Accurate blood vessel positioning system for robot-assisted inferior membranous artery priority method

Abstract

The embodiment of the invention provides a blood vessel precise positioning system for a robot-assisted inferior membranous artery priority method, and belongs to the technical field of information positioning. Comprises: an edge detection module performs edge detection on image data to obtain target edge information; the model reconstruction module performs three-dimensional reconstruction according to the image data and the target edge information to obtain a three-dimensional model; the position obtaining module obtains a first position of the initial blood vessel and a second position of the target peripheral tissue from the three-dimensional model; the position determination module determines an initial operation position according to the first position and the second position; the data acquisition module obtains first blood data of the initial blood vessel and operates the target robot at the initial operation position to obtain second blood data; the state judgment module performs abnormal recognition according to the first blood data and the second blood data to obtain a target influence state of the initial blood vessel; and the result determination module performs accurate blood vessel positioning according to the target influence state in combination with the initial blood vessel and the first position to obtain a blood vessel positioning result.

Description

Technical Field

[0001] The present invention relates to the technical field of information positioning, and in particular, to a vascular precise positioning system for the superior mesenteric artery priority method assisted by a robot. Background Art

[0002] In the current medical field, pancreatic cancer, a highly malignant disease, seriously endangers the lives and health of patients. Surgical resection remains the only possible way to cure this disease at present. However, the special physiological position of the pancreas deep in the abdominal cavity poses a huge obstacle to surgical treatment. The anatomical structure around the pancreas is extremely complex, and many key blood vessels are densely intertwined here, such as the superior mesenteric artery (SMA), the superior mesenteric vein (SMV), and the portal vein. These blood vessels not only play an important role in the human blood circulation, but their own structures and courses are extremely complex, greatly increasing the difficulty and risk of the surgery.

[0003] In recent years, with the remarkable progress of medical technology, the technology of surgical robot-assisted surgery has emerged, providing a new solution for hepatobiliary and pancreatic surgeries. The surgical assistance robot system has many remarkable advantages. Its robotic arm can achieve fine movements at the millimeter level, greatly improving the accuracy of doctors' surgical operations. However, when using surgical robots for vascular positioning, due to the limitations of medical imaging data itself, it is impossible to clearly and accurately display the vascular conditions, thus making it difficult to achieve precise vascular positioning, which also to a certain extent limits the full play of the advantages of surgical robots.

[0004] Therefore, it is urgent to design a technical solution to solve at least one of the above technical problems. Summary of the Invention

[0005] The main purpose of the embodiments of the present invention is to provide a vascular precise positioning system for the superior mesenteric artery priority method assisted by a robot, aiming to solve the problem that in the related technology, when using surgical robots for vascular positioning, due to the limitations of medical imaging data itself, it is impossible to clearly and accurately display the vascular conditions, thus making it difficult to achieve precise vascular positioning.

[0006] In a first aspect, the embodiments of the present invention provide a vascular precise positioning system for the superior mesenteric artery priority method assisted by a robot, including:

[0007] An image acquisition module, configured to acquire image data corresponding to a target area of a target patient by using a medical imaging sensor, where the image data at least includes an object to be resected and the initial blood vessels and target surrounding tissues corresponding to the periphery of the object to be resected;

[0008] An edge detection module, configured to perform edge detection on the image data to obtain target edge information corresponding to the target area;

[0009] A model reconstruction module, configured to perform three-dimensional reconstruction based on the image data and the target edge information to obtain a target three-dimensional model corresponding to the target region;

[0010] A position obtaining module, configured to obtain first position information corresponding to the initial blood vessel and second position information corresponding to the target surrounding tissue from the target three-dimensional model;

[0011] A position determination module, configured to determine an initial surgical position corresponding to the target patient according to the first position information and the second position information;

[0012] A data acquisition module, configured to obtain first blood data corresponding to the initial blood vessel, and perform virtual operations on a target robot at the initial surgical position to obtain second blood data corresponding to the initial blood vessel at the initial surgical position;

[0013] A state judgment module, configured to perform abnormality identification according to the first blood data and the second blood data to obtain a target influence state corresponding to the initial blood vessel during surgical operations at the initial surgical position;

[0014] A result determination module, configured to perform precise blood vessel positioning according to the target influence state in combination with the initial blood vessel and the first position information to obtain a blood vessel positioning result.

[0015] In a second aspect, an embodiment of the present invention provides a method for precise blood vessel positioning for the priority method of the membranous artery assisted by a robot, including:

[0016] Collecting image data corresponding to a target region of a target patient by using a medical image sensor, where the image data at least includes an object to be resected and an initial blood vessel and a target surrounding tissue corresponding to the periphery of the object to be resected;

[0017] Performing edge detection on the image data to obtain target edge information corresponding to the target region;

[0018] Performing three-dimensional reconstruction according to the image data and the target edge information to obtain a target three-dimensional model corresponding to the target region;

[0019] Obtaining first position information corresponding to the initial blood vessel and second position information corresponding to the target surrounding tissue from the target three-dimensional model;

[0020] Determining an initial surgical position corresponding to the target patient according to the first position information and the second position information;

[0021] Obtain the first blood data corresponding to the initial blood vessel, and perform virtual operations on the target robot at the initial surgical position to obtain the second blood data corresponding to the initial blood vessel at the initial surgical position;

[0022] Perform anomaly recognition based on the first blood data and the second blood data to obtain the target impact state corresponding to the initial blood vessel during surgical operations at the initial surgical position;

[0023] Perform precise blood vessel positioning based on the target impact state in combination with the initial blood vessel and the first position information to obtain a blood vessel positioning result.

[0024] In a third aspect, an embodiment of the present invention further provides a terminal device, which includes a processor, a memory, a computer program stored on the memory and executable by the processor, and a data bus for realizing the connection and communication between the processor and the memory. When the computer program is executed by the processor, it implements the steps of any vascular precise positioning system for the membrane artery priority method assisted by a robot provided in the specification of the present invention.

[0025] In a fourth aspect, an embodiment of the present invention further provides a storage medium for computer-readable storage, characterized in that the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of any vascular precise positioning system for the membrane artery priority method assisted by a robot provided in the specification of the present invention.

[0026] An embodiment of the present invention provides a vascular precise positioning system for the artery - first method assisted by a robot. The system includes: an image acquisition module for acquiring image data corresponding to a target area of a target patient by using a medical imaging sensor. The image data at least includes an object to be excised, an initial blood vessel corresponding to the periphery of the object to be excised, and target peripheral tissues. The edge detection module is used to perform edge detection on the image data to obtain target edge information, which helps to clearly define the boundaries of the object to be excised, the initial blood vessel, and the peripheral tissues, thereby reducing accidental injury to surrounding normal tissues during the operation and improving the safety of the operation. Then, the model reconstruction module performs three - dimensional reconstruction based on the image data and the target edge information to obtain a target three - dimensional model of the target area, providing an intuitive and three - dimensional view of the surgical area. Compared with traditional two - dimensional images, the spatial relationships between various structures, such as the course of blood vessels and the layers of tissues, can be observed more clearly, which helps to formulate a more reasonable surgical plan. Thus, the obtained position module obtains the first position information of the initial blood vessel and the second position information of the target peripheral tissues from the target three - dimensional model, providing an accurate coordinate basis for determining the surgical position. Furthermore, by comparing the first position information and the second position information, the spatial relationship between the initial blood vessel and the peripheral tissues is analyzed in depth to better plan the surgical path and avoid damaging important structures. Then, the position determination module determines the initial surgical position by using the first position information and the second position information, making the selection of the surgical incision and the operation path more scientific and reasonable. This helps to reduce surgical trauma. Thus, the data acquisition module acquires the first blood data of the initial blood vessel, such as blood flow velocity, blood pressure, etc. Then, the target robot performs virtual operations at the initial surgical position to obtain the second blood data of the initial blood vessel at this position. Furthermore, the state judgment module performs abnormal recognition based on the first blood data and the second blood data to obtain the target influence state of the surgical operation on the initial blood vessel at the initial surgical position, providing a risk warning for potential blood vessel damage risks during the operation, such as abnormal reduction in blood flow and blood pressure fluctuations. Finally, the result determination module performs precise vascular positioning based on the target influence state, the initial blood vessel, and the first position information to obtain a vascular positioning result, enabling the doctor to accurately find the target blood vessel during the operation and adopt appropriate operation methods to minimize damage to the blood vessel and improve the success rate and safety of the operation. And it solves the problem in the related technology that when using a surgical robot for vascular positioning, due to the limitations of medical imaging data itself, the blood vessel conditions cannot be clearly and accurately displayed, resulting in difficulty in achieving precise vascular positioning. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] To more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can also be obtained based on these drawings.

[0028] Figure 1 It is a schematic diagram of the module structure of a vascular precise positioning system for the inferior mesenteric artery priority method assisted by a robot provided by an embodiment of the present invention;

[0029] Figure 2 It is a schematic flowchart of another vascular precise positioning method for the inferior mesenteric artery priority method assisted by a robot provided by an embodiment of the present invention;

[0030] Figure 3 It is a schematic diagram of the structure of a terminal device provided by an embodiment of the present invention. Detailed implementation manners

[0031] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0032] The flowcharts shown in the accompanying drawings are only illustrative examples and do not necessarily include all contents and operations / steps, nor do they necessarily need to be executed in the described order. For example, some operations / steps can also be decomposed, combined, or partially merged. Therefore, the actual execution order may be changed according to the actual situation.

[0033] It should be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in this specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" are intended to include the plural forms.

[0034] An embodiment of the present invention provides a vascular precise positioning system for the inferior mesenteric artery priority method assisted by a robot. Among them, the vascular precise positioning system for the inferior mesenteric artery priority method assisted by a robot can be applied to a terminal device, and the terminal device can be an electronic device such as a tablet computer, a notebook computer, a desktop computer, a personal digital assistant, and a wearable device. The terminal device can be a server or a server cluster.

[0035] The following will describe in detail some embodiments of the present invention with reference to the accompanying drawings. Without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0036] Please refer to Figure 1 , Figure 1 which is a schematic diagram of the module structure of a vascular precise positioning system for the method of preferentially treating the membranous artery assisted by a robot according to an embodiment of the present invention.

[0037] As Figure 1 shown, the vascular precise positioning system 100 for the method of preferentially treating the membranous artery assisted by a robot includes an image acquisition module 101, an edge detection module 102, a model reconstruction module 103, a position acquisition module 104, a position determination module 105, a data acquisition module 106, a state judgment module 107, and a result determination module 108. Among them, the image acquisition module 101 is used to acquire image data corresponding to the target area of the target patient by using a medical imaging sensor, and the image data at least includes the object to be excised and the initial blood vessels and target surrounding tissues corresponding to the periphery of the object to be excised; the edge detection module 102 is used to perform edge detection on the image data to obtain the target edge information corresponding to the target area; the model reconstruction module 103 is used to perform three-dimensional reconstruction according to the image data and the target edge information to obtain the target three-dimensional model corresponding to the target area; the position acquisition module 104 is used to obtain the first position information corresponding to the initial blood vessels and the second position information corresponding to the target surrounding tissues from the target three-dimensional model; the position determination module 105 is used to determine the initial surgical position corresponding to the target patient according to the first position information and the second position information; the data acquisition module 106 is used to obtain the first blood data corresponding to the initial blood vessels and the second blood data corresponding to the initial blood vessels at the initial surgical position obtained by performing virtual operations on the target robot at the initial surgical position; the state judgment module 107 is used to perform abnormal recognition according to the first blood data and the second blood data to obtain the target influence state corresponding to the initial blood vessels when performing surgical operations at the initial surgical position; the result determination module 108 is used to perform precise vascular positioning according to the target influence state in combination with the initial blood vessels and the first position information to obtain a vascular positioning result.

[0038] Exemplarily, the image acquisition module 101 selects appropriate medical imaging sensors such as X-ray, CT scanner, MRI device, ultrasound probe, etc. according to the target area and inspection requirements, and then acquires image data by performing image acquisition on the target area of the target patient using the medical imaging sensor. The image data may be multiple images acquired from multiple perspectives. The target area is the area in the target patient where there is an object to be resected, such as a pancreatic cancer area. The image data at least includes the object to be resected and the corresponding initial blood vessels and target surrounding tissues around the object to be resected.

[0039] Exemplarily, the edge detection module 102 selects edge detection algorithms such as those based on Sobel operator, Prewitt operator, Laplacian operator, and Canny edge detection algorithm according to the image features and actual requirements of the target area, and then performs edge detection on the image data according to the edge detection algorithm to obtain the target edge information corresponding to the target area.

[0040] Exemplarily, the model reconstruction module 103 first extracts representative corner features from the image data using algorithms such as Harris corner detection, SIFT (Scale-Invariant Feature Transform), SURF (Speeded-Up Robust Features), etc., and then combines the existing target edge information to further extract feature points on the edge, such as curvature change points of the edge, etc., so as to generate feature descriptors for each extracted feature point. Then, the feature descriptors are matched between the image data from different perspectives, and the geometric constraint conditions (such as epipolar constraint) are used to screen the matching results to remove the wrong matching point pairs. After calibrating the internal and external parameters of the medical imaging sensor to obtain the calibration parameters, for the matched feature point pairs, the coordinates in the three-dimensional space are calculated using the principle of triangulation. And according to the calibration parameters, combined with the pixel coordinates of the feature points in different images, the coordinates of the three-dimensional points are obtained by solving the equations, so as to generate a three-dimensional point cloud, and then three-dimensional reconstruction is performed according to the three-dimensional point cloud to obtain the target three-dimensional model corresponding to the target area.

[0041] Exemplarily, the position acquisition module 104 performs target recognition on the target edge information to obtain the corresponding blood vessel position and tissue position in the target edge information, and then according to the mapping relationship between the target edge information and the target three-dimensional model, combines the blood vessel position to obtain the first position information corresponding to the initial blood vessel from the target three-dimensional model, and combines the tissue position to obtain the second position information corresponding to the target surrounding tissue from the target three-dimensional model.

[0042] Exemplarily, the position determination module 105 obtains the associated position information corresponding to the object to be resected from the image data, and then establishes a unified three-dimensional Cartesian coordinate system. For example, taking a certain fixed anatomical landmark point of the human body as the origin, the directions of the coordinate axes (such as the front-back, left-right, and up-down directions) are determined. The associated position information, the first position information, and the second position information are all transformed into this unified coordinate system and represented by coordinate points. Then, in the three-dimensional space, the distance from the initial surgical position to the object to be resected, the distances from the initial surgical position to each point on the initial blood vessel, and the distances from the initial surgical position to each point on the initial surrounding tissue are calculated. Thus, the optimization function is determined to include making the initial surgical position far from the initial blood vessel and the initial surrounding tissue and making the distance from the initial surgical position to the object to be resected within the normal surgical range. Then, the optimization function is solved according to the gradient descent method, genetic algorithm, simulated annealing algorithm, etc. to obtain the initial surgical position with the optimal value. The initial surgical position not only meets the requirement of being far from the initial blood vessel and the initial surrounding tissue but also ensures that the distance from it to the object to be resected is within the normal surgical range.

[0043] Exemplarily, the data acquisition module 106 obtains the first blood data corresponding to the initial blood vessel by using ultrasonic detection and accurately places the virtual model of the target robot at the initial surgical position. Then, according to the operation parameters and functions of the actual robot, the virtual robot is correspondingly set to ensure that its operation in the virtual environment is consistent with the actual situation. For example, parameters such as the movement range and operation force of the robot are set. Thus, in the virtual surgical environment, the target robot is controlled to perform virtual operations according to the preset surgical operation process. During the operation, the physical simulation engine in the virtual environment is used to calculate the dynamic changes of the blood in the initial blood vessel in real time, such as changes in blood flow rate and pressure. At the same time, through the simulation of virtual sensors, the second blood data corresponding to the initial blood vessel under virtual operation is collected.

[0044] Exemplarily, the state judgment module 107 calculates the data gap between the first blood data and the second blood data. Thus, when the data gap exceeds the preset range, it is determined that the target influence state on the initial blood vessel during the surgical operation at the initial surgical position is abnormal; when the data gap does not exceed the preset range, it is determined that the target influence state on the initial blood vessel during the surgical operation at the initial surgical position is normal.

[0045] Exemplarily, when the target influence state is normal, the result determination module 208 determines the first position information as the blood vessel positioning result. When the target influence state is abnormal, the first position information corresponding to the initial blood vessel is recalculated, and the target influence state is rejudged according to the recalculated first position information until the target influence state is normal. Then, the position information corresponding to the initial blood vessel in the target influence state is determined as the blood vessel positioning result.

[0046] In some embodiments, the edge detection module includes: a parameter calculation module configured to determine a first mapping function and a second mapping function, and calculate a corresponding target fuzzy parameter through fuzzy parameter calculation by combining the first mapping function and the second mapping function with the gray-level function corresponding to the image data; a coefficient calculation module configured to calculate a target contrast coefficient corresponding to the image data according to the first mapping function, the second mapping function, and the gray-level function by using a minimum offset criterion; an enhancement processing module configured to perform image enhancement on the image data according to the target contrast coefficient and the target fuzzy parameter to obtain a target enhanced image; a discrete processing module configured to convert the target enhanced image into a target discrete matrix according to the target gray level corresponding to each pixel value in the target enhanced image; a data determination module configured to determine a target window and determine a target membership degree corresponding to the image data according to the target window and the target discrete matrix; and an edge processing module configured to perform edge processing on the image data according to the target membership degree to obtain the target edge information corresponding to the target region.

[0047] Exemplarily, the parameter calculation module determines the first mapping function and the second mapping function by analyzing information such as the gray-level distribution of the image data. The first mapping function and the second mapping function can be regarded as a kind of rule for performing a certain transformation on the gray-level values of the image. By performing statistical analysis on a large number of similar images, the relationship between the gray-level values and certain features can be found, so as to determine a suitable mapping function. Then, after obtaining the mapping function, it is combined with the gray-level function corresponding to the image data. The gray-level function describes the gray-level value of each pixel in the image. Furthermore, after multiplying the first mapping function and the second mapping function and then subtracting the derivative of the gray-level function, a fuzzy parameter function corresponding to the image data is obtained. Then, each pixel in the image data is substituted into the fuzzy parameter function to obtain the target fuzzy parameter corresponding to each pixel.

[0048] Exemplarily, the coefficient calculation module first determines that the minimum offset criterion is that the gray-level value after being processed by the mapping function has the smallest deviation from a certain ideal state. Then, in combination with the first mapping function, the second mapping function, and the gray-level function, a target contrast function that can reflect the contrast situation of the image is calculated according to the minimum offset criterion. Thus, each pixel in the image data is substituted into the target contrast function to obtain the target contrast coefficient corresponding to each pixel.

[0049] Exemplarily, the enhancement processing module processes the image data according to the calculated target contrast coefficient and target fuzzy parameter. By adjusting the brightness, contrast, etc. of the image, the details and edge information in the image can be highlighted, thereby obtaining a target enhanced image.

[0050] Exemplarily, the discrete processing module analyzes the gray value of each pixel in the target enhanced image, divides it into different target gray levels, and thus organizes the target gray level information corresponding to each pixel in the target enhanced image into a matrix, namely the target discrete matrix.

[0051] Exemplarily, the data determination module selects a target window of a suitable size, and then slides the target window in the target discrete matrix to obtain the discrete data corresponding to the target window, and thus performs clustering analysis on the discrete data to obtain the target membership degree corresponding to each discrete data. The target membership degree can reflect the possibility that each pixel belongs to a specific region or edge.

[0052] Exemplarily, the edge processing module sets a suitable threshold, and determines the pixels with a target membership degree greater than the threshold as edge pixels according to the target membership degree, so as to obtain the target edge information corresponding to the target region.

[0053] Specifically, through image enhancement processing, the details and edge information in the image can be highlighted, making the image clearer. The calculation and processing of the blur parameter can reduce the blur effect in the image and improve the clarity and readability of the image. Thus, using the target membership degree for edge processing can more accurately extract the edge information in the image. Compared with traditional edge detection methods, this method considers more image features and information and can better adapt to different types of images.

[0054] In some embodiments, the data determination module includes: a matrix obtaining module, configured to slide the target window in the target discrete matrix to obtain the window discrete matrix corresponding to the target window; a first calculation module, configured to calculate the membership degree of each sub-data in the window discrete matrix to obtain the first value corresponding to the sub-data; a number determination module, configured to perform normalization processing on the first value to obtain the second value corresponding to the sub-data, and determine the loop number corresponding to the sub-data when calculating the membership degree in the window discrete matrix according to the second value; a second calculation module, configured to perform multiple membership degree calculations on each sub-data in the window discrete matrix according to the loop number to obtain the third value corresponding to the sub-data; and a data conversion module, configured to obtain the corresponding maximum value and minimum value from the third value, and perform membership degree conversion on the third value according to the maximum value and the minimum value to obtain the target membership degree corresponding to the image data.

[0055] Exemplarily, the matrix obtaining module performs a sliding operation on the target discrete matrix with a pre-determined target window, and then, as the target window slides, the target discrete matrix region covered each time forms a window discrete matrix.

[0056] Exemplarily, for each sub-data in the window discrete matrix (i.e., each element in the matrix), the first calculation module uses a specific membership degree calculation method to calculate its corresponding first value. The membership degree calculation method can be selected according to specific application scenarios and requirements. For example, it can be based on relevant theories of fuzzy mathematics and calculate the membership degree according to the similarity between the sub-data and certain preset criteria or features.

[0057] Exemplarily, the number determination module normalizes the first value obtained by the first calculation module and maps it to a specific range (usually [0, 1]) to obtain a second value. The purpose of normalization is to eliminate the dimensional differences between different first values, make them comparable, and then determine the number of cycles for each sub-data in the window discrete matrix when calculating the membership degree subsequently according to a certain rule based on the normalized second value. This rule can be a preset functional relationship. For example, the larger the second value, the more cycles correspond to it.

[0058] Exemplarily, the second calculation module performs multiple membership degree calculations on each sub-data in the window discrete matrix according to the number of cycles determined by the number determination module. Each calculation may be based on different conditions or parameters. Through multiple calculations, the membership characteristics of the sub-data can be considered more comprehensively, and finally, a third value corresponding to each sub-data is obtained.

[0059] Exemplarily, the data conversion module finds the maximum value and the minimum value from the third values obtained by the second calculation module. These two values represent the extreme cases of the membership degree of the sub-data. According to the maximum value and the minimum value, the third values are further processed and converted into the target membership degree that can reflect the overall characteristics of the image data.

[0060] Specifically, through multiple membership degree calculations (the second calculation module), more factors and situations are considered, avoiding the errors and one-sidedness that may be brought by single calculation. Multiple calculations can capture the membership characteristics of the sub-data more comprehensively, thus obtaining more accurate membership degree values. The normalization process (the number determination module) makes the membership degree calculation results of different sub-data comparable, and determining the number of cycles according to the normalized values can flexibly adjust the number of calculations according to the actual situation of the sub-data, further improving the calculation accuracy.

[0061] In some embodiments, the model reconstruction module includes: a feature extraction module for extracting feature points from a first image in the image data to obtain first feature information and extracting feature points from a second image in the image data to obtain second feature information; a feature matching module for performing feature matching based on the first feature information and the second feature information to obtain a target matching result; a parameter calibration module for calibrating the internal and external parameters of the medical imaging sensor based on the target matching result to obtain a target calibration result; a depth estimation module for performing depth estimation based on the target calibration result and the target matching result to obtain first point cloud data corresponding to the first image and second point cloud data corresponding to the second image; a fusion processing module for fusing the first point cloud data and the second point cloud data based on the target matching result to obtain target point cloud data; an initial reconstruction module for performing three-dimensional reconstruction on the image data based on the target point cloud data to obtain an initial three-dimensional model; an information extraction module for obtaining relevant point cloud data corresponding to the target edge information from the target point cloud data and obtaining target region information corresponding to the target edge information from the image data; a correction processing module for obtaining a relevant three-dimensional model corresponding to the relevant point cloud data from the initial three-dimensional model and performing color filling on the relevant three-dimensional model based on the target region information to obtain a corrected three-dimensional model corresponding to the relevant three-dimensional model; and a model optimization module for optimizing the initial three-dimensional model based on the corrected three-dimensional model to obtain the target three-dimensional model corresponding to the target region information.

[0062] Exemplarily, the feature extraction module analyzes the first image in the image data, and uses a feature extraction algorithm (such as SIFT, SURF, etc.) to find significant feature points in the image, such as corner points, edge points, etc. The information carried by these feature points constitutes the first feature information, and the second image in the image data is subjected to feature point extraction in the same manner to obtain the second feature information.

[0063] Exemplarily, the feature matching module compares the first feature information and the second feature information, and by comparing the descriptors of the feature points, finds the corresponding feature point pairs in the two images, and finally obtains the target matching result, which records the corresponding relationship of the feature points in the two images.

[0064] Exemplarily, the parameter calibration module calibrates the internal parameters (such as focal length, principal point position, etc.) and external parameters (such as rotation and translation parameters) of the medical imaging sensor based on the target matching result by using a specific calibration algorithm (such as Zhang Zhengyou calibration method), so as to obtain the target calibration result.

[0065] Exemplarily, the depth estimation module combines the target calibration result and the target matching result, and uses methods such as the triangulation principle to calculate the depth information corresponding to each matching feature point in the first image and the second image. By combining this depth information with the two-dimensional coordinates of the image, the first point cloud data corresponding to the first image and the second point cloud data corresponding to the second image can be obtained.

[0066] Exemplarily, the fusion processing module merges and aligns the first point cloud data and the second point cloud data according to the target matching result. Duplicate points are removed and missing information is supplemented to finally obtain a complete target point cloud data.

[0067] Exemplarily, the initial reconstruction module uses the target point cloud data and adopts 3D reconstruction algorithms (such as Poisson reconstruction, moving least squares method, etc.) to perform 3D reconstruction on the image data to construct an initial 3D model, which generally presents the approximate shape of the object as a whole.

[0068] Exemplarily, the information extraction module filters out the point cloud data corresponding to the target edge information from the target point cloud data, and these point cloud data represent the three-dimensional information of the object edge. The target area information corresponding to the target edge information is extracted from the image data. Thus, the correction processing module finds the corresponding part in the initial 3D model from the relevant point cloud data to obtain a relevant 3D model, and then fills the relevant 3D model with colors according to the target area information to simulate the color of the target area in the real scene, thereby obtaining a corrected 3D model, making the model more real and accurate.

[0069] Exemplarily, the model optimization module applies the corrected 3D model to the initial 3D model to adjust and optimize the initial 3D model, making the model more in line with the characteristics of the actual object as a whole, and finally obtaining the target 3D model corresponding to the target area information.

[0070] Specifically, the combination of the information extraction module and the correction processing module can obtain information such as the color of the target area from the image data and apply it to the 3D model for color filling and correction. This makes the reconstructed 3D model not only more accurate in shape but also more realistic visually.

[0071] In some embodiments, the correction processing module includes: an entropy value calculation module, configured to perform feature extraction on the relevant point cloud data to obtain third feature information corresponding to the relevant point cloud data, and calculate an entropy value of the relevant point cloud data to obtain a target entropy value; a region feature extraction module, configured to perform feature extraction on the target region information to obtain fourth feature information corresponding to the target region information; a weight calculation module, configured to determine weight information corresponding to each data dimension in the relevant point cloud data, and combine the weight information to obtain a weight component; a density calculation module, configured to obtain density information corresponding to each pixel point in the relevant point cloud data according to the third feature information, the target entropy value, in combination with the fourth feature information and the weight component; a quantity calculation module, configured to obtain the number of pixels corresponding to non-edge pixels under a target pixel point from the target region information; a parameter determination module, configured to obtain a pixel average value corresponding to the target pixel point, and obtain a pixel adjustment parameter corresponding to the edge pixel point under the target pixel point according to the pixel average value and the number of pixels; a filling determination module, configured to determine a filling adjustment parameter corresponding to color filling of the relevant three-dimensional model according to the pixel adjustment parameter and the density information; a color processing module, configured to perform color filling on the relevant three-dimensional model according to the filling adjustment parameter to obtain the corrected three-dimensional model corresponding to the relevant three-dimensional model; wherein, the filling adjustment parameter is obtained according to the following formula:

[0072]

[0073] Wherein, γ represents the filling adjustment parameter, abs represents taking the absolute value, v3 represents the third feature information, p represents the target entropy value, v4 represents the fourth feature information, w represents the weight component, pix mean represents the pixel average value corresponding to the target pixel point, count represents the number of pixels, and num represents the target number corresponding to the target pixel point.

[0074] Exemplarily, the entropy value calculation module performs feature extraction operations on the relevant point cloud data, and uses a suitable feature extraction algorithm (such as a geometric feature extraction algorithm) to obtain third feature information corresponding to the relevant point cloud data, and calculates an entropy value of the relevant point cloud data to obtain a target entropy value, which reflects the complexity of the relevant point cloud data.

[0075] Exemplarily, the region feature extraction module performs feature extraction on the target region information, and uses a method suitable for image region feature extraction (such as a texture feature extraction algorithm) to obtain fourth feature information corresponding to the target region information, and these features can reflect the texture, color distribution, etc. characteristics of the target region.

[0076] Exemplarily, the weight calculation module determines corresponding weight information for each data dimension of the relevant point cloud data. This can be set according to the importance of different dimensions for subsequent color filling, and then the weight information of each data dimension is combined to obtain a weight component, which is used in subsequent calculations to reflect the importance differences of information in different dimensions.

[0077] Exemplarily, the density calculation module subtracts the third feature information from the target entropy value, takes the absolute value, divides by the fourth feature information, and then divides by the weight component to obtain the density information corresponding to each pixel point in the relevant point cloud data. This density information can reflect the distribution density of pixel points in space.

[0078] Exemplarily, the quantity calculation module finds the target pixel points corresponding to a preset quantity from the target region information, and then counts the pixel quantity of the non-edge pixel points corresponding to the target pixel points. This quantity will be used in subsequent calculations of pixel adjustment parameters.

[0079] Exemplarily, the parameter determination module calculates the pixel average value corresponding to all target pixel points. This average value can reflect the overall pixel characteristics of the target pixel points. Then, the pixel adjustment parameter is obtained by multiplying the pixel average value by the pixel quantity and then dividing by the preset quantity.

[0080] Exemplarily, the filling determination module substitutes the pixel adjustment parameter and the density information into the following formula to calculate the filling adjustment parameter corresponding to the relevant three-dimensional model for color filling. This parameter comprehensively considers factors such as the characteristics of the point cloud data, the characteristics of the target region, and the pixel quantity, and is used to precisely control the color filling process:

[0081]

[0082] where γ represents the filling adjustment parameter, abs represents taking the absolute value, v3 represents the third feature information, p represents the target entropy value, v4 represents the fourth feature information, w represents the weight component, pix mean represents the pixel average value corresponding to the target pixel point, count represents the pixel quantity, num represents the target quantity corresponding to the target pixel point, and the target quantity is also the preset quantity.

[0083] Exemplarily, the color processing module performs a color filling operation on the relevant three-dimensional model according to the filling adjustment parameter. The color is filled using the image progressive filling algorithm according to the filling adjustment parameter to obtain the corrected three-dimensional model corresponding to the relevant three-dimensional model, making the color of the model more in line with the actual situation.

[0084] Specifically, through multi-faceted feature extraction and analysis of the relevant point cloud data and target area information, factors such as the geometric features of the point cloud, complexity, and texture features of the area are comprehensively considered, enabling the filling adjustment parameters to more accurately reflect the actual situation of the model. This helps to more precisely simulate the color distribution of the real scene during color filling, avoiding problems such as overfilling or underfilling of colors. The calculation of the pixel adjustment parameters combines the average value and the number of pixels of the target pixel point, and can adjust the color according to the specific situation of the target area, making the corrected 3D model more natural and realistic in color. In addition, the entire correction processing module can automatically calculate appropriate filling adjustment parameters according to different relevant point cloud data and target area information, with strong adaptability. For object models with different shapes and textures, effective color filling and correction can be performed through this method, improving the generality and flexibility of model processing.

[0085] In some embodiments, the state judgment module includes: a quantity determination module for performing clustering quantity analysis on the first blood data and the second blood data to obtain a target clustering quantity; a clustering analysis module for performing clustering analysis on the first blood data and the second blood data according to the target clustering quantity to obtain a target clustering result; and an anomaly analysis module for obtaining the cluster quantity corresponding to each first cluster cluster according to the target clustering result, and determining the target influence state on the initial blood vessel corresponding to the initial surgical position during surgical operation according to the cluster quantity.

[0086] Exemplarily, the quantity determination module uses a clustering quantity analysis method such as the silhouette coefficient method to evaluate the quality of clustering by calculating the silhouette coefficients of each first blood data and second blood data, and finds the clustering quantity that maximizes the silhouette coefficient as the target clustering quantity.

[0087] Exemplarily, based on the determined target clustering quantity, the clustering analysis module uses a clustering algorithm (such as K-means clustering, hierarchical clustering, etc.) to perform clustering analysis on the first blood data and the second blood data. Taking K-means clustering as an example, it randomly initializes K clustering centers (K is the target clustering quantity), then assigns each data point to the cluster where the nearest clustering center is located, and then recalculates the center of each cluster, and continuously iterates until the cluster centers no longer change significantly, finally obtaining the target clustering result, which contains the cluster information to which each data point belongs.

[0088] Exemplarily, the anomaly analysis module counts the number of data points in each first clustering cluster from the target clustering result to obtain the cluster number corresponding to each first clustering cluster. The target influence state on the initial blood vessel during the surgical operation at the initial surgical position is judged according to the cluster number. For example, if the cluster number of a certain cluster differs greatly from the expected number under normal circumstances, it may mean that the surgical operation has an abnormal influence on the blood vessel. For example, a blood vessel rupture causes a change in blood components, resulting in an increase or decrease in the number of data points in some clusters. Whether the cluster number is abnormal can be judged by a preset threshold, and then the target influence state, such as normal, mildly abnormal, severely abnormal, etc., can be determined.

[0089] Specifically, by performing clustering analysis on blood data, potential patterns and features can be mined from the data. Combining the analysis of the clustering number and the cluster number can more accurately judge the influence state of the surgical operation on the initial blood vessel. Compared with the evaluation of a single index, this multi-dimensional data mining and analysis method can provide more comprehensive and accurate information to help doctors timely discover problems that may occur during the operation.

[0090] In some embodiments, the quantity determination module includes: an initial clustering module for determining an initial clustering number and performing clustering analysis on the first blood data and the second blood data according to the initial clustering number to obtain an initial clustering result; a distance calculation module for obtaining the clustering center corresponding to each second clustering cluster in the initial clustering result and calculating the data distance between each sub-data in the second clustering cluster and the clustering center; an association calculation module for obtaining the association degree between each sub-data in the second clustering cluster and the clustering center according to the data distance; a quality calculation module for determining a clustering quality characterization value corresponding to the initial clustering number according to the association degree and the initial clustering result; and a quantity adjustment module for adjusting the initial clustering number according to the clustering quality characterization value to obtain the target clustering number.

[0091] Exemplarily, the initial clustering module initially determines a clustering number by using an empirical value or a simple trial method. For example, referring to the clustering number of previous similar blood data analyses, or estimating according to the general distribution of the data. Using the selected clustering algorithm k-means clustering, according to the determined initial clustering number, clustering operations are performed on the first blood data and the second blood data. This algorithm will divide the data into different clusters, and finally obtain an initial clustering result, which contains the cluster information to which each data point belongs.

[0092] Exemplarily, the distance calculation module determines the cluster center of each second cluster from the initial clustering result. For K-means clustering, the cluster center is the mean of the data points within each cluster. For the sub-data in each second cluster, the data distance between it and the cluster center of the cluster is calculated.

[0093] Exemplarily, the association calculation module determines the association degree between each sub-data in the second cluster and the cluster center according to the calculated data distance. Generally speaking, the smaller the data distance, the higher the association degree between the sub-data and the cluster center. Furthermore, the data distance is converted into an association degree through a mapping function, such as using an inverse proportion function, so that the distance and the association degree are in an inverse proportion relationship.

[0094] Exemplarily, the quality calculation module combines the association degree and the initial clustering result to comprehensively evaluate the clustering quality characterization value under the initial number of clusters. For example, by considering factors such as the sum of the association degrees of the data within each cluster and the separation degree between clusters. These factors are weighted and summed to obtain the clustering quality characterization value corresponding to the initial number of clusters. The higher this value, the better the clustering quality.

[0095] Exemplarily, the number adjustment module adjusts the initial number of clusters according to the clustering quality characterization value. If the clustering quality characterization value is low, it indicates that the current initial number of clusters may be inappropriate, and the number of clusters needs to be increased or decreased. It can be adjusted according to certain rules. For example, each time the number of clusters is increased or decreased by one, and the above-mentioned clustering analysis, distance calculation, association calculation, and quality calculation steps are repeated until the target number of clusters that makes the clustering quality characterization value reach the optimum is found.

[0096] Specifically, by continuously adjusting the number of clusters and evaluating the clustering quality, the most suitable number of clusters for blood data can be found, so that the clustering result can more accurately reflect the internal structure of the data. Accurate clustering helps to discover different patterns and features in blood data, providing a more reliable basis for subsequent blood vessel localization results.

[0097] Please refer to Figure 2 , Figure 2 A method for precise blood vessel localization using the inferior mesenteric artery priority method assisted by a robot provided by an embodiment of the present application, the method includes steps S201 to S208:

[0098] Step S201: Use a medical imaging sensor to collect image data corresponding to the target area of the target patient. The image data at least includes the object to be resected and the initial blood vessels and target surrounding tissues corresponding to the periphery of the object to be resected;

[0099] Step S202: Perform edge detection on the image data to obtain the target edge information corresponding to the target area;

[0100] Step S203: Perform 3D reconstruction based on the image data and the target edge information to obtain the target 3D model corresponding to the target area;

[0101] Step S204: Obtain the first position information corresponding to the initial blood vessel and the second position information corresponding to the target surrounding tissue from the target 3D model;

[0102] Step S205: Determine the initial surgical position corresponding to the target patient according to the first position information and the second position information;

[0103] Step S206: Obtain the first blood data corresponding to the initial blood vessel, and perform virtual operation on the target robot at the initial surgical position to obtain the second blood data corresponding to the initial blood vessel at the initial surgical position;

[0104] Step S207: Perform anomaly recognition according to the first blood data and the second blood data to obtain the target influence state corresponding to the initial blood vessel during surgical operation at the initial surgical position;

[0105] Step S208: Perform precise blood vessel positioning according to the target influence state in combination with the initial blood vessel and the first position information to obtain a blood vessel positioning result.

[0106] In some embodiments, the method for precise blood vessel positioning for the robotic-assisted membranous artery priority method can be applied to a terminal device.

[0107] It should be noted that those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working process of the method for precise blood vessel positioning for the robotic-assisted membranous artery priority method described above can refer to the corresponding process in the embodiment of the system for precise blood vessel positioning for the robotic-assisted membranous artery priority method described above, and will not be elaborated here.

[0108] Please refer to Figure 3 , Figure 3 which is a schematic block diagram of the structure of a terminal device provided by an embodiment of the present invention.

[0109] As Figure 3 shown, the terminal device 300 includes a processor 301 and a memory 302. The processor 301 and the memory 302 are connected through a bus 303, and this bus is, for example, an I2C (Inter-integrated Circuit) bus.

[0110] Specifically, the processor 301 is used to provide computing and control capabilities to support the operation of the entire terminal device. The processor 301 can be a central processing unit (CPU), and this processor 301 can also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor can be a microprocessor or this processor can also be any conventional processor, etc.

[0111] Specifically, the memory 302 can be a Flash chip, read-only memory (ROM), magnetic disk, optical disc, USB flash drive, or mobile hard disk, etc.

[0112] Those skilled in the art can understand that Figure 3 the structure shown in

[0113] is only a block diagram of some structures related to the solution of the embodiment of the present invention, and does not constitute a limitation on the terminal device to which the solution of the embodiment of the present invention is applied. A specific server may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0114] In an embodiment, the processor is used to run a computer program stored in the memory, and when executing the computer program, implement any one of the vascular precise positioning systems for the robot-assisted membranous artery priority method provided by the embodiments of the present invention.

[0115] An image acquisition module, configured to use a medical imaging sensor to acquire image data corresponding to a target area of a target patient, where the image data at least includes an object to be excised and the initial blood vessels and target surrounding tissues corresponding to the periphery of the object to be excised;

[0116] An edge detection module, configured to perform edge detection on the image data to obtain target edge information corresponding to the target area;

[0117] A model reconstruction module, configured to perform three-dimensional reconstruction based on the image data and the target edge information to obtain a target three-dimensional model corresponding to the target area;

[0118] An acquisition position module, configured to acquire first position information corresponding to the initial blood vessel and second position information corresponding to the target surrounding tissue from the target three-dimensional model;

[0119] A position determination module, configured to determine an initial surgical position corresponding to the target patient according to the first position information and the second position information;

[0120] A data acquisition module, configured to acquire first blood data corresponding to the initial blood vessel, and to acquire second blood data corresponding to the initial blood vessel at the initial surgical position by performing virtual operations on a target robot at the initial surgical position;

[0121] A status judgment module, configured to perform anomaly recognition according to the first blood data and the second blood data to obtain a target influence status corresponding to the initial blood vessel during surgical operations at the initial surgical position;

[0122] A result determination module, configured to perform precise blood vessel positioning according to the target influence status in combination with the initial blood vessel and the first position information to obtain a blood vessel positioning result.

[0123] It should be noted that those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described terminal device can refer to the corresponding process in the embodiment of the blood vessel precise positioning system for the robot-assisted membranous artery priority method described above, and will not be elaborated here.

[0124] The embodiment of the present invention further provides a storage medium for computer-readable storage. The storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of any blood vessel precise positioning system for the robot-assisted membranous artery priority method provided in the specification of the embodiment of the present invention.

[0125] Wherein, the storage medium may be an internal storage unit of the terminal device described in the foregoing embodiment, such as the hard disk or memory of the terminal device. The storage medium may also be an external storage device of the terminal device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal device.

[0126] Those of ordinary skill in the art can understand that all or some of the steps in the methods disclosed above, and the functional modules / units in systems and devices, can be implemented as software, firmware, hardware, and appropriate combinations thereof. In a hardware embodiment, the division of functional modules / units mentioned above does not necessarily correspond to the division of physical components; for example, a physical component can have multiple functions, or a function or step can be executed by several physical components working together. Some or all physical components can be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include a computer storage medium (or non-transitory medium) and a communication medium (or transitory medium). As is well known to those of ordinary skill in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable instructions, data structures, program modules, or other data. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cassette, tape, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, as is well known to those of ordinary skill in the art, a communication medium typically contains computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transmission mechanism, and can include any information delivery medium.

[0127] It should be understood that the term "and / or" used in the specification and appended claims of the present invention refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations. It should be noted that in this text, the term "comprising", "including", or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article, or system including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article, or system. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article, or system including that element.

[0128] The serial numbers of the embodiments of the present invention above are only for description and do not represent the superiority or inferiority of the embodiments. The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A robot-assisted vascular precise positioning system using the membrane artery priority method, characterized in that: The system comprises: An image acquisition module, used to acquire image data corresponding to a target area of ​​a target patient using a medical image sensor, wherein the image data at least includes an object to be resected and initial blood vessels and target surrounding tissues corresponding to the surrounding area of ​​the object to be resected; An edge detection module, used for performing edge detection on the image data to obtain target edge information corresponding to the target area; A model reconstruction module, used for performing three-dimensional reconstruction according to the image data and the target edge information to obtain a target three-dimensional model corresponding to the target area; A position acquisition module, used for acquiring first position information corresponding to the initial blood vessel and second position information corresponding to the target surrounding tissue from the target three-dimensional model; A position determination module, configured to determine an initial surgical position corresponding to the target patient according to the first position information and the second position information; a data acquisition module, configured to obtain first blood data corresponding to the initial blood vessel, and to obtain second blood data corresponding to the initial blood vessel at the initial surgical position by performing a virtual operation on the target robot at the initial surgical position; A state judgment module, configured to perform abnormality recognition according to the first blood data and the second blood data to obtain a target impact state corresponding to the initial blood vessel when performing a surgical operation at the initial surgical position; A result determination module is used to accurately locate the blood vessel according to the target impact state in combination with the initial blood vessel and the first position information to obtain a blood vessel positioning result.

2. The system according to claim 1, characterized in that The edge detection module comprises: a parameter calculation module, used to determine a first mapping function and a second mapping function, and to perform fuzzy parameter calculation according to the first mapping function and the second mapping function in combination with a grayscale function corresponding to the image data to obtain corresponding target fuzzy parameters; A coefficient calculation module, used for calculating a target contrast coefficient corresponding to the image data by using a minimum deviation criterion according to the first mapping function and the second mapping function in combination with the grayscale function; An enhancement processing module, used for performing image enhancement on the image data according to the target contrast coefficient and the target blur parameter to obtain a target enhanced image; A discrete processing module, used for converting the target enhanced image into a target discrete matrix according to a target grayscale corresponding to each pixel value in the target enhanced image; A data determination module, used to determine a target window, and determine a target membership corresponding to the image data according to the target window and the target discrete matrix; The edge processing module is used to perform edge processing on the image data according to the target membership to obtain the target edge information corresponding to the target area.

3. The system according to claim 2, characterized in that The data determination module comprises: A matrix obtaining module, used for sliding the target window in the target discrete matrix to obtain a window discrete matrix corresponding to the target window; A first calculation module, used for calculating the degree of membership of each sub-data in the window discrete matrix to obtain a first value corresponding to the sub-data; A number determination module, used for performing normalization processing on the first value to obtain a second value corresponding to the sub-data, and determining the number of cycles corresponding to the sub-data in the window discrete matrix when calculating the membership degree according to the second value; A second calculation module, configured to perform multiple membership calculations on each of the sub-data in the window discrete matrix according to the number of cycles to obtain a third value corresponding to the sub-data; A data conversion module is used to obtain a corresponding maximum value and a corresponding minimum value from the third value, and perform membership conversion on the third value according to the maximum value and the minimum value to obtain the target membership corresponding to the image data.

4. The system according to claim 1, characterized in that The model reconstruction module comprises: A feature extraction module, configured to extract feature points from a first image in the image data to obtain first feature information and to extract feature points from a second image in the image data to obtain second feature information; A feature matching module, used for performing feature matching according to the first feature information and the second feature information to obtain a target matching result; A parameter calibration module, used for performing internal and external parameter calibration on the medical image sensor according to the target matching result to obtain a target calibration result; A depth estimation module, configured to perform depth estimation according to the target calibration result and the target matching result to obtain first point cloud data corresponding to the first image and second point cloud data corresponding to the second image; A fusion processing module, used for fusing the first point cloud data and the second point cloud data according to the target matching result to obtain target point cloud data; An initial reconstruction module, used for performing three-dimensional reconstruction on the image data according to the target point cloud data to obtain an initial three-dimensional model; An information extraction module, used to obtain relevant point cloud data corresponding to the target edge information from the target point cloud data and to obtain target area information corresponding to the target edge information from the image data; A correction processing module, used for obtaining a related three-dimensional model corresponding to the related point cloud data from the initial three-dimensional model, and filling the related three-dimensional model with color according to the target area information to obtain a corrected three-dimensional model corresponding to the related three-dimensional model; The model optimization module is used to optimize the initial three-dimensional model according to the modified three-dimensional model to obtain the target three-dimensional model corresponding to the target area information.

5. The system according to claim 4, characterized in that The correction processing module comprises: an entropy value calculation module, used for performing feature extraction on the relevant point cloud data to obtain third feature information corresponding to the relevant point cloud data, and performing entropy value calculation on the relevant point cloud data to obtain a target entropy value; A region feature extraction module, used for performing feature extraction on the target region information to obtain fourth feature information corresponding to the target region information; A weight calculation module, used to determine the weight information corresponding to each data dimension in the relevant point cloud data, and obtain the weight component according to the weight information combination; A density calculation module, used for obtaining density information corresponding to each pixel in the relevant point cloud data according to the third feature information, the target entropy value, the fourth feature information and the weight component; A quantity calculation module, used for obtaining the number of pixels corresponding to the non-edge pixel points under the target pixel point from the target area information; A parameter determination module, used to obtain a pixel average value corresponding to the target pixel point, and obtain a pixel adjustment parameter corresponding to an edge pixel point corresponding to the target pixel point according to the pixel average value and the number of pixels; A filling determination module, used to determine the corresponding filling adjustment parameters when the relevant three-dimensional model is filled with color according to the pixel adjustment parameters and the density information; A color processing module, used to fill the relevant three-dimensional model with color according to the filling adjustment parameter to obtain the modified three-dimensional model corresponding to the relevant three-dimensional model; The filling adjustment parameter is obtained according to the following formula: Wherein, γ represents the filling adjustment parameter, abs represents the absolute value, v3 represents the third feature information, p represents the target entropy value, v4 represents the fourth feature information, w represents the weight component, and pix mean represents the pixel average value corresponding to the target pixel point, count represents the number of pixels, and num represents the target number corresponding to the target pixel point.

6. The system according to claim 1, characterized in that The state judgment module comprises: a quantity determination module, configured to perform cluster quantity analysis on the first blood data and the second blood data to obtain a target cluster quantity; A cluster analysis module, used for performing cluster analysis on the first blood data and the second blood data according to the target cluster quantity to obtain a target cluster result; An abnormal analysis module is used to obtain the number of clusters corresponding to each first cluster cluster according to the target clustering result, and determine the target impact state corresponding to the initial blood vessel when the surgical operation is performed at the initial surgical position according to the number of clusters.

7. The system according to claim 6, characterized in that The quantity determination module comprises: an initial clustering module, used to determine the initial clustering number, and perform cluster analysis on the first blood data and the second blood data according to the initial clustering number to obtain an initial clustering result; A distance calculation module, used to obtain the cluster center corresponding to each second cluster in the initial clustering result, and calculate the data distance between each sub-data in the second cluster and the cluster center; An association calculation module, used for obtaining the association degree between each sub-data in the second cluster and the cluster center according to the data distance; A quality calculation module, used to determine a cluster quality representation value corresponding to the initial cluster quantity according to the association degree and the initial clustering result; The quantity adjustment module is used to adjust the initial number of clusters according to the cluster quality characterization value to obtain the target number of clusters.

8. A method for accurate vascular positioning using a robot-assisted membranous artery priority method, characterized in that: include: Using a medical imaging sensor to collect image data corresponding to a target area of ​​a target patient, the image data at least including an object to be resected and initial blood vessels and target surrounding tissues corresponding to the surrounding area of ​​the object to be resected; Performing edge detection on the image data to obtain target edge information corresponding to the target area; Performing three-dimensional reconstruction according to the image data and the target edge information to obtain a target three-dimensional model corresponding to the target area; Obtaining first position information corresponding to the initial blood vessel and second position information corresponding to the target surrounding tissue from the target three-dimensional model; determining an initial surgical position corresponding to the target patient according to the first position information and the second position information; Obtaining first blood data corresponding to the initial blood vessel, and performing a virtual operation on the target robot at the initial surgical position to obtain second blood data corresponding to the initial blood vessel at the initial surgical position; Performing abnormality identification according to the first blood data and the second blood data to obtain a target impact state corresponding to the initial blood vessel when performing a surgical operation at the initial surgical position; The blood vessel is accurately positioned according to the target impact state in combination with the initial blood vessel and the first position information to obtain a blood vessel positioning result.

9. A terminal device, characterized in that: The terminal device includes a processor and a memory; The memory is used to store computer programs; The processor is used to execute the computer program and implement the blood vessel precise positioning system for the robot-assisted inferior medullary artery priority method according to any one of claims 1 to 7 when executing the computer program.

10. A computer storage medium for computer storage, characterized in that: The computer storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of the vascular precise positioning system for the robot-assisted inferior membranous artery priority method as described in any one of claims 1 to 7.

Images