A blood vessel curved surface reconstruction method, a blood vessel curved surface reconstruction device, equipment and a medium
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHENZHEN RAYSIGHT INTELLIGENT MEDICAL TECH CO LTD
- Filing Date
- 2022-12-30
- Publication Date
- 2026-07-24
AI Technical Summary
Existing surface reconstruction techniques using the original vascular centerline to generate the reconstructed surface exhibit distortion and discontinuity, especially due to the numerous inflection points and uneven curvature of the original vascular centerline.
By acquiring the vascular centerline, determining multiple original centerline control points, performing spline interpolation and curve smoothing, generating a spline curve with normal direction information, and using the normal vector on the smoothed centerline to generate surface sampling points, reducing inflection points and uniform curvature, a smooth reconstructed surface is generated.
The generated reconstructed surface is smoother, reducing the tomography between adjacent pixels and improving the quality of vascular surface reconstruction.
Smart Images
Figure CN115861471B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of medical image processing technology, and more specifically, to a method, device, equipment, and medium for vascular surface reconstruction. Background Technology
[0002] Computed tomography (CT) and magnetic resonance imaging (MRI) are now widely used in hospitals for imaging tubular structures such as blood vessels. CT and MRI provide high-resolution volumetric data, which, when analyzed and processed, allows for visualization of anatomical structures like blood vessels. Curved surface reconstruction techniques can straighten tortuous images of blood vessels and other tubular structures and display them on a single plane.
[0003] Currently, existing surface reconstruction techniques often use the original centerline of blood vessels. However, because the original centerline of blood vessels has many inflection points and its curvature is not uniform, existing methods directly use the original centerline for sampling, resulting in some distortions or even tortuosity in the generated reconstructed surface. Summary of the Invention
[0004] In view of this, the purpose of this application is to provide a method, device, equipment and medium for vascular surface reconstruction, which can determine the direction information of all center points in the spline curve according to the direction information of the smooth center line, and obtain a spline curve with normal direction information. Using the spline curve to complete the surface reconstruction, the generated reconstructed surface will be smoother and the discontinuity phenomenon between adjacent pixels of the surface will be reduced.
[0005] In a first aspect, embodiments of this application provide a method for reconstructing vascular surfaces, the method comprising:
[0006] Obtain the vessel centerline in the original medical image, and determine multiple original centerline control points in the vessel centerline;
[0007] Spline interpolation is performed on the multiple original centerline control points to obtain a spline curve, and equal-interval sampling is performed on the spline curve at a first preset distance to obtain multiple first center points;
[0008] The multiple original centerline control points are input into spline approximation for curve smoothing to obtain a smoothed centerline. Then, samples are taken at equal intervals along the smoothed centerline at a second preset distance to obtain multiple second center points. The second preset distance is less than the first preset distance.
[0009] The normal vector of each second center point on the smooth center line is determined using the pixel coordinates of each second center point in the original medical image.
[0010] The normal vector of each first center point is determined based on the positional relationship between each first center point and each second center point, and the normal vector of each second center point.
[0011] Multiple surface sampling points are generated based on the position and normal vector of each first center point, and the surface reconstruction result of the blood vessel is generated based on the multiple surface sampling points.
[0012] Furthermore, determining the normal vector of each second center point in the original medical image using the pixel coordinates of each second center point on the smoothed center line includes:
[0013] For each second center point, the tangent vector of the second center point is determined based on the pixel coordinates of the second center point and the pixel coordinates of the second center points adjacent to the second center point;
[0014] For the first second center point among the plurality of second center points, the normal vector of the first second center point is determined based on the tangent vector of the first second center point;
[0015] Determine the next second center point adjacent to the first second center point, and determine the binormal vector of the next second center point based on the normal vector of the first second center point and the tangent vector of the next second center point;
[0016] The normal vector of the next second center point is determined based on the tangent vector of the next second center point and the binormal vector of the next second center point.
[0017] The next second center point is determined as the first second center point, and the process returns to the step of determining the next second center point adjacent to the first second center point, until there is no next second center point adjacent to the first second center point.
[0018] Furthermore, determining the tangent vector of the second center point based on the pixel coordinates of the second center point and the pixel coordinates of the second center points adjacent to the second center point includes:
[0019] When the second center point is the starting second center point among the plurality of second center points, the first pixel coordinates of the starting second center point in the original medical image and the second pixel coordinates of the first adjacent center point adjacent to the starting second center point in the original medical image are determined, and the tangent vector of the starting second center point is determined based on the first pixel coordinates and the second pixel coordinates.
[0020] When the second center point is the last second center point among the plurality of second center points, the third pixel coordinate of the last second center point in the original medical image and the fourth pixel coordinate of the second adjacent center point adjacent to the last second center point in the original medical image are determined, and the tangent vector of the last second center point is determined based on the third pixel coordinate and the fourth pixel coordinate.
[0021] When the second center point is any one of the plurality of second center points other than the starting second center point and the ending second center point, the fifth pixel coordinate of the next second center point adjacent to the second center point in the original medical image and the sixth pixel coordinate of the previous second center point adjacent to the second center point in the original medical image are determined, and the tangent vector of the second center point is determined based on the fifth pixel coordinate and the sixth pixel coordinate.
[0022] Furthermore, determining the normal vector of each first center point based on the positional relationship between each first center point and each second center point, and the normal vector of each second center point, includes:
[0023] For each first center point, the distance between the first center point and each second center point is determined based on the pixel coordinates of the first center point in the original medical image and the pixel coordinates of each second center point in the original medical image.
[0024] The normal vector of the second center point that is closest to the first center point among the plurality of second center points is determined as the normal vector of the first center point.
[0025] Furthermore, the step of generating multiple surface sampling points based on the position and normal vector of each first center point, and generating the surface reconstruction result of the blood vessel based on the multiple surface sampling points, includes:
[0026] For each first center point, multiple equally spaced surface sampling points are created along the positive and negative directions of the normal vector of the first center point, with the first center point as the center.
[0027] Linear interpolation is performed on the original medical image using the surface sampling points corresponding to each first center point, and the two-dimensional image generated in the original medical image along the spline curve is determined as the surface reconstruction result of the blood vessel.
[0028] Secondly, embodiments of this application also provide a vascular surface reconstruction device, the vascular surface reconstruction device comprising:
[0029] The centerline control point generation module is used to acquire the centerline of blood vessels in the original medical image and determine multiple original centerline control points in the centerline of blood vessels.
[0030] The first center point generation module is used to perform spline interpolation on the multiple original centerline control points to obtain a spline curve, and to perform equal-interval sampling on the spline curve according to a first preset distance to obtain multiple first center points;
[0031] The second center point generation module is used to input the multiple original centerline control points into spline approximation for curve smoothing to obtain a smooth centerline, and to sample at equal intervals along the smooth centerline according to a second preset distance to obtain multiple second center points; wherein, the second preset distance is less than the first preset distance;
[0032] The first normal vector determination module is used to determine the normal vector of each second center point in the original medical image using the pixel coordinates of each second center point on the smooth center line.
[0033] The second normal vector determination module is used to determine the normal vector of each first center point based on the positional relationship between each first center point and each second center point and the normal vector of each second center point.
[0034] The surface reconstruction module is used to generate multiple surface sampling points based on the position and normal vector of each first center point, and to generate the surface reconstruction result of the blood vessel based on the multiple surface sampling points.
[0035] Furthermore, when the first normal vector determination module determines the normal vector of each second center point in the original medical image using the pixel coordinates of each second center point on the smoothed center line, the first normal vector determination module is also used for:
[0036] For each second center point, the tangent vector of the second center point is determined based on the pixel coordinates of the second center point and the pixel coordinates of the second center points adjacent to the second center point;
[0037] For the first second center point among the plurality of second center points, the normal vector of the first second center point is determined based on the tangent vector of the first second center point;
[0038] Determine the next second center point adjacent to the first second center point, and determine the binormal vector of the next second center point based on the normal vector of the first second center point and the tangent vector of the next second center point;
[0039] The normal vector of the next second center point is determined based on the tangent vector of the next second center point and the binormal vector of the next second center point.
[0040] The next second center point is determined as the first second center point, and the process returns to the step of determining the next second center point adjacent to the first second center point, until there is no next second center point adjacent to the first second center point.
[0041] Furthermore, when the first normal vector determination module determines the tangent vector of the second center point based on the pixel coordinates of the second center point and the pixel coordinates of the second center points adjacent to the second center point, the first normal vector determination module is also used for:
[0042] When the second center point is the starting second center point among the plurality of second center points, the first pixel coordinates of the starting second center point in the original medical image and the second pixel coordinates of the first adjacent center point adjacent to the starting second center point in the original medical image are determined, and the tangent vector of the starting second center point is determined based on the first pixel coordinates and the second pixel coordinates.
[0043] When the second center point is the last second center point among the plurality of second center points, the third pixel coordinate of the last second center point in the original medical image and the fourth pixel coordinate of the second adjacent center point adjacent to the last second center point in the original medical image are determined, and the tangent vector of the last second center point is determined based on the third pixel coordinate and the fourth pixel coordinate.
[0044] When the second center point is any one of the plurality of second center points other than the starting second center point and the ending second center point, the fifth pixel coordinate of the next second center point adjacent to the second center point in the original medical image and the sixth pixel coordinate of the previous second center point adjacent to the second center point in the original medical image are determined, and the tangent vector of the second center point is determined based on the fifth pixel coordinate and the sixth pixel coordinate.
[0045] Thirdly, embodiments of this application also provide an electronic device, including: a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus. When the machine-readable instructions are executed by the processor, the steps of the vascular surface reconstruction method described above are performed.
[0046] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a computer program that, when executed by a processor, performs the steps of the vascular surface reconstruction method described above.
[0047] The vascular surface reconstruction method and apparatus provided in this application first acquire the vascular centerline in the original medical image and determine multiple original centerline control points on the vascular centerline; then, perform spline interpolation on the multiple original centerline control points to obtain a spline curve, and sample the center point positions at equal intervals according to a first preset distance on the spline curve to obtain multiple first center points; input the multiple original centerline control points into spline approximation for curve smoothing to obtain a smoothed centerline, and sample the center point positions at equal intervals according to a second preset distance on the smoothed centerline to obtain multiple second center points; use the pixel coordinates of each second center point on the smoothed centerline in the original medical image to determine the normal vector of each second center point; determine the normal vector of each first center point based on the positional relationship between each first center point and each second center point and the normal vector of each second center point; finally, generate multiple surface sampling points based on the position and normal vector of each first center point, and generate the vascular surface reconstruction result based on the multiple surface sampling points.
[0048] The vascular surface reconstruction method provided in this application first generates a spline curve based on multiple original centerline control points in the vascular centerline. Then, it samples the spline curve with equally spaced center points to obtain a set of sparsely spaced center points. Next, the multiple original centerline control points are input into the spline approximation to generate a new smooth centerline. Then, a denser set of equally spaced center points is generated on the smooth centerline, and direction information of the smooth centerline is generated at the center point positions. Based on the direction information of the smooth centerline, the direction information of all center points in the spline curve is determined, thus obtaining a spline curve with normal direction information. Finally, this spline curve is used to complete the surface reconstruction. According to the vascular surface reconstruction method provided in this application, the generated reconstructed surface is smoother and reduces the discontinuity between adjacent pixel layers.
[0049] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description
[0050] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.
[0051] Figure 1 A flowchart of a method for reconstructing vascular surfaces provided in an embodiment of this application;
[0052] Figure 2 A flowchart illustrating a method for determining the normal vector of a second center point, provided in an embodiment of this application.
[0053] Figure 3 This is a schematic diagram of the structure of a vascular surface reconstruction device provided in an embodiment of this application;
[0054] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation
[0055] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, 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. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. Based on the embodiments of this application, every other embodiment obtained by those skilled in the art without inventive effort falls within the scope of protection of this application.
[0056] First, the applicable scenarios for this application will be introduced. This application can be applied to the field of medical image processing technology.
[0057] Computed tomography (CT) and magnetic resonance imaging (MRI) are now widely used in hospitals for imaging tubular structures such as blood vessels. CT and MRI provide high-resolution volumetric data, which, when analyzed and processed, allows for visualization of anatomical structures like blood vessels. Curved surface reconstruction techniques can straighten tortuous images of blood vessels and other tubular structures and display them on a single plane.
[0058] Currently, the existing surface reconstruction techniques follow this approach: A centerline is generated, then the centerline is sampled at equal intervals to generate the direction of the center point; then, using the sampling location as the center, uniform surface sampling line coordinates are generated based on the direction of the sampling point; interpolation is performed based on the surface sampling line coordinates to obtain the reconstructed surface, which often uses the original centerline of the blood vessel. However, because the original centerline of the blood vessel has many inflection points and its curvature is not uniform, existing methods that directly use the original centerline for sampling result in reconstructed surfaces with distortions or even tortuosity.
[0059] Based on this, the embodiments of this application provide a method, apparatus, device and medium for vascular surface reconstruction, which will generate a smoother reconstructed surface and reduce the discontinuity between adjacent pixels of the surface.
[0060] Please see Figure 1 , Figure 1 This is a flowchart illustrating a method for reconstructing vascular surfaces provided in an embodiment of this application. Figure 1 As shown in the embodiments of this application, the method for vascular surface reconstruction includes:
[0061] S101, Obtain the vascular centerline in the original medical image, and determine multiple original centerline control points on the vascular centerline.
[0062] It should be noted that the original medical image refers to a medical image that includes vascular images. The original medical image contains the vascular centerline corresponding to the blood vessel. The original centerline control points are control points extracted from the vascular centerline, used to control the interpolation points of the overall centerline curve.
[0063] Regarding step S101 above, in specific implementation, the original medical image is acquired, the vascular centerline of the blood vessel in the original medical image is determined, and multiple original centerline control points are determined within the vascular centerline. Here, multiple original centerline control points can be marked on the vascular centerline manually, or multiple original centerline control points can be generated on the vascular centerline using an automatic path extraction algorithm. The automatic path extraction algorithm is described in detail in existing technologies and will not be elaborated here.
[0064] S102, perform spline interpolation on the multiple original centerline control points to obtain spline curves, and sample the center point positions at equal intervals on the spline curves according to a first preset distance to obtain multiple first center points.
[0065] It should be noted that a spline curve refers to a curve obtained by performing spline interpolation on multiple centerline control points. Spline interpolation is a mathematical method that uses a variable spline to construct a smooth curve passing through a series of points. The resulting spline curve is a smooth curve passing through all centerline control points. The first preset distance is pre-set, representing the distance at which equally spaced center point positions are sampled on the spline curve. This first preset distance can be set to 0.4 mm, and this application does not impose specific limitations on it. The first center point is the center point obtained after sampling equally spaced center point positions on the spline curve.
[0066] Regarding step S102 above, in specific implementation, after obtaining multiple original centerline control points in step S101, spline interpolation is performed using these multiple original centerline control points to obtain a spline curve. The method for spline interpolation is explained in detail in existing technology and will not be repeated here. Then, center point positions are sampled at equal intervals on the spline curve according to a first preset distance, for example, at equal intervals of 0.4 mm, to obtain multiple equally spaced first center points.
[0067] S103, input the multiple original centerline control points into spline approximation for curve smoothing to obtain a smooth centerline, and sample the center point positions at equal intervals on the smooth centerline according to the second preset distance to obtain multiple second center points.
[0068] It should be noted that curve smoothing refers to minimizing the number of inflection points on a curve and ensuring a uniform curvature change throughout the curve. Therefore, smoothing a curve involves reducing the number of inflection points and achieving a uniform curvature change. The smoothing centerline is a smoothed approximation centerline obtained from multiple first center points, characterized by fewer inflection points and more uniform curvature. The second preset distance is pre-set, representing the distance between equally spaced center point samples along the smoothing centerline. This second preset distance can be set to 0.1 mm, and this application does not impose specific limitations on it. Here, the second preset distance must be less than the first preset distance. The second center point is the center point obtained after sampling equally spaced center point positions along the smoothing centerline.
[0069] Regarding step S103 above, in specific implementation, after obtaining multiple original centerline control points in step S101, these control points are input into spline approximation for curve smoothing to obtain a smoothed centerline. Since the smoothed centerline does not need to pass through every original centerline control point, the number of inflection points can be reduced, and the curvature of the curve can be controlled more uniformly through the energy equation. After obtaining the smoothed centerline, center point positions are sampled at equal intervals along the smoothed centerline according to a second preset distance, for example, at equal intervals of 0.1 mm, to obtain multiple equally spaced second center points. Here, spline approximation can employ methods such as ordinary spline approximation, B-spline approximation, or P-spline approximation; this application does not specifically limit this method.
[0070] S104, using the pixel coordinates of each second center point on the smooth center line in the original medical image to determine the normal vector of each second center point.
[0071] Regarding step S104 above, in specific implementation, the normal vector of each second center point is determined by using the pixel coordinates of each second center point on the smooth center line obtained in step S103 in the original medical image.
[0072] Please see Figure 2 , Figure 2 This is a flowchart illustrating a method for determining the normal vector of a second center point, as provided in an embodiment of this application. Figure 2 As shown, for step S104 above, determining the normal vector of each second center point in the original medical image using the pixel coordinates of each second center point on the smoothed center line includes:
[0073] S201, for each second center point, determine the tangent vector of the second center point based on the pixel coordinates of the second center point and the pixel coordinates of the second center points adjacent to the second center point.
[0074] In specific implementation of step S201, for each second center point, the pixel coordinates of the second center point in the original medical image and the pixel coordinates of the second center points adjacent to the second center point in the original medical image are determined, and the tangent vector of the second center point is determined based on the pixel coordinates of the second center point and the pixel coordinates of the second center points adjacent to the second center point.
[0075] According to the embodiments provided in this application, in specific implementation, multiple second center points on the smooth center line are divided into three categories of second center points: the first category is the starting second center point located at the beginning of the smooth center line; the second category is the ending second center point located at the end of the smooth center line; and the third category is other second center points besides the starting and ending second center points. Regarding step S201 above, determining the tangent vector of the second center point based on its pixel coordinates and the pixel coordinates of the second center points adjacent to it includes:
[0076] A: When the second center point is the starting second center point among the plurality of second center points, determine the first pixel coordinates of the starting second center point in the original medical image and the second pixel coordinates of the first adjacent center point adjacent to the starting second center point in the original medical image, and determine the tangent vector of the starting second center point based on the first pixel coordinates and the second pixel coordinates.
[0077] Regarding step A above, in specific implementation, when the second center point is the starting second center point among multiple second center points, firstly, the first adjacent center point adjacent to the starting second center line is determined, which is the second center line among the smoothed center lines. Then, the first pixel coordinates of the starting second center point and the second pixel coordinates of the first adjacent center point in the original medical image are determined, and the tangent vector of the starting second center point is determined based on the first and second pixel coordinates. Specifically, the tangent vector of the starting second center point can be determined by subtracting the first pixel coordinates of the starting second center point from the second pixel coordinates of the first adjacent center point.
[0078] B: When the second center point is the last second center point among the plurality of second center points, determine the third pixel coordinate of the last second center point in the original medical image and the fourth pixel coordinate of the second adjacent center point adjacent to the last second center point in the original medical image, and determine the tangent vector of the last second center point based on the third pixel coordinate and the fourth pixel coordinate.
[0079] Regarding step B above, in specific implementation, when the second center point is the last second center point among multiple second center points, firstly, determine the second adjacent center point adjacent to the last second center line, which is the second-to-last center line in the smoothed center line. Then, determine the third pixel coordinate of the last second center point in the original medical image and the fourth pixel coordinate of the second adjacent center point in the original medical image, and determine the tangent vector of the last second center point based on the third and fourth pixel coordinates. Specifically, the tangent vector of the last second center point can be determined by subtracting the fourth pixel coordinate of the second adjacent center point from the third pixel coordinate of the last second center point.
[0080] C: When the second center point is any one of the plurality of second center points other than the starting second center point and the ending second center point, determine the fifth pixel coordinate of the next second center point adjacent to the second center point in the original medical image, and the sixth pixel coordinate of the previous second center point adjacent to the second center point in the original medical image, and determine the tangent vector of the second center point based on the fifth pixel coordinate and the sixth pixel coordinate.
[0081] Regarding step C above, in specific implementation, when the second center point is any second center point other than the starting and ending second center points among multiple second center points, first determine the next adjacent second center point and the previous adjacent center line. Then, determine the fifth pixel coordinate of the next second center point in the original medical image and the sixth pixel coordinate of the previous adjacent center point in the original medical image, and determine the tangent vector of the second center point based on the fifth and sixth pixel coordinates. Specifically, the tangent vector of the second center point can be determined by subtracting the sixth pixel coordinate of the previous second center point from the fifth pixel coordinate of the next second center point.
[0082] S202, for the first second center point among the plurality of second center points, determine the normal vector of the first second center point based on the tangent vector of the first second center point.
[0083] Regarding step S202 above, in specific implementation, for the first second center point among multiple second center points, the normal vector of the first second center point is determined based on the tangent vector of the first second center point. Here, the normal direction of the first second center point must be perpendicular to the tangent direction of the first second center point. Knowing the tangent vector of the first second center point, the normal vector of the first second center point can be determined.
[0084] S203, determine the next second center point adjacent to the first second center point, and determine the binormal vector of the next second center point based on the normal vector of the first second center point and the tangent vector of the next second center point.
[0085] S204, determine the normal vector of the next second center point based on the tangent vector of the next second center point and the binormal vector of the next second center point.
[0086] It should be noted that the binormal vector is a concept in spatial analytic geometry. The vector represented by the line perpendicular to the osculating plane at a point on the osculating plane is the binormal vector of that plane. The osculating plane is the tangent plane that most closely approximates the curve.
[0087] Regarding steps S203-S204 above, in specific implementation, firstly, the next second center point adjacent to the first second center point is determined. Then, the binormal vector of the next second center point is determined based on the normal vector of the first second center point and the tangent vector of the next second center point. Specifically, the binormal vector of the next second center point can be obtained by using the cross product between the normal vector of the first second center point and the tangent vector of the next second center point. The binormal vector of the next second center point can be calculated using the following formula:
[0088] B k =N k-1 ×T k
[0089] Where, N k-1 Let T represent the normal vector of the first second center point. k B represents the tangent vector to the next second center point. k This represents the binormal vector of the next second center point.
[0090] After determining the binormal vector of the next second center point, the normal vector of the next second center point is determined based on its tangent vector and binormal vector. Specifically, the normal vector of the next second center point is obtained by the cross product of its tangent vector and binormal vector. The normal vector of the next second center point can be calculated using the following formula:
[0091] N k =T k ×B k
[0092] Where Nk represents the normal vector of the next second center point.
[0093] S205, determine the next second center point as the first second center point, return to the step of determining the next second center point adjacent to the first second center point, until there is no next second center point adjacent to the first second center point.
[0094] Regarding step S205 above, in specific implementation, after calculating the normal vector of the next second center point in step S204, the next second center point is determined as the first second center point. The process then returns to step S203, where the next second center point adjacent to the first second center point is determined. The normal vector of the next second center point is then calculated again until no next second center point adjacent to the first second center point exists. In this way, when the tangent direction angle deviation between two adjacent points is small, this calculation method allows the normal vector of the previous point to participate in the calculation of the normal vector of the next point, ensuring that the deviation between the normal vectors of these two points is also small.
[0095] S105, determine the normal vector of each first center point based on the positional relationship between each first center point and each second center point and the normal vector of each second center point.
[0096] Regarding step S105 above, in specific implementation, after the normal vector of each second center point is determined, the normal vector of each first center point is determined based on the positional relationship between each first center point and each second center point and the normal vector of each second center point.
[0097] Specifically, regarding step S105 above, determining the normal vector of each first center point based on the positional relationship between each first center point and each second center point, and the normal vector of each second center point, includes:
[0098] Step 1051: For each first center point, determine the distance between the first center point and each second center point based on the pixel coordinates of the first center point in the original medical image and the pixel coordinates of each second center point in the original medical image.
[0099] Step 1052: Determine the normal vector of the second center point that is closest to the first center point among the plurality of second center points as the normal vector of the first center point.
[0100] Regarding steps 1051-1052 above, in specific implementation, for each first center point, based on the pixel coordinates of the first center point in the original medical image and the pixel coordinates of each second center point in the original medical image, the distance between the first center point and each second center point is determined. Then, the normal vector of the second center point closest to the first center point among the multiple second center points is determined as the normal vector of the first center point. Thus, by finding the second center point closest to the first center point among all the second center points on the smooth center line, the normal vector of the second center point closest to the first center point is determined as the normal vector of the first center point.
[0101] S106, generate multiple surface sampling points based on the position and normal vector of each first center point, and generate the surface reconstruction result of the blood vessel based on the multiple surface sampling points.
[0102] Here, Curved Planar Reformat (CPR) is a commonly used technique that can straighten tubular images such as curved blood vessels and display them on a plane.
[0103] Regarding step S106 above, in specific implementation, for each first center point, multiple surface sampling points corresponding to the first center point are generated according to the position and normal vector of the first center point, and the surface reconstruction result of the blood vessel is generated according to the multiple surface sampling points corresponding to each first center point.
[0104] Specifically, regarding step S106 above, the step of generating multiple surface sampling points based on the position and normal vector of each first center point, and generating the surface reconstruction result of the blood vessel based on the multiple surface sampling points, includes:
[0105] Step 1061: For each first center point, multiple equally spaced surface sampling points are created along the positive and negative directions of the normal vector of the first center point, with the first center point as the center.
[0106] Step 1062: Linear interpolation is performed on the original medical image using the surface sampling points corresponding to each first center point, and the two-dimensional image generated in the original medical image along the spline curve is determined as the surface reconstruction result of the blood vessel.
[0107] Regarding steps 1061-1062 above, in specific implementation, for each first center point, multiple equally spaced surface sampling points are created along the positive and negative directions of the normal vector of the first center point, centered on that first center point. Here, N uniform sampling positions are taken along the positive and negative directions of the obtained normal vector, centered on the first center point. Thus, there are a total of 2N+1 points on a line, with 2N+1 uniform surface sampling points generated for each first center point. Then, linear interpolation is performed on the original medical image using the surface sampling points corresponding to each first center point, and the resulting two-dimensional image along the spline curve in the original medical image is determined as the surface reconstruction result of the blood vessel. Specifically, the interpolation points corresponding to each first center point are sorted according to the order of the first center points in the spline curve to obtain the two-dimensional unfolded image of the blood vessel, i.e., the surface reconstruction result of the blood vessel. Here, linear interpolation can be performed using methods such as cubic interpolation or spline interpolation, and this application does not specifically limit this method.
[0108] The vascular surface reconstruction method provided in this application firstly acquires the vascular centerline in the original medical image and determines multiple original centerline control points on the vascular centerline; then, it performs spline interpolation on the multiple original centerline control points to obtain a spline curve, and samples the center point positions at equal intervals according to a first preset distance on the spline curve to obtain multiple first center points; it inputs the multiple original centerline control points into spline approximation for curve smoothing to obtain a smoothed centerline, and samples the center point positions at equal intervals according to a second preset distance on the smoothed centerline to obtain multiple second center points; it uses the pixel coordinates of each second center point on the smoothed centerline in the original medical image to determine the normal vector of each second center point; it determines the normal vector of each first center point based on the positional relationship between each first center point and each second center point and the normal vector of each second center point; finally, it generates multiple surface sampling points based on the position and normal vector of each first center point, and generates the vascular surface reconstruction result based on the multiple surface sampling points.
[0109] The vascular surface reconstruction method provided in this application first generates a spline curve based on multiple original centerline control points in the vascular centerline. Then, it samples the spline curve with equally spaced center points to obtain a set of sparsely spaced center points. Next, the multiple original centerline control points are input into the spline approximation to generate a new smooth centerline. Then, a denser set of equally spaced center points is generated on the smooth centerline, and direction information of the smooth centerline is generated at the center point positions. Based on the direction information of the smooth centerline, the direction information of all center points in the spline curve is determined, thus obtaining a spline curve with normal direction information. Finally, this spline curve is used to complete the surface reconstruction. According to the vascular surface reconstruction method provided in this application, the generated reconstructed surface is smoother and reduces the discontinuity between adjacent pixel layers.
[0110] Please see Figure 3 , Figure 3 This is a schematic diagram of the structure of a vascular surface reconstruction device provided in an embodiment of this application. Figure 3 As shown, the vascular surface reconstruction device 300 includes:
[0111] The centerline control point generation module 301 is used to acquire the centerline of the blood vessel in the original medical image and determine multiple original centerline control points in the centerline of the blood vessel.
[0112] The first center point generation module 302 is used to perform spline interpolation on the plurality of original centerline control points to obtain a spline curve, and to perform equal-interval sampling on the spline curve according to a first preset distance to obtain a plurality of first center points;
[0113] The second center point generation module 303 is used to input the plurality of original center line control points into spline approximation for curve smoothing to obtain a smooth center line, and to sample at equal intervals on the smooth center line according to a second preset distance to obtain a plurality of second center points; wherein, the second preset distance is less than the first preset distance.
[0114] The first normal vector determination module 304 is used to determine the normal vector of each second center point in the original medical image using the pixel coordinates of each second center point on the smooth center line.
[0115] The second normal vector determination module 305 is used to determine the normal vector of each first center point based on the positional relationship between each first center point and each second center point and the normal vector of each second center point.
[0116] The surface reconstruction module 306 is used to generate multiple surface sampling points based on the position and normal vector of each first center point, and to generate the surface reconstruction result of the blood vessel based on the multiple surface sampling points.
[0117] Furthermore, when the first normal vector determination module 304 determines the normal vector of each second center point in the original medical image using the pixel coordinates of each second center point on the smoothed center line, the first normal vector determination module 304 is also used to:
[0118] For each second center point, the tangent vector of the second center point is determined based on the pixel coordinates of the second center point and the pixel coordinates of the second center points adjacent to the second center point;
[0119] For the first second center point among the plurality of second center points, the normal vector of the first second center point is determined based on the tangent vector of the first second center point;
[0120] Determine the next second center point adjacent to the first second center point, and determine the binormal vector of the next second center point based on the normal vector of the first second center point and the tangent vector of the next second center point;
[0121] The normal vector of the next second center point is determined based on the tangent vector of the next second center point and the binormal vector of the next second center point.
[0122] The next second center point is determined as the first second center point, and the process returns to the step of determining the next second center point adjacent to the first second center point, until there is no next second center point adjacent to the first second center point.
[0123] Furthermore, when the first normal vector determination module 304 determines the tangent vector of the second center point based on the pixel coordinates of the second center point and the pixel coordinates of the second center points adjacent to the second center point, the first normal vector determination module 304 is also used to:
[0124] When the second center point is the starting second center point among the plurality of second center points, the first pixel coordinates of the starting second center point in the original medical image and the second pixel coordinates of the first adjacent center point adjacent to the starting second center point in the original medical image are determined, and the tangent vector of the starting second center point is determined based on the first pixel coordinates and the second pixel coordinates.
[0125] When the second center point is the last second center point among the plurality of second center points, the third pixel coordinate of the last second center point in the original medical image and the fourth pixel coordinate of the second adjacent center point adjacent to the last second center point in the original medical image are determined, and the tangent vector of the last second center point is determined based on the third pixel coordinate and the fourth pixel coordinate.
[0126] When the second center point is any one of the plurality of second center points other than the starting second center point and the ending second center point, the fifth pixel coordinate of the next second center point adjacent to the second center point in the original medical image and the sixth pixel coordinate of the previous second center point adjacent to the second center point in the original medical image are determined, and the tangent vector of the second center point is determined based on the fifth pixel coordinate and the sixth pixel coordinate.
[0127] Furthermore, when the second normal vector determination module 305 determines the normal vector of each first center point based on the positional relationship between each first center point and each second center point and the normal vector of each second center point, the second normal vector determination module 305 is also used to:
[0128] For each first center point, the distance between the first center point and each second center point is determined based on the pixel coordinates of the first center point in the original medical image and the pixel coordinates of each second center point in the original medical image.
[0129] The normal vector of the second center point that is closest to the first center point among the plurality of second center points is determined as the normal vector of the first center point.
[0130] Furthermore, when the surface reconstruction module 306 generates multiple surface sampling points based on the position and normal vector of each first center point, and generates the surface reconstruction result of the blood vessel based on the multiple surface sampling points, the surface reconstruction module 306 is also used for:
[0131] For each first center point, multiple equally spaced surface sampling points are created along the positive and negative directions of the normal vector of the first center point, with the first center point as the center.
[0132] Linear interpolation is performed on the original medical image using the surface sampling points corresponding to each first center point, and the two-dimensional image generated in the original medical image along the spline curve is determined as the surface reconstruction result of the blood vessel.
[0133] Please see Figure 4 , Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 4 As shown, the electronic device 400 includes a processor 410, a memory 420, and a bus 430.
[0134] The memory 420 stores machine-readable instructions executable by the processor 410. When the electronic device 400 is running, the processor 410 communicates with the memory 420 via the bus 430. When the machine-readable instructions are executed by the processor 410, they can perform the operations described above. Figure 1 and Figure 2 The steps of the vascular surface reconstruction method in the illustrated method embodiment can be found in the method embodiment for specific implementation, and will not be repeated here.
[0135] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, can perform the above-described actions. Figure 1 and Figure 2 The steps of the vascular surface reconstruction method in the illustrated method embodiment can be found in the method embodiment for specific implementation, and will not be repeated here.
[0136] 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.
[0137] 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. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the shown or discussed mutual couplings, direct couplings, or communication connections may be through some communication interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.
[0138] 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.
[0139] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.
[0140] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, 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 (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0141] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.
[0142] Finally, it should be noted that the above-described embodiments are merely specific implementations of this application, used to illustrate the technical solutions of this application, and not to limit them. The scope of protection of this application is not limited thereto. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the scope of the technology disclosed in this application. Such modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be covered 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 reconstructing vascular surfaces, characterized in that, The method for reconstructing the vascular surface includes: Obtain the vessel centerline in the original medical image, and determine multiple original centerline control points in the vessel centerline; Spline interpolation is performed on the multiple original centerline control points to obtain a spline curve, and equal-interval sampling is performed on the spline curve at a first preset distance to obtain multiple first center points; The multiple original centerline control points are input into spline approximation for curve smoothing to obtain a smoothed centerline. Then, samples are taken at equal intervals along the smoothed centerline at a second preset distance to obtain multiple second center points. The second preset distance is less than the first preset distance. The normal vector of each second center point on the smooth center line is determined using the pixel coordinates of each second center point in the original medical image. The normal vector of each first center point is determined based on the positional relationship between each first center point and each second center point, and the normal vector of each second center point. Multiple surface sampling points are generated based on the position and normal vector of each first center point, and the surface reconstruction result of the blood vessel is generated based on the multiple surface sampling points.
2. The method for vascular surface reconstruction according to claim 1, characterized in that, The step of determining the normal vector of each second center point in the original medical image using the pixel coordinates of each second center point on the smoothed center line includes: For each second center point, the tangent vector of the second center point is determined based on the pixel coordinates of the second center point and the pixel coordinates of the second center points adjacent to the second center point; For the first second center point among the plurality of second center points, the normal vector of the first second center point is determined based on the tangent vector of the first second center point; Determine the next second center point adjacent to the first second center point, and determine the binormal vector of the next second center point based on the normal vector of the first second center point and the tangent vector of the next second center point; The normal vector of the next second center point is determined based on the tangent vector of the next second center point and the binormal vector of the next second center point. The next second center point is determined as the first second center point, and the process returns to the step of determining the next second center point adjacent to the first second center point, until there is no next second center point adjacent to the first second center point.
3. The method for vascular surface reconstruction according to claim 2, characterized in that, Determining the tangent vector of the second center point based on the pixel coordinates of the second center point and the pixel coordinates of the adjacent second center points includes: When the second center point is the starting second center point among the plurality of second center points, the first pixel coordinates of the starting second center point in the original medical image and the second pixel coordinates of the first adjacent center point adjacent to the starting second center point in the original medical image are determined, and the tangent vector of the starting second center point is determined based on the first pixel coordinates and the second pixel coordinates. When the second center point is the last second center point among the plurality of second center points, the third pixel coordinate of the last second center point in the original medical image and the fourth pixel coordinate of the second adjacent center point adjacent to the last second center point in the original medical image are determined, and the tangent vector of the last second center point is determined based on the third pixel coordinate and the fourth pixel coordinate. When the second center point is any one of the plurality of second center points other than the starting second center point and the ending second center point, the fifth pixel coordinate of the next second center point adjacent to the second center point in the original medical image and the sixth pixel coordinate of the previous second center point adjacent to the second center point in the original medical image are determined, and the tangent vector of the second center point is determined based on the fifth pixel coordinate and the sixth pixel coordinate.
4. The method for vascular surface reconstruction according to claim 1, characterized in that, The normal vector of each first center point is determined based on the positional relationship between each first center point and each second center point, and the normal vector of each second center point, including: For each first center point, the distance between the first center point and each second center point is determined based on the pixel coordinates of the first center point in the original medical image and the pixel coordinates of each second center point in the original medical image. The normal vector of the second center point that is closest to the first center point among the plurality of second center points is determined as the normal vector of the first center point.
5. The method for vascular surface reconstruction according to claim 1, characterized in that, The process of generating multiple surface sampling points based on the position and normal vector of each first center point, and generating the surface reconstruction result of the blood vessel based on the multiple surface sampling points, includes: For each first center point, multiple equally spaced surface sampling points are created along the positive and negative directions of the normal vector of the first center point, with the first center point as the center. Linear interpolation is performed on the original medical image using the surface sampling points corresponding to each first center point, and the two-dimensional image generated in the original medical image along the spline curve is determined as the surface reconstruction result of the blood vessel.
6. A vascular surface reconstruction device, characterized in that, The vascular surface reconstruction device includes: The centerline control point generation module is used to acquire the centerline of blood vessels in the original medical image and determine multiple original centerline control points in the centerline of blood vessels. The first center point generation module is used to perform spline interpolation on the multiple original centerline control points to obtain a spline curve, and to perform equal-interval sampling on the spline curve according to a first preset distance to obtain multiple first center points; The second center point generation module is used to input the multiple original centerline control points into spline approximation for curve smoothing to obtain a smooth centerline, and to sample the smooth centerline at equal intervals according to a second preset distance to obtain multiple second center points; wherein, the second preset distance is less than the first preset distance; The first normal vector determination module is used to determine the normal vector of each second center point in the original medical image using the pixel coordinates of each second center point on the smooth center line. The second normal vector determination module is used to determine the normal vector of each first center point based on the positional relationship between each first center point and each second center point and the normal vector of each second center point. The surface reconstruction module is used to generate multiple surface sampling points based on the position and normal vector of each first center point, and to generate the surface reconstruction result of the blood vessel based on the multiple surface sampling points.
7. The vascular surface reconstruction device according to claim 6, characterized in that, When the first normal vector determination module determines the normal vector of each second center point in the original medical image using the pixel coordinates of each second center point on the smooth center line, the first normal vector determination module is further configured to: For each second center point, the tangent vector of the second center point is determined based on the pixel coordinates of the second center point and the pixel coordinates of the second center points adjacent to the second center point; For the first second center point among the plurality of second center points, the normal vector of the first second center point is determined based on the tangent vector of the first second center point; Determine the next second center point adjacent to the first second center point, and determine the binormal vector of the next second center point based on the normal vector of the first second center point and the tangent vector of the next second center point; The normal vector of the next second center point is determined based on the tangent vector of the next second center point and the binormal vector of the next second center point. The next second center point is determined as the first second center point, and the process returns to the step of determining the next second center point adjacent to the first second center point, until there is no next second center point adjacent to the first second center point.
8. The vascular surface reconstruction device according to claim 7, characterized in that, When the first normal vector determination module determines the tangent vector of the second center point based on the pixel coordinates of the second center point and the pixel coordinates of the second center points adjacent to the second center point, the first normal vector determination module is further configured to: When the second center point is the starting second center point among the plurality of second center points, the first pixel coordinates of the starting second center point in the original medical image and the second pixel coordinates of the first adjacent center point adjacent to the starting second center point in the original medical image are determined, and the tangent vector of the starting second center point is determined based on the first pixel coordinates and the second pixel coordinates. When the second center point is the last second center point among the plurality of second center points, the third pixel coordinate of the last second center point in the original medical image and the fourth pixel coordinate of the second adjacent center point adjacent to the last second center point in the original medical image are determined, and the tangent vector of the last second center point is determined based on the third pixel coordinate and the fourth pixel coordinate. When the second center point is any one of the plurality of second center points other than the starting second center point and the ending second center point, the fifth pixel coordinate of the next second center point adjacent to the second center point in the original medical image and the sixth pixel coordinate of the previous second center point adjacent to the second center point in the original medical image are determined, and the tangent vector of the second center point is determined based on the fifth pixel coordinate and the sixth pixel coordinate.
9. An electronic device, characterized in that, include: The device includes a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus, and the machine-readable instructions are executed by the processor to perform the steps of the vascular surface reconstruction method as described in any one of claims 1 to 5.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the steps of the vascular surface reconstruction method as described in any one of claims 1 to 5.