General-purpose mother platform configurable image processing method and device for positioning type surgical robot

Abstract

The application discloses a positioning type surgical robot general mother platform configurable image processing method and device, and belongs to the technical field of image processing. The method comprises the following steps: acquiring image processing requirement information of a user; determining target algorithm nodes used for constituting an image processing flow and node connection relationships between the target algorithm nodes according to the image processing requirement information and a pre-constructed image processing algorithm library; and generating a processing flow configuration file according to the target algorithm nodes and the node connection relationships between the target algorithm nodes; wherein the processing flow configuration file is used for being directly parsed and executed to run a corresponding image processing flow. The technical scheme improves the configuration efficiency of the image processing flow, simultaneously realizes the modularization reuse, flow visualization and standardized configuration of the image processing algorithm, and greatly improves the adaptability and universality of the positioning type surgical robot general mother platform to various surgical scenes.

Description

Technical Field

[0001] This application belongs to the field of image processing technology, specifically relating to a configurable image processing method and apparatus for a general-purpose master platform for positioning surgical robots. Background Technology

[0002] Positioning-type surgical robots are widely used in minimally invasive surgical scenarios such as orthopedics, neurosurgery, and interventional therapy. Their accompanying image processing functions perform a series of processes on pre- or intraoperative image data, including preprocessing, target detection, segmentation, 3D reconstruction, image registration, and surgical planning. The processed results are then output to the robotic arm control module of the positioning-type surgical robot to guide precise operations. The image processing results are the foundation for subsequent positioning and manipulation; their accuracy and real-time performance directly affect the quality of the surgery.

[0003] Currently, the arrangement of image processing workflows for different surgical types and clinical needs mainly relies on professionals to manually sort and set them based on experience, determining the algorithm modules to be called and their execution order for each step. When the surgical plan is adjusted, the algorithm is updated, or new imaging equipment is introduced, manual evaluation and workflow re-arrangement are required. This process is cumbersome and inefficient, not only consuming a lot of human resources but also making it difficult to quickly respond to dynamic changes in clinical needs, thus limiting the ease of clinical promotion and application of positioning surgical robots. Summary of the Invention

[0004] This application provides a configurable image processing method and apparatus for a general-purpose master platform for positioning surgical robots. The purpose is to improve the configuration efficiency of the image processing workflow, while realizing the modular reuse of image processing algorithms and the visualization and standardized configuration of the workflow, thereby significantly improving the adaptability and versatility of the general-purpose master platform for positioning surgical robots to various surgical scenarios.

[0005] In a first aspect, embodiments of this application provide a configurable image processing method for a universal master platform of a positioning surgical robot, the method comprising: Obtain information about the user's image processing needs; Based on the image processing requirements and the pre-built image processing algorithm library, the target algorithm nodes used to constitute the image processing flow and the node connection relationships between the target algorithm nodes are determined. Based on the target algorithm node and the node connection relationship between the target algorithm nodes, a processing flow configuration file is generated; wherein, the processing flow configuration file is used to be directly parsed and executed to run the corresponding image processing flow.

[0006] Furthermore, the step of generating a processing flow configuration file based on the target algorithm node and the node connection relationships between the target algorithm nodes includes: Based on the target algorithm nodes and the node connection relationships between them, an initial processing flowchart is generated; Perform structural verification on the initial processing flowchart, and determine the initial processing flowchart that passes the structural verification as the target processing flowchart; Generate a processing flow configuration file based on the target processing flow diagram.

[0007] Furthermore, the structural verification of the initial processing flowchart includes: If a loop is detected in the initial processing flowchart, it is determined that the structure verification of the initial processing flowchart fails. And / or, If a broken chain node is detected in the initial processing flowchart, it is determined that the structure verification of the initial processing flowchart fails. And / or, If abnormal node connections are detected in the initial processing flowchart, it is determined that the structure verification of the initial processing flowchart fails.

[0008] Furthermore, the step of generating an initial processing flowchart based on the target algorithm node and the node connection relationships between the target algorithm nodes includes: Based on the target algorithm nodes and the node connection relationships between them, a basic processing flowchart is generated; Detect whether the data type conversion conditions are met between the target algorithm nodes that have node connection relationships in the basic processing flowchart. In the basic processing flowchart, data type conversion nodes are generated between target algorithm nodes that meet the data type conversion conditions, and the node connection relationship between the target algorithm nodes is updated to obtain the initial processing flowchart.

[0009] Furthermore, the step of generating a processing flow configuration file based on the target processing flow diagram includes: The target processing flowchart is topologically sorted to obtain a topological sorting result, and parallel execution branches in the target processing flowchart that do not have mutual dependencies are identified based on the topological sorting result. A processing flow configuration file is generated based on the topology sorting result, and a parallel execution flag is added to the parallel execution branch in the processing flow configuration file so that the parallel execution branch is scheduled to be executed in parallel when the processing flow configuration file is parsed and executed.

[0010] Furthermore, the process of pre-building an image processing algorithm library includes: Obtain node description information and create algorithm nodes to be registered based on the node description information; Based on the node type, input data type, and output data type in the node description information, a compatible connection relationship is established between the algorithm node to be registered and the existing algorithm nodes in the image processing algorithm library, and a list of connectable subsequent nodes for the algorithm node to be registered is generated. The algorithm nodes to be registered and the list of connectable subsequent nodes are written into the image processing algorithm library.

[0011] Furthermore, the image processing requirement information includes the target surgical type, the modality type of the image to be processed, and the type of the expected output processing result; The step of determining the target algorithm nodes used to constitute the image processing flow and the node connection relationships between the target algorithm nodes based on the image processing requirement information and the pre-built image processing algorithm library includes: Based on the target surgical type and the modality type of the image to be processed, a starting algorithm node is determined in the image processing algorithm library, and based on the desired output processing result type, a terminating algorithm node is determined in the image processing algorithm library. Based on the starting algorithm node, the ending algorithm node, the existing algorithm nodes in the image processing algorithm library, and the list of connectable subsequent nodes of the existing algorithm nodes, a process path search is performed to obtain the target algorithm nodes used to constitute the image processing process and the node connection relationships between the target algorithm nodes.

[0012] Secondly, embodiments of this application provide a configurable image processing device for a universal master platform of a positioning surgical robot, the device comprising: The information acquisition module is used to acquire the user's image processing requirements. The node determination module is used to determine the target algorithm nodes that constitute the image processing flow and the node connection relationships between the target algorithm nodes based on the image processing requirement information and the pre-built image processing algorithm library. The process configuration module is used to generate a processing process configuration file based on the target algorithm node and the node connection relationship between the target algorithm nodes; wherein, the processing process configuration file is used to be directly parsed and executed to run the corresponding image processing process.

[0013] Furthermore, the process configuration module is specifically used for: Based on the target algorithm nodes and the node connection relationships between them, an initial processing flowchart is generated; Perform structural verification on the initial processing flowchart, and determine the initial processing flowchart that passes the structural verification as the target processing flowchart; Generate a processing flow configuration file based on the target processing flow diagram.

[0014] Furthermore, the process configuration module is specifically used for: If a loop is detected in the initial processing flowchart, it is determined that the structure verification of the initial processing flowchart fails. And / or, If a broken chain node is detected in the initial processing flowchart, it is determined that the structure verification of the initial processing flowchart fails. And / or, If abnormal node connections are detected in the initial processing flowchart, it is determined that the structure verification of the initial processing flowchart fails.

[0015] Furthermore, the process configuration module is specifically used for: Based on the target algorithm nodes and the node connection relationships between them, a basic processing flowchart is generated; Detect whether the data type conversion conditions are met between the target algorithm nodes that have node connection relationships in the basic processing flowchart. In the basic processing flowchart, data type conversion nodes are generated between target algorithm nodes that meet the data type conversion conditions, and the node connection relationship between the target algorithm nodes is updated to obtain the initial processing flowchart.

[0016] Furthermore, the process configuration module is specifically used for: The target processing flowchart is topologically sorted to obtain a topological sorting result, and parallel execution branches in the target processing flowchart that do not have mutual dependencies are identified based on the topological sorting result. A processing flow configuration file is generated based on the topology sorting result, and a parallel execution flag is added to the parallel execution branch in the processing flow configuration file so that the parallel execution branch is scheduled to be executed in parallel when the processing flow configuration file is parsed and executed.

[0017] Furthermore, the device is also used for: Obtain node description information and create algorithm nodes to be registered based on the node description information; Based on the node type, input data type, and output data type in the node description information, a compatible connection relationship is established between the algorithm node to be registered and the existing algorithm nodes in the image processing algorithm library, and a list of connectable subsequent nodes for the algorithm node to be registered is generated. The algorithm nodes to be registered and the list of connectable subsequent nodes are written into the image processing algorithm library.

[0018] Furthermore, the image processing requirement information includes the target surgical type, the modality type of the image to be processed, and the type of the expected output processing result; The node determination module is specifically used for: Based on the target surgical type and the modality type of the image to be processed, a starting algorithm node is determined in the image processing algorithm library, and based on the desired output processing result type, a terminating algorithm node is determined in the image processing algorithm library. Based on the starting algorithm node, the ending algorithm node, the existing algorithm nodes in the image processing algorithm library, and the list of connectable subsequent nodes of the existing algorithm nodes, a process path search is performed to obtain the target algorithm nodes used to constitute the image processing process and the node connection relationships between the target algorithm nodes.

[0019] Thirdly, embodiments of this application provide an electronic device including a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the method described in the first aspect.

[0020] Fourthly, embodiments of this application provide a readable storage medium on which a program or instructions are stored, which, when executed by a processor, implement the method described in the first aspect.

[0021] In this embodiment, the user's image processing requirements are obtained; based on the image processing requirements and a pre-built image processing algorithm library, target algorithm nodes for constituting the image processing flow and the node connection relationships between the target algorithm nodes are determined; a processing flow configuration file is generated based on the target algorithm nodes and the node connection relationships between the target algorithm nodes; wherein, the processing flow configuration file is used to be directly parsed and executed to run the corresponding image processing flow. The aforementioned general-purpose master platform for positioning surgical robots can configure image processing methods, improving the configuration efficiency of image processing flows, while simultaneously realizing modular reuse of image processing algorithms and process visualization and standardized configuration, significantly improving the adaptability and versatility of the general-purpose master platform for positioning surgical robots to various surgical scenarios. Attached Figure Description

[0022] Figure 1 This is a flowchart illustrating the configurable image processing method for the universal mother platform of the positioning surgical robot provided in Embodiment 1 of this application; Figure 2 This is a flowchart illustrating the configurable image processing method for the universal mother platform of the positioning surgical robot provided in Embodiment 2 of this application; Figure 3This is a flowchart illustrating the process of pre-building an image processing algorithm library as provided in Embodiment 3 of this application; Figure 4 This is a schematic diagram of the structure of the configurable image processing device for the universal mother platform of the positioning surgical robot provided in Embodiment 4 of this application; Figure 5 This is a schematic diagram of the structure of the electronic device provided in Embodiment 5 of this application. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of this application clearer, specific embodiments of this application will be described in further detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely for explaining this application and not for limiting it. It should also be noted that, for ease of description, only the parts relevant to this application are shown in the drawings, not all of them. Before discussing exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe operations (or steps) as sequential processes, many of these operations can be performed in parallel, concurrently, or simultaneously. Furthermore, the order of the operations can be rearranged. The process can be terminated when its operation is completed, but may also have additional steps not included in the drawings. The process can correspond to a method, function, procedure, subroutine, subprogram, etc.

[0024] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0025] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0026] The configurable image processing method and apparatus for a general-purpose mother platform for positioning surgical robots provided in this application will be described in detail below with reference to the accompanying drawings and through specific embodiments and application scenarios.

[0027] First, this application is applicable to scenarios that require image processing, especially scenarios that require processing medical images to achieve surgical target area reconstruction and surgical instrument positioning guidance, such as pedicle screw implantation path planning in spinal surgery, craniofacial osteotomy guide plate design, or stereotactic puncture navigation in neurosurgery.

[0028] It is understood that the implementing entity of this application can be a general-purpose parent platform for positioning surgical robots. In this solution, the general-purpose parent platform for positioning surgical robots can, according to the configured image processing flow, transform the acquired raw medical images into key data such as three-dimensional models and target structure segmentation results required for surgery, and then integrate and run surgical planning and navigation functions based on these data, ultimately driving the positioning surgical robot to perform precise positioning of surgical instruments.

[0029] Example 1 Figure 1 This is a flowchart illustrating the configurable image processing method for the universal master platform of the positioning surgical robot provided in Embodiment 1 of this application. For example... Figure 1 As shown, the specific steps include the following: S101, obtain the user's image processing requirements information.

[0030] The image processing requirement information can be structured information representing the user's ideal image processing workflow. This information may include one or more target algorithm nodes selected by the user and the node connections between them. Alternatively, it may include surgical scenario type information corresponding to the image processing workflow. Specifically, the surgical scenario type information can be a predefined surgical planning scenario identifier, such as "spinal pedicle screw placement planning," "craniofacial osteotomy guide plate design," "neurosurgery stereotactic puncture navigation," or "joint replacement prosthesis matching," etc.

[0031] In one embodiment, the general-purpose master platform for positioning surgical robots can provide a visual process configuration interface to receive image processing requirements input by the user.

[0032] S102, based on the image processing requirement information and the pre-built image processing algorithm library, determine the target algorithm nodes used to constitute the image processing flow and the node connection relationships between the target algorithm nodes.

[0033] The image processing algorithm library can be a collection of pre-packaged image processing functional modules, each of which is encapsulated as an algorithm node with standard input / output data ports. The image processing algorithm library may include medical image segmentation algorithm nodes, medical image registration algorithm nodes, medical image keypoint detection algorithm nodes, and medical image structure recognition algorithm nodes, etc.

[0034] The image processing flow can be a directed combination of a series of processing steps that convert raw medical images into data required for surgical localization. Furthermore, the target algorithm nodes in the image processing flow can be specific algorithm node instances selected from an image processing algorithm library to implement specific image processing functions, such as CT bone window segmentation nodes or spinal vertebral body recognition nodes. The node connections between target algorithm nodes can be directed edges representing data flow paths, defining the source of input data for each target algorithm node and the target algorithm node to which the output data is destined.

[0035] In one embodiment, when the image processing requirement information includes one or more target algorithm nodes selected by the user and the node connection relationships between the target algorithm nodes, the image processing requirement information can be parsed to extract the node names and node connection relationships of the target algorithm nodes specified by the user. Matching and verification can be performed in the image processing algorithm library based on each node name. After confirming that the target algorithm nodes corresponding to all node names exist and are available, the target algorithm nodes selected by the user and their node connection relationships are determined as the target algorithm nodes and their node connection relationships constituting the current image processing flow.

[0036] In one embodiment, when the image processing requirement information includes the surgical scenario type information corresponding to the image processing process, a preset process template associated with the surgical scenario type information can be found in the image processing algorithm library based on the surgical scenario type information. The recommended algorithm nodes and their node connection relationships defined in the preset process template can be obtained as the target algorithm nodes and their node connection relationships constituting the current image processing process.

[0037] S103, Based on the target algorithm node and the node connection relationship between the target algorithm nodes, a processing flow configuration file is generated; wherein, the processing flow configuration file is used to be directly parsed and executed to run the corresponding image processing flow.

[0038] The processing flow configuration file can be a structured data file that describes the flow topology and the configuration parameters set for each target algorithm node and the entire image processing flow, such as a flow definition file in JSON or XML format.

[0039] The processing flow configuration file can be directly parsed and executed to run the corresponding image processing flow. That is, the process execution engine built into the general mother platform of the positioning surgical robot can read the processing flow configuration file and schedule the processing programs of the corresponding target algorithm nodes in sequence according to the node connection relationship defined therein. The image processing results can be directly output without recompilation or user programming intervention.

[0040] In one embodiment, the process of generating a processing flow configuration file based on the target algorithm nodes and the node connection relationships between them may include: obtaining global configuration parameters for the entire image processing flow; instantiating each target algorithm node to obtain each target algorithm node instance; converting the node connection relationships into an edge list representing the data flow direction; using a serialization tool to convert the global configuration parameters, each target algorithm node instance, and the edge list into text content in a preset data exchange format compatible with the process execution engine of the general parent platform of the positioning surgical robot; and storing it as a processing flow configuration file.

[0041] The global configuration parameters for the entire image processing workflow, as well as the configuration parameters used to instantiate each target algorithm node, can use default values, user-input values, or recommended values ​​from a pre-defined workflow template. The global configuration parameters can include GPU / CPU resource configuration parameters, number of threads, running precision, log level, timeout, and exception handling strategies.

[0042] In one embodiment, during the process of the process execution engine parsing and executing the processing flow configuration file, the runtime monitoring module can record the runtime status information of each target algorithm node instance in the processing flow configuration file in real time. This runtime status information may include the start time, end time, execution time, resource usage, execution result, exception information, and log information of the target algorithm node instance.

[0043] In one embodiment, when a target algorithm node instance fails to run, the process execution engine can perform corresponding exception handling operations according to a preset exception handling strategy. The exception handling strategy may include: re-executing the current target algorithm node instance, skipping the current target algorithm node instance and continuing to execute subsequent nodes, executing a pre-configured backup algorithm node instance, and terminating the entire image processing flow.

[0044] In one embodiment, after all target algorithm node instances in the processing flow configuration file have been executed, the process execution engine can output the final processing result according to the output method configured by the user, and persistently save the processing flow structure corresponding to the processing flow configuration file, the configuration parameters of each target algorithm node instance, the algorithm version information, running status information, result file and execution statistics information of each target algorithm node.

[0045] In one embodiment, a user can save the currently saved processing flow structure and configuration parameters as a flow template. This flow template can be directly loaded later, and by modifying the configuration parameters of some target algorithm nodes or replacing some target algorithm nodes, rapid reuse can be achieved between different medical image processing tasks.

[0046] In this embodiment, the user's image processing requirements are obtained; based on the image processing requirements and a pre-built image processing algorithm library, target algorithm nodes for constituting the image processing flow and the node connection relationships between the target algorithm nodes are determined; a processing flow configuration file is generated based on the target algorithm nodes and the node connection relationships between the target algorithm nodes; wherein, the processing flow configuration file is used to be directly parsed and executed to run the corresponding image processing flow. The aforementioned general-purpose master platform for positioning surgical robots can configure image processing methods, improving the configuration efficiency of image processing flows, while simultaneously realizing modular reuse of image processing algorithms and process visualization and standardized configuration, significantly improving the adaptability and versatility of the general-purpose master platform for positioning surgical robots to various surgical scenarios.

[0047] Example 2 Figure 2 This is a flowchart illustrating the configurable image processing method for the universal master platform of the positioning surgical robot provided in Embodiment 2 of this application. Figure 2 As shown, the specific steps include the following: S201, Obtain the user's image processing requirements information.

[0048] S202, based on the image processing requirement information and the pre-built image processing algorithm library, determine the target algorithm nodes used to constitute the image processing flow and the node connection relationships between the target algorithm nodes.

[0049] S203, Generate an initial processing flowchart based on the target algorithm node and the node connection relationship between the target algorithm nodes.

[0050] The initial processing flowchart can be a logical representation of the image processing flow using a directed graph data structure. Specifically, each target algorithm node corresponds to a vertex in the directed graph, and the node connections between target algorithm nodes correspond to directed edges in the directed graph.

[0051] In one embodiment, the process of generating an initial processing flowchart based on the target algorithm nodes and the node connection relationships between the target algorithm nodes may include: creating a directed graph data structure, traversing all target algorithm nodes, adding each target algorithm node as a vertex to the directed graph, traversing all node connection relationships, converting each node connection relationship into a directed edge corresponding to the vertex, and obtaining the initial processing flowchart.

[0052] In one embodiment, generating an initial processing flowchart based on the target algorithm nodes and the node connection relationships between them includes: generating a basic processing flowchart based on the target algorithm nodes and the node connection relationships between them; detecting whether the target algorithm nodes with node connection relationships in the basic processing flowchart meet the data type conversion conditions; generating data type conversion nodes between the target algorithm nodes that meet the data type conversion conditions in the basic processing flowchart, and updating the node connection relationships between the target algorithm nodes to obtain the initial processing flowchart.

[0053] The basic processing flowchart can be a preliminary directed graph representation without data type compatibility processing. Its vertices are target algorithm nodes, and the directed edges are the original node connection relationships between target algorithm nodes. At this time, the data type of the output port and input port of adjacent target algorithm nodes is not considered.

[0054] In one embodiment, the process of generating a basic processing flowchart based on the target algorithm nodes and the node connection relationships between the target algorithm nodes may include: creating a directed graph data structure, traversing all target algorithm nodes, adding each target algorithm node as a vertex to the directed graph, traversing all node connection relationships, converting each node connection relationship into a directed edge corresponding to the vertex, and obtaining the basic processing flowchart.

[0055] In one embodiment, the process of detecting whether the data type conversion conditions are met between target algorithm nodes that have node connections in the basic processing flowchart may include: traversing each directed edge in the basic processing flowchart, obtaining the output data type of the target algorithm node corresponding to the starting vertex of the directed edge and the input data type of the target algorithm node corresponding to the ending vertex of the directed edge, determining whether the two are consistent, and if they are inconsistent, determining that the data type conversion conditions are met between the two target algorithm nodes connected by the directed edge.

[0056] Among them, the data type conversion node can be a dedicated algorithm node pre-encapsulated in the image processing algorithm library, used to convert the output of one data type into the input of another data type, such as converting the label map of the segmentation result into the patch data format required for 3D surface reconstruction, or performing spatial transformation and alignment on the registration results of different coordinate spaces.

[0057] In one embodiment, in the basic processing flowchart, the process of generating data type conversion nodes between target algorithm nodes that meet the data type conversion conditions may include: for upstream and downstream target algorithm nodes that meet the data type conversion conditions, obtaining the output data type of the upstream target algorithm node and the input data type of the downstream target algorithm node, searching in the image processing algorithm library for data type conversion nodes whose input type is consistent with the output data type of the upstream target algorithm node and whose output type is consistent with the input data type of the downstream target algorithm node, and then inserting it as a new vertex between the upstream and downstream target algorithm nodes.

[0058] In one embodiment, the process of updating the node connection relationship between target algorithm nodes may include: deleting the original directed edges between the upstream target algorithm node and the downstream target algorithm node, adding directed edges from the upstream target algorithm node to the data type conversion node, and from the data type conversion node to the downstream target algorithm node, thereby completing the update of the node connection relationship.

[0059] The advantage of this approach is that by automatically detecting data type compatibility between target algorithm nodes and inserting data type conversion nodes where necessary, users can build a smooth image processing workflow without having to worry about the details of matching the underlying data formats. This lowers the technical threshold for workflow configuration while ensuring the correctness and consistency of data transmission within the workflow.

[0060] S204, perform structural verification on the initial processing flowchart, and determine the initial processing flowchart that passes the structural verification as the target processing flowchart.

[0061] The target processing flowchart can be a processing flowchart that confirms the integrity and correctness of the directed graph data structure after structural verification.

[0062] In one embodiment, structural verification of the initial processing flowchart includes: determining that the initial processing flowchart fails structural verification if a loop is detected in the initial processing flowchart; and / or determining that the initial processing flowchart fails structural verification if a broken node is detected in the initial processing flowchart; and / or determining that the initial processing flowchart fails structural verification if an abnormal node connection relationship is detected in the initial processing flowchart.

[0063] In this context, a loop can be a closed path in the initial processing flowchart that starts from a certain vertex, traverses along the directed edge direction, and returns to that vertex.

[0064] In one embodiment, the process of identifying whether there is a loop in the initial processing flowchart may include: performing a topological sort or a depth-first search traversal on the initial processing flowchart; if a back edge is detected during the traversal or the topological sort cannot be completed, it is determined that there is a loop in the initial processing flowchart.

[0065] The presence of loops in the initial processing flowchart indicates a circular dependency of data flows within the image processing workflow. This could lead to the execution engine entering an infinite loop or deadlock state, thus the initial processing flowchart structure verification fails.

[0066] Among them, a broken chain node can be an isolated target algorithm node with an in-degree of zero or an out-degree of zero, which exists in the initial processing flowchart, apart from the initial target algorithm node and the final target algorithm node, indicating that the target algorithm node is not connected to the data flow path.

[0067] In one embodiment, the process of identifying whether there are broken chain nodes in the initial processing flowchart may include: traversing all vertices in the initial processing flowchart, counting the in-degree and out-degree of each vertex, and determining that the target algorithm node corresponding to the vertex is a broken chain node, except for the starting vertex and the final vertex, if there is a vertex with an in-degree of zero or an out-degree of zero.

[0068] The initial processing flowchart contains a broken chain node, which means that the target algorithm node cannot obtain input data or cannot pass the processing result to the downstream target algorithm node. As a result, the processing function corresponding to the target algorithm node cannot participate in the calculation normally during the process execution. Therefore, it is determined that the structure verification of the initial processing flowchart fails.

[0069] Among them, abnormal node connection relationships may be in the initial processing flowchart where the target algorithm nodes associated with the two vertices of the directed edge are incompatible in a practical sense. For example, connecting the bone window segmentation node for CT images to the output of the soft tissue segmentation node for MRI images, incorrectly concatenating algorithm nodes for different anatomical sites, or directly connecting the output of the two-dimensional image processing node to the input of the three-dimensional spatial registration node, etc.

[0070] In one embodiment, the method for identifying whether there are abnormal node connections in the initial processing flowchart can be as follows: traverse each directed edge in the initial processing flowchart, obtain the attribute information bound to the upstream and downstream target algorithm nodes of the directed edge, the attribute information may include input and output data types, applicable image modalities, processing dimensions, and applicable anatomical parts, etc., determine whether there is a conflict between the upstream and downstream target algorithm nodes in at least one of the attribute information, and if there is a conflict, determine that the directed edge constitutes an abnormal node connection.

[0071] The presence of abnormal node connections in the initial processing flowchart indicates that there are combinations of algorithm nodes in the image processing flow that cannot be connected from the perspective of processing object, modality, dimension, or application scenario. In actual operation, data semantic errors or processing logic paradoxes will still occur. Therefore, it is determined that the structure verification of the initial processing flowchart fails.

[0072] The advantage of this approach is that by performing structural verification on the initial processing flowchart in three dimensions—loops, broken nodes, and abnormal node connections—it can comprehensively cover structural defects that may occur in the image processing flow, such as data flow circular dependencies, isolated nodes, and logical incompatibility. This prevents defective image processing flows from entering the instantiation and execution stages, thereby improving the accuracy of flow configuration and the success rate of flow execution.

[0073] S205, Generate a processing flow configuration file according to the target processing flow diagram; wherein, the processing flow configuration file is used to be directly parsed and executed to run the corresponding image processing flow.

[0074] In one embodiment, the process of generating a processing flow configuration file based on the target processing flowchart may include: obtaining global configuration parameters for the entire image processing flow, instantiating each target algorithm node to obtain each target algorithm node instance, using a serialization tool to convert the global configuration parameters, each target algorithm node instance, and the target processing flowchart into text content in a preset data exchange format compatible with the process execution engine of the general parent platform of the positioning surgical robot, and storing it as a processing flow configuration file.

[0075] In one embodiment, generating a processing flow configuration file based on a target processing flow diagram includes: performing a topological sort on the target processing flow diagram to obtain a topological sorting result, and identifying parallel execution branches in the target processing flow diagram that do not have mutual dependencies based on the topological sorting result; generating a processing flow configuration file based on the topological sorting result, and adding parallel execution flags to the parallel execution branches in the processing flow configuration file so that when the processing flow configuration file is parsed and executed, the parallel execution branches are scheduled to be executed in parallel.

[0076] In one embodiment, the process of performing topological sorting on the target processing flowchart to obtain the topological sorting result may include: executing a topological sorting algorithm on the target processing flowchart, determining the linear execution order of each target algorithm node according to the directed node connection relationship between each target algorithm node, and obtaining the topological sorting result.

[0077] In this context, parallel execution branches that do not have mutual dependencies can be multiple node chains in the target processing flowchart that are not directly connected by directed edges or have indirect dependency paths passed from other nodes. These node chains can be continuous path segments composed of consecutive target algorithm nodes and may include at least one target algorithm node.

[0078] In one embodiment, the process of identifying parallel execution branches in the target processing flowchart that do not have mutual dependencies based on the topology sorting result may include: dividing the topology sorting result into multiple levels, and identifying the node chains in the same level as a group of parallel execution branches if there are no direct directed edges connecting them and no indirect dependent paths.

[0079] In one embodiment, the process of generating a processing flow configuration file based on the topology sorting result may include: obtaining global configuration parameters for the entire image processing flow, instantiating each target algorithm node to obtain each target algorithm node instance, using a serialization tool to convert the global configuration parameters, each target algorithm node instance, and the topology sorting result into text content in a preset data exchange format compatible with the process execution engine of the general parent platform of the positioning surgical robot, and storing it as a processing flow configuration file.

[0080] The execution flag can be an identifier field used to identify the parallel execution group.

[0081] In one embodiment, the process of adding parallel execution markers to parallel execution branches in the processing flow configuration file may include: assigning a unique parallel group identifier to each identified group of parallel execution branches; and writing the target algorithm node instances belonging to the same parallel execution branch into the parallel group identifier as parallel execution markers when serializing each target algorithm node instance, so that the process execution engine can identify the parallel execution group when parsing the processing flow configuration file.

[0082] When the processing flow configuration file is parsed and executed, the parallel execution branches are scheduled and executed in parallel. That is, using multi-threading or thread pool mechanisms, the target algorithm nodes belonging to different parallel execution branches are assigned to different threads for simultaneous execution.

[0083] The advantage of this approach is that by performing topological sorting on the target processing flowchart and automatically identifying parallel execution branches with no dependencies, and explicitly marking them with parallel execution flags in the processing flow configuration file, parallel execution can be directly scheduled without re-analyzing dependencies at runtime when executing the image processing flow. This fully utilizes multi-core computing resources while ensuring the correctness of data dependencies, effectively shortening the overall execution time of the image processing flow.

[0084] The advantage of this approach is that it uniformly represents the configured image processing flow as a directed graph data structure, and automatically identifies and eliminates logical defects in the image processing flow through graph structure verification, ensuring that only logically valid image processing flows can enter the execution stage, thereby improving the reliability of the flow configuration and the stability of the flow execution.

[0085] Example 3 Figure 3 This is a flowchart illustrating the process of pre-building an image processing algorithm library as provided in Embodiment 3 of this application. Figure 3 As shown, the specific steps include the following: S301, Obtain node description information and create an algorithm node to be registered based on the node description information.

[0086] The node description information can be structured information used to define the various attributes of a new algorithm node, including node name, node type, algorithm name, input data type, output data type, parameter configuration items, resource requirement information, version information, and node description information.

[0087] Among them, the algorithm node to be registered can be an algorithm node created based on the node description information that has not yet been written into the image processing algorithm library. It encapsulates the corresponding image processing algorithm logic internally and exposes standard input / output data ports and configurable parameter items that conform to the node description information definition.

[0088] In one embodiment, the process of creating a node to be registered based on node description information may include: performing integrity verification on the node description information; loading the corresponding image processing algorithm implementation program according to the algorithm name in the node description information; mapping the input data type and output data type to the standard input port and standard output port of the node to be registered, respectively; mapping the parameter configuration items to the configurable parameter list of the node to be registered; binding the resource requirement information and version information to the metadata attributes of the node to be registered; and completing the creation of the node to be registered.

[0089] S302, based on the node type, input data type and output data type in the node description information, establish a compatible connection relationship between the algorithm node to be registered and the existing algorithm nodes in the image processing algorithm library, and generate a list of connectable subsequent nodes for the algorithm node to be registered.

[0090] The list of connectable subsequent nodes for the algorithm node to be registered can be a set of existing algorithm nodes in the image processing algorithm library that can directly receive the output data of the algorithm node to be registered as input.

[0091] In one embodiment, the process of establishing a compatible connection between the algorithm node to be registered and existing algorithm nodes in the image processing algorithm library based on the node type, input data type, and output data type in the node description information, and generating a list of connectable subsequent nodes for the algorithm node to be registered, may include: obtaining the output data type of the algorithm node to be registered; traversing all existing algorithm nodes in the image processing algorithm library; matching the input data type of the existing algorithm nodes with the output data type of the algorithm node to be registered; simultaneously obtaining the node type of the algorithm node to be registered and the node type of the existing algorithm nodes, and determining whether they are compatible in the application scenario; and adding existing algorithm nodes with matching input data types and compatible node types to the list of connectable subsequent nodes for the algorithm node to be registered.

[0092] S303, the algorithm node to be registered and the list of connectable subsequent nodes are written into the image processing algorithm library.

[0093] In one embodiment, the process of writing the algorithm node to be registered and the list of connectable subsequent nodes into the image processing algorithm library may include: assigning a unique algorithm library index identifier to the algorithm node to be registered; persistently storing the node description information, algorithm implementation program reference, standard input / output port definition, and configurable parameter list of the algorithm node to be registered as an algorithm node entry in the image processing algorithm library; simultaneously associating the list of connectable subsequent nodes with the algorithm library index identifier of the algorithm node to be registered for node compatibility query during image processing workflow configuration; traversing all existing algorithm nodes in the image processing algorithm library; matching the output data type of the existing algorithm nodes with the input data type of the algorithm node to be registered; simultaneously obtaining the node type of the algorithm node to be registered and the node type of the existing algorithm nodes; determining whether the two are compatible in the application scenario; and adding the algorithm node to be registered to the list of connectable subsequent nodes of the existing algorithm nodes whose output data type matches and whose node type is compatible.

[0094] In one embodiment, the image processing requirement information includes the target surgical type, the modality type of the image to be processed, and the type of the expected output processing result. Based on the image processing requirement information and a pre-built image processing algorithm library, the target algorithm nodes used to constitute the image processing flow and the node connection relationships between the target algorithm nodes are determined, including: determining the starting algorithm node in the image processing algorithm library based on the target surgical type and the modality type of the image to be processed, and determining the ending algorithm node in the image processing algorithm library based on the type of the expected output processing result. Based on the starting algorithm node, the ending algorithm node, the existing algorithm nodes in the image processing algorithm library, and the list of connectable subsequent nodes of the existing algorithm nodes, a flow path search is performed to obtain the target algorithm nodes used to constitute the image processing flow and the node connection relationships between the target algorithm nodes.

[0095] The image processing requirements information can include the target surgery type, the modality type of the image to be processed, and the type of the expected output processing result. Specifically, the target surgery type can be the type of surgical planning scenario that the user expects to perform, such as "spinal pedicle screw placement planning," "craniofacial osteotomy guide design," or "neurosurgery stereotactic puncture navigation," etc.; the modality type of the image to be processed can be the imaging modality of the original medical image provided by the user, such as "CT image," "MRI image," "PET image," or "ultrasound image," etc.; the type of expected output processing result can be the type of data of the final result that the user hopes the image processing workflow will generate, such as "3D bone surface model," "surgical path planning scheme," "registered multimodal fusion image," or "segmentation result of key anatomical structures," etc.

[0096] The starting algorithm node can be an algorithm node in the image processing algorithm library whose node type in its node description information matches the target surgical type and the modality type of the image to be processed. It serves as the data input and preprocessing entry point for the entire image processing process and is responsible for converting the original medical image into a standard format that can be processed by subsequent algorithm nodes. The terminating algorithm node can be an algorithm node in the image processing algorithm library whose output data type matches the expected output processing result type. It serves as the final output algorithm node for the entire image processing process.

[0097] In one embodiment, the process of determining the starting algorithm node in the image processing algorithm library based on the target surgical type and the modality type of the image to be processed may include: traversing all existing algorithm nodes in the image processing algorithm library, obtaining the node type and input data type of each existing algorithm node, and determining the existing algorithm nodes that match the target surgical type and whose input data type is consistent with the modality type of the image to be processed as candidate starting algorithm nodes; if there are multiple candidate starting algorithm nodes, filtering is performed based on the version information and resource requirement information of each candidate starting algorithm node, and selecting the candidate starting algorithm node with the latest version and resource requirements compatible with the current parent platform operating environment as the starting algorithm node.

[0098] In one embodiment, the process of determining the termination algorithm node in the image processing algorithm library based on the expected output processing result type may include: traversing all existing algorithm nodes in the image processing algorithm library, obtaining the output data type of each existing algorithm node, and determining the existing algorithm node whose output data type matches the expected output processing result type as a candidate termination algorithm node; if there are multiple candidate termination algorithm nodes, filtering is performed based on the version information and applicable scenario information of each candidate termination algorithm node, and selecting the candidate termination algorithm node with the highest correlation to the target surgical type as the termination algorithm node.

[0099] In one embodiment, the process of performing a flow path search to obtain the target algorithm nodes and node connection relationships between the target algorithm nodes, based on the starting algorithm node, the ending algorithm node, existing algorithm nodes in the image processing algorithm library, and the list of connectable subsequent nodes of the existing algorithm nodes, may include: using the starting algorithm node as the search starting point and the ending algorithm node as the search ending point, performing a graph search algorithm in a directed compatibility graph composed of existing algorithm nodes in the image processing algorithm library and their list of connectable subsequent nodes to search for at least one feasible path from the starting algorithm node to the ending algorithm node; determining all algorithm nodes on the searched feasible path as the target algorithm nodes constituting the image processing flow, and converting the connectable relationships between the target algorithm nodes on the path into node connection relationships between the target algorithm nodes.

[0100] The advantage of this solution is that users only need to specify high-level requirements such as the target surgical type, the modality type of the image to be processed, and the type of the expected output processing result. The solution can automatically match the starting and ending algorithm nodes in the image processing algorithm library and automatically search and generate a complete image processing flow based on the list of connectable subsequent nodes of the existing algorithm nodes. This greatly reduces the user's configuration burden on the details of the algorithm nodes and the flow topology. At the same time, the use of graph search algorithms ensures the path connectivity and node compatibility of the generated flow, improving the automation and accuracy of the flow configuration.

[0101] The advantage of this approach is that it enables the registration of new algorithm nodes through standardized node description information, ensuring the continuous scalability of the image processing algorithm library and allowing the general-purpose platform for positioning surgical robots to flexibly adapt to the ever-increasing surgical scenarios and image processing needs.

[0102] Example 4 Figure 4 This is a schematic diagram of the structure of the configurable image processing device for the universal master platform of the positioning surgical robot provided in Embodiment 4 of this application. Figure 4 As shown, the device includes: Information acquisition module 410 is used to acquire the user's image processing requirements information; The node determination module 420 is used to determine the target algorithm nodes used to constitute the image processing flow and the node connection relationships between the target algorithm nodes based on the image processing requirement information and the pre-built image processing algorithm library. The process configuration module 430 is used to generate a processing process configuration file based on the target algorithm node and the node connection relationship between the target algorithm nodes; wherein, the processing process configuration file is used to be directly parsed and executed to run the corresponding image processing process.

[0103] Furthermore, the process configuration module 430 is specifically used for: Based on the target algorithm nodes and the node connection relationships between them, an initial processing flowchart is generated; Perform structural verification on the initial processing flowchart, and determine the initial processing flowchart that passes the structural verification as the target processing flowchart; Generate a processing flow configuration file based on the target processing flow diagram.

[0104] Furthermore, the process configuration module 430 is specifically used for: If a loop is detected in the initial processing flowchart, it is determined that the structure verification of the initial processing flowchart fails. And / or, If a broken chain node is detected in the initial processing flowchart, it is determined that the structure verification of the initial processing flowchart fails. And / or, If abnormal node connections are detected in the initial processing flowchart, it is determined that the structure verification of the initial processing flowchart fails.

[0105] Furthermore, the process configuration module 430 is specifically used for: Based on the target algorithm nodes and the node connection relationships between them, a basic processing flowchart is generated; Detect whether the data type conversion conditions are met between the target algorithm nodes that have node connection relationships in the basic processing flowchart. In the basic processing flowchart, data type conversion nodes are generated between target algorithm nodes that meet the data type conversion conditions, and the node connection relationship between the target algorithm nodes is updated to obtain the initial processing flowchart.

[0106] Furthermore, the process configuration module 430 is specifically used for: The target processing flowchart is topologically sorted to obtain a topological sorting result, and parallel execution branches in the target processing flowchart that do not have mutual dependencies are identified based on the topological sorting result. A processing flow configuration file is generated based on the topology sorting result, and a parallel execution flag is added to the parallel execution branch in the processing flow configuration file so that the parallel execution branch is scheduled to be executed in parallel when the processing flow configuration file is parsed and executed.

[0107] Furthermore, the device is also used for: Obtain node description information and create algorithm nodes to be registered based on the node description information; Based on the node type, input data type, and output data type in the node description information, a compatible connection relationship is established between the algorithm node to be registered and the existing algorithm nodes in the image processing algorithm library, and a list of connectable subsequent nodes for the algorithm node to be registered is generated. The algorithm nodes to be registered and the list of connectable subsequent nodes are written into the image processing algorithm library.

[0108] Furthermore, the image processing requirement information includes the target surgical type, the modality type of the image to be processed, and the type of the expected output processing result; The node determination module 420 is specifically used for: Based on the target surgical type and the modality type of the image to be processed, a starting algorithm node is determined in the image processing algorithm library, and based on the desired output processing result type, a terminating algorithm node is determined in the image processing algorithm library. Based on the starting algorithm node, the ending algorithm node, the existing algorithm nodes in the image processing algorithm library, and the list of connectable subsequent nodes of the existing algorithm nodes, a process path search is performed to obtain the target algorithm nodes used to constitute the image processing process and the node connection relationships between the target algorithm nodes.

[0109] In this embodiment, the information acquisition module is used to acquire the user's image processing requirements information; the node determination module is used to determine the target algorithm nodes that constitute the image processing flow and the node connection relationships between the target algorithm nodes based on the image processing requirements information and a pre-built image processing algorithm library; the flow configuration module is used to generate a processing flow configuration file based on the target algorithm nodes and the node connection relationships between the target algorithm nodes; wherein, the processing flow configuration file is used to be directly parsed and executed to run the corresponding image processing flow. The above-mentioned general-purpose master platform for positioning surgical robots can be configured with image processing devices, improving the configuration efficiency of image processing flows, while realizing the modular reuse of image processing algorithms and the visualization and standardized configuration of the flow, significantly improving the adaptability and versatility of the general-purpose master platform for positioning surgical robots to various surgical scenarios.

[0110] The configurable image processing device of the general-purpose mother platform for positioning surgical robots in this application embodiment can be a device, or a component, integrated circuit, or chip in a terminal. This device can be a mobile electronic device or a non-mobile electronic device. For example, mobile electronic devices can be mobile phones, tablets, laptops, PDAs, in-vehicle electronic devices, wearable devices, ultra-mobile personal computers (UMPCs), netbooks, or personal digital assistants (PDAs), etc., while non-mobile electronic devices can be servers, network-attached storage (NAS), personal computers (PCs), televisions (TVs), ATMs, or self-service machines, etc. This application embodiment does not impose specific limitations.

[0111] The configurable image processing device of the general-purpose mother platform for the positioning surgical robot in this application embodiment can be a device with an operating system. This operating system can be Android, iOS, or other possible operating systems; this application embodiment does not specifically limit it.

[0112] The universal mother platform for positioning surgical robots provided in this application embodiment can be configured with an image processing device to realize the various processes implemented in the above embodiments. To avoid repetition, it will not be described again here.

[0113] Example 5 Figure 5 This is a schematic diagram of the structure of the electronic device provided in Embodiment 5 of this application. Figure 5 As shown, this application embodiment also provides an electronic device 500, including a processor 501, a memory 502, and a program or instructions stored in the memory 502 and executable on the processor 501. When the program or instructions are executed by the processor 501, they implement the various processes of the above-described embodiment of the configurable image processing method for the general mother platform of the positioning surgical robot, and can achieve the same technical effect. To avoid repetition, they will not be described again here.

[0114] It should be noted that the electronic devices in the embodiments of this application include the mobile electronic devices and non-mobile electronic devices described above.

[0115] Example 6 This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described embodiments of the configurable image processing method for the general mother platform of the positioning surgical robot, and achieve the same technical effect. To avoid repetition, these will not be described again here.

[0116] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0117] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0118] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0119] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

[0120] The above description is merely a preferred embodiment and the technical principles employed in this application. This application is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions that can be made by those skilled in the art will not depart from the scope of protection of this application. Therefore, although this application has been described in detail through the above embodiments, this application is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of this application, the scope of which is determined by the scope of the claims.

Claims

1. A configurable image processing method for a universal master platform of a positioning surgical robot, characterized in that, The method includes: Obtain information about the user's image processing needs; Based on the image processing requirements and the pre-built image processing algorithm library, the target algorithm nodes used to constitute the image processing flow and the node connection relationships between the target algorithm nodes are determined. Based on the target algorithm nodes and the node connection relationships between them, a processing flow configuration file is generated; wherein, the processing flow configuration file is used to be directly parsed and executed to run the corresponding image processing flow.

2. The configurable image processing method for the universal master platform of the positioning surgical robot according to claim 1, characterized in that, The step of generating a processing flow configuration file based on the target algorithm node and the node connection relationships between the target algorithm nodes includes: Based on the target algorithm nodes and the node connection relationships between them, an initial processing flowchart is generated; Perform structural verification on the initial processing flowchart, and determine the initial processing flowchart that passes the structural verification as the target processing flowchart; Generate a processing flow configuration file based on the target processing flow diagram.

3. The configurable image processing method for the universal master platform of the positioning surgical robot according to claim 2, characterized in that, The structural verification of the initial processing flowchart includes: If a loop is detected in the initial processing flowchart, it is determined that the structure verification of the initial processing flowchart fails. And / or, If a broken chain node is detected in the initial processing flowchart, it is determined that the structure verification of the initial processing flowchart fails. And / or, If abnormal node connections are detected in the initial processing flowchart, it is determined that the structure verification of the initial processing flowchart fails.

4. The configurable image processing method for the universal master platform of the positioning surgical robot according to claim 2, characterized in that, The step of generating an initial processing flowchart based on the target algorithm node and the node connection relationships between the target algorithm nodes includes: Based on the target algorithm nodes and the node connection relationships between them, a basic processing flowchart is generated; Detect whether the data type conversion conditions are met between the target algorithm nodes that have node connection relationships in the basic processing flowchart. In the basic processing flowchart, data type conversion nodes are generated between target algorithm nodes that meet the data type conversion conditions, and the node connection relationship between the target algorithm nodes is updated to obtain the initial processing flowchart.

5. The configurable image processing method for the universal master platform of the positioning surgical robot according to claim 2, characterized in that, The step of generating a processing flow configuration file based on the target processing flow diagram includes: The target processing flowchart is topologically sorted to obtain a topological sorting result, and parallel execution branches in the target processing flowchart that do not have mutual dependencies are identified based on the topological sorting result. A processing flow configuration file is generated based on the topology sorting result, and a parallel execution flag is added to the parallel execution branch in the processing flow configuration file so that the parallel execution branch is scheduled to be executed in parallel when the processing flow configuration file is parsed and executed.

6. The configurable image processing method for the universal master platform of the positioning surgical robot according to claim 1, characterized in that, The process of pre-building an image processing algorithm library includes: Obtain node description information and create algorithm nodes to be registered based on the node description information; Based on the node type, input data type, and output data type in the node description information, a compatible connection relationship is established between the algorithm node to be registered and the existing algorithm nodes in the image processing algorithm library, and a list of connectable subsequent nodes for the algorithm node to be registered is generated. The algorithm nodes to be registered and the list of connectable subsequent nodes are written into the image processing algorithm library.

7. The configurable image processing method for the universal master platform of the positioning surgical robot according to claim 6, characterized in that, The image processing requirements information includes the target surgical type, the modality type of the image to be processed, and the type of expected output processing result. The step of determining the target algorithm nodes used to constitute the image processing flow and the node connection relationships between the target algorithm nodes based on the image processing requirement information and the pre-built image processing algorithm library includes: Based on the target surgical type and the modality type of the image to be processed, a starting algorithm node is determined in the image processing algorithm library, and based on the desired output processing result type, a terminating algorithm node is determined in the image processing algorithm library. Based on the starting algorithm node, the ending algorithm node, the existing algorithm nodes in the image processing algorithm library, and the list of connectable subsequent nodes of the existing algorithm nodes, a process path search is performed to obtain the target algorithm nodes used to constitute the image processing process and the node connection relationships between the target algorithm nodes.

8. A universal master platform for a positioning surgical robot, configurable with an image processing device, characterized in that, The device includes: The information acquisition module is used to acquire the user's image processing requirements. The node determination module is used to determine the target algorithm nodes that constitute the image processing flow and the node connection relationships between the target algorithm nodes based on the image processing requirement information and the pre-built image processing algorithm library. The process configuration module is used to generate a processing process configuration file based on the target algorithm node and the node connection relationship between the target algorithm nodes; wherein, the processing process configuration file is used to be directly parsed and executed to run the corresponding image processing process.

9. An electronic device, characterized in that, It includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the configurable image processing method for a general master platform of a positioning surgical robot as described in any one of claims 1-7.

10. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the configurable image processing method for a universal master platform of a positioning surgical robot as described in any one of claims 1-7.

Images