Vascular structure root node extraction method and device, computer equipment and storage medium

Abstract

The invention relates to a vessel structure root node extraction method and device, computer equipment and a storage medium. The method comprises the following steps: carrying out center line extraction on a bronchus segmentation mask of a target object to obtain a bronchus center line corresponding to the bronchus segmentation mask; calculating each bronchial segment label value of the bronchial central line, and searching each bronchial central line end point corresponding to the bronchial central line; the bronchial segment label value represents the type of the bronchial segment structure; and screening out at least one vessel structure root node in the bronchial segment segmentation mask from the endpoints of the bronchial center lines according to the bronchial segment label values. By adopting the method, the segmentation accuracy of the lung image can be improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method, apparatus, computer equipment, storage medium and computer program product for extracting root nodes of vascular structures. Background Art

[0002] There are usually two methods for the problem of segmenting lung images. The first method uses an end-to-end lung image segmentation algorithm based on deep learning. This method does not require a complex image processing process, but the results lack interpretability and are not convenient to optimize or adjust when the results are not ideal. The second method is to determine the lung image segmentation interface by combining the segmentation information of arterial or venous images, or by combining the segmentation information of bronchial images. However, there is a defect in both methods. The lung image segmentation interface may not pass through the root node of the vascular segmentation, resulting in low segmentation accuracy of the lung image. Summary of the invention

[0003] Based on this, it is necessary to provide a method, apparatus, computer device, computer-readable storage medium and computer program product for extracting root nodes of vascular structures that can improve the segmentation accuracy of lung images in order to solve the above technical problems.

[0004] In the first aspect, the present application provides a method for extracting a root node of a vascular structure. The method comprises: performing centerline extraction on a bronchial segmentation mask of a target object to obtain a bronchial centerline corresponding to the bronchial segmentation mask; calculating each bronchial segmentation label value of the bronchial centerline, and searching for each bronchial centerline endpoint corresponding to the bronchial centerline; the bronchial segmentation label value represents the type of bronchial segmentation structure; and according to each bronchial segmentation label value, screening out at least one vascular structure root node in the bronchial segmentation mask from each bronchial centerline endpoint.

[0005] In the second aspect, the present application also provides a vascular structure root node extraction device. The device includes: a bronchial centerline extraction module, which is used to extract the centerline of the bronchial segmentation mask of the target object to obtain the bronchial centerline corresponding to the bronchial segmentation mask; a bronchial parameter acquisition module, which is used to calculate the label values ​​of each bronchial segmentation of the bronchial centerline, and search for each bronchial centerline endpoint corresponding to the bronchial centerline; the bronchial segmentation label value represents the type of bronchial segmentation structure; a vascular structure root node identification module, which is used to filter out at least one vascular structure root node in the bronchial segmentation mask from each bronchial centerline endpoint according to each bronchial segmentation label value.

[0006] In a third aspect, the present application also provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program: extracting the centerline of the bronchial segmentation mask of the target object to obtain the bronchial centerline corresponding to the bronchial segmentation mask; calculating the label values ​​of each bronchial segment of the bronchial centerline, and searching for each bronchial centerline endpoint corresponding to the bronchial centerline; the bronchial segmentation label value represents the type of bronchial segmentation structure; according to each bronchial segmentation label value, screening out at least one vascular structure root node in the bronchial segmentation mask from each bronchial centerline endpoint.

[0007] In a fourth aspect, the present application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented: performing centerline extraction on the bronchial segmentation mask of the target object to obtain the bronchial centerline corresponding to the bronchial segmentation mask; calculating each bronchial segmentation label value of the bronchial centerline, and searching for each bronchial centerline endpoint corresponding to the bronchial centerline; the bronchial segmentation label value represents the type of bronchial segmentation structure; according to each bronchial segmentation label value, screening out at least one vascular structure root node in the bronchial segmentation mask from each bronchial centerline endpoint.

[0008] In a fifth aspect, the present application also provides a computer program product. The computer program product includes a computer program, which implements the following steps when executed by a processor: extracting the centerline of the bronchial segmentation mask of the target object to obtain the bronchial centerline corresponding to the bronchial segmentation mask; calculating the label values ​​of each bronchial segment of the bronchial centerline, and searching for each bronchial centerline endpoint corresponding to the bronchial centerline; the bronchial segmentation label value represents the type of bronchial segmentation structure; according to each bronchial segmentation label value, screening out at least one vascular structure root node in the bronchial segmentation mask from each bronchial centerline endpoint.

[0009] The above-mentioned method, device, computer equipment, storage medium and computer program product for extracting the root node of a vascular structure perform centerline extraction on the bronchial segmentation mask of the target object to obtain the bronchial centerline corresponding to the bronchial segmentation mask; calculate the label values ​​of each bronchial segment of the bronchial centerline, and search for each bronchial centerline endpoint corresponding to the bronchial centerline; the bronchial segmentation label value represents the type of bronchial segmentation structure; and according to each bronchial segmentation label value, screen out at least one vascular structure root node in the bronchial segmentation mask from each bronchial centerline endpoint.

[0010] By extracting the bronchial centerline corresponding to the bronchial segmentation mask of the target object and combining it with the bronchial segmentation labeling algorithm, the various bronchial segmentation structures corresponding to the bronchial segmentation mask are determined; further based on each bronchial segmentation structure, a regular bifurcation point extraction algorithm is used to search and identify the vascular structure root node. In the case of complex structures such as bronchi and blood vessels, the common vascular structure root node of at least one bronchial segmentation structure can be accurately extracted, which helps to improve the segmentation accuracy of lung images. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 This is an application environment diagram of a vascular structure root node extraction method according to an embodiment;

[0012] Figure 2 A schematic diagram of a flow chart of a method for extracting a root node of a vascular structure in an embodiment;

[0013] Figure 3 A schematic diagram of a flow chart of a method for determining a bronchial segmentation label value in one embodiment;

[0014] Figure 4 A schematic flow chart of a method for obtaining a bronchial sub-segment centerline endpoint in one embodiment;

[0015] Figure 5 A schematic diagram of a flow chart of a method for obtaining a vascular structure root node in one embodiment;

[0016] Figure 6 A schematic diagram of a flow chart of a method for determining a bronchial segmentation label value in another embodiment;

[0017] Figure 7 It is a flowchart of a method for obtaining a first vascular structure root node in one embodiment;

[0018] Figure 8 is a flow chart of a method for obtaining a second vascular structure root node in one embodiment;

[0019] Fig. 9 is a flow chart of a method for obtaining a root node of a third vascular structure in one embodiment;

[0020] Fig.10 is a schematic flow chart of a method for obtaining a fourth vascular structure root node in an embodiment;

[0021] Fig.11 is a schematic diagram of a bronchial segmentation mask in one embodiment;

[0022] Fig.12 A schematic diagram of the extraction result of the bronchial centerline in one embodiment;

[0023] Fig.13 A schematic diagram of various markings for points on a center line in one embodiment;

[0024] Fig.14 A schematic diagram of calculating bronchial segment label values ​​in one embodiment;

[0025] Fig.15 A schematic diagram of screening results of vascular structure root nodes in one embodiment;

[0026] Fig.16 A schematic diagram of the first type of vascular structure root node screening result in one embodiment;

[0027] Fig.17 This is a diagram showing the first type of vascular structure root node screening result in one embodiment;

[0028] Fig.18 A schematic diagram of the second type of vascular structure root node screening result in one embodiment;

[0029] Fig.19 This is a diagram showing the screening results of the second vascular structure root node in one embodiment;

[0030] Fig. 20 A schematic diagram of the screening results of the root node of the third vascular structure in one embodiment;

[0031] Fig.21 A diagram showing the screening results of the root node of the third vascular structure in one embodiment;

[0032] Fig. 22 A schematic diagram of the screening results of the root nodes of the fourth type of vascular structure in one embodiment;

[0033] Fig.23 This is a diagram showing the screening results of the root node of the fourth vascular structure in one embodiment;

[0034] Fig.24 A schematic diagram of the screening results of the root nodes of the vascular structures of different lung segments in one embodiment;

[0035] Fig.25 It is a structural block diagram of a vascular structure root node extraction device in one embodiment;

[0036] Fig.26 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0037] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction 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.

[0038] The present invention provides a method for extracting a vascular structure root node, which can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The server 104 obtains the bronchial segmentation mask of the target object from the terminal 102, and further uses the server 104 to extract the centerline of the bronchial segmentation mask of the target object to obtain the bronchial centerline corresponding to the bronchial segmentation mask; calculates the label value of each bronchial segment of the bronchial centerline, and searches for each bronchial centerline endpoint corresponding to the bronchial centerline; the bronchial segmentation label value characterizes the type of bronchial segmentation structure; according to each bronchial segmentation label value, at least one vascular structure root node in the bronchial segmentation mask is screened out from each bronchial centerline endpoint. Among them, the terminal 102 can be, but is not limited to, various Internet of Things devices and portable wearable devices. The server 104 can be implemented with an independent server or a server cluster consisting of multiple servers.

[0039] In one embodiment, Figure 2 As shown, a method for extracting the root node of a vascular structure is provided, and the method is applied to Figure 1 The server in the example is used to illustrate the following steps:

[0040] Step 202 : extracting the centerline of the bronchus segmentation mask of the target object to obtain the bronchus centerline corresponding to the bronchus segmentation mask.

[0041] The target object may be a human or an animal, wherein the target object includes a region of interest, such as the liver, kidneys, lungs, etc. in the human body.

[0042] The bronchial segmentation mask may be an image obtained by segmenting the bronchial segmentation structure of the lungs, wherein the bronchial segmentation mask is a binary image composed of 0 and 1, such as Fig.11 The bronchial segmentation mask shown can be defined by specifying data values, data ranges, finite or infinite values, regions of interest, and annotation files. The bronchial segmentation mask is as follows: Fig.11 As shown, in some embodiments, Fig.11 The main part of the bronchial segmentation mask shown can be represented by color A (ie, any color, such as yellow, red, green, blue, black, etc.), while other bronchial segment structures can be represented by colors different from color A.

[0043] The bronchial centerline may be a set of center points obtained by traversing the axes of each bronchus in the bronchial segmentation mask.

[0044] Specifically, the server 104 obtains the bronchial segmentation mask of the target object from the terminal 102. The server 104 extracts the centerline of the bronchial segmentation mask by using an algorithm based on topological refinement to obtain the bronchial centerline corresponding to the bronchial segmentation mask. The extraction result of the bronchial centerline is as follows: Fig.12 The bronchial centerline shown, in some embodiments, as Fig.12 The bronchial centerline of the main trunk can be represented by color A (i.e., any color, such as yellow, red, green, blue, black, etc.), while the bronchial centerlines of other bronchial segment structures can be represented by colors different from color A; multiple center points on the axis of the bronchus, including the centerline endpoints, centerline bifurcation points, and centerline continuity points of the bronchial centerline. Fig.13 In the example of the bronchus shown, it can be seen that the axis of the bronchus has a centerline, the end of the centerline is the centerline endpoint, the point where the centerline bifurcates is the centerline bifurcation point, and the continuous points on the centerline are the centerline continuous points; further, as Fig.13 Various marks on the centerline points are shown. The number of bifurcation point connections at the centerline endpoints is 1, the number of bifurcation point connections at the centerline bifurcation points is greater than or equal to 3, and the number of bifurcation point connections at the centerline continuous points is 2.

[0045] Step 204, calculating the label value of each bronchial segment of the bronchial centerline, and searching for each bronchial centerline endpoint corresponding to the bronchial centerline.

[0046] The bronchial segmentation label value may be a description of the type of each bronchial segmentation structure, that is, a description of the different locations of the current bronchial branch structure in the lung anatomy (anatomical position, anatomical knowledge).

[0047] The bronchial centerline endpoints may be the centerline endpoints of each bronchial branch structure, and the number of bifurcation point connections of these endpoints is equal to 1 or greater than or equal to 3.

[0048] Specifically, the bronchial centerline corresponding to the bronchial segmentation mask is taken as the calculation object, and the label value of the centerline corresponding to each bronchial branch structure in the bronchial segmentation mask is calculated, such as Fig.13As shown in FIG, the mask of the bronchial branch label value is obtained by calculating the label value of the center line of each bronchial branch structure. Since the label value of the center line corresponding to each bronchial branch structure indicates the type of the corresponding bronchial branch structure, each bronchial branch structure is classified according to the label value of the center line corresponding to each bronchial branch structure, and the bronchial segmentation label value corresponding to each bronchial segmentation structure is determined. The bronchial segmentation label value calculation result of the bronchial segmentation structure is shown in FIG. Fig.14 As shown, in some embodiments, Fig.14 The bronchial segment label value of the main trunk part shown can be represented by color A (i.e., any color, yellow, red, green, blue, black, etc.), while the bronchial segment label values ​​of other bronchial segment structures can be represented by colors different from color A.

[0049] All centerline branches are acquired through the information of the bronchial centerline, and the information of all bronchial branches is counted, including the starting point, end point, curve point, radius and average radius, etc.; that is, all centerline branches are searched through the information of the bronchial centerline to obtain all centerline description points of the bronchial centerline; however, any centerline description point is not an isolated point, so through the positional relationship between any current centerline description point and at least one adjacent centerline description point, the positional characteristics of the current centerline description point (centerline endpoint, centerline bifurcation point and centerline continuous point), as well as the information of the centerline endpoint, the information of the centerline bifurcation point and the information of the centerline continuous point can be determined.

[0050] Step 206: Filter out at least one vascular structure root node in the bronchial segmentation mask from the endpoints of each bronchial centerline according to the label value of each bronchial segment.

[0051] The vascular structure root node may be a bifurcation point at the boundary between two associated bronchial segments in the lung structure.

[0052] Specifically, each bronchial segmentation label value is classified, and the main segmentation label value corresponding to the main trunk and branch segmentation bronchi, as well as the bronchial sub-segment label value corresponding to each bronchial segmentation structure other than the main trunk segmentation label value, are selected. The partial centerline corresponding to the main trunk and branch segmentation bronchi is selected according to the main trunk segmentation label value, and the partial centerline is further searched to obtain the two endpoints of the partial centerline of the main trunk and branch segmentation bronchi; similarly, for any bronchial segmentation structure and the corresponding bronchial sub-segment label value, the partial centerline corresponding to the bronchial segmentation structure is selected according to the bronchial sub-segment label value, and the partial centerline is further searched to obtain the two endpoints of the partial centerline of the bronchial segmentation structure.

[0053] By traversing the overlapping information of all endpoints, the endpoints extracted from the part of the centerline corresponding to the main trunk and branch segmented bronchus and / or the endpoints extracted from the part of the centerline of each bronchial segment structure that have overlaps are used as each target centerline bifurcation point. However, for each target centerline bifurcation point, the number of bifurcation point connections is at least three. Then, for each target centerline bifurcation point, the bronchial segmentation label values ​​corresponding to each bronchi intersecting at the target centerline bifurcation point and the distribution of the main trunk segmentation label values ​​are searched based on the main trunk segmentation label value. When the distribution conforms to the preset bronchial segmentation label distribution, the target centerline bifurcation point is used as the root node of the vascular structure; when the distribution does not conform to the preset bronchial segmentation label distribution, the target centerline bifurcation point is discarded. Fig.15 is the screening result of each vascular structure root node in the bronchial segmentation mask; among them, Fig.15 The white circles in the figure are different root nodes of vascular structures.

[0054] In the above-mentioned method for extracting the root node of the vascular structure, the centerline of the bronchial segmentation mask of the target object is extracted, so as to obtain the bronchial centerline corresponding to the bronchial segmentation mask; the label values ​​of each bronchial segment of the bronchial centerline are calculated, and the endpoints of each bronchial centerline corresponding to the bronchial centerline are searched; the bronchial segmentation label value represents the type of the bronchial segmentation structure; and according to the label values ​​of each bronchial segment, at least one vascular structure root node in the bronchial segmentation mask is screened out from the endpoints of each bronchial centerline.

[0055] By extracting the bronchial centerline corresponding to the bronchial segmentation mask of the target object and combining it with the bronchial segmentation labeling algorithm, the various bronchial segmentation structures corresponding to the bronchial segmentation mask are determined; further based on each bronchial segmentation structure, a regular bifurcation point extraction algorithm is used to search and identify the vascular structure root node. In the case of complex structures such as bronchi and blood vessels, the common vascular structure root node of at least one bronchial segmentation structure can be accurately extracted, which helps to improve the segmentation accuracy of lung images.

[0056] In one embodiment, Figure 3 As shown, the bronchial centerline includes the centerlines of each bronchial branch; the label values ​​of each bronchial segment corresponding to the bronchial centerline are calculated, including:

[0057] Step 302: for any bronchial branch centerline, search for label information of each centerline information point corresponding to the bronchial branch centerline.

[0058] Among them, the bronchial branch centerline can be a part of the centerline of the bronchial branch centerline located in the bronchial branch structure, wherein the bronchial branch structure can be the structural manifestation of each bronchial branch in the lungs in the bronchial topological structure; the bronchial segment structure can be a bronchial segment composed of at least one bronchial branch structure.

[0059] Specifically, in practice, the label values ​​of all points on the centerline corresponding to each bronchial branch structure are generally the same, but different label values ​​may exist at special points on the centerline. Therefore, for any bronchial branch centerline corresponding to a bronchial branch structure, a traversal method is adopted to search the bronchial branch centerline to obtain the label information of each centerline information point of the bronchial branch centerline corresponding to each bronchial branch structure.

[0060] Step 304: collect statistics on the label information of each centerline information point to determine the bronchial branch label value corresponding to the bronchial branch centerline.

[0061] The bronchial branch label value may be a segmentation type that describes each bronchial branch structure, that is, to which bronchial segmentation structure the current bronchial branch structure belongs.

[0062] Specifically, for each centerline information point label information corresponding to any bronchial branch structure, statistics are performed on the label information of each centerline information point, and the label information of the point with the highest proportion of the centerline information points of the bronchial branch centerline corresponding to each bronchial branch structure is used as the bronchial branch label value corresponding to the bronchial branch centerline.

[0063] Step 306: Determine the bronchial segmentation label value corresponding to each bronchial segmentation structure according to the bronchial branch label value corresponding to the center line of each bronchial branch.

[0064] Specifically, because the bronchial branch label value of each bronchial branch structure is used to describe which bronchial segment structure each bronchial branch structure belongs to, the bronchial branch label values ​​of the same category are classified to obtain each bronchial segment label value in the bronchial segment segmentation mask, wherein each bronchial branch label value in the bronchial segment structure is a subset of the bronchial segment label value; the bronchial segment structure and the bronchial segment label value have a corresponding relationship.

[0065] In this embodiment, the bronchial branch label value of each bronchial branch structure is determined by the label information of each centerline information point of the bronchial branch centerline, and the bronchial segment label value is obtained by classifying each bronchial branch label value. The label information of each centerline information point can be accurately classified to ensure the accuracy of extracting the root node of the vascular structure.

[0066] In one embodiment, Figure 4 As shown, the bronchial centerline endpoints corresponding to the bronchial centerline are searched, including:

[0067] Step 402, searching for the bronchial segment centerline corresponding to the trunk segment label value, and obtaining the endpoints of each trunk segment centerline.

[0068] The trunk segment label value may be a description that the bronchial segment structure belongs to the trunk bronchial segment structure.

[0069] The endpoints of the centerline of the trunk segment may be the endpoints of the centerline of the main trunk bronchial segment structure, and the number of bifurcation point connections of these endpoints is equal to 1 or greater than or equal to 3.

[0070] Specifically, the main trunk bronchial segmentation structure is determined by the main trunk bronchial segmentation label value, wherein the main trunk bronchial segmentation structure has a corresponding bronchial segmentation centerline, and the information of the main trunk bronchial segmentation structure, including the starting point, end point, curve point, radius and average radius, etc., is statistically obtained by using the information of the bronchial segmentation centerline corresponding to the main trunk bronchial segmentation structure; that is, by searching the bronchial segmentation centerline corresponding to the main trunk bronchial segmentation structure, the bronchial centerline endpoints of the bronchial segmentation centerline corresponding to the main trunk bronchial segmentation structure are determined in combination with the main trunk bronchial segmentation structure, that is, the centerline endpoints, centerline bifurcation points and centerline continuous points of the bronchial segmentation centerline corresponding to the main trunk bronchial segmentation structure, as well as the information of the centerline endpoints, the information of the centerline bifurcation points and the information of the centerline continuous points are determined.

[0071] Step 404, searching for the bronchial segment centerline corresponding to each bronchial subsegment label value to obtain the centerline endpoint of each bronchial subsegment.

[0072] The bronchial sub-segment label value may describe that each bronchial segment structure belongs to a bronchial sub-segment structure.

[0073] The endpoints of the bronchial sub-segment centerline may be the endpoints of the centerlines of the respective bronchial sub-segment structures, and the number of bifurcation point connections of these endpoints is equal to 1 or greater than or equal to 3.

[0074] Specifically, the corresponding bronchial subsegment structure is determined by each bronchial subsegment label value, wherein each bronchial subsegment structure has a corresponding bronchial segment centerline, and the information of the bronchial segment centerline corresponding to each bronchial subsegment structure is used to count the information of each bronchial subsegment structure, including the starting point, end point, curve point, radius and average radius, etc.; that is, by searching the bronchial segment centerline corresponding to each bronchial subsegment label value, combined with each bronchial subsegment structure, the bronchial centerline endpoints of the bronchial segment centerline corresponding to each bronchial subsegment label value are determined, that is, the centerline endpoints, centerline bifurcation points and centerline continuous points of the bronchial segment centerline corresponding to each bronchial subsegment label value, as well as the information of the centerline endpoints, the information of the centerline bifurcation points and the information of the centerline continuous points are determined.

[0075] In this embodiment, by taking the bronchial segment label value as the unit, searching for the corresponding bronchial segment centerline and determining the centerline endpoint of each bronchial segment label value, the overlap of all centerline endpoints can be accurately obtained, which is beneficial to subsequently reducing the search amount for the target centerline bifurcation point.

[0076] In one embodiment, Figure 5 As shown, according to the label value of each bronchial segment, at least one vascular structure root node in the bronchial segment segmentation mask is selected from the endpoints of each bronchial centerline, including:

[0077] Step 502: The overlapping endpoints of the centerline endpoints of each trunk segment and / or each bronchial sub-segment are used as the target centerline bifurcation points.

[0078] The target centerline bifurcation point may be the coincidence point of the centerline endpoints of different bronchi.

[0079] Specifically, the information of each centerline endpoint is traversed, wherein the centerline endpoint information at least includes the position of the centerline endpoint, the number of bifurcation point connections of the centerline endpoint, the centerline information point label information, etc. The information with the same centerline endpoint is filtered out from multiple centerline endpoints as each target centerline bifurcation point. The target centerline bifurcation point can be an endpoint that coincides with the centerline endpoint of the trunk segment and the centerline endpoint of the bronchial subsegment, or an endpoint that coincides with the centerline endpoint of the bronchial subsegment.

[0080] Step 504: for any target centerline bifurcation point, search for the label values ​​of each bronchial segment constituting the target centerline bifurcation point.

[0081] Specifically, for any target centerline bifurcation point, the number of bifurcation point connections of the target center bifurcation point is determined to obtain a bifurcation point connection number determination result; when the bifurcation point connection number determination result indicates that the number of bifurcation point connections of the target center bifurcation point is greater than or equal to 3, each bronchial segment centerline constituting the target center bifurcation point is searched to obtain a bronchial segment label value. Using the same method as above, at least one bronchial segment label value corresponding to each target centerline bifurcation point can be obtained.

[0082] Step 506: When the label values ​​of each bronchial segment meet the preset bronchial segment label distribution, the target centerline bifurcation point is used as the root node of the vascular structure.

[0083] The preset bronchial segment label distribution may be a distribution situation in which the bronchial segment label values ​​in each lung segment are fixed.

[0084] Specifically, supported by a large amount of clinical data, each segment of each lung has a fixed bronchial segment structure, that is, a fixed distribution of bronchial segment label values. Under the constraint of one of the lung segments, the bronchial segment label values ​​constituting the target centerline bifurcation point are matched with the preset bronchial segment label distribution of the lung segment to obtain the bronchial segment label value matching result. If the bronchial segment label value matching result indicates that the bronchial segment label values ​​constituting the target centerline bifurcation point are completely consistent with the preset bronchial segment label distribution of the lung segment, the target centerline bifurcation point is used as the root node of the vascular structure. If there is more than one target centerline bifurcation point under the constraint of one of the lung segments in the lung, similarly, the bronchial segment label values ​​constituting the target centerline bifurcation point are matched with the preset bronchial segment label distribution of the lung segment to obtain the bronchial segment label value matching result. If the bronchial segment label value matching result indicates that the bronchial segment label values ​​constituting the target centerline bifurcation point completely conform to the preset bronchial segment label distribution of the lung segment, the target centerline bifurcation point is used as the vascular structure root node. For each lung segment in the bronchial segment segmentation mask, the above-mentioned vascular structure root node determination method is used to determine the vascular structure root node in each lung segment.

[0085] In this embodiment, when the target centerline bifurcation point has a label value that conforms to the preset bronchial segment label distribution, the target centerline bifurcation point is used as the vascular structure root node. The vascular structure root node can be determined by combining clinical data with the distribution of each bronchial segment label value, thereby improving the accuracy of identifying the vascular structure root node.

[0086] In one embodiment, Figure 6As shown, for any target centerline bifurcation point, the label values ​​of each bronchial segment constituting the target centerline bifurcation point are searched, including:

[0087] Step 602, confirming the number of bifurcation point connections corresponding to the bifurcation point constituting the target centerline.

[0088] The number of bifurcation point connections may be the number of bronchial segment structures at the bifurcation point with the target centerline.

[0089] Specifically, since the target centerline bifurcation point is the overlapping point of multiple segmented centerline endpoints, the centerline information point label information of the overlapping points of each centerline endpoint of the target centerline bifurcation point is traversed. When the centerline information point label information of the overlapping points of each centerline endpoint all indicate that they have the same number of bifurcation point connections, then it is used as the number of bifurcation point connections corresponding to the target centerline bifurcation point.

[0090] Step 604 , when the number of bifurcation point connections is not less than the bifurcation point connectivity, search for each bronchial segment label value according to the target centerline bifurcation point and the number of bifurcation point connections.

[0091] The bifurcation point connectivity may be the minimum value of the number of bronchial segment structures corresponding to the target centerline bifurcation point that may become the root node of the vascular structure, wherein the minimum value of the bifurcation point connectivity is 3.

[0092] Specifically, the number of bifurcation point connections of the target center line bifurcation point is compared with the bifurcation point connectivity. If the bifurcation point connection number judgment result indicates that the number of bifurcation point connections of the target center bifurcation point is greater than or equal to 3, then the target center line bifurcation point is used as the basis, and the number of bifurcation point connections is used as the lower limit of the search number to search for each bronchial segment center line that constitutes the target center bifurcation point. Since each bronchial segment center line has a corresponding relationship with each bronchial segment structure, the bronchial segment structure corresponding to each bronchial segment center line is determined by the each bronchial segment center line that constitutes the target center bifurcation point. Furthermore, the bronchial segment structure also has a corresponding relationship with the bronchial segment label value, and the bronchial segment label value is obtained by the bronchial segment structure. Using the same method as above, at least one bronchial segment label value corresponding to each target center line bifurcation point can be obtained.

[0093] In this embodiment, by comparing the number of bifurcation point connections corresponding to the target centerline bifurcation point with the bifurcation point connectivity, it is possible to avoid using the target centerline bifurcation point with a bifurcation point connection number of 1 as the root node of the vascular structure, thereby reducing the error rate of identifying the root node of the vascular structure.

[0094] In one embodiment, Figure 7As shown in FIG. 1 , when the label value of each bronchial segment meets the preset bronchial segment label distribution, the target centerline bifurcation point is used as the root node of the vascular structure, including:

[0095] Step 702: When the number of bifurcation point connections is the first characteristic connectivity, determine whether each bronchial segment label value is two trunk segment label values ​​and one bronchial sub-segment label value.

[0096] The first characteristic connectivity may be the case where the number of bifurcation point connections is 3.

[0097] Specifically, if the value of the number of bifurcation point connections is the first characteristic connectivity, that is, the value of the number of bifurcation point connections is 3, traverse each bronchial segment label value to obtain the bronchial segment label value traversal result, and further determine whether the bronchial segment label value traversal result is two main segment label values ​​and one bronchial sub-segment label value.

[0098] Step 704: When two trunk segment label values ​​and one bronchial sub-segment label value conform to the preset bronchial segment label distribution, the target centerline bifurcation point is used as the vascular structure root node.

[0099] Specifically, if the traversal result of the bronchial segment label value indicates that the target centerline bifurcation point is the intersection of two trunk segment label values ​​and one bronchial sub-segment label value, and the distribution of the two trunk segment label values ​​and one bronchial sub-segment label value conforms to the preset bronchial segment label distribution in the corresponding lung segment, then the target centerline bifurcation point is taken as the vascular structure root node. Fig.16 As shown, the target centerline bifurcation point is the trunk and sub-segment 1, and the target centerline bifurcation point is the intersection of the trunk segmentation label values ​​corresponding to the two trunks and the bronchial sub-segment label values ​​corresponding to sub-segment 1. In one embodiment, Fig.17 In the middle of each white circle in the figure, under the condition of two trunk segment label values ​​and one bronchial sub-segment label value, the vascular structure root nodes of the dorsal segment of the left lower lobe and the main bronchus, the vascular structure root nodes of the posterior segment of the left upper lobe apex and the anterior segment of the left upper lobe, the vascular structure root nodes of the anterior basal segment of the right lower lobe and the main bronchus, and the vascular structure root nodes of the inner basal segment of the right lower lobe and the main bronchus are screened out.

[0100] In this embodiment, by taking the target centerline bifurcation point that satisfies the first characteristic connectivity, two trunk segment label values ​​and one bronchial sub-segment label value as the root node of the vascular structure, it is possible to verify whether the characteristic information of the target centerline bifurcation point is consistent with the clinical data of the corresponding lung segment, thereby ensuring the accuracy of the root node of the vascular structure.

[0101] In one embodiment, Figure 8As shown in FIG. 1 , when the label value of each bronchial segment meets the preset bronchial segment label distribution, the target centerline bifurcation point is used as the root node of the vascular structure, including:

[0102] Step 802: When the number of bifurcation point connections is the first characteristic connectivity, determine whether each bronchial segment label value is a trunk segment label value and two bronchial sub-segment label values.

[0103] Specifically, if the value of the number of bifurcation point connections is the first characteristic connectivity, that is, the value of the number of bifurcation point connections is 3, traverse each bronchial segment label value to obtain the bronchial segment label value traversal result, and further determine whether the bronchial segment label value traversal result is a main segment label value and two bronchial sub-segment label values.

[0104] Step 804: When a trunk segment label value and two bronchial sub-segment label values ​​meet the preset bronchial segment label distribution, the target centerline bifurcation point is used as the vascular structure root node.

[0105] Specifically, if the traversal result of the bronchial segment label value indicates that the target centerline bifurcation point is the intersection of a trunk segment label value and two bronchial sub-segment label values, and the distribution of a trunk segment label value and two bronchial sub-segment label values ​​conforms to the preset bronchial segment label distribution in the corresponding lung segment, then the target centerline bifurcation point is used as the vascular structure root node. Fig.18 As shown, the target centerline bifurcation point is the trunk, subsegment 1 and subsegment 2, which constitutes the intersection of the trunk segment label value corresponding to the trunk, the bronchial subsegment label value corresponding to subsegment 1, and the bronchial subsegment label value corresponding to subsegment 2. In one embodiment, Fig.19 In the middle of each white circle in the figure, under the condition of one trunk segment label value and two bronchial sub-segment label values, the vascular structure root nodes of the posterior segment of the left upper lobe apex and the anterior segment of the left upper lobe, the vascular structure root nodes of the upper lingual segment of the left upper lobe and the lower lingual segment of the left upper lobe, and the vascular structure root nodes of the outer basal segment of the right lower lobe and the posterior basal segment of the right lower lobe are screened out.

[0106] In this embodiment, by taking the target centerline bifurcation point that satisfies the first characteristic connectivity, a trunk segment label value and two bronchial sub-segment label values ​​as the root node of the vascular structure, it is possible to verify whether the characteristic information of the target centerline bifurcation point is consistent with the clinical data of the corresponding lung segment, thereby ensuring the accuracy of the root node of the vascular structure.

[0107] In one embodiment, Fig. 9 As shown in FIG. 1 , when the label value of each bronchial segment meets the preset bronchial segment label distribution, the target centerline bifurcation point is used as the root node of the vascular structure, including:

[0108] Step 902: When the number of bifurcation point connections is the second characteristic connectivity, determine whether each bronchial segment label value is a trunk segment label value and at least three bronchial sub-segment label values.

[0109] The second characteristic connectivity may be a case where the number of bifurcation point connections is greater than 3.

[0110] Specifically, if the value of the number of bifurcation point connections is the second characteristic connectivity, that is, the value of the number of bifurcation point connections is greater than 3, traverse each bronchial segment label value to obtain the bronchial segment label value traversal result, and further determine whether the bronchial segment label value traversal result is a trunk segment label value and at least three bronchial sub-segment label values.

[0111] Step 904: When a trunk segment label value and at least three bronchial sub-segment label values ​​meet the preset bronchial segment label distribution, the target centerline bifurcation point is used as the vascular structure root node.

[0112] Specifically, if the traversal result of the bronchial segment label value indicates that the target centerline bifurcation point is the intersection of a trunk segment label value and at least three bronchial sub-segment label values, and the distribution of a trunk segment label value and at least three bronchial sub-segment label values ​​conforms to the preset bronchial segment label distribution in the corresponding lung segment, then the target centerline bifurcation point is used as the vascular structure root node. Fig. 20 As shown, the target centerline bifurcation point is the trunk, subsegment 1, subsegment 2 and subsegment 3, which constitutes the intersection of the trunk segment label value corresponding to the trunk, the bronchial subsegment label value corresponding to subsegment 1, the bronchial subsegment label value corresponding to subsegment 2 and the bronchial subsegment label value corresponding to subsegment 3. In one embodiment, Fig.21 The white circle in the middle is the root node of the vascular structure of the anterior inner basal segment, the posterior basal segment and the outer basal segment of the left lower lobe, which is screened out with one trunk segment label value and at least three bronchial sub-segment label values.

[0113] In this embodiment, by taking the target centerline bifurcation point that satisfies the second characteristic connectivity, a trunk segment label value and three bronchial sub-segment label values ​​as the root node of the vascular structure, it is possible to verify whether the characteristic information of the target centerline bifurcation point is consistent with the clinical data of the corresponding lung segment, thereby ensuring the accuracy of the root node of the vascular structure.

[0114] In one embodiment, Fig.10 As shown, after the step of using the coincident endpoints of the centerline endpoints of each trunk segment and / or each bronchial sub-segment as each target centerline bifurcation point, the method further includes:

[0115] Step 1002: determine at least two target centerline bifurcation points corresponding to any bronchial segment label value.

[0116] Specifically, if the number of bifurcation point connections of the endpoints at both ends of the center line of any bronchial segment label value is 3, each target center line bifurcation point is traversed to select two target center line bifurcation points corresponding to the bronchial segment label value.

[0117] Step 1004 , searching for each bronchial segment label value in each target centerline bifurcation point respectively.

[0118] Specifically, one of the two target centerline bifurcation points is set as the first target centerline bifurcation point, and the other is set as the second target centerline bifurcation point. The centerline information point label information of the coincidence points of each centerline endpoint of the first target centerline bifurcation point and the second target centerline bifurcation point is traversed. When the centerline information point label information of the coincidence points of each centerline endpoint corresponding to the two indicates that they have the same number of bifurcation point connections, the first number of bifurcation point connections corresponding to the first target centerline bifurcation point and the second number of bifurcation point connections corresponding to the second target centerline bifurcation point are used.

[0119] If the value of the first bifurcation point connection number and the value of the second bifurcation point connection number are both the first characteristic connectivity, that is, the value of the first bifurcation point connection number and the value of the second bifurcation point connection number are both 3, traverse the various bronchial segment label values ​​that constitute the first target centerline bifurcation point and the various bronchial segment label values ​​that constitute the second target centerline bifurcation point to obtain the bronchial segment label value traversal result, and further determine whether the various bronchial segment label values ​​of one of the target centerline bifurcation points are one trunk segment label value and two bronchial sub-segment label values, and whether the other target centerline bifurcation point is one trunk segment label value and two bronchial sub-segment label values ​​or three bronchial sub-segment label values.

[0120] Step 1006: For each target centerline bifurcation point, if each bronchial segment label value conforms to a preset bronchial segment label distribution, each target centerline bifurcation point is used as a vascular structure root node.

[0121] Specifically, if the traversal result of the bronchial segmentation label values ​​indicates that the first target centerline bifurcation point is the intersection of a trunk segmentation label value and two bronchial sub-segment label values, and the second target centerline bifurcation point is the intersection of a trunk segmentation label value and two bronchial sub-segment label values ​​or three bronchial sub-segment label values; or, the traversal result of the bronchial segmentation label values ​​indicates that the first target centerline bifurcation point is the intersection of a trunk segmentation label value and two bronchial sub-segment label values ​​or three bronchial sub-segment label values, and the second target centerline bifurcation point is the intersection of a trunk segmentation label value and two bronchial sub-segment label values; and the distribution of each label value of the first target centerline bifurcation point and the second target centerline bifurcation point conforms to the preset bronchial segmentation label distribution in the corresponding lung segment, then the two target centerline bifurcation points are used as the root nodes of the vascular structure. Fig. 22 As shown, if one of the target centerline bifurcation points is the trunk, subsegment 1 and subsegment 2, then the intersection of the trunk segment label value corresponding to the trunk, the bronchial subsegment label value corresponding to subsegment 1, and the bronchial subsegment label value corresponding to subsegment 2 is constituted; if another target centerline bifurcation point is the trunk / field and the remaining two subsegments, then the intersection of the label value corresponding to the trunk / field and the bronchial subsegment label values ​​corresponding to the remaining two subsegments is constituted. In one embodiment, Fig.23 The middle of the white circle in the figure is the intersection of one trunk segment label value and two bronchial sub-segment label values ​​at the first target centerline bifurcation point, and the intersection of one trunk segment label value and two bronchial sub-segment label values ​​or three bronchial sub-segment label values ​​at the second target centerline bifurcation point; or, the bronchial segment label value traversal result indicates that when the first target centerline bifurcation point is the intersection of one trunk segment label value and two bronchial sub-segment label values ​​or three bronchial sub-segment label values, and the second target centerline bifurcation point is the intersection of one trunk segment label value and two bronchial sub-segment label values, the vascular structure root nodes of the apical segment, posterior segment and anterior segment of the right upper lobe are screened out.

[0122] In one embodiment, Fig.24As shown in the white circles, they are the root node screening results of the vascular structure of the posterior segment of the left upper lobe apex and the anterior segment of the left upper lobe, the upper lingular segment of the left upper lobe and the lower lingular segment of the left upper lobe, the dorsal segment of the left lower lobe and the main bronchus, the anterior inner basal segment and the outer basal segment of the left lower lobe, the outer basal segment and the posterior basal segment of the left lower lobe, the apical segment and posterior segment of the right upper lobe, the apical segment and anterior segment of the right upper lobe, the lateral segment of the right middle lobe and the medial segment of the right middle lobe, the outer basal segment of the right lower lobe and the posterior basal segment of the right lower lobe, and the dorsal segment of the right lower lobe and the main bronchus.

[0123] In this embodiment, by checking the bronchial segment label distribution of the bronchial segment label values ​​with two target centerline bifurcation points, it is possible to check whether the characteristic information of the two target centerline bifurcation points is consistent with the clinical data of the corresponding lung segments at the same time, thereby ensuring the accuracy of the vascular structure root node.

[0124] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages 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 carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0125] Based on the same inventive concept, the embodiment of the present application also provides a vascular structure root node extraction device for implementing the vascular structure root node extraction method involved above. The implementation solution provided by the device to solve the problem is similar to the implementation solution recorded in the above method, so the specific limitations in one or more vascular structure root node extraction device embodiments provided below can refer to the limitations of a vascular structure root node extraction method above, and will not be repeated here.

[0126] In one embodiment, Fig.25 As shown, a vascular structure root node extraction device is provided, comprising: a bronchial centerline extraction module 2502, a bronchial parameter acquisition module 2504 and a vascular structure root node identification module 2506, wherein:

[0127] The bronchial centerline extraction module 2502 is used to extract the centerline of the bronchial segmentation mask of the target object to obtain the bronchial centerline corresponding to the bronchial segmentation mask;

[0128] The bronchial parameter obtaining module 2504 is used to calculate the label value of each bronchial segment of the bronchial centerline and search for each bronchial centerline endpoint corresponding to the bronchial centerline; the bronchial segment label value represents the type of bronchial segment structure;

[0129] The vascular structure root node identification module 2506 is used to filter out at least one vascular structure root node in the bronchial segmentation mask from the endpoints of each bronchial centerline according to the label value of each bronchial segment.

[0130] In one embodiment, the bronchial parameter obtaining module 2504 is also used to search for the label information of each centerline information point corresponding to the bronchial branch centerline for any bronchial branch centerline; to perform statistics on the label information of each centerline information point to determine the bronchial branch label value corresponding to the bronchial branch centerline; and to determine the corresponding bronchial segmentation label value of each bronchial segmentation structure based on the bronchial branch label value corresponding to each bronchial branch centerline.

[0131] In one embodiment, the bronchial parameter obtaining module 2504 is also used to search for the bronchial segment centerline corresponding to the trunk segment label value to obtain the endpoints of each trunk segment centerline; search for the bronchial segment centerline corresponding to each bronchial sub-segment label value to obtain the endpoints of each bronchial sub-segment centerline.

[0132] In one embodiment, the vascular structure root node identification module 2506 is also used to use the overlapping endpoints of the centerline endpoints of each trunk segment and / or the centerline endpoints of each bronchial sub-segment as each target centerline bifurcation point; for any target centerline bifurcation point, search for the label values ​​of each bronchial segment that constitutes the target centerline bifurcation point; when the label values ​​of each bronchial segment conform to the preset bronchial segment label distribution, the target centerline bifurcation point is used as the vascular structure root node.

[0133] In one embodiment, the vascular structure root node identification module 2506 is also used to confirm the number of bifurcation point connections corresponding to the target centerline bifurcation point; when the number of bifurcation point connections is not less than the bifurcation point connectivity, the label value of each bronchial segment is searched according to the target centerline bifurcation point and the number of bifurcation point connections.

[0134] In one embodiment, the vascular structure root node identification module 2506 is also used to determine whether each bronchial segment label value is two trunk segment label values ​​and one bronchial sub-segment label value when the number of bifurcation point connections is the first characteristic connectivity; when the two trunk segment label values ​​and one bronchial sub-segment label value meet the preset bronchial segment label distribution, the target centerline bifurcation point is used as the vascular structure root node.

[0135] In one embodiment, the vascular structure root node identification module 2506 is also used to determine whether each bronchial segment label value is a trunk segment label value and two bronchial sub-segment label values ​​when the number of bifurcation point connections is the first characteristic connectivity; when one trunk segment label value and two bronchial sub-segment label values ​​meet the preset bronchial segment label distribution, the target centerline bifurcation point is used as the vascular structure root node.

[0136] In one embodiment, the vascular structure root node identification module 2506 is also used to determine whether each bronchial segment label value is a trunk segment label value and at least three bronchial sub-segment label values ​​when the number of bifurcation point connections is the second characteristic connectivity; when a trunk segment label value and at least three bronchial sub-segment label values ​​meet the preset bronchial segment label distribution, the target centerline bifurcation point is used as the vascular structure root node.

[0137] In one embodiment, the vascular structure root node identification module 2506 is also used to determine at least two target centerline bifurcation points corresponding to any bronchial segment label value; search for each bronchial segment label value in each target centerline bifurcation point respectively; for each target centerline bifurcation point, when each bronchial segment label value conforms to a preset bronchial segment label distribution, each target centerline bifurcation point is used as the vascular structure root node.

[0138] Each module in the above-mentioned vascular structure root node extraction device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0139] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Fig.26As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store server data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for extracting a root node of a vascular structure is implemented.

[0140] Those skilled in the art will understand that Fig.26 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0141] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0142] In one embodiment, a computer-readable storage medium is provided, storing a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0143] In one embodiment, a computer program product or computer program is provided, the computer program product or computer program includes computer instructions, the computer instructions are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps in the above-mentioned method embodiments.

[0144] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0145] 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, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the 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 (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0146] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0147] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for extracting root nodes of vascular structures, characterized in that: The method comprises: Performing centerline extraction on the bronchial segmentation mask of the target object to obtain the bronchial centerline corresponding to the bronchial segmentation mask; Calculating the label value of each bronchial segment of the bronchial centerline, and searching for each bronchial centerline endpoint corresponding to the bronchial centerline; the bronchial segment label value represents the type of bronchial segment structure; At least one vascular structure root node in the bronchial segmentation mask is selected from each bronchial centerline endpoint according to each bronchial segment label value.

2. The method according to claim 1, characterized in that The bronchial centerline includes the centerlines of each bronchial branch; the calculating of each bronchial segment label value corresponding to the bronchial centerline includes: For any of the bronchial branch centerlines, searching for label information of each centerline information point corresponding to the bronchial branch centerline; Performing statistics on the label information of each centerline information point to determine the bronchial branch label value corresponding to the bronchial branch centerline; According to the bronchial branch label value corresponding to each bronchial branch centerline, the bronchial segment label value corresponding to each bronchial segment structure is determined.

3. The method according to claim 1, characterized in that The bronchial segment label value includes a trunk segment label value and a bronchial sub-segment label value; the bronchial centerline endpoint includes a trunk segment centerline endpoint and a bronchial sub-segment centerline endpoint; the searching for each bronchial centerline endpoint corresponding to the bronchial centerline includes: Searching for the bronchial segment centerline corresponding to the trunk segment label value to obtain the endpoints of each trunk segment centerline; The bronchial segment centerline corresponding to each bronchial subsegment label value is searched to obtain the centerline endpoint of each bronchial subsegment.

4. The method according to claim 3, characterized in that The step of selecting at least one vascular structure root node in the bronchial segmentation mask from each bronchial centerline endpoint according to each bronchial segmentation label value includes: The overlapping endpoints of the centerline endpoints of each trunk segment and / or each bronchial sub-segment centerline endpoint are used as the target centerline bifurcation points; For any of the target centerline bifurcation points, searching for the bronchial segment label values ​​constituting the target centerline bifurcation point; In the case that each of the bronchial segment label values ​​conforms to the preset bronchial segment label distribution, the target centerline bifurcation point is used as the vascular structure root node.

5. The method according to claim 4, characterized in that The step of searching for each of the bronchial segment label values ​​constituting the target centerline bifurcation point for any of the target centerline bifurcation points includes: Determine the number of bifurcation point connections corresponding to the bifurcation point constituting the target centerline; When the number of bifurcation point connections is not less than the bifurcation point connectivity, the label value of each bronchial segment is searched according to the target centerline bifurcation point and the number of bifurcation point connections.

6. The method according to claim 4, characterized in that In the case where each of the bronchial segment label values ​​conforms to the preset bronchial segment label distribution, the target centerline bifurcation point is used as the vascular structure root node, including: In a case where the number of bifurcation point connections is the first characteristic connectivity, determining whether each of the bronchial segment label values ​​is two of the trunk segment label values ​​and one of the bronchial sub-segment label values; In the case where two of the trunk segment label values ​​and one of the bronchial sub-segment label values ​​conform to the preset bronchial segment label distribution, the target centerline bifurcation point is used as the vascular structure root node.

7. The method according to claim 4, characterized in that In the case where each of the bronchial segment label values ​​conforms to the preset bronchial segment label distribution, the target centerline bifurcation point is used as the vascular structure root node, including: In a case where the number of bifurcation point connections is the first characteristic connectivity, determining whether each of the bronchial segment label values ​​is one of the trunk segment label values ​​and two of the bronchial sub-segment label values; When one of the trunk segment label values ​​and two of the bronchial sub-segment label values ​​conform to the preset bronchial segment label distribution, the target centerline bifurcation point is used as the vascular structure root node.

8. The method according to claim 4, characterized in that In the case where each of the bronchial segment label values ​​conforms to the preset bronchial segment label distribution, the target centerline bifurcation point is used as the vascular structure root node, including: In a case where the number of bifurcation point connections is the second characteristic connectivity, determining whether each of the bronchial segment label values ​​is one of the trunk segment label values ​​and at least three of the bronchial sub-segment label values; When one of the trunk segment label values ​​and at least three of the bronchial sub-segment label values ​​conform to the preset bronchial segment label distribution, the target centerline bifurcation point is used as the vascular structure root node.

9. The method according to claim 4, characterized in that After the step of using the coincident endpoints of the centerline endpoints of each trunk segment and / or each bronchial sub-segment as each target centerline bifurcation point, the method further includes: Determine at least two of the target centerline bifurcation points corresponding to any of the bronchial segment label values; Searching for each bronchial segment label value in each target centerline bifurcation point respectively; For each of the target centerline bifurcation points, when each of the bronchial segment label values ​​conforms to a preset bronchial segment label distribution, each of the target centerline bifurcation points is used as the root node of the vascular structure.

10. A vascular structure root node extraction device, characterized in that: The device comprises: A bronchial centerline extraction module is used to extract the centerline of the bronchial segmentation mask of the target object to obtain the bronchial centerline corresponding to the bronchial segmentation mask; A bronchial parameter obtaining module, used to calculate the label value of each bronchial segment of the bronchial centerline, and to search for each bronchial centerline endpoint corresponding to the bronchial centerline; the bronchial segment label value represents the type of bronchial segment structure; The vascular structure root node identification module is used to filter out at least one vascular structure root node in the bronchial segmentation mask from the endpoints of each bronchial centerline according to the label value of each bronchial segment.

11. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 9 are implemented.

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

13. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 9 are implemented.

Images