Method, device, equipment, medium and program product for obtaining aortic endpoint set

Abstract

The present application provides a method, apparatus, device, medium, and program product for obtaining an aortic endpoint set, including: preprocessing a CTA image based on a pretrained convolutional neural network algorithm to obtain a target segmentation prediction result and a trunk segmentation prediction result; obtaining a vascular vertex set (including at least one vascular endpoint) based on a vascular skeleton line of the target segmentation prediction result; extracting a first vascular endpoint from the at least one vascular endpoint to obtain a first endpoint set of the target aorta; determining a second endpoint set of the target aorta (aortic sinus endpoint, left iliac artery endpoint, and right iliac artery endpoint) based on the trunk segmentation prediction result; deduplicating the left iliac artery endpoint, the right iliac artery endpoint, and each first vascular endpoint to obtain a third endpoint set, removing the vascular endpoint closest to the aortic sinus endpoint in the third endpoint set to obtain an aortic endpoint set, thereby increasing the speed of determining vascular endpoints.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of medical imaging, and in particular to a method, apparatus, device, medium, and program product for obtaining an aortic endpoint set. Background Art

[0002] Currently, doctors can use the aortic centerline to analyze the presence, severity, and location of aortic lesions (such as aortic dissection or abdominal aortic aneurysm). The aortic centerline refers to the characteristic curve of the aorta obtained from aortic vascular imaging. Aortic vascular imaging refers to a three-dimensional vascular image of the patient's aorta obtained using a computed tomography angiography (CTA) device.

[0003] In the related art, the vascular endpoints (such as the starting point, bifurcation point and end point) manually marked by the marking party are first received, and each vascular endpoint and each vascular center point are connected to obtain the aortic centerline. The doctor analyzes the aortic centerline to obtain the lesion judgment result.

[0004] However, when manually marking the blood vessel endpoints, the marker needs to use auxiliary marking methods such as human-computer interaction, image magnification, and selection of magnified areas, which will result in a slow and inefficient manual marking of the blood vessel endpoints. Summary of the Invention

[0005] The present application provides a method, apparatus, device, medium and program product for obtaining an aortic endpoint set to increase the speed of determining vascular endpoints and improve efficiency.

[0006] In a first aspect, a method for obtaining an aortic endpoint set is provided, comprising: first, preprocessing a computed tomography angiography (CTA) image based on a pretrained convolutional neural network algorithm to obtain a target segmentation prediction result of the target aorta and a trunk segmentation prediction result of the target aorta. Next, based on the vascular skeleton line of the target segmentation prediction result, a vascular vertex set of the vascular segmentation in the target aorta is obtained. Then, a first vascular endpoint is extracted from at least one vascular endpoint to obtain a first endpoint set of the target aorta. Furthermore, based on the trunk segmentation prediction result, a second endpoint set of the target aorta is determined. Finally, a deduplication operation is performed on the left iliac artery endpoint, the right iliac artery endpoint, and each first vascular endpoint to obtain a third endpoint set of the target aorta, and the vascular endpoint closest to the aortic sinus endpoint in the third endpoint set is removed to obtain an aortic endpoint set.

[0007] The CTA image includes a slice image of the target aorta. The vascular vertices in the vascular vertex set include at least one vascular endpoint and at least one bifurcation point. The average endpoint radius of the vascular segment corresponding to the first vascular endpoint is greater than a preset radius threshold. The second endpoint set includes an aortic sinus endpoint, a left iliac artery endpoint, and a right iliac artery endpoint.

[0008] In a second aspect, a device for acquiring an aortic endpoint set is provided, comprising: a first acquisition module, a second acquisition module, a first processing module, a determination module, a second processing module, and a third acquisition module;

[0009] The first acquisition module is configured to preprocess the computed tomography angiography (CTA) image based on a pretrained convolutional neural network algorithm to obtain a target segmentation prediction result of the target aorta and a trunk segmentation prediction result of the target aorta; the CTA image includes a slice image of the target aorta;

[0010] A second acquisition module is configured to acquire a vascular vertex set of a vascular segment in a target aorta based on a vascular skeleton line of a target segmentation prediction result; the vascular vertices in the vascular vertex set include at least one vascular endpoint and at least one bifurcation point;

[0011] a first processing module, configured to extract a first blood vessel endpoint from at least one blood vessel endpoint to obtain a first endpoint set of a target aorta; wherein an average endpoint radius of a blood vessel segment corresponding to the first blood vessel endpoint is greater than a preset radius threshold;

[0012] a determination module, configured to determine a second endpoint set of the target aorta based on the trunk segmentation prediction result; the second endpoint set includes an aortic sinus endpoint, a left iliac artery endpoint, and a right iliac artery endpoint;

[0013] The second processing module is used to deduplicate the left iliac artery endpoint, the right iliac artery endpoint, and each first blood vessel endpoint to obtain a third endpoint set of the target aorta, and remove the blood vessel endpoint closest to the aortic sinus endpoint in the third endpoint set to obtain an aortic endpoint set.

[0014] In a third aspect, an electronic device is provided, comprising: a processor and a memory, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the method in the first aspect or its various implementations.

[0015] In a fourth aspect, a computer-readable storage medium is provided for storing a computer program, wherein the computer program enables a computer to execute the method according to the first aspect or its various implementations.

[0016] In a fifth aspect, a computer program product is provided, comprising computer program instructions, which enable a computer to execute the method in the first aspect or its various implementations.

[0017] In a sixth aspect, a computer program is provided, which enables a computer to execute the method in the first aspect or its various implementations.

[0018] Through the technical solution provided in this application, an electronic device can first preprocess a computed tomography angiography (CTA) image based on a pretrained convolutional neural network algorithm to obtain target segmentation prediction results for the target aorta and a trunk segmentation prediction result for the target aorta. Next, based on the vascular skeleton lines in the target segmentation prediction result, a set of vascular vertices for the vascular segments in the target aorta is obtained. Then, a first vascular endpoint is extracted from at least one vascular endpoint to obtain a first endpoint set for the target aorta. Furthermore, based on the trunk segmentation prediction result, a second endpoint set for the target aorta is determined. Finally, a deduplication operation is performed on the left iliac artery endpoint, the right iliac artery endpoint, and each first vascular endpoint to obtain a third endpoint set for the target aorta. The vascular endpoint closest to the aortic sinus endpoint in the third endpoint set is removed to obtain an aortic endpoint set. In this process, due to the network connection structure between the vascular endpoints, the electronic device can select first vascular endpoints with larger average endpoint radius using a preset radius threshold. This increases the likelihood that the first vascular endpoint belongs to the aortic centerline, speeds up vascular endpoint determination, and thus improves the efficiency of lesion diagnosis results. In the above process, the endpoint of the aortic sinus in the ascending aorta is determined by the structural characteristics of the aortic trunk, and the endpoint of the left iliac artery and the endpoint of the right iliac artery are further determined by determining the main trunk termination point of the descending aorta (the termination point of the descending aorta). In this way, the vascular endpoints in the first endpoint set are re-screened to increase the possibility that the vascular endpoints in the third endpoint set belong to the vascular endpoints on the centerline of the aorta, thereby increasing the speed of determining the vascular endpoints. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0020] Figure 1 An application scenario diagram provided for an embodiment of the present application;

[0021] Figure 2 A flow chart of the first method for obtaining an aortic endpoint set provided in an embodiment of the present application;

[0022] Figure 3 A flowchart of a second method for obtaining an aortic endpoint set provided in an embodiment of the present application;

[0023] Figure 4 A schematic diagram of a blood vessel outline provided in an embodiment of the present application;

[0024] Figure 5 A flowchart of a third method for obtaining an aortic endpoint set provided in an embodiment of the present application;

[0025] Figure 6 A flowchart of the fourth method for obtaining an aortic endpoint set provided in an embodiment of the present application;

[0026] Figure 7 A schematic diagram of an aortic endpoint provided in an embodiment of the present application;

[0027] Figure 8 A flowchart of the fifth method for obtaining an aortic endpoint set provided in an embodiment of the present application;

[0028] Figure 9 A schematic diagram of an aortic endpoint set provided in an embodiment of the present application;

[0029] Figure 10 A schematic diagram of an apparatus 1000 for acquiring an aortic endpoint set provided in an embodiment of the present application;

[0030] Figure 11 It is a schematic block diagram of an electronic device 1100 provided in an embodiment of the present application. DETAILED DESCRIPTION

[0031] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0032] It should be noted that the terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0033] As described above, in related technologies, the process first receives manually marked vascular endpoints (e.g., starting points, bifurcations, and endpoints) from a marker, then connects each vascular endpoint and each vascular center point to obtain the aortic centerline. The physician then analyzes the aortic centerline to determine the lesion. However, the manual marking of vascular endpoints by the marker requires auxiliary marking methods such as human-computer interaction, image magnification, and selection of magnified areas. This results in a slower manual marking process, which in turn reduces the efficiency of lesion determination.

[0034] To address the above technical problems, the present invention is based on the following concepts: an electronic device can map the continuity of blood vessels and the structural characteristics of the aorta, which consists of the ascending and descending aorta, into image features, thereby preventing subjective factors from affecting the accuracy of the aortic centerline. The electronic device can filter out first blood vessel endpoints with larger average endpoint radiuses using a preset radius threshold, thereby increasing the likelihood that the first blood vessel endpoints belong to the aortic centerline, improving the speed of determining blood vessel endpoints, and thus improving the efficiency of lesion diagnosis results. The electronic device can also determine the endpoints of the aortic sinus in the ascending aorta based on the structural characteristics of the aortic trunk, and further determine the endpoints of the left and right iliac arteries by determining the main terminus of the descending aorta (the terminus of the descending aorta). This further screens the blood vessel endpoints in the first endpoint set to increase the likelihood that the blood vessel endpoints in the third endpoint set belong to blood vessel endpoints on the aortic centerline, improving the speed of determining blood vessel endpoints, and thus improving the efficiency of lesion diagnosis results.

[0035] It should be understood that the technical solution of this application can be applied to the following scenarios, but is not limited to:

[0036] In some implementations, Figure 1 An application scenario diagram provided in an embodiment of the present application, such as Figure 1As shown, the application scenario may include an electronic device 110 and a network device 120. The electronic device 110 may establish a connection with the network device 120 via a wired network or a wireless network.

[0037] For example, electronic device 110 may be a desktop computer, laptop computer, tablet computer, etc., but is not limited thereto. Network device 120 may be a terminal device or a server, but is not limited thereto. In one embodiment of the present application, electronic device 110 may send a request message to network device 120, where the request message may be used to request acquisition of a CTA image. Furthermore, electronic device 110 may receive a response message from network device 120, where the response message includes the CTA image. Electronic device 110 may also perform image processing on the CTA image to obtain an aortic endpoint set.

[0038] also, Figure 1 An electronic device and a network device are given as an example, and in fact other numbers of electronic devices and network devices may be included, and this application does not impose any limitation on this.

[0039] In other possible implementations, the technical solution of the present application may also be executed by the above-mentioned electronic device 110, or the technical solution of the present application may also be executed by the above-mentioned network device 120, and the present application does not impose any restrictions on this.

[0040] After introducing the application scenarios of the embodiments of the present application, the technical solutions of the present application will be described in detail below:

[0041] Figure 2 A flowchart of a method for obtaining an aortic endpoint set provided in an embodiment of the present application, the method can be performed as follows Figure 1 The electronic device 110 shown in FIG. Figure 2 As shown, the method may include the following steps:

[0042] S210: The electronic device preprocesses the computed tomography angiography (CTA) image based on a pretrained convolutional neural network algorithm to obtain a target segmentation prediction result of the target aorta and a trunk segmentation prediction result of the target aorta.

[0043] In the embodiments of the present application, a CTA image is an X-ray scan of the target aorta after intravenous injection of a contrast agent, resulting in a computer-processed image that displays the internal features of the blood vessels in three dimensions. Specifically, a CTA image includes multiple slice images. The size of a CTA image can be M*N*L, where M and N are the length and width of each slice image, for example, M is 512, N is 512, and L is the number of slice images in the CTA image, that is, the number of slice image layers. Typically, slice images are acquired layer by layer, in the direction from the feet to the head of the human body.

[0044] In the embodiment of the present application, the CTA image includes a slice image of the target aorta, and also includes viscera, bones, muscles, fat and other human tissues in the same layer as the target aorta. The purpose of preprocessing the CTA image is to segment the vascular contour image from the CTA image.

[0045] In some implementations, such as Figure 3 As shown, the electronic device obtains the target segmentation prediction result of the target aorta and the trunk segmentation prediction result of the target aorta, which may include:

[0046] S310: The electronic device acquires each slice image in the CTA image.

[0047] S320: The electronic device inputs the grayscale value of each pixel in each layer of the slice image into a pre-trained convolutional neural network algorithm to obtain the grayscale feature value of each pixel in each layer of the slice image.

[0048] S330: The electronic device obtains a main trunk mask and a branch mask of the target aorta according to a preset main trunk threshold, a preset branch threshold, and a grayscale feature value of each pixel in each slice image.

[0049] S340: The electronic device determines the image corresponding to the trunk mask as the trunk segmentation prediction result of the target aorta, and combines the trunk mask and the branch mask to obtain the artery mask, and determines the image corresponding to the artery mask as the target segmentation prediction result of the target aorta.

[0050] In the embodiment of the present application, the slice image can be represented by grayscale values, and the corresponding grayscale value of each slice image can be recorded by a matrix, and the number of rows and columns of the matrix is ​​the same as that of the CTA image.

[0051] For example, each slice image is represented by a matrix where a mn Represents the grayscale value of the mth row and nth column.

[0052] In the embodiments of the present application, the pre-trained convolutional neural network algorithm refers to a neural network algorithm that has been trained with preset samples. It is a deep learning model commonly used to analyze visual images. Specifically, a Unet network, a VGGnet network, or a CNN network can be used.

[0053] For example, after pre-training the convolutional neural network algorithm, the grayscale feature value of each pixel in each slice image is obtained, and each slice image represented by the matrix Among them, f mn Represents the grayscale eigenvalue of the mth row and nth column.

[0054] For example, the trunk mask can be represented by a matrix, and the number of rows and columns of the matrix is ​​the same as the number of rows and columns corresponding to the slice image. Specifically, the grayscale eigenvalue of each pixel is compared with the preset trunk threshold T1. If the grayscale eigenvalue is greater than T1, the corresponding value of the pixel in the trunk mask matrix is ​​set to 1, and the corresponding values ​​of the remaining pixels are set to 0. Then, the image corresponding to the trunk mask is determined as the trunk segmentation prediction result of the target aorta. Figure 4 As shown in (a) in FIG. 3 , the trunk segmentation prediction result includes the vascular contour of the aortic trunk of the target aorta.

[0055] For example, similarly, the branch mask can also be represented by a matrix, and the number of rows and columns of the matrix is ​​the same as the number of rows and columns corresponding to the slice image. Specifically, the grayscale eigenvalue of each pixel is compared with the preset branch threshold T2. If the grayscale eigenvalue is greater than T2, the corresponding value of the pixel in the branch mask matrix is ​​determined to be set to 2, and the corresponding values ​​of the remaining pixels are set to 0. Then, the image corresponding to the branch mask is determined as the branch segmentation prediction result of the target aorta. It should be noted that the specific values ​​of T1 and T2 are not limited in the embodiment of the present application. Figure 4 As shown in (b) in FIG. 5 , the branch segmentation prediction result includes the vascular contours of the aortic branches of the target aorta.

[0056] For example, the trunk mask and the branch mask are combined to obtain the artery mask, and the image corresponding to the artery mask is determined as the target segmentation prediction result of the target aorta. The image corresponding to the artery mask is the mask image of the slice image. The mask image of each slice image Among them, b mn The pixel mask of the mth row and nth column is represented by the first mark of the aorta trunk of the target aorta being 1, the second mark of the aorta branch of the target aorta being 2, and the mark of the other parts except the aorta trunk and aorta branches being 0. Figure 4 As shown in (c) in FIG. 5 , the target segmentation prediction result includes the vascular contours of the aorta main trunk and aorta branches of the target aorta.

[0057] In this way, the CTA image is preprocessed by a pre-trained convolutional neural network to obtain a mask image of the CTA image. The aorta, aorta branches and non-aorta parts in the image are clearly distinguished through the mask image, so as to obtain a clear and accurate vascular contour image (i.e., the target segmentation prediction result of the target aorta, the trunk segmentation prediction result of the aorta), which can narrow the range of vascular endpoints for obtaining the aorta endpoint set, thereby improving the speed of obtaining the aorta endpoint set.

[0058] S220: The electronic device obtains a blood vessel vertex set of the blood vessel segment in the target aorta according to the blood vessel skeleton line of the target segmentation prediction result.

[0059] It can be understood that the vascular skeleton line refers to a thin vascular curve that is consistent with the original vascular connectivity and topological structure.

[0060] The blood vessel vertices in the blood vessel vertex set include at least one blood vessel endpoint and at least one bifurcation point.

[0061] In some implementations, such as Figure 5 As shown, the electronic device obtains a vascular vertex set of a vascular segment in the target aorta according to the vascular skeleton line of the target segmentation prediction result, which may include:

[0062] S510: The electronic device refines the target segmentation prediction result according to a preset refinement algorithm to obtain a vascular skeleton line of the target aorta.

[0063] The preset thinning algorithm may be a morphological thinning algorithm or a binary thinning algorithm, and the position of the target pixel point may be determined by gradually corroding the target segmentation prediction result from the outer layer to obtain the blood vessel skeleton line.

[0064] S520: The electronic device obtains blood vessel vertices of the blood vessel segment in the target aorta according to the number of neighboring points of each pixel point on the blood vessel skeleton line, and obtains a blood vessel vertex set.

[0065] In the embodiment of the present application, the number of neighboring points of each pixel on the blood vessel skeleton line is obtained, and the number of neighboring points can be 1, 2, 3, or more than 3. If the number of neighboring points is 1, then the pixel is a blood vessel endpoint; if the number of neighboring points is 2, then the pixel is a common connection point; if the number of neighboring points is 3 or more, then the pixel is a bifurcation point.

[0066] In the embodiment of the present application, both the blood vessel endpoints and bifurcation points are blood vessel vertices. After determining whether all pixel points on the blood vessel skeleton line are blood vessel vertices, a blood vessel vertex set is obtained.

[0067] In this way, the vascular vertices in the vascular vertex concentration include vascular endpoints on the aortic centerline, so that the number of endpoints in the aortic centerline can be reduced, and the speed of acquiring the aortic centerline can be increased.

[0068] S230: The electronic device extracts a first blood vessel endpoint from at least one blood vessel endpoint to obtain a first endpoint set of the target aorta.

[0069] The average radius of the endpoints of the blood vessel segments corresponding to the first blood vessel endpoint is greater than a preset radius threshold.

[0070] In some implementations, such as Figure 5 As shown, the electronic device extracts a first blood vessel endpoint from at least one blood vessel endpoint to obtain a first endpoint set of the target aorta, which may include:

[0071] S530: The electronic device obtains an average vertex radius of each blood vessel vertex according to the adjacency order of each blood vessel vertex in the blood vessel vertex set obtained through the blood vessel skeleton line.

[0072] In the embodiment of the present application, after two directly connected blood vessel vertices are determined, the average radius of the blood vessel segment between the two directly connected blood vessel vertices is defined as the average vertex radius of the blood vessel segment.

[0073] It should be noted that two blood vessel vertices with a directly connected radius (average radius of vertices) may be a blood vessel endpoint and a bifurcation point, or a bifurcation point and a bifurcation point, or a blood vessel endpoint and a blood vessel endpoint.

[0074] For example, the vascular vertex set includes five vascular endpoints (E0, E1, E2, E3, and E4) and three bifurcation points (B0, B1, and B2). The adjacency order of each vascular vertex is as follows: vascular endpoint E0 is connected to bifurcation point B0, bifurcation point B0 is connected to bifurcation points B1 and B2 respectively, bifurcation point B1 is connected to vascular endpoint E1 and vascular endpoint E2 respectively, and bifurcation point B2 is connected to vascular endpoint E3 and vascular endpoint E4 respectively. Based on the connection relationship between the above eight vascular vertices, it can be seen that the direct connection radius between each vascular vertex (i.e., the average vertex radius) includes: E0-B0 direct connection radius, B0-B1 direct connection radius, B1-E1 direct connection radius, B1-E2 direct connection radius, B0-B2 direct connection radius, B2-E3 direct connection radius, and B2-E4 direct connection radius.

[0075] In the above example, for the E0-B0 direct connection radius, the specific calculation process may include: first, the electronic device obtains the common connection points between the blood vessel endpoint E0 and the bifurcation point B0 (a total of 10); next, the electronic device obtains 10 inscribed sphere radii corresponding to the 10 common connection points respectively, and with each common connection point as the center, the pixel points within the range of the corresponding inscribed sphere radius (spherical radius) are all pixel points in the blood vessel skeleton line; finally, the electronic device determines the average value of the 10 inscribed sphere radii as the average radius between the blood vessel vertices E0-B0.

[0076] S540: The electronic device obtains an endpoint average radius of a blood vessel segment corresponding to each blood vessel endpoint in at least one blood vessel endpoint according to the vertex average radius of each blood vessel vertex and the adjacency order of each blood vessel vertex in the blood vessel vertex set.

[0077] It is understood that, among the direct connection radii of the vascular vertices obtained in S530, if one of the vascular vertices is a vascular endpoint, then the direct connection radius is the average endpoint radius corresponding to the vascular endpoint. The vascular endpoint refers to any one of the at least one vascular endpoints.

[0078] Exemplarily, according to the example involved in S530, the vascular vertex set includes 5 vascular endpoints (E0, E1, E2, E3 and E4) and 3 bifurcation points (B0, B1 and B2). Then the average endpoint radius of the vascular segment corresponding to each vascular endpoint includes the E0-B0 direct connection radius, the B1-E1 direct connection radius, the B1-E2 direct connection radius, the B2-E3 direct connection radius and the B2-E4 direct connection radius.

[0079] S550: The electronic device extracts a first blood vessel endpoint from at least one blood vessel endpoint according to a preset image layering direction to obtain a first endpoint set of the target aorta.

[0080] Among them, the average endpoint radius of the vascular segment corresponding to the first vascular endpoint is greater than the preset radius threshold. The first endpoint set can also be called the larger radius endpoint set, that is, the endpoints corresponding to the thicker vascular segments on the vascular skeleton line. According to the structural characteristics of the aorta, the vascular endpoint corresponding to the thicker vascular segment is more likely to be the vascular endpoint on the centerline of the aorta. Therefore, the first vascular endpoint in the first endpoint set may be the left iliac artery endpoint, the right iliac artery endpoint, the left subclavian artery endpoint, the left common carotid artery endpoint, the right common carotid artery endpoint, the right subclavian artery endpoint, the left renal artery endpoint, the right renal artery endpoint, etc.

[0081] It should be noted that the electronic device obtains the first of the at least one vascular endpoints according to a preset image layering direction, and determines whether the average endpoint radius of the vascular segment corresponding to the first vascular endpoint is greater than a preset radius threshold. If the determination result is yes, the first vascular endpoint is confirmed as the first vascular endpoint and added to the first endpoint set. If the determination result is no, the electronic device proceeds to the next step. Next, the electronic device obtains the second of the at least one vascular endpoints according to the preset image layering direction, and determines whether the average endpoint radius of the vascular segment corresponding to the second vascular endpoint is greater than the preset radius threshold. This process continues until each of the at least one vascular endpoints is determined, and the first endpoint set of the target aorta is obtained based on the comparison results.

[0082] In this way, the vascular skeleton line of the target segmentation prediction result is used to extract the first vascular endpoint with a larger vascular radius in the aorta, so as to reduce the number of endpoints in the aortic centerline, thereby increasing the speed of obtaining the aortic centerline, retaining the curve characteristics of the aorta, and increasing the possibility that the first vascular endpoint belongs to the aortic centerline, without affecting the doctor's judgment of the lesion.

[0083] S240: The electronic device determines a second endpoint set of the target aorta based on the trunk segmentation prediction result.

[0084] The second endpoint set includes an aortic sinus endpoint, a left iliac artery endpoint, and a right iliac artery endpoint.

[0085] It should be noted that the trunk segmentation prediction result refers to the vascular contour of the aorta. The aorta is the largest artery in the human body. It originates from the left ventricle of the heart, extending upward, rightward, and downward in a slightly arched shape. It then descends along the spine and branches into many smaller arteries within the chest and abdominal cavities. The aorta's anatomical structure is an arch, originating from the left ventricle, extending upward and rightward, and then descending along the chest cavity into the abdominal cavity. It has a complex morphological structure. Specifically, the aorta consists of the ascending aorta, the aortic arch, and the descending aorta.

[0086] In some implementations, such as Figure 6 As shown, the electronic device determines the second endpoint set of the target aorta based on the trunk segmentation prediction result, which may include:

[0087] S610: The electronic device extracts, from at least one blood vessel endpoint, a blood vessel endpoint corresponding to the ascending aorta and a blood vessel endpoint corresponding to the descending aorta based on the aortic trunk structure.

[0088] S620: The electronic device searches for a second blood vessel endpoint among the blood vessel endpoints corresponding to the ascending aorta according to a preset image layering direction.

[0089] The preset image layering direction may be a layering direction from a minimum layering direction value corresponding to a blood vessel endpoint in the first endpoint set to a maximum layering direction value, where the layering direction value decreases as the blood vessel endpoint is closer to the foot. The number of connected regions corresponding to the current slice image where the second blood vessel endpoint is located is 1, and the number of connected regions corresponding to the next slice image where the second blood vessel endpoint is located is 2.

[0090] S630: The electronic device determines the main trunk starting point at the center of the connected area corresponding to the current layer slice image where the second blood vessel endpoint is located as the aortic sinus endpoint.

[0091] S640: The electronic device determines the center point of the connected area corresponding to the current layer slice image where the third blood vessel endpoint is located as the main trunk end point.

[0092] The third vascular endpoint is the vascular endpoint corresponding to the minimum preset image layer direction value among the vascular endpoints corresponding to the descending active state. The minimum preset image layer direction value is the minimum layer direction value among the direction values ​​corresponding to the preset image layer directions for each slice image in which the vascular endpoints in the third vascular endpoints are located.

[0093] S650: The electronic device searches for a fourth blood vessel endpoint that is farthest from the main trunk endpoint among at least one blood vessel endpoint, and a fifth blood vessel endpoint that is farthest from the fourth blood vessel endpoint among at least one blood vessel endpoint, and determines the fourth blood vessel endpoint as the left iliac artery endpoint or the right iliac artery endpoint, and correspondingly, determines the fifth blood vessel endpoint as the right iliac artery endpoint or the left iliac artery endpoint.

[0094] S660: The electronic device adds the aortic sinus endpoint, the left iliac artery endpoint, and the right iliac artery endpoint to the second endpoint set.

[0095] For example, the initial endpoint set E0 is formed by all the blood vessel endpoints of at least one blood vessel endpoint in the blood vessel vertex set, which is equal to (e1, e2, ..., e k ), get e k The Z value is Z max , the Z value of e1 is Z min , where the Z value changes gradually from small to large along the preset image layering direction. min to Z max within the scope of Figure 7 As shown in (a), the center point of the region where the current slice image has a connected region and the next slice image has two connected regions is found, which is C0 = (x0, y0, z0). Among the vascular endpoints corresponding to the descending aorta, as shown in Figure 7 As shown in (b), the blood vessel endpoint with the smallest Z value is determined as the main trunk termination point C1 = (x1, y1, z1), and the Z value Z of the main trunk termination point is recorded. main_end From Z min to Z main_end In the range of k ) corresponding endpoint subset E2=(e1,e2,…,e m )(m≤k), find the endpoint C2 from this subset that is farthest from the main trunk's end point C1. Map the endpoint subset to a plane parallel to the Z axis and find the endpoint C3 within this plane that is farthest from C2. C2 and μ3 are the endpoints of the left or right iliac artery, respectively.

[0096] Thus, in the above process, the endpoint of the aortic sinus in the ascending aorta is determined by the structural characteristics of the aortic trunk, and the endpoint of the left iliac artery and the right iliac artery are further determined by determining the main trunk termination point of the descending aorta (the termination point of the descending aorta), so as to increase the possibility that the vascular endpoint in the third endpoint concentration belongs to the vascular endpoint on the center line of the aorta, increase the speed of determining the vascular endpoint, and thereby improve the efficiency of obtaining the lesion judgment results.

[0097] S250: The electronic device performs a deduplication operation on the left iliac artery endpoint, the right iliac artery endpoint, and each first blood vessel endpoint to obtain a third endpoint set of the target aorta, removes the blood vessel endpoint closest to the aortic sinus endpoint in the third endpoint set, and obtains an aortic endpoint set.

[0098] It should be noted that during the deduplication process, deduplication can be performed when the distance between any two of the left iliac artery endpoint, the right iliac artery endpoint, and each first vessel endpoint is less than a preset threshold. The removed vessel endpoint can be any vessel endpoint that meets the deduplication criteria.

[0099] It should also be noted that by removing the vascular endpoint closest to the aortic sinus endpoint in the third endpoint concentration, it is avoided that adjacent vascular endpoints influence each other, resulting in an inaccurate curve of the aortic centerline.

[0100] In an embodiment of the present application, the aortic endpoint set includes the aortic sinus endpoint, the left iliac artery endpoint, the right iliac artery endpoint, the left subclavian artery endpoint, the left common carotid artery endpoint, the right common carotid artery endpoint, the right subclavian artery endpoint, the left renal artery endpoint and the right renal artery endpoint.

[0101] In summary, in the above-mentioned process of obtaining the aortic endpoint set of the target aorta, due to the network connection structure between the various vascular endpoints, the electronic device can screen out the first vascular endpoint with a larger endpoint average radius through a preset radius threshold, which can increase the possibility that the first vascular endpoint belongs to the aortic centerline, improve the speed of determining the vascular endpoint, and thus improve the efficiency of obtaining the lesion judgment result. In the above-mentioned process of obtaining the aortic centerline of the target aorta, due to the structural characteristics of the aortic trunk, the endpoint of the aortic sinus in the ascending aorta is determined, and by determining the main trunk termination point of the descending aorta (the termination point of the descending aorta), the left iliac artery endpoint and the right iliac artery endpoint are further determined, so as to re-screen the vascular endpoints in the first endpoint set, so as to increase the possibility that the vascular endpoints in the third endpoint set belong to the vascular endpoints on the aortic centerline, improve the speed of determining the vascular endpoint, and thus improve the efficiency of obtaining the lesion judgment result.

[0102] In the embodiment of the present application, due to individual lesion differences, CTA images may have abnormalities, resulting in the image display position of the vascular endpoint in the aorta endpoint being significantly different from the image display position of the actual vascular endpoint. To this end, the present application also provides a human-computer interaction solution, such as Figure 8 As shown, after obtaining the aortic endpoint set, the method for obtaining the aortic endpoint set provided by the present application further includes:

[0103] S810: The electronic device displays each blood vessel endpoint in the aorta endpoint set on an image display interface.

[0104] S820: In response to the user's endpoint modification operation, the electronic device re-labels at least one blood vessel endpoint in the aorta endpoint set and determines it as the aorta endpoint set.

[0105] It should be noted that the endpoint modification operation can modify the image display position of any vascular endpoint in the aortic endpoint set. The electronic device can modify the image display positions of multiple vascular endpoints in response to a single user endpoint modification operation (for multiple vascular endpoints). The electronic device can also modify the image display position of the same vascular endpoint in response to multiple user endpoint modification operations (for the same vascular endpoint).

[0106] It is understandable that the electronic device can also receive image processing operations performed by the user on the slice image, such as zooming in, zooming out, moving, highlighting, etc., which is not limited in the embodiments of the present application.

[0107] In this way, by setting up a human-computer interaction mechanism, the user can re-mark the vascular endpoints of the aortic endpoint set, which can improve the accuracy of the aortic endpoint set and further improve the accuracy of the obtained aortic centerline.

[0108] In an embodiment of the present application, after obtaining the aortic endpoint set, the electronic device can start from the aortic sinus endpoint and traverse each vascular endpoint in the aortic endpoint set in sequence according to the adjacency relationship between the vascular endpoints. If the slice images corresponding to the adjacent vascular endpoints are also adjacent, then the two adjacent vascular endpoints are directly determined as pixel points on the aortic centerline. If the slice images corresponding to the adjacent vascular endpoints are not adjacent, then the pixel points on the aortic centerline are determined based on the curve direction of the vascular segmentation in the target segmentation prediction result. In this way, Figure 9 As shown, the aortic centerline of the target aorta is obtained from the CTA image.

[0109] Figure 10 The present invention provides a schematic diagram of a device 1000 for obtaining an aortic endpoint set. Figure 10 As shown, the device 1000 includes:

[0110] A first acquisition module 1001 is configured to pre-process a computed tomography angiography (CTA) image based on a pre-trained convolutional neural network algorithm to obtain a target segmentation prediction result of a target aorta and a trunk segmentation prediction result of the target aorta; the CTA image includes a slice image of the target aorta;

[0111] A second acquisition module 1002 is configured to acquire a vascular vertex set of a vascular segment in a target aorta based on a vascular skeleton line of a target segmentation prediction result; the vascular vertices in the vascular vertex set include at least one vascular endpoint and at least one bifurcation point;

[0112] The first processing module 1003 is configured to extract a first blood vessel endpoint from at least one blood vessel endpoint to obtain a first endpoint set of the target aorta; the average endpoint radius of the blood vessel segment corresponding to the first blood vessel endpoint is greater than a preset radius threshold;

[0113] A determination module 1004 is configured to determine a second endpoint set of the target aorta based on the trunk segmentation prediction result; the second endpoint set includes an aortic sinus endpoint, a left iliac artery endpoint, and a right iliac artery endpoint;

[0114] The second processing module 1005 is used to deduplicate the left iliac artery endpoint, the right iliac artery endpoint, and each first blood vessel endpoint to obtain a third endpoint set of the target aorta, and remove the blood vessel endpoint closest to the aortic sinus endpoint in the third endpoint set to obtain an aortic endpoint set.

[0115] It should be understood that the embodiment of the apparatus for obtaining the aortic endpoint set and the embodiment of the method for obtaining the aortic endpoint set may correspond to each other, and similar descriptions may refer to the embodiment of the method for obtaining the aortic endpoint set. To avoid repetition, they will not be described here. Specifically, Figure 10 The device 1000 shown can execute the above-mentioned method embodiment for obtaining the aortic endpoint set, and the aforementioned and other operations and / or functions of each module in the device 1000 are respectively for implementing the corresponding processes in the above-mentioned method for obtaining the aortic endpoint set. For the sake of brevity, they will not be repeated here.

[0116] The above description of the device 1000 according to the embodiment of the present application is based on the functional modules in conjunction with the accompanying drawings. It should be understood that the functional modules can be implemented in hardware, or in software, or in combination with hardware and software modules. Specifically, the steps of the method for obtaining the aortic endpoint set in the embodiment of the present application can be completed by the hardware integrated logic circuit and / or software instructions in the processor. The steps of the method for obtaining the aortic endpoint set disclosed in the embodiment of the present application can be directly embodied as being executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. Optionally, the software module can be located in a mature storage medium in the art, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps in the above-mentioned method for obtaining the aortic endpoint set in combination with its hardware.

[0117] Figure 11 It is a schematic block diagram of an electronic device 1100 provided in an embodiment of the present application.

[0118] like Figure 11 As shown, the electronic device 1100 may include:

[0119] The memory 1110 and the processor 1120 are configured to store computer programs and transmit the program code to the processor 1120. In other words, the processor 1120 can call and execute the computer program from the memory 1110 to implement the method in the embodiment of the present application.

[0120] For example, the processor 1120 may be configured to execute the above method embodiments according to instructions in the computer program.

[0121] In some embodiments of the present application, the processor 1120 may include but is not limited to:

[0122] General-purpose processor, digital signal processor (DSP), application-specific integrated circuit (ASIC), field-programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, etc.

[0123] In some embodiments of the present application, the memory 1110 includes but is not limited to:

[0124] Volatile memory and / or non-volatile memory. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct RAM bus random access memory (DR RAM).

[0125] In some embodiments of the present application, the computer program may be divided into one or more modules, which are stored in the memory 1110 and executed by the processor 1120 to implement the method provided by the present application. The one or more modules may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program in the electronic device.

[0126] like Figure 11 As shown, the electronic device may further include:

[0127] The transceiver 1130 may be connected to the processor 1120 or the memory 1110 .

[0128] The processor 1120 may control the transceiver 1130 to communicate with other devices. Specifically, it may send information or data to other devices or receive information or data sent by other devices. The transceiver 1130 may include a transmitter and a receiver. The transceiver 1130 may further include an antenna, which may be one or more.

[0129] It should be understood that the various components in the electronic device are connected via a bus system, wherein the bus system includes not only a data bus but also a power bus, a control bus and a status signal bus.

[0130] The present application also provides a computer storage medium having a computer program stored thereon, which, when executed by a computer, enables the computer to perform the method of the above-mentioned method embodiment. In other words, the present application also provides a computer program product containing instructions, which, when executed by a computer, enables the computer to perform the method of the above-mentioned method embodiment.

[0131] When software is used for implementation, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a digital video disc (DVD)), or a semiconductor medium (e.g., a solid state drive (SSD)).

[0132] Those skilled in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0133] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the modules is merely a logical function division. In actual implementation, there may be other division methods, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0134] Modules described as separate components may or may not be physically separate, and components displayed as modules may or may not be physical modules, i.e., they may be located in one place or distributed across multiple network elements. Some or all of the modules may be selected based on actual needs to achieve the purpose of the present embodiment. For example, the functional modules in the various embodiments of the present application may be integrated into a processing module, or each module may exist physically separately, or two or more modules may be integrated into a single module.

[0135] The above are only specific embodiments of the present application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A method for obtaining an aortic endpoint set, characterized in that: include: Preprocessing a computed tomography angiography (CTA) image based on a pretrained convolutional neural network algorithm to obtain a target segmentation prediction result of a target aorta and a trunk segmentation prediction result of the target aorta; the CTA image includes a slice image of the target aorta; Acquire a vascular vertex set of the vascular segment in the target aorta according to the vascular skeleton line of the target segmentation prediction result; the vascular vertices in the vascular vertex set include at least one vascular endpoint and at least one bifurcation point; Extracting a first blood vessel endpoint from the at least one blood vessel endpoint to obtain a first endpoint set of the target aorta; wherein an average endpoint radius of the blood vessel segment corresponding to the first blood vessel endpoint is greater than a preset radius threshold; determining a second endpoint set of the target aorta according to the trunk segmentation prediction result; The second endpoint set includes an aortic sinus endpoint, a left iliac artery endpoint, and a right iliac artery endpoint; performing a deduplication operation on the left iliac artery endpoint, the right iliac artery endpoint, and each of the first blood vessel endpoints to obtain a third endpoint set of the target aorta, and removing the blood vessel endpoint closest to the aortic sinus endpoint in the third endpoint set to obtain an aortic endpoint set; Wherein, determining the second endpoint set of the target aorta according to the trunk segmentation prediction result includes: Extracting, from the at least one blood vessel endpoint, a blood vessel endpoint corresponding to the ascending aorta and a blood vessel endpoint corresponding to the descending aorta according to the aortic trunk structure; searching, according to a preset image layering direction, for a second vascular endpoint among the vascular endpoints corresponding to the ascending aorta, wherein the number of connected regions corresponding to the current slice image where the second vascular endpoint is located is 1, and the number of connected regions corresponding to the next slice image where the second vascular endpoint is located is 2; Determine the main starting point of the center of the connected area corresponding to the current slice image where the second blood vessel endpoint is located as the aortic sinus endpoint; Determine the center point of the connected area corresponding to the current slice image where the third blood vessel endpoint is located as the main trunk termination point, wherein the third blood vessel endpoint is the blood vessel endpoint corresponding to the minimum preset image layer direction value among the blood vessel endpoints corresponding to the descending aorta; searching for a fourth blood vessel endpoint farthest from the main trunk endpoint among the at least one blood vessel endpoint, and a fifth blood vessel endpoint farthest from the fourth blood vessel endpoint among the at least one blood vessel endpoint, determining the fourth blood vessel endpoint as the left iliac artery endpoint or the right iliac artery endpoint, and correspondingly determining the fifth blood vessel endpoint as the right iliac artery endpoint or the left iliac artery endpoint; The aortic sinus endpoint, the left iliac artery endpoint, and the right iliac artery endpoint are added to the second endpoint set.

2. The method according to claim 1, characterized in that The method of preprocessing the CTA image based on the pretrained convolutional neural network algorithm to obtain the target segmentation prediction result of the target aorta and the trunk segmentation prediction result of the target aorta includes: Acquiring each slice image in the CTA image; Inputting the grayscale value of each pixel in each layer of the slice image into the pre-trained convolutional neural network algorithm to obtain the grayscale feature value of each pixel in each layer of the slice image; Obtaining a main trunk mask and a branch mask of the target aorta according to a preset main trunk threshold, a preset branch threshold, and a grayscale feature value of each pixel in each slice image; The image corresponding to the trunk mask is determined as the trunk segmentation prediction result of the target aorta, and the trunk mask and the branch mask are combined to obtain an artery mask, and the image corresponding to the artery mask is determined as the target segmentation prediction result of the target aorta.

3. The method according to claim 1 or 2, characterized in that The step of obtaining a vascular vertex set of a vascular segment in the target aorta according to the vascular skeleton line of the target segmentation prediction result includes: Refining the target segmentation prediction result according to a preset refinement algorithm to obtain a vascular skeleton line of the target aorta; Obtaining the vascular vertices of the vascular segment in the target aorta according to the number of neighboring points of each pixel point on the vascular skeleton line to obtain the vascular vertex set; The step of extracting a first blood vessel endpoint from the at least one blood vessel endpoint to obtain a first endpoint set of the target aorta includes: Obtaining an average vertex radius of each blood vessel vertex according to an adjacency order of each blood vessel vertex in the blood vessel vertex set obtained through the blood vessel skeleton line; Obtaining an endpoint average radius of a blood vessel segment corresponding to each blood vessel endpoint in the at least one blood vessel endpoint according to the vertex average radius of each blood vessel vertex and the adjacency order of each blood vessel vertex in the blood vessel vertex set; According to a preset image layering direction, a first blood vessel endpoint is extracted from the at least one blood vessel endpoint to obtain a first endpoint set of the target aorta; the average endpoint radius of the blood vessel segment corresponding to the first blood vessel endpoint is greater than a preset radius threshold.

4. The method according to claim 1, wherein After performing a deduplication operation on the left iliac artery endpoint, the right iliac artery endpoint, and each of the first blood vessel endpoints to obtain a third endpoint set of the target aorta, and removing the blood vessel endpoint closest to the aortic sinus endpoint in the third endpoint set to obtain the aortic endpoint set, the method further includes: On an image display interface, displaying each blood vessel endpoint in the aorta endpoint set; In response to the user's endpoint modification operation, at least one blood vessel endpoint in the re-labeled aortic endpoint set is determined as the aortic endpoint set.

5. A device for obtaining an aortic endpoint set, characterized in that: include: a first acquisition module, configured to preprocess a computed tomography angiography (CTA) image based on a pretrained convolutional neural network algorithm to obtain a target segmentation prediction result of a target aorta and a trunk segmentation prediction result of the target aorta; the CTA image includes a slice image of the target aorta; A second acquisition module is configured to acquire a vascular vertex set of the vascular segment in the target aorta based on the vascular skeleton line of the target segmentation prediction result; the vascular vertices in the vascular vertex set include at least one vascular endpoint and at least one bifurcation point; a first processing module, configured to extract a first blood vessel endpoint from the at least one blood vessel endpoint to obtain a first endpoint set of the target aorta; wherein the average endpoint radius of the blood vessel segment corresponding to the first blood vessel endpoint is greater than a preset radius threshold; a determination module, configured to determine a second endpoint set of the target aorta based on the trunk segmentation prediction result; The second endpoint set includes an aortic sinus endpoint, a left iliac artery endpoint, and a right iliac artery endpoint; a second processing module, configured to perform a deduplication operation on the left iliac artery endpoint, the right iliac artery endpoint, and each of the first blood vessel endpoints to obtain a third endpoint set of the target aorta, and remove the blood vessel endpoint closest to the aortic sinus endpoint from the third endpoint set to obtain an aortic endpoint set; Wherein, determining the second endpoint set of the target aorta according to the trunk segmentation prediction result includes: Extracting, from the at least one blood vessel endpoint, a blood vessel endpoint corresponding to the ascending aorta and a blood vessel endpoint corresponding to the descending aorta according to the aortic trunk structure; searching, according to a preset image layering direction, for a second vascular endpoint among the vascular endpoints corresponding to the ascending aorta, wherein the number of connected regions corresponding to the current slice image where the second vascular endpoint is located is 1, and the number of connected regions corresponding to the next slice image where the second vascular endpoint is located is 2; Determine the main starting point of the center of the connected area corresponding to the current slice image where the second blood vessel endpoint is located as the aortic sinus endpoint; Determine the center point of the connected area corresponding to the current slice image where the third blood vessel endpoint is located as the main trunk termination point, wherein the third blood vessel endpoint is the blood vessel endpoint corresponding to the minimum preset image layer direction value among the blood vessel endpoints corresponding to the descending aorta; searching for a fourth blood vessel endpoint farthest from the main trunk endpoint among the at least one blood vessel endpoint, and a fifth blood vessel endpoint farthest from the fourth blood vessel endpoint among the at least one blood vessel endpoint, determining the fourth blood vessel endpoint as the left iliac artery endpoint or the right iliac artery endpoint, and correspondingly determining the fifth blood vessel endpoint as the right iliac artery endpoint or the left iliac artery endpoint; The aortic sinus endpoint, the left iliac artery endpoint, and the right iliac artery endpoint are added to the second endpoint set.

6. The device according to claim 5, characterized in that The first acquisition module is specifically configured to: Acquiring each slice image in the CTA image; Inputting the grayscale value of each pixel in each layer of the slice image into the pre-trained convolutional neural network algorithm to obtain the grayscale feature value of each pixel in each layer of the slice image; Obtaining a main trunk mask and a branch mask of the target aorta according to a preset main trunk threshold, a preset branch threshold, and a grayscale feature value of each pixel in each slice image; The image corresponding to the trunk mask is determined as the trunk segmentation prediction result of the target aorta, and the trunk mask and the branch mask are combined to obtain an artery mask, and the image corresponding to the artery mask is determined as the target segmentation prediction result of the target aorta.

7. An electronic device, characterized in that: include: A processor and a memory, the memory being used to store a computer program, and the processor being used to call and run the computer program stored in the memory to execute the method according to any one of claims 1 to 4.

8. A computer-readable storage medium, characterized in that Used to store a computer program, wherein the computer program causes a computer to execute the method according to any one of claims 1 to 4.

9. A computer program product comprising instructions, characterized in that When the computer program product is run on an electronic device, the electronic device is enabled to execute the method according to any one of claims 1 to 4.

Images