Vessel centerline extraction method and device, and vessel straightening method and device

Abstract

The application provides a blood vessel center line extraction method and device, a blood vessel straightening method and device, an electronic device and a computer readable storage medium, and relates to the field of medical image processing. The method comprises the following steps: determining the blood vessel segmentation data, the blood vessel skeleton and the region CTA image of each target blood vessel region based on the head and neck CTA image and the blood vessel segmentation data of the head and neck CTA image; for each target blood vessel region in the plurality of target blood vessel regions, determining the optimal path between the starting point and the ending point of the blood vessel skeleton based on the CT value of the pixel in the region CTA image of the target blood vessel region and the blood vessel segmentation data of the target blood vessel region; determining the center line of the target blood vessel region based on the optimal path to obtain the center line corresponding to the target blood vessel region; and fusing the blood vessel skeleton of the target blood vessel region and the center line corresponding to the target blood vessel region to obtain the blood vessel center line corresponding to the target blood vessel region. The method can effectively alleviate the center line deviation problem, so that a more accurate blood vessel center line is obtained.

Description

Technical Field

[0001] This application relates to the field of medical image processing, specifically to a method and apparatus for extracting the centerline of blood vessels, a method and apparatus for straightening blood vessels, an electronic device, and a computer-readable storage medium. Background Technology

[0002] Extracting the vascular centerline is a core foundational task in clinical practice and product development. The extracted centerline can be used for vascular modeling, visualization analysis, and interventional surgical navigation, which is of great significance for the subsequent diagnosis and treatment of vascular diseases. Therefore, accurately extracting the vascular centerline is crucial.

[0003] However, traditional methods for extracting the centerline of blood vessels cannot accurately obtain the centerline of blood vessels when faced with complex situations such as tortuous or adhered blood vessels. Summary of the Invention

[0004] In view of this, embodiments of this application provide a method and apparatus for extracting the centerline of a blood vessel, a method and apparatus for straightening a blood vessel, an electronic device, and a computer-readable storage medium to solve the problem of being unable to accurately obtain the centerline of a blood vessel when faced with complex situations such as tortuous or adhered blood vessels.

[0005] According to a first aspect of the embodiments of this application, a method for extracting the centerline of a blood vessel is provided. The method includes: determining, based on a head and neck CTA image and blood vessel segmentation data from the head and neck CTA image, blood vessel segmentation data, blood vessel segmentation data, and regional CTA images of multiple target blood vessel regions; for each target blood vessel region, determining, based on the CT values ​​of pixels in the regional CTA image of the target blood vessel region and the blood vessel segmentation data of the target blood vessel region, an optimal path between the start and end points of the blood vessel segmentation data; determining the midline corresponding to the target blood vessel region based on the optimal path; and fusing the blood vessel segmentation data and the midline corresponding to the target blood vessel region to obtain the centerline of the blood vessel region corresponding to the target blood vessel region.

[0006] In one embodiment, determining the optimal path between the start and end points of a vascular skeleton based on the CT values ​​of pixels in a regional CTA image of the target vascular region and vascular segmentation data of the target vascular region includes: determining a distance map corresponding to the vascular segmentation data, wherein the distance map is used to characterize the distance between each pixel in the vascular segmentation data and the contour data corresponding to the vascular segmentation data; performing window transformation and weight mapping operations on the regional CTA image based on the vascular segmentation data and the CT values ​​of each pixel in the regional CTA image to obtain a weight map corresponding to the regional CTA image, wherein the weight map is used to characterize the weight of each pixel in the regional CTA image; performing pixel-wise weighting on the distance map and the weight map to obtain a weighted distance value corresponding to each pixel in the vascular segmentation data, thereby determining the distance weight map corresponding to the target vascular region; and searching for the optimal path between the start and end points based on the distance weight map.

[0007] In one embodiment, based on blood vessel segmentation data and the CT values ​​of pixels in a regional CTA image, a window transformation operation and a weight mapping operation are performed on the regional CTA image to obtain a weight map corresponding to the regional CTA image. This includes: determining window width parameters and window level parameters based on blood vessel segmentation data; performing a window transformation operation on the regional CTA image using the window width parameters and window level parameters; and mapping the CT value of each pixel in the regional CTA image to a preset weight threshold during the window transformation operation to obtain a weight map.

[0008] In one embodiment, searching for the optimal path between the start point and the end point based on the distance weight map includes: selecting the region corresponding to the blood vessel segmentation data between the start point and the end point as the feasible region; using the Dijkstra algorithm within the feasible region based on the distance weight map to find the path with the smallest total distance weight value; and determining the path with the smallest total distance weight value as the optimal path.

[0009] In one embodiment, based on head and neck CTA images and vascular segmentation data from the head and neck CTA images, determining vascular segmentation data, vascular skeletons, and regional CTA images for multiple target vascular regions includes: determining vascular segmentation data for each of the multiple target vascular regions based on the vascular segmentation data from the head and neck CTA images; performing skeleton extraction on the vascular segmentation image of each target vascular region to obtain the vascular skeleton corresponding to the target vascular region; and selecting regional CTA images of the target vascular regions from the head and neck CTA images based on the vascular segmentation data of the target vascular regions.

[0010] According to a second aspect of the embodiments of this application, a method for straightening blood vessels is provided, the method comprising:

[0011] The vascular centerlines corresponding to multiple target vascular regions are determined, and the vascular centerlines corresponding to the target vascular regions are determined based on the vascular centerline extraction method described in the first aspect above; for each target vascular region...

[0012] For each target blood vessel region, the centerline of the blood vessel is straightened using curvature smoothing and frame smoothing operations to obtain the straightened image corresponding to the target blood vessel region.

[0013] According to a third aspect of the embodiments of this application, a vascular centerline extraction device is provided. The device includes: a first determining module configured to determine vascular segmentation data, vascular skeleton, and regional CTA images of multiple target vascular regions based on head and neck CTA images and vascular segmentation data of the head and neck CTA images; a second determining module configured to determine, for each target vascular region 0 in the multiple target vascular regions, an optimal path between the start and end points of the vascular skeleton based on the CT values ​​of pixels in the regional CTA images of the target vascular region and the vascular segmentation data of the target vascular region; a third determining module configured to determine the midline of the target vascular region based on the optimal path, thereby obtaining the midline corresponding to the target vascular region; and a fusion module configured to fuse the vascular skeleton and the midline to obtain the vascular centerline corresponding to the target vascular region.

[0014] 5. According to a fourth aspect of the embodiments of this application, a blood vessel straightening device is provided, the device comprising:

[0015] The vascular centerline determination module is configured to determine the vascular centerlines corresponding to multiple target vascular regions, and the vascular centerlines corresponding to the target vascular regions are determined by the vascular centerline extraction method described in the first aspect above; the straightening module is configured to, for each target vascular region, use curvature smoothing operations...

[0016] The model and frame smoothing operation straightens the centerline of the blood vessel, resulting in a straightened image of the target blood vessel region.

[0017] According to a fifth aspect of the embodiments of this application, an electronic device is provided, including: a processor; and a memory storing computer program instructions, which, when executed by the processor, cause the processor to perform the methods as described in the first or second aspect above.

[0018] According to a sixth aspect of the embodiments of this application, a computer-readable storage medium is provided, on which computer program instructions are stored, which, when executed by a processor, cause the processor to perform the methods as described in the first or second aspect above.

[0019] The vascular centerline extraction method provided in this application determines the optimal path between the start and end points of the vascular skeleton based on the CT values ​​of pixels in the regional CTA image of the target vascular region and the vascular segmentation data of the target vascular region. Based on the optimal path, the midline of the target vascular region is determined, and the vascular skeleton and midline are fused to accurately obtain the vascular centerline corresponding to the target vascular region. Because this extraction method integrates the vascular skeleton extracted based on the skeleton and the midline determined by the optimal path, it can effectively alleviate the midline offset problem caused by vascular tortuosity or adhesion, thereby achieving a more accurate vascular centerline. Therefore, even in complex situations such as vascular tortuosity or adhesion, it can still accurately obtain the vascular centerline. Attached Figure Description

[0020] Figure 1 The diagram shown is a flowchart of a method for extracting the centerline of a blood vessel according to an embodiment of this application.

[0021] Figure 2 The diagram shows vascular segmentation data of a head and neck CTA image and vascular segmentation data of four target vascular regions, provided in an embodiment of this application.

[0022] Figure 3 The diagram shows a flowchart of an embodiment of this application, which uses the CT values ​​of pixels in a regional CTA image of a target blood vessel region and the blood vessel segmentation data of the target blood vessel region to determine the optimal path between the start and end points of the blood vessel skeleton.

[0023] Figure 4 The diagram shown is a schematic diagram of the Distance Map corresponding to the blood vessel segmentation data provided in an embodiment of this application.

[0024] Figure 5 The diagram shown is a flowchart of a blood vessel straightening method provided in an embodiment of this application.

[0025] Figure 6 The diagram shown is a structural schematic of a vascular centerline extraction device provided in an embodiment of this application.

[0026] Figure 7 The diagram shown is a structural schematic of a blood vessel straightening device provided in an embodiment of this application.

[0027] Figure 8 The diagram shown is a structural schematic of an electronic device provided in an embodiment of this application. Detailed Implementation

[0028] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0029] The vascular centerline is of great significance for the subsequent diagnosis and treatment of vascular diseases. Vascular modeling based on the vascular centerline and subsequent visualization analysis allow physicians to observe the three-dimensional structure of blood vessels from any angle, thus facilitating the analysis of vascular diseases and enabling more accurate diagnosis and treatment. Furthermore, interventional vascular surgery has become an effective treatment for vascular diseases, and the vascular centerline can provide the interventional path for navigation. Therefore, accurately extracting the vascular centerline is essential.

[0030] However, traditional methods for extracting the centerline of blood vessels cannot accurately obtain the centerline of blood vessels when faced with complex situations such as tortuous or adhered blood vessels.

[0031] To address the aforementioned issues, this application provides a method for extracting the vascular centerline. By using the CT values ​​of pixels in a regional CTA image of the target vascular region and vascular segmentation data of the target vascular region, the optimal path between the start and end points of the vascular skeleton is determined. Based on this optimal path, the midline of the target vascular region is determined, and the vascular skeleton and midline are fused to accurately obtain the vascular centerline corresponding to the target vascular region. Because this extraction method integrates the vascular skeleton extracted from the skeleton and the midline determined by the optimal path, it effectively alleviates the midline offset problem caused by vascular tortuosity or adhesions, thereby achieving a more accurate vascular centerline. Furthermore, even in complex situations such as vascular tortuosity or adhesions, accurate acquisition of the vascular centerline can still be achieved.

[0032] The following is combined Figures 1 to 8 This application provides a detailed description of the vascular centerline extraction method, vascular centerline extraction device, vascular straightening method, vascular straightening device, electronic device, and computer-readable storage medium mentioned in the embodiments.

[0033] Exemplary method for extracting the centerline of blood vessels

[0034] Figure 1 The diagram shown is a schematic flowchart of a method for extracting the centerline of a blood vessel according to an embodiment of this application. Figure 1 As shown, the method for extracting the centerline of a blood vessel includes the following steps.

[0035] S101: Based on head and neck CTA images and vascular segmentation data of head and neck CTA images, determine the vascular segmentation data, vascular skeleton and regional CTA images of multiple target vascular regions.

[0036] Head and neck CTA images refer to computed tomography (CTA) images of the head and neck.

[0037] Vascular segmentation data in head and neck CTA images refers to segmenting different categories of blood vessels in head and neck CTA images, resulting in segments labeled with different markers (e.g., different colors). For example, Figure 2 The diagram shown is a schematic representation of vascular segmentation data and vascular segmentation data for four target vascular regions in a head and neck CTA image provided in an embodiment of this application. Figure 2 As shown in the first image on the left, the blood vessels in the head and neck CTA image include the aortic arch, left internal carotid artery, left common carotid artery, right internal carotid artery, right common carotid artery, basilar artery, left vertebral artery, left subclavian artery, right vertebral artery, right subclavian artery, brachiocephalic trunk, etc. Different colors are used to represent different types of blood vessel segments.

[0038] It should be noted that, Figure 2 The colors in the image cannot be displayed, but the blood vessel segmentation data is distinguished by different colors.

[0039] For example, the specific implementation of obtaining vascular segmentation data of head and neck CTA images is to input the neck CTA image into a pre-trained vascular segmentation model to obtain vascular segmentation data of head and neck CTA images.

[0040] Target vascular regions refer to the division of all vascular segments into several target vascular regions based on the needs of the actual application scenario. The division of target vascular regions can also be tailored to user requirements. For example, combining... Figure 2 As shown in the second to fifth images from left to right, four target vessel regions were defined using segmented vascular data: Target vessel region 1: left internal carotid artery, left common carotid artery, and aortic arch; Target vessel region 2: right internal carotid artery, right common carotid artery, and aortic arch; Target vessel region 3: basilar artery, left vertebral artery, left subclavian artery, brachiocephalic trunk, and aortic arch; Target vessel region 4: basilar artery, right vertebral artery, right subclavian artery, and aortic arch. Vascular segmentation data refers to the data used to distinguish vessels from the background.

[0041] In some embodiments, the specific implementation of determining the vascular segmentation data, vascular skeleton, and regional CTA image of multiple target vascular regions based on head and neck CTA images and vascular segmentation data of head and neck CTA images is as follows: Based on the vascular segmentation data of head and neck CTA images, determine the vascular segmentation data of multiple target vascular regions; for each target vascular region, perform skeleton extraction (skeletonization) on the vascular segmentation image of the target vascular region to obtain the vascular skeleton corresponding to the target vascular region; and select the regional CTA image of the target vascular region from the head and neck CTA images based on the vascular segmentation data of the target vascular region.

[0042] Specifically, several target vascular regions are pre-defined. Based on vascular segmentation data, vascular segments belonging to each target vascular region are obtained, thus generating a vascular segmentation image for each target vascular region. A skeleton extraction operation is performed on the vascular segmentation images of the target vascular regions to obtain the corresponding vascular skeletons. Based on the vascular segments belonging to each target vascular region, the region image corresponding to the target vascular region is extracted from the head and neck CTA image, and this region image is determined as the regional CTA image of the target vascular region.

[0043] S102: For each target vascular region among multiple target vascular regions, based on the CT values ​​of pixels in the regional CTA image of the target vascular region and the vascular segmentation data of the target vascular region, determine the optimal path between the start and end points of the vascular skeleton.

[0044] The optimal route refers to the route that is most centrally located. Specifically, considering that the vessel contour can be determined based on the vessel segmentation data of the target vessel region, and the position of the vessel contour is closely related to the vessel centerline, the vessel segmentation data of the target vessel region is an important factor in determining the optimal path. Furthermore, considering that vessel segmentation data is not 100% accurate, and that the CT values ​​of the vessel region and the surrounding area differ, and that CT values ​​can, to some extent, correct the vessel segmentation data, thus affecting the vessel centerline, the CT values ​​of pixels in the regional CTA image are also an important factor in determining the optimal path. Based on this, after obtaining the vessel skeleton of the target vessel region, the starting and ending points of the vessel skeleton are first determined. Then, based on the CT values ​​of pixels in the regional CTA image of the target vessel region and the vessel segmentation data of the target vessel region, the optimal path between the starting and ending points is extracted using the TEASAR function.

[0045] CT value is a unit of measurement used in CT scans, commonly known as the Hounsfield unit (HU).

[0046] S103: Determine the midline corresponding to the target vascular region based on the optimal path.

[0047] For example, the optimal path between the start and end points of the vascular skeleton is extracted using the TEASAR function, and this optimal path is determined to be the midline corresponding to the target vascular region.

[0048] The optimal path between the start and end points of the vascular skeleton is extracted using the TEASAR function, and the midline corresponding to the target vascular region is determined based on the optimal path. This can also be understood as extracting the midline corresponding to the target vascular region using the TEASAR function.

[0049] S104: Merge the vascular skeleton of the target vascular region and the midline corresponding to the target vascular region to obtain the vascular centerline corresponding to the target vascular region.

[0050] Specifically, the midline corresponding to the target blood vessel region is extracted based on the TEASAR function, which ensures that the obtained midline is centered in the blood vessel. Furthermore, the blood vessel skeleton is obtained using the skeletonize extraction operation. The combination of these two methods can further effectively alleviate the midline offset problem caused by blood vessel tortuosity or adhesion, thereby obtaining a more accurate blood vessel centerline. Thus, even when facing complex situations such as blood vessel tortuosity or adhesion, the blood vessel centerline can be accurately obtained.

[0051] In this embodiment, the optimal path between the start and end points of the vascular skeleton is determined based on the CT values ​​of pixels in the regional CTA image of the target vascular region and the vascular segmentation data of the target vascular region. The midline of the target vascular region is then determined based on the optimal path, and the vascular skeleton and midline are fused to accurately obtain the vascular centerline corresponding to the target vascular region. Because this extraction method integrates the vascular skeleton extracted based on the skeleton and the midline determined by the optimal path, it can effectively alleviate the midline offset problem caused by vascular tortuosity or adhesion, thereby achieving a more accurate vascular centerline. Furthermore, even in complex situations such as vascular tortuosity or adhesion, the vascular centerline can still be accurately obtained.

[0052] The following is combined Figure 3 This document details the specific implementation method for determining the optimal path between the start and end points of the vascular skeleton based on the CT values ​​of pixels in the regional CTA image of the target vascular region and the vascular segmentation data of the target vascular region.

[0053] Figure 3 The diagram illustrates a flowchart of an embodiment of this application, illustrating the determination of the optimal path between the start and end points of a vascular skeleton based on the CT values ​​of pixels in a regional CTA image of a target vascular region and vascular segmentation data of the target vascular region. Figure 3 As shown, the steps for determining the optimal path between the start and end points of the vascular skeleton based on the CT values ​​of pixels in the regional CTA image of the target vascular region and the vascular segmentation data of the target vascular region include the following steps.

[0054] S301: Determine the distance map corresponding to the blood vessel segmentation data.

[0055] The distance map is used to represent the distance between each pixel in the blood vessel segmentation data and the contour data corresponding to the blood vessel segmentation data.

[0056] For example, determining the distance map corresponding to the blood vessel segmentation data can be performed by obtaining blood vessel contour data based on the blood vessel segmentation data, calculating the distance between each pixel in the blood vessel segmentation data and the blood vessel contour data, thereby obtaining the Distance Map corresponding to the blood vessel segmentation data. Figure 4 The image shown is a fact of this application.

[0057] The example provides a schematic diagram of the Distance Map corresponding to the vessel segmentation data. The specific form of the Distance Map is as follows: Figure 4 As shown, the thickness of each layer of the Distance Map is defined as one pixel width. The further in you go, the more centered the layer becomes, and the smaller the distance.

[0058] The optimal route is known to be the route that is most centrally located within the blood vessel. It is also known that the closer a pixel is to the center, the smaller the distance. Therefore, the optimal route is represented by the shortest path. The shortest path does not refer to the actual shortest physical distance, but rather to the most central location.

[0059] 5S302: Based on blood vessel segmentation data and the CT value of each pixel in the regional CTA image, window transformation and weight mapping operations are performed on the regional CTA image to obtain the weight map corresponding to the regional CTA image.

[0060] Weight maps are used to characterize the weight of each pixel in a region CTA image.

[0061] It is known that blood vessel segmentation data is not 100% accurate, and that the CT values ​​of the blood vessel region and the surrounding region are different. The CT value can correct the blood vessel segmentation data to some extent. In other words, the weights determined based on the CT value can correct the distance map, thereby making the obtained blood vessel centerline more centered.

[0062] For example, based on blood vessel segmentation data and the CT value of each pixel in the regional CTA image, window transformation and weight mapping operations are performed on the regional CTA image to obtain the corresponding...

[0063] The weight map can be generated as follows: Based on vessel segmentation data, determine the window width and window level parameters. Using these parameters, perform a window transformation operation on the regional CTA image. During the window transformation, map the CT value of each pixel in the regional CTA image to a preset weight threshold to obtain the weight map.

[0064] Specifically, the preset weight threshold is between 0 and 1. An adaptive window width and window level are calculated based on the blood vessel segmentation data. The adaptive window width and window level are used to perform window transformation on the regional CTA image. The CT value of each pixel is mapped between [0, 1] to obtain the weight map.

[0065] S303: Perform pixel-by-pixel weighting on the distance map and weight map to obtain the weighted distance value corresponding to each pixel in the blood vessel segmentation data, so as to determine the distance weight map corresponding to the target blood vessel region.

[0066] Specifically, the weight map and the distance map are multiplied pixel by pixel to obtain the distance weight map, which can represent the weighted distance value of each pixel.

[0067] S304: Based on the distance-weighted graph, search for the optimal path between the starting point and the ending point.

[0068] For example, based on the distance weight graph, searching for the optimal path between the starting point and the ending point can be performed as follows: based on the distance weight graph, using Dijkstra's algorithm, search for the path with the smallest total distance weight value within the feasible region; determine the path with the smallest total distance weight value as the optimal path.

[0069] Dijkstra's algorithm is a shortest path algorithm that finds the shortest path from one vertex to all other vertices in a weighted graph.

[0070] Specifically, there are countless possible paths from the starting point through the feasible region to the ending point. According to the distance weight map, the sum of the weighted distance values ​​corresponding to each pixel in each possible path is calculated to obtain the total distance weight value. The Dijkstra algorithm is used to select the path with the smallest total distance weight value, which is the shortest path, also known as the optimal path.

[0071] In this embodiment, a distance weight map is used to constrain the final selected path to move towards the center rather than close to the blood vessel contour, so that the obtained optimal path is centered to the greatest extent, thereby effectively alleviating the midline offset problem caused by blood vessel tortuosity or adhesion, and thus achieving the goal of accurately obtaining the blood vessel centerline even when facing complex situations such as blood vessel tortuosity or adhesion.

[0072] Exemplary method for straightening blood vessels

[0073] After obtaining the centerline of the target blood vessel region, it needs to be straightened to obtain a lumen image for subsequent vascular analysis. Specifically, the straightening operation refers to curved planar reforming (CPR). CPR is often used for vascular analysis because the vascular structure is very tortuous, making it difficult to visually observe the overall state of the blood vessels on CT. CPR can straighten the tortuous blood vessels and display them on a single plane, making it easier to observe the condition of the inner wall of the blood vessels.

[0074] The following is combined Figure 5 This section details the specific implementation method of blood vessel straightening.

[0075] Figure 5 The diagram shown is a schematic flowchart of a blood vessel straightening method provided in an embodiment of this application. Figure 5 As shown, the method for straightening blood vessels includes the following steps.

[0076] S501: Determine the center line of the blood vessels corresponding to each of the multiple target blood vessel regions.

[0077] The vascular centerline corresponding to the target vascular region is determined based on the vascular centerline extraction method provided in any of the above embodiments.

[0078] S502: For each target blood vessel region, straighten the centerline of the blood vessel using curvature smoothing and frame smoothing operations to obtain the straightened image corresponding to the target blood vessel region.

[0079] For example, the specific implementation of straightening the vessel centerline using curvature smoothing and frame smoothing operations to obtain a straightened image of the target vessel region is as follows: Calculate the curvature of the vessel centerline. Perform curvature smoothing on the curvature to obtain a smoothed curvature. Based on the smoothed curvature, construct an initial rotation-minimized frame. Smooth the normals in the initial rotation-minimized frame to perform frame smoothing on the initial rotation-minimized frame, obtaining a smoothed rotation-minimized frame. Use the smoothed rotation-minimized frame to straighten the vessel centerline, obtaining a straightened image of the target vessel region.

[0080] Specifically, after obtaining the centerlines of multiple target vascular regions, each centerline undergoes arc-length parameterization to obtain the curvature of the vascular center. This curvature is then smoothed to obtain a smoothed curvature. The smoothed curvature corresponds to mutually perpendicular coordinate systems at each point on the line, thus constructing an initial rotation minimization frame (RMF). The normals and negative normals in the initial RMF are smoothed to obtain a smoothed RMF. The smoothed RMF is then used to straighten the vascular centerlines, resulting in a lumen image. Because the smoothed RMF has a smaller rotation, the pixel value difference between adjacent pixels is smaller, resulting in a smoother lumen image.

[0081] In this embodiment, CPR is performed based on the smoothed RMF. Compared with the traditional method, the smoothed RMF can significantly reduce the rotation of the frame system, thereby achieving the goal of obtaining a smoother lumen image.

[0082] The above text combined Figures 1 to 5 The method embodiments of this application are described in detail below, in conjunction with... Figure 6 and Figure 7 The present application provides a detailed description of the apparatus embodiments. Furthermore, it should be understood that the descriptions of the method embodiments correspond to the descriptions of the apparatus embodiments; therefore, any parts not described in detail can be found in the preceding method embodiments.

[0083] Exemplary vascular centerline extraction device

[0084] Figure 6 The diagram shown is a structural schematic of a vascular centerline extraction device provided in an embodiment of this application. Figure 6 As shown, the vascular centerline extraction device 600 provided in this application embodiment includes a first determining module 610, a second determining module 620, a third determining module 630, and a fusion module 640.

[0085] In this embodiment, the first determining module 610 is configured to determine, based on head and neck CTA images and vascular segmentation data of the head and neck CTA images, the vascular segmentation data of each of multiple target vascular regions, their respective vascular segmentation data, vascular skeletons, and regional CTA images. The second determining module 620 is configured to, for each of the multiple target vascular regions, determine the optimal path between the start and end points of the vascular skeleton based on the CT values ​​of pixels in the regional CTA image of the target vascular region and the vascular segmentation data of the target vascular region. The third determining module 630 is configured to determine the midline of the target vascular region based on the optimal path, thereby obtaining the midline corresponding to the target vascular region. The fusion module 640 is configured to fuse the vascular skeleton and the midline to obtain the vascular centerline corresponding to the target vascular region.

[0086] In this embodiment, the optimal path between the start and end points of the vascular skeleton is determined based on the CT values ​​of pixels in the regional CTA image of the target vascular region and the vascular segmentation data of the target vascular region. The midline of the target vascular region is then determined based on the optimal path, and the vascular skeleton and midline are fused to accurately obtain the vascular centerline corresponding to the target vascular region. Because this extraction method integrates the vascular skeleton extracted based on the skeleton and the midline determined by the optimal path, it can effectively alleviate the midline offset problem caused by vascular tortuosity or adhesion, thereby achieving the goal of obtaining a more accurate vascular centerline.

[0087] In one embodiment, the second determining unit 620 is further configured to determine a distance map corresponding to the vessel segmentation data, wherein the distance map is used to characterize the distance between each pixel in the vessel segmentation data and the contour data corresponding to the vessel segmentation data. Based on the vessel segmentation data and the CT value of each pixel in the regional CTA image, a window transformation operation and a weight mapping operation are performed on the regional CTA image to obtain a weight map corresponding to the regional CTA image, wherein the weight map is used to characterize the weight of each pixel in the regional CTA image. The distance map and the weight map are weighted pixel by pixel to obtain the weighted distance value corresponding to each pixel in the vessel segmentation data, so as to determine the distance weight map corresponding to the target vessel region. Based on the distance weight map, the optimal path between the starting point and the ending point is searched.

[0088] In one embodiment, the second determining unit 620 is further configured to determine window width parameters and window level parameters based on blood vessel segmentation data. Using the window width parameters and window level parameters, a window transformation operation is performed on the regional CTA image. During the window transformation operation, the CT value of each pixel in the regional CTA image is mapped to a preset weight threshold to obtain a weighted map.

[0089] In one embodiment, the second determining unit 620 is further configured to select the region corresponding to the blood vessel segmentation data between the starting point and the ending point as the feasible region. Based on the distance weight map, the Dijkstra algorithm is used to search for the path with the minimum total distance weight value within the feasible region. The path with the minimum total distance weight value is determined as the optimal path.

[0090] In one embodiment, the first determining unit 610 is further configured to determine vascular segmentation data for multiple target vascular regions based on vascular segmentation data from head and neck CTA images. For each target vascular region, a skeleton extraction operation is performed on the vascular segmentation image of the target vascular region to obtain the vascular skeleton corresponding to the target vascular region. Based on the vascular segmentation data of the target vascular region, a regional CTA image of the target vascular region is selected from the head and neck CTA images.

[0091] Exemplary blood vessel straightening device

[0092] Figure 7 The diagram shown is a structural schematic of a blood vessel straightening device provided in an embodiment of this application. Figure 7 As shown, the blood vessel straightening device 700 provided in this application embodiment includes a blood vessel centerline determination module 710 and a straightening module 720.

[0093] In this embodiment, the vessel centerline determination module 710 is configured to determine the vessel centerline corresponding to each of multiple target vessel regions, wherein the vessel centerline corresponding to the target vessel region is determined based on the vessel centerline extraction method provided in any of the above embodiments. The straightening module 720 is configured to perform a straightening operation on the vessel centerline for each target vessel region using curvature smoothing and frame smoothing operations to obtain a straightened image corresponding to the target vessel region.

[0094] In this embodiment, CPR is performed based on the smoothed RMF. Compared with the traditional method, the smoothed RMF can significantly reduce the rotation of the frame system, thereby achieving the goal of obtaining a smoother lumen image.

[0095] In one embodiment, the straightening module 720 is further configured to calculate the curvature of the vessel centerline. A curvature smoothing operation is performed on the curvature to obtain a smoothed curvature. Based on the smoothed curvature, an initial rotation-minimized frame is constructed. The normals in the initial rotation-minimized frame are smoothed to perform a frame smoothing operation on the initial rotation-minimized frame, resulting in a smoothed rotation-minimized frame. The smoothed rotation-minimized frame is used to straighten the vessel centerline to obtain a straightened image corresponding to the target vessel region.

[0096] Exemplary electronic devices and computer-readable storage media

[0097] Figure 8 The diagram shown is a structural schematic of an electronic device provided in an embodiment of this application. Figure 8 The electronic device 800 shown (which may specifically be a computer device) includes a memory 801, a processor 802, a communication interface 803, and a bus 804. The memory 801, processor 802, and communication interface 803 are interconnected via the bus 804.

[0098] The memory 801 may be a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 801 may store a program. When the program stored in the memory 801 is executed by the processor 802, the processor 802 and the communication interface 803 are used to execute the various steps of the vascular centerline extraction method or vascular straightening method of the embodiments of this application.

[0099] The processor 802 may be a general-purpose central processing unit (CPU), microprocessor, application specific integrated circuit (ASIC), graphics processing unit (GPU), or one or more integrated circuits, used to execute relevant programs to achieve the functions required by the units in the vascular centerline extraction device or vascular straightening device of this application embodiment.

[0100] The processor 802 can also be an integrated circuit chip with signal processing capabilities. During implementation, each step of the vessel centerline extraction method or vessel straightening method of this application can be completed by the integrated logic circuitry in the hardware of the processor 802 or by instructions in software form. The aforementioned processor 802 can also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules can be located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in the memory 801. The processor 802 reads the information in the memory 801 and, in conjunction with its hardware, performs the functions required by the units included in the vascular centerline extraction device or vascular straightening device of this application embodiment, or performs the vascular centerline extraction method or vascular straightening method of this application method embodiment.

[0101] The communication interface 803 uses transceiver devices, such as, but not limited to, transceivers, to enable communication between the electronic device 800 and other devices or communication networks.

[0102] Bus 804 may include a pathway for transmitting information between various components of electronic device 800 (e.g., memory 801, processor 802, communication interface 803).

[0103] It should be noted that, although Figure 8The illustrated electronic device 800 only shows the memory, processor, and communication interface. However, those skilled in the art should understand that in specific implementations, the electronic device 800 may also include other devices necessary for normal operation. Furthermore, depending on specific needs, those skilled in the art should understand that the electronic device 800 may also include hardware devices for implementing other additional functions. Moreover, those skilled in the art should understand that the electronic device 800 may only include the devices necessary for implementing the embodiments of this application, and may not necessarily include... Figure 8 All the devices shown.

[0104] In addition to the methods, apparatus, and devices described above, embodiments of this application may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform various steps of the vascular centerline extraction method or vascular straightening method provided in the various embodiments of this application.

[0105] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this application. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0106] Furthermore, embodiments of this application may also be computer-readable storage media storing computer program instructions thereon, which, when executed by a processor, cause the processor to perform various steps of the vascular centerline extraction method or vascular straightening method provided in the various embodiments of this application.

[0107] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may, for example, include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0108] Those skilled in the art will recognize that the units and algorithm steps of the various examples 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 implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art 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.

[0109] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0110] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0111] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0112] In addition, the functional units in the various embodiments of this application can be integrated into a similar region segmentation unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0113] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory, random access memory, magnetic disks, or optical disks.

[0114] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for extracting the centerline of a blood vessel, characterized in that, include: Based on head and neck CTA images and the vascular segmentation data of the head and neck CTA images, vascular segmentation data, vascular skeletons and regional CTA images of multiple target vascular regions are determined. For each of the multiple target vascular regions, based on the CT values ​​of pixels in the regional CTA image of the target vascular region and the vascular segmentation data of the target vascular region, the optimal path between the start and end points of the vascular skeleton is determined. Based on the optimal path, the midline corresponding to the target vascular region is determined; By fusing the vascular skeleton of the target vascular region and the midline corresponding to the target vascular region, the vascular centerline corresponding to the target vascular region is obtained. The determination of the optimal path between the start and end points of the vascular skeleton based on the CT values ​​of pixels in the regional CTA image of the target vascular region and the vascular segmentation data of the target vascular region includes: Determine a distance map corresponding to the blood vessel segmentation data, wherein the distance map is used to characterize the distance between each pixel in the blood vessel segmentation data and the contour data corresponding to the blood vessel segmentation data; Based on the blood vessel segmentation data and the CT value of each pixel in the regional CTA image, a window transformation operation and a weight mapping operation are performed on the regional CTA image to obtain a weight map corresponding to the regional CTA image. The weight map is used to characterize the weight of each pixel in the regional CTA image. The distance map and the weight map are weighted pixel by pixel to obtain the weighted distance value corresponding to each pixel in the blood vessel segmentation data, so as to determine the distance weight map corresponding to the target blood vessel region; Based on the distance weight graph, the optimal path between the starting point and the ending point is searched.

2. The method according to claim 1, characterized in that, The step of performing window transformation and weight mapping operations on the regional CTA image based on the blood vessel segmentation data and the CT values ​​of pixels in the regional CTA image to obtain a weight map corresponding to the regional CTA image includes: Based on the blood vessel segmentation data, the window width parameter and window level parameter are determined; The window transformation operation is performed on the CTA image of the region using the window width parameter and the window level parameter; During the window transformation operation, the CT value of each pixel in the regional CTA image is mapped to a preset weight threshold to obtain the weight map.

3. The method according to claim 1, characterized in that, The step of searching for the optimal path between the starting point and the ending point based on the distance weight graph includes: Select the region corresponding to the blood vessel segmentation data between the starting point and the ending point as the feasible region; Based on the distance weight graph, the Dijkstra algorithm is used to search for the path with the minimum total distance weight value within the feasible region. The path with the smallest total distance weight value is determined as the optimal path.

4. The method according to any one of claims 1 to 3, characterized in that, The determination of vascular segmentation data, vascular skeleton, and regional CTA images for multiple target vascular regions based on head and neck CTA images and vascular segmentation data of the head and neck CTA images includes: Based on the vascular segmentation data of head and neck CTA images, the vascular segmentation data of each of the multiple target vascular regions is determined. For each target blood vessel region in the target blood vessel region, a skeleton extraction operation is performed on the blood vessel segmentation image of the target blood vessel region to obtain the blood vessel skeleton corresponding to the target blood vessel region. Based on the vascular segmentation data of the target vascular region, a regional CTA image of the target vascular region is selected from the head and neck CTA image.

5. A method for straightening blood vessels, characterized in that, include: Determine the vascular centerline corresponding to each of multiple target vascular regions, wherein the vascular centerline corresponding to the target vascular region is determined based on the vascular centerline extraction method provided in any one of claims 1 to 4; For each target blood vessel region, the centerline of the blood vessel is straightened using curvature smoothing and frame smoothing operations to obtain a straightened image corresponding to the target blood vessel region.

6. The method according to claim 5, characterized in that, The process of straightening the blood vessel centerline using curvature smoothing and frame smoothing operations to obtain a straightened image corresponding to the target blood vessel region includes: Calculate the curvature of the vessel's centerline; Perform the curvature smoothing operation on the curvature to obtain the smoothed curvature; Based on the smoothed curvature, an initial rotation minimization framework is constructed; The normals in the initial rotation minimization frame are smoothed to perform the frame smoothing operation on the initial rotation minimization frame, resulting in the smoothed rotation minimization frame. The smoothed and rotated minimized framework is used to straighten the center line of the blood vessel to obtain a straightened image corresponding to the target blood vessel region.

7. A device for extracting the central line of a blood vessel, characterized in that, include: The first determining module is configured to determine the vascular segmentation data, vascular skeleton and regional CTA images of multiple target vascular regions based on head and neck CTA images and vascular segmentation data of the head and neck CTA images. The second determining module is configured to, for each of the plurality of target vascular regions, determine the optimal path between the start and end points of the vascular skeleton based on the CT values ​​of pixels in the regional CTA image of the target vascular region and the vascular segmentation data of the target vascular region. The third determining module is configured to determine the midline corresponding to the target vascular region based on the optimal path; The fusion module is configured to fuse the vascular skeleton and the midline to obtain the vascular centerline corresponding to the target vascular region. The determination of the optimal path between the start and end points of the vascular skeleton based on the CT values ​​of pixels in the regional CTA image of the target vascular region and the vascular segmentation data of the target vascular region includes: Determine a distance map corresponding to the blood vessel segmentation data, wherein the distance map is used to characterize the distance between each pixel in the blood vessel segmentation data and the contour data corresponding to the blood vessel segmentation data; Based on the blood vessel segmentation data and the CT value of each pixel in the regional CTA image, a window transformation operation and a weight mapping operation are performed on the regional CTA image to obtain a weight map corresponding to the regional CTA image. The weight map is used to characterize the weight of each pixel in the regional CTA image. The distance map and the weight map are weighted pixel by pixel to obtain the weighted distance value corresponding to each pixel in the blood vessel segmentation data, so as to determine the distance weight map corresponding to the target blood vessel region; Based on the distance weight graph, the optimal path between the starting point and the ending point is searched.

8. A blood vessel straightening device, characterized in that, include: The vascular centerline determination module is configured to determine the vascular centerline corresponding to each of multiple target vascular regions, wherein the vascular centerline corresponding to the target vascular region is determined based on the vascular centerline extraction method provided in any one of claims 1 to 4. The straightening module is configured to perform a straightening operation on the centerline of each target blood vessel region using curvature smoothing and frame smoothing operations to obtain a straightened image corresponding to the target blood vessel region.

9. An electronic device, characterized in that, include: processor; as well as A memory storing computer program instructions that, when executed by the processor, cause the processor to perform the method as described in any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions that, when executed by a processor, cause the processor to perform the method as described in any one of claims 1 to 6.

Images