Path planning method, path planning device and electronic equipment

Abstract

The invention provides a path planning method, a path planning device and electronic equipment, and relates to the technical field of image processing, and the method comprises the steps: obtaining a lesion image of a target object, and determining a target region in the lesion image; traversing each target area, determining a plurality of initial paths from the path planning start area to the path planning end point area, and determining a path evaluation value corresponding to each initial path; and based on the path evaluation value, screening a target path from the path planning start area to the path planning end point area from the plurality of initial paths. According to the process, a target path from a path planning starting area to a path planning end point area is screened based on a path evaluation value, path planning is carried out in an intelligent calculation mode, objectivity and standardization of path planning can be guaranteed in the planning process, the overall quality of path planning can be improved, and the path planning efficiency is improved. Therefore, scientific auxiliary information can be provided for the operation, and the subsequent treatment effect is improved.

Description

Technical Field

[0001] The present application relates to the technical field of image processing, and particularly to a path planning method, a planning device, and an electronic device. Background Art

[0002] In the field of neurosurgery, minimally invasive neurosurgery for deep localization utilizes advanced imaging techniques, navigation systems, and minimally invasive surgical instruments and techniques to precisely operate on deep brain or spinal cord structures. Using this type of surgery can minimize damage to surrounding normal tissues, ensure precise positioning of the surgical area, thereby improving the safety and effectiveness of the surgery, and can also significantly improve the postoperative recovery of patients and enhance the treatment effect of patients.

[0003] Existing surgical path planning requires skilled operation of surgical instruments and highly relies on the experience of surgeons. However, surgical path planning based on the experience of surgeons has a certain degree of subjectivity, and the experience of different surgeons may lead to differences in surgical paths, easily resulting in errors in the planned surgical paths, being unable to provide standardized auxiliary information for the surgery, and thus easily affecting the subsequent treatment effect. Summary of the Invention

[0004] The present application provides a path planning method, a path planning device, and an electronic device, which use reinforcement learning to determine the path evaluation values of multiple initial paths from the path planning start area to the path planning end area, and determine the target path from the path planning start area to the path planning end area based on the path evaluation values, considering the applicability of the path planning of the target path, ensuring the objectivity and standardization of the path planning, and thus improving the accuracy and safety of the path planning.

[0005] In a first aspect, a path planning method is provided, and the method includes: Obtain a lesion image of a target object, and determine a target area in the lesion image, where the target area includes multiple areas passed between the path planning start area and the path planning end area; Traverse each target area, determine multiple initial paths from the path planning start area to the path planning end area, and determine the path evaluation value corresponding to each initial path; Based on the path evaluation value, screen the target path from the path planning start area to the path planning end area among the multiple initial paths.

[0006] In a second aspect, a path planning device is provided, including: An area determination module, configured to obtain a lesion image of a target object, and determine a target area in the lesion image, where the target area includes multiple areas passed between the path planning start area and the path planning end area; An initial path determination module for traversing each target area to determine multiple initial paths from the path planning start area to the path planning end area, and determining a path evaluation value corresponding to each initial path; A target path determination module for screening a target path from the path planning start area to the path planning end area among multiple initial paths based on the path evaluation value.

[0007] In a third aspect, an electronic device is provided, including: a processor and a memory. The memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the method in the first aspect or its various implementation manners.

[0008] In a fourth aspect, a computer-readable storage medium is provided for storing a computer program, and the computer program causes a computer to execute the method in the first aspect or its various implementation manners.

[0009] Through the technical solution provided by this application, a lesion image of a target object can be obtained, and a target area in the lesion image can be determined, where the target area includes multiple areas passed between the path planning start area and the path planning end area; traverse each target area to determine multiple initial paths from the path planning start area to the path planning end area, and determine a path evaluation value corresponding to each initial path; based on the path evaluation value, screen a target path from the path planning start area to the path planning end area among multiple initial paths. This process uses reinforcement learning to determine the path evaluation values of multiple initial paths from the path planning start area to the path planning end area, and screens the target path from the path planning start area to the path planning end area based on the path evaluation value. The path is planned in an intelligent calculation manner, and the objectivity and standardization of path planning can be guaranteed during the planning process, which can improve the overall quality of path planning, and thus can provide scientific auxiliary information for surgery and improve the subsequent treatment effect.

[0010] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit this application. Other features and advantages of this application will be described in detail in the subsequent specific implementation part. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of this application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of this application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0012] Figure 1 A scenario diagram provided for the embodiments of this application; Figure 2 A flowchart of a path planning method provided for an embodiment of the present application; Figure 3 A flowchart of a method for determining an initial path evaluation value provided for an embodiment of the present application; Figure 4 A structural diagram of a path planning device provided for an embodiment of the present application; Figure 5 A structural diagram of an electronic device provided for an embodiment of the present application. Detailed implementation manners

[0013] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0014] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present application described here can be implemented in an order other than those illustrated or described here. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0015] In the field of neurosurgery, minimally invasive neurosurgery for deep localization utilizes advanced imaging techniques, navigation systems, and minimally invasive surgical instruments and techniques to precisely operate on deep brain or spinal cord structures. Using this type of surgery can minimize damage to surrounding normal tissues, ensure precise positioning of the surgical area, thereby improving the safety and effectiveness of the surgery, and can also significantly improve the postoperative recovery of patients and enhance the treatment effect of patients. The selection of the surgical path is based on the quantitative assessment of the lesion and the identification of the surgical area. For the deep localization requirement, the path distance within the lesion is extended as much as possible, important functional areas and important organs are avoided, and a basic decision set of the position, angle, depth, etc. of the deep localization surgery is provided.

[0016] Existing surgical path planning requires skilled operation of surgical instruments and highly relies on the experience of surgeons. However, surgical path planning based on the experience of surgeons is somewhat subjective, and the experience of different doctors may lead to differences in surgical paths, affecting the standardization and repeatability of surgeries. It cannot guarantee the objectivity and standardization of surgical path planning, easily resulting in errors in the planned surgical paths, unable to provide standardized auxiliary information for surgeries, and thus easily affecting subsequent treatment effects.

[0017] To solve the above technical problems, the inventive concept of this application is as follows: Based on the lesion image of the target object, determine all the regions between the path planning start region and the path planning end region included in the lesion image. Traverse multiple regions passed through between the path planning start region and the path planning end region, determine all the initial paths from the path planning start region to the path planning end region, and perform path evaluation on each initial path to obtain the path evaluation value corresponding to each initial path. Determine the target path from the path planning start region to the path planning end region according to the path evaluation value. This process determines the initial path passing through each target region through reinforcement learning, calculates the path evaluation value of the initial path, and obtains the target path from the path planning start region to the path planning end region. During the planning process, it can ensure the objectivity and standardization of path planning, improve the overall quality of path planning, and thus can provide scientific auxiliary information for surgeries and improve subsequent treatment effects.

[0018] It should be noted that the path planning method proposed in this application can be used for clinical auxiliary diagnosis in the field of neurosurgery, and can also be used in pathology and imaging research in the field of neurosurgery. It can also be combined with the image data of other lesions and used in the research of other fields such as medical imaging and clinical auxiliary diagnosis of other diseases, not limited to the research in the field of neurosurgery.

[0019] It should be understood that the technical solution of this application can be applied to the following scenarios, but is not limited to: In some implementable ways, Figure 1 This is an application scenario diagram provided for the embodiment of this application. As Figure 1 shown, this application scenario may include an electronic device 110 and a network device 120. The electronic device 110 can establish a connection with the network device 120 through a wired network or a wireless network.

[0020] Exemplarily, the electronic device 110 may be a desktop computer, a laptop computer, a tablet computer, etc., but not limited thereto. The network device 120 may be a terminal device or a server, but not limited thereto. In an embodiment of the present application, the electronic device 110 may send a request message to the network device 120, and the request message may be used to request to obtain a target path from the path planning start area to the path planning end area. Further, the electronic device 110 may receive a response message sent by the network device 120, and the response message includes the target path from the path planning start area to the path planning end area.

[0021] In addition, Figure 1 Exemplarily, an electronic device 110 and a network device 120 are given. Actually, other numbers of electronic devices and network devices may be included, and the present application does not limit this.

[0022] In some other implementable manners, the technical solution of the present application may also be executed by the above-mentioned electronic device 110, and the present application does not limit this.

[0023] After introducing the application scenarios of the embodiments of the present application, the technical solution of the present application will be elaborated in detail below: Figure 2 A flowchart of a path planning method provided for an embodiment of the present application. This method may be executed by an electronic device 110 as shown in Figure 1 but not limited thereto. As shown in Figure 2 the method may include the following steps: Step 210: Obtain a lesion image of a target object and determine a target area in the lesion image.

[0024] In a specific application field, the target object may be a patient, and the lesion image is a three-dimensional image including a lesion area. The target area in the lesion image includes at least a path planning start area and a path planning end area. The path planning start area is the initial incision area when a surgeon or a surgical instrument performs a surgery or the catheter insertion entrance area in an interventional surgery. The path planning end area may be the lesion area. The target area may also include multiple areas between the path planning start area and the path planning end area. The target area may be determined by a path planning device that executes the path planning method, or may be determined by a surgeon who performs the surgery. The present application does not limit this.

[0025] Step 220: Traverse each target area, determine multiple initial paths from the path planning start area to the path planning end area, and determine a path evaluation value corresponding to each initial path.

[0026] In a specific application scenario, the initial path is the surgical operation route within the lesion image from the path planning start area to the path planning end area, passing through each target area. The path evaluation value corresponding to each initial path can be determined according to the influencing parameters corresponding to each initial path, and the path evaluation value can be used to evaluate the planning situation of the initial path. The path evaluation value is a comprehensive evaluation index and is a relative concept. There may be differences in the evaluation values between different patients and different surgical paths. Therefore, during the evaluation process, multiple factors need to be comprehensively considered and reasonable decisions should be made according to the actual situation. It involves considerations in multiple aspects, such as but not limited to: 1. Path safety: It is used to evaluate whether the surgical path avoids important blood vessels, nerves, and other sensitive structures to reduce surgical risks and complications.

[0027] 2. Path length: It is used to evaluate the straight-line distance of the surgical path or the length of the actual surgical operation path. A shorter path can reduce the surgical time and trauma and improve the surgical efficiency.

[0028] 3. Path accessibility: It is used to evaluate whether the surgical instruments can reach the lesion area smoothly and meet the requirements of surgical operations. Considering the size, angle, and flexibility of the surgical instruments, the path that can best approach the lesion should be selected.

[0029] 4. Path perpendicularity: It is used to evaluate the perpendicular degree of the surgical path to the lesion plane. A perpendicular path can provide a better surgical field of view and operating space, which is beneficial to the accuracy and safety of the surgery.

[0030] 5. Damage to surrounding tissues by the path: It is used to evaluate the degree of damage to the surrounding normal tissues by the surgical path. The path with the least damage to the surrounding tissues should be selected, which helps to reduce the postoperative recovery time and complications.

[0031] 6. Feasibility of the path: It is used to evaluate the feasibility of the surgical path in actual operation, including the accessibility of surgical instruments, the difficulty of surgical operations, etc. Here, factors such as the doctor's technical level and the equipment conditions in the operating room need to be comprehensively considered.

[0032] 7. Postoperative recovery of the path: It is used to evaluate the impact of the surgical path on the patient's postoperative recovery. The path that is beneficial to postoperative recovery should be selected, such as reducing pain and promoting wound healing.

[0033] According to an embodiment of the present disclosure, the step of traversing each target area to determine multiple initial paths from the path planning start area to the path planning end area may include: obtaining voxel information within each target area; generating multiple initial paths from the path planning start area to the path planning end area based on the voxel information of each target area.

[0034] According to an embodiment of the present disclosure, the voxel information includes the coordinate positions of each voxel within each target area. The step of generating multiple initial paths from the path planning start area to the path planning end area based on the voxel information of each target area may include: repeatedly executing the following steps until a preset number of iterations is reached to obtain all initial paths from the path planning start area to the path planning end area; selecting a random voxel within each target area using a greedy strategy; generating an initial path from the path planning start area to the path planning end area based on the coordinate position corresponding to each random voxel.

[0035] In a specific application scenario, all initial paths from the path planning start area to the path planning end area may be determined based on reinforcement learning. Specifically, first, obtain the voxel information within each target area, where the voxel information includes the position coordinates of each voxel within each target area. Then, the following steps may be iteratively executed: randomly select a random voxel within each area using a greedy strategy, determine a random sub-path between the adjacent target areas based on the position coordinates of the random voxels in two adjacent target areas, form a random path based on each random sub-path for each random voxel, and determine the random path as an initial path from the path planning start area to the path planning end area until all initial paths from the path planning start area to the path planning end area are generated.

[0036] According to an embodiment of the present disclosure, the step of determining the path evaluation value corresponding to each initial path may include: determining the influence parameter corresponding to each initial path, where the influence parameter is data that affects path planning; determining the initial path evaluation value corresponding to the initial path based on the influence parameter; updating the initial path evaluation value based on a reinforcement learning algorithm according to the initial path evaluation value, the immediate reward for selecting the initial path, a preset discount factor, and a preset learning rate to obtain the path evaluation value.

[0037] In a specific application scenario, each time a new initial path is generated, it is necessary to calculate the path evaluation value of the initial path to evaluate the applicability of the path planning of the initial path. The selection of the surgical path is limited by the experience of the surgical implementation and other influencing parameters. Therefore, the influencing parameters corresponding to the initial path can be determined, and the path evaluation value of the initial path can be calculated using the influencing parameters. The influencing parameters can include positively correlated parameters and negatively correlated parameters. The positively correlated parameters can include the angle of the path, the trajectory of the path within the lesion, but are not limited thereto. The negatively correlated parameters can include the degree of damage to the functional area, the degree of damage to the organ, etc., but are not limited thereto. Here, the positively correlated parameters and the negatively correlated parameters can be determined by the doctor performing the surgical operation or by the path planning instrument performing the surgical operation, and the present application does not make any restrictions.

[0038] Further, the influencing parameters can be normalized using formula (1) to reduce the influence brought by different features in terms of numerical values. Formula (1) is as follows: (1) Wherein, x i is the eigenvalue of the influencing parameter, max(x) is the maximum value of the feature, min(x) is the minimum value of the feature.

[0039] Figure 3 FIG. 19 is a schematic flowchart of a method for determining the evaluation value of an initial path provided by an embodiment of the present application. The method includes: Step 310: Determine the first influence value of the positively correlated parameter according to each positively correlated parameter and the first weight value corresponding to the positively correlated parameter.

[0040] According to the embodiment of the present application, step 310 may include: determining the first weight value corresponding to each positively correlated parameter according to the positive correlation between each positively correlated parameter and the path planning; calculating the first weighted average value of the positively correlated parameters based on the positively correlated parameters and the first weight value; and obtaining the first influence value by maximizing the first numerical value, where the first numerical value is the sum of the products of the first weighted average value and each positively correlated parameter.

[0041] In a specific application scenario, the first influence value is determined according to formula (2). Formula (2) is as follows: (2) Wherein, optp 1 is the first influence value, c i is the first weighted average value, x i is the positively correlated parameter, n is the number of positively correlated parameters.

[0042] Step 320: Determine the second influence value of each negative correlation parameter according to the negative correlation parameter and the corresponding second weight value.

[0043] According to an embodiment of the present application, step 320 may include: determining the second weight value corresponding to each negative correlation parameter according to the negative correlation between each negative correlation parameter and path planning; calculating the second weighted average value of the negative correlation parameter based on the negative correlation parameter and the second weight value; obtaining the second influence value by minimizing the second numerical value, where the second numerical value is the sum of the product of the second weighted average value and each negative correlation parameter.

[0044] In a specific application scenario, the second influence value is determined according to formula (3), and formula (3) is as follows: (3) Wherein, optp 2 is the second influence value, p i is the second weighted average value, x ’ i is the negative correlation parameter, n is the number of negative correlation parameters.

[0045] Step 330: Determine the initial path evaluation value according to the first influence value and the second influence value.

[0046] Here, the difference between the first influence value and the second influence value is determined as the initial path evaluation value.

[0047] Further, after determining the initial path evaluation value of the initial path, the Q-learning reinforcement learning algorithm can be used to update the initial path evaluation value to obtain the path evaluation value. Specifically, formula (4) can be used to update the initial path evaluation value according to the initial path evaluation value, the immediate reward for selecting the initial path, the preset discount factor, and the preset learning rate. Formula (4) is as follows: (4) Wherein, Q ’ (s,a) is the path evaluation value for selecting the initial path based on the random voxel, s is the random voxel, a is the initial path, Q(s,a) is the initial path evaluation value for the random voxel to select the initial path, α represents the preset learning rate, which is a parameter between 0 and 1 and is used to determine the speed at which the updated path evaluation value covers the initial path evaluation value, r is the immediate reward for the random voxel to select the initial path, γ represents the preset discount factor, which is a parameter between 0 and 1 and is used to control the influence degree of future rewards on the current decision. Represents the maximum value among multiple path evaluation values obtained after selecting other initial paths for voxels other than the currently selected random voxel.

[0048] Returns a reference Figure 2 , step 230, based on the path evaluation value, filters the target path from the path planning start area to the path planning end area among multiple initial paths.

[0049] According to an embodiment of the present disclosure, step 230 may include: filtering the initial paths that meet the preset conditions as the target paths among multiple initial paths, where the preset condition may be that the path evaluation value of the initial path is greater than or equal to the preset evaluation value.

[0050] In a specific application scenario, the path evaluation value of each initial path can be compared with the preset evaluation, and the initial paths with path evaluation values greater than or equal to the preset evaluation value are selected as the target paths, and there may be multiple target paths. Here, the preset evaluation value can be set according to actual needs, such as 85, 90, etc., but not limited thereto. Further, the initial path corresponding to the maximum path evaluation value can be used as the optimal target path. In actual applications, the doctor performing the surgical operation can operate according to the target path and can also fine-tune the target path according to experience before operating.

[0051] In summary, according to the path planning method provided by the present application, a lesion image of a target object is obtained, and a target area in the lesion image is determined, where the target area includes multiple areas passed between the path planning start area and the path planning end area; each target area is traversed to determine multiple initial paths from the path planning start area to the path planning end area, and the path evaluation value corresponding to each initial path is determined; based on the path evaluation value, the target path from the path planning start area to the path planning end area is filtered among multiple initial paths. This process uses reinforcement learning to determine the path evaluation values of multiple initial paths from the path planning start area to the path planning end area, filters the target path from the path planning start area to the path planning end area based on the path evaluation value, and performs path planning through intelligent calculation. During the planning process, the objectivity and standardization of path planning can be ensured, the overall quality of path planning can be improved, and thus scientific auxiliary information can be provided for the operation, improving the subsequent treatment effect.

[0052] Based on the above Figure 2 , Figure 3 detailed description of the provided path planning method, Figure 4 FIG. is a schematic structural diagram of a path planning device provided by an embodiment of the present application. As Figure 4 shown, the device 400 includes: The region determination module 410 is configured to obtain a lesion image of a target object and determine a target region in the lesion image, where the target region includes multiple regions passed between the path planning start region and the path planning end region.

[0053] The initial path determination module 420 is configured to traverse each target region, determine multiple initial paths from the path planning start region to the path planning end region, and determine a path evaluation value corresponding to each initial path.

[0054] The target path determination module 430 is configured to screen a target path from the path planning start region to the path planning end region from multiple initial paths based on the path evaluation value.

[0055] In some embodiments of the present application, the initial path determination module 420 is further configured to obtain voxel information in each target region; and generate multiple initial paths from the path planning start region to the path planning end region based on the voxel information of each target region.

[0056] In some embodiments of the present application, the voxel information includes the coordinate positions of each voxel in each target region. The initial path determination module 420 is further configured to repeatedly execute the following steps until a preset number of iterations is reached to obtain all initial paths from the path planning start region to the path planning end region; select a random voxel in each target region using a greedy strategy; and generate an initial path from the path planning start region to the path planning end region based on the coordinate position corresponding to each random voxel.

[0057] In some embodiments of the present application, the initial path determination module 420 is further configured to determine an influence parameter corresponding to each initial path, where the influence parameter is data that affects path planning; determine an initial path evaluation value corresponding to the initial path based on the influence parameter; and update the initial path evaluation value based on a reinforcement learning algorithm according to the initial path evaluation value, an immediate reward for selecting the initial path, a preset discount factor, and a preset learning rate to obtain a path evaluation value.

[0058] In some embodiments of the present application, the influence parameter includes a positive correlation parameter and a negative correlation parameter. The initial path determination module 420 is further configured to determine a first influence value of the positive correlation parameter according to each positive correlation parameter and a first weight corresponding to the positive correlation parameter; determine a second influence value of the negative correlation parameter according to each negative correlation parameter and a second weight corresponding to the negative correlation parameter; and determine the initial path evaluation value according to the first influence value and the second influence value.

[0059] In some embodiments of the present application, the initial path determination module 420 is further configured to determine a first weight value corresponding to each positive correlation parameter according to the positive correlation between each positive correlation parameter and path planning; calculate a first weighted average value of the positive correlation parameters based on the positive correlation parameters and the first weight values; obtain a first influence value by maximizing a first numerical value, where the first numerical value is the sum of the products of the first weighted average value and each positive correlation parameter; determine a second weight value corresponding to each negative correlation parameter according to the negative correlation between each negative correlation parameter and path planning; calculate a second weighted average value of the negative correlation parameters based on the negative correlation parameters and the second weight values; obtain a second influence value by minimizing a second numerical value, where the second numerical value is the sum of the products of the second weighted average value and each negative correlation parameter.

[0060] In some embodiments of the present application, the target path determination module 430 is configured to screen out an initial path that meets a preset condition as the target path from multiple initial paths, where the preset condition is that the path evaluation value of the initial path is greater than or equal to a preset evaluation value.

[0061] Regarding the device in the above embodiments, the specific manners in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated herein.

[0062] According to the embodiments of the present application, intelligent calculation can be used to assist doctors in making evaluations, improve the scientific nature of the selection of surgical plan paths, provide support for doctors in designing surgical paths, and improve the treatment effect. It can also combine human expert knowledge and reinforcement learning technology to feedback and learn surgical path planning methods in practice, thereby improving the safety and accuracy of surgical path planning.

[0063] In the foregoing, the path planning device of the embodiments of the present application has been described from the perspective of functional modules in conjunction with the drawings. It should be understood that the functional modules can be implemented in the form of hardware, can also be implemented by instructions in software form, or can be implemented by a combination of hardware and software modules. Specifically, each step of the path planning method embodiment in the embodiments of the present application can be completed by the integrated logic circuit in the hardware in the processor and / or instructions in software form. The steps of the path planning method applied in conjunction with the embodiments of the present application can be directly embodied as being executed by a hardware decoding processor, or can be executed by a combination of the hardware and software modules in the decoding processor. Optionally, the software module can be located in mature storage media in the art such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage media is located in the memory, and the processor reads the information in the memory and combines its hardware to complete the steps in the path planning method embodiment described above.

[0064] Figure 5 It is a schematic block diagram of an electronic device 500 according to an embodiment provided by the present application.

[0065] As Figure 5 shown, the electronic device 500 may include: A memory 510 and a processor 520. The memory 510 is used to store a computer program and transmit the program code to the processor 520. In other words, the processor 520 can call and run the computer program from the memory 510 to implement the method in the embodiments of the present application.

[0066] For example, the processor 520 can be used to execute the above method embodiments according to the instructions in the computer program.

[0067] In some embodiments of the present application, the processor 520 may include, but is not limited to: A general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and so on.

[0068] In some embodiments of the present application, the memory 510 includes, but is not limited to: Volatile memory and / or non-volatile memory. Among them, the non-volatile memory can be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable PROM (EEPROM), or a flash memory. The volatile memory can be a Random Access Memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double DataRate SDRAM (DDR SDRAM), Enhanced SDRAM (ESDRAM), Synch link DRAM (SLDRAM), and Direct Rambus RAM (DR RAM).

[0069] In some embodiments of the present application, the computer program may be divided into one or more modules, which are stored in the memory 510 and executed by the processor 520 to complete the method provided by the present application. The one or more modules may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program in the controller.

[0070] As Figure 5 shown, the electronic device 500 may further include: A transceiver 530, which may be connected to the processor 520 or the memory 510.

[0071] Among them, the processor 520 can control the transceiver 530 to communicate with other devices. Specifically, it can send data to other devices or receive data sent by other devices. The transceiver 530 may include a transmitter and a receiver. The transceiver 530 may further include an antenna, and the number of antennas may be one or more.

[0072] It should be understood that the various components in the electronic device are connected through a bus system. Among them, the bus system includes, in addition to a data bus, a power bus, a control bus, and a status signal bus.

[0073] The present application also provides a computer storage medium, on which a computer program is stored. When the computer program is executed by a computer, the computer can execute the methods in the above method embodiments. Or rather, an embodiment provided by the present application also provides a computer program product containing instructions. When the instructions are executed by a computer, the computer executes the methods in the above method embodiments.

[0074] When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions according to this embodiment of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire (such as coaxial cable, optical fiber, Digital Subscriber Line (DSL)) or wirelessly (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that the computer can access or a data storage device such as a server or data center that includes one or more integrated available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a Digital Video Disc (DVD)), or a semiconductor medium (such as a Solid State Disk (SSD)), etc.

[0075] Those of ordinary skill in the art can realize that the modules and algorithm steps of each example described in combination with the embodiments claimed in this application can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0076] In several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division. In actual implementation, there may be other division methods. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections between each other can be through some interfaces. The indirect couplings or communication connections of the devices or modules can be in electrical, mechanical, or other forms.

[0077] The modules described as separate components may or may not be physically separated. The components shown as modules may or may not be physical modules, that is, they can be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. For example, in each embodiment of the present application, the functional modules can be integrated in a processing module, or each module can exist physically alone, or two or more modules can be integrated in one module.

[0078] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A path planning method, characterized in that, Including: Obtain a lesion image of a target object, and determine a target area in the lesion image, where the target area includes a plurality of areas passed between a path planning start area and a path planning end area; Traverse each of the target areas, determine a plurality of initial paths from the path planning start area to the path planning end area, and determine a path evaluation value corresponding to each of the initial paths; Based on the path evaluation value, screen a target path from the path planning start area to the path planning end area among the plurality of initial paths.

2. The method according to claim 1, wherein The traversing each of the target areas and determining a plurality of initial paths from the path planning start area to the path planning end area includes: Obtain voxel information within each of the target areas; Based on the voxel information of each of the target areas, generate a plurality of initial paths from the path planning start area to the path planning end area.

3. The method according to claim 2, wherein The voxel information includes the coordinate positions of each voxel within each of the target areas; The generating a plurality of initial paths from the path planning start area to the path planning end area based on the voxel information of each of the target areas includes: Repeatedly execute the following steps until a preset number of iterations is reached to obtain all the initial paths from the path planning start area to the path planning end area; Use a greedy strategy to select a random voxel within each of the target areas; Based on the coordinate position corresponding to each of the random voxels, generate the initial path from the path planning start area to the path planning end area.

4. The method according to claim 1, characterized in that The determining a path evaluation value corresponding to each of the initial paths includes: Determine an influence parameter corresponding to each of the initial paths, where the influence parameter is data that affects path planning; Based on the influence parameter, determine an initial path evaluation value corresponding to the initial path; Based on a reinforcement learning algorithm, update the initial path evaluation value according to the initial path evaluation value, the immediate reward for selecting the initial path, a preset discount factor, and a preset learning rate to obtain the path evaluation value.

5. The method according to claim 4, characterized in that, The influence parameter includes a positive correlation parameter and a negative correlation parameter; The determining the initial path evaluation value corresponding to the initial path based on the influence parameter includes: According to each positive correlation parameter and the first weight value corresponding to the positive correlation parameter, determine a first influence value of the positive correlation parameter; According to each negative correlation parameter and the second weight value corresponding to the negative correlation parameter, determine a second influence value of the negative correlation parameter; According to the first influence value and the second influence value, determine the initial path evaluation value.

6. The method according to claim 5, wherein The according to each positive correlation parameter and the first weight value corresponding to the positive correlation parameter, determining the first influence value of the positive correlation parameter includes: According to the positive correlation between each positive correlation parameter and path planning, determine the first weight value corresponding to each positive correlation parameter; Based on the positive correlation parameter and the first weight value, calculate a first weighted average value of the positive correlation parameter; The first influence value is obtained by maximizing a first numerical value, where the first numerical value is the sum of the products of the first weighted average and each of the positively correlated parameters; Determining the second influence value of each negatively correlated parameter according to each negatively correlated parameter and the corresponding second weight value of the negatively correlated parameter includes: Determining the corresponding second weight value of each negatively correlated parameter according to the negative correlation between each negatively correlated parameter and the path planning; Calculating the second weighted average of the negatively correlated parameters based on the negatively correlated parameters and the second weight value; The second influence value is obtained by minimizing a second numerical value, where the second numerical value is the sum of the products of the second weighted average and each of the negatively correlated parameters.

7. The method according to claim 1, wherein Based on the path evaluation value, screening the target path from the path planning start area to the path planning end area among the multiple initial paths includes: Among the multiple initial paths, screening the initial paths that meet the preset conditions as the target paths, where the preset condition is that the path evaluation value of the initial path is greater than or equal to a preset evaluation value.

8. A path planning device, characterized in that, including: A region determination module, configured to obtain a lesion image of a target object and determine a target region in the lesion image, where the target region includes multiple regions passed between the path planning start region and the path planning end region; An initial path determination module, configured to traverse each target region, determine multiple initial paths from the path planning start region to the path planning end region, and determine the path evaluation value corresponding to each initial path; A target path determination module, configured to screen the target path from the path planning start region to the path planning end region among the multiple initial paths based on the path evaluation value.

9. An electronic device, characterized in that, including: A processor and a memory, the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, For storing a computer program, the computer program causes a computer to execute the method according to any one of claims 1-7.

Images