CN114299057A

CN114299057A - Method for extracting blood vessel center line and storage medium

Info

Publication number: CN114299057A
Application number: CN202111678599.0A
Authority: CN
Inventors: 毛玉妃; 杨雄; 龚震寰; 苏赛赛
Original assignee: Shanghai United Imaging Healthcare Co Ltd
Current assignee: Shanghai United Imaging Healthcare Co Ltd
Priority date: 2021-12-31
Filing date: 2021-12-31
Publication date: 2022-04-08

Abstract

The application relates to a method, a device, computer equipment, a storage medium and a computer program product for extracting a blood vessel center line, wherein a first blood vessel segmentation image comprising at least one blood vessel segment is obtained by acquiring an initial black blood image of an object to be detected and inputting the initial black blood image into a preset first segmentation model; extracting the center line of each blood vessel segment in the first blood vessel segment image to obtain a blood vessel center line image corresponding to the initial black blood image; the automatic extraction mode that the center line of the blood vessel can be directly obtained from the black blood image can be realized, the bright blood image corresponding to the black blood image is not needed, the bright blood image is not needed to be additionally obtained, and the quality problem and the registration accuracy problem of the bright blood image are not needed to be considered; after the initial black blood image is obtained, the method in the embodiment can be used for directly identifying and processing the initial black blood image to obtain the blood vessel centerline image corresponding to the initial black blood image, and the extraction efficiency is high.

Description

Method for extracting blood vessel center line and storage medium

Technical Field

The present application relates to the field of computer and image processing technologies, and in particular, to a method and an apparatus for extracting a blood vessel centerline, a computer device, a storage medium, and a computer program product.

Background

In the diagnosis of cerebrovascular diseases, it is generally necessary to identify a main cerebrovascular vessel in an image acquired by magnetic resonance, and further, a lesion region of the cerebrovascular vessel can be detected based on the identified cerebrovascular vessel to obtain a diagnosis result. In the case of identifying a cerebral blood vessel in a black blood image of a cerebral blood vessel, it is generally necessary to first determine a center line 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 center line of the cerebral blood vessel.

In the conventional technology, the process of automatically identifying the center line of the blood vessel of the black blood image comprises the following steps: and manually or automatically acquiring a blood vessel center line in the bright blood image corresponding to the black blood image, then registering the blood vessel center line in the bright blood image to the black blood image according to a registration algorithm, and then finely adjusting the registered blood vessel center line to obtain the blood vessel center line of the black blood image.

However, in the existing blood vessel centerline acquisition method for 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 blood vessel centerline acquired from the black blood image is easily poor.

Disclosure of Invention

In view of the above, it is necessary to provide a blood vessel centerline extraction method, a device, a computer readable storage medium, and a computer program product, which can extract a blood vessel centerline only from a black blood image, thereby improving the accuracy of the blood vessel centerline extraction.

In a first aspect, the present application provides a method for extracting a centerline of a blood vessel. The method comprises the following steps:

acquiring an initial black blood image of an object to be detected;

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

and extracting the central line of each blood vessel segment in the first blood vessel segment image to obtain a blood vessel central line image corresponding to the initial black blood image.

In one embodiment, extracting the center line of each blood vessel segment in the first blood vessel segment image to obtain a blood vessel center line image corresponding to the initial black blood image, includes:

extracting the central line of each blood vessel segment aiming at each blood vessel segment;

and connecting the central line of each blood vessel segment based on the initial black blood image and a preset blood vessel connection strategy to obtain a blood vessel central line image corresponding to the initial black blood image.

In one embodiment, extracting the centerline of each vessel segment comprises:

determining a first end point and a second end point of a blood vessel segment for the blood vessel segment;

based on the first vessel segment image, connecting the first end point and the second end point of the vessel segment to obtain the centerline of the vessel segment.

In one embodiment, determining the first endpoint and the second endpoint of the vessel segment comprises:

the vessel segment comprises a plurality of sub-vessel segments;

determining a first endpoint and a second endpoint of each sub-vessel segment;

correspondingly, 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 the center line of the blood vessel segment, comprising:

for each sub-blood vessel segment, connecting a first end point and a second end point of the sub-blood vessel segment based on the first blood vessel segment image to obtain a central line of the sub-blood vessel segment;

and connecting the central lines of the sub-blood vessel segments based on the initial black blood image to obtain the central lines of the blood vessel segments.

In one embodiment, the method further comprises:

determining at least one vessel bifurcation point based on the vessel centerline image and the first vessel segmentation image;

and based on each blood vessel bifurcation point, carrying out segmentation processing on each blood vessel central line in the blood vessel central line image to obtain a blood vessel central line segmented image.

In one embodiment, determining at least one vessel bifurcation point based on the vessel centerline image and the first vessel segmentation image comprises:

determining a position of a first bifurcation point in the first vessel segment image and a position of a second bifurcation point in the vessel centerline image;

judging whether the position of the second bifurcation point is within a preset range of the position of the first bifurcation point;

and determining the second bifurcation point as the vessel bifurcation point if the position of the second bifurcation point is within the preset range of the position of the first bifurcation point.

In one embodiment, the method further comprises: and under the condition that the position of the second bifurcation point is not within the preset range of the position of the first bifurcation point, returning to perform the step of connecting the central lines of each blood vessel segment based on the initial black blood image and the blood vessel connection strategy again to obtain an adjusted blood vessel central line image, and determining the position of the second bifurcation point in the adjusted blood vessel central line image until the position of the second bifurcation point is within the preset range of the position of the first bifurcation point.

In one embodiment, the method further comprises:

based on the initial black blood image, acquiring a cross-section image corresponding to each point on each blood vessel central line in the blood vessel central line image;

and processing each cross section image to obtain a target blood vessel image corresponding to the blood vessel central line image.

In one embodiment, processing each cross-sectional image to obtain a target blood vessel image corresponding to the blood vessel centerline image includes:

inputting each cross section image into a second segmentation model respectively to obtain a segmentation result image corresponding to each cross section image;

judging whether the blood vessel structure in each cross section image meets a preset blood vessel structure rule or not based on the segmentation result image corresponding to each cross section image;

and under the condition that the blood vessel structure in the cross-section image does not meet the preset blood vessel structure rule, removing the cross-section image which does not meet the blood vessel structure rule, and obtaining the target blood vessel image according to the rest cross-section images which meet the blood vessel structure rule.

In one embodiment, the method further comprises:

and based on each blood vessel bifurcation point, carrying out segmentation processing on each blood vessel in the target blood vessel image to obtain a target blood vessel segmented image corresponding to the target blood vessel image.

In one embodiment, the method further comprises:

detecting whether target tissues exist in blood vessels in the initial black blood image or not based on the blood vessel central line image;

when the target tissue is present in the blood vessel in the initial black blood image, the target tissue is segmented based on the initial black blood image, and a segmentation result of the target tissue is obtained.

In a second aspect, the application also provides a device for extracting the centerline of the blood vessel. The device includes:

the first acquisition module is used for acquiring an initial black blood image of the object to be detected;

the second acquisition module is used for inputting the initial black blood image into a preset first segmentation model to obtain a first blood vessel segmentation image; wherein the first vessel segment image comprises at least one vessel segment;

and the third acquisition module is used for extracting the center line of each blood vessel segment in the first blood vessel segment image to obtain a blood vessel center line image corresponding to the initial black blood image.

In a third aspect, the present application also provides a computer device. The computer device comprises a memory and a processor, the memory stores a computer program, and the processor realizes the following steps when executing the computer program:

acquiring an initial black blood image of an object to be detected;

In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of:

acquiring an initial black blood image of an object to be detected;

In a fifth aspect, the present application further provides a computer program product. The computer program product comprising a computer program which when executed by a processor performs the steps of:

acquiring an initial black blood image of an object to be detected;

The computer device obtains a first blood vessel segmentation image comprising at least one blood vessel segmentation by obtaining an initial black blood image of an object to be detected and inputting the initial black blood image into a preset first segmentation model, and then extracts the central line of each blood vessel segmentation in the first blood vessel segmentation image to obtain a blood vessel central line image corresponding to the initial black blood image; the automatic extraction mode that the center line of the blood vessel can be directly obtained from the black blood image is realized, the bright blood image corresponding to the black blood image is not needed, the bright blood image is not needed to be additionally obtained, and the quality problem and the registration accuracy problem of the bright blood image are not needed to be considered; after the initial black blood image is obtained, the blood vessel centerline image corresponding to the initial black blood image can be obtained directly by identifying and processing the initial black blood image through the method in the embodiment, the operation is simple and rapid, time and labor are saved, the accuracy of the obtained blood vessel centerline image is high, and the extraction efficiency is high.

Drawings

FIG. 1 is a schematic flow chart of a method for extracting a vessel centerline according to an embodiment;

FIG. 2 is a schematic structural diagram of a first vessel segment image in one embodiment;

FIG. 3 is a schematic structural diagram of a centerline image of a blood vessel in one embodiment;

FIG. 4 is a schematic flow chart of a method for extracting a blood vessel centerline according to another embodiment;

FIG. 5 is a schematic flow chart of a method for extracting a blood vessel centerline according to another embodiment;

FIG. 6 is a flow chart of a method for extracting a blood vessel centerline according to another embodiment;

FIG. 7 is a diagram illustrating a centerline extraction process for vessel segmentation in one embodiment;

FIG. 8 is a flowchart illustrating a method for extracting a centerline of a blood vessel according to another embodiment;

FIG. 9 is a schematic flow chart of a method for extracting a blood vessel centerline according to another embodiment;

FIG. 10 is a flowchart illustrating a method for extracting a centerline of a blood vessel according to another embodiment;

FIG. 11 is a flowchart illustrating a method for extracting a centerline of a blood vessel according to another embodiment;

FIG. 12 is a complete diagram illustrating the variation of the vessel centerline extraction method in one embodiment;

FIG. 13 is a block diagram showing the structure of a blood vessel centerline extraction device according to an embodiment;

FIG. 14 is a diagram illustrating an internal structure of a computer device according to an embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.

The method for extracting the blood vessel center line provided by the embodiment of the application can be applied to computer equipment, the computer equipment 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 equipment, processing equipment connected with the scanning equipment and the like, and the server can be realized by an independent server or a server cluster formed by a plurality of servers.

In one embodiment, as shown in fig. 1, a method for extracting a blood vessel centerline is provided, which is described by taking the method as an example for being applied to the computer device, and includes the following steps:

step 101, obtaining an initial black blood image of an object to be detected.

Optionally, the initial black blood image may be acquired from an acquisition device, may be acquired from a server, may be a historical initial black blood image locally acquired from a device, or the like; the embodiment does not limit the manner of obtaining the initial black blood image of the object to be measured. In addition, the initial black blood image may be a black blood sequence of different morphologies, including but not limited to a T1 enhanced image, a T1 image, a T2 image, a proton density image, and the like, and the form of the initial black blood image is not limited in this embodiment.

And 102, 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 segment image comprises at least one blood vessel segment, each blood vessel segment may be a part of blood vessels distributed in different tissues or organs, or may be different types of blood vessels in the same tissue or organ, for example: arterial vessels, venous vessels, capillaries, and the like. Optionally, in the first vessel segment image, different vessel segments may be labeled by different line types, for example: the distinguishing and labeling can be carried out according to the line colors, the line thickness, the line shapes and the like; identification information may also be employed to distinguish between different vessel segments, for example: character marks, numerical marks, symbol marks and the like can be adopted; of course, different vessel segments can be distinguished by adopting a labeling mode combining multiple modes, and the labeling mode of the vessel segments is not limited in this embodiment.

Optionally, the first segmentation model may be a segmentation model obtained by training a first initial segmentation network by using a plurality of black blood sample images and a blood vessel segment label image corresponding to each black blood sample image, where the first initial segmentation network may be based on an existing deep learning network of any type, or a segmentation network combining networks of multiple different types, and the like, and this embodiment does not limit this.

Through the first segmentation model, blood vessel segmentation processing can be carried out on the initial black blood image to obtain a first blood vessel segmented image corresponding to the initial black blood image; optionally, the number of vessel segments in the first vessel segment image may be the same as the number of vessel segments in the initial black blood image, and the vessel segment effect is better. For example: as shown in fig. 2, the first blood vessel segment image is obtained by performing blood vessel segmentation on the initial black blood image.

Step 103, extracting the center line of each blood vessel segment in the first blood vessel segment image to obtain a blood vessel center line image corresponding to the initial black blood image.

Optionally, after the first blood vessel image including at least one blood vessel segment corresponding to the initial black blood image is obtained, centerline extraction may be performed on each blood vessel segment in the first blood vessel segment image to obtain a centerline corresponding to each blood vessel segment, that is, a blood vessel centerline image corresponding to the initial black blood image may be obtained, as shown in fig. 3.

Optionally, a preset centerline extraction algorithm may be adopted to extract a centerline of each blood vessel segment in the first blood vessel segment image, or an online learning algorithm and the like may be adopted to extract a centerline of each blood vessel segment in the first blood vessel segment image, where the centerline extraction algorithm may be a model-based centerline extraction algorithm or a non-model-based centerline extraction algorithm, and the present embodiment does not limit the extraction manner of the blood vessel centerline and the principle and manner of the centerline extraction algorithm.

In the method for extracting the blood vessel center line, computer equipment obtains a first blood vessel segmentation image comprising at least one blood vessel segmentation by obtaining an initial black blood image of an object to be detected and inputting the initial black blood image into a preset first segmentation model, 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; the automatic extraction mode that the center line of the blood vessel can be directly obtained from the black blood image is realized, the bright blood image corresponding to the black blood image is not needed, the bright blood image is not needed to be additionally obtained, and the quality problem and the registration accuracy problem of the bright blood image are not needed to be considered; after the initial black blood image is obtained, the blood vessel centerline image corresponding to the initial black blood image can be obtained directly by identifying and processing the initial black blood image through the method in the embodiment, the operation is simple and rapid, time and labor are saved, the accuracy of the obtained blood vessel centerline image is high, and the extraction efficiency is high.

Fig. 4 is a schematic flow chart of a method for extracting a blood vessel centerline in another embodiment. The embodiment relates to one optional implementation process of extracting the center line of each blood vessel segment in a first blood vessel segment image by computer equipment to obtain a blood vessel center line image corresponding to an initial black blood image; as shown in fig. 4, on the basis of the above embodiment, the step 103 includes:

step 401, for each blood vessel segment, extracting a center line of each blood vessel segment.

Regarding the implementation manner of extracting the center line of the blood vessel segment, reference may be made to the related contents in step 103, which are not described herein again. Optionally, different line colors may be used to label different vessel segments in this embodiment.

And 402, connecting the central line of each blood vessel segment based on the initial black blood image and a preset blood vessel connection strategy to obtain a blood vessel central line image corresponding to the initial black blood image.

The preset blood vessel connection strategy may include connection rules of a plurality of blood vessels, and the connection rule of each blood vessel may include connection rules of a plurality of blood vessel segments located in different tissues or organs; for example: for a complete artery blood vessel, it can shuttle to a plurality of different tissues or organs, for a plurality of blood vessel segments of the artery blood vessel in different tissues or organs can be distinguished by using different line colors, and the connection sequence between a plurality of blood vessel segments corresponding to the artery blood vessel can be preset.

Optionally, after extracting the center line of each blood vessel segment, the computer device may connect the center lines of the blood vessel segments having an association relationship in each blood vessel segment based on the initial black blood image and the blood vessel connection policy to obtain a blood vessel center line image corresponding to the initial black blood image, where the blood vessel center line image includes at least one complete blood vessel.

Optionally, the computer device may determine, based on the blood vessel connection policy, two blood vessel segments to be connected having an association relationship in a first blood vessel to be currently connected according to a blood vessel connection sequence of each blood vessel in the blood vessel connection policy, and then, based on the initial black blood image, perform connection processing on center lines of the two blood vessel segments to be connected by using an optimal path algorithm, and so on until the center lines of each blood vessel segment in the first blood vessel are connected, so as to obtain a first blood vessel center line corresponding to the first blood vessel; similarly, after the connection of the center lines of the first blood vessels is completed, the center lines of the second blood vessels may be connected, and so on, until the center lines of all the blood vessel segments having the association relation are connected, the blood vessel center line image may be obtained.

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 policy to obtain a blood vessel center line image corresponding to the initial black blood image, so that the accuracy of extracting the blood vessel center line can be improved, and the efficiency of improving the blood vessel center line can be improved.

Fig. 5 is a schematic flow chart of a method for extracting a blood vessel centerline in another embodiment. The embodiment relates to one optional implementation process of extracting the central line of each blood vessel segment by a computer device; as shown in fig. 5, on the basis of the above embodiment, the step 401 includes:

in step 501, for a vessel segment, a first end point and a second end point of the vessel segment are determined.

The first end point of the blood vessel segment may be a center point of a head end of the blood vessel segment, and the second end point of the blood vessel segment may be a center point of a tail end of the blood vessel segment.

Step 502, based on the first vessel segment image, connecting the first end point and the second end point of the vessel segment to obtain the centerline of the vessel segment.

Optionally, when determining the centerline of the vessel segment in the first vessel segment image, after determining the first end point and the second end point of the vessel segment, the centerline of the vessel segment may be formed by connecting the first end point and the second end point of the vessel segment based on the segmented vessel in the first vessel segment image; optionally, based on the segmented blood vessel in the first blood vessel segmented image, a blood vessel refinement algorithm may be adopted to obtain central points at multiple positions of the segmented blood vessel, and the central points at the multiple positions are connected with the first end point and the second end point of the blood vessel segment to obtain a center line of the blood vessel segment; or based on the segmented blood vessel in the first blood vessel segmented image, connecting the first endpoint and the second endpoint of the blood vessel segment by adopting an optimal path algorithm to obtain the central line of the blood vessel segment; it should be noted that, in this embodiment, a specific implementation manner of connecting the first end point and the second end point of the blood vessel segment to form the centerline of the blood vessel segment is not limited, and in practical application, any existing centerline determination method may be used to implement the method.

In this embodiment, for a blood vessel segment, the computer device obtains a center line of the blood vessel segment by determining a first end point and a second end point of the blood vessel segment and connecting the first end point and the second end point of the blood vessel segment based on a first blood vessel segment image, and the obtained center line of the blood vessel segment has high accuracy, a simple implementation process, and high extraction efficiency of the center line.

In an optional embodiment of the present application, based on the influence of some objective factors, there may be problems of poor occlusion and poor visualization effects in different blood vessel segments in an initial black blood image of an object to be measured, which may cause a situation that each blood vessel segment in a first blood vessel segment image corresponding to the initial black blood image output by a first segmentation model may be fractured, that is, for a same blood vessel segment, there may be multiple sub-blood vessel segments (for example, multiple blood vessel segments of the same color may appear in the first blood vessel segment image, and the multiple blood vessel segments of the same color are partial blood vessels of a blood vessel in the same tissue or organ); in this case, when determining the centerline of the blood vessel segment, the centerlines of a plurality of sub-blood vessel segments corresponding to the blood vessel segment may be determined, and then the centerlines of the sub-blood vessel segments are connected to obtain the centerline of the blood vessel segment.

Fig. 6 is a schematic flow chart of a method for extracting a blood vessel centerline in another embodiment. The embodiment relates to one optional implementation process of extracting the central line of each blood vessel segment by a computer device under the condition that the blood vessel segment comprises a plurality of sub blood vessel segments; as shown in fig. 6, on the basis of the above embodiment, the step 501 includes:

step 601, determining a first end point and a second end point of each sub-vessel segment.

The first end point of the sub-blood vessel segment may be a head-end center point of the sub-blood vessel segment, and the second end point of the sub-blood vessel segment may be a tail-end center point of the sub-blood vessel segment.

Accordingly, step 502 includes:

step 602, for each sub-vessel segment, connecting a first end point and a second end point of the sub-vessel segment based on the first vessel segment image, and obtaining a centerline of the sub-vessel segment.

The manner of determining the center line of the sub-vessel segment may refer to the implementation manner of determining the center line of the vessel segment in step 502, which is not described herein again.

And step 603, connecting the central lines of the sub-blood vessel segments based on the initial black blood image to obtain the central lines of the blood vessel segments.

Alternatively, after the central lines of a plurality of sub-blood vessel segments of a certain blood vessel segment are determined, a connection order of the central lines of the sub-blood vessel segments can be determined based on the initial black blood image, and then the central lines of two adjacent sub-blood vessel segments can be connected according to the connection order to obtain the central line of the blood vessel segment; optionally, when connecting the center lines of two adjacent sub-blood vessel segments, for the vacant part between the center lines of the two sub-blood vessel segments, an optimal path algorithm may be adopted, and a partial center line between the center lines of the two sub-blood vessel segments is generated by means of the initial black blood image, so as to connect the center lines of the two sub-blood vessel segments; of course, other connection manners or connection algorithms may also be used to connect the centerlines of two adjacent sub-vessel segments, which is not limited in this embodiment of the application.

In this embodiment, in a case that the blood vessel segment includes a plurality of sub-blood vessel segments, a first end point and a second end point of each sub-blood vessel segment may be determined, and for each sub-blood vessel segment, the first end point and the second end point of the sub-blood vessel segment are connected based on the first blood vessel segment image, so as to obtain a center line of the sub-blood vessel segment; then, based on the initial black blood image, connecting the central lines of the sub-blood vessel segments to obtain the central lines of the blood vessel segments; the obtained center line of the blood vessel segment is high in accuracy, the obtained center line of the blood vessel segment is more complete, and the accuracy and the integrity of center line extraction are improved.

In another optional embodiment of the present application, in a case that the blood vessel segment includes a plurality of sub-blood vessel segments, the longest two sub-blood vessel segments may be further determined from the plurality of sub-blood vessel segments corresponding to the blood vessel segment, and the centerline of the blood vessel segment may be obtained based on the two longest sub-blood vessel segments; optionally, for a blood vessel segment (shown in fig. 7(a), which is a structural diagram of the blood vessel segment), a longest sub-blood vessel segment and a second longest sub-blood vessel segment may be determined from a plurality of sub-blood vessel segments of the blood vessel segment, and a first end point of the longest sub-blood vessel segment and a first end point of the second longest sub-blood vessel segment are determined as a first end point of the blood vessel segment, and a second end point of the longest sub-blood vessel segment and a second end point of the second longest sub-blood vessel segment are determined as a second end point of the blood vessel segment; that is, the first end point and the second end point of the longest sub-vessel segment are determined, and the first end point and the second end point of the second longest sub-vessel segment are determined; then, for the longest sub-vessel segment, connecting the first end point and the second end point of the longest sub-vessel segment to obtain a first center line of the longest sub-vessel segment, and for the second sub-vessel segment, connecting the first end point and the second end point of the second sub-vessel segment to obtain a second center line of the second sub-vessel segment (as shown in fig. 7(b), a structural diagram of the center line of the longest sub-vessel segment and the center line of the second sub-vessel segment in the vessel segment); then, the first center line of the longest sub-vessel segment and the second center line of the sub-longest sub-vessel segment may be connected to represent the center line of the vessel segment (as shown in fig. 7(c), which is a structural diagram of the center line of the vessel segment).

Optionally, when the first end point and the second end point of the longest sub-blood vessel segment are connected, an optimal path algorithm may be used to connect the first end point of the longest sub-blood vessel segment and the second end point of the longest sub-blood vessel segment based on the first blood vessel segment image, so as to obtain a center line of the longest sub-blood vessel segment; similarly, when the first end point of the sub-long sub-blood vessel segment and the second end point of the sub-long sub-blood vessel segment are connected, the first end point of the sub-long sub-blood vessel segment and the second end point of the sub-long sub-blood vessel segment may be connected by using an optimal path algorithm based on the first blood vessel segment image to obtain the center line of the sub-long sub-blood vessel segment; then, based on the initial black blood image, an optimal path algorithm may be used to connect the center line of the longest sub-blood vessel segment and the center line of the sub-longest sub-blood vessel segment, so as to obtain the center line of the blood vessel segment.

In this embodiment, in the case that the blood vessel segment includes a plurality of sub-blood vessel segments, the center line of the blood vessel segment may 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 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 increased, and the accuracy of the center line of the blood vessel segment can be ensured.

Fig. 8 is a schematic flow chart of a method for extracting a blood vessel centerline in another embodiment. The embodiment relates to a method for further determining one optional implementation process of a segmented image of a blood vessel centerline by computer equipment on the basis of the blood vessel centerline image; as shown in fig. 8, on the basis of the above embodiment, the method further includes:

step 801, determining at least one vessel bifurcation point based on the vessel centerline image and the first vessel segmentation image.

In the above embodiment, a center line of each blood vessel segment is obtained, and a plurality of 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, that is, a blood vessel center line image; after the blood vessel centerline image is obtained, each complete blood vessel in the blood vessel centerline may be segmented to obtain a blood vessel centerline segmented image corresponding to the first blood vessel segmented image. Each blood vessel segment central line in the blood vessel central line segmented image corresponds to each blood vessel segment in the first blood vessel segmented image one by one, but compared with the central line of each blood vessel segment obtained based on the initial black blood image and the first blood vessel segmented image, the central line of each blood vessel segment obtained based on the blood vessel central line image and the first blood vessel segmented image is more complete, the connectivity between the central lines of two mutually connected blood vessel segments is better, and the distribution of the blood vessel segments of each blood vessel in different tissues or organs can be accurately distinguished while the integrity of each blood vessel is ensured.

Optionally, before segmenting the blood vessel centerline image, a plurality of bifurcation points are determined, where the plurality of blood vessel bifurcation points are connection points between blood vessel segments, so that the computer device can perform segmentation processing on a plurality of blood vessels in the blood vessel centerline image according to each bifurcation point; when determining the bifurcation point, a plurality of bifurcation points in the first vessel segmentation image and a plurality of bifurcation points in the vessel centerline image may be determined, and then, a plurality of vessel bifurcation points finally segmenting the vessel centerline image may be obtained by comparing the plurality of bifurcation points in the first vessel segmentation image and the plurality of bifurcation points in the vessel centerline image.

Optionally, a location of a first bifurcation point in a first vessel segment image and a location of a second bifurcation point in a vessel centerline image may be determined, wherein the first bifurcation point and the second bifurcation point are bifurcation points between the same vessels in the first vessel segment image and the vessel centerline image; then, whether the position of the second bifurcation point is within a preset range of the position of the first bifurcation point can be judged; in the case where the position of the second bifurcation point is determined to be within the preset range of the position of the first bifurcation point, the second bifurcation point may be determined as a vessel bifurcation point, that is, in this case, it indicates that the cross-connection between several vessels in the first vessel segmentation image substantially coincides with the cross-connection between the several vessels in the vessel centerline, and it also indicates that the degree of matching between the centerline of each vessel in the vessel centerline image and the actual vessel in the initial black blood image is high, and the obtained vessel centerline is more accurate.

Optionally, in a case that the position of the second bifurcation point is not within the preset range of the position of the first bifurcation point, it is described that the centerline of the complete blood vessel obtained after connecting the centerlines of the plurality of blood vessel segments having an association relation is different from the actual blood vessel in the initial black blood image; at this time, the method may return to re-execute the initial black blood image and the blood vessel connection strategy to connect the center lines of each blood vessel segment to obtain an adjusted blood vessel centerline image, and then, may continue to execute the step of determining the position of the second bifurcation point in the adjusted blood vessel centerline image, and determine 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 segment image, if so, may use the second bifurcation point in the adjusted blood vessel centerline image as the blood vessel bifurcation point for finally segmenting the blood vessel centerline image; if the position of the second bifurcation point is not in the preset range of the position of the first bifurcation point, returning to continue to execute 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 to obtain an adjusted blood vessel center line image and the subsequent steps.

And step 802, based on each blood vessel bifurcation point, performing segmentation processing on each blood vessel center line in the blood vessel center line image to obtain a blood vessel center line segmented image.

Alternatively, after the segmentation processing, the segmentation markers identical to the vessel segments in the first vessel segment image may be used to mark the vessel centerline segments after the segmentation processing, so that the obtained vessel centerline segment image and the first vessel segment image have a one-to-one correspondence.

In this embodiment, after determining the blood vessel centerline image, the computer device may further determine at least one blood vessel bifurcation point based on the blood vessel centerline image and the first blood vessel segmentation image; then, each blood vessel center line in the blood vessel center line image can be segmented based on each blood vessel bifurcation point to obtain a blood vessel center line segmented image, namely, the blood vessel center line segmented image corresponding to the first blood vessel segmented image one by one is obtained, so that a user can more intuitively master the blood vessel distribution of different blood vessels in different tissues or organs, and the user experience is improved.

In an optional embodiment of the present application, before determining at least one vessel bifurcation point based on the vessel centerline image and the first vessel segment image, the computer device may further extend each vessel centerline in the vessel centerline image based on the initial black blood image, to obtain an extended vessel centerline image; because the first blood vessel segment image obtained by performing blood vessel segmentation on the initial black blood image by using the first segmentation model may have a missing edge blood vessel, or may cause an incomplete blood vessel center line when the center lines of the longest two blood vessel segments are connected to obtain the blood vessel center line, in this embodiment, each blood vessel in the blood vessel center line image is subjected to two-end extension processing, the center line of each blood vessel subjected to the extension processing is more complete, and the whole form of an actual blood vessel in the initial black blood image can be more reflected.

Optionally, when performing the extending processing on each blood vessel center line in the blood vessel center line image, the extending processing of the preset length may be performed on both ends of each blood vessel center line based on the initial black blood image, or the extending processing of the preset length may be performed along the blood vessel flow direction based on the blood vessel flow direction at both ends of each blood vessel center line, and the implementation manner and the extending length of the extending blood vessel center line are not limited in this embodiment.

Fig. 9 is a schematic flow chart of a method for extracting a blood vessel centerline in another embodiment. The embodiment relates to a method for restoring blood vessels by computer equipment on the basis of the blood vessel central line image to further determine one optional implementation process of a target blood vessel image; as shown in fig. 9, on the basis of the above embodiment, the method further includes:

step 901, acquiring cross-section images corresponding to each point on each blood vessel central line in the blood vessel central line images based on the initial black blood images.

Alternatively, for each vessel centerline in the vessel centerline image, a plurality of points on the vessel centerline may be predetermined, and the distance between each point should be less than or equal to a preset distance threshold, for example: the distance between each point may be less than or equal to 0.7 mm; optionally, an interpolation algorithm may be used to perform interpolation processing on each blood vessel centerline to obtain a plurality of points, where a distance between two corresponding to each blood vessel centerline is less than or equal to a preset distance threshold; then, based on the initial black blood image, a cross-sectional image of the blood vessel position corresponding to each point may be acquired.

And 902, processing each cross-section image to obtain a target blood vessel image corresponding to the blood vessel central line image.

Optionally, after obtaining a cross-sectional image corresponding to each point of the centerline of the blood vessel, processing the cross-sectional image corresponding to each point, so that the cross-sectional image corresponding to each point satisfies a preset blood vessel structure rule, where the preset blood vessel structure rule may include, but is not limited to, that the lumen contour does not exceed the tube wall contour, the size of the lumen, the size of the tube wall, the spacing distance between the lumen and the tube wall, and the like; under the condition that the cross section image corresponding to a certain point is judged not to meet the vascular structure rule, the cross section image corresponding to the point can be adjusted to obtain the adjusted cross section image meeting the vascular structure rule; finally, a target blood vessel image corresponding to the blood vessel center line image can be generated based on the cross section images corresponding to all the points and meeting the blood vessel structure rule; the cross-section images of two adjacent points can be filled in a filling mode to obtain the target blood vessel image.

In this embodiment, the computer device may obtain, based on the initial black blood image, cross-sectional images corresponding to respective points on each blood vessel centerline in the blood vessel centerline image, and process the respective cross-sectional images to obtain a target blood vessel image corresponding to the blood vessel centerline image; the target blood vessel image can reflect the form and distribution of each blood vessel in the initial black blood image, can more intuitively show the distribution of each blood vessel of the object to be detected for the user, and improves the viewing experience and the visualization degree of the user.

Fig. 10 is a flowchart illustrating a method for extracting a blood vessel centerline according to another embodiment. The embodiment relates to one optional implementation process of processing each cross-section image by computer equipment to obtain a target blood vessel image corresponding to a blood vessel central line image; as shown in fig. 10, on the basis of the foregoing embodiment, the foregoing step 902 includes:

and 1001, respectively inputting each cross-section image into a second segmentation model to obtain a segmentation result image corresponding to each cross-section image.

The segmentation result image corresponding to the cross-sectional image may be an annotated image having annotation information of a lumen contour and a wall contour of a blood vessel in the cross-sectional image.

The second segmentation model is obtained by training a second initial segmentation network according to the cross-section sample images of the multiple blood vessels and the segmentation result labels corresponding to the cross-section sample images of each blood vessel, and the second initial segmentation network may be a deep learning network based on any type in the prior art, or a segmentation network combining multiple different types of networks, and the like, which is not limited in this embodiment. In addition, the second initial split network may be the same or different initial split network as the first initial split network.

Step 1002, based on the segmentation result images corresponding to the cross-sectional images, determining whether the blood vessel structure in each cross-sectional image meets a preset blood vessel structure rule.

And 1003, under the condition that the blood vessel structure in the cross-section image does not meet the preset blood vessel structure rule, removing the cross-section image which does not meet the blood vessel structure rule, and obtaining a target blood vessel image according to the rest cross-section images which meet the blood vessel structure rule.

Optionally, the other cross-sectional images satisfying the vascular structure rule may be subjected to filling processing to obtain the target vascular image; or based on the other cross section images meeting the blood vessel structure rule, performing first filling processing on two adjacent cross section images to generate an intermediate blood vessel image; in the intermediate blood vessel image, a blood vessel gap exists at the position where the cross section image which does not meet the blood vessel structure rule is removed, and for the blood vessel gap, second filling processing can be further carried out on the intermediate blood vessel image to obtain the target blood vessel image; the first filling process and the second filling process may adopt different filling processes in the prior art.

Optionally, before the second filling processing is performed on the intermediate blood vessel image to obtain the target blood vessel image, an interpolation algorithm may be used to determine a new blood vessel section with respect to a missing blood vessel section in the intermediate blood vessel image (that is, a cross-sectional image that does not satisfy the blood vessel structure rule is removed), and then the new blood vessel section may be interpolated to a missing position in the intermediate blood vessel image to obtain an interpolated intermediate blood vessel image, so that the second filling processing may be performed on the interpolated intermediate blood vessel image to obtain the target blood vessel image.

Optionally, after performing the second filling processing on the interpolated intermediate blood vessel image, performing post-processing operation on the blood vessel image after the filling processing to obtain the target blood vessel image; alternatively, the post-treatment operation may include, but is not limited to, removing non-vascular points from the surface of the blood vessel, smoothing the surface of the blood vessel, etc., to improve the smoothness of the surface of the blood vessel.

In this embodiment, the computer device obtains a segmentation result image corresponding to each cross-sectional image by inputting each cross-sectional image into the second segmentation model, and determines whether the blood vessel structure in each cross-sectional image satisfies a preset blood vessel structure rule based on the segmentation result image corresponding to each cross-sectional image, removes the cross-sectional image that does not satisfy the blood vessel structure rule under the condition that the blood vessel structure in the cross-sectional image does not satisfy the preset blood vessel structure rule, and obtains a target blood vessel image according to the remaining cross-sectional images that satisfy the blood vessel structure rule; the cross-section images which do not meet the blood vessel structure rule are removed, and the target blood vessel image is generated by the other cross-section images which meet the blood vessel structure rule, blood vessels in the obtained target blood vessel image are more consistent with standard blood vessels, the obtained target blood vessel image is more accurate, and the accuracy of the target blood vessel image is improved.

In an optional embodiment of the present application, based on the obtained multiple blood vessel bifurcation points and the target blood vessel image, further, the computer device may further perform segmentation processing on each blood vessel in the target blood vessel image based on the obtained multiple blood vessel bifurcation points, so as to obtain a target blood vessel segmented image corresponding to the target blood vessel image; compared with the first blood vessel segmentation image, the blood vessel shape 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 the incidence relation is better, and the blood vessel extraction effect is better.

Fig. 11 is a flowchart illustrating a method for extracting a blood vessel centerline according to another embodiment. The embodiment relates to one optional implementation process of carrying out tissue detection on an initial black blood image by computer equipment based on a blood vessel central line image; as shown in fig. 11, on the basis of the foregoing embodiment, the foregoing method further includes:

step 1101, detecting whether target tissue exists in the blood vessel in the initial black blood image based on the blood vessel centerline image.

Optionally, in the first embodiment of the present application, after determining, according to the initial black blood image, a blood vessel centerline image corresponding to the initial black blood image, the computer device may further detect and locate a target tissue in a blood vessel of the object to be detected according to the blood vessel centerline image, for example: plaque detection, stenosis detection, or the like can be performed on the blood vessel of the object to be measured based on the blood vessel centerline image.

Optionally, based on the blood vessel centerline image, the blood vessel in the initial black blood image may be segmented, and the blood vessel in the segmented initial black blood image may be detected and analyzed to determine whether the target tissue exists in the blood vessel; optionally, after the blood vessels in the initial black blood image are segmented, the blood vessels may be analyzed layer by layer, and a cross-sectional image of the blood vessel corresponding to each layer is obtained, then, the cross-sectional image of the blood vessel of each layer may be segmented to determine the lumen and the wall of the blood vessel, then, the lumen and the wall of the segmented blood vessel may be subjected to caliber analysis to identify the stenosis portion of the blood vessel, and components between the lumen and the wall of the identified stenosis portion of the blood vessel may be identified, and whether the target tissue exists in the stenosis portion may be determined according to the identification result. It should be noted that, in this embodiment, the identification of the target tissue in the blood vessel may adopt the prior art, and therefore, the specific implementation process of the identification of the target tissue is not described herein again.

Step 1102, under the condition that the target tissue exists in the blood vessel in the initial black blood image, performing segmentation processing on the target tissue based on the initial black blood image to obtain a segmentation result of the target tissue.

Optionally, under the condition that it is determined that the target tissue exists in the blood vessel in the initial black blood image, a preset third segmentation model may be adopted, and based on the initial black blood image, segmentation processing may be performed on the target tissue to obtain a segmentation result of the target tissue; the third segmentation model may be a segmentation model obtained by training a third initial segmentation network by using a plurality of black blood sample images with target tissues and target tissue labels corresponding to each of the black blood sample images, where the third initial segmentation network may be based on any existing type of deep learning network, or a segmentation network combining a plurality of different types of networks, and the like, and this embodiment does not limit this; the third initial split network may be the same as or different from the first initial split network or the second initial split network.

In this embodiment, the computer device detects whether a target tissue exists in a blood vessel in the initial black blood image based on the blood vessel centerline image; under the condition 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; in other words, in the whole detection process, the extraction of the blood vessel center line and the detection of the target tissue can be realized only by acquiring the initial black blood image of the object to be detected, and the whole process is efficient and real-time and has high detection precision.

A complete embodiment of a method for extracting a vessel centerline is provided below, which may include the steps of:

1. acquiring an initial black blood image of an object to be detected, and inputting the initial black blood image into a preset first segmentation model to obtain a first blood vessel segmentation image which comprises at least one blood vessel segment and corresponds to the initial black blood image, as shown in fig. 12 (a);

2. extracting a center line of each vessel segment in the first vessel segment image, as shown in fig. 12 (b);

3. based on the initial black blood image and a preset blood vessel connection strategy, connecting the center line of each blood vessel segment to obtain a blood vessel center line image corresponding to the initial black blood image, as shown in fig. 12 (c);

4. extending the central line of each blood vessel segment to obtain an extended blood vessel central line image, as shown in fig. 12 (d);

5. determining at least one vessel bifurcation point based on the vessel centerline image and the first vessel segmentation image, and performing segmentation processing on each vessel centerline in the vessel centerline image based on each vessel bifurcation point to obtain a vessel centerline segmentation image, as shown in fig. 12 (e);

6. performing interpolation processing on each blood vessel in the blood vessel centerline image to obtain a plurality of points on each blood vessel centerline, as shown in fig. 12(f), then, based on the initial black blood image, obtaining a cross-sectional image corresponding to each point on each blood vessel centerline in the blood vessel centerline image, and judging whether the blood vessel structure in the cross-sectional image corresponding to each point meets a preset blood vessel structure rule; removing the cross-sectional image which does not meet the vascular structure rule, and reserving the cross-sectional image which meets the vascular structure rule to obtain an intermediate vascular image, as shown in fig. 12 (g);

7. determining a new blood vessel section corresponding to the missing position point in the intermediate blood vessel image by adopting an interpolation algorithm for the missing blood vessel section in the intermediate blood vessel image, interpolating the new blood vessel section to the missing position in the intermediate blood vessel image to obtain an interpolated intermediate blood vessel image, and then performing filling processing on the interpolated intermediate blood vessel image to obtain a target blood vessel image, as shown in fig. 12 (h); performing post-processing operation (for example, removing surface non-blood vessel points) on the target blood vessel image to obtain a processed target blood vessel image, as shown in fig. 12 (i);

8. the target blood vessel image is segmented based on the blood vessel bifurcation points to obtain segmented target blood vessel images after vessel bifurcation, as shown in fig. 12 (j).

It should be noted that each schematic diagram in fig. 12 is merely illustrated as an example of the embodiment, and is not used to limit the concrete expression of each step in the embodiment.

It should be understood that, although the steps in the flowcharts related to the embodiments as described above are sequentially displayed as indicated by arrows, the steps are not necessarily performed sequentially as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a part of the steps in the flowcharts related to the embodiments described above may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the execution order of the steps or stages is not necessarily sequential, but may be rotated or alternated with other steps or at least a part of the steps or stages in other steps.

Based on the same inventive concept, the embodiment of the present application further provides a blood vessel centerline extraction device for implementing the blood vessel centerline extraction method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so specific limitations in the following embodiments of the device for extracting one or more blood vessel center lines may refer to the limitations on the method for extracting the blood vessel center lines, and are not described herein again.

In one embodiment, as shown in fig. 13, there is provided a blood vessel centerline extraction device, including: a first obtaining module 1301, a second obtaining module 1302, and a third obtaining module 1303, wherein:

a first obtaining module 1301, configured to obtain an initial black blood image of a to-be-detected object;

a second obtaining module 1302, configured to input the initial black blood image into a preset first segmentation model, so as to obtain a first blood vessel segmentation image; wherein the first vessel segment image comprises at least one vessel segment;

the third obtaining module 1303 is configured to extract a center line of each blood vessel segment in the first blood vessel segment image, so as to obtain a blood vessel center line image corresponding to the initial black blood image.

In one embodiment, the third obtaining module 1303 includes an extracting unit and a obtaining unit; the extraction unit is used for extracting the central line of each blood vessel segment aiming at each blood vessel segment; and the acquisition unit is used for connecting the center line of each blood vessel segment based on the initial black blood image and a preset blood vessel connection strategy to obtain a blood vessel center line image corresponding to the initial black blood image.

In one embodiment, the extracting unit is specifically configured to determine, for a blood vessel segment, a first end point and a second end point of the blood vessel segment; based on the first vessel segment image, connecting the first end point and the second end point of the vessel segment to obtain the centerline of the vessel segment.

In one embodiment, the extracting unit is specifically configured to determine a first end point and a second end point of each sub-blood vessel segment when the blood vessel segment includes a plurality of sub-blood vessel segments; connecting a first end point and a second end point of each sub-blood vessel segment based on the first blood vessel segment image aiming at each sub-blood vessel segment to obtain a central line of the sub-blood vessel segment; and connecting the central lines of the sub-blood vessel segments based on the initial black blood image to obtain the central lines of the blood vessel segments.

In one embodiment, the apparatus further comprises a determining module and a fourth obtaining module; the determination module is used for determining at least one vessel bifurcation point based on the vessel centerline image and the first vessel segmentation image; and the fourth acquisition module is used for carrying out segmentation processing on each blood vessel central line in the blood vessel central line image based on each blood vessel bifurcation point to obtain a blood vessel central line segmented image.

In one embodiment, the determining module includes a first determining unit, a judging unit and a second determining unit; wherein the first determining unit is used for determining 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; a judging unit configured to judge whether a position of the second bifurcation point is within a preset range of a position of the first bifurcation point; a second determination unit for determining the second bifurcation point as a vessel bifurcation point in a case where a position of the second bifurcation point is within a preset range of a position of the first bifurcation point.

In one embodiment, the second determining unit is further configured to, in a case that the location of the second bifurcation point is not within the preset range of the location of the first bifurcation point, return to re-perform the step of connecting the centerlines of each of the vessel segments based on the initial black blood image and the vessel connection strategy to obtain an adjusted vessel centerline image, and perform the step of determining the location of the second bifurcation point in the adjusted vessel centerline image until the location of the second bifurcation point is within the preset range of the location of the first bifurcation point.

In one embodiment, the apparatus further comprises a fifth obtaining module and a sixth obtaining module; the fifth acquisition module is used for acquiring cross-section images corresponding to each point on each blood vessel central line in the blood vessel central line images based on the initial black blood images; and the sixth acquisition module is used for processing each cross section image to obtain a target blood vessel image corresponding to the blood vessel central line image.

In one embodiment, the sixth obtaining module includes a first obtaining unit, a determining unit, and a second obtaining unit; the first acquisition unit is used for respectively inputting each cross-section image into the second segmentation model to obtain a segmentation result image corresponding to each cross-section image; the judging unit is used for judging whether the blood vessel structure in each cross section image meets a preset blood vessel structure rule or not based on the segmentation result image corresponding to each cross section image; and the second acquisition unit is used for removing the cross-section image which does not meet the blood vessel structure rule under the condition that the blood vessel structure in the cross-section image does not meet the preset blood vessel structure rule, and obtaining the target blood vessel image according to the rest cross-section images which meet the blood vessel structure rule.

In one embodiment, the apparatus further comprises a seventh obtaining module; the seventh obtaining module is configured to perform segmentation processing on each blood vessel in the target blood vessel image based on each blood vessel bifurcation point to obtain a target blood vessel segmented image corresponding to the target blood vessel image.

In one embodiment, the apparatus further comprises a detection module and an eighth acquisition module; the detection module is used for detecting whether target tissues exist in blood vessels in the initial black blood image or not based on the blood vessel central line image; and the eighth acquiring module is used for performing segmentation processing on the target tissue based on the initial black blood image under the condition that the target tissue exists in the blood vessel in the initial black blood image to obtain a segmentation result of the target tissue.

The modules in the blood vessel centerline extraction device can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.

In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 14. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile 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 operation of an operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless communication can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a method of vessel centerline extraction. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.

Those skilled in the art will appreciate that the architecture shown in fig. 14 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.

In one embodiment, a computer device is provided, which includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the blood vessel centerline extraction method in any one of the above embodiments when executing the computer program.

In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method for extracting a vessel centerline according to any one of the above embodiments.

In an embodiment, a computer program product is provided, comprising a computer program which, when being executed by a processor, carries out the steps of the method for extracting a vessel centerline according to any of the above embodiments.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high-density embedded nonvolatile Memory, resistive Random Access Memory (ReRAM), Magnetic Random Access Memory (MRAM), Ferroelectric Random Access Memory (FRAM), Phase Change Memory (PCM), graphene Memory, and the like. Volatile Memory can include Random Access Memory (RAM), external cache Memory, and the like. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others. The databases referred to in various embodiments provided herein may include at least one of relational and non-relational databases. The non-relational database may include, but is not limited to, a block chain based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing based data processing logic devices, etc., without limitation.

The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.

The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A method of extracting a vessel centerline, the method comprising:

acquiring an initial black blood image of an object to be detected;

2. The method according to claim 1, wherein the extracting the centerline of each blood vessel segment in the first blood vessel segment image to obtain a blood vessel centerline image corresponding to the initial black blood image comprises:

3. The method of claim 2, wherein the extracting the centerline of each vessel segment comprises:

determining, for the vessel segment, a first end point and a second end point of the vessel segment;

and connecting the first end point and the second end point based on the first blood vessel segment image to obtain the central line of the blood vessel segment.

4. The method of claim 3, wherein the determining the first endpoint and the second endpoint of the vessel segment comprises:

the vessel segment comprises a plurality of sub-vessel segments;

determining a first end point and a second end point of each of the sub-vessel segments;

correspondingly, the connecting the first endpoint and the second endpoint based on the first blood vessel segment image to obtain the centerline of the blood vessel segment includes:

for each sub-vessel segment, connecting a first end point and a second end point of the sub-vessel segment based on the first vessel segment image to obtain a central line of the sub-vessel segment;

and connecting the central lines of the sub-vessel segments based on the initial black blood image to obtain the central lines of the vessel segments.

5. The method of claim 2, further comprising:

and carrying out segmentation processing on each blood vessel central line in the blood vessel central line image based on each blood vessel bifurcation point to obtain a blood vessel central line segmented image.

6. The method of claim 5, wherein determining at least one vessel bifurcation point based on the vessel centerline image and the first vessel segmentation image comprises:

determining a location of a first bifurcation point in the first vessel segment image and a location of a second bifurcation point in the vessel centerline image;

and if so, determining the second bifurcation point as the vessel bifurcation point.

7. The method of claim 6, further comprising: if not, returning to re-executing 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 executing the step of determining the position of a 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.

8. The method of claim 5, further comprising:

acquiring cross-section images corresponding to each point on each blood vessel central line in the blood vessel central line images based on the initial black blood images;

and processing each cross section image to obtain a target blood vessel image corresponding to the blood vessel center line image.

9. The method according to claim 8, wherein the processing each cross-sectional image to obtain a target blood vessel image corresponding to the blood vessel centerline image comprises:

judging whether the blood vessel structure in each cross-section image meets a preset blood vessel structure rule or not based on the segmentation result image corresponding to each cross-section image;

if not, removing the cross section image which does not meet the blood vessel structure rule, and obtaining the target blood vessel image according to the rest cross section images which meet the blood vessel structure rule.

10. The method of claim 8, further comprising:

11. The method of claim 1, further comprising:

detecting whether target tissue exists in the blood vessel in the initial black blood image based on the blood vessel central line image;

and if so, carrying out segmentation processing on the target tissue based on the initial black blood image to obtain a segmentation result of the target tissue.

12. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 11.