Target basin determination method, device, equipment, storage medium and program product

Abstract

The application relates to a target flow field determination method, device, equipment, storage medium and program product. The method comprises the following steps: obtaining a to-be-measured point selected by a user on a to-be-measured blood vessel in at least one candidate blood vessel; the at least one candidate blood vessel has a relative position relationship with a preset to-be-measured tissue; determining a target blood vessel corresponding to the to-be-measured point and the end of the to-be-measured blood vessel according to the to-be-measured point and the to-be-measured blood vessel; calculating a tissue range corresponding to the target blood vessel in the to-be-measured tissue to obtain a target flow field. The method can reduce the operation complexity in the calculation of the flow field.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method, apparatus, device, storage medium, and program product for determining a target watershed. Background Technology

[0002] The liver is a vital organ in the human body, primarily responsible for metabolic functions. The portal vein, a crucial blood vessel, transforms nutrients absorbed by the intestines, transports them into the bloodstream for circulation, and then delivers them to the liver to provide nourishment. The liver is typically divided into eight segments, and the portal vein also includes various branches. These branches supply different segments of the liver, and the segment supplied by each branch is its corresponding watershed. Analyzing the watersheds of different branches provides a data foundation for further image processing of liver segments.

[0003] In related technologies, when analyzing the watersheds corresponding to different branches of the portal vein, a medical image including the liver and portal vein can be obtained first. Then, doctors or technicians mark the starting and ending points of each branch of the portal vein based on their experience. Then, the liver segments supplied by each branch are delineated, and finally, the size of each branch, each liver segment, and the watershed corresponding to each branch are obtained.

[0004] However, the above-mentioned technologies have the problem of being complex to operate. Summary of the Invention

[0005] Therefore, it is necessary to provide a method, apparatus, device, storage medium, and program product for determining a target watershed that can reduce the operational complexity of calculating the watershed, in order to address the above-mentioned technical problems.

[0006] Firstly, this application provides a method for determining a target watershed, the method comprising:

[0007] The test point selected by the user on the test vessel in at least one candidate vessel has a relative positional relationship with the preset test tissue.

[0008] Based on the test point and the test vessel, determine the target vessel corresponding to the end of the test vessel from the test point;

[0009] Calculate the tissue extent corresponding to the target blood vessel in the tissue to be tested to obtain the target watershed.

[0010] In one embodiment, the determination of the at least one candidate blood vessel includes:

[0011] According to the obtained original image, a first mask image of each sub-tissue in the to-be-tested tissue and a second mask image of the blood vessels are determined; the original image includes the to-be-tested tissue and the blood vessels;

[0012] According to the second mask image, a blood vessel tree corresponding to the blood vessels is constructed; the blood vessel tree includes a main blood vessel and at least one branch blood vessel;

[0013] According to the overlapping information between the main blood vessel and the at least one branch blood vessel and the first mask image, the main blood vessel and the at least one branch blood vessel are classified and named to obtain at least one candidate blood vessel.

[0014] In one embodiment, according to the second mask image, the blood vessel tree corresponding to the blood vessels is constructed, including:

[0015] The center line of the blood vessels in the second mask image is extracted to obtain a center line mask image corresponding to the center line of the blood vessels;

[0016] According to the center line mask image, the main blood vessel and the at least one branch blood vessel of the blood vessels are detected to determine the blood vessel tree corresponding to the blood vessels.

[0017] In one embodiment, according to the center line mask image, the main blood vessel and the at least one branch blood vessel of the blood vessels are detected to determine the blood vessel tree corresponding to the blood vessels, including:

[0018] According to the center line mask image, an undirected graph corresponding to the center line of the blood vessels is constructed; the undirected graph is composed of at least one node constituting the center line of the blood vessels;

[0019] According to the overlapping information between the undirected graph and the first mask image, a target node connected inside and outside the to-be-tested tissue in the undirected graph is determined;

[0020] According to the target node, the main blood vessel and the at least one branch blood vessel of the blood vessels are detected to determine the blood vessel tree corresponding to the blood vessels.

[0021] In one embodiment, according to the target node, the main blood vessel and the at least one branch blood vessel of the blood vessels are detected to determine the blood vessel tree corresponding to the blood vessels, including:

[0022] According to the target node, at least one node is divided to obtain a first node inside the to-be-tested tissue and determine a first direction into the to-be-tested tissue;

[0023] A tracking operation is performed, including: taking the target node as a root node or a parent node, tracking along the first direction, and taking a first node adjacent to the root node or the parent node as a child node;

[0024] The child node is taken as a new parent node, and the execution tracking operation is returned until each of the first nodes has a corresponding parent node, the trunk blood vessel and the at least one branch blood vessel are determined, and the blood vessel tree diagram is obtained.

[0025] In one of the embodiments, the level division and naming of the trunk blood vessel and the at least one branch blood vessel according to the overlap information between each of the trunk blood vessel and the at least one branch blood vessel and the first mask image to obtain at least one candidate blood vessel includes:

[0026] The level of the trunk blood vessel is determined as the first level according to the overlap information between the trunk blood vessel and the first mask image, and the trunk blood vessel is named;

[0027] According to the overlap information between the at least one branch blood vessel and the first mask image, the levels of branch blood vessels lower than the trunk blood vessel are determined from the at least one branch blood vessel in a bottom-up manner, and each of the levels of branch blood vessels is named;

[0028] The named trunk blood vessel and the named levels of branch blood vessels are taken as candidate blood vessels to obtain at least one candidate blood vessel.

[0029] In one of the embodiments, the level division of the at least one branch blood vessel according to the overlap information between the at least one branch blood vessel and the first mask image in a bottom-up manner to determine the levels of branch blood vessels lower than the trunk blood vessel includes:

[0030] The distal branch of each branch blood vessel is obtained;

[0031] The blood vessel distance between the distal branch of each branch blood vessel and the trunk blood vessel is calculated according to the overlap information between the distal branch of the at least one branch blood vessel and the first mask image in a bottom-up manner;

[0032] The at least one branch blood vessel is divided into levels according to the blood vessel distance of each branch blood vessel to determine the levels of branch blood vessels.

[0033] In one of the embodiments, the calculation of the tissue range of the target blood vessel in the to-be-measured tissue to obtain the target flow field includes:

[0034] The first shortest distance from each point in the to-be-measured tissue to the target blood vessel is calculated according to the position information of the target blood vessel and the position information of each point in the to-be-measured tissue;

[0035] The non-target blood vessel in the at least one candidate blood vessel is determined according to the target blood vessel, and the second shortest distance from each point in the to-be-measured tissue to the non-target blood vessel is calculated;

[0036] Determine a target point in the to-be-tested tissue according to the first shortest distance and the second shortest distance, and take the tissue range formed by the target point as the target flow region.

[0037] In a second aspect, the present application further provides a target flow region determination device, which comprises:

[0038] a to-be-tested point acquisition module, configured to acquire a to-be-tested point selected by a user on a to-be-tested blood vessel in at least one candidate blood vessel, wherein the at least one candidate blood vessel has a relative position relationship with a preset to-be-tested tissue;

[0039] a target blood vessel determination module, configured to determine a target blood vessel corresponding to a to-be-tested point and an end of a to-be-tested blood vessel according to the to-be-tested point and the to-be-tested blood vessel;

[0040] a target flow region determination module, configured to calculate a tissue range corresponding to the target blood vessel in the to-be-tested tissue, and obtain a target flow region.

[0041] In a third aspect, the present application further provides a computer device, which comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the following steps when executing the computer program:

[0042] acquire a to-be-tested point selected by a user on a to-be-tested blood vessel in at least one candidate blood vessel, wherein the at least one candidate blood vessel has a relative position relationship with a preset to-be-tested tissue;

[0043] determine a target blood vessel corresponding to a to-be-tested point and an end of a to-be-tested blood vessel according to the to-be-tested point and the to-be-tested blood vessel;

[0044] calculate a tissue range corresponding to the target blood vessel in the to-be-tested tissue, and obtain a target flow region.

[0045] In a fourth aspect, the present application further provides a computer readable storage medium, which stores a computer program, and the computer program realizes the following steps when executed by a processor:

[0046] acquire a to-be-tested point selected by a user on a to-be-tested blood vessel in at least one candidate blood vessel, wherein the at least one candidate blood vessel has a relative position relationship with a preset to-be-tested tissue;

[0047] determine a target blood vessel corresponding to a to-be-tested point and an end of a to-be-tested blood vessel according to the to-be-tested point and the to-be-tested blood vessel;

[0048] calculate a tissue range corresponding to the target blood vessel in the to-be-tested tissue, and obtain a target flow region.

[0049] In a fifth aspect, the present application further provides a computer program product, which comprises a computer program, and the computer program realizes the following steps when executed by a processor:

[0050] obtaining a to-be-measured point selected by the user on a to-be-measured blood vessel in the at least one candidate blood vessel, the at least one candidate blood vessel having a relative positional relationship with the preset to-be-measured tissue;

[0051] determining a target blood vessel corresponding to a to-be-measured point and a to-be-measured blood vessel, the to-be-measured point being selected by the user on the to-be-measured blood vessel, the to-be-measured blood vessel being in the at least one candidate blood vessel, the at least one candidate blood vessel having a relative positional relationship with the preset to-be-measured tissue;

[0052] calculating a tissue range corresponding to the target blood vessel in the to-be-measured tissue, to obtain a target flow region.

[0053] The target flow region determination method, device, equipment, storage medium, and program product, by selecting a to-be-measured point on a to-be-measured blood vessel in a candidate blood vessel by the user and obtaining the to-be-measured point, then determining a target blood vessel between the to-be-measured point and an end of the to-be-measured blood vessel, calculating a tissue range corresponding to the target blood vessel in the to-be-measured tissue, and obtaining a target flow region, wherein the candidate blood vessel has a relative positional relationship with the to-be-measured tissue. In this method, the target blood vessel can be obtained after the user selects the to-be-measured point, and the corresponding target flow region can be calculated, so that the interaction between the user and the background can be realized, and the user only needs to select the to-be-measured point, and the background can quickly calculate the target flow region of the target blood vessel, so that the calculation process of the target flow region can be simplified, that is, the operation complexity of the target flow region calculation process can be reduced. BRIEF DESCRIPTION OF DRAWINGS

[0054] Figure 1 An application environment diagram of the target flow region determination method in one embodiment;

[0055] Figure 2 A flowchart of the target flow region determination method in one embodiment;

[0056] Figure 3 A flowchart of the target flow region determination method in another embodiment;

[0057] Figure 4 A flowchart of the target flow region determination method in another embodiment;

[0058] Figure 5 An example diagram of the liver in the liver direction in another embodiment;

[0059] Figure 6 A flowchart of the target flow region determination method in another embodiment;

[0060] Figure 7 An example diagram of the liver and each branch blood vessel in another embodiment;

[0061] Figure 8 A flowchart of the target flow region determination method in another embodiment;

[0062] Figure 9 An example diagram of a watershed in a liver calculated in another embodiment;

[0063] Figure 10 An example diagram of interaction between a client and a server in another embodiment;

[0064] Figure 11 A structural block diagram of a target watershed determination apparatus in one embodiment;

[0065] Figure 12 An internal structural diagram of a computer device in one embodiment. DETAILED DESCRIPTION

[0066] In order to make the purposes, technical solutions and advantages of the present application clearer, further detailed description will be made to the present application in combination with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application.

[0067] The target watershed determination method provided by the embodiments of the present application can be applied in an application environment as shown in Figure 1 . The client 102 and the server 104 can interact with each other, for example, a user inputs data on the client 102 by means of mouse clicking, etc., then the client 102 can acquire the data and transmit it to the server 104, so that the server 104 can process the data; the server 104 can also transmit the processed data to the client 102 and display it to the user on the client 102. The client 102 and the server 104 herein can be application software installed on a computer device, and the client 102 and the server 104 can be installed on one computer device or on two computer devices respectively, and the computer device herein can be a terminal or a server, which is not limited in particular.

[0068] In one embodiment, as shown in Figure 2 , a target watershed determination method is provided, which will be described by taking the computer device (specifically, the server 104) in Figure 1 as an example. The method can include the following steps:

[0069] S202, acquiring a to-be-measured point selected by a user on a to-be-measured blood vessel in at least one candidate blood vessel; the at least one candidate blood vessel has a relative position relationship with a preset to-be-measured tissue.

[0070] In this step, the at least one candidate blood vessel is a blood vessel after pre-classification and naming, which can be a blood vessel in a liver, for example, a portal vein and its branches, or a blood vessel in a heart, for example, a coronary vessel and its branches, or other blood vessels, which are not limited herein.

[0071] For example, the candidate blood vessel is a blood vessel in the liver, the tissue to be measured can be the liver, and the liver and the blood vessel in the liver have a relative positional relationship, which can be the specific position of the blood vessel into the liver, etc. For example, the candidate blood vessel is a blood vessel in the heart, the tissue to be measured can be the heart, and the heart and the blood vessel in the heart have a relative positional relationship, which can be the specific position of the blood vessel into the heart, etc.

[0072] Specifically, the blood vessels in the tissue to be measured can be pre-processed for grading and naming, etc., to obtain at least one candidate blood vessel; then the at least one candidate blood vessel can be displayed on the display interface of the computer device, i.e., on the client; then the user can click on the at least one candidate blood vessel through a mouse or the like, so that the computer device can obtain the point selected by the user, which is denoted as a measured point. Through the measured point selected by the user, the computer device can also know which blood vessel in the candidate blood vessel the measured point is in through the pre-processing of the grading and naming of the candidate blood vessel, which can be denoted as a measured blood vessel. Here, the computer device can specifically obtain the position information of the measured point, which can be the position information relative to the tissue to be measured, or the position information relative to the candidate blood vessel and the measured blood vessel, or other cases.

[0073] In addition, for the measured point selected by the user, the measured point can be displayed on the display interface, or not, which can be determined by the user.

[0074] S204, according to the measured point and the measured blood vessel, determining a target blood vessel corresponding between the measured point and the end of the measured blood vessel.

[0075] In this step, after the measured point and the measured blood vessel are determined, the direction of the measured blood vessel from the origin to the end can also be obtained, and then the position information of the measured point can be taken as the starting point to traverse to the end of the measured blood vessel, to obtain all points between the measured point and the end of the measured blood vessel, which constitute the target blood vessel. At the same time, the position information of each point in the target blood vessel can also be obtained during the traversal.

[0076] S206, calculating the tissue range corresponding to the target blood vessel in the tissue to be measured, to obtain a target drainage area.

[0077] The drainage area refers to the tissue range that can be supported by the blood vessel in the tissue to be measured, which has a relative positional relationship with the blood vessel. By obtaining the drainage area corresponding to the blood vessel, the next step of image analysis and processing can be facilitated.

[0078] In this step, the computer device can also obtain the position information of each point in the to-be-tested tissue in advance, and then calculates, by using the position information of each point in the target blood vessel and the position information of each point in the to-be-tested tissue, and in combination with the relative position relationship between the at least one candidate blood vessel and the to-be-tested tissue, in which part of the to-be-tested tissue each point in the target blood vessel falls into, so as to obtain the corresponding tissue range of the target blood vessel in the to-be-tested tissue, and the tissue range is the target flow field.

[0079] It should be noted that the to-be-tested tissue and the at least one candidate blood vessel are in the same coordinate system, and therefore the target blood vessel in the candidate blood vessel and the to-be-tested tissue can be calculated at the same time to improve the calculation efficiency.

[0080] In the target flow field determination method, the user selects a to-be-tested point on the to-be-tested blood vessel in the candidate blood vessel and obtains the to-be-tested point, and then determines the target blood vessel between the to-be-tested point and the end of the to-be-tested blood vessel, calculates the corresponding tissue range of the target blood vessel in the to-be-tested tissue, and obtains the target flow field; the candidate blood vessel has a relative position relationship with the to-be-tested tissue. In this method, the target blood vessel can be obtained after the user selects the to-be-tested point, and the corresponding target flow field can be calculated, so that the interaction between the user and the background can be realized, and the user only needs to select the to-be-tested point, and the background can quickly calculate the target flow field of the target blood vessel, so that the calculation process of the target flow field can be simplified, that is, the operation complexity of the target flow field calculation process can be reduced.

[0081] In the above embodiment, it is mentioned that the user can select a to-be-tested point in the candidate blood vessel, and the candidate blood vessel can be a blood vessel that is pre-divided into levels and named. The following embodiment describes a possible implementation of the pre-determined candidate blood vessel.

[0082] In another embodiment, another target flow field determination method is provided, which is based on the above embodiment, as shown in Figure 3 The determination method of the at least one candidate blood vessel can include the following steps:

[0083] S302, according to the obtained original image, determine the first mask image of each sub-organ in the to-be-tested tissue and the second mask image of the blood vessel; the original image includes the to-be-tested tissue and the blood vessel.

[0084] In this step, the to-be-tested tissue and the blood vessel of the to-be-tested object can be scanned in one phase or multiple phases, and the scanning data in the corresponding phase can be reconstructed to obtain the original image in the corresponding phase. The original image here can be an original image in any modality, which is not limited here.

[0085] After obtaining the original images of the corresponding phases, an optimal phase can be selected, and then the original images under the optimal phase are subjected to segmentation processing of the to-be-tested tissue and each sub-tissue therein, to obtain a segmentation image of the to-be-tested tissue and a segmentation image of each sub-tissue in the to-be-tested tissue. Here, the segmentation image of each sub-tissue in the to-be-tested tissue can be denoted as a first mask image, which can be a multi-valued mask image, and the specific values can be determined according to the number of sub-tissues. In general, each sub-tissue and the background can be distinguished through the first mask image.

[0086] Similarly, the original images under the optimal phase can also be subjected to segmentation processing of each branch in the blood vessels, to obtain a segmentation image of each branch in the blood vessels, denoted as a second mask image. The second mask image can also be a multi-valued mask image, and the specific multi-values can also be determined according to the number of each branch in the blood vessels. In general, each branch in the blood vessels can be distinguished through the second mask image. It should be noted that each branch in the blood vessels segmented here is a blood vessel without grading and naming, i.e., the main blood vessels and branch blood vessels cannot be distinguished from the second mask image.

[0087] For example, assuming that the to-be-tested tissue here is a liver, the mask image of the liver, the mask image of each segment in the liver (for example, the mask image of the Couinaud eight segments of the liver), and the mask images of the blood vessels such as the portal vein, the hepatic vein, and the hepatic artery and their branches can be segmented.

[0088] In addition, any convolutional neural network can be used for segmentation processing when segmenting the original images, which is not limited here.

[0089] In S304, a blood vessel tree corresponding to the blood vessels is constructed according to the second mask image. The blood vessel tree includes the main blood vessels and at least one branch blood vessel.

[0090] In this step, for the process of constructing the blood vessel tree from the mask images of each branch of the blood vessels, as an optional embodiment, the following steps can be used:

[0091] In step A1, the center line of the blood vessels in the second mask image is extracted to obtain a center line mask image corresponding to the center line of the blood vessels.

[0092] In step A2, the main blood vessels and at least one branch blood vessel of the blood vessels are detected according to the center line mask image, to determine the blood vessel tree corresponding to the blood vessels.

[0093] In the second mask image, the various branch vessels of the blood vessel are segmented, and each branch vessel also includes the main vessel. The centerline of each branch vessel can be extracted using a centerline extraction algorithm, such as skeletonization algorithm. Alternatively, the centerline of each branch vessel can be extracted directly from the second mask image, thus obtaining a mask image of the centerlines of each branch vessel, denoted as the centerline mask image.

[0094] After obtaining the masked images of the centerlines of each branch vessel, the vessels within the tissue under test can be selected from the branch vessels by using the overlap information between the centerlines of each branch vessel and the first masked images of each sub-tissue of the tissue under test. Simultaneously, combining the definition of the main branch vessels (e.g., the origin of a main branch is generally the point connecting the inside and outside of the tissue under test), the main branch vessels (i.e., the trunk vessels) are first selected from the branch vessels. All vessels other than the main branch vessels are considered branch vessels. Then, the trunk vessels and branch vessels can be connected to form a tree-like structure, obtaining a vascular tree diagram. This vascular tree diagram can include the positional information of each point within the trunk vessels and branch vessels, as well as the relative positional relationships between the trunk vessels and branch vessels.

[0095] Here, the center line in the second mask image is extracted before blood vessel detection. Since the center line has a smaller data volume and a clearer phase position compared to the blood vessel segmentation result, the accuracy and efficiency of constructing the blood vessel dendrogram can be improved.

[0096] S306, based on the overlap information between the main blood vessel and at least one branch blood vessel and the first mask image, classify the main blood vessel and at least one branch blood vessel into levels and perform naming processing to obtain at least one candidate blood vessel.

[0097] In this step, after obtaining the main and branch vessels as described above, the positional information of each point in each of the main and branch vessels can be obtained. Similarly, the positional information of each point in each sub-tissue of the tissue under test in the first mask image can also be obtained. Then, the intersection of the positional information of each point in each of the main and branch vessels with the positional information of each point in each sub-tissue of the tissue under test can be performed to determine which points in the main and branch vessels fall into the sub-tissues of the tissue under test. Combining the relative positional relationship between the vessels and the tissue under test, as well as prior knowledge, the main and branch vessels are identified and specifically graded and named. After that, the graded and named candidate vessels can be obtained.

[0098] The hierarchy and naming here can be, for example, that the main blood vessel is a first-level blood vessel and is given a corresponding name, and other branch blood vessels can be second-level, third-level, or even more levels of blood vessels, etc., and are given corresponding names.

[0099] In this embodiment, the mask images of each sub-tissue in the to-be-tested tissue and the mask images of each branch in the blood vessel are obtained through the original image, and a blood vessel tree diagram including the main blood vessel and the branch blood vessel is constructed accordingly. Thereafter, the main blood vessel and the branch blood vessel in the blood vessel tree diagram can be hierarchized and named to obtain at least one candidate blood vessel. Thus, the process of hierarchizing and naming the blood vessel through the obtained mask images and the blood vessel tree diagram is simple and accurate, and therefore the accuracy and efficiency of obtaining the candidate blood vessel can be improved.

[0100] The above embodiment mentions that the corresponding blood vessel tree diagram can be obtained through the center line mask image of the blood vessel. The following embodiment describes the specific determination process of the blood vessel tree diagram.

[0101] In another embodiment, another target flow field determination method is provided, which is based on the above-mentioned embodiment, as shown in Figure 4 The above-mentioned step A2 can include the following steps:

[0102] S402, constructing an undirected graph corresponding to the center line of the blood vessel according to the center line mask image; the undirected graph is composed of at least one node constituting the center line of the blood vessel.

[0103] In this step, the center line in the obtained center line mask image can be composed of a plurality of discrete points or a plurality of discrete line segments, and the line segments and points can be recorded as nodes.

[0104] After obtaining each node on the center line, an undirected graph corresponding to the center line can be constructed through the association relationship between each node. The nodes in the undirected graph can be divided into two categories. If the two ends of a node are adjacent to other nodes, it can be called an adjacent node or a connecting node. The nodes other than the adjacent nodes or connecting nodes in the center line can be terminal nodes, and one end of the terminal node has no adjacent node or connecting node.

[0105] After the nodes are divided, the nodes can be connected according to the association relationship between the nodes to obtain the undirected graph of the center line.

[0106] S404, determining the target node in the undirected graph that connects the inside and outside of the to-be-tested tissue according to the overlapping information between the undirected graph and the first mask image.

[0107] In this step, after the construction of the undirected graph, the position information of each node in the undirected graph can also be obtained. Then, the position information of each point in each sub-organism of the to-be-tested organism can be used to determine which point in the undirected graph is located at the edge of the to-be-tested organism, i.e., the point connecting the inside and outside of the to-be-tested organism, which is recorded as a target node. Through the target node, each branch in the blood vessel can be quickly classified.

[0108] Here, when the intersection determination is performed on the position information of each node in the undirected graph and the position information of each point in each sub-organism of the to-be-tested organism, the position information of the point located at the edge of the to-be-tested organism can be obtained through the position information of each point in each sub-organism of the to-be-tested organism. Then, it is determined whether there is a point in the position information of each node in the undirected graph that is the same as the position information of the point located at the edge of the to-be-tested organism. If there is, the point can be used as the point in the undirected graph located at the edge of the to-be-tested organism.

[0109] For example, assuming that the to-be-tested organism is a liver, the point connecting the inside and outside of the to-be-tested organism in the undirected graph can be a point connecting the inside and outside of the liver.

[0110] S406, detecting the main blood vessel and at least one branch blood vessel of the blood vessel according to the target node, and determining a blood vessel tree diagram corresponding to the blood vessel.

[0111] In this step, after the target node connecting the inside and outside of the to-be-tested organism is determined, the detection of the main stem and branches in the blood vessel can be performed. As an optional embodiment, the detection can be performed through the following steps:

[0112] Step B1, dividing at least one node according to the target node to obtain a first node in the to-be-tested organism and determine a first direction into the to-be-tested organism.

[0113] Step B2, performing a tracking operation, wherein the tracking operation includes: taking the target node as a root node or a parent node, tracking along the first direction, and taking a first node adjacent to the root node or the parent node as a child node.

[0114] Step B3, taking the child node as a new parent node, returning to perform the tracking operation until each first node has a corresponding parent node, determining the main blood vessel and at least one branch blood vessel, and obtaining a blood vessel tree diagram.

[0115] Wherein, after obtaining the target node, the nodes in the undirected graph of the center line can be divided by the target node, specifically, the nodes in the undirected graph of the center line located inside the to-be-tested tissue can be recorded as first nodes, and the nodes in the undirected graph of the center line located outside the to-be-tested tissue can be recorded as second nodes (this second node can be ignored or removed); at the same time, the direction of the target node towards the first node can be taken as the first direction of entering the to-be-tested tissue. For example, taking the to-be-tested tissue as the liver, referring to FIG. 8, the points in the circle in the figure are the target nodes connecting the inside and outside of the liver, and the direction towards the liver, i.e. the direction indicated by the arrow in the figure, is the first direction here. Figure 5

[0116] After that, the target node can be taken as a root node or an initial parent node, and the reverse tracking mode can be used to track adjacent nodes in the first direction. If an adjacent node is tracked, the tracked adjacent node can be taken as a child node of the root node or the initial parent node. Then, the child node can be taken as a parent node for the next tracking, and whether there is an adjacent node can be tracked. If there is, it can be taken as a child node of the parent node. Then, the child node can be taken as a parent node for the next tracking, and the tracking can continue until there is no adjacent node of the parent node, i.e. there is no child node. In this way, the end of the blood vessel can be found, and the tracking of a blood vessel branch is completed, and a blood vessel branch can be obtained.

[0117] According to this reverse tracking mode, other blood vessel branches can be tracked to obtain other blood vessel branches, and finally the obtained blood vessel branches can be combined to obtain the constructed blood vessel tree graph.

[0118] For example, taking the to-be-tested tissue as the liver, the blood vessels therein can be portal vein vessels, and generally, each branch of the portal vein vessel has certain prior information with the Couinaud liver eight segments of the liver, for example, the left main stem / left branch (LPV) overlaps with the II and III segments in the Couinaud liver eight segments, the right front (RA) overlaps with the V and VIII segments in the Couinaud liver eight segments, and the right back (RP) overlaps with the VI and VII segments in the Couinaud liver eight segments.

[0119] ​After that, the three main branches of LPV, RP and RA can be located by means of the overlapped prior information and the method of reverse tracing. Taking LPV as an example, through the parent-child node relationship of each node in the portal vein tree, the terminal branch (the two directions of the blood vessel segment, only one direction has a neighbor, and the other direction neighbor is empty) can be obtained, and then the terminal branch in the range of II and III segments in the Couinaud liver eight segment segmentation result is found, one of them is selected, the parent node is found reversely, then the parent node of the parent node is found, and the iteration is repeated for many times until the parent node of a certain parent node is equal to the main branch node, and the iteration stops, at this time, the parent node is the root node of the left main stem / left branch LPV. In the same way, the root nodes of RA and RP can be located. Generally, the two child nodes of the main branch are the right main stem RM and the left main stem LPV, and the parent node of RA and RP is the right main stem of RM. By using these related information, it can be quickly judged whether RM exists or not, and the branch node of RM can be quickly located when RM exists. Finally, the vascular tree diagram is obtained through the detected main stem blood vessels and branch blood vessels.

[0120] In the embodiment, the undirected graph including at least one node is constructed according to the center line mask image, the target node connecting the inside and outside of the to-be-detected tissue is determined through the overlapping information between the undirected graph and the mask image of each sub-tissue of the to-be-detected tissue, and the main stem blood vessels and branch blood vessels are detected according to the target node. By connecting the target node inside and outside the to-be-detected tissue to detect the main stem blood vessels and branch blood vessels, the obtained main stem blood vessels and branch blood vessels can be more accurate, and the constructed vascular tree diagram can be more accurate. In addition, the nodes in the undirected graph are divided into the first node inside the to-be-detected tissue and the first direction determined to enter the to-be-detected tissue through the target node, and then the main stem blood vessels and branch blood vessels can be obtained through node tracking according to the first node inside the to-be-detected tissue and the first direction determined to enter the to-be-detected tissue. By detecting the main stem blood vessels and branch blood vessels through the first node inside the to-be-detected tissue and the first direction determined to enter the to-be-detected tissue, the number of detected nodes is reduced, so that the detection efficiency can be improved, and the detected nodes are determined inside the to-be-detected tissue, so that the nodes outside the to-be-detected tissue are not blindly detected, and the detection accuracy can be improved.

[0121] The above embodiment mentions that the blood vessels can be classified and named, and the following embodiment describes a possible implementation of the process.

[0122] In another embodiment, another target flow field determination method is provided, which is based on the above-mentioned embodiment, as shown in Figure 6 The S306 can include the following steps:

[0123] S502, according to the overlapping information between the main stem blood vessels and the first mask image, the level of the main stem blood vessels is determined as the first level, and the main stem blood vessels are named.

[0124] In this step, the example is that the tissue to be detected is the liver, and the blood vessels therein can be the portal vein blood vessels, see Figure 7 The example diagram of the overlap of the main blood vessels and their branch blood vessels in different cases with the liver, wherein A, P, S, I, L, and R are the orientation information in the software, respectively representing the front, back, up, down, left, and right orientations. After detecting the main blood vessels, the main blood vessels can be obtained through the overlap information of each point in the main blood vessels and each sub-tissue of the tissue to be detected (the overlap information can be the prior information mentioned above), and the main blood vessels are set as the first-level blood vessels, and the main blood vessels are named according to the actual blood vessels.

[0125] S504, according to the overlap information between the at least one branch blood vessel and the first mask image, the lower branch blood vessels than the main blood vessels are determined from the at least one branch blood vessel in a bottom-up manner, and each branch blood vessel is named.

[0126] In this step, when classifying and naming each branch blood vessel, as an optional embodiment, the following steps can be used:

[0127] Step C1, obtaining the terminal branch of each branch blood vessel.

[0128] Step C2, according to the overlap information between the terminal branch of the at least one branch blood vessel and the first mask image, calculating the blood vessel distance between the terminal branch of each branch blood vessel and the main blood vessel in a bottom-up manner.

[0129] Step C3, according to the blood vessel distance of each branch blood vessel, classifying the at least one branch blood vessel into different levels to determine the branch blood vessels of each level.

[0130] After obtaining each branch blood vessel, the branch blood vessels can be obtained through the overlap information of each point in the branch blood vessels and each sub-tissue of the tissue to be detected (the overlap information can be the prior information mentioned above). Then the terminal branch of each branch blood vessel can be obtained, specifically the position information of the node of the terminal branch can be obtained, and the position information of the main blood vessel can also be obtained, and the blood vessel distance between the terminal branch of each branch blood vessel and the main blood vessel can be calculated through the position information of the branch blood vessel, the overlap information (i.e. the position overlap information) of each sub-tissue of the tissue to be detected, and the position information of the main blood vessel. The blood vessel distance can be specifically the number of nodes passed between the terminal branch of each branch blood vessel and the main blood vessel.

[0131] Afterwards, each sub-organism in the to-be-tested organism corresponding to each branch blood vessel can be obtained through the overlapping information of each point in the branch blood vessel and each sub-organism of the to-be-tested organism (the overlapping information can be the prior information mentioned above); afterwards, the distal branch of the branch blood vessel covered by the sub-organism of the to-be-tested organism can be obtained, and one distal branch farthest from the main blood vessel is selected (the farthest definition is that the number of parent nodes from the distal branch to the main blood vessel is the most) through the blood vessel distance calculated above; then, the parent node which is the main blood vessel in these parent nodes is obtained, that is, the starting node of the secondary branch blood vessel, and the naming is performed according to the actual blood vessel. According to this bottom-up manner, the classification and naming of all branch blood vessels can be realized.

[0132] It should be noted that when classifying and naming each branch blood vessel, the classification and naming are equivalent, that is, the classification determines the naming, or the naming determines the classification. For example, the to-be-tested organism is the liver, and the blood vessel is the portal vein, so after determining that the RA is the right anterior branch, the corresponding classification can also be determined, that is, it corresponds to a tertiary blood vessel.

[0133] For example, taking the to-be-tested organism as the liver, the blood vessel can be the portal vein, and the blood vessel example diagram shown in FIG. 4 can be continuously referred to. Figure 7 After the left main blood vessel LPV, the right main blood vessel RM, the right anterior blood vessel RA, and the right posterior blood vessel RP are obtained, the classification and naming of these blood vessels can be performed. For example, the main branch can be set as a primary blood vessel, the LM and the RM are secondary blood vessels, and the RA and the RP are tertiary blood vessels. Afterwards, the branch blood vessels under the LPV, the RA, and the RP can be further classified and named. Taking the LPV as an example, the structural characteristics of the LPV in the data set can be investigated, and a suitable classification and naming method can be established. For example, a series of conditions can be constructed according to the changes of the blood vessel radius of the parent and child branches at the branch, the blood vessel length, and other parameters, and when the conditions are met, the branch level changes. The number of branch levels can be adjusted according to the number of liver segments to be classified. Of course, the classification result set here also allows the user to correct it on the client 102.

[0134] S506, the main blood vessel after naming and each level of blood vessel after naming are taken as candidate blood vessels, and at least one candidate blood vessel is obtained.

[0135] In this step, after the classification and naming of the main blood vessel and the branch blood vessel are performed, the main blood vessel and the branch blood vessel after the classification and naming are taken as candidate blood vessels.

[0136] In this embodiment, the first mask image of the main blood vessels, branch blood vessels and each sub-tissue of the to-be-measured tissue is used to classify and name each branch blood vessel in a bottom-up manner, and a candidate blood vessel is obtained. In this way, accurate blood vessel classification and naming can be ensured, whether the blood vessels are normal or have large variations, that is, the accuracy of the candidate blood vessel after classification and naming can be improved.

[0137] The following embodiment mainly describes the implementation process of calculating the target flow region corresponding to the to-be-measured tissue.

[0138] In another embodiment, another target flow region determination method is provided, which is based on the above-mentioned embodiment, as shown in Figure 8 The S206 can include the following steps:

[0139] S602, according to the position information of the target blood vessel and the position information of each point in the to-be-measured tissue, calculating the first shortest distance from each point in the to-be-measured tissue to the target blood vessel.

[0140] In this step, after obtaining the to-be-measured point and the to-be-measured blood vessel, the blood vessel branch where the to-be-measured point is located and all sub-level branches to the periphery can be obtained, that is, the target blood vessel can be obtained. Then, the position information of each point in the target blood vessel can also be obtained. Similarly, the position information of each point in the to-be-measured tissue can also be obtained.

[0141] Then, for each point in the to-be-measured tissue, the shortest distance from each point in the to-be-measured tissue to the target blood vessel can be calculated, and the shortest distance calculated for each point in the to-be-measured tissue can be recorded as the first shortest distance. Here, when calculating, taking one point in the to-be-measured tissue as an example, the Euclidean distance between the point and each point in the target tissue can be calculated to obtain a plurality of Euclidean distances, and the shortest distance can be selected from the plurality of Euclidean distances. The shortest distance is the first shortest distance corresponding to the point. The other points in the to-be-measured tissue can be calculated in the same way.

[0142] S604, according to the target blood vessel, determining at least one non-target blood vessel in the candidate blood vessel, and calculating the second shortest distance from each point in the to-be-measured tissue to the non-target blood vessel.

[0143] In this step, after selecting the target blood vessel from the candidate blood vessel, the candidate blood vessel other than the target blood vessel can also be determined, which can be recorded as the non-target blood vessel.

[0144] Then, the shortest distance from each point in the to-be-measured tissue to the non-target blood vessel can be calculated in the same way as calculating the first shortest distance, and the shortest distance calculated for each point in the to-be-measured tissue can be recorded as the second shortest distance.

[0145] S606, determining a target point in the tissue under test according to the first shortest distance and the second shortest distance, and taking the tissue range formed by the target point as a target flow region.

[0146] In this step, after obtaining the first shortest distance from each point in the tissue under test to the target blood vessel, the first distance can be compared with a threshold condition, and the first shortest distance satisfying the threshold condition can be obtained. Correspondingly, the target point in the tissue under test corresponding to the first shortest distance satisfying the threshold condition can also be obtained.

[0147] Similarly, after obtaining the second shortest distance from each point in the tissue under test to the non-target blood vessel, the second distance can be compared with a threshold condition, and the second shortest distance satisfying the threshold condition can be obtained. Correspondingly, the target point in the tissue under test corresponding to the second shortest distance satisfying the threshold condition can also be obtained.

[0148] Then, the range formed by the target point in the tissue under test can be taken as the target flow region corresponding to the target blood vessel.

[0149] For example, the tissue under test is a liver, and the blood vessel is a portal vein and its branches. Figure 9 The target flow region calculated in different cases can be represented by different colors, so that the user can quickly distinguish different flow regions.

[0150] In this embodiment, the shortest distance between each point in the tissue under test and the target blood vessel and the non-target blood vessel is calculated, the target point in the tissue under test is determined by the shortest distance, and the target flow region is obtained. In this way, the target flow region can be quickly and accurately calculated by the shortest distance, and the efficiency and accuracy of obtaining the target flow region are improved.

[0151] The following gives a specific embodiment to illustrate the technical scheme of the present application. Taking a server and a client as an example, on the basis of the above embodiment, the method can include the following steps:

[0152] S1, the server determines a first mask image of each sub-organ in the tissue under test and a second mask image of the blood vessel according to the obtained original image; the original image includes the tissue under test and the blood vessel;

[0153] S2, the server extracts the center line of the blood vessel in the second mask image to obtain a center line mask image corresponding to the center line of the blood vessel;

[0154] S3, the server constructs an undirected graph corresponding to the center line of the blood vessel according to the center line mask image; the undirected graph is composed of at least one node constituting the center line of the blood vessel;

[0155] S4, the server determines the target node connected to the inside and outside of the to-be-tested tissue in the undirected graph according to the overlapping information between the undirected graph and the first mask image;

[0156] S5, the server divides at least one node according to the target node, obtains a first node in the to-be-tested tissue, and determines a first direction into the to-be-tested tissue;

[0157] S6, the server performs a tracking operation, and the tracking operation includes: taking the target node as a root node or a parent node, tracking along the first direction, and taking a first node adjacent to the root node or the parent node as a child node;

[0158] S7, the server takes the child node as a new parent node, returns to perform the tracking operation in S6 until each first node has a corresponding parent node, determines a main blood vessel and at least one branch blood vessel, and obtains a blood vessel tree diagram;

[0159] S8, the server determines the level of the main blood vessel as a first level and names the main blood vessel according to the overlapping information between the main blood vessel and the first mask image;

[0160] S9, the server obtains a distal branch of each branch blood vessel;

[0161] S10, the server calculates a blood vessel distance between the distal branch of each branch blood vessel and the main blood vessel in a bottom-up manner according to the overlapping information between the distal branch of each branch blood vessel and the first mask image;

[0162] S11, the server divides at least one branch blood vessel according to the blood vessel distance of each branch blood vessel, and determines branch blood vessels at different levels;

[0163] S12, the server takes the named main blood vessel and the named branch blood vessels at different levels as candidate blood vessels, and obtains at least one candidate blood vessel;

[0164] S13, the user selects a to-be-tested point in at least one candidate blood vessel on a display interface of the client, and the server obtains the to-be-tested point selected by the user on the to-be-tested blood vessel in the at least one candidate blood vessel; the at least one candidate blood vessel has a relative position relationship with the preset to-be-tested tissue;

[0165] S14, the server determines a target blood vessel corresponding to the to-be-tested point to the end of the to-be-tested blood vessel according to the to-be-tested point and the to-be-tested blood vessel;

[0166] S15, the server calculates first shortest distances from each point in the to-be-tested tissue to the target blood vessel according to position information of the target blood vessel and position information of each point in the to-be-tested tissue;

[0167] S16, the server determines a non-target blood vessel in the at least one candidate blood vessel according to the target blood vessel, and calculates second shortest distances from each point in the tissue to be measured to the non-target blood vessel;

[0168] S17, the server determines a target point in the tissue to be measured according to the first shortest distance and the second shortest distance, and regards a tissue range formed by the target point as a target watershed.

[0169] Taking the tissue to be measured as a liver and the blood vessels as portal vein blood vessels and their branches as an example, the above-mentioned service end and client flow can refer to Figure 10 , in which simple steps performed by the service end and the client are given. As can be seen, the service end can quickly classify and name the portal vein blood vessels in the above-mentioned manner, and then the user can click on at least one candidate blood vessel through a mouse or the like to obtain a user-selected point to be measured and display it for the user to view. Then, the service end can quickly calculate a target watershed corresponding to the target blood vessel.

[0170] In addition, it should be noted that the classification and naming methods in the present embodiment can also be applied to blood vessels such as hepatic veins and hepatic arteries. The watershed calculation method can also be applied to tissues to be measured other than the liver, which is not limited here.

[0171] It should be understood that although each step in the flowchart involved in each of the above-mentioned embodiments is displayed in sequence according to the arrow, these steps are not necessarily executed in the order indicated by the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other orders. Moreover, as mentioned above, at least part of the steps in the flowchart involved in each of the above-mentioned embodiments can include multiple steps or stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily sequential, but can be executed in rotation or alternation with at least part of other steps or steps or stages in other steps.

[0172] Based on the same inventive concept, the present embodiment also provides a target watershed determination device for implementing the above-mentioned target watershed determination method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above-mentioned method, so the specific limitations in one or more target watershed determination device embodiments provided below can refer to the limitations of the target watershed determination method in the above text, which will not be repeated here.

[0173] In one embodiment, as Figure 11 shown, a target watershed determination device is provided, comprising: a point to be measured acquisition module, a target blood vessel determination module and a target watershed determination module, wherein:

[0174] a to-be-measured point acquisition module configured to acquire a to-be-measured point selected by the user on a to-be-measured blood vessel in the at least one candidate blood vessel, the at least one candidate blood vessel having a relative positional relationship with the preset to-be-measured tissue;

[0175] a target blood vessel determination module configured to determine a target blood vessel corresponding to a segment between the to-be-measured point and an end of the to-be-measured blood vessel according to the to-be-measured point and the to-be-measured blood vessel;

[0176] a target flow field determination module configured to calculate a tissue range corresponding to the target blood vessel in the to-be-measured tissue to obtain a target flow field.

[0177] In another embodiment, another target flow field determination apparatus is provided, which comprises a candidate blood vessel determination module in addition to the apparatus in the above embodiment, and the candidate blood vessel determination module can comprise:

[0178] a mask image determination unit configured to determine a first mask image of each sub-tissue in the to-be-measured tissue and a second mask image of the blood vessels according to an acquired original image, the original image comprising the to-be-measured tissue and the blood vessels;

[0179] a tree graph construction unit configured to construct a blood vessel tree graph corresponding to the blood vessels according to the second mask image, the blood vessel tree graph comprising a main blood vessel and at least one branch blood vessel;

[0180] a hierarchical and naming unit configured to perform hierarchical division and naming processing on the main blood vessel and the at least one branch blood vessel according to overlapping information between the main blood vessel and the at least one branch blood vessel and the first mask image to obtain the at least one candidate blood vessel.

[0181] Optionally, the tree graph construction unit can comprise:

[0182] an extraction sub-unit configured to perform center line extraction on the blood vessels in the second mask image to obtain a center line mask image corresponding to the center line of the blood vessels;

[0183] a blood vessel detection sub-unit configured to detect the main blood vessel and the at least one branch blood vessel according to the center line mask image to determine the blood vessel tree graph corresponding to the blood vessels.

[0184] In another embodiment, another target flow region determination apparatus is provided, which is based on the above-mentioned embodiment, and the blood vessel detection subunit is specifically configured to construct an undirected graph corresponding to the center line of the blood vessel according to the center line mask image; the undirected graph is composed of at least one node constituting the center line of the blood vessel; target nodes connected to the inside and outside of the tissue to be detected are determined according to the overlapping information between the undirected graph and the first mask image; and the main blood vessel and the at least one branch blood vessel are detected according to the target nodes, so as to determine the blood vessel tree graph corresponding to the blood vessel.

[0185] Optionally, the blood vessel detection subunit is specifically configured to divide the at least one node according to the target nodes, to obtain first nodes in the tissue to be detected and to determine a first direction into the tissue to be detected; and a tracking operation is performed, which includes taking the target node as a root node or a parent node, tracking along the first direction, and taking the first node adjacent to the root node or the parent node as a child node; and taking the child node as a new parent node, returning to perform the tracking operation until each first node has a corresponding parent node, so as to determine the main blood vessel and the at least one branch blood vessel and obtain the blood vessel tree graph.

[0186] In another embodiment, another target flow region determination apparatus is provided, which is based on the above-mentioned embodiment, and the hierarchical and naming unit can include:

[0187] a first hierarchical naming subunit configured to determine the level of the main blood vessel as the first level and to name the main blood vessel according to the overlapping information between the main blood vessel and the first mask image;

[0188] a second hierarchical naming subunit configured to determine each branch blood vessel at a level lower than the main blood vessel from the at least one branch blood vessel and to name each branch blood vessel according to the overlapping information between the at least one branch blood vessel and the first mask image in a bottom-up manner;

[0189] a candidate blood vessel determination subunit configured to take the named main blood vessel and the named branch blood vessels at each level as candidate blood vessels, so as to obtain at least one candidate blood vessel.

[0190] Optionally, the second hierarchical naming subunit is specifically configured to obtain a distal branch of each branch blood vessel; to calculate the blood vessel distance between the distal branch of each branch blood vessel and the main blood vessel according to the overlapping information between the distal branch of each branch blood vessel and the first mask image in a bottom-up manner; and to divide the at least one branch blood vessel into branch blood vessels at different levels according to the blood vessel distance of each branch blood vessel.

[0191] In another embodiment, another target flow region determination apparatus is provided, which is based on the above-mentioned embodiment, and the target flow region determination module can include:

[0192] The first distance calculation unit is used to calculate the first shortest distance from each point in the tissue to the target blood vessel based on the location information of the target blood vessel and the location information of each point in the tissue to be tested.

[0193] The second distance calculation unit is used to determine at least one non-target vessel in the candidate vessels based on the target vessel, and to calculate the second shortest distance from each point in the tissue to be tested to the non-target vessel.

[0194] The target watershed determination unit is used to determine the target points in the tissue to be measured based on the first shortest distance and the second shortest distance, and to take the tissue range formed by the target points as the target watershed.

[0195] Each module in the aforementioned target watershed determination device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0196] In one embodiment, a computer device is provided, which may be a server or a terminal. Taking a terminal as an example, its internal structure diagram may be as follows: Figure 12 As shown, the computer device includes a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a method for determining a target watershed. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the computer device casing, or an external keyboard, touchpad, or mouse.

[0197] Those skilled in the art will understand that Figure 12 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0198] In one embodiment, a computer device is provided, comprising a memory and a processor, the memory storing a computer program, and the processor implementing the following steps when executing the computer program:

[0199] obtaining a to-be-measured point selected by a user on a to-be-measured blood vessel in at least one candidate blood vessel; the at least one candidate blood vessel has a relative positional relationship with a preset to-be-measured tissue; determining a target blood vessel corresponding to a to-be-measured point to an end of a to-be-measured blood vessel according to the to-be-measured point and the to-be-measured blood vessel; calculating a tissue range corresponding to the target blood vessel in the to-be-measured tissue to obtain a target flow domain.

[0200] In one embodiment, the processor further implements the following steps when executing the computer program:

[0201] determining a first mask image of each sub-tissue in the to-be-measured tissue and a second mask image of the blood vessels according to the obtained original image; the original image includes the to-be-measured tissue and the blood vessels; constructing a blood vessel tree diagram corresponding to the blood vessels according to the second mask image; the blood vessel tree diagram includes a main blood vessel and at least one branch blood vessel; performing level division and naming processing on the main blood vessel and the at least one branch blood vessel according to the overlapping information between the main blood vessel and the at least one branch blood vessel and the first mask image, to obtain at least one candidate blood vessel.

[0202] In one embodiment, the processor further implements the following steps when executing the computer program:

[0203] extracting a center line of the blood vessels in the second mask image to obtain a center line mask image corresponding to the center line of the blood vessels; detecting the main blood vessel and the at least one branch blood vessel of the blood vessels according to the center line mask image to determine the blood vessel tree diagram corresponding to the blood vessels.

[0204] In one embodiment, the processor further implements the following steps when executing the computer program:

[0205] constructing an undirected graph corresponding to the center line of the blood vessels according to the center line mask image; the undirected graph is composed of at least one node constituting the center line of the blood vessels; determining a target node connecting inside and outside of the to-be-measured tissue in the undirected graph according to the overlapping information between the undirected graph and the first mask image; detecting the main blood vessel and the at least one branch blood vessel of the blood vessels according to the target node to determine the blood vessel tree diagram corresponding to the blood vessels.

[0206] In one embodiment, the processor further implements the following steps when executing the computer program:

[0207] According to the target node, at least one node is divided, a first node in the to-be-tested tissue is obtained, and a first direction into the to-be-tested tissue is determined; a tracking operation is performed, and the tracking operation includes: taking the target node as a root node or a parent node, tracking along the first direction, and taking a first node adjacent to the root node or the parent node as a child node; taking the child node as a new parent node, returning to perform the tracking operation until each first node has a corresponding parent node, a main blood vessel and at least one branch blood vessel are determined, and a blood vessel tree diagram is obtained.

[0208] In one embodiment, the processor, when executing the computer program, also implements the following steps:

[0209] According to the intersection information between the main blood vessel and the first mask image, the level of the main blood vessel is determined as a first level, and the main blood vessel is named; according to the intersection information between the at least one branch blood vessel and the first mask image, in a bottom-up manner, each branch blood vessel lower than the main blood vessel is determined from the at least one branch blood vessel, and each branch blood vessel is named respectively; the named main blood vessel and the named each branch blood vessel are taken as candidate blood vessels, and at least one candidate blood vessel is obtained.

[0210] In one embodiment, the processor, when executing the computer program, also implements the following steps:

[0211] The distal branch of each branch blood vessel is obtained; in a bottom-up manner, according to the intersection information between the distal branch of each branch blood vessel and the first mask image, the blood vessel distance between the distal branch of each branch blood vessel and the main blood vessel is calculated; according to the blood vessel distance of each branch blood vessel, the at least one branch blood vessel is divided into levels, and each branch blood vessel is determined.

[0212] In one embodiment, the processor, when executing the computer program, also implements the following steps:

[0213] According to the position information of the target blood vessel and the position information of each point in the to-be-tested tissue, the first shortest distance from each point in the to-be-tested tissue to the target blood vessel is calculated; according to the target blood vessel, a non-target blood vessel in the at least one candidate blood vessel is determined, and the second shortest distance from each point in the to-be-tested tissue to the non-target blood vessel is calculated; according to the first shortest distance and the second shortest distance, a target point in the to-be-tested tissue is determined, and an organization range formed by the target point is taken as a target drainage area.

[0214] In one embodiment, a computer readable storage medium is provided, and the computer readable storage medium stores a computer program. The computer program is executed by a processor to implement the following steps:

[0215] acquire a to-be-measured point selected by a user on a to-be-measured blood vessel in at least one candidate blood vessel; the at least one candidate blood vessel has a relative position relationship with a preset to-be-measured tissue; according to the to-be-measured point and the to-be-measured blood vessel, a target blood vessel corresponding to a to-be-measured point-to-end distance of the to-be-measured blood vessel is determined; a tissue range corresponding to the target blood vessel in the to-be-measured tissue is calculated to obtain a target flow region.

[0216] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0217] According to the acquired original image, a first mask image of each sub-tissue in the to-be-measured tissue and a second mask image of the blood vessels are determined; the original image includes the to-be-measured tissue and the blood vessels; according to the second mask image, a blood vessel tree diagram corresponding to the blood vessels is constructed; the blood vessel tree diagram includes a main blood vessel and at least one branch blood vessel; according to the overlapping information between the main blood vessel and the at least one branch blood vessel and the first mask image, the main blood vessel and the at least one branch blood vessel are classified and named to obtain at least one candidate blood vessel.

[0218] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0219] The center line of the blood vessels in the second mask image is extracted to obtain a center line mask image corresponding to the center line of the blood vessels; according to the center line mask image, the main blood vessel and the at least one branch blood vessel of the blood vessels are detected to determine a blood vessel tree diagram corresponding to the blood vessels.

[0220] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0221] According to the center line mask image, an undirected graph corresponding to the center line of the blood vessels is constructed; the undirected graph is composed of at least one node constituting the center line of the blood vessels; according to the overlapping information between the undirected graph and the first mask image, a target node connecting inside and outside the to-be-measured tissue in the undirected graph is determined; according to the target node, the main blood vessel and the at least one branch blood vessel of the blood vessels are detected to determine a blood vessel tree diagram corresponding to the blood vessels.

[0222] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0223] According to the target node, at least one node is divided, a first node in the to-be-tested tissue is obtained, and a first direction into the to-be-tested tissue is determined; a tracking operation is performed, and the tracking operation includes: taking the target node as a root node or a parent node, tracking along the first direction, and taking a first node adjacent to the root node or the parent node as a child node; taking the child node as a new parent node, returning to perform the tracking operation until each first node has a corresponding parent node, a main blood vessel and at least one branch blood vessel are determined, and a blood vessel tree diagram is obtained.

[0224] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0225] According to the intersection information between the main blood vessel and the first mask image, the level of the main blood vessel is determined as a first level, and the main blood vessel is named; according to the intersection information between the at least one branch blood vessel and the first mask image, in a bottom-up manner, each branch blood vessel lower than the main blood vessel is determined from the at least one branch blood vessel, and each branch blood vessel is named respectively; the named main blood vessel and the named each branch blood vessel are taken as candidate blood vessels, and at least one candidate blood vessel is obtained.

[0226] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0227] The distal branch of each branch blood vessel is obtained; in a bottom-up manner, according to the intersection information between the distal branch of each branch blood vessel and the first mask image, the blood vessel distance between the distal branch of each branch blood vessel and the main blood vessel is calculated; according to the blood vessel distance of each branch blood vessel, the at least one branch blood vessel is divided into levels, and each branch blood vessel is determined.

[0228] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0229] According to the position information of the target blood vessel and the position information of each point in the to-be-tested tissue, the first shortest distance from each point in the to-be-tested tissue to the target blood vessel is calculated; according to the target blood vessel, a non-target blood vessel in the at least one candidate blood vessel is determined, and the second shortest distance from each point in the to-be-tested tissue to the non-target blood vessel is calculated; according to the first shortest distance and the second shortest distance, a target point in the to-be-tested tissue is determined, and a tissue range formed by the target point is taken as a target watershed.

[0230] In one embodiment, a computer program product is provided, including a computer program, which, when executed by a processor, implements the following steps:

[0231] Acquire a to-be-measured point selected by a user on a to-be-measured blood vessel in at least one candidate blood vessel; the at least one candidate blood vessel has a relative positional relationship with a preset to-be-measured tissue; determine a target blood vessel corresponding to a to-be-measured point to an end of a to-be-measured blood vessel according to the to-be-measured point and the to-be-measured blood vessel; calculate a tissue range corresponding to the target blood vessel in the to-be-measured tissue to obtain a target flow region.

[0232] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0233] According to the acquired original image, determine a first mask image of each sub-tissue in the to-be-measured tissue and a second mask image of the blood vessels; the original image includes the to-be-measured tissue and the blood vessels; construct a blood vessel tree graph corresponding to the blood vessels according to the second mask image; the blood vessel tree graph includes a main blood vessel and at least one branch blood vessel; perform level division and naming processing on the main blood vessel and the at least one branch blood vessel according to the overlapping information between the main blood vessel and the at least one branch blood vessel and the first mask image, to obtain at least one candidate blood vessel.

[0234] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0235] Extract a center line of the blood vessels in the second mask image to obtain a center line mask image corresponding to the center line of the blood vessels; detect the main blood vessel and the at least one branch blood vessel of the blood vessels according to the center line mask image to determine a blood vessel tree graph corresponding to the blood vessels.

[0236] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0237] Construct an undirected graph corresponding to the center line of the blood vessels according to the center line mask image; the undirected graph is composed of at least one node constituting the center line of the blood vessels; determine a target node connected inside and outside the to-be-measured tissue in the undirected graph according to the overlapping information between the undirected graph and the first mask image; detect the main blood vessel and the at least one branch blood vessel of the blood vessels according to the target node to determine a blood vessel tree graph corresponding to the blood vessels.

[0238] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0239] According to the target node, at least one node is divided to obtain a first node in the to-be-tested tissue, and a first direction entering the to-be-tested tissue is determined; a tracking operation is performed, and the tracking operation includes: taking the target node as a root node or a parent node, tracking along the first direction, and taking a first node adjacent to the root node or the parent node as a child node; taking the child node as a new parent node, returning to perform the tracking operation until each first node has a corresponding parent node, a main blood vessel and at least one branch blood vessel are determined, and a blood vessel tree diagram is obtained.

[0240] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0241] According to the intersection information between the main blood vessel and the first mask image, the level of the main blood vessel is determined as a first level, and the main blood vessel is named; according to the intersection information between the at least one branch blood vessel and the first mask image, in a bottom-up manner, each branch blood vessel lower than the main blood vessel is determined from the at least one branch blood vessel, and each branch blood vessel is named respectively; the named main blood vessel and the named each branch blood vessel are taken as candidate blood vessels, and at least one candidate blood vessel is obtained.

[0242] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0243] The distal branch of each branch blood vessel is obtained; in a bottom-up manner, according to the intersection information between the distal branch of each branch blood vessel and the first mask image, the blood vessel distance between the distal branch of each branch blood vessel and the main blood vessel is calculated; according to the blood vessel distance of each branch blood vessel, the at least one branch blood vessel is divided into levels to determine each branch blood vessel.

[0244] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0245] According to the position information of the target blood vessel and the position information of each point in the to-be-tested tissue, the first shortest distance from each point in the to-be-tested tissue to the target blood vessel is calculated; according to the target blood vessel, a non-target blood vessel in the at least one candidate blood vessel is determined, and the second shortest distance from each point in the to-be-tested tissue to the non-target blood vessel is calculated; according to the first shortest distance and the second shortest distance, a target point in the to-be-tested tissue is determined, and a tissue range formed by the target point is taken as a target watershed.

[0246] It should be noted that the data involved in the present application (including but not limited to data for analysis, stored data, displayed data, etc.) are all data authorized by all parties.

[0247] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric memory (Ferroelectric Random Access Memory, FRAM), phase change memory (Phase Change Memory, PCM), graphene memory, etc. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc. The database involved in the embodiments provided in 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 block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose 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., without being limited thereto.

[0248] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist contradictory, it should be considered as the scope of the present application.

[0249] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent of the present application. It should be noted that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are within the scope of protection of the present application. Therefore, the scope of protection of the present application should be subject to the appended claims.

Claims

1. A method for determining a target watershed, characterized in that, The method includes: The test point selected by the user on the test vessel in at least one candidate vessel has a relative positional relationship with the preset test tissue. Based on the test point and the test vessel, determine the target vessel corresponding to the end of the test vessel from the test point; Calculate the tissue extent corresponding to the target blood vessel in the tissue to be tested to obtain the target watershed; The step of calculating the tissue extent corresponding to the target blood vessel in the tissue to be tested includes: Obtain the location information of each point in the tissue to be tested; Based on the location information of each point in the target blood vessel, the location information of each point in the tissue to be tested, and the relative positional relationship between the at least one candidate blood vessel and the tissue to be tested, the set of locations in the tissue to be tested corresponding to each point in the target blood vessel is determined, and the set of locations is determined as the tissue range corresponding to the target blood vessel in the tissue to be tested.

2. The method according to claim 1, characterized in that, The determination of the at least one candidate blood vessel includes: Based on the acquired original image, a first mask image of each sub-tissue in the tissue under test and a second mask image of blood vessels are determined; the original image includes the tissue under test and the blood vessels. Based on the second mask image, a vascular tree diagram corresponding to the blood vessel is constructed; the vascular tree diagram includes a main trunk blood vessel and at least one branch blood vessel; Based on the overlap information between the main blood vessel and at least one branch blood vessel and the first mask image, the main blood vessel and at least one branch blood vessel are classified and named to obtain at least one candidate blood vessel.

3. The method according to claim 2, characterized in that, The step of constructing a vascular tree diagram corresponding to the blood vessels based on the second mask image includes: The centerline of the blood vessel in the second mask image is extracted to obtain the centerline mask image corresponding to the centerline of the blood vessel. Based on the centerline mask image, the main trunk vessels and at least one branch vessel of the blood vessel are detected to determine the corresponding vascular tree diagram.

4. The method according to claim 3, characterized in that, The step of detecting the main trunk vessels and at least one branch vessel of the blood vessel based on the centerline mask image to determine the corresponding vascular tree diagram includes: Based on the centerline mask image, an undirected graph corresponding to the centerline of the blood vessel is constructed; the undirected graph is composed of at least one node constituting the centerline of the blood vessel. Based on the overlap information between the undirected graph and the first mask image, the target node in the undirected graph that connects the inside and outside of the tissue to be tested is determined; Based on the target node, the main trunk vessels and at least one branch vessel of the blood vessel are detected to determine the corresponding blood vessel tree diagram.

5. The method according to claim 4, characterized in that, The step of detecting the main trunk vessels and at least one branch vessel of the blood vessel based on the target node to determine the corresponding vascular tree diagram includes: The at least one node is divided according to the target node to obtain the first node within the organization to be tested, and to determine the first direction for entering the organization to be tested; Perform a tracing operation, the tracing operation including: taking the target node as the root node or parent node, tracing along the first direction, and taking the first node adjacent to the root node or parent node as the child node; The child node is used as the new parent node, and the tracing operation is repeated until all the first nodes have a corresponding parent node. The main blood vessel and at least one branch blood vessel are determined, and the blood vessel tree diagram is obtained.

6. The method according to any one of claims 2-5, characterized in that, The step of classifying and naming the main blood vessel and at least one branch blood vessel according to the overlap information between the main blood vessel and at least one branch blood vessel and the first mask image to obtain the at least one candidate blood vessel includes: Based on the overlap information between the main blood vessel and the first mask image, the level of the main blood vessel is determined to be Level 1 and the main blood vessel is named. Based on the overlap information between the at least one branch vessel and the first mask image, branch vessels of all levels below the main vessel are identified from the at least one branch vessel in a bottom-up manner, and the branch vessels of each level are named respectively. The named main blood vessel and the named blood vessels at each level are all used as candidate blood vessels to obtain at least one candidate blood vessel.

7. A target watershed determination device, characterized in that, The device includes: The test point acquisition module is used to acquire the test point selected by the user on the test vessel in at least one candidate vessel; the at least one candidate vessel has a relative positional relationship with the preset test tissue; The target vessel determination module is used to determine the target vessel corresponding to the end of the target vessel from the test point to the test vessel based on the test point and the test vessel. The target watershed determination module is used to calculate the tissue range corresponding to the target blood vessel in the tissue to be tested, and obtain the target watershed. The aforementioned target watershed determination module is specifically used to acquire the location information of each point in the tissue to be tested; based on the location information of each point in the target blood vessel, the location information of each point in the tissue to be tested, and the relative positional relationship between the at least one candidate blood vessel and the tissue to be tested, it determines the set of locations in the tissue to be tested corresponding to each point in the target blood vessel, and determines the set of locations as the tissue range corresponding to the target blood vessel in the tissue to be tested.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

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 6.

10. A computer program product, comprising a computer program, 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 6.

Images