A method, matching device, equipment, and storage medium for matching the center line of blood vessels.

Abstract

This application provides a method, device, equipment, and storage medium for matching vascular centerlines, comprising: acquiring a first vascular centerline in a first coronary angiography image and a second vascular centerline in a second coronary angiography image; for each first vascular center point, determining an initial point pair matching anomaly based on the intersection of the polar line corresponding to the first vascular center point and the second vascular centerline; and determining the second vascular center point to be matched with the first vascular center point based on the intersection of the polar line corresponding to the first vascular center point and the second vascular centerline, and the second vascular center points already matched with the previous first vascular center point. In this way, it is possible to accurately determine an anomaly in the point pair matching of a certain point on the vascular centerline based on the intersection of the polar lines, and to correct the matching relationship based on the intersection and other determined point pairs, thereby re-determining the matching point of the vascular center point.

Description

Technical Field

[0001] This application relates to the field of medical image processing technology, and in particular to a method, matching device, equipment and storage medium for matching the center line of blood vessels. Background Technology

[0002] Coronary angiography is a commonly used and effective method for diagnosing coronary atherosclerotic heart disease (CAD). It is a relatively safe and reliable invasive diagnostic technique, widely used in clinical practice and considered the "gold standard" for diagnosing CAD. The procedure involves injecting contrast agent into the coronary arteries via a catheter, followed by X-ray imaging to obtain 2D coronary angiographic images. In the process of 3D reconstruction of blood vessels based on these angiographic images, the accuracy of the pairwise matching of points along the vessel centerlines in the two images determines whether a 3D model can be generated and the accuracy of that model, ultimately affecting the diagnostic results and treatment plan. Therefore, rapidly obtaining accurate point-to-point matching relationships along the vessel centerlines is a crucial step in angiographic image vascular analysis.

[0003] Existing methods for matching vascular centerlines mainly include epipolar tracing and segment matching. Epipolar tracing requires precise alignment of the vessel; when the epipolar line intersects with the vessel at multiple points, it becomes difficult to select the correct intersection, leading to mismatches. Alternatively, if the vessel and epipolar line do not intersect, a mismatch occurs. Segment matching only considers the start and end points, distributing intermediate points evenly, which can cause mismatches and local mismatches. The mismatches and misalignments in the centerline point pairs generated by existing methods can lead to errors or even failures in generating the 3D model, rendering it unanalyzable and impacting disease diagnosis and treatment. Summary of the Invention

[0004] In view of this, the purpose of this application is to provide a method, device, equipment and storage medium for matching the center line of a blood vessel, which can accurately determine the abnormality of the point pair matching of a certain point on the center line of a blood vessel based on the intersection of the polar lines, and correct it according to the intersection and the matching relationship of other point pairs that have been determined, thereby re-determining the matching point of the center point of the blood vessel, which is helpful for the subsequent establishment of the three-dimensional model of the blood vessel.

[0005] This application provides a method for matching the centerline of a blood vessel, the matching method comprising:

[0006] The centerline of the target blood vessel is acquired in the first coronary angiography image and the centerline of the second coronary angiography image; wherein the first coronary angiography image and the second coronary angiography image are captured from different angles;

[0007] For each first vessel center point included in the first vessel center line, based on the intersection of the polar line corresponding to the first vessel center point in the second coronary angiography image with the second vessel center line, it is determined whether there is an abnormality in the initial point pair matching of the first vessel center point in the second coronary angiography image;

[0008] If an anomaly occurs, the second vessel center point to be matched is determined based on the intersection of the polar line corresponding to the first vessel center point and the second vessel center line, and the second vessel center point that has been matched with the previous first vessel center point.

[0009] Furthermore, for each first vessel center point included in the first vessel center line, determining whether there is an anomaly in the initial point pair matching of the first vessel center point in the second coronary angiography image based on the intersection of the polar line corresponding to the first vessel center point with the second vessel center line in the second coronary angiography image includes:

[0010] If the polar line corresponding to the center point of the first blood vessel intersects the center line of the second blood vessel at multiple points, it is determined that the initial point pair matching of the center point of the first blood vessel in the second coronary angiography image is mismatched.

[0011] Alternatively, if the polar line corresponding to the center point of the first blood vessel does not intersect with the center line of the second blood vessel, then it is determined that the initial point pair matching of the center point of the first blood vessel in the second coronary angiography image has a mismatch.

[0012] Alternatively, if the polar line corresponding to the center point of the first blood vessel intersects the center line of the second blood vessel at exactly one point, then it is determined that the initial point pair matching of the center point of the first blood vessel in the second coronary angiography image is not abnormal.

[0013] Furthermore, if an anomaly occurs, the second vessel center point to be matched with the first vessel center point is determined based on the intersection of the polar line corresponding to the first vessel center point and the second vessel center line, and the second vessel center point already matched with the previous first vessel center point. This includes:

[0014] When a mismatch anomaly occurs, determine multiple intersection points between the polar line corresponding to the center point of the first blood vessel and the center line of the second blood vessel.

[0015] Based on the feature information of the second blood vessel center that has been matched with the previous first blood vessel center point and the multiple intersection points, the second blood vessel center point that should be matched with the first blood vessel center point is selected from the multiple intersection points; the feature information includes at least one of the following: distance information, direction information and image grayscale information.

[0016] Furthermore, the step of selecting the second vessel center point that should be matched by the first vessel center point from the multiple intersection points based on the feature information of the second vessel center point already matched with the first vessel center point and the multiple intersection points includes:

[0017] For each intersection point, based on the coordinates of the second blood vessel center that has been matched with the previous first blood vessel center point and the coordinates of the intersection point, determine the distance and direction vector from the second blood vessel center that has been matched with the previous first blood vessel center point to the intersection point;

[0018] Based on the coordinates of the second blood vessel center points that have been matched by the first two first blood vessel center points and the coordinates of the second blood vessel center that has been matched by the first first blood vessel center point, the reference direction vector from the second blood vessel center points that have been matched by the first two first blood vessel center points to the second blood vessel center that has been matched by the first first blood vessel center point is determined.

[0019] Based on the angle between the direction vector from the second blood vessel center that has been matched to the previous first blood vessel center point to the intersection point and the reference direction vector, the direction angle corresponding to the intersection point is determined.

[0020] Based on the gray value of the second vessel center that has been matched with the previous first vessel center point in the second coronary angiography image and the gray value of the intersection point, the gray value of the intersection point is determined.

[0021] Based on the distance from the second blood vessel center that has been matched to the previous first blood vessel center point to the intersection point, determine the distance probability corresponding to the intersection point;

[0022] Based on the directional angle corresponding to the intersection point, determine the directional probability corresponding to the intersection point;

[0023] Based on the gray level difference corresponding to the intersection point, determine the image gray level probability corresponding to the intersection point;

[0024] Based on the distance probability, direction probability, and image grayscale probability of the intersection point, determine the comprehensive probability that the intersection point is the second blood vessel center point that the first blood vessel center point should match.

[0025] The intersection point with the highest overall probability is determined as the second vessel center point that should be matched with the first vessel center point.

[0026] Furthermore, if an anomaly occurs, the second vessel center point to be matched with the first vessel center point is determined based on the intersection of the polar line corresponding to the first vessel center point and the second vessel center line, and the second vessel center point already matched with the previous first vessel center point. This includes:

[0027] When a mismatch occurs, multiple vessel center points are selected from the position of the second vessel center point that has been matched with the first vessel center point, starting from the position of the second vessel center point that was matched with the first vessel center point.

[0028] The blood vessel center point with the shortest distance to the polar line corresponding to the first blood vessel center point among the plurality of blood vessel center points is selected as the second blood vessel center point to be matched with the first blood vessel center point.

[0029] Furthermore, when there are no abnormalities in the initial point pair matching of the first vessel center point in the second coronary angiography image, the matching method further includes:

[0030] The intersection of the polar line corresponding to the center point of the first blood vessel and the center line of the second blood vessel is determined as the second blood vessel center point that should be matched with the center point of the first blood vessel.

[0031] This application embodiment also provides a matching device for the centerline of a blood vessel, the matching device comprising:

[0032] The acquisition module is used to acquire the center line of the first blood vessel in the first coronary angiography image and the center line of the second blood vessel in the second coronary angiography image; wherein the first coronary angiography image and the second coronary angiography image are captured from different angles;

[0033] The determination module is used to determine, for each first vessel center point included in the first vessel center line, whether there is an abnormality in the initial point pair matching of the first vessel center point in the second coronary angiography image based on the intersection of the polar line corresponding to the first vessel center point and the second vessel center line in the second coronary angiography image;

[0034] The matching module is used to determine the second blood vessel center point to be matched when an anomaly occurs, based on the intersection of the polar line corresponding to the first blood vessel center point and the second blood vessel center line, and the second blood vessel center point that has been matched with the previous first blood vessel center point.

[0035] Furthermore, when the determining module determines whether there is an abnormality in the initial point pair matching of each first vessel center point included in the first vessel center line, based on the intersection of the polar line corresponding to the first vessel center point in the second coronary angiography image and the second vessel center line, the determining module is used to:

[0036] If the polar line corresponding to the center point of the first blood vessel intersects the center line of the second blood vessel at multiple points, it is determined that the initial point pair matching of the center point of the first blood vessel in the second coronary angiography image is mismatched.

[0037] Alternatively, if the polar line corresponding to the center point of the first blood vessel does not intersect with the center line of the second blood vessel, then it is determined that the initial point pair matching of the center point of the first blood vessel in the second coronary angiography image has a mismatch.

[0038] Alternatively, if the polar line corresponding to the center point of the first blood vessel intersects the center line of the second blood vessel at exactly one point, then it is determined that the initial point pair matching of the center point of the first blood vessel in the second coronary angiography image is not abnormal.

[0039] Furthermore, when the matching module is used to determine the second vessel center point to be matched with the first vessel center point in the event of an anomaly, based on the intersection of the polar line corresponding to the first vessel center point and the second vessel center line, and the second vessel center point already matched with the previous first vessel center point, the matching module is used to:

[0040] When a mismatch anomaly occurs, determine multiple intersection points between the polar line corresponding to the center point of the first blood vessel and the center line of the second blood vessel.

[0041] Based on the feature information of the second blood vessel center that has been matched with the previous first blood vessel center point and the multiple intersection points, the second blood vessel center point that should be matched with the first blood vessel center point is selected from the multiple intersection points; the feature information includes at least one of the following: distance information, direction information and image grayscale information.

[0042] Furthermore, when the matching module is used to filter out the second vessel center point that should be matched with the first vessel center point from the multiple intersection points based on the feature information of the second vessel center point that has been matched with the previous first vessel center point and the multiple intersection points, the matching module is used to:

[0043] For each intersection point, based on the coordinates of the second blood vessel center that has been matched with the previous first blood vessel center point and the coordinates of the intersection point, determine the distance and direction vector from the second blood vessel center that has been matched with the previous first blood vessel center point to the intersection point;

[0044] Based on the coordinates of the second blood vessel center points that have been matched by the first two first blood vessel center points and the coordinates of the second blood vessel center that has been matched by the first first blood vessel center point, the reference direction vector from the second blood vessel center points that have been matched by the first two first blood vessel center points to the second blood vessel center that has been matched by the first first blood vessel center point is determined.

[0045] Based on the angle between the direction vector from the second blood vessel center that has been matched to the previous first blood vessel center point to the intersection point and the reference direction vector, the direction angle corresponding to the intersection point is determined.

[0046] Based on the gray value of the second vessel center that has been matched with the previous first vessel center point in the second coronary angiography image and the gray value of the intersection point, the gray value of the intersection point is determined.

[0047] Based on the distance from the second blood vessel center that has been matched to the previous first blood vessel center point to the intersection point, determine the distance probability corresponding to the intersection point;

[0048] Based on the directional angle corresponding to the intersection point, determine the directional probability corresponding to the intersection point;

[0049] Based on the gray level difference corresponding to the intersection point, determine the image gray level probability corresponding to the intersection point;

[0050] Based on the distance probability, direction probability, and image grayscale probability of the intersection point, determine the comprehensive probability that the intersection point is the second blood vessel center point that the first blood vessel center point should match.

[0051] The intersection point with the highest overall probability is determined as the second vessel center point that should be matched with the first vessel center point.

[0052] Furthermore, when the matching module is used to determine the second vessel center point to be matched with the first vessel center point in the event of an anomaly, based on the intersection of the polar line corresponding to the first vessel center point and the second vessel center line, and the second vessel center point already matched with the previous first vessel center point, the matching module is used to:

[0053] When a mismatch occurs, multiple vessel center points are selected from the position of the second vessel center point that has been matched with the first vessel center point, starting from the position of the second vessel center point that was matched with the first vessel center point.

[0054] The blood vessel center point with the shortest distance to the polar line corresponding to the first blood vessel center point among the plurality of blood vessel center points is selected as the second blood vessel center point to be matched with the first blood vessel center point.

[0055] Furthermore, when there is no anomaly in the initial point pair matching of the first vessel center point in the second coronary angiography image, the matching module is also used for:

[0056] The intersection of the polar line corresponding to the center point of the first blood vessel and the center line of the second blood vessel is determined as the second blood vessel center point that should be matched with the center point of the first blood vessel.

[0057] This application embodiment also provides an electronic device, including: a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus. When the machine-readable instructions are executed by the processor, they perform the steps of the above-described method for matching the centerline of a blood vessel.

[0058] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, performs the steps of the above-described method for matching the centerline of a blood vessel.

[0059] This application provides a method, device, equipment, and storage medium for matching vascular centerlines, comprising: acquiring a first vascular centerline of a target vascular vessel in a first coronary angiography image and a second vascular centerline in a second coronary angiography image; wherein the first coronary angiography image and the second coronary angiography image are captured from different angles; for each first vascular center point included in the first vascular centerline, determining whether the initial point pair matching of the first vascular center point in the second coronary angiography image is abnormal based on the intersection of the polar line corresponding to the first vascular center point in the second coronary angiography image and the second vascular centerline; if an abnormality occurs, determining the second vascular center point to be matched by the first vascular center point based on the intersection of the polar line corresponding to the first vascular center point and the second vascular centerline, and the second vascular center point already matched by the previous first vascular center point.

[0060] In this way, it is possible to accurately determine the point pair matching anomaly at a certain point on the blood vessel centerline based on the intersection of the epipolar lines, and correct it according to the intersection and the matching relationship of other point pairs that have been determined, thereby re-determining the matching point of the blood vessel centerline, which is helpful for the subsequent establishment of the blood vessel three-dimensional model.

[0061] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0062] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0063] Figure 1 A flowchart of a method for matching the centerline of a blood vessel provided in an embodiment of this application is shown;

[0064] Figures 2(a) and 2(b) show schematic diagrams of initial point pair matching of vascular centerlines using polar lines, provided in an embodiment of this application.

[0065] Figure 3 This illustration shows a schematic diagram of a mismatched blood vessel centerline provided in an embodiment of this application;

[0066] Figure 4 This illustration shows a schematic diagram of a mismatched anomaly in the centerline of a blood vessel, as provided in an embodiment of this application.

[0067] Figure 5 This illustration shows a schematic diagram of a matching device for the centerline of a blood vessel provided in an embodiment of this application;

[0068] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of this application is shown. Detailed Implementation

[0069] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. Based on the embodiments of this application, every other embodiment obtained by those skilled in the art without inventive effort falls within the scope of protection of this application.

[0070] Research has revealed that existing methods for matching vascular centerlines primarily include epipolar tracing and segment matching. Epipolar tracing is highly dependent on the vessel's orientation; when the epipolar line intersects with the vessel at multiple points, it becomes difficult to select the correct intersection, leading to mismatches. Alternatively, if the vessel and epipolar line do not intersect, a mismatch occurs. Segment matching, on the other hand, only considers the start and end points, distributing intermediate points evenly, which can result in some mismatches and localized mismatches. The mismatches and misalignments in the centerline point pairs generated by existing methods can lead to errors or even failures in generating the 3D model, rendering it unanalyzable and impacting disease diagnosis and treatment.

[0071] Based on this, embodiments of this application provide a method, device, equipment, and storage medium for matching blood vessel centerlines. This method can accurately determine an anomaly in the point pair matching of a certain point on the blood vessel centerline based on the intersection of the epipolar lines. It can also correct the point pair matching relationship based on the intersection and other determined point pairs, thereby re-determining the matching point of the blood vessel centerline, which is helpful for the subsequent establishment of a three-dimensional blood vessel model.

[0072] Please see Figure 1 , Figure 1 This is a flowchart illustrating a method for matching the centerline of a blood vessel, as provided in an embodiment of this application. Figure 1 As shown in the embodiments of this application, the matching method includes:

[0073] S101. Obtain the centerline of the first blood vessel in the first coronary angiography image and the centerline of the second blood vessel in the second coronary angiography image.

[0074] The first and second coronary angiography images are captured from different angles. The first vessel centerline includes multiple first vessel center points, and the second vessel centerline includes multiple initial second vessel center points. It should be noted that, in this embodiment, the initial second vessel center points are mainly used to determine the second vessel centerline, and thus determine the intersection of the polar line and the second vessel centerline. The second vessel center point that each first vessel center point should match does not necessarily coincide with any initial second vessel center point; that is, the vessel centerline matching in this embodiment does not involve matching multiple first vessel center points with multiple initial second vessel center points one by one.

[0075] In this step, the center line of the first blood vessel in the first coronary angiography image and the center line of the second blood vessel in the second coronary angiography image can be obtained by any method in the prior art, and this application is not limited thereto.

[0076] S102. For each first vessel center point included in the first vessel center line, based on the intersection of the polar line corresponding to the first vessel center point in the second coronary angiography image with the second vessel center line, determine whether there is an abnormality in the initial point pair matching of the first vessel center point in the second coronary angiography image.

[0077] Please refer to Figures 2(a) and 2(b), which show schematic diagrams of initial point pair matching of vascular centerlines using polar lines provided in an embodiment of this application.

[0078] The concept of the epipolar line is shown in Figures 2(a) and 2(b). First, a plane (called the epipolar plane) is formed by X-ray source 1, X-ray source 2, and center point 2. The intersection of this plane with image plane 1 is the epipolar line corresponding to center point 2. That is to say, the actual position of the 3D blood vessel spatial point on image plane 1 must lie on this epipolar line. Therefore, as long as the blood vessel point (center point 1) corresponding to this epipolar line is found, the true 3D center point of the blood vessel can be obtained by the intersection of two straight lines (the straight line connecting X-ray source 1 and center point 1, and the straight line connecting X-ray source 2 and center point 2). After completing the calculation of all points, the 3D blood vessel centerline can be obtained, which is an important step in completing 3D reconstruction.

[0079] In practice, firstly, along the 2D centerline on image plane 2, we can find the corresponding N epipolar lines on image plane 1 (N being the number of 2D centerline points on image plane 2). Ideally, each epipolar line intersects the 2D centerline on image plane 1 at exactly one point, thus finding the point pair matching relationship for each center point. Figure 2(b) shows the initial epipolar lines and initial point pair matching for each center point in image plane 2.

[0080] In the calculation, if the 3D spatial coordinates of X-ray source 1 are O1=(x1,y1,z1), the 3D spatial coordinates of X-ray source 2 are O2=(x2,y2,z2), and the 3D spatial coordinates of center point 2 are P=(x3,y3,z3), let the equation of the polar plane be Ax+By+Cz+D=0, where ABCD is the solution to the equation to be solved. Substituting the coordinates of points O1, O2, and P into the equation, we can obtain: A = (y3-y1)*(z3-z1)-(z2-z1)*(y3-y1); B = (x3-x1)*(z2-z1)-(x2-x1)*(z3-z1); C = (x2-x1)*(y3-y1)-(x3-x1)*(y2-y1); and D = -(A*x1+B*y1+C*z1), so we can find the value of D.

[0081] Let the equation of the polar plane be Ax + By + Cz + D = 0, and the equation of the image plane 1 be A1x + B1y + C1z + D1 = 0. Then, by combining the equations of the two planes, we can obtain the equation of the epipolar line as (x - x0) / a = (y - y0) / b = (z - z0) / c, where (a, b, c) are the direction vectors of the epipolar line, and (x0, y0, z0) is a point on the epipolar line.

[0082] Next, the intersection point between the epipolar line and the center line of image plane 1 is found, which determines the matching center point. After finding all point pairs, the matching of the vessel center lines is complete.

[0083] The experiment revealed that when the vessel centerline is curved, there may be multiple intersection points between the epipolar line and the centerline. Selecting the accurate intersection point becomes crucial; an incorrect selection can lead to a "mismatch," causing errors in the 3D model generation or even failure to analyze the data. Furthermore, when the epipolar line is parallel or nearly parallel to the vessel's direction, it may not intersect the centerline, or the intersection point may be outside the image range and therefore meaningless, resulting in a "mismatch" problem requiring manual correction. This prolongs the analysis time of the angiographic images, increases the burden on doctors, and may even extend surgical time, increasing the patient's surgical risk, which is also detrimental to the generation of the 3D model.

[0084] Accordingly, in one possible implementation, step S102 may include:

[0085] The first scenario: If the polar line corresponding to the center point of the first blood vessel has multiple intersection points with the center line of the second blood vessel, then it is determined that the initial point pair matching of the center point of the first blood vessel in the second coronary angiography image is mismatched.

[0086] Alternatively, in the second scenario: if the polar line corresponding to the center point of the first blood vessel does not intersect with the center line of the second blood vessel, then it is determined that the initial point pair matching of the center point of the first blood vessel in the second coronary angiography image is mismatched.

[0087] Alternatively, in a third scenario: if the polar line corresponding to the center point of the first blood vessel intersects the center line of the second blood vessel at exactly one point, then it is determined that the initial point pair matching of the center point of the first blood vessel in the second coronary angiography image is not abnormal.

[0088] S103. If an abnormality occurs, the second blood vessel center point to be matched is determined based on the intersection of the polar line corresponding to the first blood vessel center point and the second blood vessel center line, and the second blood vessel center point that has been matched with the previous first blood vessel center point.

[0089] Please see Figure 3 , Figure 3 This illustration shows a schematic diagram of a mismatched vascular centerline provided in an embodiment of this application.

[0090] In one possible implementation, when the mismatch anomaly in the first case described above occurs, step S103 may include:

[0091] S1031. When a mismatch anomaly occurs, determine multiple intersection points between the polar line corresponding to the center point of the first blood vessel and the center line of the second blood vessel.

[0092] For example, such as Figure 3As shown, in the first coronary angiography image, the polar line corresponding to a certain point on the center line of the first vessel intersects the center line of the second vessel at two points, q1 and q2, indicating a mismatch anomaly.

[0093] It should be noted that the second vessel centerline obtained in step S101 can be represented as a set of multiple initial second vessel center points in coordinate form. Therefore, when determining the intersection of the polar line and the second vessel centerline, the fitting straight line or curve equation can be solved based on the adjacent initial second vessel center points, thereby obtaining a set of equations in the form of a piecewise function of the second vessel centerline; the equation set is then combined with the polar line equation to determine the intersection of the polar line and the second vessel centerline.

[0094] S1032. Based on the feature information of the second blood vessel center that has been matched with the previous first blood vessel center point and the multiple intersection points, select the second blood vessel center point that should be matched with the first blood vessel center point from the multiple intersection points.

[0095] For example, such as Figure 3 As shown, the second vessel center that has been matched with the first vessel center point is p. i-1 (i is a positive integer), therefore, in this step, we can determine the value of p. i-1 The feature information of q1 and q2 is used to select the second blood vessel center point that should match the first blood vessel center point. The feature information includes at least one of the following: distance information, orientation information, and image grayscale information. The selection concept takes into account that the continuity of the vascular physiological structure may be represented by the similarity of feature information in the image. The intersection point that is more similar to the feature information of the second blood vessel center point that has been matched with the previous first blood vessel center point is selected as the second blood vessel center point to be matched.

[0096] In specific implementation, step S1032 may include:

[0097] Step 1: For each intersection point, based on the coordinates of the second blood vessel center that has been matched with the previous first blood vessel center point and the coordinates of the intersection point, determine the distance and direction vector from the second blood vessel center that has been matched with the previous first blood vessel center point to the intersection point.

[0098] In this step, assuming there are M intersection points for the i-th epipolar line, the distance from the previous epipolar line i-1 to each intersection point can be obtained based on the following formula:

[0099]

[0100] In the formula, p i-1 (x) and p i-1 (y) represents the horizontal and vertical coordinates of the second vessel center that has been matched with the previous first vessel center point; q j (x) and qj (y) represents the x and y coordinates of any intersection point.

[0101] The direction vector from the intersection point to the second blood vessel center that has been matched with the first blood vessel center point can be determined by subtracting the horizontal and vertical coordinates respectively.

[0102] Step 2: Based on the coordinates of the second blood vessel center points that have been matched by the first two first blood vessel center points and the coordinates of the second blood vessel center points that have been matched by the first first blood vessel center point, determine the reference direction vector from the second blood vessel center points that have been matched by the first two first blood vessel center points to the second blood vessel center points that have been matched by the first first blood vessel center point.

[0103] In this step, the coordinates of the second blood vessel center points that have been matched by the first two first blood vessel center points can be subtracted from the coordinates of the second blood vessel center points that have been matched by the first first blood vessel center points to determine the reference direction vector.

[0104] Step 3: Based on the angle between the direction vector from the second blood vessel center matched to the previous first blood vessel center point to the intersection point and the reference direction vector, determine the direction angle corresponding to the intersection point.

[0105] In this step, the included angle of the direction corresponding to the intersection point can be determined based on the following formula:

[0106]

[0107] In the formula, Represents the reference direction vector; This indicates the intersection point q between the second vessel center that was matched with the first vessel center point. j The direction vector.

[0108] Step 4: Based on the gray value of the second vessel center that has been matched with the previous first vessel center point in the second coronary angiography image and the gray value of the intersection point, determine the gray value difference corresponding to the intersection point.

[0109] In this step, the grayscale difference can be determined based on the following formula:

[0110] gray(p i-1 ,q j )=|I(p i-1 )-I(q j )|

[0111] In the formula, I(p) i-1 ) represents the grayscale value of the second coronary angiography image at the center of the second vessel that has been matched with the center point of the first vessel; I(q) j() represents the grayscale value of the second coronary angiography image at any intersection point.

[0112] Step 5: Based on the distance from the second blood vessel center that has been matched to the previous first blood vessel center point to the intersection point, determine the distance probability corresponding to the intersection point.

[0113] This approach is based on the fact that, following the normal course of blood vessels, among multiple intersection points, the point with the strongest continuity from the previous point has the highest probability. Therefore, in this step, the distance probability corresponding to the intersection point can be determined based on the following formula:

[0114] dist(p i-1 ,q j =10, if dist(p i-1 ,q j >10

[0115] dist(p i-1 ,q j ) = dist(p i-1 ,q j ), else

[0116]

[0117] Step 6: Determine the direction probability corresponding to the intersection point based on the included angle of the direction.

[0118] This is based on the fact that, under normal circumstances, the direction vector of the actual intersection point should not differ too much from the direction vector of the previous point; therefore, in this step, the direction probability corresponding to the intersection point can be determined based on the following formula:

[0119]

[0120] Step 7: Based on the gray level difference corresponding to the intersection point, determine the image gray level probability corresponding to the intersection point.

[0121] This is based on the imaging principle of coronary angiography. After the contrast agent is injected, it extends along the direction of the blood vessel, so the grayscale of the coronary angiography image should also change gradually. Therefore, in this step, the image grayscale probability corresponding to the intersection point can be determined based on the following formula:

[0122]

[0123] Step 8: Based on the distance probability, direction probability, and image grayscale probability of the intersection point, determine the comprehensive probability that the intersection point is the second blood vessel center point that the first blood vessel center point should match.

[0124] In this step, the distance probability, direction probability, and image grayscale probability of the intersection point can be weighted and summed to comprehensively determine the probability that the intersection point is the second blood vessel center point that the first blood vessel center point should match. The formula is expressed as:

[0125] p final (p i-1 ,q j )=w1p dist (p i-1 ,q j )+w2p angle (p i-1 ,q j )+w3p gray (p i-1 ,q j )

[0126] In the formula, w1, w2 and w3 represent the weights of each factor; for example, in the experiment, w1 = 0.6, w2 = 0.3 and w3 = 0.1.

[0127] Step 9: Determine the intersection point with the highest overall probability as the second blood vessel center point that should be matched with the first blood vessel center point.

[0128] Please see Figure 4 , Figure 4 This illustration shows a schematic diagram of a mismatched vascular centerline provided in an embodiment of this application.

[0129] In one possible implementation, when the mismatch anomaly in the second case described above occurs, step S103 may include:

[0130] S1033. When a mismatch occurs, among the multiple vessel center points included in the second vessel center line, multiple vessel center points are selected backward from the location of the second vessel center point that has been matched with the previous first vessel center point.

[0131] S1034. Select the blood vessel center point with the shortest distance to the polar line corresponding to the first blood vessel center point from among the plurality of blood vessel center points as the second blood vessel center point to be matched with the first blood vessel center point.

[0132] When the epipolar line is parallel or nearly parallel to the direction of the blood vessel, the epipolar line and the center line have no intersection point, or the intersection point is meaningless outside the image range. In this case, we take the point on the center point closest to the epipolar line as the approximate intersection point, but the condition for the approximate intersection point is that it cannot be in front of the already matched point, because the blood vessel cannot "go back"; therefore, in this step, the second blood vessel center point that should be matched by the first blood vessel center point can be determined based on the following formula:

[0133]

[0134]

[0135] In the formula, line i (a,b,c) represents the polar line corresponding to the center point of the first blood vessel; (a,b,c) represents the direction vector of the polar line.

[0136] Furthermore, when no anomaly occurs in the third scenario described above, the matching method further includes:

[0137] S104. The intersection of the polar line corresponding to the center point of the first blood vessel and the center line of the second blood vessel is determined as the second blood vessel center point that the first blood vessel center point should match.

[0138] Here, when the polar line corresponding to the center point of the first blood vessel has one and only one intersection with the center line of the second blood vessel, the intersection point is directly determined as the center point of the second blood vessel that the center point of the first blood vessel should match.

[0139] This application provides a method for matching the centerline of a blood vessel, comprising: acquiring a first centerline of a target blood vessel in a first coronary angiography image and a second centerline of a target blood vessel in a second coronary angiography image; wherein the first coronary angiography image and the second coronary angiography image are captured from different angles; for each first centerline of a blood vessel included in the first centerline of a blood vessel, determining whether the initial point pair matching of the first centerline of a blood vessel in the second coronary angiography image is abnormal based on the intersection of the polar line corresponding to the first centerline of the blood vessel in the second coronary angiography image and the second centerline of the blood vessel; if an abnormality is found, determining the second centerline of a blood vessel to be matched based on the intersection of the polar line corresponding to the first centerline of the blood vessel in the second centerline of a blood vessel and the second centerline of a blood vessel that has been matched with the previous first centerline of the blood vessel;

[0140] In this way, it is possible to accurately determine the point pair matching anomaly at a certain point on the blood vessel centerline based on the intersection of the epipolar lines, and correct it according to the intersection and the matching relationship of other point pairs that have been determined, thereby re-determining the matching point of the blood vessel centerline, which is helpful for the subsequent establishment of the blood vessel three-dimensional model.

[0141] Please see Figure 5 , Figure 5 This is a schematic diagram of a blood vessel centerline matching device provided in an embodiment of this application. Figure 5 As shown, the matching device 300 includes:

[0142] The acquisition module is used to acquire the center line of the first blood vessel in the first coronary angiography image and the center line of the second blood vessel in the second coronary angiography image; wherein the first coronary angiography image and the second coronary angiography image are captured from different angles;

[0143] The determination module is used to determine, for each first vessel center point included in the first vessel center line, whether there is an abnormality in the initial point pair matching of the first vessel center point in the second coronary angiography image based on the intersection of the polar line corresponding to the first vessel center point and the second vessel center line in the second coronary angiography image;

[0144] The matching module is used to determine the second blood vessel center point to be matched when an anomaly occurs, based on the intersection of the polar line corresponding to the first blood vessel center point and the second blood vessel center line, and the second blood vessel center point that has been matched with the previous first blood vessel center point.

[0145] Furthermore, when the determining module determines whether there is an abnormality in the initial point pair matching of each first vessel center point included in the first vessel center line, based on the intersection of the polar line corresponding to the first vessel center point in the second coronary angiography image and the second vessel center line, the determining module is used to:

[0146] If the polar line corresponding to the center point of the first blood vessel intersects the center line of the second blood vessel at multiple points, it is determined that the initial point pair matching of the center point of the first blood vessel in the second coronary angiography image is mismatched.

[0147] Alternatively, if the polar line corresponding to the center point of the first blood vessel does not intersect with the center line of the second blood vessel, then it is determined that the initial point pair matching of the center point of the first blood vessel in the second coronary angiography image has a mismatch.

[0148] Alternatively, if the polar line corresponding to the center point of the first blood vessel intersects the center line of the second blood vessel at exactly one point, then it is determined that the initial point pair matching of the center point of the first blood vessel in the second coronary angiography image is not abnormal.

[0149] Furthermore, when the matching module is used to determine the second vessel center point to be matched with the first vessel center point in the event of an anomaly, based on the intersection of the polar line corresponding to the first vessel center point and the second vessel center line, and the second vessel center point already matched with the previous first vessel center point, the matching module is used to:

[0150] When a mismatch anomaly occurs, determine multiple intersection points between the polar line corresponding to the center point of the first blood vessel and the center line of the second blood vessel.

[0151] Based on the feature information of the second blood vessel center that has been matched with the previous first blood vessel center point and the multiple intersection points, the second blood vessel center point that should be matched with the first blood vessel center point is selected from the multiple intersection points; the feature information includes at least one of the following: distance information, direction information and image grayscale information.

[0152] Furthermore, when the matching module is used to filter out the second vessel center point that should be matched with the first vessel center point from the multiple intersection points based on the feature information of the second vessel center point that has been matched with the previous first vessel center point and the multiple intersection points, the matching module is used to:

[0153] For each intersection point, based on the coordinates of the second blood vessel center that has been matched with the previous first blood vessel center point and the coordinates of the intersection point, determine the distance and direction vector from the second blood vessel center that has been matched with the previous first blood vessel center point to the intersection point;

[0154] Based on the coordinates of the second blood vessel center points that have been matched by the first two first blood vessel center points and the coordinates of the second blood vessel center that has been matched by the first first blood vessel center point, the reference direction vector from the second blood vessel center points that have been matched by the first two first blood vessel center points to the second blood vessel center that has been matched by the first first blood vessel center point is determined.

[0155] Based on the angle between the direction vector from the second blood vessel center that has been matched to the previous first blood vessel center point to the intersection point and the reference direction vector, the direction angle corresponding to the intersection point is determined.

[0156] Based on the gray value of the second vessel center that has been matched with the previous first vessel center point in the second coronary angiography image and the gray value of the intersection point, the gray value of the intersection point is determined.

[0157] Based on the distance from the second blood vessel center that has been matched to the previous first blood vessel center point to the intersection point, determine the distance probability corresponding to the intersection point;

[0158] Based on the directional angle corresponding to the intersection point, determine the directional probability corresponding to the intersection point;

[0159] Based on the gray level difference corresponding to the intersection point, determine the image gray level probability corresponding to the intersection point;

[0160] Based on the distance probability, direction probability, and image grayscale probability of the intersection point, determine the comprehensive probability that the intersection point is the second blood vessel center point that the first blood vessel center point should match.

[0161] The intersection point with the highest overall probability is determined as the second vessel center point that should be matched with the first vessel center point.

[0162] Furthermore, when the matching module is used to determine the second vessel center point to be matched with the first vessel center point in the event of an anomaly, based on the intersection of the polar line corresponding to the first vessel center point and the second vessel center line, and the second vessel center point already matched with the previous first vessel center point, the matching module is used to:

[0163] When a mismatch occurs, multiple vessel center points are selected from the position of the second vessel center point that has been matched with the first vessel center point, starting from the position of the second vessel center point that was matched with the first vessel center point.

[0164] The blood vessel center point with the shortest distance to the polar line corresponding to the first blood vessel center point among the plurality of blood vessel center points is selected as the second blood vessel center point to be matched with the first blood vessel center point.

[0165] Furthermore, when there is no anomaly in the initial point pair matching of the first vessel center point in the second coronary angiography image, the matching module is also used for:

[0166] The intersection of the polar line corresponding to the center point of the first blood vessel and the center line of the second blood vessel is determined as the second blood vessel center point that should be matched with the center point of the first blood vessel.

[0167] Please see Figure 6 , Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 6 As shown, the electronic device 600 includes a processor 610, a memory 620, and a bus 630.

[0168] The memory 620 stores machine-readable instructions executable by the processor 610. When the electronic device 600 is running, the processor 610 and the memory 620 communicate via the bus 630. When the machine-readable instructions are executed by the processor 610, they can perform the operations described above. Figure 1 So much so Figure 4 The steps of a blood vessel centerline matching method in the illustrated method embodiment can be found in the method embodiment for specific implementation, and will not be repeated here.

[0169] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, can perform the above-described actions. Figures 1 to 4 The steps of a blood vessel centerline matching method in the illustrated method embodiment can be found in the method embodiment for specific implementation, and will not be repeated here.

[0170] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0171] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the shown or discussed mutual couplings, direct couplings, or communication connections may be through some communication interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0172] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0173] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0174] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0175] Finally, it should be noted that the above-described embodiments are merely specific implementations of this application, used to illustrate the technical solutions of this application, and not to limit them. The scope of protection of this application is not limited thereto. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the scope of the technology disclosed in this application. Such modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for matching the centerline of blood vessels, characterized in that, The matching method includes: The centerline of the target blood vessel is acquired in the first coronary angiography image and the centerline of the second coronary angiography image; wherein the first coronary angiography image and the second coronary angiography image are captured from different angles; For each first vessel center point included in the first vessel center line, based on the intersection of the polar line corresponding to the first vessel center point in the second coronary angiography image with the second vessel center line, it is determined whether there is an abnormality in the initial point pair matching of the first vessel center point in the second coronary angiography image; If an anomaly occurs, the second vessel center point to be matched is determined based on the intersection of the polar line corresponding to the first vessel center point and the second vessel center line, and the second vessel center point that has been matched with the previous first vessel center point. For each first vessel center point included in the first vessel centerline, determining whether there is an anomaly in the initial point pair matching of the first vessel center point in the second coronary angiography image based on the intersection of the polar line corresponding to the first vessel center point and the second vessel centerline in the second coronary angiography image includes: If the polar line corresponding to the center point of the first blood vessel intersects the center line of the second blood vessel at multiple points, it is determined that the initial point pair matching of the center point of the first blood vessel in the second coronary angiography image is mismatched. Alternatively, if the polar line corresponding to the center point of the first blood vessel does not intersect with the center line of the second blood vessel, then it is determined that the initial point pair matching of the center point of the first blood vessel in the second coronary angiography image has a mismatch. Alternatively, if the polar line corresponding to the center point of the first blood vessel has one and only one intersection with the center line of the second blood vessel, then it is determined that the initial point pair matching of the center point of the first blood vessel in the second coronary angiography image is not abnormal. If an anomaly occurs, the second vessel center point to be matched with the first vessel center point is determined based on the intersection of the polar line corresponding to the first vessel center point and the second vessel center line, and the second vessel center point already matched with the previous first vessel center point. This includes: When a mismatch anomaly occurs, determine multiple intersection points between the polar line corresponding to the center point of the first blood vessel and the center line of the second blood vessel. Based on the feature information of the second blood vessel center that has been matched with the previous first blood vessel center point and the multiple intersection points, the second blood vessel center point that should be matched with the first blood vessel center point is selected from the multiple intersection points; the feature information includes at least one of the following: distance information, direction information and image grayscale information.

2. The matching method according to claim 1, characterized in that, The step of selecting the second vascular center point that should be matched with the first vascular center point from the multiple intersection points based on the feature information of the second vascular center point already matched with the first vascular center point and the multiple intersection points includes: For each intersection point, based on the coordinates of the second blood vessel center that has been matched with the previous first blood vessel center point and the coordinates of the intersection point, determine the distance and direction vector from the second blood vessel center that has been matched with the previous first blood vessel center point to the intersection point; Based on the coordinates of the second blood vessel center points that have been matched by the first two first blood vessel center points and the coordinates of the second blood vessel center that has been matched by the first first blood vessel center point, the reference direction vector from the second blood vessel center points that have been matched by the first two first blood vessel center points to the second blood vessel center that has been matched by the first first blood vessel center point is determined. Based on the angle between the direction vector from the second blood vessel center that has been matched to the previous first blood vessel center point to the intersection point and the reference direction vector, the direction angle corresponding to the intersection point is determined. Based on the gray value of the second vessel center that has been matched with the previous first vessel center point in the second coronary angiography image and the gray value of the intersection point, the gray value of the intersection point is determined. Based on the distance from the second blood vessel center that has been matched to the previous first blood vessel center point to the intersection point, determine the distance probability corresponding to the intersection point; Based on the directional angle corresponding to the intersection point, determine the directional probability corresponding to the intersection point; Based on the gray level difference corresponding to the intersection point, determine the image gray level probability corresponding to the intersection point; Based on the distance probability, direction probability, and image grayscale probability of the intersection point, determine the comprehensive probability that the intersection point is the second blood vessel center point that the first blood vessel center point should match. The intersection point with the highest overall probability is determined as the second vessel center point that should be matched with the first vessel center point.

3. The method according to claim 1, characterized in that, If an anomaly occurs, the second vessel center point to be matched with the first vessel center point is determined based on the intersection of the polar line corresponding to the first vessel center point and the second vessel center line, and the second vessel center point already matched with the previous first vessel center point. This includes: When a mismatch occurs, multiple vessel center points are selected from the position of the second vessel center point that has been matched with the first vessel center point, starting from the position of the second vessel center point that was matched with the first vessel center point. The blood vessel center point with the shortest distance to the polar line corresponding to the first blood vessel center point among the plurality of blood vessel center points is selected as the second blood vessel center point to be matched with the first blood vessel center point.

4. The method according to claim 1, characterized in that, When the initial point pair matching of the first vessel center point in the second coronary angiography image does not show any abnormalities, the matching method further includes: The intersection of the polar line corresponding to the center point of the first blood vessel and the center line of the second blood vessel is determined as the second blood vessel center point that should be matched with the center point of the first blood vessel.

5. A device for matching the centerline of a blood vessel, characterized in that, The matching device includes: The acquisition module is used to acquire the center line of the first blood vessel in the first coronary angiography image and the center line of the second blood vessel in the second coronary angiography image; wherein the first coronary angiography image and the second coronary angiography image are captured from different angles; The determination module is used to determine, for each first vessel center point included in the first vessel center line, whether there is an abnormality in the initial point pair matching of the first vessel center point in the second coronary angiography image based on the intersection of the polar line corresponding to the first vessel center point and the second vessel center line in the second coronary angiography image; The matching module is used to determine the second blood vessel center point to be matched when an anomaly occurs, based on the intersection of the polar line corresponding to the first blood vessel center point and the second blood vessel center line, and the second blood vessel center point that has been matched to the previous first blood vessel center point. When the determining module determines whether there is an abnormality in the initial point pair matching of the first vessel center point in the second coronary angiography image for each first vessel center point included in the first vessel center line, based on the intersection of the polar line corresponding to the first vessel center point and the second vessel center line in the second coronary angiography image, the determining module is used to: If the polar line corresponding to the center point of the first blood vessel intersects the center line of the second blood vessel at multiple points, it is determined that the initial point pair matching of the center point of the first blood vessel in the second coronary angiography image is mismatched. Alternatively, if the polar line corresponding to the center point of the first blood vessel does not intersect with the center line of the second blood vessel, then it is determined that the initial point pair matching of the center point of the first blood vessel in the second coronary angiography image has a mismatch. Alternatively, if the polar line corresponding to the center point of the first blood vessel has one and only one intersection with the center line of the second blood vessel, then it is determined that the initial point pair matching of the center point of the first blood vessel in the second coronary angiography image is not abnormal. When the matching module is used to determine the second vessel center point to be matched with the first vessel center point in the event of an anomaly, based on the intersection of the polar line corresponding to the first vessel center point and the second vessel center line, and the second vessel center point already matched with the previous first vessel center point, the matching module is used to: When a mismatch anomaly occurs, determine multiple intersection points between the polar line corresponding to the center point of the first blood vessel and the center line of the second blood vessel. Based on the feature information of the second blood vessel center that has been matched with the previous first blood vessel center point and the multiple intersection points, the second blood vessel center point that should be matched with the first blood vessel center point is selected from the multiple intersection points; the feature information includes at least one of the following: distance information, direction information and image grayscale information.

6. An electronic device, characterized in that, include: The device includes a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus. The machine-readable instructions are executed by the processor to perform the steps of a method for matching the centerline of a blood vessel as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the steps of a method for matching the centerline of a blood vessel as described in any one of claims 1 to 4.

Images