1→0 (representing a change from a non-placed particle to a placed particle and from a placed particle to a non-placed particle, respectively). The particle distribution after the state change is the random particle distribution of the candidate puncture needle.

[0208] Step 813: Based on the random particle distribution of the candidate puncture needle, a second objective function value of the objective function of particle distribution optimization is obtained.

[0209] The second objective function value refers to the objective function value calculated based on the adjusted particle distribution after the particle distribution of the puncture needle is adjusted in the current round of iteration.

[0210] In some embodiments, the processing device may calculate the dose volume of the puncture needle based on the random particle distribution, and substitute the dose volume into the above formula (4) to calculate the second objective function value.

[0211] Step 814 , determining whether to update the current particle distribution of the candidate puncture needle based on the first objective function value and the second objective function value.

[0212] In some embodiments, the processing device determines whether to update the current particle distribution of the candidate puncture needle by comparing the first objective function value and the second objective function value.

[0213] For more details on how to make judgments, see Fig. 9 If yes, then execute step 815.

[0214] Step 815: Use the random particle distribution of the candidate puncture needle to replace the current particle distribution of the candidate puncture needle.

[0215] In some embodiments, the current particle distribution of the candidate puncture needle varies according to the round of the current iteration. In the first round of iteration, the current particle distribution of the candidate puncture needle is the initialized example distribution, and in subsequent rounds of iteration, the current particle distribution of the candidate puncture needle is the particle distribution updated using the random particle distribution in the previous round of iteration.

[0216] Fig. 9 FIG. 1 is an exemplary flow chart of updating the punctured particle distribution according to some embodiments of the present specification. Fig. 9 As shown, the process 900 includes the following operations. In some embodiments, the process 900 may be performed by a particle implantation planning system or processing device.

[0217] Step 910, determine the magnitude relationship between the second objective function value and the first objective function value.

[0218] In some embodiments, the processing device may directly compare the second objective function value with the first objective function value to determine the magnitude relationship between the second objective function value and the first objective function value.

[0219] Step 920: If the second objective function value is less than the first objective function value, the current particle distribution of the candidate puncture needle is updated.

[0220] It can be understood that if the second objective function value is less than the first objective function value, it means that the currently adjusted random particle distribution is closer to the optimization target, and the current particle distribution of the candidate puncture needle is selected to be updated.

[0221] Step 930: If the second objective function value is greater than or equal to the first objective function value, determine whether to update the current particle distribution of the candidate puncture needle based on a preset probability.

[0222] In some embodiments, the preset probability may be determined based on the following method.

[0223] Among them, p is the preset probability value, T is the current temperature in the simulated annealing algorithm used, f is the second objective function value, and f t In this embodiment, by setting a preset probability to accept a suboptimal solution (a case where the second objective function value is less than the first objective function value), it helps to avoid the optimization algorithm from falling into a local optimum.

[0224] For ease of understanding, a complete embodiment of particle distribution optimization using a simulated annealing algorithm is shown in the following embodiment. Specifically, it may include the following steps S1-S7.

[0225] S1: Initialize simulated annealing parameters: set initial temperature T0, end temperature T f , cooling rate R∈(0,1);

[0226] S2: Setting the optimization target; for example, the optimization target is that V100 must exceed 90% and V150 is as small as possible; and setting the corresponding objective function (for example, the objective function shown in formula (4)).

[0227] S3: Initialize the state distribution of particles: According to the empirical formula of the number of particles N = 4.674 × V 0.562 / A (V represents the target volume, A represents the particle activity), among all the potential particle positions, randomly select N positions to place particles, calculate the current objective function value f0 (the first objective function value), and set the current temperature T = T0;

[0228] S4: Update time t=t+1, initialize f t =f t-1 ;

[0229] S5: Randomly update state distribution: randomly select 1 to 3 from all potential particle positions to change state (0→1 or 1→0), and calculate the current objective function value f (second objective function value);

[0230] S6: Determine whether to update the current particle distribution: If f <f t , then update the state distribution of the particle and let f t =f; If f ≥ f t , then update according to the preset probability, the probability is

[0231] Return to S4 and iterate for a certain number of rounds. Performing multiple iterations here (to avoid confusion, it can be called the first iteration) can randomly update the particle distribution multiple times, so as to get as close as possible to the optimization target, and can also make the optimization process using the preset optimization algorithm more stable.

[0232] S7: If T>T f , then the temperature drop T=T×R, and return to S4; otherwise, the particle distribution optimization ends. Among them, T>T in the first round of iteration f In the process, T=T0, and in the process of cooling down, T=T0×R. T in the subsequent iterations is the cooling result of the previous iteration. For example, T in the second iteration is T0×R, and T in the third iteration is T×(T0×R).

[0233] Optionally, in some embodiments, after the particle distribution optimization is completed using the simulated annealing algorithm, the processing device can perform step S8 based on the optimization result of the particle distribution.

[0234] S8: Based on the optimization result of the particle distribution, the needle group is optimized, and the target puncture needle group is determined according to the optimization result of the needle group. For example, the processing device can determine whether there is a puncture needle with a particle number of 0 according to the optimization result of the particle distribution. If so, the puncture needle with a particle number of 0 is removed from the needle group, and the remaining puncture needles are the target puncture needle group.

[0235] In some embodiments, after the planning of the puncture needle set is completed, the particle implantation planning system can output the spatial position and orientation of the puncture needles to be used. According to the spatial position and orientation of the puncture needles, a non-coplanar template is modeled and personalized 3D printing is performed to assist in the positioning of the puncture needles during particle implantation. For example, the printed non-coplanar template is as follows: Fig.17 As shown, Fig.1717 is an exemplary schematic diagram of a non-coplanar template according to some embodiments of this specification. The hole in 1710 is the planned puncture needle hole column; the hole in 1720 is an auxiliary hole. Specifically, due to various reasons (such as limited puncture accuracy during surgery, patient breathing movement, etc.), if the puncture needle is implanted with the planned puncture needle hole column during surgery and fails to cover the target area well, the auxiliary holes can be used to fill the needle.

[0236] It should be noted that the above description of each process is only for example and explanation, and does not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to each process under the guidance of this specification. However, these modifications and changes are still within the scope of this specification. For example, a storage step is added between each process step, etc.

[0237] In addition, the above-mentioned workflows are all described for a single target area. For multiple target areas, the above-mentioned processes can be executed multiple times. For a single target area that is blocked by too many organs and cannot be planned normally, the target area can be split into multiple parts and the above-mentioned processes can be executed multiple times.

[0238] For example, in some embodiments, the processing device can split the target area according to the following process and execute the above process multiple times. The processing device can obtain medical image data of the target object; determine the object characteristics of the target object based on the medical image data; split the target area of ​​the target object to obtain multiple sub-areas of the target area; for each sub-area: determine the needle entry path of the reference puncture needle based on the object characteristics of the target object; determine a candidate puncture needle group that meets the preset conditions based on at least the needle entry path of the reference puncture needle; perform particle distribution optimization and needle group optimization on the puncture needles in the candidate puncture needle group to determine the target puncture needle group.

[0239] Since the target area is divided into multiple sub-areas and needle groups are planned for each sub-area, when multiple sub-areas are merged, the target puncture needle groups corresponding to the multiple sub-areas can be merged. After the merger, the coverage of the puncture needles of two adjacent sub-areas may overlap. In this case, the processing device can perform particle distribution optimization on the merged target area again based on the particle distribution optimization method described in the embodiment of this specification.

[0240] It should be noted that when optimizing the combined target puncture needle group, the optimization object mainly considers optimizing the particle distribution (the particle distribution and the needle group can also be optimized at the same time) because even if the coverage area of ​​the puncture needle overlaps, the overdose can be avoided by optimizing the particle distribution. In some embodiments, even if there is a collision between the puncture needles of the target puncture needle group corresponding to different sub-areas, only the particle distribution optimization can be performed, because after the sub-area division, the needle collision problem can be avoided by inserting the needles in batches in a grouping manner. In the process of implanting particles, the puncture needle is first inserted to the deepest point, and then the particles are implanted. After the needle is withdrawn for a certain distance, the particles are implanted again. Therefore, when the particles in a needle are implanted, the needle is basically pulled out of the patient's body. The situation in which the needle collision occurs is that all the needles will be inserted to the deepest point they need to reach at the beginning of the implantation. If the puncture needles are originally grouped, all the needles of the first group can be inserted after the particles are implanted, and then all the needles of the second group can be inserted. It is only necessary to ensure that the puncture needles in the group will not collide.

[0241] It should be understood that the system and its modules shown in the embodiments of this specification can be implemented in various ways. For example, in some embodiments, the system and its modules can be implemented by hardware, software, or a combination of software and hardware. Among them, the hardware part can be implemented using dedicated logic; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or a dedicated design hardware. Those skilled in the art will understand that the above-mentioned methods and systems can be implemented using computer executable instructions and / or included in a processor control code, such as a carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. Such code is provided on the carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The system and its modules of this specification can not only be implemented by hardware circuits such as ultra-large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., but can also be implemented by software such as executed by various types of processors, and can also be implemented by a combination of the above-mentioned hardware circuits and software (e.g., firmware).

[0242] It should be noted that the above description of the particle implantation planning system and its modules is only for the convenience of description, 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. In some embodiments, different modules can be different modules in a system, or one module can implement the functions of two or more of the above-mentioned modules. For example, each module can share a storage module, or each module can have its own storage module. Such variations are within the scope of protection of this specification.

[0243] 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.

[0244] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0245] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0246] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0247] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the determination of such numerical values ​​is as accurate as possible within the feasible range.

[0248] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this specification are hereby incorporated by reference in their entirety. Except for application history documents that are inconsistent with or conflicting with the contents of this specification, documents that limit the broadest scope of the claims of this specification (currently or later attached to this specification) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the materials attached to this specification are inconsistent or conflicting with the contents described in this specification, the descriptions, definitions, and / or use of terms in this specification shall prevail.

[0249] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A particle implantation planning system, the system comprising a processor, the processor being configured to perform the following operations: Acquire medical imaging data of a target object; Determining object features of the target object based on the medical image data; the object features include a target area; Determining a needle insertion path of a reference puncture needle based on the object features of the target object; Determining a candidate puncture needle group that meets preset conditions based at least on the needle insertion path of the reference puncture needle; Particle distribution optimization and needle group optimization are performed on the puncture needles in the candidate puncture needle group to determine a target puncture needle group; the target puncture needle group includes the puncture paths of the target puncture needles and the particle distribution in the target puncture needles.

2. The system according to claim 1, wherein determining the insertion path of the reference puncture needle based on the object features of the target object comprises: discretize the target body surface area of ​​the target object into a plurality of body surface units; The multiple body surface units are used to construct multiple candidate needle entry points; Based on a preset first constraint condition, screening the plurality of candidate needle entry points; Based on the preset first optimization goal and the screened candidate needle entry points, the needle entry path of the reference puncture needle is determined; the puncture path of the reference puncture needle passes through the preset point of the target area.

3. The system according to claim 2, wherein the preset first constraint condition comprises a puncture needle length constraint, a puncture angle constraint and a tissue collision detection constraint.

4. According to the system of claim 2, the preset first optimization goal includes one or more of minimizing the needle insertion depth, maximizing the distance between the puncture needle and the tissue, and minimizing the puncture angle. 5 . The system according to claim 1 , wherein the preset conditions include a preset second constraint condition and a preset needle group acquisition strategy.

6. The system according to claim 5, wherein the preset second constraint condition comprises a puncture needle length constraint, a puncture angle constraint, a tissue collision detection constraint, a collision detection constraint of an acquired puncture needle, and an angle constraint with a reference puncture needle; The preset needle set acquisition strategy includes that the candidate puncture needle is located within a preset range of the acquired puncture needle set.

7. The system according to claim 5, wherein the step of determining a candidate puncture needle group that meets a preset condition based at least on the needle insertion path of the reference puncture needle comprises: discretize the target body surface area of ​​the target object into a plurality of body surface units; The multiple body surface units are used to construct multiple candidate needle entry points; Based on the uncovered area of ​​the target area, the multiple candidate needle entry points are screened to obtain the screened multiple candidate needle entry points; wherein the uncovered area of ​​the target area is determined based on the determined puncture needle group; Discretizing the surface of the target area to determine a plurality of candidate target points; At least based on the needle insertion path of the reference puncture needle, the preset condition and the multiple candidate target points, determine the candidate puncture needle group that meets the preset condition through multiple rounds of iterations; Each of the multiple rounds of iterations includes: Based on the preset conditions, screening the multiple candidate targets; Based on the screened multiple candidate needle entry points and the screened multiple candidate target points, the target area coverage rate of the puncture needle is calculated to determine multiple first candidate puncture needles and corresponding target area coverage rates; The first candidate puncture needle with the largest target area coverage is added to the current candidate puncture needle group.

8. The system according to claim 7, further comprising: The point corresponding to the puncture path with the largest target area coverage is removed from the target area point set; as well as Determining whether the coverage of the target area reaches a preset value; If yes, output the current candidate puncture needle group; If not, the next round of iteration is performed based on the puncture needles in the current candidate puncture needle group.

9. The system according to claim 7, wherein the target area coverage rate of the puncture needle is calculated based on the multiple candidate needle entry points and the multiple candidate target points after screening, and the multiple first candidate puncture needles and the corresponding target area coverage rates are determined, including: For each candidate needle entry point after screening, Screening and determining a plurality of potential target sites from the plurality of screened candidate targets; Calculating the target area coverage based on the multiple potential target points, and determining the potential target point with the largest target area coverage; Based on the potential target point with the largest target area coverage, the first candidate puncture needle of the screened candidate needle entry point and the corresponding target area coverage are determined.

10. The system according to claim 1, wherein the step of performing particle distribution optimization and needle group optimization on the puncture needles in the candidate puncture needle group to determine the target puncture needle group comprises: Determining the initial particle distribution of each candidate puncture needle in the candidate puncture needle group based on preset equally spaced scales on the puncture needle; performing particle distribution optimization based on the initial particle distribution on the candidate puncture needle; The needle group optimization is performed based on the result of the particle distribution optimization, and the target puncture needle group is determined according to the needle group optimization result.

11. The system according to claim 10, wherein the particle distribution optimization based on the initial particle distribution on the candidate puncture needle comprises: Optimizing the particle distribution of the initial particle distribution on the candidate puncture needle by performing multiple rounds of iterations; Each round of iteration includes: Obtaining a first objective function value of an objective function for particle distribution optimization; wherein the first objective function value corresponding to the first round of iteration is calculated based on the initial particle distribution of the candidate puncture needle, and the first objective function value corresponding to the subsequent round of iteration is the second objective function value of the previous round of iteration; Adjusting the current particle distribution of the candidate puncture needle to determine the random particle distribution of the candidate puncture needle; Based on the random particle distribution of the candidate puncture needle, obtaining a second objective function value of the objective function of the particle distribution optimization; Determining whether to update the current particle distribution of the candidate puncture needle based on the first objective function value and the second objective function value; If so, the current particle distribution of the candidate puncture needle is replaced by the random particle distribution of the candidate puncture needle.

12. The system according to claim 11, wherein the determining whether to update the current particle distribution of the candidate puncture needle based on the first objective function value and the second objective function value comprises: Determine the magnitude relationship between the second objective function value and the first objective function value; If the second objective function value is less than the first objective function value, updating the current particle distribution of the candidate puncture needle; If the second objective function value is greater than or equal to the first objective function value, it is determined whether to update the current particle distribution of the candidate puncture needle based on a preset probability.

13. A particle implantation planning method, the method comprising: Acquire medical imaging data of a target object; Based on the medical image data, determine the object characteristics of the target object; the object characteristics include a target area Determining a needle insertion path of a reference puncture needle based on the object features of the target object; Determining a candidate puncture needle group that meets preset conditions based at least on the needle insertion path of the reference puncture needle; Particle distribution optimization and needle group optimization are performed on the puncture needles in the candidate puncture needle group to determine a target puncture needle group; the target puncture needle group includes the puncture paths of the target puncture needles and the particle distribution in the target puncture needles.

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

Images