Method, device, equipment, medium and program product for extracting blood vessel centerline tree

Abstract

The present application provides a method, apparatus, device, medium and program product for extracting a vascular centerline tree, including: first, obtaining an aortic vascular image of the target aorta. Next, inputting the aortic vascular image into a preset surface model generation algorithm to obtain a vascular surface model of the target aorta. Then, inputting the vascular surface model, the vascular starting point of the target aorta and at least one vascular ending point of the target aorta into a preset centerline extraction algorithm to obtain an aortic vascular centerline tree of the target aorta. Finally, traversing each of the at least one vascular centerline, updating the point coordinates of the vascular centerline that meets the preset conditions to the point coordinates of the baseline centerline, and updating the aortic vascular centerline tree. This is to avoid deviations in the overlapping positions of multiple vascular centerlines.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of computer technology, and in particular to a method, apparatus, device, medium, and program product for extracting a vascular centerline tree. Background Art

[0002] Currently, aortic vascular diseases (such as aortic aneurysms and aortic dissections) are increasing annually. Once a vascular rupture occurs, it becomes a critical illness with a very high clinical mortality rate. Based on the aortic centerline tree, doctors can obtain patient lesion analysis results (such as the presence, severity, and location of the lesion) and interventional treatment plans. Therefore, how to quickly and accurately extract the aortic centerline tree has important clinical value and practical significance in the diagnosis and treatment of aortic vascular diseases.

[0003] The aortic centerline tree refers to a characteristic curve of the aortic vessel obtained from an aortic vessel image. The aortic vessel image refers to a three-dimensional vascular image obtained by imaging the patient's aorta using a computed tomography angiography (CTA) imaging device.

[0004] In the related art, first, the aortic vessel image (binary image) is input into the surface model generation function provided by the Vascular Modeling Toolkit (VMTK) to obtain the surface model of the aorta, and then the surface model and the aortic vessel endpoints (including the starting point and end point of the aortic vessel) are input into the vascular centerline extraction function provided by VMTK to obtain the aortic vessel centerline tree. However, the aortic vessel centerline tree includes multiple vessel centerlines, and the vessel centerlines correspond to the end points one by one, and each vessel centerline is independent. Therefore, there may be deviations in the overlapping positions of multiple vessel centerlines, which in turn leads to inaccurate lesion analysis results or interventional treatment plans based on the aortic vessel centerline tree. Summary of the Invention

[0005] The present application provides a method, apparatus, device, medium and program product for extracting a vascular centerline tree to avoid deviations in the overlapping positions of multiple vascular centerlines.

[0006] In a first aspect, a method for extracting a vascular centerline tree is provided, comprising: first, acquiring an aortic vascular image of a target aorta. Next, inputting the aortic vascular image into a preset surface model generation algorithm to obtain a vascular surface model of the target aorta. Then, inputting the vascular surface model, a vascular starting point of the target aorta, and at least one vascular ending point of the target aorta into a preset centerline extraction algorithm to obtain an aortic vascular centerline tree of the target aorta. Finally, traversing each of the at least one vascular centerline, updating the point coordinates of the vascular centerline that meets preset conditions to the point coordinates of the reference centerline, and updating the aortic vascular centerline tree.

[0007] The aortic vascular image is a binary image obtained by segmenting a computed tomography angiography (CTA) image. The CTA image is a slice image that includes the target aorta. The at least one vascular endpoint includes a left iliac endpoint or a right iliac endpoint. The aortic vascular centerline tree includes at least one vascular centerline. The at least one vascular centerline corresponds one-to-one with the at least one vascular endpoint. A preset condition for extracting the vascular centerline tree is that the position deviation value compared to the reference centerline is less than a preset deviation threshold. The reference centerline refers to the vascular centerline corresponding to the left iliac endpoint or the right iliac endpoint.

[0008] In a second aspect, a device for extracting a blood vessel centerline tree is provided, comprising: an image acquisition module, a patch acquisition module, a line tree extraction module, and a line tree update module.

[0009] The image acquisition module is used to acquire an aortic vascular image of the target aorta; the aortic vascular image is a binary image obtained by segmenting the computed tomography angiography (CTA) image; the CTA image is a slice image including the target aorta;

[0010] A patch acquisition module is used to input the aortic blood vessel image into a preset surface model generation algorithm to obtain a blood vessel surface model of the target aorta;

[0011] a line tree extraction module, configured to input a vascular surface model, a vascular starting point of the target aorta, and at least one vascular end point of the target aorta into a preset centerline extraction algorithm to obtain an aortic vascular centerline tree of the target aorta; wherein the at least one vascular end point includes a left iliac end point or a right iliac end point; the aortic vascular centerline tree includes at least one vascular centerline; and the at least one vascular centerline corresponds one-to-one with the at least one vascular end point.

[0012] A line tree update module is used to traverse each of at least one vascular centerline, update the point coordinates of the vascular centerline that meets the preset conditions to the point coordinates of the reference centerline, and update the aortic vascular centerline tree; the preset conditions are: compared with the reference centerline, the position deviation value is less than the preset deviation threshold; the reference centerline is the vascular centerline corresponding to the left iliac termination point or the right iliac termination point.

[0013] In a third aspect, an electronic device is provided, comprising: a processor and a memory, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the method in the first aspect or its various implementations.

[0014] In a fourth aspect, a computer-readable storage medium is provided for storing a computer program, wherein the computer program enables a computer to execute the method according to the first aspect or its various implementations.

[0015] In a fifth aspect, a computer program product is provided, comprising computer program instructions, which enable a computer to execute the method in the first aspect or its various implementations.

[0016] In a sixth aspect, a computer program is provided, which enables a computer to execute the method in the first aspect or its various implementations.

[0017] Through the technical solution provided by the present application, first, the electronic device can obtain the aortic vascular image of the target aorta. Next, the electronic device inputs the extracted aortic vascular image of the vascular centerline tree into a preset surface model generation algorithm to obtain the vascular surface model of the extracted target aorta of the vascular centerline tree. Then, the electronic device inputs the extracted vascular surface model of the vascular centerline tree, the vascular starting point of the extracted target aorta of the vascular centerline tree, and at least one vascular ending point of the extracted target aorta of the vascular centerline tree into a preset centerline extraction algorithm to obtain the aortic vascular centerline tree of the extracted target aorta of the vascular centerline tree. Finally, the electronic device traverses each vascular centerline of the at least one extracted vascular centerline of the vascular centerline tree, updates the point coordinates of the vascular centerline that meets the preset conditions to the point coordinates of the reference centerline, and updates the extracted aortic vascular centerline tree of the vascular centerline tree. In the above process, the electronic device can make the point coordinates of the vascular centerline that meets the preset conditions in each vascular centerline the same as the point coordinates of the reference centerline, that is, the point coordinates corresponding to the overlapping position of the reference centerline and other vascular centerlines are the same. In this way, deviations in the overlapping positions of multiple vascular centerlines can be avoided, thereby improving the accuracy of the lesion analysis results or interventional treatment plans obtained based on the aortic vascular centerline tree. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0019] Figure 1 An application scenario diagram provided for an embodiment of the present application;

[0020] Figure 2 A flowchart of a method for extracting a blood vessel centerline tree provided in an embodiment of the present application;

[0021] Figure 3 A schematic diagram of an aortic vessel image provided in an embodiment of the present application;

[0022] Figure 4 A schematic diagram of an aortic blood vessel centerline tree provided in an embodiment of the present application;

[0023] Figure 5 A flowchart of another method for extracting a blood vessel centerline tree provided in an embodiment of the present application;

[0024] Figure 6 A schematic diagram of a blood vessel centerline tree extraction device 600 provided in an embodiment of the present application;

[0025] Figure 7 It is a schematic block diagram of an electronic device 700 provided in an embodiment of the present application. DETAILED DESCRIPTION

[0026] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0027] It should be noted that the terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0028] As described above, in the related art, first, the aortic vessel image (binary image) is input into the surface model generation function to obtain the surface model of the aorta. Then, the surface model and the aortic vessel endpoints (including the starting point and end point of the aortic vessel) are input into the vessel centerline extraction function to obtain the aortic vessel centerline tree. The aortic vessel centerline tree thus obtained includes multiple vessel centerlines, each corresponding one-to-one to the end point, and each vessel centerline is independent. Therefore, there may be deviations in the overlapping positions of multiple vessel centerlines, which in turn may lead to inaccurate lesion analysis results or interventional treatment plans obtained based on the aortic vessel centerline tree.

[0029] In order to solve the above technical problems, the inventive concept of this application is: the electronic device can set the point coordinates corresponding to the overlapping positions of multiple blood vessel centerlines to the same point coordinates, thereby avoiding deviations in the overlapping positions of multiple blood vessel centerlines, and thereby improving the accuracy of the lesion analysis results or interventional treatment plans obtained based on the aortic blood vessel centerline tree.

[0030] It should be understood that the technical solution of this application can be applied to the following scenarios, but is not limited to:

[0031] In some implementations, Figure 1 An application scenario diagram provided in an embodiment of the present application, such as Figure 1 As shown, the application scenario may include an electronic device 110 and a network device 120. The electronic device 110 may establish a connection with the network device 120 via a wired network or a wireless network.

[0032] For example, electronic device 110 may be a desktop computer, a laptop computer, a tablet computer, etc., but is not limited thereto. Network device 120 may be a terminal device or a server, but is not limited thereto. In one embodiment of the present application, electronic device 110 may send a request message to network device 120, where the request message may be used to request acquisition of an aortic vessel image, a vessel starting point, and a vessel ending point. Furthermore, electronic device 110 may receive a response message sent by network device 120, where the response message includes the aortic vessel image, a vessel starting point, and a vessel ending point.

[0033] also, Figure 1 An electronic device and a network device are given as an example, and in fact other numbers of electronic devices and network devices may be included, and this application does not impose any limitation on this.

[0034] In other possible implementations, the technical solution of the present application may also be executed by the above-mentioned electronic device 110, or the technical solution of the present application may also be executed by the above-mentioned network device 120, and the present application does not impose any restrictions on this.

[0035] After introducing the application scenarios of the embodiments of the present application, the technical solutions of the present application will be described in detail below:

[0036] Figure 2 This is a flow chart of a method for extracting a blood vessel centerline tree provided in an embodiment of the present application. The method can be performed as follows: Figure 1 The electronic device 110 shown in FIG. Figure 2 As shown, the method may include the following steps:

[0037] S210: The electronic device acquires an aortic blood vessel image of the target aorta.

[0038] Among them, such as Figure 3 The aortic image shown is a binary image obtained by segmenting a computed tomography angiography (CTA) image. A CTA image is a slice image of the target aorta. After intravenous injection of a contrast agent, a CTA image is obtained by scanning the target aorta in sections one by one using a precisely collimated X-ray beam, gamma rays, ultrasound, or other technology, along with a highly sensitive detector. This creates a three-dimensional image.

[0039] Specifically, the CTA image includes multiple slice images, and the size of the CTA image can be M*N*L.

[0040] Where M and N are the length and width of each slice image, for example, M is 512 and N is 512, and L is the number of slice images in the CTA image, that is, the number of slice layers (usually greater than 500). Typically, the axial spacing between adjacent slice images is between 0.5 mm and 2 mm. The axial direction refers to the Z-axis of the CT scan, which is the direction from the feet to the head of the human body.

[0041] In some embodiments, the electronic device can use the NNUNet model to segment the CTA image to obtain the aortic vessel image, and can also obtain the aortic vessel image from other electronic devices, which is not limited in the embodiments of the present application.

[0042] In some embodiments, due to potential bifurcation defects in aortic vessel images, electronic devices may make errors when extracting the aortic vessel centerline tree, potentially terminating the extraction process. To avoid premature termination, the electronic device can use a morphological closing operation to repair the defects.

[0043] Specifically, the electronic device can perform expansion and corrosion processing on the aortic blood vessel image according to a preset expansion kernel radius and a preset corrosion kernel radius to obtain the aortic blood vessel image after defect repair.

[0044] It is understood that the electronic device first dilates the aortic vessel image according to a preset dilation kernel radius, filling the vascular connection defects. Then, the electronic device erodes the dilated image according to a preset erosion kernel radius, restoring the processed image to its original size. For example, the preset dilation kernel radius can be 5 (the number of adjacent pixels), and similarly, the preset erosion kernel radius can also be 5 (the number of adjacent pixels).

[0045] In this way, the connection and bifurcation defects of the aortic vessel image can be repaired through the expansion and corrosion operation, thereby avoiding extraction errors in the process of extracting the aortic vessel centerline tree, and thus avoiding termination of the extraction process.

[0046] S220: The electronic device inputs the aorta blood vessel image into a preset surface model generation algorithm to obtain a blood vessel surface model of the target aorta.

[0047] The preset surface model generation algorithm may be an isosurface extraction algorithm, which is specifically used to extract discrete triangular facets from a three-dimensional discrete data field (aortic vessel image) to obtain a vessel surface model.

[0048] In an embodiment of the present application, the vascular surface model includes at least two vascular facets. In fact, in order to improve the consistency between the vascular surface model and the aortic vascular image, especially to represent fine blood vessels, the number of facets in the vascular surface model will be large. Therefore, in the subsequent process of extracting the aortic vascular centerline tree, a large number of corresponding calculations need to be performed, resulting in extremely low efficiency in extracting the aortic vascular centerline tree. To this end, the electronic device can extract some vascular facets in the vascular surface model to reduce the amount of calculation for extracting the aortic vascular centerline tree, improve the efficiency of extracting the aortic vascular centerline tree, and at the same time do not affect the accuracy of the aortic vascular centerline tree.

[0049] Specifically, the electronic device can perform a patch extraction operation on the blood vessel surface model to update the blood vessel surface model. It is understandable that the patch extraction operation is used to attenuate the number of patches. The patch extraction operation can reduce the number of patches by uniform attenuation. By setting the extraction coefficient, the attenuation rate of the blood vessel patch is controlled. The attenuation rate can be 30%, 50%, 90%.

[0050] For example, the vascular surface model includes 100 vascular patches. Assuming the extraction coefficient is 2, the first vascular patch in the vascular surface model is extracted first, then the third vascular patch in the vascular surface model is extracted, and so on. 50 vascular patches are extracted from the 100 vascular patches, and the attenuation rate at this time is 50%.

[0051] For example, the vascular surface model includes 100 vascular patches. Assuming the extraction coefficient is 5, the first vascular patch in the vascular surface model is extracted first, then the sixth vascular patch in the vascular surface model is extracted, and so on. 20 vascular patches are extracted from the 100 vascular patches, and the attenuation rate at this time is 80%.

[0052] In this way, by extracting part of the vascular patches from at least two vascular patches, the computational complexity of extracting the aortic vascular centerline tree can be reduced without affecting the accuracy of the aortic vascular centerline tree, thereby improving the efficiency of extracting the aortic vascular centerline tree.

[0053] In other embodiments, due to differences in pixel density corresponding to different vascular patches in the vascular surface model, the surface of the vascular image corresponding to the vascular surface model is uneven, which may result in poor extraction of the aortic centerline tree. The electronic device may also smooth the vascular surface model based on a preset smoothing algorithm and a preset smoothness threshold. It should be noted that if the vascular surface model is not subjected to patch extraction, then the vascular surface model is smoothed after the vascular surface model is obtained. If the vascular surface model is subjected to patch extraction, then the vascular surface model is smoothed after the patch extraction is performed.

[0054] Specifically, the preset smoothing algorithm may be a Taubin smoothing algorithm, and the smoothing rate and the number of iterations may be changed in the preset smoothing algorithm so that the smoothness parameter value falls within a preset range, such as 0.1-0.2.

[0055] In this way, the electronic device smoothes the blood vessel surface model based on a preset smoothing algorithm and a preset smoothness threshold, which can make the blood vessel image surface corresponding to the blood vessel surface model smoother, thereby improving the extraction effect of the aortic blood vessel centerline tree.

[0056] S230: The electronic device inputs the blood vessel surface model, the blood vessel starting point of the target aorta, and at least one blood vessel ending point of the target aorta into a preset centerline extraction algorithm to obtain an aortic blood vessel centerline tree of the target aorta.

[0057] The at least one vessel termination point includes a left iliac termination point or a right iliac termination point, and the aortic vessel centerline tree includes at least one vessel centerline. The at least one vessel centerline corresponds one-to-one with the at least one vessel termination point.

[0058] It is understood that the vessel starting point may be the starting endpoint of the ascending aorta of the target aorta, that is, the endpoint of the aortic sinus. At least one vessel ending point may be the end of a branch vessel of the target aorta, such as the left iliac ending point, the right iliac ending point, the left clavicular ending point, the left carotid ending point, the right carotid ending point, the right clavicular ending point, the left renal ending point, and the right renal ending point.

[0059] In an embodiment of the present application, the electronic device can obtain the blood vessel starting point and at least one blood vessel ending point based on user input, the electronic device can also obtain it based on transmission from other electronic devices, and the electronic device can also obtain it from the aortic blood vessel image based on a blood vessel endpoint extraction algorithm. In this embodiment of the present application, there is no limitation on the source of the blood vessel starting point and at least one blood vessel ending point.

[0060] In an embodiment of the present application, the preset centerline extraction algorithm may be a weighted shortest path algorithm. Specifically, a vessel centerline is generated by tracing from a vessel start point to any one of at least one vessel end point. Corresponding to the at least one vessel end point, the at least one vessel centerline included in the aortic vessel centerline tree, i.e., a centerline sequence, is arranged in the order of the at least one vessel end point.

[0061] Illustratively, the centerlines of the at least one blood vessel are superimposed on each other, such as Figure 4 As shown, the aortic vascular centerline tree is obtained.

[0062] In some embodiments, the electronic device may further perform smoothing and uniform processing on each vascular centerline in the aortic vascular centerline tree according to a preset point distance step length.

[0063] Specifically, the pixels on the blood vessel centerline obtained by the preset centerline extraction algorithm are uneven. The electronic device can set a preset point distance step size (such as 2 mm) and perform a spline curve on each blood vessel centerline to make the pixels on the blood vessel centerline smoothly and evenly distributed.

[0064] In this way, after each vascular centerline in the aortic vascular centerline tree is smoothed and uniformly processed, the aortic vascular centerline tree will not be affected if operations such as zooming in, zooming out, or local manual adjustment are performed, thereby improving the accuracy of lesion analysis results or interventional treatment plans obtained based on the aortic vascular centerline tree.

[0065] S240: The electronic device traverses each of the at least one blood vessel centerline, updates the point coordinates of the blood vessel centerline that meets the preset conditions as the point coordinates of the reference centerline, and updates the aorta blood vessel centerline tree.

[0066] The preset condition is that: compared with the reference center line, the position deviation value is less than a preset deviation threshold; the reference center line refers to the blood vessel center line corresponding to the left iliac termination point or the right iliac termination point.

[0067] In an embodiment of the present application, the aortic vessel centerline tree includes at least one vessel centerline. Each vessel centerline begins at a vessel starting point and ends at one of at least one vessel ending point; that is, each vessel centerline is independent of the other. Due to the structural characteristics of the aorta, any two of the at least one vessel centerlines may overlap. Since each vessel centerline is independent, the overlapping positions of the individual vessel centerlines may deviate. Electronic devices can mitigate this deviation by merging and sharing the overlapping positions.

[0068] Exemplarily, the blood vessel centerline corresponding to the left iliac termination point starts from the blood vessel starting point (end point of the aortic sinus), passes through the bifurcation points corresponding to the left clavicular artery, the bifurcation points corresponding to the left carotid artery, the bifurcation points corresponding to the right carotid artery, the bifurcation points corresponding to the right clavicular artery, the bifurcation points corresponding to the left renal artery, and the bifurcation points corresponding to the right renal artery, and reaches the bifurcation point corresponding to the left iliac artery, until the left kidney and left iliac termination points. The blood vessel centerline corresponding to the left renal termination point starts from the blood vessel starting point (end point of the aortic sinus), passes through the bifurcation points corresponding to the left clavicular artery, the bifurcation points corresponding to the left carotid artery, the bifurcation points corresponding to the right carotid artery, and the bifurcation points corresponding to the right clavicular artery, and reaches the bifurcation point corresponding to the left renal artery, until the left kidney and left iliac termination points. Therefore, the overlapping position of the blood vessel centerlines corresponding to the left renal termination point and the left iliac termination point starts from the blood vessel starting point (end point of the aortic sinus), passes through the bifurcation points corresponding to the left clavicular artery, the bifurcation points corresponding to the left carotid artery, the bifurcation points corresponding to the right carotid artery, and the bifurcation points corresponding to the right clavicular artery, until the bifurcation point corresponding to the left renal artery.

[0069] In some implementations, such as Figure 5 As shown, this step S240 may include:

[0070] S510: The electronic device obtains centerline dictionary data corresponding to the aorta centerline tree according to a preset data conversion function.

[0071] Among them, the centerline dictionary data includes a dictionary identifier, an identity identifier ID array and a point coordinate array; the dictionary identifier is used to mark the centerline sequence of the blood vessel centerline; the identity identifier ID array includes a point sequence set of all pixel points contained in the blood vessel centerline marked by the dictionary identifier, and the point coordinate array includes the three-dimensional coordinate data of all pixel points contained in the blood vessel centerline marked by the dictionary identifier; the pixel points corresponding to the point coordinate array start from the blood vessel starting point and end at the blood vessel ending point of the blood vessel centerline marked by the dictionary identifier.

[0072] In the embodiment of the present application, the aortic vessel centerline tree is vtkPolyData model data composed of points, lines and surfaces. The aortic vessel centerline tree (vtkPolyData model data) is converted into centerline dictionary data (point coordinate data) through a preset data conversion function.

[0073] For example, assuming the aortic centerline tree includes 10 centerlines, for the first centerline (with 351 pixels), the corresponding dictionary identifier can be set to "001," and the identity document (ID) array can be set to [1, 2, ..., 351]. The centerlines are numbered sequentially. For the second centerline (with 240 pixels), the corresponding dictionary identifier can be set to "002," and the ID array can be set to [352, 353, ..., 591]. This is repeated for the third through tenth centerlines.

[0074] For example, based on the previous example, the coordinate array is stored in association with the ID number and contains all the point coordinates. For the first blood vessel centerline (the number of pixels is 351), the point coordinate array includes 351 coordinate elements, each coordinate element corresponds to a pixel point, and each coordinate element includes three coordinate values ​​of x, y, and z. The electronic device can use (001,1) to identify the first pixel point in the first blood vessel centerline. Similarly, the electronic device can use (002,353) to identify the second pixel point in the second blood vessel centerline. In this way, the electronic device can find the coordinate value of any pixel point on the aortic blood vessel centerline tree.

[0075] S520: The electronic device determines the blood vessel centerline corresponding to the left iliac termination point or the right iliac termination point as the reference centerline.

[0076] The reference centerline is the vessel centerline corresponding to the left or right iliac termination point. Because the aorta extends from ascending to descending to the iliac artery branches, the reference centerline is the longest vessel centerline in the aortic centerline tree. This ensures that all possible overlapping locations lie on the reference centerline.

[0077] It is understandable that after the electronic device obtains at least one blood vessel termination point, it can set the left iliac termination point or the right iliac termination point as the first blood vessel termination point.

[0078] S530: The electronic device traverses each of the at least one blood vessel centerline in the order of the dictionary identifiers, compares the point coordinate array corresponding to each blood vessel centerline with the point coordinate array corresponding to the reference centerline, and calculates the position deviation value of the pixel point pair starting from the blood vessel starting point.

[0079] In an embodiment of the present application, the point coordinate array corresponding to one blood vessel centerline is compared with the point coordinate array corresponding to the reference centerline each time according to the dictionary identification order, that is, the arrangement order of each blood vessel centerline in at least one blood vessel centerline.

[0080] For example, assume that the aortic vessel centerline tree includes 10 vessel centerlines. The first vessel centerline is the reference centerline. The first vessel centerline is compared with the second vessel centerline. The point coordinates corresponding to the first pixel are extracted from the point coordinate array corresponding to the first vessel centerline. The point coordinates corresponding to the first pixel are then extracted from the point coordinate array corresponding to the second vessel centerline. The two corresponding pixel points constitute a pixel point pair. The three pairs of x, y, and z coordinate values ​​are compared separately to determine the position deviation value. The position deviation value may include three differences corresponding to the three pairs of coordinate values.

[0081] S540: If the position deviation value of the electronic device is less than a preset deviation threshold, the reference point coordinates and reference point sequence of the pixel points belonging to the reference center line in the pixel point pair corresponding to the position deviation value are obtained, and the point coordinates of the pixel points that do not belong to the reference center line in the pixel point pair corresponding to the position deviation value are replaced with the reference point coordinates. At the same time, the point sequence of the pixel points that do not belong to the reference center line in the pixel point pair corresponding to the position deviation value is replaced with the reference point sequence.

[0082] In the embodiment of the present application, the position deviation value is less than the preset deviation threshold, which can be understood as the three differences corresponding to the three pairs of coordinate values ​​are all less than the preset deviation threshold (2 mm).

[0083] For example, assuming the aortic centerline tree includes 10 centerlines, if the position deviation values ​​corresponding to 100 pixels of the reference centerline and the second centerline are all less than a preset deviation threshold, the reference point coordinates and reference point sequence of the 100 pixels in the reference centerline are obtained, along with the ID array [1, 2, ..., 100] and the 100 reference coordinate elements in the corresponding point coordinate array. The ID array [352, 353, ..., 591] corresponding to the second centerline is then replaced with [1, 2, ..., 100, 453, ..., 591], and the 100 undetermined coordinate elements in the corresponding point coordinate array are replaced with the 100 reference coordinate elements.

[0084] If the position deviation value is not less than the preset deviation threshold, the position deviation value corresponding to the next blood vessel centerline is judged until each blood vessel centerline of the at least one blood vessel centerline is traversed.

[0085] S550: The electronic device resets the point sequence in the ID array corresponding to each blood vessel centerline except the reference point sequence according to the point sequence step between different pixel points in the reference centerline.

[0086] For example, the ID array corresponding to the second replaced vessel centerline, [1, 2, ..., 100, 453, ..., 591], is reset to [1, 2, ..., 100, 352, 453, ..., 490] based on the point sequence step size of 1 between [1, 2, ..., 100] and the ID array corresponding to the baseline centerline, [1, 2, ..., 351]. Similarly, the point sequence of the pixels in the non-overlapping positions of the ID array corresponding to the third vessel centerline is continued starting from 491, until the ID arrays corresponding to all vessel centerlines are reset.

[0087] S560: The electronic device updates the aorta centerline tree according to the replaced point coordinates, the replaced point sequence, and the reset point sequence.

[0088] In an embodiment of the present application, after the point coordinates are replaced, the point sequence is replaced, and the point sequence is reset, the overlapping positions corresponding to different vascular centerlines have the same ID number and the same point coordinates, and the ID numbers corresponding to the non-overlapping positions are numbered consecutively, so that deviations in the overlapping positions of multiple vascular centerlines can be avoided.

[0089] In some embodiments, after the electronic device determines the reference centerline, it can also re-establish centerline dictionary data for each blood vessel centerline, that is, re-store the above-mentioned updated ID number to directly obtain the replaced point coordinates, the replaced point sequence and the reset point sequence.

[0090] In this way, by replacing the point coordinates, replacing the point sequence and resetting the point sequence so that the overlapping positions have the same point coordinates and point sequence, the deviation of the overlapping positions of multiple vascular centerlines can be avoided, thereby improving the accuracy of the lesion analysis results or interventional treatment plans obtained based on the aortic vascular centerline tree.

[0091] In the above process, the electronic device can make the point coordinates of the vascular centerline that meets the preset conditions in each vascular centerline the same as the point coordinates of the reference centerline, that is, the point coordinates corresponding to the overlapping position of the reference centerline and other vascular centerlines are the same. In this way, deviations in the overlapping positions of multiple vascular centerlines can be avoided, thereby improving the accuracy of the lesion analysis results or interventional treatment plans obtained based on the aortic vascular centerline tree.

[0092] Figure 6 The present invention provides a schematic diagram of a device 600 for extracting a blood vessel centerline tree. Figure 6 As shown, the apparatus 600 includes: an image acquisition module 610 , a patch acquisition module 620 , a line tree extraction module 630 and a line tree update module 640 .

[0093] An image acquisition module 610 is configured to acquire an aortic vascular image of a target aorta; the aortic vascular image is a binary image obtained by segmenting a computed tomography angiography (CTA) image; and the CTA image is a slice image including the target aorta.

[0094] The patch acquisition module 620 is used to input the aortic blood vessel image into a preset surface model generation algorithm to obtain a blood vessel surface model of the target aorta;

[0095] The line tree extraction module 630 is configured to input the vessel surface model, the vessel start point of the target aorta, and at least one vessel end point of the target aorta into a preset centerline extraction algorithm to obtain an aortic vessel centerline tree of the target aorta; wherein the at least one vessel end point includes a left iliac end point or a right iliac end point; the aortic vessel centerline tree includes at least one vessel centerline; and the at least one vessel centerline corresponds one-to-one with the at least one vessel end point.

[0096] A line tree update module 640 is configured to traverse each of at least one vascular centerline, update the point coordinates of the vascular centerline that meets a preset condition to the point coordinates of the reference centerline, and update the aortic vascular centerline tree; the preset condition is: compared with the reference centerline, the position deviation value is less than a preset deviation threshold; the reference centerline is the vascular centerline corresponding to the left iliac termination point or the right iliac termination point.

[0097] In some implementations, the line tree update module 640 is specifically used to obtain the centerline dictionary data corresponding to the aortic vascular centerline tree according to a preset data conversion function; the centerline dictionary data includes a dictionary identifier, an identity identifier ID array and a point coordinate array; the dictionary identifier is used to mark the centerline line sequence of the vascular centerline; the identity identifier ID array includes a point sequence set of all pixel points contained in the vascular centerline marked by the dictionary identifier, and the point coordinate array includes the three-dimensional coordinate data of all pixel points contained in the vascular centerline marked by the dictionary identifier; the pixel points corresponding to the point coordinate array start from the vascular starting point and end at the vascular end point of the vascular centerline marked by the dictionary identifier; the vascular centerline corresponding to the left iliac end point or the right iliac end point is determined as the reference centerline; each vascular centerline of at least one vascular centerline is traversed in the order of the dictionary identifiers, and The point coordinate array corresponding to each vascular centerline is compared with the point coordinate array corresponding to the benchmark centerline, and the position deviation value of the pixel pair is calculated starting from the starting point of the vascular blood vessel; if the position deviation value is less than the preset deviation threshold, the benchmark point coordinates and benchmark point sequence of the pixel point belonging to the benchmark centerline in the pixel point pair corresponding to the position deviation value are obtained, and the point coordinates of the pixel point that does not belong to the benchmark centerline in the pixel point pair corresponding to the position deviation value are replaced with the benchmark point coordinates. At the same time, the point sequence of the pixel point that does not belong to the benchmark centerline in the pixel point pair corresponding to the position deviation value is replaced with the benchmark point sequence; according to the point sequence step between different pixel points in the benchmark centerline, the point sequence in the ID array corresponding to each vascular centerline is reset except for the benchmark point sequence; according to the replaced point coordinates, replaced point sequence and reset point sequence, the aortic vascular centerline tree is updated.

[0098] In some implementations, such as Figure 6 As shown, the above device further includes: an image processing module 650.

[0099] The image processing module 650 is used to obtain the aortic vessel image of the target aorta, and then perform expansion and corrosion processing on the aortic vessel image according to a preset expansion kernel radius and a preset corrosion kernel radius to obtain the aortic vessel image after defect repair.

[0100] In some implementations, the vessel surface model includes at least two vessel patches, such as Figure 7 As shown, the above device further includes: a patch extraction module 660.

[0101] The patch extraction module 660 is used to input the aortic vessel image into a preset surface model generation algorithm, obtain the vessel surface model of the target aorta, and then perform patch extraction operation on the vessel surface model to update the vessel surface model; the patch extraction operation is used to attenuate the number of patches.

[0102] In some implementations, such as Figure 6As shown, the above device further includes: a surface treatment module 670.

[0103] The surface processing module 670 is used to input the aortic vessel image into a preset surface model generation algorithm, obtain the vessel surface model of the target aorta, and then smooth the vessel surface model based on a preset smoothing algorithm and a preset smoothness threshold.

[0104] In some implementations, such as Figure 6 As shown, the above device further includes: a line processing module 680.

[0105] The line processing module 680 is used to perform smoothing and uniform processing on each vessel centerline in the aortic vessel centerline tree according to a preset point distance step after updating the aortic vessel centerline tree.

[0106] It should be understood that the embodiment of the device for extracting the vascular centerline tree and the embodiment of the method for extracting the vascular centerline tree may correspond to each other, and similar descriptions may refer to the embodiment of the method for extracting the vascular centerline tree. To avoid repetition, they will not be described here. Specifically, Figure 6 The device 600 shown can execute the above-mentioned embodiment of the method for extracting the vascular centerline tree, and the aforementioned and other operations and / or functions of each module in the device 600 are respectively for realizing the corresponding processes in the above-mentioned method for extracting the vascular centerline tree. For the sake of brevity, they will not be repeated here.

[0107] The above describes the device 600 of the embodiment of the present application from the perspective of functional modules in conjunction with the accompanying drawings. It should be understood that the functional module can be implemented in the form of hardware, can be implemented by instructions in the form of software, and can also be implemented by a combination of hardware and software modules. Specifically, the various steps of the embodiment of the method for extracting the vascular centerline tree in the embodiment of the present application can be completed by the hardware integrated logic circuit and / or software instructions in the processor. The steps of the method for extracting the vascular centerline tree disclosed in the embodiment of the present application can be directly reflected as being executed by a hardware decoding processor, or can be executed by a combination of hardware and software modules in the decoding processor. Optionally, the software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps in the above-mentioned embodiment of the medical team configuration method in combination with its hardware.

[0108] Figure 7 It is a schematic block diagram of an electronic device 700 provided in an embodiment of the present application.

[0109] like Figure 7 As shown, the electronic device 700 may include:

[0110] The memory 710 and the processor 720 are configured to store computer programs and transmit the program code to the processor 720. In other words, the processor 720 can call and run the computer program from the memory 710 to implement the method in the embodiment of the present application.

[0111] For example, the processor 720 may be configured to execute the above method embodiments according to instructions in the computer program.

[0112] In some embodiments of the present application, the processor 720 may include but is not limited to:

[0113] General-purpose processor, digital signal processor (DSP), application-specific integrated circuit (ASIC), field-programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, etc.

[0114] In some embodiments of the present application, the memory 710 includes but is not limited to:

[0115] Volatile memory and / or non-volatile memory. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct RAM bus random access memory (DR RAM).

[0116] In some embodiments of the present application, the computer program may be divided into one or more modules, which are stored in the memory 710 and executed by the processor 720 to implement the method provided by the present application. The one or more modules may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program in the electronic device.

[0117] like Figure 7 As shown, the electronic device may further include:

[0118] The transceiver 730 may be connected to the processor 720 or the memory 710 .

[0119] The processor 720 may control the transceiver 730 to communicate with other devices. Specifically, the processor 720 may send information or data to other devices or receive information or data sent by other devices. The transceiver 730 may include a transmitter and a receiver. The transceiver 730 may further include one or more antennas.

[0120] It should be understood that the various components in the electronic device are connected via a bus system, wherein the bus system includes not only a data bus but also a power bus, a control bus and a status signal bus.

[0121] The present application also provides a computer storage medium having a computer program stored thereon, which, when executed by a computer, enables the computer to perform the method of the above-mentioned method embodiment. In other words, the present application also provides a computer program product containing instructions, which, when executed by a computer, enables the computer to perform the method of the above-mentioned method embodiment.

[0122] When software is used for implementation, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a digital video disc (DVD)), or a semiconductor medium (e.g., a solid state drive (SSD)).

[0123] Those skilled in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0124] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the modules is merely a logical function division. In actual implementation, there may be other division methods, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0125] Modules described as separate components may or may not be physically separate, and components displayed as modules may or may not be physical modules, i.e., they may be located in one place or distributed across multiple network elements. Some or all of the modules may be selected based on actual needs to achieve the purpose of the present embodiment. For example, the functional modules in the various embodiments of the present application may be integrated into a processing module, or each module may exist physically separately, or two or more modules may be integrated into a single module.

[0126] The above are only specific embodiments of the present application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A method for extracting a blood vessel centerline tree, characterized in that: include: Acquire an aortic vascular image of the target aorta; the aortic vascular image is a binary image obtained by segmenting a computed tomography angiography (CTA) image; the CTA image is a slice image including the target aorta; Inputting the aorta blood vessel image into a preset surface model generation algorithm to obtain a blood vessel surface model of the target aorta; Inputting the vascular surface model, the vascular starting point of the target aorta, and at least one vascular ending point of the target aorta into a preset centerline extraction algorithm to obtain an aortic vascular centerline tree of the target aorta; wherein the at least one vascular ending point includes a left iliac ending point or a right iliac ending point; the aortic vascular centerline tree includes at least one vascular centerline; and the at least one vascular centerline corresponds one-to-one to the at least one vascular ending point. Each of the at least one vascular centerline is traversed, the point coordinates of the vascular centerline that meets a preset condition are updated as the point coordinates of the reference centerline, and the aortic vascular centerline tree is updated; the preset condition is: compared with the reference centerline, the position deviation value is less than a preset deviation threshold; the reference centerline is the vascular centerline corresponding to the left iliac termination point or the right iliac termination point.

2. The method according to claim 1, characterized in that The traversing each of the at least one blood vessel centerline, updating the point coordinates of the blood vessel centerline that meets the preset conditions as the point coordinates of the reference centerline, and updating the aorta blood vessel centerline tree, includes: According to a preset data conversion function, centerline dictionary data corresponding to the aortic vessel centerline tree is obtained; the centerline dictionary data includes a dictionary identifier, an identity identifier ID array, and a point coordinate array; the dictionary identifier is used to mark the centerline sequence of the vessel centerline; the identity identifier ID array includes a point sequence set of all pixel points included in the vessel centerline marked by the dictionary identifier, and the point coordinate array includes three-dimensional coordinate data of all pixel points included in the vessel centerline marked by the dictionary identifier; the pixel points corresponding to the point coordinate array start from the vessel starting point and end at the vessel ending point of the vessel centerline marked by the dictionary identifier; Determining the blood vessel centerline corresponding to the left iliac termination point or the right iliac termination point as the reference centerline; traversing each of the at least one blood vessel centerline in the order of the dictionary identifiers, comparing the point coordinate array corresponding to each blood vessel centerline with the point coordinate array corresponding to the reference centerline, and calculating position deviation values ​​of pixel pairs starting from the blood vessel starting point; If the position deviation value is less than a preset deviation threshold, obtaining the reference point coordinates and reference point sequence of the pixel points belonging to the reference center line in the pixel point pair corresponding to the position deviation value, replacing the point coordinates of the pixel points that do not belong to the reference center line in the pixel point pair corresponding to the position deviation value with the reference point coordinates, and at the same time, replacing the point sequence of the pixel points that do not belong to the reference center line in the pixel point pair corresponding to the position deviation value with the reference point sequence; Resetting the point sequence in the ID array corresponding to each blood vessel centerline except the reference point sequence according to the point sequence step between different pixel points in the reference centerline; The aorta centerline tree is updated according to the replaced point coordinates, the replaced point sequence and the reset point sequence.

3. The method according to claim 1, characterized in that After acquiring the aortic blood vessel image of the target aorta, the method further includes: The aortic vessel image is subjected to expansion and corrosion processing according to a preset expansion kernel radius and a preset corrosion kernel radius to obtain an aortic vessel image after defect repair.

4. The method according to claim 1, wherein The blood vessel surface model includes at least two blood vessel patches. After inputting the aortic blood vessel image into a preset surface model generation algorithm to obtain the blood vessel surface model of the target aorta, the method further includes: Performing a patch extraction operation on the blood vessel surface model to update the blood vessel surface model; the patch extraction operation is used to attenuate the number of patches.

5. The method according to claim 1, characterized in that After inputting the aortic vessel image into a preset surface model generation algorithm to obtain the vessel surface model of the target aorta, the method further includes: Based on a preset smoothing algorithm, the blood vessel surface model is smoothed according to a preset smoothness threshold.

6. The method according to any one of claims 1 to 5, characterized in that After updating the aortic vessel centerline tree, the method further includes: Each vascular centerline in the aortic vascular centerline tree is smoothed and uniformly processed according to the preset point distance step.

7. A device for extracting a blood vessel centerline tree, characterized in that: include: An image acquisition module is configured to acquire an aortic vascular image of a target aorta; the aortic vascular image is a binary image obtained by segmenting a computed tomography angiography (CTA) image; the CTA image is a slice image including the target aorta; A patch acquisition module, configured to input the aorta blood vessel image into a preset surface model generation algorithm to obtain a blood vessel surface model of the target aorta; a line tree extraction module, configured to input the vascular surface model, the vascular starting point of the target aorta, and at least one vascular ending point of the target aorta into a preset centerline extraction algorithm to obtain an aortic vascular centerline tree of the target aorta; wherein the at least one vascular ending point includes a left iliac ending point or a right iliac ending point; the aortic vascular centerline tree includes at least one vascular centerline; and the at least one vascular centerline corresponds one-to-one to the at least one vascular ending point. A line tree updating module is configured to traverse each of the at least one vascular centerline, update the point coordinates of the vascular centerline that meets a preset condition to the point coordinates of the reference centerline, and update the aortic vascular centerline tree; the preset condition is that the position deviation value compared with the reference centerline is less than a preset deviation threshold; the reference centerline is the vascular centerline corresponding to the left iliac termination point or the right iliac termination point.

8. An electronic device, characterized in that: include: A processor and a memory, the memory being used to store a computer program, and the processor being used to call and run the computer program stored in the memory to execute the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that Used to store a computer program, wherein the computer program causes a computer to execute the method according to any one of claims 1 to 6.

10. A computer program product comprising instructions, characterized in that When the computer program product is run on an electronic device, the electronic device is enabled to execute the method according to any one of claims 1 to 6.

Images