Blood vessel image segmentation method and device, electronic equipment and storage medium

Abstract

The application discloses a blood vessel image segmentation method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring an initial blood vessel image, determining a coronary skeleton image of the initial blood vessel image; determining each skeleton point on the skeleton line in the coronary skeleton image, and determining a skeleton branch point in each skeleton point based on the degree of each skeleton point; acquiring a skeleton connected path between any adjacent skeleton branch points, and determining a venous branch line segment in the coronary skeleton image based on the skeleton connected path; and determining a coronary segmentation image of the initial blood vessel image based on the initial blood vessel image and the venous branch line segment. The technical scheme disclosed by the application removes the venous branch in the initial blood vessel image to obtain a coronary vessel image of the initial blood vessel image, solves the problem of low coronary segmentation accuracy of blood vessels in the prior art, and achieves the technical effect of improving the coronary segmentation accuracy.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical image processing, and in particular to a blood vessel image segmentation method and device, an electronic device, and a storage medium. BACKGROUND

[0002] With the improvement of imaging speed and scanning accuracy of CT (Computed Tomography, i.e. electronic computed tomography) equipment, CT medical images have been widely used in heart examination and plaque diagnosis. Heart coronary artery segmentation based on CT medical images is widely used, which can extract the outline of the coronary artery and plaque in the lumen, facilitate the observation of stenosis, calcification and plaque by doctors, and provide a basis for early prevention and diagnosis of cardiovascular diseases by doctors.

[0003] At present, in the process of heart coronary artery segmentation, due to the similar image features (close distance or even adhesion, close CT value, etc.) of veins and coronary arteries, the veins are easily misidentified, and the veins are easy to form a branch closed loop with the coronary arteries. Meanwhile, if the branch and the main stem are parallel (small distance), and the included angle is small, the coronary artery also has a branch closed loop between the proximal ends of the branches, resulting in low accuracy of heart coronary artery segmentation. SUMMARY

[0004] The present application provides a blood vessel image segmentation method, device, electronic device and storage medium, which removes the vein branches in the initial blood vessel image to obtain the coronary artery image of the initial blood vessel image, solves the problem of low accuracy of coronary artery segmentation of blood vessels in the prior art, and achieves the technical effect of improving the accuracy of coronary artery segmentation.

[0005] In a first aspect, an embodiment of the present application provides a blood vessel image segmentation method, which comprises:

[0006] obtaining an initial blood vessel image, and determining a coronary artery skeleton image of the initial blood vessel image;

[0007] determining each skeleton point on a skeleton line in the coronary artery skeleton image, and determining a skeleton branch point in each skeleton point based on the degree of each skeleton point;

[0008] obtaining a skeleton connected path between any adjacent skeleton branch points, and determining a vein branch line segment in the coronary artery skeleton image based on the skeleton connected path;

[0009] determining a coronary artery segmentation image of the initial blood vessel image based on the initial blood vessel image and the vein branch line segment.

[0010] Optionally, the determination of the skeleton branch point in each skeleton point based on the degree of each skeleton point comprises:

[0011] For any skeleton point, determine each neighborhood point of the current skeleton point, and determine the degree of the current skeleton point based on skeleton points contained in the neighborhood points;

[0012] Obtain a preset degree threshold, and if the degree of the current skeleton point is within the range of the degree threshold, the current skeleton point is a skeleton branch point on the skeleton line.

[0013] Optionally, the skeleton connected path between any adjacent skeleton branch points is obtained, and the vein branch line segment in the coronary skeleton image is determined based on the skeleton connected path, comprising:

[0014] Obtain the skeleton line in the coronary skeleton image, and determine the skeleton connected path between any adjacent skeleton branch points based on the skeleton line;

[0015] Determine the vein branch line segment in the coronary skeleton image based on each skeleton connected path.

[0016] Optionally, the vein branch line segment in the coronary skeleton image is determined based on each skeleton connected path, comprising:

[0017] For any adjacent skeleton branch point, determine the number of paths of the skeleton connected path between the current adjacent skeleton branch points;

[0018] If the number of paths is greater than a preset number threshold, each branch skeleton line segment contained in each skeleton connected path of the current adjacent skeleton branch points is obtained respectively;

[0019] Determine the vein branch line segment in the coronary skeleton image based on each branch skeleton line segment.

[0020] Optionally, the vein branch line segment in the coronary skeleton image is obtained by respectively performing vein identification on each non-coincidence line segment, comprising:

[0021] For any branch skeleton line segment, determine the line segment curvature of the current branch skeleton line segment;

[0022] Based on the comparison result of the line segment curvature and a preset curvature threshold, determine the vein branch line segment identification result of the current branch skeleton line segment.

[0023] Optionally, the vein branch line segment in the coronary skeleton image is determined based on each branch skeleton line segment, comprising:

[0024] For any branch skeleton line segment, determine the blood vessel pixel mean value of the current branch skeleton line segment;

[0025] Based on the comparison result of the blood vessel pixel mean value and a preset pixel threshold, determine the vein branch line segment identification result of the current branch skeleton line segment.

[0026] Optionally, the determining the coronary vessel segmentation image of the initial blood vessel image based on the initial blood vessel image and the venous branch includes:

[0027] performing a coronary vessel rough segmentation on the initial blood vessel image to obtain a coronary vessel rough segmentation image of the initial blood vessel image;

[0028] obtaining a branch expansion parameter of the venous branch, and performing an expansion processing on the venous branch based on the branch expansion parameter to obtain a venous expansion image corresponding to the venous branch;

[0029] performing a venous removal processing on the coronary vessel rough segmentation image based on the venous expansion image to obtain the coronary vessel segmentation image of the initial blood vessel image.

[0030] In a second aspect, an embodiment of the present application further provides a blood vessel image segmentation device, which comprises:

[0031] a coronary skeleton image determination module, configured to obtain an initial blood vessel image, and determine a coronary skeleton image of the initial blood vessel image;

[0032] a skeleton branch point determination module, configured to determine each skeleton point on a skeleton line in the coronary skeleton image, and determine a skeleton branch point in each of the skeleton points based on a degree of each of the skeleton points;

[0033] a venous branch line segment determination module, configured to obtain a skeleton connected path between any adjacent skeleton branch points, and determine a venous branch line segment in the coronary skeleton image based on the skeleton connected path;

[0034] a coronary vessel segmentation image determination module, configured to determine a coronary vessel segmentation image of the initial blood vessel image based on the initial blood vessel image and the venous branch line segment.

[0035] In a third aspect, an embodiment of the present application further provides an electronic device, which comprises:

[0036] at least one processor; and

[0037] a memory connected with the at least one processor in communication; wherein,

[0038] the memory stores a computer program which can be executed by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the blood vessel image segmentation method in any of the embodiments of the present application.

[0039] In a fourth aspect, the embodiments of the present application further provide a computer readable storage medium, which stores computer instructions for causing a processor to implement the blood vessel image segmentation method of any of the embodiments of the present application when executed.

[0040] The technical scheme of the embodiments of the present application acquires an initial blood vessel image, determines a coronary skeleton image of the initial blood vessel image, determines each skeleton point on a skeleton line in the coronary skeleton image, and determines a skeleton branch point in each skeleton point based on the degree of each skeleton point. The technical scheme acquires a skeleton connected path between any adjacent skeleton branch points, and determines a venous branch line segment in the coronary skeleton image based on the skeleton connected path. The technical scheme determines a coronary segmentation image of the initial blood vessel image based on the initial blood vessel image and the venous branch line segment. The technical scheme removes the venous branch in the initial blood vessel image to obtain a coronary vessel image of the initial blood vessel image, solves the problem of low accuracy of coronary segmentation of blood vessels in the prior art, and achieves the technical effect of improving the accuracy of coronary segmentation.

[0041] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0043] Figure 1 is a flowchart of a blood vessel image segmentation method according to an embodiment of the present application;

[0044] Figure 2 is a schematic diagram of a coronary rough segmentation image according to an embodiment of the present application;

[0045] Figure 3 is a schematic diagram of a coronary skeleton image according to an embodiment of the present application;

[0046] Figure 4 is a schematic diagram of another coronary skeleton image according to an embodiment of the present application;

[0047] Figure 5 is a schematic diagram of another coronary rough segmentation image according to an embodiment of the present application;

[0048] Figure 6is a schematic diagram of a skeleton connected path according to an embodiment of the present application;

[0049] Figure 7 is a schematic diagram of a vein branch segment according to an embodiment of the present application;

[0050] Figure 8 is a schematic diagram of a vein expansion image according to an embodiment of the present application;

[0051] Figure 9 is a schematic diagram of a coronary artery segmentation image according to an embodiment of the present application;

[0052] Figure 10 is a flowchart of another blood vessel image segmentation method according to an embodiment of the present application;

[0053] Figure 11 is a schematic diagram of another skeleton connected path according to an embodiment of the present application;

[0054] Figure 12 is a schematic diagram of a blood vessel image segmentation device according to an embodiment of the present application;

[0055] Figure 13 is a schematic diagram of an electronic device implementing a blood vessel image segmentation method according to an embodiment of the present application. DETAILED DESCRIPTION

[0056] In order to make the persons skilled in the art better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work should belong to the scope of protection of the present application.

[0057] It should be noted that the terms "first", "second", and the like in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily have to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein.

[0058] The names of the messages or information exchanged between the plurality of devices in the embodiments of the present disclosure are only for illustrative purposes, and are not intended to limit the scope of the messages or information.

[0059] It can be understood that, before using the technical solutions disclosed in the embodiments of the present disclosure, the type of personal information involved in the present disclosure, the use range, the use scenario, etc. should be informed to the user and the authorization of the user should be obtained through appropriate means according to relevant laws and regulations.

[0060] For example, in response to receiving an active request of a user, a prompt information is sent to the user to explicitly prompt the user that the operation requested to be performed will require obtaining and using personal information of the user. Thus, the user can voluntarily choose whether to provide personal information to the software or hardware such as an electronic device, an application program, a server or a storage medium performing the operation of the technical solutions of the present disclosure according to the prompt information.

[0061] As an optional but non-limiting implementation manner, in response to receiving an active request of a user, the manner of sending a prompt information to the user may, for example, be a pop-up window manner, in which the prompt information can be presented in a text manner. In addition, the pop-up window can also carry a selection control for the user to select "agree" or "disagree" to provide personal information to the electronic device.

[0062] It can be understood that the above notification and obtaining of user authorization process is only illustrative and does not limit the implementation manner of the present disclosure, and other manners meeting relevant laws and regulations can also be applied to the implementation manner of the present disclosure.

[0063] It can be understood that the data involved in the present technical solutions (including but not limited to the data itself, the acquisition or use of the data) should comply with the requirements of relevant laws and regulations and relevant provisions.

[0064] Figure 1 A flowchart of a blood vessel image segmentation method is provided for the embodiments of the present application, and the present embodiment can be applied to the segmentation of blood vessels to obtain coronary vessels.

[0065] In the prior art, the coronary artery segmentation result obtained by segmenting the blood vessel image usually contains vein branches interlaced with the coronary arteries, resulting in that the vein branches and the coronary artery branches form a branch closed loop in the segmentation result, and due to the possible branch adhesion between the coronary arteries, the branch closed loop also exists between the coronary artery branches, thereby causing inaccurate coronary artery segmentation result. For the above technical problems, the present embodiment provides an image segmentation method, which processes the blood vessel image to be segmented to obtain each branch point in the blood vessel, identifies the blood vessel between each branch point to obtain the vein branches therein, and then optimizes the coronary artery segmentation result based on the identified vein branches to eliminate the branch closed loop in the segmentation result, thereby obtaining the final coronary artery segmentation result and improving the accuracy of the coronary artery segmentation.

[0066] The method can be performed by a blood vessel image segmentation device, which can be implemented in the form of hardware and / or software, and can be configured in a smart terminal device and a cloud server. Figure 1 As shown in the figure, the method comprises the following steps.

[0067] In S110, an initial blood vessel image is acquired, and a coronary skeleton image of the initial blood vessel image is determined.

[0068] In the embodiment of the present application, the initial blood vessel image can be understood as a blood vessel image obtained by scanning the blood vessels around the heart. The initial blood vessel image contains a vein image that collects blood flowing back into the heart and a coronary image that sends blood provided by the heart to the whole body.

[0069] Specifically, the method for acquiring the initial blood vessel image can be to read image data in a local database or a database of a cloud server to obtain the original initial blood vessel image, or to scan the heart part of a scanning object based on a medical scanning device to obtain the initial blood vessel image. The embodiment does not limit the acquisition method. Optionally, the medical scanning device can be, but is not limited to, a CT device, a PET-CT device and an MRI device. Correspondingly, the obtained initial blood vessel image can include, but is not limited to, at least one of CT image data, PET image data and MRI image data.

[0070] In the embodiment, the coronary skeleton image can be understood as an image containing coronary skeleton information obtained by first performing coronary rough segmentation on the initial blood vessel image and then performing result refinement processing on the rough segmentation result.

[0071] On the basis of acquiring the initial blood vessel image, the technical solution of the embodiment can acquire a skeleton segmentation model that has been pre-trained, input the initial blood vessel image into the skeleton segmentation model, and obtain a coronary skeleton image output by the skeleton segmentation model after performing segmentation and refinement processing on the initial blood vessel image. Optionally, the embodiment can also perform coronary rough segmentation on the initial blood vessel image to obtain a coronary rough segmentation image by using existing segmentation technology, and then perform refinement processing on the coronary rough segmentation image by using a refinement processing method (such as an optimal path algorithm) to obtain the coronary skeleton image.

[0072] For example, referring to Figure 2 , Figure 2 The coronary rough segmentation image is obtained after performing coronary rough segmentation on the initial blood vessel image. The coronary rough segmentation image is refined to obtain the coronary skeleton image as shown in Figure 3 .

[0073] Of course, the present embodiment can also obtain the coronary skeleton image of the initial blood vessel image by other existing manners, and the obtaining manner is not limited.

[0074] S120, determine each skeleton point on the skeleton line in the coronary skeleton image, and determine the skeleton branch point in each skeleton point based on the degree of each skeleton point.

[0075] In the present embodiment, the coronary skeleton image contains a skeleton line representing the skeleton information of the coronary blood vessel. For example, see Figure 3 , the skeleton line can be regarded as being composed of an infinite number of skeleton points. Specifically, the degree of each skeleton point in the skeleton line is determined, and the type of each skeleton point is determined according to the degree of each skeleton point. In the present embodiment, the type of the skeleton point includes but is not limited to the skeleton branch point, the skeleton center point and the skeleton end point, etc.

[0076] It needs to be explained that for any node in the undirected graph, the number of other nodes associated with the node is called the degree of the node. Based on this, the degree of the skeleton point in the present embodiment can be understood as the number of points having an association relationship with the other skeleton points of the skeleton line where the current skeleton point is located.

[0077] Optionally, the method for determining the skeleton branch point based on the degree of the skeleton point in the present embodiment can include: for any skeleton point, determining each neighborhood point of the current skeleton point, and determining the degree of the current skeleton point based on the skeleton points contained in the neighborhood points; obtaining a preset degree threshold, if the degree of the current skeleton point is within the range of the degree threshold, the current skeleton point is a skeleton branch point on the skeleton line.

[0078] Among them, the neighborhood point can be understood as the adjacent point of the current skeleton point in each spatial direction. Specifically, it is judged whether the neighborhood point of the current skeleton point coincides with other skeleton points in the current skeleton line, and the degree of the current skeleton point is determined based on the judgment result. For example, taking the existence of 26 neighborhood points of the current skeleton point as an example, if the 26 neighborhood points are not coincided with other skeleton points, the degree of the current skeleton point is 0; otherwise, if there are neighborhood points coincided with other skeleton points in the 26 neighborhood points, the degree of the current skeleton point is determined based on the number of coincided neighborhood points.

[0079] In the present embodiment, the degree threshold can be understood as a threshold for dividing the types of the skeleton points. Different types of skeleton points can be determined based on different degree thresholds. Specifically, the degree threshold corresponding to the skeleton branch point is obtained, and whether the current skeleton point is a skeleton branch point is determined based on the degree threshold and the degree of the current skeleton point. Optionally, the degree of the current skeleton point is compared with the degree threshold, if the degree of the current skeleton point is within the range of the degree threshold, it is determined that the current skeleton point is a skeleton branch point on the skeleton line; otherwise, it is determined that the current skeleton point is a skeleton point of other types in the skeleton line.

[0080] For example, the degree threshold corresponding to the skeleton branch point is 3. If it is determined that the degree of the current skeleton point is 3, it can be determined that the current skeleton point is a skeleton branch point based on the degree threshold. If it is determined that the degree of the current skeleton point is 2, 4 or other values, it can be determined that the current skeleton point is a skeleton point of other types based on the degree threshold. Referring to Figure 4 , the circular points in the figure represent skeleton branch points, and the rectangular points and square points represent skeleton points of other types, such as skeleton end points and skeleton center points. It should be noted that the reason for setting the degree threshold corresponding to the skeleton branch point to 3 is that if the degree of the skeleton point is 3, it means that there are three adjacent points in the skeleton line, and based on this, it can be determined that the current skeleton point is located at the branch of the skeleton line, that is, it can be determined that the current skeleton point is a skeleton branch point.

[0081] In S130, a skeleton connection path between any adjacent skeleton branch points is obtained, and a vein branch line segment in the coronary skeleton image is determined based on the skeleton connection path.

[0082] In the embodiment of the present application, the skeleton connection path between any two skeleton points can be understood as a skeleton line segment composed of the two skeleton points and all the skeleton points between the two skeleton points.

[0083] Specifically, the skeleton connection path between any adjacent skeleton branch points can be determined based on the skeleton branch points and the coronary skeleton image. Alternatively, the skeleton connection path can be determined based on a pre-trained neural network model, or it can be obtained based on a traditional image algorithm, and the present embodiment does not limit this.

[0084] Further, vein branch line segment recognition is performed based on the skeleton connection path determined above. Alternatively, a pre-trained vein branch recognition algorithm can be obtained, and the skeleton connection path obtained above can be input into the vein branch recognition algorithm to obtain the vein branch line segment recognition result output by the model. Vein branch recognition can also be performed based on the line segment characteristics of each skeleton line segment contained in the skeleton connection path, and the present embodiment does not limit this.

[0085] It should be noted that in actual applications, since the coronary artery has rich branches, there are many skeleton bifurcation line segments in the skeleton line of the coronary skeleton image. For example, referring to Figure 5 , Figure 5 is another coronary skeleton image. In Figure 5The middle arrow indicates the position of the branch point on the skeleton line in the image. Specifically, branching is performed at branch point 1 to obtain two coronary branch lines with branch point 1 as the starting point and branch point 2 and branch point 3 as the ending points, respectively. Then, branching is performed again at branch point 2 to obtain two coronary branch lines with branch point 2 as the starting point and branch point 4 and branch point 5 as the ending points, respectively. Since in actual application all coronary branch lines do not have a compensatory branch, that is, there is only one branch between the starting point and the ending point of the branch in the skeleton line, and there is no merging after branching, there is only one path in the same branch of the heart. Therefore, if there are multiple paths between two skeleton branch points, it is possible that there are misidentified venous branches between the two branch points during segmentation. However, if any two skeleton branch points, for example, branch point 1 and branch point 4, are used, there are two skeleton connected paths between the two skeleton branch points, but the two skeleton connected paths pass through skeleton branch point 2 and skeleton branch point 3, respectively. In this case, based on the skeleton connected path between branch point 1 and branch point 4, the coronary branch in the identification result may be misidentified as a venous branch, resulting in a decrease in the accuracy of the final coronary identification result.

[0086] To solve the above technical problems, the embodiment proposes to determine adjacent skeleton branch points among the skeleton branch points, and perform venous branch identification based on the skeleton connected path of the adjacent skeleton branch points.

[0087] The adjacent skeleton branch points can be understood as skeleton connected paths between the branch points that do not contain other branch points. Specifically, the adjacent branch points of each skeleton branch point are determined based on the position of each skeleton branch point in the skeleton line. For example, referring to Figure 5 , the adjacent skeleton branch points include but are not limited to branch point 1 and branch point 2, branch point 1 and branch point 3, branch point 2 and branch point 4, and branch point 3 and branch point 4, etc. Further, based on the skeleton connected path between any two adjacent skeleton branch points determined in the above embodiment or other embodiments, venous branch identification is performed based on the skeleton connected path to reduce the probability of misidentifying a coronary branch as a venous branch, thereby improving the accuracy of the coronary identification result.

[0088] For example, based on the identification of each skeleton branch point in Figure 4 , the skeleton connected path of any adjacent skeleton branch point is determined based on the skeleton line. For example, the skeleton connected path between each adjacent skeleton branch point is shown in Figure 6 . Further, venous branch identification is performed on each skeleton connected path in Figure 6 , to obtain a venous branch line segment. For example, the venous branch line segment is shown in Figure 7 .

[0089] S140, determine a coronary vessel segmentation image of the initial blood vessel image based on the initial blood vessel image and the vein branch line segment.

[0090] In the embodiment of the present application, based on the vein branch line segment, the vein is removed from the coronary vessel rough segmentation image of the initial blood vessel image to obtain the coronary vessel segmentation result.

[0091] Optionally, the method for determining the coronary vessel segmentation image of the initial blood vessel image in the embodiment can include: performing coronary vessel rough segmentation on the initial blood vessel image to obtain a coronary vessel rough segmentation image of the initial blood vessel image; obtaining branch expansion parameters of the vein branch, and performing expansion processing on the vein branch based on the branch expansion parameters to obtain a vein expansion image corresponding to the vein branch; and performing vein removal processing on the coronary vessel rough segmentation image based on the vein expansion image to obtain the coronary vessel segmentation image of the initial blood vessel image.

[0092] In the embodiment, the branch expansion parameter can be understood as an expansion diameter parameter that needs to be expanded for the vein branch line segment. The branch expansion parameter can include an end point expansion parameter and a center expansion parameter of the vein branch line segment.

[0093] It should be noted that the vein expansion image obtained by expanding the vein branch line segment based on the expansion parameter in the embodiment needs to satisfy the condition of completely covering the vein branch in the coronary vessel rough segmentation image. In this case, the vein branch in the coronary vessel rough segmentation image can be completely removed based on the vein expansion image. Therefore, the branch expansion parameter for expanding the vein branch line segment needs to be determined according to the rough segmentation result in the coronary vessel rough segmentation image.

[0094] Specifically, the coronary vessel rough segmentation image can be obtained by performing coronary vessel rough segmentation on the initial blood vessel image by using the existing segmentation technology, or the coronary vessel rough segmentation image can be obtained by performing segmentation processing on the initial blood vessel image by using the traditional image processing algorithm, and the embodiment does not limit the segmentation manner.

[0095] Further, based on the determination of the vein branch line segments, the vein branch line segments are expanded to obtain a vein expansion image. Optionally, the method of expansion in the embodiment can include: for any end point of any vein branch line segment, the end point expansion parameter is determined based on the line segment end point parameter of the vein branch line segment and the vessel parameter of other vessels connected to the vein branch in the coronary rough segmentation image. Further, based on the determination of the end point expansion parameters of the two line segment end points of the vein branch line segment, the expansion parameter of the middle point of the vein branch line segment is fitted based on the two end point expansion parameters to determine at least one center point expansion parameter of the vein branch line segment, and then the expansion of the vein branch line segment is performed with the expansion of each end point expansion parameter and each center expansion parameter as the expansion target to obtain the vein expansion image of the vein branch line segment. Optionally, based on the above implementation, all vein branch line segments are traversed to obtain the vein expansion image.

[0096] Further, based on the determination of the vein expansion image and the coronary rough segmentation image, the branch region overlapping with the vein branch image in the coronary rough segmentation image is determined, and the branch region is removed from the coronary segmentation image. The proposed image is the coronary segmentation image with the vein branch removed.

[0097] Exemplarily, the vein branch line segment shown in FIG. 8 is expanded to obtain the vein expansion image as shown in FIG. 9, and the coronary rough segmentation image shown in FIG. 10 is processed to remove the vein branch based on the vein expansion image to obtain the coronary segmentation image as shown in FIG. 11. Figure 7 Figure 8 Exemplarily, the vein branch line segment shown in FIG. 8 is expanded to obtain the vein expansion image as shown in FIG. 9, and the coronary rough segmentation image shown in FIG. 10 is processed to remove the vein branch based on the vein expansion image to obtain the coronary segmentation image as shown in FIG. 11. Figure 2 Figure 9 Exemplarily, the vein branch line segment shown in FIG. 8 is expanded to obtain the vein expansion image as shown in FIG. 9, and the coronary rough segmentation image shown in FIG. 10 is processed to remove the vein branch based on the vein expansion image to obtain the coronary segmentation image as shown in FIG. 11.

[0098] The blood vessel image segmentation method provided by the embodiment of the application includes: obtaining an initial blood vessel image; determining a coronary skeleton image of the initial blood vessel image; determining each skeleton point on a skeleton line in the coronary skeleton image, and determining a skeleton branch point in each skeleton point based on the degree of the skeleton point; obtaining a skeleton connected path between any adjacent skeleton branch points, and determining a vein branch line segment in the coronary skeleton image based on the skeleton connected path; and determining a coronary segmentation image of the initial blood vessel image based on the initial blood vessel image and the vein branch line segment. The above technical solution processes the blood vessel image to be segmented to obtain each branch point in the blood vessel; identifies the blood vessel between each branch point to obtain the vein branch; and optimizes the coronary segmentation result based on the identified vein branch to obtain the final coronary segmentation result, thereby improving the accuracy of coronary segmentation.

[0099] Figure 10 The flowchart of another blood vessel image segmentation method provided by the embodiment of the application is based on the above embodiment, and optionally,

[0100] As​​Figure 10 The method comprises the following steps of:

[0101] S210, acquiring an initial blood vessel image, and determining a coronary skeleton image of the initial blood vessel image.

[0102] S220, determining each skeleton point on a skeleton line in the coronary skeleton image, and determining a skeleton branch point in each skeleton point based on a degree of each skeleton point.

[0103] S230, acquiring a skeleton line in the coronary skeleton image, and determining a skeleton connection path between any adjacent skeleton branch points based on the skeleton line.

[0104] In the embodiment of the present application, at least one adjacent branch point corresponding to each skeleton branch point is determined based on the skeleton line and the position of each skeleton branch point in the skeleton line. Optionally, for any two adjacent skeleton branch points, the method of determining the skeleton connection path can comprise the following steps: acquiring a pre-trained skeleton connection path extraction model, inputting the two adjacent skeleton branch points and the skeleton line to which the two skeleton branch points belong into the skeleton connection path extraction model, and obtaining the skeleton connection path between the two adjacent skeleton branch points; optionally, the method of obtaining the skeleton connection path between the adjacent skeleton branch points can also be to acquire a path calculation algorithm, and perform path calculation on the two adjacent skeleton branch points and the skeleton line to which the skeleton branch points belong based on the path calculation algorithm, so as to determine the skeleton connection path between the adjacent skeleton branch points. Of course, the skeleton connection path between any adjacent skeleton branch points can also be obtained by traversing each skeleton point on the skeleton line, and the method of determining the skeleton connection path is not limited in the embodiment.

[0105] S240, determining a venous branch line segment in the coronary skeleton image based on each skeleton connection path.

[0106] In the embodiment of the present application, the method of determining the venous branch line segment in the coronary skeleton image based on the skeleton connection path can comprise the following steps: for any adjacent skeleton branch points, determining the number of the skeleton connection paths between the two adjacent skeleton branch points; if the number of the skeleton connection paths is greater than a preset number threshold, obtaining each branch skeleton line segment contained in each skeleton connection path of the two adjacent skeleton branch points, respectively; and determining the venous branch line segment in the coronary skeleton image based on each branch skeleton line segment.

[0107] Specifically, the number of the skeleton connection paths is determined based on the determination of the adjacent skeleton connection paths. For example, for any two adjacent skeleton branch points, the number of the skeleton connection paths between the two skeleton branch points is determined based on the number of the skeleton lines to which the two skeleton branch points belong. Figure 6The skeleton connection paths between each adjacent skeleton branch point are determined, and the number of the skeleton connection paths corresponding to each adjacent skeleton branch point is determined. In actual application, since the coronary artery has no compensatory branch, the number threshold is set to 1, and the adjacent skeleton branch points corresponding to the number of connection paths greater than the number threshold are determined based on the above-mentioned skeleton connection paths. Further, the skeleton connection paths of the screened adjacent skeleton branch points are determined. For example, the skeleton connection paths of the screened adjacent skeleton branch points are as shown in FIG. 8. Figure 11 For any adjacent skeleton branch point, the branch skeleton line segments contained in the skeleton connection path between the current adjacent skeleton branch points are obtained, and the vein identification is performed on each branch skeleton line segment to obtain the vein branch line segment.

[0108] In actual application, Figure 11 In the segmentation result of the coronary artery coarse segmentation, the branch closed loop formed by the interlaced vein branch and the coronary branch, or the branch closed loop formed by the adherent coronary artery, is embodied. In order to obtain accurate coronary artery segmentation result, the branch line segment in the above-mentioned branch closed loop needs to be identified. If the identification result contains the vein branch, the identified vein branch is removed to obtain the accurate segmentation result. Otherwise, if the identification result does not contain the vein branch, it is indicated that the above-mentioned closed loop is the branch closed loop formed by the adherent coronary artery, and the adherent area in the above-mentioned branch needs to be identified and removed to obtain the accurate coronary artery segmentation result.

[0109] Optionally, the method for identifying the vein branch line segment of each branch skeleton line segment in the embodiment can include: determining the line segment curvature of the current branch skeleton line segment for any branch skeleton line segment; determining the vein branch line segment identification result of the current branch skeleton line segment based on the comparison result of the line segment curvature and the preset curvature threshold.

[0110] In actual application, compared with the vein, the blood vessel curvature of the coronary artery is greater, so a suitable curvature threshold is set according to the blood vessel curvature characteristics of the coronary artery.

[0111] Specifically, the line segment curvature of each branch skeleton line segment is calculated respectively, and the comparison between each line segment curvature and the preset curvature threshold is performed respectively, and the vein branch line segment identification result of each branch skeleton line segment is determined based on the comparison result of the curvature. Optionally, if the curvature of the current branch skeleton line segment is greater than the curvature threshold, it is indicated that the current branch skeleton line segment is the coronary branch. Otherwise, if the curvature of the current branch skeleton line segment is less than the curvature threshold, it is indicated that the current skeleton line segment is the vein branch.

[0112] Optionally, the method for vein identification of each branch skeleton line segment in the embodiment can further include: determining the blood vessel pixel mean value of the current branch skeleton line segment; and determining the vein branch line segment identification result of the current branch skeleton line segment based on the comparison result of the blood vessel pixel mean value and the preset pixel threshold value.

[0113] In actual application, in order to better the coronary artery, the concentration of the contrast agent in the coronary artery of the blood circulation system is higher during CT imaging, that is, the image brightness of the coronary artery is larger during CT imaging, so the pixel value of the coronary artery is higher than that of the vein, and therefore, the appropriate pixel value threshold is set in advance according to the blood vessel pixel characteristics of the coronary artery.

[0114] Specifically, the blood vessel pixel mean value of each branch skeleton line segment is calculated. Specifically, for any branch skeleton line segment, the blood vessel segment corresponding to the current branch skeleton line segment is determined based on the position of the current branch skeleton line segment in the initial blood vessel, and the pixel value of each pixel point corresponding to the current blood vessel segment is calculated, and then the pixel mean value corresponding to the current branch skeleton line segment is obtained.

[0115] Further, each blood vessel pixel mean value is compared with the preset pixel threshold value, and the vein branch line segment identification result of each branch skeleton line segment is determined based on the comparison result of the pixel. Optionally, if the blood vessel pixel mean value of the current branch skeleton line segment is greater than the pixel threshold value, it indicates that the current branch skeleton line segment is a coronary artery branch; otherwise, if the blood vessel pixel mean value of the current branch skeleton line segment is less than the pixel threshold value, it indicates that the current skeleton line segment is a vein branch.

[0116] On the basis of the above-mentioned embodiments, the technical scheme of the embodiment can further perform vein identification by calculating other image statistical information of the branch skeleton line segment, such as determining the blood flow direction of the branch skeleton line segment. Of course, vein identification can also be performed based on the comparison result between each branch skeleton line segment, which is not limited in the embodiment.

[0117] S250, determining a coronary artery segmentation image of the initial blood vessel image based on the initial blood vessel image and the vein branch line segment.

[0118] The technical scheme of the embodiment of the application performs vein identification through the skeleton connection path between adjacent skeleton branch points, and removes the vein branch in the initial blood vessel image based on the identification result to obtain the coronary artery image of the initial blood vessel image, thereby solving the problem of low accuracy of coronary artery segmentation of blood vessels in the prior art and achieving the technical effect of improving the accuracy of coronary artery segmentation.

[0119] Figure 12 A structure schematic diagram of a blood vessel image segmentation device provided by the embodiment of the application is shown in FIG. 1. Figure 12As shown, the device comprises a coronary skeleton image determination module 310, a skeleton branch point determination module 320, a vein branch line segment determination module 330, and a coronary segmentation image determination module 340; wherein,

[0120] The coronary skeleton image determination module 310 is configured to acquire an initial blood vessel image, and determine a coronary skeleton image of the initial blood vessel image.

[0121] The skeleton branch point determination module 320 is configured to determine each skeleton point on a skeleton line in the coronary skeleton image, and determine a skeleton branch point in each skeleton point based on a degree of each skeleton point.

[0122] The vein branch line segment determination module 330 is configured to acquire a skeleton connected path between any adjacent skeleton branch points, and determine a vein branch line segment in the coronary skeleton image based on the skeleton connected path.

[0123] The coronary segmentation image determination module 340 is configured to determine a coronary segmentation image of the initial blood vessel image based on the initial blood vessel image and the vein branch line segment.

[0124] On the basis of the above-mentioned embodiments, the skeleton branch point determination module 320 comprises:

[0125] A skeleton point degree determination sub-module is configured to determine, for any skeleton point, each neighborhood point of the current skeleton point, and determine a degree of the current skeleton point based on skeleton points contained in the neighborhood points.

[0126] A skeleton branch point determination sub-module is configured to acquire a preset degree threshold value, and if the degree of the current skeleton point is within the range of the degree threshold value, the current skeleton point is a skeleton branch point on the skeleton line.

[0127] On the basis of the above-mentioned embodiments, the vein branch line segment determination module 330 comprises:

[0128] A skeleton connected path determination sub-module is configured to acquire a skeleton line in the coronary skeleton image, and determine a skeleton connected path between any adjacent skeleton branch points based on the skeleton line.

[0129] A vein branch line segment determination sub-module is configured to determine a vein branch line segment in the coronary skeleton image based on each skeleton connected path.

[0130] On the basis of the above-mentioned embodiments, the vein branch line segment determination sub-module comprises:

[0131] A path number determination unit is configured to determine, for any adjacent skeleton branch points, a path number of the skeleton connected path between the current adjacent skeleton branch points.

[0132] The branch skeleton line segment determination unit is configured to acquire each branch skeleton line segment included in each skeleton connected path of the current adjacent skeleton branch point if the number of the paths is greater than a preset number threshold.

[0133] The vein branch line segment determination unit is configured to determine a vein branch line segment in the coronary skeleton image based on each branch skeleton line segment.

[0134] On the basis of the above-mentioned embodiments, the vein branch line segment determination unit can comprise:

[0135] The line segment curvature determination sub-unit is configured to determine the line segment curvature of the current non-coincidence line segment for any non-coincidence line segment.

[0136] The first vein branch line segment determination sub-unit is configured to determine the vein branch line segment identification result of the current non-coincidence line segment based on the comparison result of the line segment curvature and the preset curvature threshold.

[0137] On the basis of the above-mentioned embodiments, the vein branch line segment determination unit can comprise:

[0138] The blood vessel pixel mean value determination sub-unit is configured to determine the blood vessel pixel mean value of the current branch skeleton line segment for any branch skeleton line segment.

[0139] The second vein branch line segment determination sub-unit is configured to determine the vein branch line segment identification result of the current branch skeleton line segment based on the comparison result of the blood vessel pixel mean value and the preset pixel threshold.

[0140] On the basis of the above-mentioned embodiments, the coronary segmentation image determination module 340 can comprise:

[0141] The coronary rough segmentation image obtaining sub-module is configured to perform coronary rough segmentation on the initial blood vessel image to obtain a coronary rough segmentation image of the initial blood vessel image.

[0142] The vein expansion image obtaining sub-module is configured to acquire branch expansion parameters of the vein branch and perform expansion processing on the vein branch based on the branch expansion parameters to obtain a vein expansion image corresponding to the vein branch.

[0143] The coronary segmentation image obtaining sub-module is configured to perform vein removal processing on the coronary rough segmentation image based on the vein expansion image to obtain a coronary segmentation image of the initial blood vessel image.

[0144] The blood vessel image segmentation device provided in the embodiments of the present application can execute the blood vessel image segmentation method provided in any of the embodiments of the present application, and has the corresponding function modules and beneficial effects of the execution method.

[0145] Figure 13 A structural diagram of an electronic device 10 that can be used to implement embodiments of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular telephones, smart phones, wearable devices (e.g., headsets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present application described and / or claimed in this document.

[0146] As shown, the electronic device 10 includes at least one processor 11, and memory, such as read-only memory (ROM) 12, random access memory (RAM) 13, etc., communicatively connected to the at least one processor 11, where the memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer programs stored in the read-only memory (ROM) 12 or loaded into the random access memory (RAM) 13 from the storage unit 18. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14. Figure 13

[0147] Various components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc., an output unit 17, such as various types of displays, speakers, etc., a storage unit 18, such as a magnetic disk, an optical disk, etc., and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0148] The processor 11 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 performs various methods and processes described above, such as the blood vessel image segmentation method.

[0149] ​In some embodiments, the blood vessel image segmentation method can be implemented as a computer program tangibly embodied in a computer readable storage medium, e.g., storage unit 18. In some embodiments, parts or all of the computer program can be loaded and / or installed onto electronic device 10 via, e.g., ROM 12 and / or communication unit 19. When the computer program is loaded onto RAM 13 and executed by processor 11, one or more steps of the blood vessel image segmentation method described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the blood vessel image segmentation method by other means, e.g., with the aid of firmware.

[0150] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, specially designed application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0151] Computer programs used to implement the blood vessel image segmentation method of the present application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the computer program running on the processor implements the functions / operations specified in the flowcharts and / or the block diagrams. The computer program can be executed entirely on a machine, partially on a machine, partially on a machine as part of a standalone software package, or entirely on a remote machine or server.

[0152] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer-readable storage medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of a machine-readable storage medium will include one or more lines of a program of instructions in a transitory signal, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0153] To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0154] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0155] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS service.

[0156] It should be understood that the various forms of flow shown above can be used to reorder, add or delete steps. For example, each step described in the present application can be executed in parallel, sequentially or in a different order, as long as the desired results of the technical solutions of the present application can be achieved, which is not limited herein.

[0157] The above detailed description does not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A blood vessel image segmentation method characterized by, The method comprises the following steps: obtaining an initial blood vessel image, and determining a coronary skeleton image of the initial blood vessel image; determining each skeleton point on a skeleton line in the coronary skeleton image, and determining a skeleton branch point in each skeleton point based on a degree of each skeleton point; obtaining a skeleton connected path between any adjacent skeleton branch points, and determining a venous branch line segment in the coronary skeleton image based on the skeleton connected path; determining a coronary segmentation image of the initial blood vessel image based on the initial blood vessel image and the venous branch line segment; the step of obtaining the skeleton connected path between any adjacent skeleton branch points and determining the venous branch line segment in the coronary skeleton image based on the skeleton connected path comprises: obtaining a skeleton line in the coronary skeleton image, and determining a skeleton connected path between any adjacent skeleton branch points based on the skeleton line; determining a venous branch line segment in the coronary skeleton image based on each skeleton connected path; the step of determining the venous branch line segment in the coronary skeleton image based on each skeleton connected path comprises: for any adjacent skeleton branch points, determining a path number of the skeleton connected path between the current adjacent skeleton branch points; if the path number is greater than a preset number threshold, obtaining each branch skeleton line segment contained in each skeleton connected path of the current adjacent skeleton branch points respectively; determining a venous branch line segment in the coronary skeleton image based on each branch skeleton line segment; the step of determining the venous branch line segment in the coronary skeleton image based on each branch skeleton line segment comprises: for any branch skeleton line segment, determining a line segment curvature of the current branch skeleton line segment; based on a comparison result of the line segment curvature and a preset curvature threshold, determining a venous branch line segment identification result of the current branch skeleton line segment; or the step of determining the venous branch line segment in the coronary skeleton image based on each branch skeleton line segment comprises: for any branch skeleton line segment, determining a blood vessel pixel mean value of the current branch skeleton line segment; based on a comparison result of the blood vessel pixel mean value and a preset pixel threshold, determining a venous branch line segment identification result of the current branch skeleton line segment.

2. The method of claim 1, wherein, the step of determining the skeleton branch point in each skeleton point based on the degree of each skeleton point comprises: for any skeleton point, determining each neighborhood point of the current skeleton point, and determining a degree of the current skeleton point based on the skeleton points contained in the neighborhood points; obtaining a preset degree threshold, if the degree of the current skeleton point is within the range of the degree threshold, the current skeleton point is a skeleton branch point on the skeleton line.

3. The method of claim 1, wherein, the step of determining the coronary segmentation image of the initial blood vessel image based on the initial blood vessel image and the venous branch comprises: performing coronary rough segmentation on the initial blood vessel image to obtain a coronary rough segmentation image of the initial blood vessel image; obtaining a branch expansion parameter of the venous branch, and performing expansion processing on the venous branch based on the branch expansion parameter to obtain a venous expansion image corresponding to the venous branch; performing venous removal processing on the coronary rough segmentation image based on the venous expansion image to obtain a coronary segmentation image of the initial blood vessel image.

4. A blood vessel image segmentation apparatus characterized by comprising: the method comprises the following steps: The coronary skeleton image determination module is configured to acquire an initial blood vessel image and determine a coronary skeleton image of the initial blood vessel image. The skeleton branch point determination module is configured to determine each skeleton point on a skeleton line in the coronary skeleton image and determine a skeleton branch point in each skeleton point based on a degree of each skeleton point. The vein branch line segment determination module is configured to acquire a skeleton connected path between any adjacent skeleton branch points and determine a vein branch line segment in the coronary skeleton image based on the skeleton connected path. The coronary segmentation image determination module is configured to determine a coronary segmentation image of the initial blood vessel image based on the initial blood vessel image and the vein branch line segment. The vein branch line segment determination module includes: The skeleton connected path determination submodule is configured to acquire a skeleton line in the coronary skeleton image and determine a skeleton connected path between any adjacent skeleton branch points based on the skeleton line. The vein branch line segment determination submodule is configured to determine a vein branch line segment in the coronary skeleton image based on each skeleton connected path. The vein branch line segment determination submodule includes: The path number determination unit is configured to determine a path number of the skeleton connected path between the current adjacent skeleton branch points for any adjacent skeleton branch points. The branch skeleton line segment determination unit is configured to acquire each branch skeleton line segment contained in each skeleton connected path of the current adjacent skeleton branch points if the path number is greater than a preset number threshold. The vein branch line segment determination unit is configured to determine a vein branch line segment in the coronary skeleton image based on each branch skeleton line segment. The vein branch line segment determination unit includes: The line segment curvature determination subunit is configured to determine a line segment curvature of the current non-coinciding line segment for any non-coinciding line segment. The first vein branch line segment determination subunit is configured to determine a vein branch line segment identification result of the current non-coinciding line segment based on a comparison result of the line segment curvature and a preset curvature threshold. Or The vein branch line segment determination unit includes: The blood vessel pixel mean value determination subunit is configured to determine a blood vessel pixel mean value of the current branch skeleton line segment for any branch skeleton line segment. The second vein branch line segment determination subunit is configured to determine a vein branch line segment identification result of the current branch skeleton line segment based on a comparison result of the blood vessel pixel mean value and a preset pixel threshold.

5. An electronic device, comprising: The electronic device includes: at least one processor; and a memory connected with the at least one processor in communication; wherein The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the blood vessel image segmentation method of any one of claims 1-3.

6. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions for causing the processor to execute when the blood vessel image segmentation method of any one of claims 1-3 is executed.

Images