A CT image blood vessel reconstruction method using a region growing method

Abstract

The application discloses a CT image blood vessel reconstruction method adopting a region growing method, relates to the field of blood vessel reconstruction, acquires a CT image of a target part through a CT image acquisition step, pre-processes the CT image through an image pre-processing step to obtain a processable CT image, and finally reconstructs blood vessels through a seed point selection step, a region growing analysis step, a region judgment step and a blood vessel reconstruction step, so that the accuracy of blood vessel reconstruction is greatly improved, the work efficiency of blood vessel reconstruction is further improved, the medical development in the field of blood vessel reconstruction is promoted, the blood vessel region is reanalyzed through a region stopping judgment step, the labeling of the blood vessel region before blood vessel reconstruction is more perfect and specific, the accuracy and the integrity of the blood vessel reconstruction result are improved, the probability of medical accidents is reduced, and the life and property safety of patients are ensured.

Description

Technical Field

[0001] This application relates to the field of vascular reconstruction, and in particular to a vascular reconstruction method for CT images using a region growing approach. Background Technology

[0002] With social progress and the rapid development of science and technology, medical and health technologies have also made great strides, and people's health levels have improved significantly. However, there are still the following shortcomings in vascular reconstruction technology for vascular diseases.

[0003] Current technologies for vascular reconstruction at diseased sites typically rely on medical staff's experience to complete the reconstruction, which increases the inaccuracy of the results, reduces the efficiency of the procedure, and hinders the development of the field. Furthermore, existing technologies only perform a single, one-way analysis of the vascular region without considering its regeneration, resulting in incomplete reconstruction outcomes, increasing the risk of medical accidents, and threatening patients' lives and property. Summary of the Invention

[0004] The purpose of this invention is to provide a CT image vascular reconstruction method using region growing, in order to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, this application provides a CT image vascular reconstruction method using region growing, comprising:

[0006] CT image acquisition steps: to acquire CT images of the target area, thus obtaining the CT image of the target area;

[0007] Image preprocessing steps: used to preprocess the CT images of the target area to obtain a processable CT image of the target area;

[0008] Seed point selection step: Used to select blood vessel seed points in the processable CT image of the target area;

[0009] Region growth analysis step: used to analyze the vascular seed points and neighboring pixels in the processable CT image of the target area to obtain the quasi-vascular region;

[0010] Region stopping judgment step: used to analyze and judge whether the quasi-vascular region of the target site can grow, and to obtain the vascular region of the target site;

[0011] Vascular reconstruction steps: Used to reconstruct blood vessels in the target area, resulting in a vascular model of the target area.

[0012] Database: Used to store standard irradiation methods for CT images of various parts, standard CT image contour models corresponding to various parts, gray values ​​of optimal seed points of blood vessels and gray weights of optimal sub-regions corresponding to optimal seed points of blood vessels, and upper and lower threshold values ​​of gray values ​​of pixel points of blood vessels corresponding to various parts.

[0013] In the preferred embodiment of this application, the CT image acquisition step specifically includes the following sub-steps:

[0014] Establish the data extraction relationship between the CT image acquisition steps and the database, extract the standard irradiation methods of CT images for each body part stored in the database, and select the corresponding standard irradiation methods of CT images based on the target body part;

[0015] The target area is irradiated using a vascular reconstruction device and a standard irradiation method corresponding to the selected target area to obtain a CT image of the target area.

[0016] In a preferred embodiment of this application, the image preprocessing step specifically includes the following sub-steps:

[0017] Establish the data extraction relationship between the image preprocessing steps and the database, extract the standard CT image contour models corresponding to each part stored in the database, and filter the corresponding standard CT image contour models by the target part;

[0018] A high-precision contour scanner is used to perform high-precision scanning on the CT image of the target area to obtain the CT image contour model of the target area. The CT image contour model of the target area is then compared with the standard CT image contour model corresponding to the target area to obtain the similarity Q between the CT image contour model of the target area and the standard CT image contour model corresponding to the target area.

[0019] Based on the similarity Q between the CT image contour model of the target area and the standard CT image contour model corresponding to the target area, the CT image of the target area is transformed accordingly to obtain a processable CT image of the target area.

[0020] In a preferred embodiment of this application, the seed point selection step can handle the grayscale weight analysis step for each sub-region in the CT image, specifically including the following sub-steps:

[0021] The processable CT image of the target area is divided into sub-regions in the processable CT image using a preset method;

[0022] Filter and label the grayscale values ​​of each pixel in each sub-region of a processable CT image. Where i represents the number of each sub-region in the processable CT image, i = 1, 2, ..., k, and j represents the pixel number corresponding to each sub-region in the processable CT image, j = 1, 2, ..., p;

[0023] This can process the grayscale values ​​of each pixel in each sub-region of a CT image. Substitute into the formula, Obtain the grayscale weights w of each sub-region in the processable CT image. i , where α represents the preset weighting influence factor.

[0024] In a preferred embodiment of this application, the seed point selection step can handle the vascular seed point analysis step in CT images, specifically including the following sub-steps:

[0025] Establish the data extraction relationship between the seed point selection step and the database, and extract the gray values ​​of the optimal seed points of blood vessels in the processable CT images of each part stored in the database, as well as the gray weight values ​​of the optimal sub-regions corresponding to the optimal seed points of blood vessels in each part.

[0026] Based on the target location, the optimal seed point grayscale value of blood vessels in CT images can be selected for processing. The grayscale weights of the optimal sub-region corresponding to the optimal seed point of the blood vessel

[0027] Based on the target location, the grayscale weights w of each sub-region in the CT image can be processed. i The grayscale weights of the optimal sub-region corresponding to the optimal seed point of the blood vessel Comparative analysis was conducted to select the optimal sub-region corresponding to the optimal seed point of blood vessels in the processable CT image for locating the target area. This was achieved by analyzing the gray values ​​of each pixel within the optimal sub-region of blood vessels in the processable CT image. Gray value of the optimal seed point of the blood vessel Comparative analysis was conducted to compare the gray values ​​of each pixel in the optimal sub-region corresponding to the optimal seed point of the blood vessel in the processable CT image. Gray value of the optimal seed point of the blood vessel The closest pixel is recorded as the target location, which can be used to process blood vessel seed points in CT images.

[0028] In the preferred embodiment of this application, the regional growth analysis step specifically includes the following sub-steps:

[0029] Establish the data extraction relationship between the database and the regional growth analysis steps, extract the upper and lower threshold values ​​of the grayscale values ​​of blood vessel pixels corresponding to each location, and filter the upper threshold H of the grayscale values ​​of blood vessel pixels corresponding to the target location. 上 and lower limit threshold H 下 ;

[0030] Each pixel in the processable CT image of the target area is classified according to its distance from the blood vessel seed point in the processable CT image of the target area, and divided into first level, second level, ..., nth level;

[0031] The grayscale value of each pixel at each level is sequentially compared with the upper limit threshold H of the grayscale value of the corresponding blood vessel pixel in the target area. 上 and lower limit threshold H 下 Comparative analysis was conducted, and the grayscale values ​​of each pixel in each level were compared within (H). 下 H 上 The pixels in the interval are sequentially recorded as the corresponding blood vessel pixels of the target part, and the area where the corresponding blood vessel pixels of the target part are located is recorded as the quasi-blood vessel area.

[0032] In a preferred embodiment of this application, the gradient analysis step for the changes of each reference pixel and blood vessel seed point in the region stopping determination step specifically includes the following sub-steps:

[0033] Each pixel in the non-quasi-vascular region and the adjacent non-quasi-vascular region is recorded as a reference pixel.

[0034] The grayscale values ​​and levels of each reference pixel are statistically analyzed and filtered, and each reference pixel is marked as... Where n represents the level of the reference pixel, n = 1, 2, ... u, and m represents the arrangement number of the reference pixels according to a preset order, m = 1, 2, ..., q;

[0035] Each reference pixel Substitute into the formula The gradient of changes between each reference pixel and the blood vessel seed point is obtained. Let denot be the gradient of each reference pixel, where β represents the preset gradient change influence factor.

[0036] In the preferred embodiment of this application, the target site vascular region analysis step in the region stopping determination step specifically includes the following sub-steps:

[0037] The gradient of each reference pixel is compared with the preset standard gradient of the reference pixel. If the gradient of the reference pixel is less than the preset standard gradient, it means that the reference pixel meets the corresponding requirements and the area where the reference pixel is located is classified into the blood vessel region. If the gradient of the reference pixel is greater than the preset standard gradient, it means that the reference pixel does not meet the corresponding requirements and the area where the reference pixel is located is not classified into the blood vessel region. The blood vessel region of the target site is obtained by summarizing the above analysis.

[0038] In a preferred embodiment of this application, the vascular reconstruction step specifically includes the following sub-steps:

[0039] The vascular reconstruction device is used to reconstruct the vascular region of the target site, thereby obtaining a vascular model of the target site's vascular region.

[0040] In summary, this application includes at least one of the following beneficial technical effects:

[0041] This invention acquires CT images of the target area through a CT image acquisition step, then preprocesses the CT images to obtain processable CT images through an image preprocessing step, and finally reconstructs blood vessels through a seed point selection step, a region growth analysis step, a region judgment step, and a blood vessel reconstruction step. This greatly improves the accuracy of blood vessel reconstruction, further enhances the efficiency of blood vessel reconstruction, and promotes the medical development in the field of blood vessel reconstruction.

[0042] This invention uses a region-stop judgment step to reanalyze the already confirmed vascular regions, making the labeling of vascular regions more complete and specific before vascular reconstruction. This improves the accuracy and completeness of vascular reconstruction results, reduces the probability of medical accidents, and protects the life and property safety of patients. Attached Figure Description

[0043] The present invention will be further described with reference to the accompanying drawings, but the embodiments in the drawings do not constitute any limitation on the present invention. For those skilled in the art, other drawings can be obtained based on the following drawings without creative effort.

[0044] Figure 1 This is a schematic diagram illustrating the connection steps of the present invention. Detailed Implementation

[0045] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0046] Please see Figure 1 The present invention provides a technical solution: an automatic image capture system for a video surveillance platform, including a CT image acquisition step, an image preprocessing step, a seed point selection step, a region growth analysis step, a region stopping judgment step, a blood vessel reconstruction step, and a database.

[0047] The CT image acquisition step is connected to the image preprocessing step; the image preprocessing step is connected to the seed point selection step and the database; the seed point selection step is connected to the region growth analysis step and the database; the region growth analysis step is connected to the region stopping judgment step and the database; and the region stopping judgment step is connected to the vascular reconstruction step.

[0048] The CT image acquisition step is used to acquire CT images of the target area to obtain CT images of the target area;

[0049] Furthermore, the CT image acquisition process specifically includes the following sub-steps:

[0050] Establish the data extraction relationship between the CT image acquisition steps and the database, extract the standard irradiation methods of CT images for each body part stored in the database, and select the corresponding standard irradiation methods of CT images based on the target body part;

[0051] The target area is irradiated using a vascular reconstruction device and a standard irradiation method corresponding to the selected target area to obtain a CT image of the target area.

[0052] The image preprocessing step is used to preprocess the CT image of the target area to obtain a processable CT image of the target area;

[0053] Further, the image preprocessing steps specifically include the following sub-steps:

[0054] Establish the data extraction relationship between the image preprocessing steps and the database, extract the standard CT image contour models corresponding to each part stored in the database, and filter the corresponding standard CT image contour models by the target part;

[0055] A high-precision contour scanner is used to perform high-precision scanning on the CT image of the target area to obtain the CT image contour model of the target area. The CT image contour model of the target area is then compared with the standard CT image contour model corresponding to the target area to obtain the similarity Q between the CT image contour model of the target area and the standard CT image contour model corresponding to the target area.

[0056] Based on the similarity Q between the CT image contour model of the target area and the standard CT image contour model corresponding to the target area, the CT image of the target area is transformed accordingly to obtain a processable CT image of the target area.

[0057] The seed point selection step is used to select blood vessel seed points in the processable CT images of the target area;

[0058] Furthermore, the seed point selection step can handle the grayscale weight analysis of each sub-region in the CT image, specifically including the following sub-steps:

[0059] The processable CT image of the target area is divided into sub-regions in the processable CT image using a preset method;

[0060] Filter and label the grayscale values ​​of each pixel in each sub-region of a processable CT image. Where i represents the number of each sub-region in the processable CT image, i = 1, 2, ..., k, and j represents the pixel number corresponding to each sub-region in the processable CT image, j = 1, 2, ..., p;

[0061] This can process the grayscale values ​​of each pixel in each sub-region of a CT image. Substitute into the formula, Obtain the grayscale weights w of each sub-region in the processable CT image. i , where α represents the preset weighting influence factor;

[0062] The formula can handle the grayscale weights w of each sub-region in a CT image. i The gray values ​​of each pixel corresponding to each sub-region in the processable CT image It shows a positive correlation and can process the gray values ​​of each pixel corresponding to each sub-region in CT images. The larger the value, the higher the grayscale weight w of the corresponding sub-region in the CT image that can be processed. i The larger.

[0063] Furthermore, the seed point selection step can handle the vascular seed point analysis step in CT images, specifically including the following sub-steps:

[0064] Establish the data extraction relationship between the seed point selection step and the database, and extract the gray values ​​of the optimal seed points of blood vessels in the processable CT images of each part stored in the database, as well as the gray weight values ​​of the optimal sub-regions corresponding to the optimal seed points of blood vessels in each part.

[0065] Based on the target location, the optimal seed point grayscale value of blood vessels in CT images can be selected for processing. The grayscale weights of the optimal sub-region corresponding to the optimal seed point of the blood vessel

[0066] Based on the target location, the grayscale weights w of each sub-region in the CT image can be processed. i The grayscale weights of the optimal sub-region corresponding to the optimal seed point of the blood vessel Comparative analysis was conducted to select the optimal sub-region corresponding to the optimal seed point of blood vessels in the processable CT image for locating the target area. This was achieved by analyzing the gray values ​​of each pixel within the optimal sub-region of blood vessels in the processable CT image. Gray value of the optimal seed point of the blood vessel Comparative analysis was conducted to compare the gray values ​​of each pixel in the optimal sub-region corresponding to the optimal seed point of the blood vessel in the processable CT image. Gray value of the optimal seed point of the blood vessel The closest pixel is recorded as the target location, which can be used to process blood vessel seed points in CT images.

[0067] The region growth analysis step is used to analyze the vascular seed points and neighboring pixels in the processable CT images of the target area to obtain the quasi-vascular region.

[0068] Further, the regional growth analysis step specifically includes the following sub-steps:

[0069] Establish the data extraction relationship between the database and the regional growth analysis steps, extract the upper and lower threshold values ​​of the grayscale values ​​of blood vessel pixels corresponding to each location, and filter the upper threshold H of the grayscale values ​​of blood vessel pixels corresponding to the target location. 上 and lower limit threshold H 下 ;

[0070] Each pixel in the processable CT image of the target area is classified according to its distance from the blood vessel seed point in the processable CT image of the target area, and divided into first level, second level, ..., nth level;

[0071] The grayscale value of each pixel at each level is sequentially compared with the upper limit threshold H of the grayscale value of the corresponding blood vessel pixel in the target area. 上 and lower limit threshold H 下 Comparative analysis was conducted, and the grayscale values ​​of each pixel in each level were compared within (H). 下 H 上 The pixels in the interval are sequentially recorded as the corresponding blood vessel pixels of the target part, and the area where the corresponding blood vessel pixels of the target part are located is recorded as the quasi-blood vessel area.

[0072] The region cessation judgment step is used to analyze and judge whether the quasi-vascular region of the target site can grow, and to obtain the vascular region of the target site;

[0073] Furthermore, the gradient analysis step for the changes of each reference pixel and blood vessel seed point in the region stopping determination step specifically includes the following sub-steps:

[0074] Each pixel in the non-quasi-vascular region and the adjacent non-quasi-vascular region is recorded as a reference pixel.

[0075] The grayscale values ​​and levels of each reference pixel are statistically analyzed and filtered, and each reference pixel is marked as... Where n represents the level of the reference pixel, n = 1, 2, ... u, and m represents the arrangement number of the reference pixels according to a preset order, m = 1, 2, ..., q;

[0076] Each reference pixel Substitute into the formula The gradient of changes between each reference pixel and the blood vessel seed point is obtained. Let β be the gradient of each reference pixel, where β represents the preset gradient influence factor.

[0077] In the formula, the higher the level number of each reference pixel, the closer the gray value of each reference pixel is to the gray value of the optimal seed point of blood vessels in the processable CT image. The smaller the difference between them, the more likely each reference pixel is to be a pixel within the blood vessel region.

[0078] Furthermore, the target site vascular region analysis step in the region stopping judgment step specifically includes the following sub-steps:

[0079] The gradient of each reference pixel is compared with the preset standard gradient of the reference pixel. If the gradient of the reference pixel is less than the preset standard gradient, it means that the reference pixel meets the corresponding requirements and the area where the reference pixel is located is classified into the blood vessel region. If the gradient of the reference pixel is greater than the preset standard gradient, it means that the reference pixel does not meet the corresponding requirements and the area where the reference pixel is located is not classified into the blood vessel region. The blood vessel region of the target site is obtained by summarizing the above analysis.

[0080] The vascular reconstruction step is used to reconstruct blood vessels in the target area, thereby obtaining a vascular model of the target area.

[0081] Further, the vascular reconstruction steps specifically include the following sub-steps:

[0082] The vascular reconstruction device is used to reconstruct the vascular region of the target site, thereby obtaining a vascular model of the target site's vascular region.

[0083] The database is used to store the standard irradiation methods for CT images of various body parts, the standard CT image contour models corresponding to each body part, the gray values ​​of the optimal seed points of blood vessels and the gray weights of the optimal sub-regions corresponding to the optimal seed points of blood vessels, and the upper and lower threshold values ​​of the gray values ​​of the corresponding blood vessel pixels for each body part.

[0084] The above are all preferred embodiments of this application, and are not intended to limit the scope of protection of this application. Therefore, all equivalent changes made in accordance with the structure, shape and principle of this application should be covered within the scope of protection of this application.

Claims

1. A CT image blood vessel reconstruction method using a region growing method, characterized by: The method comprises the following steps: a CT image acquisition step: collecting a CT image of a target part based on a standard irradiation method of the CT image of each part stored in a database, to obtain the CT image of the target part; an image preprocessing step: preprocessing the CT image of the target part based on a standard CT image contour model corresponding to each part stored in the database, to obtain a processable CT image of the target part; a seed point selection step: selecting a blood vessel seed point in the processable CT image of the target part; The seed point selection step comprises a gray weight analysis step of processing each sub-region in the CT image, specifically comprising the following sub-steps: The processable CT image of the target part is divided into each sub-region in the processable CT image by a predetermined method; Screening and marking the gray scale value of each pixel point corresponding to each sub-region in the processable CT image , wherein is expressed as the number of each sub-region in the processable CT image, , is expressed as the number of each pixel point corresponding to the sub-region in the processable CT image, ; The gray scale values of each pixel point in each sub-region in the processable CT image are obtained Substituting the formula, The gray scale weight of each sub-region in the processable CT image is obtained Wherein is a preset weight influence factor The seed point selection step further comprises a blood vessel seed point analysis step in the CT image, specifically comprising the following sub-steps: establishing a data extraction relationship between the seed point selection step and the database, and extracting the gray value of the optimal seed point of the blood vessel in the processable CT image of each part stored in the database and the gray weight of the optimal sub-region corresponding to the optimal seed point of the blood vessel of each part; According to the target site, the gray value of the optimal seed point of the blood vessel in the CT image is screened and the gray weight of the optimal sub-region corresponding to the optimal seed point of the blood vessel ; According to the target site, the gray weight of each sub-region in the processable CT image is processed The gray weight of the optimal sub-region corresponding to the optimal seed point of the blood vessel Through comparative analysis, the optimal sub-region corresponding to the optimal seed point of the blood vessel in the processable CT image of the positioning target site is screened, and the gray value of each pixel point in the optimal sub-region of the blood vessel in the processable CT image is compared with the gray value of the optimal seed point of the blood vessel The gray value of each pixel point in the optimal sub-region corresponding to the optimal seed point of the blood vessel in the processable CT image is compared with the gray value of the optimal seed point of the blood vessel The gray value of each pixel point in the optimal sub-region corresponding to the optimal seed point of the blood vessel in the processable CT image is compared with the gray value of the optimal seed point of the blood vessel The gray value of each pixel point in the optimal sub-region corresponding to the optimal seed point of the blood vessel in the processable CT image is compared with the gray value of the optimal seed point of the blood vessel The pixel point closest to the optimal seed point of the blood vessel is recorded as the target site processable CT image of the blood vessel seed point a region growing analysis step: analyzing the blood vessel seed point and the adjacent pixel point in the processable CT image of the target part based on the upper threshold and the lower threshold of the gray value of the blood vessel pixel point corresponding to each part, to obtain a quasi-blood vessel region; a region stopping judgment step: analyzing and judging whether the quasi-blood vessel region of the target part can grow, to obtain the blood vessel region of the target part; The change gradient analysis step of each referenceable pixel point and the blood vessel seed point in the region stopping judgment step, specifically comprising the following sub-steps: Each pixel point in the non-quasi-blood vessel region adjacent to the quasi-blood vessel region is recorded as each referenceable pixel point; The statistical and screened reference pixel points are marked as , wherein n represents the level of the reference pixel point, , and m represents the arrangement number of the reference pixel point in the preset order. ; The reference pixel points are denoted as The formula is The change gradient of each reference pixel point and the vessel seed point is obtained , denoted as the change gradient of each reference pixel point, wherein is a preset change gradient influence factor; The target part blood vessel region analysis step in the region stopping judgment step, specifically comprising the following sub-steps: Comparing and analyzing the change gradient of each referenceable pixel point with the standard change gradient of the referenceable pixel point, if the change gradient of the referenceable pixel point is less than the standard change gradient of the referenceable pixel point, it means that the referenceable pixel point meets the corresponding requirements, and the region where the referenceable pixel point is located is included in the blood vessel region, if the change gradient of the referenceable pixel point is greater than the standard change gradient of the referenceable pixel point, it means that the referenceable pixel point does not meet the corresponding requirements, and the region where the referenceable pixel point is located is not included in the blood vessel region, and the blood vessel region of the target part is obtained through the above analysis; a blood vessel reconstruction step: reconstructing the blood vessel region of the target part, to obtain a blood vessel model of the blood vessel region of the target part.

2. The CT image vessel reconstruction method using a region growing method according to claim 1, characterized in that: The CT image acquisition step specifically comprises the following sub-steps: establishing a data extraction relationship between the CT image acquisition step and the database, and selecting a CT image standard irradiation method corresponding to the target part; irradiating the target part by the blood vessel reconstruction device and the CT image standard irradiation method corresponding to the target part, to obtain the CT image of the target part.

3. The CT image vessel reconstruction method using a region growing method according to claim 1, characterized in that: The image preprocessing step specifically comprises the following sub-steps: The data extraction relationship between the image preprocessing step and the database is established, and the corresponding standard CT image contour model is screened through the target site; The CT image of the target part is scanned with high precision by a high-precision profile scanner to obtain a CT image profile model of the target part, and the CT image profile model of the target part is compared with a standard CT image profile model corresponding to the target part to obtain a similarity of the CT image profile model of the target part and the standard CT image profile model corresponding to the target part According to the similarity of the CT image profile model of the target part and the standard CT image profile model corresponding to the target part The CT image of the target part is subjected to corresponding transformation processing to obtain a processable CT image of the target part.

4. The CT image vessel reconstruction method using a region growing method according to claim 1, characterized in that: The region growing analysis step specifically includes the following sub-steps: The data extraction relationship between the database and the region growing analysis step is established, the upper limit threshold and the lower limit threshold of the corresponding blood vessel pixel point gray value of each part are extracted and stored, and the upper limit threshold and the lower limit threshold of the corresponding blood vessel pixel point gray value of the target part are screened through the target part and the lower limit threshold ​ The pixels of the blood vessel seed point in the target site processable CT image are classified into first, second,..., and nth levels according to the distance length of the blood vessel seed point in the target site processable CT image. The gray value of each pixel point in each level is compared with the upper threshold value of the gray value of the blood vessel pixel point corresponding to the target part and the lower threshold value of the blood vessel pixel point corresponding to the target part The pixel points in each level whose gray value is in the interval are sequentially recorded as the blood vessel pixel points corresponding to the target part, and the region where the blood vessel pixel points corresponding to the target part are located is recorded as the quasi-blood vessel region.

5. The CT image vessel reconstruction method using a region growing method according to claim 1, characterized in that: The blood vessel reconstruction step specifically includes the following sub-steps: The blood vessel model of the target site blood vessel region is obtained through the blood vessel reconstruction of the blood vessel region of the target site facing the blood vessel reconstruction device.

Images