Method for acquiring digitalized structure of blood vessels, electronic device and storage medium

Abstract

The application provides a blood vessel digital structure acquisition method, an electronic device and a storage medium. The method comprises the following steps: segmenting a pre-acquired medical image to obtain a blood vessel mask image; acquiring a blood vessel center line corresponding to a blood vessel region of interest according to the blood vessel mask image; determining a cross section corresponding to each center point on the blood vessel center line according to the blood vessel mask image; and acquiring a digital structure of the blood vessel region of interest according to the blood vessel center line and the cross section corresponding to each center point on the blood vessel center line. The application can realize digital representation of any blood vessel segment, and has small storage capacity and is convenient for subsequent processing and analysis of the blood vessel.

Description

Technical Field

[0001] This invention relates to the field of image processing technology, and in particular to a method for acquiring digital structures of blood vessels, an electronic device, and a storage medium. Background Technology

[0002] With the continuous development of medical imaging equipment, image processing technology has been widely used in the preoperative diagnosis of cardiovascular diseases. Equipment capable of imaging blood vessels includes CT, MRI, single-photon imaging, positron emission tomography (PET), digital subtraction angiography (DSA), and ultrasound. Although the vascular images obtained by various devices differ somewhat due to their different imaging principles, the diagnostic criteria for vascular diseases are consistent, primarily relying on parameters of the vascular lesion site in the image, including the diameter of the stenotic vessel, the reference diameter of the vessel, the length of the lesion site, and the vessel centerline.

[0003] Traditional techniques typically measure vascular parameters based on two-dimensional vascular images. However, two-dimensional vascular images lack sufficient information to fully represent vascular information, leading to inaccurate vascular parameter measurements and hindering in-depth analysis of vascular conditions. Furthermore, current techniques generally employ graphical grid structures to represent vascular structural information. This representation method not only requires large storage space but also presents significant inconvenience for later applications. Summary of the Invention

[0004] The purpose of this invention is to provide a method, electronic device, and storage medium for acquiring digital structures of blood vessels, which can realize digital representation of any blood vessel segment, with small storage requirements and facilitates subsequent processing and analysis of blood vessels.

[0005] To achieve the above objectives, the present invention provides a method for obtaining digital vascular structures, comprising:

[0006] The pre-acquired medical images are segmented to obtain vascular mask images;

[0007] Based on the vascular mask image, obtain the center line of the vascular region of interest;

[0008] Based on the vascular mask image, determine the cross-section corresponding to each center point on the vascular centerline;

[0009] The digital structure of the blood vessel region of interest is obtained based on the blood vessel centerline and the cross-section corresponding to each center point on the blood vessel centerline.

[0010] Optionally, obtaining the digital structure of the region of interest based on the vessel centerline and the cross-section corresponding to each center point on the vessel centerline includes:

[0011] The region of interest is divided into a corresponding number of vessel segments based on the number of center points on the vessel centerline.

[0012] Based on the cross-section corresponding to each center point on the center line of the blood vessel, the parameters of the corresponding blood vessel segment are obtained;

[0013] Based on the parameters of each blood vessel segment, three-dimensional reconstruction is performed to obtain the digital structure of the blood vessel region of interest.

[0014] Optionally, the parameters include the coordinates of the center point and the coordinates of the closed contour line.

[0015] Optionally, the parameters may also include the area and / or perimeter and / or the maximum diameter and / or the minimum diameter and / or the coordinates of the contour points corresponding to the maximum diameter and / or the coordinates of the contour points corresponding to the minimum diameter and / or the normal vector.

[0016] Optionally, obtaining the parameters of the corresponding blood vessel segment based on the cross-section corresponding to each center point on the blood vessel centerline includes:

[0017] For each center point on the central line of the aforementioned blood vessel:

[0018] Map the cross section corresponding to the center point onto the plane Z=0 to obtain the mapping plane corresponding to the center point;

[0019] Based on the position coordinates of each pixel on the mapping plane, the attribute information of the mapping plane is obtained;

[0020] Based on the attribute information of the mapping plane, the parameters of the blood vessel segment corresponding to the center point are obtained.

[0021] Optionally, determining the cross-section corresponding to each center point on the blood vessel centerline based on the blood vessel mask image includes:

[0022] Calculate the position coordinates of each non-zero pixel in the blood vessel mask image;

[0023] For each center point on the central line of the aforementioned blood vessel:

[0024] The center point and its adjacent neighboring center points are combined to form a first vector, and the center point and each of the non-zero pixel points are combined to form a second vector.

[0025] Calculate the angle between the first vector and the second vector;

[0026] The set of points consisting of non-zero pixels with included angles within a preset range is taken as the set of points of the cross section corresponding to the center point;

[0027] The center point and the set of points corresponding to its cross-section are fitted together to obtain the cross-section corresponding to the center point.

[0028] Optionally, obtaining the center line of the blood vessel corresponding to the region of interest based on the blood vessel mask image includes:

[0029] Based on the vascular mask image, obtain the position coordinates of a starting point and several ending points;

[0030] Based on the position coordinates of the starting point and the ending point, a preset algorithm is used to determine the target path between the starting point and the ending point;

[0031] Merge all target paths to obtain the vascular centerline corresponding to the region of interest.

[0032] Optionally, the step of using a preset algorithm to determine the target path between the starting point and the ending point includes:

[0033] Using the starting point as the starting node and the ending point as the target node, the A* algorithm is used to determine the target path between the starting point and the ending point.

[0034] Optionally, the cost function used in the A* algorithm is as follows:

[0035] F(P) = w1*G(P) + w2*H(P)

[0036]

[0037]

[0038] In the formula, F(P) is the total cost, G(P) is the actual cost from the starting node to node P, and H(P) is the estimated cost from node P to the ending node D. Let be the Euclidean distance from node P to the terminal node D. Let w1 be the Euclidean distance from node P to its parent node, w2 be the first weight coefficient, and w1 be the second weight coefficient.

[0039] Optionally, before using the A* algorithm to determine the target path between the starting point and the ending point, the method further includes:

[0040] For each non-zero pixel in the blood vessel mask image, its surrounding neighboring pixels are traversed from near to far until the zero pixel closest to the non-zero pixel is found. The distance between the non-zero pixel and the zero pixel is calculated and set as the pixel value of the non-zero pixel to obtain the blood vessel distance transformation image.

[0041] The formula for calculating the first weighting coefficient w1 is as follows:

[0042] w1=β*e ΔP

[0043] Wherein, β is the first adjustment factor, and 0 < β < 1, and ΔP is the absolute value of the difference between the maximum pixel value in the blood vessel distance transformation image and the pixel value of node P in the blood vessel distance transformation image.

[0044] Optionally, the formula for calculating the second weighting coefficient w2 is as follows:

[0045]

[0046] Where σ is the second adjustment factor, and 0 < σ < 1, |Z P -Z D | is the Z-coordinate of the node P. P The Z coordinate of the termination node D D The absolute value of the difference between them.

[0047] Optionally, before merging all target paths to obtain the vessel centerline corresponding to the region of interest, the method further includes:

[0048] The target path is modified to obtain a modified target path;

[0049] The process of merging all target paths to obtain the vascular centerline corresponding to the region of interest includes:

[0050] Merge all the corrected target paths to obtain the vessel centerline corresponding to the region of interest.

[0051] Optionally, the step of correcting the target path to obtain a corrected target path includes:

[0052] A first correction process is performed on each path point on the target path corresponding to the unbranched blood vessel region to obtain the corresponding first corrected path point;

[0053] A second correction process is performed on each path point on the target path corresponding to the bifurcation vessel region to obtain the corresponding second corrected path point;

[0054] Based on the first and second corrected path points, obtain the corrected target path.

[0055] Optionally, before performing the first correction process on each path point corresponding to the unbranched vessel region on the target path, the method further includes:

[0056] For each non-zero pixel in the blood vessel mask image, its surrounding neighboring pixels are traversed from near to far until the zero pixel closest to the non-zero pixel is found. The distance between the non-zero pixel and the zero pixel is calculated and set as the pixel value of the non-zero pixel to obtain the blood vessel distance transformation image.

[0057] The first correction process for each path point on the target path corresponding to the unbranched blood vessel region to obtain the corresponding first corrected path point includes:

[0058] For each path point on the target path corresponding to the unbranched blood vessel region:

[0059] The path point is mapped onto the first cross-sectional image corresponding to the blood vessel distance transformation image onto the plane Z=0 to obtain the corresponding first mapped image;

[0060] The pixel with the largest pixel value in the first mapped image is taken as the corresponding first mapping point;

[0061] Based on the first mapping point, obtain the corresponding first correction point.

[0062] Optionally, the second correction process for each path point on the target path corresponding to the bifurcation vessel region to obtain the corresponding second corrected path point includes:

[0063] For each path point on the target path corresponding to the bifurcation vessel region:

[0064] The path point is mapped onto the second cross-sectional image corresponding to the blood vessel distance transformation image onto the plane Z=0 to obtain the corresponding second mapped image;

[0065] Based on the pixel values ​​of each pixel in the second mapped image, two peak points are obtained;

[0066] The peak point closest to the path point is taken as the corresponding second mapping point;

[0067] Based on the second mapping point, obtain the corresponding second correction point.

[0068] To achieve the above objectives, the present invention also provides an electronic device, including a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, it implements the method for acquiring the digital structure of blood vessels described above.

[0069] To achieve the above objectives, the present invention also provides a readable storage medium storing a computer program, which, when executed by a processor, implements the method for acquiring the digital structure of blood vessels described above.

[0070] Compared with existing technologies, the method, electronic device, and storage medium for acquiring digital vascular structures provided by this invention have the following advantages: This invention first segments a pre-acquired medical image to obtain a vascular mask image; then, based on the vascular mask image, it obtains the vascular centerline corresponding to the region of interest; next, based on the vascular mask image, it determines the cross-section corresponding to each center point on the vascular centerline; finally, based on the vascular centerline and the cross-section corresponding to each center point on the vascular centerline, it acquires the digital structure of the region of interest. Therefore, based on this digital structure, any vascular segment can be digitally represented, requiring less storage and facilitating subsequent processing and analysis of the blood vessels. Attached Figure Description

[0071] Figure 1 This is a flowchart illustrating a method for obtaining digital vascular structures according to an embodiment of the present invention.

[0072] Figure 2 This is a schematic diagram of a medical image in a specific example of the present invention;

[0073] Figure 3 This is a schematic diagram of a blood vessel mask image in a specific example of the present invention;

[0074] Figure 4 This is a schematic diagram of the process for obtaining the center line of a blood vessel in a specific example of the present invention;

[0075] Figure 5 This is a flowchart illustrating the process of determining the target path between the starting node and the target node in a specific example of the present invention.

[0076] Figure 6 This is a schematic diagram of the first correction process in a specific example of the present invention;

[0077] Figure 7 This is a schematic diagram of the second correction process in a specific example of the present invention;

[0078] Figure 8 This is a schematic diagram illustrating the acquisition of the second mapping point in a specific example of the present invention;

[0079] Figure 9 This is a schematic diagram of the blood vessel centerline in a specific example of the present invention;

[0080] Figure 10A schematic diagram of the process for obtaining a cross-section provided by one embodiment of the present invention;

[0081] Figure 11 This is a schematic diagram illustrating the specific process of obtaining digital vascular structures according to one embodiment of the present invention;

[0082] Figure 12 This is a schematic diagram showing the parameter representation of a blood vessel segment in a specific example of the present invention;

[0083] Figure 13 A schematic diagram illustrating the specific process for obtaining parameters of a blood vessel segment according to an embodiment of the present invention;

[0084] Figure 14 This is a schematic diagram of a connected component obtained using the watershed algorithm in one embodiment of the present invention;

[0085] Figure 15 This is a schematic diagram of the digital structure of blood vessels in a specific example of the present invention;

[0086] Figure 16 This is a block diagram of an electronic device according to one embodiment of the present invention;

[0087] The reference numerals in the attached figures are as follows:

[0088] Path point -1; Peak points -21, 22; Contour line -3;

[0089] Processor-101; Communication interface-102; Memory-103; Communication bus-104. Detailed Implementation

[0090] The following detailed description, in conjunction with the accompanying drawings and specific embodiments, further illustrates the method for acquiring digital vascular structures, the electronic device, and the storage medium proposed in this invention. The advantages and features of this invention will become clearer from the following description. It should be noted that the accompanying drawings are in a very simplified form and use non-precise proportions, used only to facilitate and clearly illustrate the embodiments of this invention. Please refer to the accompanying drawings to make the objectives, features, and advantages of this invention more apparent and understandable. It should be understood that the structures, proportions, sizes, etc., depicted in the accompanying drawings are only for illustrative purposes and to enable those skilled in the art to understand and read them, and are not intended to limit the implementation conditions of this invention. Any modifications to the structure, changes in proportions, or adjustments to the size, provided that the effects and objectives achieved by this invention are the same or similar, should still fall within the scope of the technical content disclosed in this invention.

[0091] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0092] The core idea of ​​this invention is to provide a method, electronic device and storage medium for acquiring digital structures of blood vessels, which can realize digital representation of any segment of blood vessels, with small storage requirements and convenient subsequent processing and analysis of blood vessels.

[0093] It should be noted that the electronic device in the embodiments of the present invention can be a personal computer, a mobile terminal, etc., and the mobile terminal can be a mobile phone, tablet computer, or other hardware device with various operating systems. Furthermore, it should be noted that although this article uses the acquisition of a partial digital structure of the aorta as an example for illustration, as those skilled in the art will understand, the present invention can also be used to acquire the digital structure of the entire aorta, as well as the digital structures of other blood vessels besides the aorta, such as neurovascular vessels, radial arteries, etc.

[0094] To achieve the above-mentioned goals, this invention provides a method for acquiring digital vascular structures. Please refer to [the relevant documentation]. Figure 1 The flowchart illustrating a method for acquiring digital vascular structures according to an embodiment of the present invention is shown below. Figure 1 As shown, the method for obtaining the digital structure of blood vessels includes the following steps:

[0095] Step S100: Segment the pre-acquired medical image to obtain a vascular mask image;

[0096] Step S200: Obtain the center line of the blood vessel corresponding to the region of interest based on the blood vessel mask image;

[0097] Step S300: Based on the vascular mask image, determine the cross-section corresponding to each center point on the vascular centerline;

[0098] Step S400: Obtain the digital structure of the region of interest based on the blood vessel centerline and the cross-section corresponding to each center point on the blood vessel centerline.

[0099] Therefore, this invention obtains the vascular centerline of the region of interest and the cross-section corresponding to each center point on the vascular centerline, and obtains the digital structure of the region of interest based on the vascular centerline and the cross-section corresponding to each center point. This enables the digital representation of any vascular segment, which not only requires less storage but also facilitates subsequent processing and analysis of the blood vessels.

[0100] Specifically, the pre-acquired medical images can be CTA (Computed Tomography Angiography) images, MRA (Magnetic Resonance Angiography) images, or other medical images. These medical images can be acquired using image acquisition devices such as CT and MRI imaging equipment, or obtained through internet searches, or by scanning with a scanning device. The size of the medical images can be set according to specific circumstances, and this invention does not impose any limitations on this; for example, the size of the medical image can be 512×512×130 pixels.

[0101] Preferably, before segmenting the medical image, the method further includes: filtering the pre-acquired medical image. Please refer to [link / reference]. Figure 2 It schematically illustrates a filtered medical image in a specific example of the present invention, such as... Figure 2 As shown, by filtering the acquired medical image (e.g., Gaussian filtering), noise in the medical image can be effectively removed, laying a good foundation for obtaining accurate vascular mask images.

[0102] Correspondingly, step S100 involves segmenting the filtered medical image to obtain a vascular mask image. It should be noted that, as those skilled in the art will understand, existing image segmentation methods, such as thresholding, region growing, and deep learning-based neural network segmentation, can be used to segment the medical image. This invention does not limit the segmentation method. Please refer to... Figure 3 The diagram illustrates a vascular mask image in a specific example of the present invention. Figure 3 As shown, by analyzing Figure 2 The medical image is segmented to obtain a complete aortic vascular mask image. In the aortic vascular mask image, the pixel value of the aortic vascular region is 1, and the pixel value of other regions is 0.

[0103] Further, please refer to Figure 4 The diagram illustrates a flowchart of obtaining the vascular centerline according to an embodiment of the present invention. Figure 4As shown, step S200, obtaining the center line of the blood vessel corresponding to the region of interest based on the blood vessel mask image, includes:

[0104] Based on the vascular mask image, obtain the position coordinates of a starting point and several ending points;

[0105] Based on the position coordinates of the starting point and the ending point, a preset algorithm is used to determine the target path between the starting point and the ending point;

[0106] Merge all target paths to obtain the vascular centerline corresponding to the region of interest.

[0107] Specifically, based on actual needs, the center position of the cross-section at the beginning of the region of interest (ROI) on the vascular mask image where the centerline needs to be calculated can be used as the starting point, and the center positions of the cross-sections at each end of the ROI can be used as the ending points. Based on the positions of the starting and ending points on the vascular mask image, the position coordinates (coordinates in the image coordinate system) of the starting and ending points can be obtained. It should be noted that, as those skilled in the art will understand, the starting and ending points can be selected manually or by a computer according to a pre-set algorithm; this invention does not impose any limitations on this. Furthermore, it should be noted that in some other embodiments, existing methods for extracting vascular centerlines can also be used, such as methods based on region growing and methods based on vascular centerline models; this invention does not impose any limitations on this.

[0108] Furthermore, the step of using a preset algorithm to determine the target path between the starting point and the ending point includes:

[0109] Using the starting point as the starting node and the ending point as the target node, the A* algorithm is used to determine the target path between the starting point and the ending point.

[0110] For details, please refer to Figure 5 This diagram illustrates a flowchart of determining the target path between the starting node and the target node according to an embodiment of the present invention. Figure 5 As shown, the target path between the starting node and the target node can be determined using the following steps:

[0111] Step A: Create an open list to store nodes to be detected and a closed list to store detected nodes, and put the starting point into the open list;

[0112] Step B: Determine whether the open list is an empty set. If yes, end the calculation; otherwise, proceed to step C.

[0113] Step C: Sort the cost function F values ​​of each node in the open list, select the node with the smallest cost function F value as the current node, and move the current node from the open list to the closed list, wherein:

[0114] F(P) = w1*G(P) + w2*H(P);

[0115]

[0116]

[0117] In the formula, F(P) is the cost function, G(P) is the actual cost from the starting node to node P, and H(P) is the estimated cost from node P to the ending node D. Let be the Euclidean distance from node P to the terminal node D. Let w1 be the Euclidean distance from node P to its parent node, w2 be the first weight coefficient, and w1 be the second weight coefficient.

[0118] Step D: Determine whether the current node is a termination node. If yes, proceed to step E; otherwise, proceed to step F1.

[0119] Step E: Starting from the termination node, trace back the parent node step by step until the starting node is reached. Connect all the traced nodes sequentially from the starting node to form the target path.

[0120] Step F1: Based on the blood vessel mask image, determine all neighboring nodes in the surrounding area of ​​the current node, and select one of the neighboring nodes as the current neighboring node;

[0121] Step F2: Determine whether the current neighboring node is in the closed list. If yes, proceed to step F3; otherwise, proceed to step F4.

[0122] Step F3: Skip the current neighbor node, and take the next neighbor node as the current neighbor node, then return to execute step F2;

[0123] Step F4: Determine whether the current neighboring node is in the open list. If yes, proceed to step F5; otherwise, proceed to step F6.

[0124] Step F5: Calculate the G value of the current neighbor node relative to the current node. If the newly calculated G value is less than the existing G value of the current neighbor node, update the existing G value of the current neighbor node to the newly calculated G value, update the parent node of the current neighbor node to the current node, and execute step F7.

[0125] Step F6: Add the neighboring node to the open list, set the current node as the parent node of the neighboring node, and execute step F7;

[0126] Step F7: Determine whether the current neighbor node is the last neighbor node. If yes, return to step B; otherwise, proceed to step F8.

[0127] Step F8: Select the next neighboring node as the current neighboring node and return to step F2.

[0128] Specifically, when only the starting node exists in the open list, the starting node is removed from the open list. Each node in the open list has its own stored total cost (F value), actual cost (G value), and estimated cost (H value), which can be respectively referred to as the node's stored total cost (F value), stored actual cost (G value), and stored estimated cost (H value). The starting node's stored actual cost is 0. As the node's parent node information is updated, the node's stored total cost (F value) and stored actual cost (G value) change accordingly. The neighboring nodes adjacent to the starting node initially all have the starting node as their parent node.

[0129] in:

[0130]

[0131]

[0132] When obtaining the neighboring nodes of the current node, the non-zero pixels in the 26 neighborhoods of the current node on the blood vessel mask image (preferably the smoothed blood vessel mask image) are selected as the neighboring nodes of the current node.

[0133] It should be noted that, as those skilled in the art will understand, after traversing all neighboring nodes of the current node, the process returns to step B until the final selected current node is the termination node. From the termination node, the process moves towards its parent node, and then from that parent node towards its own parent node, and so on, until the starting node is reached. The path formed by these nodes is the target path, i.e., the vascular centerline. Furthermore, it should be noted that although this invention uses the A* algorithm as an example, as those skilled in the art will understand, other existing path algorithms, such as breadth-first search, Dijkstra's algorithm, and best-first search, can also be used to determine the target path between the starting node and the termination node. This invention does not limit this approach.

[0134] Therefore, for each pair of starting and ending points, the path algorithm described above is used to calculate the target path between each pair of starting and ending points. This target path is the vascular centerline of the vascular region corresponding to the starting and ending points. By merging all the target paths, the vascular centerline of the vascular region of interest can be obtained.

[0135] Furthermore, the first weighting coefficient is a dynamic coefficient related to the node P. Therefore, by setting the first weighting coefficient to a dynamic coefficient related to the node P, the present invention can achieve dynamic adjustment of the cost function, thereby facilitating efficient finding of the target path.

[0136] Specifically, before using the A* algorithm to determine the target path between the starting point and the ending point, the method further includes:

[0137] For each non-zero pixel in the blood vessel mask image, its surrounding neighboring pixels are traversed from near to far until the zero pixel closest to the non-zero pixel is found. The distance between the non-zero pixel and the zero pixel is calculated and set as the pixel value of the non-zero pixel to obtain the blood vessel distance transformation image.

[0138] The formula for calculating the first weighting coefficient w1 is as follows:

[0139] w1=β*e ΔP

[0140] Wherein, β is the first adjustment factor, and 0 < β < 1, and ΔP is the absolute value of the difference between the maximum pixel value in the blood vessel distance transformation image and the pixel value of node P in the blood vessel distance transformation image.

[0141] Since the center point of each cross-section of a blood vessel is furthest from the vessel wall, the pixel value of the pixel at the center point of each cross-section of the blood vessel region is the largest in the blood vessel distance transformation image. If the pixel value of node P in the blood vessel distance transformation image is larger, the value of w1 is smaller. That is, the first weight coefficient corresponding to node P which is closer to the actual center line of the blood vessel is smaller. This setting can ensure that the finally obtained path node walks along the center of the blood vessel as much as possible, that is, ensure that the obtained target path is closer to the actual center line of the blood vessel, thereby ensuring the accuracy of the obtained blood vessel center line.

[0142] Furthermore, the second weighting coefficient w2 is also a dynamic coefficient related to the node P. Therefore, by setting the second weighting coefficient as a dynamic coefficient related to the node P, dynamic adjustment of the cost function can be further achieved, which is more conducive to efficiently finding the target path.

[0143] Specifically, the formula for calculating the second weighting coefficient w2 is as follows:

[0144]

[0145] Where σ is the second adjustment factor, and 0 < σ < 1, |Z P -Z D | is the Z-coordinate of the node P. P The Z coordinate of the termination node D D The absolute value of the difference between them.

[0146] Since the slice layers of the starting node and the ending node are furthest apart by default (i.e., the absolute value of the difference between the Z-coordinates of the starting and ending nodes is the largest), for example, the aorta runs from top to bottom along the head and neck of the human body. Therefore, by setting the second weighting coefficient W2 to be dynamically related to the slice layer (i.e., the Z-coordinate), where the larger the absolute value of the difference between the Z-coordinates of node P and the ending node D, the larger W2 becomes, it is more conducive to efficiently finding the optimal path. It should be noted that, as those skilled in the art will understand, if the acquired medical image contains nerves and blood vessels, the parameter W2 can be directly set to 1.

[0147] Preferably, before merging all target paths to obtain the vessel centerline corresponding to the region of interest, the method further includes:

[0148] The target path is modified to obtain a modified target path;

[0149] The process of merging all target paths to obtain the vessel centerline corresponding to the region of interest includes:

[0150] Merge all the corrected target paths to obtain the vessel centerline corresponding to the region of interest.

[0151] Although the present invention dynamically adjusts the values ​​of the first weighting coefficient W1 and the second weighting coefficient W2 when determining the target path, there is still a possibility that some path points on the calculated target path may not be in the middle of the blood vessel, but instead travel along the blood vessel wall. Therefore, the present invention can ensure that all points on the final target path travel along the center of the blood vessel by correcting the target path, thereby ensuring the accuracy of the final obtained blood vessel centerline.

[0152] Further, the step of correcting the target path to obtain a corrected target path includes:

[0153] A first correction process is performed on each path point on the target path corresponding to the unbranched blood vessel region to obtain the corresponding first corrected path point;

[0154] A second correction process is performed on each path point on the target path corresponding to the bifurcation vessel region to obtain the corresponding second corrected path point;

[0155] Based on the first and second corrected path points, obtain the corrected target path.

[0156] Therefore, the present invention performs a first correction process on each path point corresponding to the unbranched vessel region on the target path, and a second correction process on each path point corresponding to the bifurcation vessel region on the target path, which can further ensure the accuracy of the finally obtained vessel centerline.

[0157] Furthermore, before performing the first correction process on each path point corresponding to the unbranched vessel region on the target path, the method further includes:

[0158] For each non-zero pixel in the blood vessel mask image, its surrounding neighboring pixels are traversed from near to far until the zero pixel closest to the non-zero pixel is found. The distance between the non-zero pixel and the zero pixel is calculated and set as the pixel value of the non-zero pixel to obtain a blood vessel distance transformation image.

[0159] Please continue to refer to this. Figure 6 The diagram illustrates a flowchart of the first correction process provided by an embodiment of the present invention. Figure 6 As shown, the first correction process for each path point on the target path corresponding to the unbranched blood vessel region to obtain the corresponding first corrected path point includes:

[0160] For each path point on the target path corresponding to the unbranched blood vessel region:

[0161] The path point is mapped onto the first cross-sectional image corresponding to the blood vessel distance transformation image onto the plane Z=0 to obtain the corresponding first mapped image;

[0162] The pixel with the largest pixel value in the first mapped image is taken as the corresponding first mapping point;

[0163] Based on the first mapping point, obtain the corresponding first correction point.

[0164] Taking one of the path points on the target path corresponding to the unbranched blood vessel region as an example, the first cross-sectional image corresponding to the pixel point on the blood vessel distance transformation image can be obtained based on the path point and the point set of its corresponding cross-section (refer to the relevant description below); then, the first cross-sectional image is mapped to the Z=0 plane (i.e., the plane with Z coordinate of 0, i.e., the XOY plane with the image coordinate system as the reference) through a rotation and translation matrix to obtain the corresponding first mapped image; then, each pixel point in the first mapped image is traversed to find the pixel point with the largest pixel value (i.e., the point farthest from the edge of the blood vessel, i.e., the center point), and the pixel point with the largest pixel value is taken as the first mapped point corresponding to the path point; finally, the first mapped point is mapped to the first cross-sectional image through the inverse matrix of the rotation and translation matrix to obtain the first correction point corresponding to the pixel point.

[0165] Please continue to refer to this. Figure 7 The diagram illustrates a flowchart of the second correction process provided by an embodiment of the present invention. Figure 7 As shown, the second correction process for each path point on the target path corresponding to the bifurcation vessel region to obtain the corresponding second corrected path point includes:

[0166] For each path point on the target path corresponding to the bifurcation vessel region:

[0167] The path point is mapped onto the second cross-sectional image corresponding to the blood vessel distance transformation image onto the plane Z=0 to obtain the corresponding second mapped image;

[0168] Based on the pixel values ​​of each pixel in the second mapped image, two peak points are obtained;

[0169] The peak point closest to the path point is taken as the corresponding second mapping point;

[0170] Based on the second mapping point, obtain the corresponding second correction point.

[0171] Specifically, taking a path point on the target path corresponding to a bifurcation vessel region as an example, the second cross-sectional image corresponding to the path point on the vessel distance transformation image can be obtained based on the point set of the path point and its corresponding cross-section (refer to the relevant description below); then, the second cross-sectional image is mapped onto the Z=0 plane (i.e., the plane with Z coordinate 0, i.e., the XOY plane with the image coordinate system as the reference) through a rotation and translation matrix to obtain the corresponding second mapped image; then, each pixel in the second mapped image is traversed to find two pixel peak points (these two peak points correspond to the centers of the two branch vessels, respectively). The two pixel peaks may be the two points with the largest pixel values ​​in the second mapped image (i.e., the two peaks have the same pixel value and the largest pixel value), or they may be the largest pixel value point and the second largest pixel value point in the second mapped image (i.e., one peak point is the largest pixel value point and the other is the second largest pixel value point). The distances between these two peaks and the path point are then calculated, and the peak point closest to the path point is taken as the second mapped point of the path point. Finally, the second mapped point is mapped onto the second cross-sectional image using the inverse of the rotation and translation matrix to obtain the second correction point corresponding to the path point. Please refer to [reference needed]. Figure 8 The diagram illustrates the acquisition of the second mapping point according to a specific example of the present invention. Figure 8 As shown, in the second mapping image corresponding to path point 1, two peak points were found: peak point 21 and peak point 22. Peak point 21 is closer to path point 1, so peak point 21 is taken as the second correction point corresponding to path point 1.

[0172] Please continue to refer to this. Figure 9 The diagram illustrates the central line of a blood vessel in a specific example of the present invention. Figure 9 As shown, the center line of the blood vessel is formed by merging the modified target paths AB, AC, and AD.

[0173] Further, please refer to Figure 10 The diagram illustrates a process for obtaining a cross-section according to an embodiment of the present invention. Figure 10 As shown, step S300, determining the cross-section corresponding to each center point on the blood vessel centerline based on the blood vessel mask image, includes:

[0174] Calculate the position coordinates of each non-zero pixel in the blood vessel mask image;

[0175] For each center point on the central line of the aforementioned blood vessel:

[0176] The center point and its adjacent neighboring center points are combined to form a first vector, and the center point and each of the non-zero pixel points are combined to form a second vector.

[0177] Calculate the angle between the first vector and the second vector;

[0178] The set of points consisting of non-zero pixels whose included angle is within a preset range is taken as the set of points of the cross section corresponding to the center point;

[0179] The center point and the set of points corresponding to its cross-section are fitted together to obtain the cross-section corresponding to the center point.

[0180] Specifically, the position coordinates of all non-zero pixels (pixels with a pixel value of 1) can be stored in a valid set. Then, the first center point on the blood vessel centerline (i.e., the starting pixel on the blood vessel centerline) is taken as the current point, and the current point and the next center point (i.e., the second pixel on the blood vessel centerline) are combined to form a first vector. And to form a second vector by combining the current point (i.e., the starting pixel) with the first non-zero pixel A1 in the valid set. By calculating the first vector With the second vector The included angle θ 11 And determine the included angle θ 11 Whether it is within a preset range (e.g., 90°±1°), if the judgment result is the included angle θ 11 If the pixel is within a preset range, it indicates that the non-zero pixel is a point on the cross-section corresponding to the current point. Therefore, point A1 is saved to the set of points used to store the cross-section of the current point. Then, the current point and the next non-zero pixel A2 in the valid set are combined to form a second vector. And determine the first vector With the second vector The included angle θ 12 If the point A2 is within a preset range, and the result is yes, then the point A2 is saved to a set of points used to store the cross-section of the current point. This process is repeated for each non-zero pixel in the valid set until all non-zero pixels in the valid set have been traversed to obtain the point set of the cross-section corresponding to the first center point. After obtaining the point set of the cross-section corresponding to the first center point, the second center point is used as the current point, and the above process is repeated to obtain the point set of the cross-section corresponding to the second center point. This continues until the current point is the last center point. For the last center point, a first vector can be formed by the last center point and its adjacent previous center point to obtain the point set of the cross-section corresponding to the last center point.

[0181] It should be noted that, as those skilled in the art will understand, the coordinates of the current point are assumed to be (X... j ,Y j Z j The coordinates of the adjacent center point are (X... k ,Y k Z k The coordinates of the non-zero pixel point Ai are (X... Ai ,Y Ai Z Ai If ), then the first vector Second vector The angle between the first vector and the second vector is:

[0182]

[0183] Furthermore, it should be noted that in some other embodiments, when obtaining the first vector, if the current point is neither the first center point nor the last center point on the blood vessel centerline, the current point can be combined with the previous or next center point on the blood vessel centerline to form the first vector. This invention does not impose any limitations on this.

[0184] Since the obtained cross-sectional point set data is discrete, it is impossible to directly calculate the parameters of the blood vessel. Therefore, by fitting each center point on the blood vessel's centerline to the point set of its corresponding cross-section, the cross-section corresponding to each center point on the blood vessel's centerline can be obtained. Specifically, by fitting the first center point on the blood vessel's centerline to the point set of its corresponding cross-section, for example using least squares fitting, the cross-section corresponding to the first center point can be obtained; by fitting the second center point on the blood vessel's centerline to the point set of its corresponding cross-section, for example using least squares fitting, the cross-section corresponding to the second center point can be obtained; and so on, the cross-section corresponding to each center point on the blood vessel's centerline can be obtained.

[0185] Please continue to refer to this. Figure 11 The diagram illustrates a specific process for obtaining the digital structure of blood vessels according to an embodiment of the present invention. Figure 11 As shown, obtaining the digital structure of the region of interest based on the vessel centerline and the cross-section corresponding to each center point on the vessel centerline includes:

[0186] The region of interest is divided into a corresponding number of vessel segments based on the number of center points on the vessel centerline.

[0187] Based on the cross-section corresponding to each center point on the center line of the blood vessel, the parameters of the corresponding blood vessel segment are obtained;

[0188] Based on the parameters of each blood vessel segment, three-dimensional reconstruction is performed to obtain the digital structure of the blood vessel region of interest.

[0189] It should be noted that, as those skilled in the art will understand, the number of segmented blood vessels is the same as the number of center points on the centerline of the blood vessel, and the parameters of each segment are related to the properties of the cross-section corresponding to its center point. Specifically, the parameters include the coordinates of the center point and the coordinates of the closed contour line. Furthermore, the parameters also include any one or more of the following: area, perimeter, maximum diameter, minimum diameter, coordinates of the contour point corresponding to the maximum diameter, coordinates of the contour point corresponding to the minimum diameter, and normal vector. Please refer to [reference needed]. Figure 12 The diagram illustrates the parameter representation of a blood vessel segment in a specific example of the present invention. Figure 12 As shown, the coordinates of point o are the coordinates of the center point, the length of contour line 3 is the perimeter of the blood vessel segment, the area enclosed by contour line 3 is the area of ​​the blood vessel segment, the length of ab is the maximum diameter, the length of cd is the minimum diameter, the coordinates of points a and b are the coordinates of the contour points corresponding to the maximum diameter, and the coordinates of points c and d are the coordinates of the contour points corresponding to the minimum diameter. It should be noted that, as those skilled in the art will understand, the normal vector of the blood vessel segment is the vector formed by the coordinates of the center point of the blood vessel segment and the coordinates of the center points of its adjacent blood vessel segments.

[0190] Further, please refer to Figure 13 The diagram illustrates a specific process for obtaining parameters of a blood vessel segment according to an embodiment of the present invention. Figure 13 As shown, obtaining the parameters of the corresponding blood vessel segment based on the cross-section corresponding to each center point on the blood vessel centerline includes:

[0191] For each center point on the central line of the aforementioned blood vessel:

[0192] Map the cross section corresponding to the center point onto the plane Z=0 to obtain the mapping plane corresponding to the center point;

[0193] Based on the position coordinates of each pixel on the mapping plane, the attribute information of the mapping plane is obtained;

[0194] Based on the attribute information of the mapping plane, the parameters of the blood vessel segment corresponding to the center point are obtained.

[0195] Therefore, this invention significantly reduces computation by first mapping the cross-sections corresponding to each center point on the blood vessel's central line to a plane with Z=0 (i.e., a plane with Z coordinates of 0, also known as the XOY plane with the image coordinate system as the reference) before calculating parameters. Specifically, taking one center point as an example, the cross-section corresponding to that center point can be moved to the plane with Z=0 through rotation and translation operations to obtain the corresponding mapping plane (the Z coordinates of each pixel on the mapping plane are 0). The positional mapping relationship between the mapping plane and the cross-section can be represented by a rotation and translation matrix, with different cross-sections corresponding to different rotation and translation matrices. Based on the position coordinates of each pixel on the mapping plane, the perimeter, area, maximum diameter, minimum diameter, coordinates of the contour points corresponding to the maximum diameter, and coordinates of the contour points corresponding to the minimum diameter of the mapping plane can be obtained. Since the perimeter, area, maximum diameter, and minimum diameter are fixed attributes and do not change with rotation and translation... Therefore, the perimeter, area, maximum diameter, and minimum diameter of the mapping plane are the same as the perimeter, area, maximum diameter, and minimum diameter of the cross-section (i.e., the perimeter, area, maximum diameter, and minimum diameter of the blood vessel segment corresponding to the cross-section). By inversely transforming the contour coordinates of the mapping plane, the coordinates of the contour point corresponding to the maximum diameter, and the coordinates of the contour point corresponding to the minimum diameter onto the cross-section using the rotation and translation matrix, the contour coordinates of the cross-section, the coordinates of the contour point corresponding to the maximum diameter, and the coordinates of the contour point corresponding to the minimum diameter (i.e., the contour coordinates of the blood vessel segment corresponding to the cross-section, the coordinates of the contour point corresponding to the maximum diameter, and the coordinates of the contour point corresponding to the minimum diameter) can be obtained.

[0196] Preferably, the method for obtaining digital vascular structures provided by the present invention further includes:

[0197] The parameters of the vascular segment corresponding to each center point on the vascular centerline corresponding to the bifurcation vascular region are corrected.

[0198] Specifically, based on the second mapping point corresponding to the center point (reference) Figure 8 Using the seed point as a reference, the watershed algorithm is used to segment the corresponding second mapping image (refer to the relevant description above); and the parameters of the corresponding blood vessel segment are corrected based on the feature information of the connected domain where the second mapping point is located.

[0199] Specifically, in the second mapped image, the second mapped point can be used as a seed point. Then, based on the seed point, surrounding pixels are traversed. When a pixel with a value of 1 is encountered or no pixel is found, the process stops, thus separating the two branch vessel regions. The connected component where the second mapped point is located is the branch vessel region of interest. For more information on the watershed algorithm, please refer to existing technologies; it will not be elaborated upon here. Please refer to [reference needed]. Figure 14 The diagram illustrates a connected component obtained using the watershed algorithm in one embodiment of the present invention. Figure 14 As shown, by employing the watershed algorithm, the regions containing peak point 21 (i.e., the second mapping point) and peak point 22 can be completely separated. Therefore, based on the attribute information corresponding to the connected component where the second mapping point is located, the parameters of the blood vessel segment at the corresponding location can be corrected. Specifically, based on the position coordinates of each pixel in the connected component where the second mapping point is located, the perimeter, area, contour coordinates, maximum diameter, minimum diameter, coordinates of the contour point corresponding to the maximum diameter, and coordinates of the contour point corresponding to the minimum diameter of the connected component can be obtained. The perimeter, area, maximum diameter, and minimum diameter of this connected component are the perimeter, area, maximum diameter, and minimum diameter of the corresponding blood vessel segment. By using the inverse matrix of the rotation and translation matrix between the second cross-sectional image and the second mapping image, the contour coordinates, the coordinates of the contour point corresponding to the maximum diameter, and the coordinates of the contour point corresponding to the minimum diameter of the corresponding blood vessel segment can be obtained.

[0200] Please refer to Figure 15 The diagram illustrates a specific example of the digital structure of blood vessels according to the present invention. Figure 15 As shown, by using the method provided by this invention to obtain the digital vascular structure, in subsequent processing and analysis of blood vessels, it is only necessary to specify a certain blood vessel segment or certain blood vessel segments to be analyzed to obtain fully digital vascular structure information, thereby making it easier to measure and analyze blood vessels.

[0201] Based on the same inventive concept, the present invention also provides an electronic device, please refer to... Figure 16 A block diagram illustrating an embodiment of the electronic device provided by the present invention is shown. Figure 16 As shown, the electronic device includes a processor 101 and a memory 103. The memory 103 stores a computer program. When the computer program is executed by the processor 101, it implements the method for acquiring the digital structure of blood vessels described above.

[0202] like Figure 16As shown, the electronic device also includes a communication interface 102 and a communication bus 104, wherein the processor 101, the communication interface 102, and the memory 103 communicate with each other via the communication bus 104. The communication bus 104 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus 104 can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is used in the figure, but this does not indicate that there is only one bus or one type of bus. The communication interface 102 is used for communication between the aforementioned electronic device and other devices.

[0203] The processor 101 referred to in this invention can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor. The processor 101 is the control center of the electronic device, connecting various parts of the electronic device through various interfaces and lines.

[0204] The memory 103 can be used to store the computer program. The processor 101 implements various functions of the electronic device by running or executing the computer program stored in the memory 103 and calling the data stored in the memory 103.

[0205] The memory 103 may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0206] The present invention also provides a readable storage medium storing a computer program, which, when executed by a processor, can implement the method for acquiring the digital vascular structure described above.

[0207] The readable storage medium of embodiments of the present invention can be any combination of one or more computer-readable media. The readable medium can be a computer-readable signal medium or a computer-readable storage medium. Computer-readable storage media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: electrical connections having one or more wires, portable computer hard 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. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus, or device.

[0208] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0209] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as "C" or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0210] In summary, compared with existing technologies, the method, apparatus, electronic device, and storage medium for acquiring digital vascular structures provided by this invention have the following advantages: This invention first segments a pre-acquired medical image to obtain a vascular mask image; then, based on the vascular mask image, it obtains the vascular centerline corresponding to the region of interest; next, based on the vascular mask image, it determines the cross-section corresponding to each center point on the vascular centerline; finally, based on the vascular centerline and the cross-section corresponding to each center point on the vascular centerline, it acquires the digital structure of the region of interest. Therefore, based on this digital structure, any vascular segment can be digitally represented, requiring less storage and facilitating subsequent processing and analysis of the blood vessels.

[0211] It should be noted that the apparatus and methods disclosed in the embodiments herein can also be implemented in other ways. The apparatus embodiments described above are merely illustrative; for example, the flowcharts and block diagrams in the accompanying drawings show the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments herein. In this regard, each block in a flowchart or block diagram may represent a module, program, or part of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system to perform the specified function or action, or can be implemented using a combination of dedicated hardware and computer instructions.

[0212] In addition, the functional modules in the various embodiments of this article can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0213] The above description is merely a description of preferred embodiments of the present invention and is not intended to limit the scope of the invention in any way. Any changes or modifications made by those skilled in the art based on the above disclosure are within the protection scope of the present invention. Obviously, those skilled in the art can make various modifications and variations to the present invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the present invention and its equivalents, the present invention also intends to include these modifications and variations.

Claims

1. A method for acquiring digital vascular structures, characterized in that, include: The pre-acquired medical images are segmented to obtain vascular mask images; Based on the vascular mask image, obtain the center line of the vascular region of interest; Based on the vascular mask image, determine the cross-section corresponding to each center point on the vascular centerline; The digital structure of the blood vessel region of interest is obtained based on the blood vessel centerline and the cross-section corresponding to each center point on the blood vessel centerline. The step of obtaining the center line of the blood vessel corresponding to the region of interest based on the blood vessel mask image includes: Based on the vascular mask image, obtain the position coordinates of a starting point and several ending points; Using the starting point as the starting node and the ending point as the target node, the A* algorithm is used to determine the target path between the starting point and the ending point; Merge all target paths to obtain the vessel centerline corresponding to the region of interest; The cost function used in the A* algorithm is as follows: In the formula, F(P) is the total cost, G(P) is the actual cost from the starting node to node P, and H(P) is the estimated cost from node P to the ending node D. Let be the Euclidean distance from node P to the terminal node D. Let w1 be the Euclidean distance from node P to its parent node, w2 be the first weight coefficient, and w1 be the second weight coefficient. The formula for calculating the second weighting coefficient w2 is as follows: in, It is the second regulating factor, and , Let Z be the Z coordinate of node P. P The Z coordinate of the termination node D D The absolute value of the difference between them.

2. The method for obtaining digital vascular structures according to claim 1, characterized in that, The step of obtaining the digital structure of the region of interest based on the blood vessel centerline and the cross-section corresponding to each center point on the blood vessel centerline includes: The region of interest is divided into a corresponding number of vessel segments based on the number of center points on the vessel centerline. Based on the cross-section corresponding to each center point on the center line of the blood vessel, the parameters of the corresponding blood vessel segment are obtained; Based on the parameters of each blood vessel segment, three-dimensional reconstruction is performed to obtain the digital structure of the blood vessel region of interest.

3. The method for obtaining digital vascular structures according to claim 2, characterized in that, The parameters include the coordinates of the center point and the coordinates of the closed contour line.

4. The method for obtaining digital vascular structures according to claim 3, characterized in that, The parameters also include the area and / or perimeter and / or the maximum diameter and / or the minimum diameter and / or the coordinates of the contour points corresponding to the maximum diameter and / or the coordinates of the contour points corresponding to the minimum diameter and / or the normal vector.

5. The method for obtaining digital vascular structures according to claim 2, characterized in that, The step of obtaining the parameters of the corresponding blood vessel segment based on the cross-section corresponding to each center point on the blood vessel centerline includes: For each center point on the central line of the aforementioned blood vessel: Map the cross section corresponding to the center point onto the plane Z=0 to obtain the mapping plane corresponding to the center point; Based on the position coordinates of each pixel on the mapping plane, the attribute information of the mapping plane is obtained; Based on the attribute information of the mapping plane, the parameters of the blood vessel segment corresponding to the center point are obtained.

6. The method for obtaining digital vascular structures according to claim 1, characterized in that, The step of determining the cross-section corresponding to each center point on the blood vessel centerline based on the blood vessel mask image includes: Calculate the position coordinates of each non-zero pixel in the blood vessel mask image; For each center point on the central line of the aforementioned blood vessel: The center point and its adjacent neighboring center points are combined to form a first vector, and the center point and each of the non-zero pixel points are combined to form a second vector. Calculate the angle between the first vector and the second vector; The set of points consisting of non-zero pixels whose included angle is within a preset range is taken as the set of points of the cross section corresponding to the center point; The center point and the set of points corresponding to its cross-section are fitted together to obtain the cross-section corresponding to the center point.

7. The method for obtaining digital vascular structures according to claim 1, characterized in that, Before using the A* algorithm to determine the target path between the starting point and the ending point, the method further includes: For each non-zero pixel in the blood vessel mask image, its surrounding neighboring pixels are traversed from near to far until the zero pixel closest to the non-zero pixel is found. The distance between the non-zero pixel and the zero pixel is calculated and set as the pixel value of the non-zero pixel to obtain the blood vessel distance transformation image. The formula for calculating the first weighting coefficient w1 is as follows: in, It is the first regulating factor, and , It is the absolute value of the difference between the maximum pixel value in the blood vessel distance transformation image and the pixel value of node P in the blood vessel distance transformation image.

8. The method for obtaining digital vascular structures according to claim 1, characterized in that, Before merging all target paths to obtain the vessel centerline corresponding to the region of interest, the method further includes: The target path is modified to obtain a modified target path; The process of merging all target paths to obtain the vessel centerline corresponding to the region of interest includes: Merge all the corrected target paths to obtain the vessel centerline corresponding to the region of interest.

9. The method for obtaining digital vascular structures according to claim 8, characterized in that, The step of correcting the target path to obtain a corrected target path includes: A first correction process is performed on each path point on the target path corresponding to the unbranched blood vessel region to obtain the corresponding first corrected path point; A second correction process is performed on each path point on the target path corresponding to the bifurcation vessel region to obtain the corresponding second corrected path point; Based on the first and second corrected path points, obtain the corrected target path.

10. The method for obtaining digital vascular structures according to claim 9, characterized in that, Before performing the first correction process on each path point corresponding to the unbranched blood vessel region on the target path, the method further includes: For each non-zero pixel in the blood vessel mask image, its surrounding neighboring pixels are traversed from near to far until the zero pixel closest to the non-zero pixel is found. The distance between the non-zero pixel and the zero pixel is calculated and set as the pixel value of the non-zero pixel to obtain the blood vessel distance transformation image. The first correction process for each path point on the target path corresponding to the unbranched blood vessel region to obtain the corresponding first corrected path point includes: For each path point on the target path corresponding to the unbranched blood vessel region: The path point is mapped onto the first cross-sectional image corresponding to the blood vessel distance transformation image onto the Z=0 plane to obtain the corresponding first mapped image; The pixel with the largest pixel value in the first mapped image is taken as the corresponding first mapping point; Based on the first mapping point, obtain the corresponding first correction point.

11. The method for acquiring digital vascular structures according to claim 10, characterized in that, The second correction process for each path point on the target path corresponding to the bifurcation vessel region, to obtain the corresponding second corrected path point, includes: For each path point on the target path corresponding to the bifurcation vessel region: The path point is mapped onto the second cross-sectional image corresponding to the blood vessel distance transformation image onto the Z=0 plane to obtain the corresponding second mapped image; Based on the pixel values ​​of each pixel in the second mapped image, two peak points are obtained; The peak point closest to the path point is taken as the corresponding second mapping point; Based on the second mapping point, obtain the corresponding second correction point.

12. An electronic device, characterized in that, It includes a processor and a memory, wherein the memory stores a computer program, which, when executed by the processor, implements the method of any one of claims 1 to 11.

13. A readable storage medium, characterized in that, The readable storage medium stores a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 11.

Images