Method for extracting a blood vessel centerline and storage medium

Abstract

The application relates to a blood vessel center line extraction method and device, computer equipment, a storage medium and a computer program product. An initial black blood image of a to-be-measured object is acquired, and the initial black blood image is input into a preset first segmentation model to obtain a first blood vessel segmentation image comprising at least one blood vessel segment. The center line of each blood vessel segment in the first blood vessel segmentation image is extracted to obtain a blood vessel center line image corresponding to the initial black blood image. The automatic extraction method can directly acquire the blood vessel center line from the black blood image, does not need to use a bright blood image corresponding to the black blood image, does not need to additionally acquire the bright blood image, and does not need to consider the quality problem of the bright blood image and the accuracy problem of registration. After the initial black blood image is acquired, the method in the embodiment can directly obtain the blood vessel center line image corresponding to the initial black blood image through identification and processing of the initial black blood image, and the extraction efficiency is high.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer and image processing, and particularly relates to a blood vessel centerline extraction method and device, a computer device, a storage medium and a computer program product. BACKGROUND

[0002] In the diagnosis of cerebral vascular diseases, it is usually necessary to identify the main cerebral blood vessels in the image obtained by magnetic resonance, and then detect the lesion area of the cerebral blood vessels based on the identified cerebral blood vessels to obtain a diagnosis result. For a black blood image of a cerebral blood vessel, when identifying the cerebral blood vessel in the black blood image, it is usually necessary to first determine the centerline of the cerebral blood vessel in the black blood image, and then extract the cerebral blood vessel in the black blood image based on the centerline of the cerebral blood vessel.

[0003] In the conventional technology, the process of automatically identifying the blood vessel centerline of the black blood image is as follows: manually or automatically obtaining the blood vessel centerline in the bright blood image corresponding to the black blood image, then registering the blood vessel centerline in the bright blood image to the black blood image according to a registration algorithm, and then fine-tuning the registered blood vessel centerline to obtain the blood vessel centerline of the black blood image.

[0004] However, in the existing method of obtaining the blood vessel centerline of the black blood image, when the quality of the bright blood image is not high or the registration algorithm is not accurate, the accuracy of the obtained blood vessel centerline of the black blood image is poor. SUMMARY

[0005] Therefore, it is necessary to provide a blood vessel centerline extraction method, device, computer device, computer readable storage medium and computer program product capable of extracting the blood vessel centerline only by using the black blood image, thereby improving the extraction accuracy of the blood vessel centerline.

[0006] In a first aspect, the present application provides a blood vessel centerline extraction method. The method comprises:

[0007] obtaining an initial black blood image of a to-be-detected object;

[0008] inputting the initial black blood image into a preset first segmentation model to obtain a first blood vessel segmentation image; wherein the first blood vessel segmentation image comprises at least one blood vessel segmentation;

[0009] extracting the centerline of each blood vessel segmentation in the first blood vessel segmentation image to obtain a blood vessel centerline image corresponding to the initial black blood image.

[0010] In one embodiment, extracting the centerline of each blood vessel segmentation in the first blood vessel segmentation image to obtain a blood vessel centerline image corresponding to the initial black blood image comprises:

[0011] For each blood vessel segment, a center line of the blood vessel segment is extracted;

[0012] Based on the initial black blood image and a preset blood vessel connection strategy, the center lines of each blood vessel segment are connected to obtain a blood vessel center line image corresponding to the initial black blood image.

[0013] In one embodiment, the extraction of the center line of each blood vessel segment includes:

[0014] For the blood vessel segment, a first end point and a second end point of the blood vessel segment are determined;

[0015] Based on the first blood vessel segment image, the first end point and the second end point of the blood vessel segment are connected to obtain the center line of the blood vessel segment.

[0016] In one embodiment, the determination of the first end point and the second end point of the blood vessel segment includes:

[0017] The blood vessel segment includes a plurality of sub-blood vessel segments;

[0018] The first end point and the second end point of each sub-blood vessel segment are determined;

[0019] Correspondingly, based on the first blood vessel segment image, the first end point and the second end point of the blood vessel segment are connected to obtain the center line of the blood vessel segment, including:

[0020] For each sub-blood vessel segment, based on the first blood vessel segment image, the first end point and the second end point of the sub-blood vessel segment are connected to obtain the center line of the sub-blood vessel segment;

[0021] Based on the initial black blood image, the center lines of the sub-blood vessel segments are connected to obtain the center line of the blood vessel segment.

[0022] In one embodiment, the method further includes:

[0023] Based on the blood vessel center line image and the first blood vessel segment image, at least one blood vessel bifurcation point is determined;

[0024] Based on each blood vessel bifurcation point, each blood vessel center line in the blood vessel center line image is segmented to obtain a blood vessel center line segment image.

[0025] In one embodiment, based on the blood vessel center line image and the first blood vessel segment image, at least one blood vessel bifurcation point is determined, including:

[0026] The position of a first bifurcation point in the first blood vessel segment image and the position of a second bifurcation point in the blood vessel center line image are determined;

[0027] It is judged whether the position of the second bifurcation point is within a preset range of the position of the first bifurcation point;

[0028] In a case where the position of the second bifurcation point is within the preset range of the position of the first bifurcation point, the second bifurcation point is determined as the blood vessel bifurcation point.

[0029] In one of the embodiments, the method further comprises: in a case where the position of the second bifurcation point is not within the preset range of the position of the first bifurcation point, returning to re-perform the steps of connecting the center lines of each blood vessel segment based on the initial black-blood image and the blood vessel connection strategy, obtaining an adjusted blood vessel center line image, and determining the position of the second bifurcation point in the adjusted blood vessel center line image until the position of the second bifurcation point is within the preset range of the position of the first bifurcation point.

[0030] In one of the embodiments, the method further comprises:

[0031] Based on the initial black-blood image, obtaining a cross-sectional image corresponding to each point on each blood vessel center line in the blood vessel center line image;

[0032] Processing each cross-sectional image to obtain a target blood vessel image corresponding to the blood vessel center line image.

[0033] In one of the embodiments, processing each cross-sectional image to obtain a target blood vessel image corresponding to the blood vessel center line image comprises:

[0034] Inputting each cross-sectional image into a second segmentation model to obtain a segmentation result image corresponding to each cross-sectional image;

[0035] Based on the segmentation result image corresponding to each cross-sectional image, determining whether the blood vessel structure in each cross-sectional image satisfies a preset blood vessel structure rule;

[0036] In a case where the blood vessel structure in the cross-sectional image does not satisfy the preset blood vessel structure rule, removing the cross-sectional image that does not satisfy the blood vessel structure rule, and obtaining a target blood vessel image according to the remaining cross-sectional images that satisfy the blood vessel structure rule.

[0037] In one of the embodiments, the method further comprises:

[0038] Based on each blood vessel bifurcation point, performing segmentation processing on each blood vessel in the target blood vessel image to obtain a target blood vessel segmentation image corresponding to the target blood vessel image.

[0039] In one of the embodiments, the method further comprises:

[0040] Based on the blood vessel center line image, detecting whether there is a target tissue in the blood vessel in the initial black-blood image;

[0041] In a case where the target tissue exists in the blood vessels in the initial black-blood image, the target tissue is segmented based on the initial black-blood image to obtain a segmentation result of the target tissue.

[0042] In a second aspect, the present application further provides a blood vessel centerline extraction device. The device comprises:

[0043] A first acquisition module is configured to acquire an initial black-blood image of a to-be-tested object.

[0044] A second acquisition module is configured to input the initial black-blood image into a preset first segmentation model to obtain a first blood vessel segmentation image; the first blood vessel segmentation image comprises at least one blood vessel segmentation.

[0045] A third acquisition module is configured to extract a centerline of each blood vessel segmentation in the first blood vessel segmentation image to obtain a blood vessel centerline image corresponding to the initial black-blood image.

[0046] In a third aspect, the present application further provides a computer device. The computer device comprises a memory and a processor; the memory stores a computer program; and the processor implements the following steps when executing the computer program:

[0047] acquiring an initial black-blood image of a to-be-tested object;

[0048] inputting the initial black-blood image into a preset first segmentation model to obtain a first blood vessel segmentation image; the first blood vessel segmentation image comprises at least one blood vessel segmentation;

[0049] extracting a centerline of each blood vessel segmentation in the first blood vessel segmentation image to obtain a blood vessel centerline image corresponding to the initial black-blood image.

[0050] In a fourth aspect, the present application further provides a computer readable storage medium. The computer readable storage medium stores a computer program; and the computer program is executed by a processor to implement the following steps:

[0051] acquiring an initial black-blood image of a to-be-tested object;

[0052] inputting the initial black-blood image into a preset first segmentation model to obtain a first blood vessel segmentation image; the first blood vessel segmentation image comprises at least one blood vessel segmentation;

[0053] extracting a centerline of each blood vessel segmentation in the first blood vessel segmentation image to obtain a blood vessel centerline image corresponding to the initial black-blood image.

[0054] In a fifth aspect, the present application further provides a computer program product. The computer program product comprises a computer program; and the computer program is executed by a processor to implement the following steps:

[0055] obtaining an initial black-blood image of a to-be-tested object;

[0056] inputting the initial black-blood image into a preset first segmentation model to obtain a first blood vessel segmentation image, wherein the first blood vessel segmentation image comprises at least one blood vessel segmentation;

[0057] extracting a center line of each blood vessel segmentation in the first blood vessel segmentation image to obtain a blood vessel center line image corresponding to the initial black-blood image.

[0058] The blood vessel center line extraction method, device, computer device, storage medium and computer program product, the computer device obtains an initial black-blood image of a to-be-tested object, inputs the initial black-blood image into a preset first segmentation model to obtain a first blood vessel segmentation image comprising at least one blood vessel segmentation, then extracts a center line of each blood vessel segmentation in the first blood vessel segmentation image to obtain a blood vessel center line image corresponding to the initial black-blood image; an automatic extraction method of directly obtaining a blood vessel center line from a black-blood image is realized, without the need to use a bright-blood image corresponding to the black-blood image, or the need to additionally obtain a bright-blood image, and of course, there is no need to consider the quality problem of the bright-blood image and the accuracy problem of registration; after obtaining the initial black-blood image, the blood vessel center line image corresponding to the initial black-blood image can be directly obtained through the identification and processing of the initial black-blood image in the method, which is simple and fast, saves time and effort, the accuracy of the obtained blood vessel center line image is high, and the extraction efficiency is high. BRIEF DESCRIPTION OF DRAWINGS

[0059] Figure 1 A flowchart of the blood vessel center line extraction method in one embodiment is shown;

[0060] Figure 2 A structural diagram of the first blood vessel segmentation image in one embodiment is shown;

[0061] Figure 3 A structural diagram of the blood vessel center line image in one embodiment is shown;

[0062] Figure 4 A flowchart of the blood vessel center line extraction method in another embodiment is shown;

[0063] Figure 5 A flowchart of the blood vessel center line extraction method in another embodiment is shown;

[0064] Figure 6 A flowchart of the blood vessel center line extraction method in another embodiment is shown;

[0065] Figure 7 A center line extraction process diagram of a blood vessel segmentation in one embodiment is shown;

[0066] Figure 8 Flowchart of the method for extracting the blood vessel centerline in another embodiment;

[0067] Figure 9 Flowchart of the method for extracting the blood vessel centerline in another embodiment;

[0068] Figure 10 Flowchart of the method for extracting the blood vessel centerline in another embodiment;

[0069] Figure 11 Flowchart of the method for extracting the blood vessel centerline in another embodiment;

[0070] Figure 12 Complete schematic diagram of the variation process of the method for extracting the blood vessel centerline in one embodiment;

[0071] Figure 13 Structural block diagram of the device for extracting the blood vessel centerline in one embodiment;

[0072] Figure 14 Internal structural diagram of the computer device in one embodiment. DETAILED DESCRIPTION

[0073] In order to make the purposes, technical solutions and advantages of the present application clearer, the present application is further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0074] The method for extracting the blood vessel centerline provided by the embodiments of the present application can be applied in a computer device, which can be a terminal or a server. The terminal can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, scanning devices and processing devices connected with the scanning devices, etc. The server can be implemented by an independent server or a server cluster composed of multiple servers.

[0075] In one embodiment, as shown in Figure 1 A method for extracting the blood vessel centerline is provided. Taking the case that the method is applied in the above computer device as an example, the method comprises the following steps:

[0076] Step 101: An initial black-blood image of a to-be-tested object is acquired.

[0077] Optionally, the initial black blood image can be acquired from the acquisition device, can be acquired from the server, can be a historical initial black blood image acquired locally from the device, etc. The embodiment does not limit the acquisition mode of the initial black blood image of the to-be-tested object. In addition, the initial black blood image can be a black blood sequence of different forms, including but not limited to a T1 enhanced image, a T1 image, a T2 image, a proton density image, etc. The embodiment does not limit the form of the initial black blood image.

[0078] In step 102, the initial black blood image is input into a preset first segmentation model to obtain a first blood vessel segmentation image.

[0079] The first blood vessel segmentation image includes at least one blood vessel segmentation. Each blood vessel segmentation can be a part of blood vessels distributed in different tissues or organs, or can be different types of blood vessels in the same tissue or organ, such as arterial blood vessels, venous blood vessels, capillary blood vessels, etc. Optionally, in the first blood vessel segmentation image, different blood vessel segmentations can be marked by different line types, such as color line marking, thickness line marking, shape line marking, etc. Different blood vessel segmentations can also be distinguished by using identification information, such as text identification, digital identification, symbol identification, etc. Of course, a combination of multiple ways can also be used to distinguish different blood vessel segmentations. The embodiment does not limit the marking mode of the blood vessel segmentation.

[0080] Optionally, the first segmentation model can be a segmentation model obtained by training a first initial segmentation network using a plurality of black blood sample images and a blood vessel segmentation label image corresponding to each black blood sample image. The first initial segmentation network can be any type of existing deep learning network, or a combination of multiple different types of networks, etc. The embodiment does not limit this.

[0081] The first segmentation model can be used to perform blood vessel segmentation on the initial black blood image to obtain a first blood vessel segmentation image corresponding to the initial black blood image. Optionally, the number of blood vessel segmentations in the first blood vessel segmentation image can be the same as the number of blood vessel segmentations in the initial black blood image, and the effect of the blood vessel segmentation is better. For example, as shown in FIG. 2, the first blood vessel segmentation image after blood vessel segmentation of the initial black blood image is shown. Figure 2

[0082] In step 103, a center line of each blood vessel segmentation in the first blood vessel segmentation image is extracted to obtain a blood vessel center line image corresponding to the initial black blood image.

[0083] ​Optionally, after obtaining the first blood vessel segmentation image corresponding to the initial black blood image and comprising at least one blood vessel segmentation, a center line of each blood vessel segmentation in the first blood vessel segmentation image can be extracted to obtain a center line corresponding to each blood vessel segmentation, that is, a blood vessel center line image corresponding to the initial black blood image can be obtained, as shown in Figure 3

[0084] Optionally, a preset center line extraction algorithm can be used to extract the center line of each blood vessel segmentation in the first blood vessel segmentation image, and an online learning algorithm or the like can also be used to extract the center line of each blood vessel segmentation in the first blood vessel segmentation image. The center line extraction algorithm can be a model-based center line extraction algorithm or a non-model-based center line extraction algorithm, and the extraction method of the blood vessel center line and the principle and method of the center line extraction algorithm are not limited in this embodiment.

[0085] In the above blood vessel center line extraction method, the computer device obtains an initial black blood image of the object to be measured, inputs the initial black blood image into a preset first segmentation model to obtain a first blood vessel segmentation image comprising at least one blood vessel segmentation, and then extracts the center line of each blood vessel segmentation in the first blood vessel segmentation image to obtain a blood vessel center line image corresponding to the initial black blood image. This method realizes automatic extraction of the blood vessel center line directly from the black blood image without the need for a bright blood image corresponding to the black blood image or the need for additional acquisition of the bright blood image, and thus there is no need to consider the quality of the bright blood image and the accuracy of registration. After obtaining the initial black blood image, the method in this embodiment can directly obtain the blood vessel center line image corresponding to the initial black blood image through identification and processing of the initial black blood image, which is simple and fast, saves time and effort, has high accuracy of the obtained blood vessel center line image, and has high extraction efficiency.

[0086] Figure 4 This embodiment relates to one of the optional implementation processes of the computer device extracting the center line of each blood vessel segmentation in the first blood vessel segmentation image to obtain a blood vessel center line image corresponding to the initial black blood image. As shown in Figure 4

[0087] Step 401: For each blood vessel segmentation, the center line of each blood vessel segmentation is extracted.

[0088] For the implementation method of extracting the center line of the blood vessel segmentation, reference can be made to the related content in step 103, which will not be repeated here. Optionally, different blood vessel segmentations can be marked by using different line colors in this embodiment.

[0089] ​​At step 402, based on the initial black blood image and a preset blood vessel connection strategy, the center lines of each blood vessel segment are connected to obtain a blood vessel center line image corresponding to the initial black blood image.

[0090] The preset blood vessel connection strategy can include connection rules of multiple blood vessels, and each connection rule of a blood vessel can include connection rules of multiple blood vessel segments in different tissues or organs. For example, for a complete arterial blood vessel, it can shuttle between multiple different tissues or organs. Different line colors can be used to distinguish the multiple blood vessel segments of the arterial blood vessel in different tissues or organs, and the connection order of the multiple blood vessel segments corresponding to the arterial blood vessel can be preset.

[0091] Optionally, after extracting the center line of each blood vessel segment, the computer device can connect the center lines of blood vessel segments having a correlation relationship based on the initial black blood image and the blood vessel connection strategy to obtain a blood vessel center line image corresponding to the initial black blood image, wherein the blood vessel center line image includes at least one complete blood vessel.

[0092] Optionally, the computer device can determine two blood vessel segments having a correlation relationship in a first blood vessel to be connected according to the blood vessel connection order of each blood vessel in the blood vessel connection strategy based on the blood vessel connection strategy. Then, the center lines of the two blood vessel segments to be connected can be connected by using an optimal path algorithm based on the initial black blood image. This process is repeated until the center lines of all blood vessel segments in the first blood vessel are connected to obtain a first blood vessel center line corresponding to the first blood vessel. Similarly, after the center line of the first blood vessel is connected, the center line of the second blood vessel can be connected. This process is repeated until the center lines of all blood vessel segments having a correlation relationship are connected, and the blood vessel center line image is obtained.

[0093] In this embodiment, for each blood vessel segment, the computer device extracts the center line of each blood vessel segment, and connects the center lines of each blood vessel segment based on the initial black blood image and the preset blood vessel connection strategy to obtain a blood vessel center line image corresponding to the initial black blood image. This can improve the accuracy of blood vessel center line extraction and improve the efficiency of blood vessel center line extraction.

[0094] Figure 5 This embodiment relates to one of the optional implementation processes of the computer device extracting the center line of each blood vessel segment. As shown in the flowchart of the blood vessel center line extraction method in another embodiment, Figure 5 The above step 401 includes:

[0095] Step 501, for a blood vessel segment, determining a first end point and a second end point of the blood vessel segment.

[0096] The first end point of the blood vessel segment can be a center point of a head end of the blood vessel segment, and the second end point of the blood vessel segment can be a center point of a tail end of the blood vessel segment.

[0097] Step 502, connecting the first end point and the second end point of the blood vessel segment based on the first blood vessel segment image to obtain a center line of the blood vessel segment.

[0098] Optionally, when determining the center line of the blood vessel segment in the first blood vessel segment image, after the first end point and the second end point of the blood vessel segment are determined, the first end point and the second end point of the blood vessel segment can be connected based on the segmented blood vessel in the first blood vessel segment image to form the center line of the blood vessel segment; optionally, based on the segmented blood vessel in the first blood vessel segment image, a blood vessel thinning algorithm can be used to obtain center points at a plurality of positions of the segmented blood vessel, and the center points at the plurality of positions and the first end point and the second end point of the blood vessel segment are connected to obtain the center line of the blood vessel segment; or based on the segmented blood vessel in the first blood vessel segment image, an optimal path algorithm can be used to connect the first end point and the second end point of the blood vessel segment to obtain the center line of the blood vessel segment; it should be noted that the specific implementation manner of connecting the first end point and the second end point of the blood vessel segment to form the center line of the blood vessel segment is not limited in the embodiment, and in actual application, any existing center line determination method can be used to realize.

[0099] In the embodiment, for a blood vessel segment, the computer device determines a first end point and a second end point of the blood vessel segment, and connects the first end point and the second end point of the blood vessel segment based on a first blood vessel segment image to obtain a center line of the blood vessel segment, the accuracy of the obtained center line of the blood vessel segment is high, the implementation process is simple, and the extraction efficiency of the center line is high.

[0100] In an optional embodiment of the present application, due to the influence of some objective factors, different blood vessel segments in the initial black blood image of the to-be-tested object can have the problems of occlusion and poor development effect, which can cause the blood vessel segments in the first blood vessel segment image corresponding to the initial black blood image output by the first segmentation model to be broken, that is, for the same blood vessel segment, there can be multiple sub-blood vessel segments (for example, multiple blood vessel segments of the same color can appear in the first blood vessel segment image, and the multiple blood vessel segments of the same color are part of the blood vessel in the same tissue or organ); in this case, when determining the center line of the blood vessel segment, the center lines of the multiple sub-blood vessel segments corresponding to the blood vessel segment can be determined respectively, and then the center lines of the sub-blood vessel segments are connected to obtain the center line of the blood vessel segment.

[0101] Figure 6 For another embodiment of the flowchart of the method for extracting the centerline of the blood vessel. The embodiment relates to one of the optional implementation processes of the computer device for extracting the centerline of each blood vessel segment when the blood vessel segmentation includes multiple sub-blood vessel segments; as shown in the figure, Figure 6 Based on the above embodiment, the step 501 includes:

[0102] Step 601, determining the first end point and the second end point of each sub-blood vessel segment.

[0103] The first end point of the sub-blood vessel segment can be the head center point of the sub-blood vessel segment, and the second end point of the sub-blood vessel segment can be the tail center point of the sub-blood vessel segment.

[0104] Correspondingly, the step 502 includes:

[0105] Step 602, for each sub-blood vessel segment, connecting the first end point and the second end point of the sub-blood vessel segment based on the first blood vessel segment image to obtain the centerline of the sub-blood vessel segment.

[0106] Here, the way of determining the centerline of the sub-blood vessel segment can refer to the implementation way of determining the centerline of the blood vessel segment in the step 502, which will not be repeated here.

[0107] Step 603, connecting the centerlines of the sub-blood vessel segments based on the initial black blood image to obtain the centerline of the blood vessel segment.

[0108] Optionally, after the centerlines of the multiple sub-blood vessel segments of a blood vessel segment are determined, the connection order of the centerlines of the sub-blood vessel segments can be determined based on the initial black blood image, and then the centerlines of the adjacent two sub-blood vessel segments can be connected according to the connection order to obtain the centerline of the blood vessel segment; optionally, when the centerlines of the adjacent two sub-blood vessel segments are connected, the optimal path algorithm can be used for the gap between the centerlines of the two sub-blood vessel segments, and the initial black blood image is used to generate the part of the centerline between the centerlines of the two sub-blood vessel segments to connect the centerlines of the two sub-blood vessel segments; of course, other connection methods or connection algorithms can also be used to connect the centerlines of the adjacent two sub-blood vessel segments, and the present embodiment does not make any limitation in this regard.

[0109] In the embodiment, in the case that the blood vessel segmentation includes a plurality of sub-blood vessel segmentations, the first end point and the second end point of each sub-blood vessel segmentation can be determined, and for each sub-blood vessel segmentation, the first end point and the second end point of the sub-blood vessel segmentation are connected based on the first blood vessel segmentation image to obtain a center line of the sub-blood vessel segmentation; then, the center lines of the sub-blood vessel segmentations are connected based on the initial black blood image to obtain the center line of the blood vessel segmentation; the obtained center line of the blood vessel segmentation is accurate and complete, and the accuracy and completeness of the center line extraction are improved.

[0110] In another optional embodiment of the present application, in the case that the blood vessel segmentation includes a plurality of sub-blood vessel segmentations, the two longest sub-blood vessel segmentations can also be determined from the plurality of sub-blood vessel segmentations corresponding to the blood vessel segmentation, and the center line of the blood vessel segmentation is obtained based on the two longest sub-blood vessel segmentations; optionally, for a blood vessel segmentation (such as Figure 7 (a) is a structural diagram of the blood vessel segmentation), the longest sub-blood vessel segmentation and the second longest sub-blood vessel segmentation can be determined from the plurality of sub-blood vessel segmentations of the blood vessel segmentation, and the first end point of the longest sub-blood vessel segmentation and the first end point of the second longest sub-blood vessel segmentation are determined as the first end point of the blood vessel segmentation, and the second end point of the longest sub-blood vessel segmentation and the second end point of the second longest sub-blood vessel segmentation are determined as the second end point of the blood vessel segmentation; that is, the first end point and the second end point of the longest sub-blood vessel segmentation are determined, and the first end point and the second end point of the second longest sub-blood vessel segmentation are determined; then, for the longest sub-blood vessel segmentation, the first end point and the second end point of the longest sub-blood vessel segmentation are connected to obtain a first center line of the longest sub-blood vessel segmentation, and for the second longest sub-blood vessel segmentation, the first end point and the second end point of the second longest sub-blood vessel segmentation are connected to obtain a second center line of the second longest sub-blood vessel segmentation (such as Figure 7 (b) is a structural diagram of the center line of the longest sub-blood vessel segmentation and the center line of the second longest sub-blood vessel segmentation in the blood vessel segmentation); then, the first center line of the longest sub-blood vessel segmentation and the second center line of the second longest sub-blood vessel segmentation can be connected to represent the center line of the blood vessel segmentation (such as Figure 7 (c) is a structural diagram of the center line of the blood vessel segmentation).

[0111] Optionally, when connecting the first end point and the second end point of the longest sub-blood vessel segment, the first end point of the longest sub-blood vessel segment and the second end point of the longest sub-blood vessel segment can be connected based on the first blood vessel segment image by using the optimal path algorithm to obtain the center line of the longest sub-blood vessel segment; similarly, when connecting the first end point and the second end point of the second longest sub-blood vessel segment, the first end point of the second longest sub-blood vessel segment and the second end point of the second longest sub-blood vessel segment can be connected based on the first blood vessel segment image by using the optimal path algorithm to obtain the center line of the second longest sub-blood vessel segment; then, the center line of the longest sub-blood vessel segment and the center line of the second longest sub-blood vessel segment can be connected based on the initial black blood image by using the optimal path algorithm to obtain the center line of the blood vessel segment.

[0112] In the embodiment, when the blood vessel segment includes a plurality of sub-blood vessel segments, the center line of the blood vessel segment can be determined based on the longest sub-blood vessel segment and the second longest sub-blood vessel segment in the plurality of sub-blood vessel segments corresponding to the blood vessel segment, that is, the blood vessel segment is represented by the two longest sub-blood vessel segments in the blood vessel segment, so that the extraction rate of the center line of the blood vessel segment can be improved and the accuracy of the center line of the blood vessel segment can be ensured.

[0113] Figure 8 The flowchart of the blood vessel center line extraction method in another embodiment is shown. The embodiment relates to one of the optional implementation processes of the computer device for further determining the blood vessel center line segment image based on the blood vessel center line image. Figure 8 As shown in the embodiment, the method further includes:

[0114] In step 801, at least one blood vessel bifurcation point is determined based on the blood vessel center line image and the first blood vessel segment image.

[0115] In the above embodiments, the center line of each blood vessel segment is obtained, and the blood vessel segments belonging to the same blood vessel and having an association relationship are connected to obtain a complete blood vessel center line including a plurality of blood vessels, i.e., the blood vessel center line image; after the blood vessel center line image is obtained, each complete blood vessel in the blood vessel center line can be segmented to obtain a blood vessel center line segmented image corresponding to the first blood vessel segmented image. Each blood vessel segment center line in the blood vessel center line segmented image corresponds to each blood vessel segment in the first blood vessel segmented image one by one, but compared with the center line of each blood vessel segment obtained based on the initial black blood image and the first blood vessel segmented image, the center line of each blood vessel segment obtained based on the blood vessel center line image and the first blood vessel segmented image is more complete, and the connectivity between the center lines of two blood vessel segments connected with each other is also better, which can accurately distinguish the distribution of the blood vessel segments of each blood vessel in different tissues or organs while ensuring the integrity of each blood vessel.

[0116] Optionally, before the blood vessel center line image is segmented, a plurality of bifurcation points need to be determined first, the plurality of blood vessel bifurcation points being the connection points between the blood vessel segments, so that the computer device can segment the plurality of blood vessels in the blood vessel center line image according to each bifurcation point; when the bifurcation points are determined, a plurality of bifurcation points in the first blood vessel segmented image and a plurality of bifurcation points in the blood vessel center line image can be determined, and then the plurality of blood vessel bifurcation points for segmenting the blood vessel center line image can be obtained by comparing the plurality of bifurcation points in the first blood vessel segmented image and the plurality of bifurcation points in the blood vessel center line image.

[0117] Optionally, the position of a first bifurcation point in the first blood vessel segmentation image and the position of a second bifurcation point in the blood vessel centerline image can be determined, wherein the first bifurcation point and the second bifurcation point are bifurcation points between the same blood vessels in the first blood vessel segmentation image and the blood vessel centerline image; then, it can be determined whether the position of the second bifurcation point is within a preset range of the position of the first bifurcation point; in a case where it is determined that the position of the second bifurcation point is within the preset range of the position of the first bifurcation point, the second bifurcation point can be determined as a blood vessel bifurcation point, that is, in this case, it is indicated that the cross connections between several blood vessels in the first blood vessel segmentation image are basically consistent with the cross connections between the several blood vessels in the blood vessel centerline, and it is also indicated that the matching degree of the centerlines of the blood vessels in the blood vessel centerline image with the actual blood vessels in the initial black-blood image is relatively high, and the obtained blood vessel centerline is more accurate, so in this case, the second bifurcation point determined from the blood vessel centerline image can be directly used as the final blood vessel bifurcation point for segmenting the blood vessel centerline image.

[0118] Optionally, in a case where the position of the second bifurcation point is not within the preset range of the position of the first bifurcation point, it is indicated that there is a difference between the centerline of the complete blood vessel obtained after connecting the centerlines of the segmented blood vessels having the association relationship and the actual blood vessel in the initial black-blood image; at this time, the process can return to re-perform the connecting of the centerlines of each blood vessel segmentation based on the initial black-blood image and the blood vessel connection strategy to obtain an adjusted blood vessel centerline image, and then the process can continue to perform the step of determining the position of the second bifurcation point in the adjusted blood vessel centerline image and determining whether the position of the second bifurcation point in the adjusted blood vessel centerline image is within the preset range of the position of the first bifurcation point in the first blood vessel segmentation image; if yes, the second bifurcation point in the adjusted blood vessel centerline image can be used as the final blood vessel bifurcation point for segmenting the blood vessel centerline image; if no, the process can continue to perform the connecting of the centerlines of each blood vessel segmentation based on the initial black-blood image and the blood vessel connection strategy to obtain an adjusted blood vessel centerline image and the subsequent steps until the position of the second bifurcation point is within the preset range of the position of the first bifurcation point.

[0119] In step 802, each blood vessel centerline in the blood vessel centerline image is segmented based on each blood vessel bifurcation point to obtain a blood vessel centerline segmentation image.

[0120] Optionally, after the segmentation processing, the same segmentation markers as those of each blood vessel segmentation in the first blood vessel segmentation image can be used to mark each blood vessel centerline segmentation after the segmentation processing, and thus the obtained blood vessel centerline segmentation image and the first blood vessel segmentation image are one-to-one corresponding.

[0121] In this embodiment, after the computer device determines the vessel centerline image, the computer device can further determine at least one vessel bifurcation point based on the vessel centerline image and the first vessel segmentation image. Then, the computer device can segment each vessel centerline in the vessel centerline image based on each vessel bifurcation point to obtain a vessel centerline segmentation image, that is, to obtain a vessel centerline segmentation image corresponding to the first vessel segmentation image one by one, so that the user can more intuitively master the vessel distribution of different vessels in different tissues or organs and improve the user experience.

[0122] In an optional embodiment of the present application, before the computer device determines at least one vessel bifurcation point based on the vessel centerline image and the first vessel segmentation image, the computer device can also extend each vessel centerline in the vessel centerline image based on the initial black-blood image to obtain an extended vessel centerline image. Since the first vessel segmentation image obtained after the first segmentation model is used to segment the vessels in the initial black-blood image may have missing edge vessels, or the connection of the centerline of the two longest vessels in the above-mentioned vessel segmentation may result in an incomplete vessel centerline, in this embodiment, each vessel in the vessel centerline image is extended at both ends, and each vessel centerline after the extension processing is more complete and can better reflect the overall shape of the actual vessel in the initial black-blood image.

[0123] Optionally, when the vessel centerline image is extended, the two ends of each vessel centerline can be extended by a preset length based on the initial black-blood image, or the two ends of each vessel centerline can be extended by a preset length along the blood flow direction of the two ends of each vessel centerline, and the like. The present embodiment does not limit the implementation manner and the extension length of the extended vessel centerline.

[0124] Figure 9 The flowchart of the extraction method of the vessel centerline in another embodiment. The present embodiment relates to one of the optional implementation processes of the computer device for restoring the vessels and further determining the target vessel image based on the above-mentioned vessel centerline image. As shown in the figure, Figure 9 The above-mentioned method further includes the following steps based on the above-mentioned embodiment:

[0125] In step 901, based on the initial black-blood image, the computer device obtains the cross-sectional image corresponding to each point on each vessel centerline in the vessel centerline image.

[0126] Optionally, for each blood vessel centerline in the blood vessel centerline image, a plurality of points on the blood vessel centerline can be determined in advance, and the distance between each point should be less than or equal to a preset distance threshold, for example, the distance between each point can be less than or equal to 0.7 mm; optionally, an interpolation algorithm can be used to interpolate each blood vessel centerline to obtain a plurality of points corresponding to each blood vessel centerline, and the distance between any two points is less than or equal to the preset distance threshold; then, based on the initial black blood image, a cross-sectional image corresponding to the blood vessel position of each point can be obtained.

[0127] At step 902, each cross-sectional image is processed to obtain a target blood vessel image corresponding to the blood vessel centerline image.

[0128] Optionally, after obtaining the cross-sectional image corresponding to each point of the blood vessel centerline, the cross-sectional image corresponding to each point can be processed so that each cross-sectional image corresponding to each point satisfies a preset blood vessel structure rule, which can include but is not limited to a lumen profile not exceeding a tube wall profile, a lumen size, a tube wall size, a distance between the lumen and the tube wall, and the like; in the case where it is determined that the cross-sectional image corresponding to a certain point does not satisfy the blood vessel structure rule, the cross-sectional image corresponding to the point can be adjusted to obtain an adjusted cross-sectional image that satisfies the blood vessel structure rule; finally, based on the cross-sectional images corresponding to each point that satisfy the blood vessel structure rule, a target blood vessel image corresponding to the blood vessel centerline image can be generated; the cross-sectional images of adjacent two points can be filled in a filling manner to obtain the target blood vessel image.

[0129] In this embodiment, the computer device can obtain the cross-sectional image corresponding to each point on each blood vessel centerline in the blood vessel centerline image based on the initial black blood image, and process each cross-sectional image to obtain a target blood vessel image corresponding to the blood vessel centerline image; the target blood vessel image can reflect the morphology and distribution of each blood vessel in the initial black blood image, and can more intuitively show the user the distribution of each blood vessel of the to-be-tested object, thereby improving the user viewing experience and the visualization degree.

[0130] Figure 10 A flowchart of the blood vessel centerline extraction method in another embodiment is shown. This embodiment relates to one of the optional implementation processes of the computer device processing each cross-sectional image to obtain a target blood vessel image corresponding to the blood vessel centerline image; as shown in Figure 10 The above step 902 includes:

[0131] At step 1001, each cross-sectional image is input into a second segmentation model to obtain a segmentation result image corresponding to each cross-sectional image.

[0132] The segmentation result image corresponding to the cross-sectional image can be a labeled image with labeled information of a lumen contour and a tube wall contour of the blood vessel in the cross-sectional image.

[0133] The second segmentation model is a segmentation model obtained by training a second initial segmentation network according to the cross-sectional sample images of the plurality of blood vessels and the segmentation result labels corresponding to the cross-sectional sample images of each blood vessel. The second initial segmentation network can be any existing type of deep learning network, or a segmentation network combining a plurality of different types of networks, and the like, and the embodiment is not limited thereto. In addition, the second initial segmentation network can be the same or different from the first initial segmentation network.

[0134] At step 1002, whether the blood vessel structure in each cross-sectional image satisfies a preset blood vessel structure rule is determined based on the segmentation result image corresponding to each cross-sectional image.

[0135] At step 1003, in a case where the blood vessel structure in the cross-sectional image does not satisfy the preset blood vessel structure rule, the cross-sectional image that does not satisfy the blood vessel structure rule is removed, and a target blood vessel image is obtained based on the remaining cross-sectional images that satisfy the blood vessel structure rule.

[0136] Optionally, the remaining cross-sectional images that satisfy the blood vessel structure rule can be subjected to padding processing to obtain the target blood vessel image. Alternatively, based on the remaining cross-sectional images that satisfy the blood vessel structure rule, first padding processing can be performed on two adjacent cross-sectional images to generate an intermediate blood vessel image. In the intermediate blood vessel image, there is a blood vessel gap at the position where the cross-sectional image that does not satisfy the blood vessel structure rule is removed. The intermediate blood vessel image can be further subjected to second padding processing to obtain the target blood vessel image. The first padding processing and the second padding processing can adopt different padding processing methods in the prior art.

[0137] Optionally, before the second padding processing is performed on the intermediate blood vessel image to obtain the target blood vessel image, an interpolation algorithm can be used to determine a new blood vessel section for the missing blood vessel section (i.e., the cross-sectional image that does not satisfy the blood vessel structure rule is removed) in the intermediate blood vessel image. Then, the new blood vessel section can be interpolated into the missing position in the intermediate blood vessel image to obtain an interpolated intermediate blood vessel image. At this point, the second padding processing can be performed on the interpolated intermediate blood vessel image to obtain the target blood vessel image.

[0138] Optionally, after the second filling processing on the interpolated intermediate blood vessel image, a post-processing operation can also be performed on the filled blood vessel image to obtain the target blood vessel image; optionally, the post-processing operation can include but is not limited to removing non-blood vessel points on the blood vessel surface, performing smoothing processing on the blood vessel surface, etc., to improve the smoothness of the blood vessel surface.

[0139] In this embodiment, the computer device inputs each cross-sectional image into the second segmentation model respectively to obtain a segmentation result image corresponding to each cross-sectional image, and judges whether the blood vessel structure in each cross-sectional image meets the preset blood vessel structure rule based on the segmentation result image corresponding to each cross-sectional image. In the case where the blood vessel structure in the cross-sectional image does not meet the preset blood vessel structure rule, the cross-sectional image that does not meet the blood vessel structure rule is removed, and the target blood vessel image is obtained according to the remaining cross-sectional images that meet the blood vessel structure rule. The cross-sectional image that does not meet the blood vessel structure rule is removed to generate the target blood vessel image from the remaining cross-sectional images that meet the blood vessel structure rule. The blood vessels in the obtained target blood vessel image are more consistent with the standard blood vessels, the obtained target blood vessel image is more accurate, and the accuracy of the target blood vessel image is improved.

[0140] In an optional embodiment of the present application, based on the above-obtained multiple blood vessel bifurcation points and the above target blood vessel image, the computer device can further perform segmentation processing on each blood vessel in the target blood vessel image based on the blood vessel bifurcation points to obtain a target blood vessel segmentation image corresponding to the target blood vessel image. Compared with the first blood vessel segmentation image, the blood vessel morphology of each blood vessel segment in the target blood vessel segmentation image is more matched with the standard blood vessel structure, the blood vessel surface is smoother, the connectivity between each blood vessel segment with a correlation relationship is better, and the blood vessel extraction effect is better.

[0141] Figure 11 The flowchart of the blood vessel centerline extraction method in another embodiment. The present embodiment relates to one of the optional implementation processes of the computer device for detecting the target tissue in the initial black blood image based on the blood vessel centerline image; as shown in the figure, Figure 11 The above method further includes:

[0142] Step 1101, based on the blood vessel centerline image, detecting whether the target tissue exists in the blood vessel in the initial black blood image.

[0143] Optionally, in the first embodiment of the present application, after the computer device determines the blood vessel centerline image corresponding to the initial black-blood image according to the initial black-blood image, the computer device can further detect and locate the target tissue in the blood vessel of the to-be-tested object based on the blood vessel centerline image, for example, the computer device can perform plaque detection or stenosis detection on the blood vessel of the to-be-tested object based on the blood vessel centerline image.

[0144] Optionally, based on the blood vessel centerline image, the blood vessel in the initial black-blood image can be segmented, and the segmented blood vessel in the initial black-blood image can be detected and analyzed to determine whether the target tissue exists in the blood vessel; optionally, after the blood vessel in the initial black-blood image is segmented, the blood vessel can be analyzed layer by layer, and the cross-sectional image of the blood vessel corresponding to each layer can be obtained, then, the cross-sectional image of the blood vessel of each layer can be segmented to determine the lumen and the wall of the blood vessel, and then, the lumen and the wall of the segmented blood vessel can be analyzed to identify the stenosis position of the blood vessel, and the composition between the lumen and the wall of the identified stenosis position of the blood vessel can be identified, and whether the target tissue exists in the stenosis position can be determined according to the identification result. It should be noted that the identification of the target tissue in the blood vessel in the present embodiment can use the existing technology, and therefore, the specific implementation process of the target tissue identification will not be described here.

[0145] In step 1102, in the case that the target tissue exists in the blood vessel in the initial black-blood image, the target tissue is segmented based on the initial black-blood image to obtain a segmentation result of the target tissue.

[0146] Optionally, in the case that the target tissue exists in the blood vessel in the initial black-blood image, a third preset segmentation model can be used to segment the target tissue based on the initial black-blood image to obtain a segmentation result of the target tissue; the third segmentation model can be a segmentation model obtained by training a third initial segmentation network based on a plurality of black-blood sample images with target tissues and a target tissue label corresponding to each black-blood sample image, the third initial segmentation network can be based on any type of existing deep learning network, or a segmentation network combining a plurality of different types of networks, and the present embodiment does not limit the third initial segmentation network; in addition, the third initial segmentation network can be the same as or different from the first initial segmentation network or the second initial segmentation network.

[0147] In this embodiment, the computer device detects whether the target tissue exists in the blood vessels in the initial black blood image based on the blood vessel centerline image; and in the case that the target tissue exists in the blood vessels in the initial black blood image, the target tissue is segmented based on the initial black blood image to obtain the segmentation result of the target tissue; that is, the target tissue detection and segmentation process in this embodiment is the detection and segmentation of the target tissue based on the blood vessel centerline image obtained by detecting and recognizing only the black blood image, in other words, only the initial black blood image of the to-be-detected object needs to be obtained to realize the extraction of the blood vessel centerline and the detection of the target tissue in the entire detection process, and the entire process is efficient and real-time, and has high detection accuracy.

[0148] A complete embodiment of the extraction method of the blood vessel centerline will be provided below, which can include the following steps:

[0149] 1. An initial black blood image of a to-be-detected object is obtained, and the initial black blood image is input into a preset first segmentation model to obtain a first blood vessel segmentation image corresponding to the initial black blood image and including at least one blood vessel segment, as shown in (a); Figure 12

[0150] 2. The centerline of each blood vessel segment in the first blood vessel segmentation image is extracted, as shown in (b); Figure 12

[0151] 3. The centerline of each blood vessel segment is connected based on the initial black blood image and a preset blood vessel connection strategy to obtain a blood vessel centerline image corresponding to the initial black blood image, as shown in (c); Figure 12

[0152] 4. The centerline of each blood vessel segment is extended to obtain an extended blood vessel centerline image, as shown in (d); Figure 12

[0153] 5. At least one blood vessel bifurcation point is determined based on the blood vessel centerline image and the first blood vessel segmentation image, and each blood vessel centerline in the blood vessel centerline image is segmented based on each blood vessel bifurcation point to obtain a blood vessel centerline segmentation image, as shown in (e); Figure 12

[0154] 6. Each blood vessel in the blood vessel centerline image is inserted to obtain a plurality of points on each blood vessel centerline, as shown in (f); Figure 12 ​​​​​(f) is shown, then, based on the initial black blood image, cross-sectional images corresponding to each point on each vessel centerline in the vessel centerline image are obtained, and it is determined whether the vessel structure in the cross-sectional image corresponding to each point satisfies a preset vessel structure rule; cross-sectional images that do not satisfy the vessel structure rule are removed, and cross-sectional images that satisfy the vessel structure rule are retained, to obtain an intermediate vessel image, as shown in Figure 12 (g) is shown;

[0155] 7. For missing vessel sections in the intermediate vessel image, an interpolation algorithm is used to determine new vessel sections corresponding to missing position points, and the new vessel sections are interpolated into the missing positions in the intermediate vessel image to obtain an interpolated intermediate vessel image, then, the interpolated intermediate vessel image is filled to obtain a target vessel image, as shown in Figure 12 (h) is shown; the target vessel image is subjected to post-processing operations (for example, removing surface non-vessel points) to obtain a processed target vessel image, as shown in Figure 12 (i) is shown;

[0156] 8. Based on the above-described various vessel bifurcation points, the target vessel image is subjected to segmentation processing to obtain a segmented target vessel segmentation image, as shown in Figure 12 (j) is shown.

[0157] It should be noted that the various schematic diagrams in the above Figure 12 are only used for illustrative purposes to illustrate one example of the embodiment, and are not used to limit the specific forms of the various steps in the embodiment.

[0158] It should be understood that, although the various steps in the flowchart involved in the above-described embodiments are displayed in sequence according to the arrows, these steps are not necessarily executed in sequence according to the arrows. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other sequences. Moreover, at least a part of the steps in the flowchart involved in the above-described embodiments can include multiple steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence of these steps or stages is not necessarily sequential, but can be executed in rotation or alternation with at least a part of other steps or steps or stages in other steps.

[0159] Based on the same inventive concept, the embodiment of the present application also provides a blood vessel centerline extraction device for implementing the blood vessel centerline extraction method described above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more blood vessel centerline extraction device embodiments provided below can refer to the limitations of the blood vessel centerline extraction method described above, which will not be repeated here.

[0160] In one embodiment, as shown in Figure 13 A blood vessel centerline extraction device is provided, comprising: a first acquisition module 1301, a second acquisition module 1302, and a third acquisition module 1303, wherein:

[0161] The first acquisition module 1301 is configured to acquire an initial black-blood image of a to-be-tested object.

[0162] The second acquisition module 1302 is configured to input the initial black-blood image into a preset first segmentation model to obtain a first blood vessel segmentation image; wherein the first blood vessel segmentation image comprises at least one blood vessel segmentation.

[0163] The third acquisition module 1303 is configured to extract a centerline of each blood vessel segmentation in the first blood vessel segmentation image to obtain a blood vessel centerline image corresponding to the initial black-blood image.

[0164] In one embodiment, the third acquisition module 1303 comprises an extraction unit and an acquisition unit; wherein the extraction unit is configured to extract a centerline of each blood vessel segmentation for each blood vessel segmentation; and the acquisition unit is configured to connect the centerlines of each blood vessel segmentation based on the initial black-blood image and a preset blood vessel connection strategy to obtain a blood vessel centerline image corresponding to the initial black-blood image.

[0165] In one embodiment, the extraction unit is specifically configured to determine a first end point and a second end point of the blood vessel segmentation for the blood vessel segmentation; and connect the first end point and the second end point of the blood vessel segmentation based on the first blood vessel segmentation image to obtain a centerline of the blood vessel segmentation.

[0166] In one embodiment, the extraction unit is specifically configured to determine a first end point and a second end point of each sub-blood vessel segmentation in the case where the blood vessel segmentation comprises a plurality of sub-blood vessel segmentations; and connect the first end point and the second end point of each sub-blood vessel segmentation based on the first blood vessel segmentation image to obtain a centerline of the sub-blood vessel segmentation; and connect the centerlines of each sub-blood vessel segmentation based on the initial black-blood image to obtain a centerline of the blood vessel segmentation.

[0167] In one of the embodiments, the device further comprises a determining module and a fourth obtaining module; the determining module is configured to determine at least one blood vessel bifurcation point based on the blood vessel centerline image and the first blood vessel segmentation image; and the fourth obtaining module is configured to segment each blood vessel centerline in the blood vessel centerline image based on each blood vessel bifurcation point to obtain the blood vessel centerline segmentation image.

[0168] In one of the embodiments, the determining module comprises a first determining unit, a judging unit and a second determining unit; the first determining unit is configured to determine the position of the first bifurcation point in the first blood vessel segmentation image and the position of the second bifurcation point in the blood vessel centerline image; the judging unit is configured to judge whether the position of the second bifurcation point is within a preset range of the position of the first bifurcation point; and the second determining unit is configured to determine the second bifurcation point as a blood vessel bifurcation point in the case that the position of the second bifurcation point is within the preset range of the position of the first bifurcation point.

[0169] In one of the embodiments, the second determining unit is further configured to return to re-perform the steps of connecting the centerlines of each blood vessel segmentation based on the initial black-blood image and the blood vessel connection strategy to obtain the adjusted blood vessel centerline image, and determining the position of the second bifurcation point in the adjusted blood vessel centerline image until the position of the second bifurcation point is within the preset range of the position of the first bifurcation point in the case that the position of the second bifurcation point is not within the preset range of the position of the first bifurcation point.

[0170] In one of the embodiments, the device further comprises a fifth obtaining module and a sixth obtaining module; the fifth obtaining module is configured to obtain the cross-sectional image corresponding to each point on each blood vessel centerline in the blood vessel centerline image based on the initial black-blood image; and the sixth obtaining module is configured to process each cross-sectional image to obtain the target blood vessel image corresponding to the blood vessel centerline image.

[0171] In one of the embodiments, the sixth obtaining module comprises a first obtaining unit, a judging unit and a second obtaining unit; the first obtaining unit is configured to input each cross-sectional image into the second segmentation model to obtain the segmentation result image corresponding to each cross-sectional image; the judging unit is configured to judge whether the blood vessel structure in each cross-sectional image meets the preset blood vessel structure rule based on the segmentation result image corresponding to each cross-sectional image; and the second obtaining unit is configured to remove the cross-sectional image that does not meet the blood vessel structure rule and obtain the target blood vessel image based on the remaining cross-sectional images that meet the blood vessel structure rule in the case that the blood vessel structure in the cross-sectional image does not meet the preset blood vessel structure rule.

[0172] In one of the embodiments, the device further comprises a seventh acquisition module; the seventh acquisition module is configured to segment each blood vessel in the target blood vessel image based on each blood vessel bifurcation point, to obtain a target blood vessel segmentation image corresponding to the target blood vessel image.

[0173] In one of the embodiments, the device further comprises a detection module and an eighth acquisition module; the detection module is configured to detect whether the target tissue exists in the blood vessel in the initial black blood image based on the blood vessel centerline image; and the eighth acquisition module is configured to, in the case that the target tissue exists in the blood vessel in the initial black blood image, segment the target tissue based on the initial black blood image, to obtain a segmentation result of the target tissue.

[0174] The modules in the blood vessel centerline extraction device can be realized by software, hardware, or a combination thereof. The modules can be embedded in or independent of a processor in a computer device in hardware form, or stored in a memory in the computer device in software form, so as to be called and executed by the processor to perform the operations corresponding to the modules.

[0175] In one embodiment, a computer device is provided, which can be a terminal, and an internal structure diagram of the computer device can be as shown in FIG. Figure 14 The computer device comprises a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The communication interface of the computer device is configured to perform wired or wireless communication with an external terminal. The wireless communication can be achieved through WIFI, mobile cellular network, NFC (near field communication), or other technologies. The computer program is executed by the processor to implement a blood vessel centerline extraction method. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball, or touchpad arranged on the shell of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0176] Those skilled in the art can understand that Figure 14 The structure shown in FIG.

[0177] In one embodiment, a computer device is provided, comprising a memory and a processor, the memory storing a computer program, the processor implementing the steps of the method for extracting a blood vessel centerline in any of the above embodiments when executing the computer program.

[0178] In one embodiment, a computer readable storage medium is provided, storing a computer program, the computer program implementing the steps of the method for extracting a blood vessel centerline in any of the above embodiments when executed by a processor.

[0179] In one embodiment, a computer program product is provided, comprising a computer program, the computer program implementing the steps of the method for extracting a blood vessel centerline in any of the above embodiments when executed by a processor.

[0180] A person of ordinary skill in the art can understand that all or part of the processes in the above embodiments can be completed by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above embodiments. Any reference to a memory, database or other medium in the embodiments provided by the present application can include at least one of a non-volatile and volatile memory. The non-volatile memory can include a read-only memory (ROM), a magnetic tape, a floppy disk, a flash memory, an optical storage, a high-density embedded non-volatile memory, a resistive memory (ReRAM), a magnetoresistive memory (MRAM), a ferroelectric memory (FRAM), a phase change memory (PCM), a graphene memory, etc. The volatile memory can include a random access memory (RAM) or an external cache memory, etc. As an illustration but not limitation, the RAM can be in various forms, such as a static random access memory (SRAM) or a dynamic random access memory (DRAM), etc. The database involved in the embodiments provided by the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a blockchain, etc., but is not limited thereto. The processor involved in the embodiments provided by the present application can be a general processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0181] Any combination of the technical features in the above embodiments can be made. For the sake of brevity, the foregoing description has not described all possible combinations of the technical features in the above embodiments, however, it is understood that any combination of the technical features is within the scope of the present disclosure as long as there is no contradiction.

[0182] The above embodiments only express several implementation manners of the present application, and the description is relatively specific and detailed, but it should not be understood as a limitation on the patent scope of the present application. It should be pointed out that, for ordinary skilled persons in the art, several modifications and improvements can be made without departing from the concept of the present application, and these are within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A method for extracting the centerline of a blood vessel, characterized in that, The method includes: Obtain the initial black blood image of the object to be tested; The initial black blood image is input into a preset first segmentation model to obtain a first blood vessel segment image; wherein, the first blood vessel segment image includes at least one blood vessel segment; Extracting the centerline of each blood vessel segment from the first blood vessel segmentation image to obtain the blood vessel centerline image corresponding to the initial black blood image; the method further includes: Based on the blood vessel centerline image and the first blood vessel segmentation image, at least one blood vessel bifurcation point is determined; based on each blood vessel bifurcation point, each blood vessel centerline in the blood vessel centerline image is segmented to obtain a blood vessel centerline segmentation image; based on the initial black blood image, a cross-sectional image corresponding to each point on each blood vessel centerline in the blood vessel centerline image is obtained. Each of the cross-sectional images is input into the second segmentation model to obtain the segmentation result image corresponding to each of the cross-sectional images; Based on the segmentation result images corresponding to each of the cross-sectional images, it is determined whether the vascular structure in each of the cross-sectional images meets the preset vascular structure rules; If not, remove the cross-sectional images that do not meet the vascular structure rules, and obtain the target vascular image based on the remaining cross-sectional images that meet the vascular structure rules.

2. The method according to claim 1, characterized in that, The step of extracting the centerline of each blood vessel segment in the first blood vessel segment image to obtain the blood vessel centerline image corresponding to the initial black blood image includes: For each blood vessel segment, extract the centerline of each segment; Based on the initial black blood image and the preset blood vessel connection strategy, the center lines of each blood vessel segment are connected to obtain the blood vessel center line image corresponding to the initial black blood image.

3. The method according to claim 2, characterized in that, The extraction of the centerline of each blood vessel segment includes: For the aforementioned blood vessel segment, the first endpoint and the second endpoint of the blood vessel segment are determined; Based on the first segmented image of the blood vessel, the centerline of the blood vessel segment is obtained by connecting the first endpoint and the second endpoint.

4. The method according to claim 3, characterized in that, Determining the first and second endpoints of the vascular segment includes: The vascular segmentation includes multiple sub-vascular segments; Determine the first and second endpoints of each of the sub-vessel segments; Accordingly, the step of connecting the first endpoint and the second endpoint based on the first segmented blood vessel image to obtain the centerline of the blood vessel segment includes: For each sub-vessel segment, based on the first vessel segment image, the first endpoint and the second endpoint of the sub-vessel segment are connected to obtain the centerline of the sub-vessel segment; Based on the initial black blood image, the center lines of each of the sub-vessel segments are connected to obtain the center lines of the vessel segments.

5. The method according to claim 1, characterized in that, The step of determining at least one blood vessel bifurcation point based on the blood vessel centerline image and the first blood vessel segmentation image includes: Determine the location of the first bifurcation point in the first segmented blood vessel image and the location of the second bifurcation point in the blood vessel centerline image; Determine whether the position of the second bifurcation point is within a preset range of the position of the first bifurcation point; If so, then the second bifurcation point is determined as the blood vessel bifurcation point.

6. The method according to claim 5, characterized in that, The method further includes: if not, returning to re-execute the step of connecting the center lines of the blood vessel segments based on the initial black blood image and the blood vessel connection strategy to obtain an adjusted blood vessel center line image, and performing the step of determining the position of the second bifurcation point in the adjusted blood vessel center line image until the position of the second bifurcation point is within a preset range of the position of the first bifurcation point.

7. The method according to claim 1, characterized in that, The method further includes: Based on each of the aforementioned blood vessel bifurcation points, each blood vessel in the target blood vessel image is segmented to obtain a target blood vessel segmented image corresponding to the target blood vessel image.

8. The method according to claim 1, characterized in that, The method further includes: Based on the blood vessel centerline image, detect whether there is target tissue inside the blood vessels in the initial dark blood image; If so, the target tissue is segmented based on the initial black blood image to obtain the segmentation result of the target tissue.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 8.

Images