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

Abstract

This invention discloses a method, apparatus, electronic device, and storage medium for segmenting blood vessel images. The method includes: acquiring an initial blood vessel image; determining a coarse coarse segmentation image of the coarse coarse segmentation image of the initial blood vessel image; determining the coarse coarse segmentation image of ...

Description

Technical Field

[0001] This invention relates to the field of medical image processing technology, and in particular to a method, apparatus, electronic device, and storage medium for segmenting blood vessel images. Background Technology

[0002] With the improvement of imaging speed and scanning accuracy of CT (Computed Tomography) equipment, CT medical imaging has been widely used in cardiac examinations and plaque diagnosis. Coronary artery segmentation based on CT medical images is widely used. It can extract the contours of plaques in the coronary arteries and lumen, facilitating doctors' observation of stenosis, calcification, and plaque, providing a basis for doctors to conduct early prevention and diagnosis of cardiovascular diseases.

[0003] Currently, in the process of segmenting coronary arteries, veins are easily misidentified because their imaging characteristics (close proximity or even adhering, similar CT values, etc.) are similar to those of coronary arteries. They are also prone to forming branch loops with coronary arteries. In addition, if the branches run parallel to the main trunk (with a small distance) and the angle between them is small, branch loops can also exist between the proximal ends of the branches, resulting in a low accuracy rate of coronary artery segmentation. Summary of the Invention

[0004] This invention provides a method, apparatus, electronic device, and storage medium for segmenting blood vessel images. By removing venous branches from the coarse segmentation results of coronary arteries, it addresses the problem of low accuracy in coronary artery segmentation in existing technologies, thereby improving the accuracy of coronary artery segmentation.

[0005] In a first aspect, embodiments of the present invention provide a method for segmenting blood vessel images, the method comprising:

[0006] Acquire an initial vascular image, determine a coarse segmentation image of the coarse segmentation image of the coarse vascular ...

[0007] Edge recognition is performed on the coarse segmentation image of the coarse segmentation of the coarse segmentation of the coarse segmentation of the coarse segmentation of the coarse segmentation image ...

[0008] Identify the root endpoint and at least one terminal branch endpoint among the said skeleton endpoints, and determine the venous branch segments in the coronary artery skeleton line based on the skeleton connectivity path between the root endpoint and each of the said terminal branch endpoints;

[0009] The coronary artery segmentation image of the initial vascular image is determined based on the coarse segmentation image of the coronary artery and the line segments of the vein branches.

[0010] Optionally, the step of performing edge recognition on the coarse segmentation image of the coronary arteries to obtain at least one segmentation edge point in the coarse segmentation image of the coronary arteries includes:

[0011] Obtain the pixel value of each pixel in the coarse segmentation image of the coronary artery, and determine at least one abrupt pixel based on each pixel value;

[0012] At least one segmentation edge point in the coarse segmentation image of the coronary artery is determined based on each of the aforementioned mutated pixel points.

[0013] Optionally, determining at least one skeleton endpoint in each of the coronary artery skeleton lines based on each of the segmentation edge points includes:

[0014] For any segmentation edge point, the edge segmentation line segment corresponding to the current segmentation edge point is determined based on the current segmentation edge point and a preset number of adjacent edge points of the current segmentation edge point;

[0015] Determine the curvature of the edge segment, and determine whether the current segmentation edge point is a segmentation endpoint based on the segment curvature and a preset curvature threshold;

[0016] The skeleton endpoints are determined based on each of the segmentation endpoints and the coronary artery skeleton line.

[0017] Optionally, the step of determining the root endpoint and at least one terminal endpoint among the skeleton endpoints includes:

[0018] The aorta location in the coarse segmentation image of the coronary artery is determined, and the root endpoint and at least one terminal branch endpoint in each of the skeleton endpoints are determined based on the aorta location and the location of each skeleton endpoint.

[0019] Optionally, determining the venous branch segments in the coronary artery skeleton line based on the skeleton connectivity path between the root endpoint and each of the terminal branch endpoints includes:

[0020] Obtain each skeleton segment in the coronary artery skeleton line, and determine the skeleton connection path between the root endpoint and any terminal branch endpoint based on each skeleton segment;

[0021] For any terminal endpoint, determine the number of skeleton connection paths between the current terminal endpoint and the root endpoint. If the number of paths is greater than a preset threshold, then obtain the skeleton line segments of each branch in the skeleton connection path between the current terminal endpoint and the root endpoint.

[0022] The venous branch segments in the coronary artery skeleton line are determined based on each of the aforementioned branch skeleton segments.

[0023] Optionally, determining the venous branch segments in the coronary artery skeleton line based on each of the branch skeleton segments includes:

[0024] By comparing the line segments of each branch skeleton line segment, the non-overlapping line segments in each branch skeleton line segment are obtained.

[0025] Vein identification is performed on each of the non-overlapping line segments to obtain the venous branch segments in the coronary artery skeleton line.

[0026] Optionally, determining the coronary artery segmentation image of the initial vascular image based on the initial vascular image and the venous branches includes:

[0027] The initial vascular image is subjected to coarse coronary artery segmentation to obtain a coarse coronary artery segmentation image of the initial vascular image;

[0028] Obtain the branch expansion parameters of the vein branch, and perform expansion processing on the vein branch based on the branch expansion parameters to obtain the vein expansion image corresponding to the vein branch;

[0029] Based on the vein extension image, the coarse segmentation image of the coronary artery is processed to remove veins, thereby obtaining the coronary artery segmentation image of the initial blood vessel image.

[0030] Secondly, embodiments of the present invention also provide a blood vessel image segmentation apparatus, the apparatus comprising:

[0031] The coarse segmentation image determination module for coarse segmentation of ...

[0032] The skeleton endpoint determination module is used to perform edge recognition on the coarse segmentation image of the coarse segmentation ...

[0033] A venous branch segment determination module is used to determine the root endpoint and at least one terminal branch endpoint among the skeleton endpoints, and to determine the venous branch segments in the coronary artery skeleton line based on the skeleton connection path between the root endpoint and each terminal branch endpoint.

[0034] The coronary artery segmentation image determination module is used to determine the coronary artery segmentation image of the initial blood vessel image based on the coarse coronary artery segmentation image and the venous branch line segments.

[0035] Thirdly, embodiments of the present invention also provide an electronic device, comprising:

[0036] At least one processor; and

[0037] A memory communicatively connected to the at least one processor; wherein,

[0038] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the blood vessel image segmentation method according to any embodiment of the present invention.

[0039] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing computer instructions that are used to cause a processor to execute the blood vessel image segmentation method of any embodiment of the present invention.

[0040] The vascular image segmentation method provided in this invention acquires an initial vascular image, determines a coarse coarse segmentation image of the coarse coarse segmentation image, and determines the coarse coarse segmentation skeleton line of the coarse coarse segmentation image; performs edge recognition on the coarse coarse segmentation image to obtain at least one segmentation edge point in the coarse coarse segmentation image, and determines at least one skeleton endpoint in each coarse coarse segmentation skeleton line based on each segmentation edge point; determines the root endpoint and at least one terminal branch endpoint in each skeleton endpoint, and determines the venous branch segment in the coarse coarse segmentation skeleton line based on the skeleton connection path between the root endpoint and each terminal branch endpoint; and determines the coarse segmentation image of the initial vascular image based on the coarse coarse segmentation image and the venous branch segment. The above technical solution processes the vascular image to be segmented to obtain each endpoint in the vascular system; identifies the vascular systems between each endpoint to obtain the venous branches; and then optimizes the coarse coarse segmentation result based on the identified venous branches to obtain the final coarse coarse segmentation result, thereby improving the accuracy of coarse coarse segmentation.

[0041] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

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

[0044] Figure 2 This is a schematic diagram of a coarse segmentation image of a coronary artery provided according to an embodiment of the present invention;

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

[0046] Figure 4 This is a schematic diagram of another coarse segmentation image of the coronary artery provided according to an embodiment of the present invention;

[0047] Figure 5 This is a schematic diagram of a skeleton endpoint provided according to an embodiment of the present invention;

[0048] Figure 6 This is a schematic diagram of another coarse segmentation image of the coronary artery provided according to an embodiment of the present invention;

[0049] Figure 7 This is a schematic diagram of a skeleton connectivity path provided according to an embodiment of the present invention;

[0050] Figure 8 This is a schematic diagram of a vein branch segment provided according to an embodiment of the present invention;

[0051] Figure 9 This is a schematic diagram of a vein expansion image provided according to an embodiment of the present invention;

[0052] Figure 10 This is a schematic diagram of a coronary artery segmentation image provided according to an embodiment of the present invention;

[0053] Figure 11 This is a flowchart of another blood vessel image segmentation method provided according to an embodiment of the present invention;

[0054] Figure 12 This is a schematic diagram of a branch skeleton line segment provided according to an embodiment of the present invention;

[0055] Figure 13 This is a schematic diagram of a non-overlapping line segment provided according to an embodiment of the present invention;

[0056] Figure 14 This is a schematic diagram of the structure of a blood vessel image segmentation device according to an embodiment of the present invention;

[0057] Figure 15 This is a schematic diagram of the structure of an electronic device that implements the blood vessel image segmentation method of this invention. Detailed Implementation

[0058] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. 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 should fall within the scope of protection of the present invention.

[0059] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in sequences other than those illustrated or described herein.

[0060] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0061] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0062] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the software or hardware, such as the electronic device, application, server, or storage medium performing the operations of this disclosed technical solution, based on the prompt message.

[0063] As an optional but non-limiting implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0064] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0065] It is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and related provisions.

[0066] Figure 1 The present invention provides a flowchart of a blood vessel image segmentation method, which is applicable to the situation of segmenting blood vessels to obtain coronary arteries.

[0067] In existing technologies, segmentation of vascular images often results in coronary artery segmentation containing intersecting venous branches. This leads to branching loops between venous and coronary artery branches, and the potential for branch adhesions between coronary artery branches can also cause branching loops between branches, resulting in inaccurate coronary artery segmentation. To address these issues, this embodiment provides an image segmentation method. This method processes the vascular image to obtain the endpoints of the vessels; identifies the vessels between each endpoint to obtain venous branches; and then optimizes the coronary artery segmentation results based on the identified venous branches, eliminating branching loops and obtaining the final coronary artery segmentation result, thus improving the accuracy of coronary artery segmentation.

[0068] This method can be executed by a blood vessel image segmentation device, which can be implemented in hardware and / or software and can be configured in a smart terminal or cloud server. For example... Figure 1 As shown, the method includes:

[0069] S110. Obtain the initial blood vessel image, determine the coronary artery coarse segmentation image of the initial blood vessel image, and determine the coronary artery skeleton line of the coronary artery coarse segmentation image.

[0070] In this embodiment of the invention, the initial vascular image can be understood as a vascular image obtained by scanning the blood vessels surrounding the heart. The initial vascular image includes images of veins that collect blood returning to the heart and images of coronary arteries that supply blood from the heart to the rest of the body. The coarse coronary artery segmentation image is the result of coarse coronary artery segmentation from the initial vascular image. This coarse coronary artery segmentation result may contain misidentified venous branches, so venous branch identification is required to obtain accurate coronary artery segmentation results. The coronary artery skeleton line can be understood as the coronary artery skeleton information obtained after refining the coarse coronary artery segmentation result. The coronary artery skeleton information contains information about each branch in the coarse coronary artery segmentation result. In this embodiment, the coronary artery skeleton line can be considered as being composed of an infinite number of skeleton points.

[0071] Specifically, the method for obtaining initial vascular images can be to read image data from a local database or a cloud server database to obtain the original initial vascular image, or it can be to obtain the initial vascular image by scanning the heart area of ​​the scanned object using a medical scanning device. This embodiment does not limit the acquisition method. Optionally, the medical scanning device can be, but is not limited to, a CT device, a PET (Positron Emission Computed Tomography)-CT device, and an MRI (Magnetic Resonance Imaging) device. The corresponding initial vascular image obtained can include, but is not limited to, at least one of CT image data, PET image data, and MRI image data.

[0072] Based on the initial vascular image, the technical solution of this embodiment can acquire a pre-trained coarse coarse segmentation model for the coarse coarse segmentation of the coarse coarse vascular image. The initial vascular image is then input into this model to obtain the coarsely segmented coarse coarse image of the coarse coarse vascular image output by the model. Optionally, this embodiment can also use other existing segmentation techniques to perform coarse coarse segmentation of the coarse vascular image to obtain the coarsely segmented coarse coarse image. This embodiment does not limit the method for obtaining the coarsely segmented coarse coarse image of the coarse coarse vascular image. See also the exemplary embodiments. Figure 2 , Figure 2 The coarse segmented image of the coronary arteries after coarse segmentation of the initial vascular image.

[0073] Specifically, based on the obtained coarse segmentation image of the coronary arteries, a thinning process is applied, such as the optimal path algorithm, to refine the coarse segmentation image, resulting in a coronary artery skeleton image. Optionally, a pre-trained skeleton segmentation model can be obtained, and the initial vessel image can be input into this model to obtain the coronary artery skeleton image output by the skeleton segmentation model after segmenting and thinning the initial vessel image. See the example below. Figure 3 , Figure 3 This is the coronary artery skeleton image corresponding to the initial blood vessel image after segmentation and refinement in this embodiment.

[0074] S120. Perform edge recognition on the coarse segmentation image of the coarse segmentation of the coarse segmentation of the coarse segmentation image of the coarse segmentation of the coarse segmentation image of the coarse segmentation, and determine at least one skeleton endpoint of each coarse skeleton line based on each segmentation edge point.

[0075] In this embodiment of the invention, the edge can be understood as the edge of the segmentation result of each branch in the coarse segmentation image of the coronary artery. The segmentation edge point can be understood as each edge pixel of the segmentation result.

[0076] Optionally, in this embodiment, the method for performing edge recognition on the coarse segmentation image of the coronary artery to obtain segmentation edge points may include: obtaining the pixel value of each pixel in the coarse segmentation image of the coronary artery, determining at least one abrupt change pixel based on each pixel value, and determining at least one segmentation edge point in the coarse segmentation image of the coronary artery based on each abrupt change pixel.

[0077] Here, a mutation pixel can be understood as a pixel in the image whose pixel value differs from other adjacent pixels by a preset threshold. In this embodiment, a mutation pixel can be understood as a pixel at the edge of the coarse segmentation result of the coronary artery.

[0078] Specifically, to obtain the pixel values ​​of each pixel in the coarse segmentation image of the coronary arteries, it should be noted that the coarse segmentation image of the coronary arteries includes the segmentation result (coronary artery branches) and the image background. The obtained pixels in the coarse segmentation image are either pixels corresponding to the segmentation result or pixels in the image background. Since the difference between the pixel values ​​of the segmentation result and the pixel values ​​of the image background in the coarse segmentation image is relatively large, for any pixel, the pixel values ​​of the current pixel are compared with those of its neighboring pixels. If the difference between the pixel values ​​of the current pixel and its neighboring pixels is greater than a preset difference threshold, then the current pixel is determined to be a pixel abrupt change point. Optionally, based on the above implementation method, all pixels in the coarse segmentation image of the coronary arteries are traversed to determine all pixel abrupt change points in the image.

[0079] In practical applications, due to potential lesions or other problems within the coronary arteries, the pixel value difference between pixels inside the segmented vessel and their adjacent pixels may exceed a preset threshold, leading to them being mistakenly identified as aberrant pixels. However, these misidentified pixels are not located at the edges of the segmentation result. Therefore, it is necessary to remove these misidentified aberrant pixels and use them as the basis for segmentation edge points. Optionally, pixel fitting can be performed on all acquired aberrant pixels, and pixels located at the edges of the segmentation result can be used as segmentation edge points based on the fitting results. Of course, other methods can also be used to filter aberrant pixels to obtain segmentation edge points; this embodiment does not limit this approach.

[0080] Specifically, based on the determination of each segmentation edge point, the segmentation edge points are screened to determine at least one skeleton endpoint in the coronary artery skeleton line. Optionally, the method for determining the skeleton endpoint in this embodiment may include: for any segmentation edge point, determining the edge segmentation line segment corresponding to the current segmentation edge point based on the current segmentation edge point and a preset number of adjacent edge points; determining the line curvature of the edge segmentation line segment; determining whether the current segmentation edge point is a segmentation endpoint based on the line curvature and a preset curvature threshold; and determining the skeleton endpoint based on each segmentation endpoint and the coronary artery skeleton line.

[0081] Here, the edge segmentation line segment can be understood as an edge segmentation line segment composed of the current segmentation edge point and a preset number of adjacent edge points on both sides of the current segmentation edge point. The line segment curvature can be understood as the degree of bending of the edge segmentation line segment. In practical applications, the curvature of the line segment at the inflection point of the segmentation result is greater than the curvature of the line segment at other positions. Therefore, based on the line segment curvature of the edge segmentation line segment corresponding to each segmentation edge point, it can be determined whether each segmentation edge point is an inflection point of the segmentation result. Optionally, in this embodiment, any existing method for determining the line segment curvature can be used to determine the line segment curvature of the edge segmentation line segment, and a preset curvature threshold is used to compare it with the segmentation edge line segments of each segmentation edge point to determine the segmentation inflection point in each segmentation edge point.

[0082] Optionally, in practical applications, not all segmentation inflection points are segmentation endpoints; some segmentation inflection points may be segmentation branch points in the segmentation result. See examples below. Figure 4 . Figure 4 For another coarse segmentation image of the coronary artery, in Figure 4 In this embodiment, the segmentation inflection points contained within the region of interest enclosed in a square frame are segmentation branch points, and the segmentation inflection points contained within the region of interest enclosed in a circular frame are segmentation endpoints. Optionally, the method for determining whether a segmentation inflection point is a segmentation endpoint may include acquiring each pixel within a preset region including the segmentation inflection point. If the number of pixels in the segmented result is greater than the number of background pixels, then the current segmentation inflection point is a segmentation endpoint; conversely, if the number of background pixels is greater than the number of pixels in the segmented result, then the current segmentation inflection point is a segmentation branch point. Optionally, the segmentation inflection point and the coarse segmentation image of the coronary artery can also be simultaneously input into a pre-trained segmentation endpoint recognition model to obtain the recognition result output by the model. Of course, recognition can also be performed based on other methods, which are not limited in this embodiment.

[0083] It should be noted that the skeleton endpoints can be understood as the endpoints of each branch in the coronary artery skeleton line. Furthermore, other skeleton points in the coronary artery skeleton line refer to other types of skeleton points, such as skeleton branch points and skeleton center points.

[0084] Specifically, since the coarse segmentation result of the coronary artery may contain multiple segmentation endpoints at the branch endpoints, based on this, each segmentation endpoint is compared with the coronary artery skeleton line of the coarse segmentation result, and the segmentation endpoints that coincide with the coronary artery skeleton line are determined as skeleton endpoints.

[0085] See examples Figure 5 In the diagram, square dots represent the endpoints of the coronary artery skeleton line, while circular and rectangular dots represent other types of skeleton points, such as skeleton branch points.

[0086] S130. Determine the root endpoint and at least one terminal branch endpoint among the skeleton endpoints, and determine the venous branch segments in the coronary skeleton line based on the skeleton connection path between the root endpoint and each terminal branch endpoint.

[0087] In this embodiment, the root endpoint can be understood as the branch endpoint of a coronary artery branch originating from the aorta. Specifically, the root endpoint includes a left root endpoint and a right root endpoint. In practical applications, the aorta branches into two coronary artery branches on the left and right sides, respectively, in the left and right sinus regions. Therefore, the point where the left sinus region connects to the left coronary artery branch is the left root endpoint, and the point where the right sinus region connects to the right coronary artery branch is the right root endpoint. The terminal endpoint can be understood as the endpoint of the final branch of each coronary artery branch.

[0088] See examples Figure 6 In the diagram, the thickest vessel in the middle is the aorta, which has been divided. The aorta branches into two branches: the left coronary artery branch and the right coronary artery branch. The point where the left branch connects to the aorta is the left endpoint of the root, and the point where the right branch connects to the aorta is the right endpoint of the root. See also... Figure 6 The terminal endpoints of the branches of the coronary arteries are called terminal branch endpoints.

[0089] Optionally, the method for determining the root endpoint and at least one terminal branch endpoint among the skeleton endpoints in this embodiment may include: determining the aorta location in the coarse segmentation image of the coronary artery, and determining the root endpoint and at least one terminal branch endpoint among the skeleton endpoints based on the aorta location and the location of each skeleton endpoint.

[0090] Specifically, a pre-trained endpoint classification model can be obtained. Based on the endpoint positions of each skeletal endpoint and the arterial position of the aorta, the root endpoint and terminal branch endpoint among the skeletal endpoints can be determined using the aforementioned endpoint classification model. Optionally, the technical solution of this embodiment can also be to determine whether each skeletal endpoint is connected to the left or right sinus in the aorta. If so, it is identified as the left or right root endpoint; otherwise, it is identified as the terminal branch endpoint. This embodiment can also use other methods to identify endpoints, and the comparison is not limited.

[0091] Furthermore, based on determining the root endpoint and at least one terminal branch endpoint in each skeleton endpoint, the skeleton connection path between the root endpoint and each terminal branch endpoint is determined, and the venous branch segments in the coronary skeleton line are determined based on the skeleton connection path.

[0092] In this context, a skeletonized connected path can be understood as a skeleton line segment consisting of two skeleton points and all other skeleton points between them. Similarly, a skeletonized connected path between the root endpoint and each of the terminal endpoints can be understood as a skeleton line segment between the root endpoint and each of the terminal endpoints.

[0093] Optionally, the skeleton connectivity path can be determined based on a pre-trained neural network model, or it can be obtained based on a traditional image algorithm. This embodiment does not limit this.

[0094] Furthermore, vein branch segment identification is performed based on the skeleton connectivity path determined above. Optionally, a pre-trained vein branch identification algorithm can be obtained, and the obtained skeleton connectivity path can be input into the vein branch identification algorithm to obtain the vein branch segment identification result output by the model. Other vein branch identification results can also be used, and this embodiment of the invention is not limited thereto.

[0095] For example, in determining Figure 6 Based on the identified root endpoints and terminal endpoints, the skeletal connectivity paths between the root endpoints and each terminal endpoint are determined using the coronary artery skeleton line. For example, a schematic diagram of the skeletal connectivity paths between the root endpoints and each terminal endpoint is shown below. Figure 7 As shown. Furthermore, regarding... Figure 7 The vein branches are identified by performing vein branch identification on each skeleton connection path in the graph, resulting in vein branch segments. An example vein branch segment is shown below. Figure 8 As shown.

[0096] S140. Coronary artery segmentation image based on coarse segmentation of coronary artery image and venous branch segments to determine the initial vascular image.

[0097] In this embodiment of the invention, based on the determination of venous branch segments, vein removal is performed on the coarse segmentation image of the coronary artery based on the venous branch segments to obtain the coronary artery segmentation result.

[0098] Optionally, a method for removing veins from a coarsely segmented coronary artery image based on vein branch segments to obtain coronary artery segmentation results may include: obtaining branch extension parameters of vein branches, and performing extension processing on vein branches based on branch extension parameters to obtain vein extension images corresponding to vein branches; and performing vein removal processing on the coarsely segmented coronary artery image based on the vein extension images to obtain a coronary artery segmentation image of the initial vascular image.

[0099] In this embodiment, the branch expansion parameter can be understood as the expansion diameter parameter that the venous branch segment needs to be expanded. The branch expansion parameter may include the endpoint expansion parameter and the center expansion parameter of the venous branch segment.

[0100] It should be noted that, in this embodiment, the vein extension image obtained after extending the vein branch segments based on the extension parameters must completely cover the vein branches in the coarse coarse segmentation image of the coronary artery. Only under these conditions can vein removal processing be performed on the vein branches in the coarse coarse segmentation image of the coronary artery based on the vein extension image. Therefore, it is necessary to determine the branch extension parameters for extending the vein branch segments based on the coarse segmentation results in the coarse coarse segmentation image of the coronary artery.

[0101] Specifically, a coarse segmentation image of the coronary arteries can be obtained by performing coarse segmentation of the initial vascular image using existing segmentation techniques, or by performing segmentation processing on the initial vascular image using traditional image processing algorithms. This embodiment does not limit the segmentation method.

[0102] Furthermore, based on the determination of each venous branch segment, the venous branch segments are expanded to obtain an expanded venous image. Optionally, the expansion processing method in this embodiment may include: for any endpoint of any venous branch segment, the endpoint expansion parameter is determined based on the segment endpoint parameter of the venous branch segment and the vascular parameters of other vessels connected to the venous branch in the coarse segmentation image of the coronary artery. Further, based on the determination of the endpoint expansion parameters of the two endpoints of the venous branch segment, the expansion parameter of the midpoint of the venous branch segment is fitted using the two endpoint expansion parameters to determine at least one center point expansion parameter of the venous branch segment. Then, each endpoint expansion parameter and each center point expansion parameter are used as expansion targets to expand the venous branch segment, obtaining an expanded venous image of the venous branch segment. Optionally, based on the above implementation method, all venous branch segments are traversed to obtain expanded venous images respectively.

[0103] Furthermore, based on the determined venous extension image and coarse segmentation image of the ...

[0104] For example, for Figure 8 The venous branch segments shown are expanded to obtain the following: Figure 9 The image shown depicts an expanded vein, and based on this expanded vein image, [the following is a list of parameters / methods]. Figure 2 The coarse segmentation image of the coronary artery shown is processed by removing vein branches to obtain the following result: Figure 10 The image shown is a segmented image of the coronary arteries.

[0105] The vascular image segmentation method provided in this invention acquires an initial vascular image, determines a coarse coarse segmentation image of the coarse coarse segmentation image, and determines the coarse coarse segmentation skeleton line of the coarse coarse segmentation image; performs edge recognition on the coarse coarse segmentation image to obtain at least one segmentation edge point in the coarse coarse segmentation image, and determines at least one skeleton endpoint in each coarse coarse segmentation skeleton line based on each segmentation edge point; determines the root endpoint and at least one terminal branch endpoint in each skeleton endpoint, and determines the venous branch segment in the coarse coarse segmentation skeleton line based on the skeleton connection path between the root endpoint and each terminal branch endpoint; and determines the coarse segmentation image of the initial vascular image based on the coarse coarse segmentation image and the venous branch segment. The above technical solution processes the vascular image to be segmented to obtain each endpoint in the vascular system; identifies the vascular systems between each endpoint to obtain the venous branches; and then optimizes the coarse coarse segmentation result based on the identified venous branches to obtain the final coarse coarse segmentation result, thereby improving the accuracy of coarse coarse segmentation.

[0106] Figure 11 This is a flowchart of another vascular image segmentation method provided by an embodiment of the present invention. Based on the above implementation, this embodiment optionally determines the venous branch segments in the coronary artery skeleton line based on the skeleton connectivity path between the root endpoint and each terminal branch endpoint, including:

[0107] Obtain each skeleton segment in the coronary artery skeleton line, and determine the number of skeleton connection paths between the root endpoint and any terminal branch endpoint based on each skeleton segment.

[0108] For any terminal endpoint, if the number of current paths is greater than a preset threshold, then obtain the skeleton segments of each branch in the skeleton connected path between the current terminal endpoint and the root endpoint.

[0109] The venous branch segments in the coronary artery skeleton line are determined based on the segment lines of each branch skeleton. For example... Figure 11 As shown, the method includes:

[0110] S210. Obtain the initial blood vessel image, determine the coronary artery coarse segmentation image of the initial blood vessel image, and determine the coronary artery skeleton line of the coronary artery coarse segmentation image.

[0111] S220. Perform edge recognition on the coarse segmentation image of the coarse segmentation of the coarse segmentation image of the coarse segmentation of the coarse segmentation image of the coarse segmentation, and determine at least one skeleton endpoint of each coarse skeleton line based on each segmentation edge point.

[0112] S230. Determine the root endpoint and at least one end endpoint among the skeleton endpoints.

[0113] S240. Obtain each skeleton segment in the coronary artery skeleton line, and determine the skeleton connection path between the root endpoint and any terminal branch endpoint based on each skeleton segment.

[0114] In this embodiment of the invention, since the coronary artery is divided into a left coronary artery branch and a right coronary artery branch, when determining the skeleton connection path between the root endpoint and the terminal endpoint, it is necessary to determine the left endpoint of the root and each terminal endpoint of the left coronary artery branch, as well as the right endpoint of the root and each terminal endpoint of the right coronary artery branch.

[0115] Based on each skeleton line segment, determine the skeleton connectivity path between the current root endpoint and any last branch endpoint on the current side. Optionally, the determination method for any side can be: obtain a pre-trained skeleton connectivity path extraction model, input the current root endpoint, any last branch endpoint on the current side, and their respective skeleton lines into the skeleton connectivity path extraction model to obtain the skeleton connectivity path between the current root endpoint and any last branch endpoint on the current side; alternatively, the method for obtaining the skeleton connectivity path between the current root endpoint and any last branch endpoint on the current side can also be to obtain a path calculation algorithm, and perform path calculation on the current root endpoint, any last branch endpoint on the current side, and the skeleton lines to which the skeleton branch points belong based on the path calculation algorithm to determine the skeleton connectivity path between the current root endpoint and any last branch endpoint on the current side. Of course, the skeleton connectivity path between the current root endpoint and any last branch endpoint on the current side can also be obtained by traversing each skeleton point on the skeleton line. This embodiment does not limit the method for determining the skeleton connectivity path.

[0116] S250. For any terminal endpoint, determine the number of skeleton connected paths between the current terminal endpoint and the root endpoint. If the number of paths is greater than a preset threshold, obtain the skeleton segments of each branch in the skeleton connected path between the current terminal endpoint and the root endpoint.

[0117] Furthermore, the skeleton connectivity paths from the root endpoint to the same end endpoint are encoded, and the number of skeleton connectivity paths is determined based on the number of encodings.

[0118] In practical applications, since coronary arteries do not have compensatory branches, a pre-set threshold of one branch is used. Based on the aforementioned skeletal connectivity paths, the root and terminal endpoints corresponding to the number of connectivity paths exceeding the threshold are determined. Further, the branch skeletal segments between the selected root and terminal endpoints are determined. For example, the branch skeletal segments between the selected root and terminal endpoints are as follows: Figure 12 As shown.

[0119] S260. Determine the venous branch segments in the coronary artery skeleton line based on the branch skeleton segments.

[0120] Optionally, the method for identifying veins in each non-overlapping segment may include: comparing the overlap of each branch skeleton segment to obtain the non-overlapping segments in each branch skeleton segment; and identifying veins in each non-overlapping segment to obtain the venous branch segments in the coronary artery skeleton line.

[0121] Specifically, multiple branch skeleton segments with root and terminal endpoints are selected separately, and a skeleton segment traversal is performed on each of these segments. Based on the traversal results, non-overlapping segments are identified within the branch skeleton segments. For example, for... Figure 12 In the skeleton connected paths shown, non-overlapping line segments are removed to identify overlapping line segments, thus determining the non-overlapping line segments in each skeleton connected path. See the example below. Figure 13 , Figure 13 These are the non-overlapping line segments remaining after removal.

[0122] In practical applications, Figure 13 In the coarse segmentation of coronary arteries, non-overlapping line segments represent branching loops formed by intersecting venous and coronary artery branches, or possibly branching loops formed by adhered coronary arteries. To obtain accurate coronary artery segmentation results, it is necessary to identify the branching line segments in these branching loops. If the identification result includes venous branches, the identified venous branches are removed to obtain accurate segmentation results; conversely, if the identification result does not include venous branches, it indicates that the above loop is a branching loop formed by adhered coronary arteries, and it is necessary to identify and remove the adhered areas in the above branches to achieve accurate coronary artery segmentation results.

[0123] Optionally, in this embodiment, the method for identifying veins in each non-overlapping line segment to obtain vein branch segments may include: for any non-overlapping line segment, determining the line segment curvature of the current non-overlapping line segment; and based on the comparison result of the line segment curvature and a preset curvature threshold, determining the vein branch segment identification result of the current non-overlapping line segment.

[0124] Curvature is used to represent the degree of bending of a line segment. In practical applications, coronary arteries are more tortuous than veins, so an appropriate curvature threshold is set in advance based on the tortuous characteristics of coronary arteries.

[0125] Specifically, the curvature of each non-overlapping segment is calculated, and each segment's curvature is compared with a preset curvature threshold. Based on the comparison results, the identification result of the venous branch segment for each non-overlapping segment is determined. Optionally, if the curvature of the current non-overlapping segment is greater than the curvature threshold, it indicates that the current non-overlapping segment is a coronary artery branch; conversely, if the curvature of the current non-overlapping segment is less than the curvature threshold, it indicates that the current non-overlapping segment is a venous branch.

[0126] Optionally, the method for identifying veins in each non-overlapping line segment to obtain vein branch segments in this embodiment may further include: for any non-overlapping line segment, determining the average value of blood vessel pixels in the current non-overlapping line segment; and determining the vein branch segment identification result of the current non-overlapping line segment based on the comparison result between the average value of blood vessel pixels and a preset pixel threshold.

[0127] In practical applications, during CT angiography, in order to better visualize the coronary arteries, the contrast agent is designed to have a higher concentration in the coronary arteries of the blood circulation system. This means that the image brightness of the coronary arteries is greater during CT imaging, so the pixel value of the coronary arteries is higher than that of the veins. Therefore, an appropriate pixel value threshold is set in advance based on the pixel characteristics of the coronary arteries.

[0128] Specifically, the average pixel value of the blood vessel for each non-overlapping line segment is calculated. Specifically, for any non-overlapping line segment, the corresponding blood vessel segment is determined based on the current non-overlapping line segment's position within the initial blood vessel, and the pixel value of each pixel corresponding to the current blood vessel segment is calculated, thus obtaining the average pixel value corresponding to the current non-overlapping line segment.

[0129] Furthermore, the average pixel value of each blood vessel is compared with a preset pixel threshold, and the identification result of the vein branch segment of each non-overlapping line segment is determined based on the pixel comparison result. Optionally, if the average pixel value of the blood vessel of the current non-overlapping line segment is greater than the pixel threshold, it is said that the current non-overlapping line segment is a coronary artery branch; conversely, if the average pixel value of the blood vessel of the current non-overlapping line segment is less than the pixel threshold, it is said that the current skeleton line segment is a vein branch.

[0130] Based on the above embodiments, the technical solution of this invention for identifying venous branch segments can further be based on traversing the skeleton connection paths between the current root endpoint and each terminal endpoint in the current side for each skeleton segment. For each terminal endpoint, the longest connected path among the skeleton connection paths between the terminal endpoint and the root endpoint is determined. Optionally, if there is only one skeleton connection path between the root endpoint and the terminal endpoint, then that path is the longest connected path; if there are multiple skeleton connection paths between the root endpoint and the terminal endpoint, then the skeleton connection path containing the most skeleton points is determined as the longest connected path. Further, the difference between the combined path of the longest connected path corresponding to each terminal endpoint and the coronary artery skeleton line is calculated, and the difference result is the identified venous branch segment.

[0131] Based on the above embodiments, the technical solution of this embodiment can also perform vein recognition by calculating other image statistical information of non-overlapping line segments, such as determining the direction of blood flow in the blood vessels of the non-overlapping line segments. Of course, vein recognition can also be performed based on the comparison results between each non-overlapping line segment, and this embodiment does not limit this.

[0132] S270. Coronary artery segmentation image based on coarse segmentation of the coronary artery and venous branch segments to determine the initial vascular image.

[0133] The technical solution of this invention involves processing the blood vessel image to be segmented to obtain each endpoint of the blood vessel; identifying the blood vessels between each endpoint to obtain the venous branches; and then optimizing the coronary artery segmentation result based on the identified venous branches to obtain the final coronary artery segmentation result, thereby improving the accuracy of coronary artery segmentation.

[0134] Figure 14 This is a schematic diagram of a blood vessel image segmentation device provided in an embodiment of the present invention. Figure 14 As shown, the device includes: a coarse coarse segmentation image determination module 310, a skeleton endpoint determination module 320, a venous branch segment determination module 330, and a coronary artery segmentation image determination module 340; wherein,

[0135] The coarse segmentation image determination module 310 is used to acquire an initial blood vessel image, determine the coarse segmentation image of the coarse segmentation image of the initial blood vessel image, and determine the coarse segmentation line of the coarse segmentation image ...

[0136] The skeleton endpoint determination module 320 is used to perform edge recognition on the coarse segmentation image of the coarse segmentation of the coarse segmentation of the coarse segmentation image ...

[0137] The venous branch segment determination module 330 is used to determine the root endpoint and at least one terminal branch endpoint among the skeleton endpoints, and to determine the venous branch segments in the coronary artery skeleton line based on the skeleton connection path between the root endpoint and each terminal branch endpoint.

[0138] The coronary artery segmentation image determination module 340 is used to determine the coronary artery segmentation image of the initial blood vessel image based on the coarse segmentation image of the coronary artery and the venous branch line segments.

[0139] Based on the above embodiments, optionally, the skeleton endpoint determination module 320 includes:

[0140] A mutation pixel determination unit is used to obtain the pixel value of each pixel in the coarse segmentation image of the coronary artery and determine at least one mutation pixel based on each pixel value.

[0141] The segmentation edge point determination unit is used to determine at least one segmentation edge point in the coarse segmentation image of the coronary artery based on each of the abrupt pixel points.

[0142] Based on the above embodiments, optionally, the skeleton endpoint determination module 320 includes:

[0143] An edge segmentation line segment determination unit is used to determine the edge segmentation line segment corresponding to any segmentation edge point based on the current segmentation edge point and a preset number of adjacent edge points of the current segmentation edge point;

[0144] The segment endpoint determination unit is used to determine the curvature of the edge segmentation line segment, and determine whether the current segmentation edge point is a segment endpoint based on the line segment curvature and a preset curvature threshold.

[0145] The skeleton endpoint determination unit is used to determine the skeleton endpoints based on each of the segmented endpoints and the coronary artery skeleton line.

[0146] Based on the above implementation method, optionally, the vein branch segment determination module 330 includes:

[0147] An endpoint determination unit is used to determine the aortic position in the coarse segmentation image of the coronary artery, and to determine the root endpoint and at least one terminal branch endpoint among the skeleton endpoints based on the aortic position and the position of each skeleton endpoint.

[0148] Based on the above implementation method, optionally, the vein branch segment determination module 330 includes:

[0149] The skeleton connectivity path determination unit is used to obtain each skeleton segment in the coronary artery skeleton line, and determine the skeleton connectivity path between the root endpoint and any terminal branch endpoint based on each skeleton segment.

[0150] The branch skeleton segment determination unit is used to determine the number of skeleton connected paths between the current end endpoint and the root endpoint for any end endpoint. If the number of paths is greater than a preset threshold, then each branch skeleton segment in the skeleton connected path between the current end endpoint and the root endpoint is obtained.

[0151] A venous branch segment determination unit is used to determine the venous branch segments in the coronary artery skeleton line based on each of the branch skeleton segments.

[0152] Based on the above embodiments, optionally, the vein branch segment determination unit includes:

[0153] The non-overlapping line segment determination subunit is used to compare the line segments of each branch skeleton line segment to obtain the non-overlapping line segments in each branch skeleton line segment.

[0154] The vein branch segment determination subunit is used to identify veins in each of the non-overlapping segments to obtain the vein branch segments in the coronary artery skeleton line.

[0155] Based on the above embodiments, optionally, the coronary artery segmentation image determination module 340 includes:

[0156] The coarse segmentation image determination unit is used to perform coarse segmentation of the initial blood vessel image to obtain a coarse segmentation image of the coarse blood vessel image of the initial blood vessel image.

[0157] A vein expansion image determination unit is used to obtain the branch expansion parameters of the vein branch, and perform expansion processing on the vein branch based on the branch expansion parameters to obtain the vein expansion image corresponding to the vein branch;

[0158] The coronary artery segmentation image determination unit is used to perform vein removal processing on the coarse segmentation image of the coronary artery based on the vein extension image to obtain the coronary artery segmentation image of the initial blood vessel image.

[0159] The blood vessel image segmentation device provided in the embodiments of the present invention can execute the blood vessel image segmentation method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method.

[0160] Figure 15A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0161] like Figure 15 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0162] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0163] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of 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 suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as blood vessel image segmentation methods.

[0164] In some embodiments, the blood vessel image segmentation method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or mounted on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the blood vessel image segmentation method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the blood vessel image segmentation method by any other suitable means (e.g., by means of firmware).

[0165] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0166] Computer programs for implementing the vascular image segmentation method of the present invention 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, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0167] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0168] To provide interaction with a user, the systems and techniques described herein 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 pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; 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 sound input, voice input, or tactile input).

[0169] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0170] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0171] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0172] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. 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 substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for segmenting blood vessel images, characterized in that, include: Acquire an initial vascular image, determine a coarse segmentation image of the coarse segmentation image of the coarse vascular ... Edge recognition is performed on the coarse segmentation image of the coarse segmentation of the coarse segmentation of the coarse segmentation of the coarse segmentation of the coarse segmentation image ... Identify the root endpoint and at least one terminal branch endpoint among the said skeleton endpoints, and determine the venous branch segments in the coronary artery skeleton line based on the skeleton connectivity path between the root endpoint and each of the said terminal branch endpoints; The coronary artery segmentation image of the initial vascular image is determined based on the coarse segmentation image of the coronary artery and the line segments of the vein branches; Wherein, determining at least one skeleton endpoint of each of the coronary artery skeleton lines based on each of the segmentation edge points includes: For any segmentation edge point, the edge segmentation line segment corresponding to the current segmentation edge point is determined based on the current segmentation edge point and a preset number of adjacent edge points of the current segmentation edge point; Determine the curvature of the edge segment, and determine whether the current segmentation edge point is a segmentation endpoint based on the segment curvature and a preset curvature threshold; The skeleton endpoints are determined based on each of the segmentation endpoints and the coronary artery skeleton line; Among them, the edge segmentation line segment is a line segment composed of the current segmentation edge point and a preset number of adjacent edge points on the left and right sides of the current segmentation edge point; The step of determining the venous branch segments in the coronary artery skeleton line based on the skeleton connectivity path between the root endpoint and each of the terminal branch endpoints includes: Obtain each skeleton segment in the coronary artery skeleton line, and determine the skeleton connection path between the root endpoint and any terminal branch endpoint based on each skeleton segment; For any terminal endpoint, determine the number of skeleton connection paths between the current terminal endpoint and the root endpoint; If the number of paths is greater than a preset threshold, then obtain the skeleton segments of each branch in the skeleton connection path between the current last endpoint and the root endpoint. The venous branch segments in the coronary artery skeleton line are determined based on each of the aforementioned branch skeleton segments; The preset quantity threshold is 1.

2. The method of claim 1, wherein, The step of performing edge recognition on the coarse segmentation image of the coarse ... Obtain the pixel value of each pixel in the coarse segmentation image of the coronary artery, and determine at least one abrupt pixel based on each pixel value; At least one segmentation edge point in the coarse segmentation image of the coronary artery is determined based on each of the aforementioned mutated pixel points.

3. The method of claim 1, wherein, Determining the root endpoint and at least one terminal endpoint among the skeleton endpoints includes: The aorta location in the coarse segmentation image of the coronary artery is determined, and the root endpoint and at least one terminal branch endpoint in each of the skeleton endpoints are determined based on the aorta location and the location of each skeleton endpoint.

4. The method according to claim 1, characterized in that, The step of determining the venous branch segments in the coronary artery skeleton line based on each of the branch skeleton segments includes: By comparing the line segments of each branch skeleton line segment, the non-overlapping line segments in each branch skeleton line segment are obtained. Vein identification is performed on each of the non-overlapping segments to obtain the venous branch segments in the coronary artery skeleton line.

5. The method of claim 1, wherein, The method of determining the coronary artery segmentation image based on the coarse segmentation image of the coronary arteries and the venous branches, includes: Obtain the branch expansion parameters of the vein branch, and perform expansion processing on the vein branch based on the branch expansion parameters to obtain the vein expansion image corresponding to the vein branch; Based on the vein extension image, the coarse segmentation image of the coronary artery is processed to remove veins, thereby obtaining the coronary artery segmentation image of the initial blood vessel image.

6. A blood vessel image segmentation apparatus characterized by comprising: include: The coarse segmentation image determination module for coarse segmentation of ... The skeleton endpoint determination module is used to perform edge recognition on the coarse segmentation image of the coarse segmentation ... A venous branch segment determination module is used to determine the root endpoint and at least one terminal branch endpoint among the skeleton endpoints, and to determine the venous branch segments in the coronary artery skeleton line based on the skeleton connection path between the root endpoint and each terminal branch endpoint. A coronary artery segmentation image determination module is used to determine the coronary artery segmentation image of the initial blood vessel image based on the coarse coronary artery segmentation image and the venous branch line segments; The skeleton endpoint determination module includes: An edge segmentation line segment determination unit is used to determine the edge segmentation line segment corresponding to any segmentation edge point based on the current segmentation edge point and a preset number of adjacent edge points of the current segmentation edge point; The segment endpoint determination unit is used to determine the curvature of the edge segmentation line segment, and determine whether the current segmentation edge point is a segment endpoint based on the line segment curvature and a preset curvature threshold. A skeleton endpoint determination unit is used to determine the skeleton endpoints based on each of the segmented endpoints and the coronary artery skeleton line; Among them, the edge segmentation line segment is a line segment composed of the current segmentation edge point and a preset number of adjacent edge points on the left and right sides of the current segmentation edge point; The venous branch segment determination module includes: The skeleton connectivity path determination unit is used to obtain each skeleton segment in the coronary artery skeleton line, and determine the skeleton connectivity path between the root endpoint and any terminal branch endpoint based on each skeleton segment. The branch skeleton segment determination unit is used to determine the number of skeleton connected paths between the current end endpoint and the root endpoint for any end endpoint. If the number of paths is greater than a preset threshold, then each branch skeleton segment in the skeleton connected path between the current end endpoint and the root endpoint is obtained. A venous branch segment determination unit is used to determine the venous branch segments in the coronary artery skeleton line based on each of the branch skeleton segments; The preset quantity threshold is 1.

7. An electronic device, comprising: The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the blood vessel image segmentation method according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the blood vessel image segmentation method according to any one of claims 1-5.

Images