Lumen model generation method and apparatus, electronic device, and storage medium

Abstract

A tube cavity model generation method and device, electronic equipment and storage medium are disclosed. The method comprises: obtaining a blood vessel center line of a to-be-processed blood vessel image; determining a sharp turning region corresponding to the blood vessel center line; judging whether the profile in the sharp turning region corresponding to the blood vessel center line is crossed and / or sparse; processing the profile in the sharp turning region based on the judgment result to obtain a profile optimization set; and performing interpolation processing on the profile optimization set to obtain a tube cavity model. The above technical solution realizes profile optimization in the sharp turning region, repairs profile abnormalities, and thus generates a tube cavity model with good structure.

Description

Technical Field

[0001] This invention relates to the field of image processing technology, and in particular to a method, apparatus, electronic device, and storage medium for generating a lumen model. Background Technology

[0002] With the development of image processing technology, it has been widely used in the medical field.

[0003] Coronary arteries are characterized by abundant vascular branches, complex topology, and diverse luminal patterns. Currently, coronary artery lumen models obtained using existing image processing techniques exhibit issues such as collapse or contour intersections at luminal bends. Summary of the Invention

[0004] This invention provides a method, apparatus, electronic device, and storage medium for generating a lumen model to solve the problems of collapse at lumen bends and contour intersections.

[0005] According to one aspect of the present invention, a method for generating a lumen model is provided, comprising:

[0006] Obtain the centerline of the blood vessel in the image to be processed;

[0007] Identify the region with sharp bends corresponding to the center line of the blood vessel, and determine whether the contours within the region with sharp bends corresponding to the center line of the blood vessel intersect and / or are sparse.

[0008] Based on the judgment result, the contours in the area of ​​excessively sharp turns are processed to obtain an optimized contour set;

[0009] The contour optimization set is interpolated to obtain the lumen model.

[0010] According to another aspect of the present invention, a lumen model generation apparatus is provided, comprising:

[0011] The vessel centerline acquisition module is used to acquire the vessel centerline of the image to be processed.

[0012] The sharp bend detection module is used to determine the sharp bend area corresponding to the center line of the blood vessel, and to determine whether the contours within the sharp bend area corresponding to the center line of the blood vessel intersect and / or are sparse.

[0013] The contour optimization module is used to process the contours in the area of ​​sharp turns based on the judgment results, and obtain the contour optimization set.

[0014] The lumen model generation module is used to perform interpolation processing on the contour optimization set to obtain the lumen model.

[0015] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0016] At least one processor;

[0017] and a memory communicatively connected to the at least one processor;

[0018] The memory stores a computer program that can be executed by the at least one processor, which is then executed by the at least one processor to enable the at least one processor to perform the lumen model generation method according to any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the lumen model generation method according to any embodiment of the present invention.

[0020] The technical solution of this invention involves acquiring the centerline of a blood vessel in an image of a blood vessel to be processed; determining the region with sharp bends corresponding to the centerline; judging whether the contours within the region with sharp bends intersect and / or are sparse; processing the contours within the region with sharp bends based on the judgment results to obtain an optimized contour set; and then performing interpolation processing on the optimized contour set to obtain a lumen model. This technical solution achieves contour optimization of regions with sharp bends, repairs contour anomalies, and generates a well-structured lumen model.

[0021] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 A flowchart illustrating a method for generating a lumen model according to an embodiment of the present invention;

[0024] Figure 2 This is a schematic diagram of the coronary artery tree centerline provided in an embodiment of the present invention;

[0025] Figure 3 A schematic diagram of a coronary artery tree outline provided in an embodiment of the present invention;

[0026] Figure 4A schematic diagram of an intersection of contours provided for an embodiment of the present invention;

[0027] Figure 5 A schematic diagram of model collapse provided in an embodiment of the present invention;

[0028] Figure 6 A schematic diagram of a coronary artery tree lumen model provided in an embodiment of the present invention;

[0029] Figure 7 A flowchart illustrating a method for generating a lumen model according to an embodiment of the present invention;

[0030] Figure 8 This is a schematic diagram of a curve distance and a spatial distance provided in an embodiment of the present invention;

[0031] Figure 9 A flowchart illustrating a method for generating a lumen model according to an embodiment of the present invention;

[0032] Figure 10 A schematic diagram illustrating the determination of the radius of curvature according to an embodiment of the present invention;

[0033] Figure 11 A flowchart illustrating a method for generating a lumen model according to an embodiment of the present invention;

[0034] Figure 12 A schematic diagram illustrating an insertion optimization provided in an embodiment of the present invention;

[0035] Figure 13 A schematic diagram illustrating a deletion optimization provided in an embodiment of the present invention;

[0036] Figure 14 A flowchart illustrating a method for generating a lumen model according to an embodiment of the present invention;

[0037] Figure 15 A schematic diagram of a rotation method provided in an embodiment of the present invention;

[0038] Figure 16 A schematic diagram illustrating rotation optimization provided in an embodiment of the present invention;

[0039] Figure 17 A flowchart illustrating a method for generating a lumen model according to an embodiment of the present invention;

[0040] Figure 18 A schematic diagram of an inner product method provided in an embodiment of the present invention;

[0041] Figure 19 This is a schematic diagram of a cavity model generation device provided in an embodiment of the present invention;

[0042] Figure 20This is a schematic diagram of the structure of an electronic device that implements the lumen model generation method of this invention. Detailed Implementation

[0043] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0044] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0045] Example 1

[0046] Figure 1 This is a flowchart of a lumen model generation method provided in Embodiment 1 of the present invention. This embodiment is applicable to the automatic generation of lumen models. The method can be executed by a lumen model generation device, which can be implemented in hardware and / or software, and can be configured in a terminal and / or server. Figure 1 As shown, the method includes:

[0047] S110. Obtain the center line of the blood vessel in the image to be processed.

[0048] In this embodiment, the vascular image to be processed refers to an image containing blood vessels, which can be two-dimensional, three-dimensional, or multi-dimensional, and is not limited thereto. For example, taking coronary artery medical imaging as an example, the vascular image to be processed can be a computed tomography (CT) image of the coronary artery, or a magnetic resonance imaging (MRI) image, etc. The vascular centerline refers to a spatial curve distributed at the center of the lumen, and can be composed of multiple consecutive centerline points. For example, Figure 2This is a schematic diagram of the coronary artery tree centerline provided in an embodiment of the present invention.

[0049] Specifically, one or more vascular images to be processed can be retrieved from a preset storage path on the electronic device or from a cloud server. After acquiring the vascular images, the centerline can be extracted to obtain the vascular centerline. The centerline extraction methods include, but are not limited to, skeletonization and region growing methods.

[0050] S120. Determine the region with sharp bends corresponding to the center line of the blood vessel, and determine whether the contours within the region with sharp bends corresponding to the center line of the blood vessel intersect and / or are sparse.

[0051] In this embodiment, a contour refers to a closed curve formed by multiple spatial points on the same spatial plane. The normal vector of the contour plane is parallel to the tangent direction of the vessel centerline, and each centerline point corresponds to one contour. For example, Figure 3 This is a schematic diagram of a coronary artery tree contour provided in an embodiment of the present invention. Regions with sharp bends refer to areas where the vessel course changes abnormally; the causes of this abnormality may include contour intersections, model collapse, etc. Figure 4 A schematic diagram of an intersection of contours provided for an embodiment of the present invention; Figure 5 This is a schematic diagram of a model collapse provided in an embodiment of the present invention.

[0052] It should be noted that after identifying the region with excessively sharp turns, the contours within the turning region can be judged for intersection and / or sparsity to determine the cause of the excessively sharp turns. Contour intersection refers to the situation where contours intersect in space. Contour sparsity refers to the situation where the contour distance is greater than a distance threshold, which will lead to model collapse.

[0053] S130. Based on the judgment result, the contours in the area of ​​excessively sharp turns are processed to obtain an optimized contour set.

[0054] In this embodiment, the contour optimization set refers to the contour set after contour optimization, which may include the optimized contour within the area of ​​sharp turns, and the normal contour outside the area of ​​sharp turns.

[0055] Specifically, based on the judgment results, the contours in areas with sharp turns can be added, deleted, or repositioned to make the contour settings more reasonable.

[0056] S140. The contour optimization set is interpolated to obtain the cavity model.

[0057] In this embodiment, the lumen model refers to the spatially closed curved surface of a blood vessel. For example, Figure 6 This is a schematic diagram of a coronary artery tree lumen model provided in an embodiment of the present invention.

[0058] For example, interpolation methods such as B-spline interpolation (B-Spline) and bilinear interpolation can be used to interpolate on adjacent contours of the contour optimization set to obtain the lumen model.

[0059] The technical solution of this invention involves acquiring the centerline of a blood vessel in an image of a blood vessel to be processed; determining the region with sharp bends corresponding to the centerline; judging whether the contours within the region with sharp bends intersect and / or are sparse; processing the contours within the region with sharp bends based on the judgment results to obtain an optimized contour set; and then performing interpolation processing on the optimized contour set to obtain a lumen model. This technical solution achieves contour optimization within regions with sharp bends, repairs contour anomalies, and generates a well-structured lumen model.

[0060] Example 2

[0061] Figure 7 This is a flowchart of a lumen model generation method provided in Embodiment 2 of the present invention. The method of this embodiment can be combined with various optional schemes in the lumen model generation methods provided in the above embodiments. The lumen model generation method provided in this embodiment has been further optimized. Optionally, determining the region of sharp bends corresponding to the blood vessel centerline includes: sliding a pre-set sliding window on the blood vessel centerline and determining the curve distance and spatial distance of the blood vessel centerline within the sliding window; if the ratio of the curve distance to the spatial distance of the blood vessel centerline within the sliding window is greater than a preset ratio threshold, then determining the centerline point corresponding to the center of the sliding window as a candidate point of sharp bends; and determining the region of sharp bends corresponding to the blood vessel centerline based on the candidate points of sharp bends.

[0062] like Figure 7 As shown, the method includes:

[0063] S210. Obtain the center line of the blood vessel in the image to be processed.

[0064] S220. Slide a pre-set sliding window along the center line of the blood vessel and determine the curve distance and spatial distance of the center line of the blood vessel within the sliding window.

[0065] S230. If the ratio of the curve distance to the spatial distance of the blood vessel centerline within the sliding window is greater than a preset ratio threshold, then the centerline point corresponding to the center within the sliding window is determined as a candidate point of excessively sharp turning; based on the candidate point of excessively sharp turning, the region of excessively sharp turning corresponding to the blood vessel centerline is determined.

[0066] S240. Determine whether the contours in the area of ​​sharp bends corresponding to the center line of the blood vessel intersect and / or are sparse.

[0067] S250. Based on the judgment result, the contour in the area of ​​excessively sharp turns is processed to obtain an optimized contour set.

[0068] S260. The contour optimization set is interpolated to obtain the cavity model.

[0069] In this embodiment, the pre-set sliding window may include a preset number of centerline points. For example, the size of the sliding window may be 5 to 7 centerline points, and the specific number is not limited here.

[0070] For example, Figure 8 This is a schematic diagram of curved distance and spatial distance provided in an embodiment of the present invention, wherein the curved distance is represented by a solid line and the spatial distance is represented by a dashed line. Specifically, the ratio of the curved distance of the centerline within the window to the straight distance in space is calculated using a sliding window method. If the ratio of the curved distance of the vessel centerline within the sliding window to the spatial distance is greater than a preset ratio threshold, then the centerline point corresponding to the center of the sliding window is determined as a candidate sharp bend point, and the area within a preset distance range of the candidate sharp bend point is determined as the sharp bend region corresponding to the vessel centerline. If the ratio of the curved distance of the vessel centerline within the sliding window to the spatial distance is not greater than the preset ratio threshold, then there is no candidate sharp bend point within the sliding window.

[0071] The technical solution of this invention involves sliding a pre-set sliding window along the centerline of a blood vessel and determining the curvilinear distance and spatial distance of the centerline within the sliding window. If the ratio of the curvilinear distance to the spatial distance of the centerline within the sliding window is greater than a preset ratio threshold, then the centerline point corresponding to the center within the sliding window is determined as a candidate point of excessively sharp bends. Subsequently, based on the candidate points of excessively sharp bends, the region of excessively sharp bends corresponding to the centerline of the blood vessel is determined, thereby achieving rapid determination of the region of excessively sharp bends.

[0072] Example 3

[0073] Figure 9 This is a flowchart of a lumen model generation method provided in Embodiment 3 of the present invention. The method of this embodiment can be combined with various optional schemes in the lumen model generation methods provided in the above embodiments. The lumen model generation method provided in this embodiment has been further optimized. Optionally, determining the sharp bend region corresponding to the blood vessel centerline includes: performing spatial curve fitting on the centerline points on the blood vessel centerline to obtain a centerline curve function; determining the points where the second derivative of the centerline curve function is zero; determining the radius of curvature of the centerline curve function at the points where the second derivative is zero; if the radius of curvature of the centerline curve function at the points where the second derivative is zero is less than a radius of curvature threshold, then the points where the second derivative of the centerline curve function is zero are determined as candidate sharp bend points; and the sharp bend region corresponding to the blood vessel centerline is determined based on the candidate sharp bend points.

[0074] like Figure 9 As shown, the method includes:

[0075] S310. Obtain the center line of the blood vessel in the image of the blood vessel to be processed.

[0076] S320. Determine the point where the second derivative of the centerline curve function is zero.

[0077] S330. Determine the radius of curvature of the centerline curve function at the point where the second derivative is zero.

[0078] S340. If the radius of curvature of the centerline curve function at the point where the second derivative is zero is less than the radius of curvature threshold, then the point where the second derivative of the centerline curve function is zero is determined as a candidate point of excessively sharp bend; based on the candidate point of excessively sharp bend, the region of excessively sharp bend corresponding to the centerline of the blood vessel is determined.

[0079] S350. Determine whether the contours in the area of ​​sharp bends corresponding to the center line of the blood vessel intersect and / or are sparse.

[0080] S360. Based on the judgment result, the contour in the area of ​​the sharp turn is processed to obtain the contour optimization set.

[0081] S370. The contour optimization set is interpolated to obtain the cavity model.

[0082] For example, Figure 10 This is a schematic diagram illustrating the determination of the radius of curvature according to an embodiment of the present invention. Specifically, a spatial curve is fitted to the centerline point on the vessel centerline to obtain a centerline curve function. The fitting method can be cubic fitting, polynomial fitting, etc., which are not limited here. Then, the point where the second derivative of the centerline curve function is zero is determined, and the radius of curvature of the centerline curve function at the point where the second derivative is zero is determined. If the radius of curvature of the centerline curve function at the point where the second derivative is zero is less than the radius of curvature threshold, then the point where the second derivative is zero is determined as a candidate point of excessively sharp bend. If the radius of curvature of the centerline curve function at the point where the second derivative is zero is not less than the radius of curvature threshold, then the point is not a candidate point of excessively sharp bend. Then, the area within a preset distance range of the candidate point of excessively sharp bend is determined as the area of ​​excessively sharp bend corresponding to the vessel centerline.

[0083] The technical solution of this invention involves performing spatial curve fitting on the centerline points of the blood vessel centerline to obtain a centerline curve function; determining the points where the second derivative of the centerline curve function is zero; determining the radius of curvature of the centerline curve function at the points where the second derivative is zero; if the radius of curvature of the centerline curve function at the points where the second derivative is zero is less than a radius of curvature threshold, then the points where the second derivative of the centerline curve function is zero are identified as candidate points of excessively sharp bends; and determining the excessively sharp bend region corresponding to the blood vessel centerline based on the candidate points of excessively sharp bends, thus achieving rapid determination of the excessively sharp bend region.

[0084] Example 4

[0085] Figure 11 This is a flowchart of a lumen model generation method provided in Embodiment 4 of the present invention. The method of this embodiment can be combined with various optional schemes in the lumen model generation methods provided in the above embodiments. The lumen model generation method provided in this embodiment has been further optimized. Optionally, determining whether the contours in the sharply turning region corresponding to the vessel centerline intersect and / or are sparse includes: determining the average lumen diameter of the sharply turning region corresponding to the vessel centerline; and determining whether the contours in the sharply turning region corresponding to the vessel centerline are sparse based on the average lumen diameter of the sharply turning region corresponding to the vessel centerline.

[0086] like Figure 11 As shown, the method includes:

[0087] S410. Obtain the center line of the blood vessel in the image to be processed.

[0088] S420. Determine the area with an excessively sharp bend corresponding to the center line of the blood vessel.

[0089] S430. Determine the average lumen diameter of the region with sharp bends corresponding to the center line of the blood vessel.

[0090] S440. Based on the average lumen diameter of the region with sharp bends corresponding to the center line of the blood vessel, determine whether the contour of the region with sharp bends corresponding to the center line of the blood vessel is sparse.

[0091] S450. Based on the judgment result, the contour in the area of ​​the sharp turn is processed to obtain the contour optimization set.

[0092] S460. The contour optimization set is interpolated to obtain the cavity model.

[0093] In this embodiment, the average lumen diameter refers to the average diameter of the region where the blood vessel bends too sharply, which can be used to measure or determine whether the contour in the region where the bend is too sharp is sparse.

[0094] Specifically, electronic devices are used to calculate the average lumen diameter of the region with sharp bends corresponding to the center line of the blood vessel. Based on the average lumen diameter of the region with sharp bends, it is determined whether the contour of the region with sharp bends corresponding to the center line of the blood vessel is sparse, thus enabling rapid identification of the cause of the abnormality.

[0095] Based on the above embodiments, optionally, determining the average lumen diameter of the region with a sharp bend corresponding to the blood vessel centerline includes: lofting the contour of the region with a sharp bend corresponding to the blood vessel centerline to obtain a model of the bend region; performing volume filling processing on the model of the bend region, and determining the volume of the region with a sharp bend based on the model after volume filling processing; determining the lumen diameter of the region with a sharp bend segmented based on the volume of the region with a sharp bend; and determining the average lumen diameter based on the lumen diameter of each segment.

[0096] The volume filling method can be pixel filling or tetrahedral filling, etc., and is not limited here.

[0097] It should be noted that at the bend of a blood vessel, the centerline of the vessel may not be at the center of the actual lumen, resulting in the outline not being perpendicular to the actual lumen. Therefore, the average lumen diameter can be determined by volume to improve the reliability of the average lumen diameter.

[0098] In some embodiments, abnormal lumen diameters may be removed before determining the average lumen diameter to improve the accuracy of the average lumen diameter.

[0099] Based on the above embodiments, optionally, determining whether the contours within the sharply bend region corresponding to the vessel centerline are sparse based on the average lumen diameter of the region is as follows: if the distance between adjacent contours within the sharply bend region corresponding to the vessel centerline is greater than the average lumen diameter, then the contours within the sharply bend region corresponding to the vessel centerline are determined to be sparse; if the distance between adjacent contours within the sharply bend region corresponding to the vessel centerline is less than a preset proportion of the average lumen diameter, then the contours within the sharply bend region corresponding to the vessel centerline are determined to be dense.

[0100] For example, if the distance between adjacent contours in the region of sharp bends corresponding to the vessel centerline is greater than the average lumen diameter, then the contours in the region of sharp bends corresponding to the vessel centerline are determined to be sparse; if the distance between adjacent contours in the region of sharp bends corresponding to the vessel centerline is less than 1 / 4 of the average lumen diameter, then the contours in the region of sharp bends corresponding to the vessel centerline are determined to be dense.

[0101] Based on the above embodiments, optionally, the contours in the sharp-turn area are processed according to the judgment result to obtain a contour optimization set, including: if the judgment result is that the contours in the sharp-turn area are sparse, then the average contour of the adjacent contours is inserted at the middle position of the adjacent contours in the sharp-turn area to obtain a contour optimization set; or, if the judgment result is that the contours in the sharp-turn area are dense, then the contour with the smallest distance product among the adjacent contours in the sharp-turn area is deleted to obtain a contour optimization set.

[0102] For example, Figure 12 A schematic diagram illustrating an insertion optimization provided in an embodiment of the present invention; Figure 13 This is a schematic diagram illustrating an optimization method for deletion provided in an embodiment of the present invention. Specifically, when the contours in a region with sharp turns are sparse, an average contour of adjacent contours can be inserted at the midpoint of adjacent contours. The diameter of this average contour is the average of the diameters of adjacent contours, and the distances to adjacent contours are equal. When the contours in a region with sharp turns are dense, the contour with the smallest distance product among adjacent contours in the region with sharp turns can be deleted to make the contour spacing reasonable.

[0103] The technical solution of this invention calculates the average lumen diameter of the region with a sharp bend corresponding to the blood vessel centerline, and then, based on the average lumen diameter of the region with a sharp bend corresponding to the blood vessel centerline, determines whether the contour of the region with a sharp bend corresponding to the blood vessel centerline is sparse, thereby achieving rapid determination of the cause of the abnormality.

[0104] Example 5

[0105] Figure 14 This is a flowchart of a lumen model generation method provided in Embodiment 5 of the present invention. The method of this embodiment can be combined with various optional schemes in the lumen model generation methods provided in the above embodiments. The lumen model generation method provided in this embodiment has been further optimized. Optionally, determining whether the contours in the sharply turning area corresponding to the vessel centerline intersect and / or are sparse includes: rotating the contours in the sharply turning area corresponding to the vessel centerline around the tangent direction of the centerline to obtain a closed three-dimensional volume space; filling the closed three-dimensional volume space to obtain a filling body corresponding to the closed three-dimensional space; determining whether there are overlapping elements in the filling body corresponding to the closed three-dimensional space, and if so, determining that the contours in the sharply turning area corresponding to the vessel centerline intersect.

[0106] like Figure 14 As shown, the method includes:

[0107] S510. Obtain the center line of the blood vessel in the image to be processed.

[0108] S520. Determine the area with an excessively sharp bend corresponding to the center line of the blood vessel.

[0109] S530. Rotate the contour in the area of ​​sharp bends corresponding to the center line of the blood vessel around the tangent of the center line to obtain a closed three-dimensional volume space.

[0110] S540. Fill the closed three-dimensional space to obtain the filling body corresponding to the closed three-dimensional space.

[0111] S550. Determine whether there are overlapping elements in the filling body corresponding to the closed three-dimensional space. If so, determine that the determination result is the contour intersection in the area of ​​the sharp bend corresponding to the blood vessel centerline.

[0112] S560. Based on the judgment result, the contours in the area of ​​excessively sharp turns are processed to obtain an optimized contour set.

[0113] S570. The contour optimization set is interpolated to obtain the cavity model.

[0114] In this embodiment, the determination of contour intersections within a sharp turning area can be achieved through a rotation method. Specifically, the contours within the sharp turning area can be rotated to form a solid, and then the intersection of contours can be determined in solid space.

[0115] For example, Figure 15 This is a schematic diagram of a rotation method provided in an embodiment of the present invention. Specifically, the contour within the area of ​​sharp bends corresponding to the centerline of the blood vessel can be rotated around the tangent of the centerline to obtain a closed three-dimensional space. This closed three-dimensional space is then filled to obtain a filling body corresponding to the closed three-dimensional space. It is then determined whether there are overlapping elements in the filling body corresponding to the closed three-dimensional space. If there are, the determination result is that the contours within the area of ​​sharp bends corresponding to the centerline of the blood vessel intersect; if not, the contours do not intersect.

[0116] Based on the above embodiments, optionally, the contours in the overly sharp turning area are processed based on the judgment result to obtain a contour optimization set, including: if the judgment result is that the contours in the overly sharp turning area intersect, then the intersecting contours in the overly sharp turning area are rotated so that the normal vector of the intersecting contours in the overly sharp turning area is the same as the normal vector of the adjacent contours, thereby obtaining a contour optimization set.

[0117] For example, Figure 16 This is a schematic diagram of rotation optimization provided by an embodiment of the present invention. When contours intersect within a region of sharp turns, the intersecting contours within the region of sharp turns can be rotated so that the normal vector of the intersecting contour is the same as the normal vector of the adjacent contour, thereby repairing the contour intersection and obtaining an optimized contour set.

[0118] The technical solution of this invention involves rotating the contour within the area of ​​sharp bends corresponding to the blood vessel centerline around the tangent of the centerline to obtain a closed three-dimensional space. This closed three-dimensional space is then filled to obtain a filling body corresponding to the closed three-dimensional space. It is then determined whether there are overlapping elements in the filling body corresponding to the closed three-dimensional space. If so, the determination result is that the contours intersect within the area of ​​sharp bends corresponding to the blood vessel centerline, thus achieving rapid determination of the cause of the abnormality.

[0119] Example 6

[0120] Figure 17 This is a flowchart of a lumen model generation method provided in Embodiment Six of the present invention. The method of this embodiment can be combined with various optional schemes in the lumen model generation methods provided in the above embodiments. The lumen model generation method provided in this embodiment has been further optimized. Optionally, determining whether the contours in the sharply turning region corresponding to the vessel centerline intersect and / or are sparse includes: obtaining a first contour in the sharply turning region and determining the normal vector of the contour plane of the first contour at the center of the contour; obtaining a second contour in the sharply turning region and determining the vector from the contour point on the second contour to the contour center of the first contour; determining the dot product of the normal vector and the vector; if all values ​​in the dot product of the normal vector and the vector are simultaneously positive or simultaneously negative, then the determination result is that the contours in the sharply turning region corresponding to the vessel centerline do not intersect; if all values ​​in the dot product of the normal vector and the vector are simultaneously positive and negative, then the determination result is that the contours in the sharply turning region corresponding to the vessel centerline intersect.

[0121] like Figure 17 As shown, the method includes:

[0122] S610. Obtain the center line of the blood vessel in the image to be processed.

[0123] S620. Determine the area with an excessively sharp bend corresponding to the center line of the blood vessel.

[0124] S630. Obtain a first contour within the area of ​​sharp turns, and determine the normal vector of the contour plane of the first contour at the center of the contour.

[0125] S640. Obtain a second contour within the area of ​​sharp turns, and determine the vector from the contour point on the second contour to the contour center of the first contour.

[0126] S650. Determine the inner product of the normal vector and the vector.

[0127] S660. If all values ​​in the dot product of the normal vector and the vector are simultaneously positive or simultaneously negative, the judgment result is determined to be that the contours in the area of ​​the sharp bend corresponding to the center line of the blood vessel do not intersect; if all values ​​in the dot product of the normal vector and the vector are simultaneously positive and negative, the judgment result is determined to be that the contours in the area of ​​the sharp bend corresponding to the center line of the blood vessel intersect.

[0128] S670. Based on the judgment result, the contours in the area of ​​excessively sharp turns are processed to obtain an optimized contour set.

[0129] S680. The contour optimization set is interpolated to obtain the cavity model.

[0130] In this embodiment, the inner product method can be used to determine whether the contours in the sharp turning area intersect. The first contour is a contour randomly obtained in the sharp turning area, and the second contour is a contour other than the first contour in the sharp turning area.

[0131] For example, Figure 18 This is a schematic diagram of an inner product method provided in an embodiment of the present invention. A contour is randomly obtained within a region of sharp turns and designated as the first contour. The normal vector (V) of the contour plane of the first contour at the contour center (C) is calculated. Further, a second contour is obtained within the region of sharp turns, and the vector (S) from the contour points on the second contour to the contour center (C) of the first contour is determined. The inner product of the normal vector (V) and the vector (S) is determined. If all values ​​in the inner product of the normal vector (V) and the vector (S) are simultaneously positive or simultaneously negative, the determination result is that the contours within the region of sharp turns do not intersect. If all values ​​in the inner product of the normal vector (V) and the vector (S) simultaneously contain both positive and negative values, the determination result is that the contours within the region of sharp turns intersect.

[0132] The technical solution of this invention involves obtaining a first contour within a sharp bend region and determining the normal vector of the contour plane of the first contour at the center of the contour; obtaining a second contour within the sharp bend region and determining the vector from the contour point on the second contour to the center of the first contour; determining the dot product of the normal vector and the vector; if all values ​​in the dot product of the normal vector and the vector are simultaneously positive or simultaneously negative, the determination result is that the contours within the sharp bend region corresponding to the vessel centerline do not intersect; if all values ​​in the dot product of the normal vector and the vector are simultaneously positive and negative, the determination result is that the contours within the sharp bend region corresponding to the vessel centerline intersect, thus achieving rapid determination of whether contour intersections exist.

[0133] Example 7

[0134] Figure 19 This is a schematic diagram of a cavity model generation device provided in Embodiment 7 of the present invention. Figure 19 As shown, the device includes:

[0135] The vessel centerline acquisition module 710 is used to acquire the vessel centerline of the image to be processed.

[0136] The sharp bend judgment module 720 is used to determine the sharp bend area corresponding to the center line of the blood vessel, and to determine whether the contours in the sharp bend area corresponding to the center line of the blood vessel intersect and / or are sparse.

[0137] The contour optimization module 730 is used to process the contours in the sharp turning area based on the judgment result to obtain a contour optimization set.

[0138] The lumen model generation module 740 is used to perform interpolation processing on the contour optimization set to obtain the lumen model.

[0139] The technical solution of this invention involves acquiring the centerline of a blood vessel in an image of a blood vessel to be processed; determining the region with sharp bends corresponding to the centerline; judging whether the contours within the region with sharp bends intersect and / or are sparse; processing the contours within the region with sharp bends based on the judgment results to obtain an optimized contour set; and then performing interpolation processing on the optimized contour set to obtain a lumen model. This technical solution achieves contour optimization within regions with sharp bends, repairs contour anomalies, and generates a well-structured lumen model.

[0140] In some alternative implementations, the sharp turn detection module 720 is also used for:

[0141] The sliding window is slid along the center line of the blood vessel by a pre-set sliding window, and the curvilinear distance and spatial distance of the center line of the blood vessel within the sliding window are determined.

[0142] If the ratio of the curve distance to the spatial distance of the blood vessel centerline within the sliding window is greater than a preset ratio threshold, then the centerline point corresponding to the center within the sliding window is determined as a candidate point of sharp turning.

[0143] The sharp bend region corresponding to the centerline of the blood vessel is determined based on the candidate sharp bend points.

[0144] In some alternative implementations, the sharp turn detection module 720 is also used for:

[0145] A spatial curve fitting is performed on the centerline points along the blood vessel centerline to obtain the centerline curve function;

[0146] Determine the point where the second derivative of the centerline curve function is zero;

[0147] Determine the radius of curvature of the centerline curve function at the point where the second derivative is zero;

[0148] If the radius of curvature of the centerline curve function at the point where the second derivative is zero is less than the radius of curvature threshold, then the point where the second derivative of the centerline curve function is zero is determined as a candidate point of sharp turning.

[0149] The sharp bend region corresponding to the centerline of the blood vessel is determined based on the candidate sharp bend points.

[0150] In some alternative implementations, the sharp turn detection module 720 includes:

[0151] The average lumen diameter determination unit is used to determine the average lumen diameter of the region with a sharp bend corresponding to the centerline of the blood vessel.

[0152] The contour sparsity judgment unit is used to determine whether the contour in the region of sharp bends corresponding to the center line of the blood vessel is sparse based on the average lumen diameter of the region.

[0153] In some optional embodiments, the average lumen diameter determination unit is further configured to:

[0154] Loft the contour of the region with a sharp bend corresponding to the centerline of the blood vessel to obtain the bend region model;

[0155] The model of the turning area is filled with volume, and the volume of the area with sharp turns is determined based on the model after the volume filling process.

[0156] Based on the volume of the sharp bend region, the lumen diameter of the sharp bend region is determined segment by segment.

[0157] The average lumen diameter is determined based on the lumen diameter of each segment.

[0158] In some optional implementations, the contour sparsity determination unit is further configured to:

[0159] If the distance between adjacent contours in the region of sharp bends corresponding to the center line of the blood vessel is greater than the average lumen diameter, then the contours in the region of sharp bends corresponding to the center line of the blood vessel are determined to be sparse.

[0160] If the distance between adjacent contours in the area of ​​sharp bends corresponding to the center line of the blood vessel is less than a preset ratio of the average lumen diameter, then the contours in the area of ​​sharp bends corresponding to the center line of the blood vessel are determined to be dense.

[0161] In some alternative implementations, the sharp turn detection module 720 is also used for:

[0162] The contour within the area of ​​sharp bends corresponding to the center line of the blood vessel is rotated around the tangent of the center line to obtain a closed three-dimensional volume space.

[0163] The closed three-dimensional space is filled to obtain the filling volume corresponding to the closed three-dimensional space;

[0164] Determine whether there are overlapping elements in the filling body corresponding to the closed three-dimensional space. If so, determine that the determination result is the contour intersection in the area of ​​the sharp bend corresponding to the blood vessel centerline.

[0165] In some alternative implementations, the sharp turn detection module 720 is also used for:

[0166] In the area of ​​sharp turns, a first contour is obtained, and the normal vector of the contour plane of the first contour at the center of the contour is determined.

[0167] In the area of ​​sharp turns, a second contour is obtained, and the vector from the contour point on the second contour to the contour center of the first contour is determined.

[0168] Determine the dot product of the normal vector and the vector;

[0169] If all the values ​​in the dot product of the normal vector and the vector are simultaneously positive or simultaneously negative, then the judgment result is determined to be that the contours in the area of ​​the sharp bend corresponding to the blood vessel centerline do not intersect.

[0170] If each value in the inner product of the normal vector and the vector is both positive and negative, then the determination result is that the contour intersects within the region of the sharp bend corresponding to the center line of the blood vessel.

[0171] In some alternative implementations, the contour optimization module 730 is further configured to:

[0172] If the judgment result is that the contours intersect within the area of ​​excessively sharp turns, then rotate the intersecting contours within the area of ​​excessively sharp turns so that the normal vector of the intersecting contours within the area of ​​excessively sharp turns is the same as the normal vector of the adjacent contours, thus obtaining the contour optimization set.

[0173] In some alternative implementations, the contour optimization module 730 is further configured to:

[0174] If the judgment result is that the contours in the area of ​​sharp turns are sparse, then the average contour of the adjacent contours is inserted at the middle position of the adjacent contours in the area of ​​sharp turns to obtain the contour optimization set.

[0175] Alternatively, if the judgment result is that the contours in the area of ​​excessively sharp turns are dense, then delete the contour with the smallest distance product among the adjacent contours in the area of ​​excessively sharp turns to obtain the contour optimization set.

[0176] The lumen model generation device provided in this embodiment of the invention can execute the lumen model generation method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0177] Example 8

[0178] Figure 20 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0179] like Figure 20 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded into the RAM 13 from storage unit 18. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An I / O interface 15 is also connected to the bus 14.

[0180] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0181] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the lumen model generation method, which includes:

[0182] Obtain the centerline of the blood vessel in the image to be processed;

[0183] Identify the region with sharp bends corresponding to the center line of the blood vessel, and determine whether the contours within the region with sharp bends corresponding to the center line of the blood vessel intersect and / or are sparse.

[0184] Based on the judgment result, the contours in the area of ​​excessively sharp turns are processed to obtain an optimized contour set;

[0185] The contour optimization set is interpolated to obtain the lumen model.

[0186] In some embodiments, the lumen model generation method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or mounted on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the lumen model generation method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the lumen model generation method by any other suitable means (e.g., by means of firmware).

[0187] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0188] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0189] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer 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.

[0190] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0191] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0192] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0193] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0194] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for generating a lumen model, characterized in that, include: Obtain the centerline of the blood vessel in the image to be processed; Identify the region with sharp bends corresponding to the center line of the blood vessel, and determine whether the contours within the region with sharp bends corresponding to the center line of the blood vessel intersect and / or are sparse. Based on the judgment result, the contours in the area of ​​excessively sharp turns are processed to obtain an optimized contour set; The contour optimization set is interpolated to obtain the lumen model; The determination of the region with an excessively sharp bend corresponding to the centerline of the blood vessel includes: The sliding window is slid along the center line of the blood vessel by a pre-set sliding window, and the curvilinear distance and spatial distance of the center line of the blood vessel within the sliding window are determined. If the ratio of the curve distance to the spatial distance of the blood vessel centerline within the sliding window is greater than a preset ratio threshold, then the centerline point corresponding to the center within the sliding window is determined as a candidate point of sharp turning. Based on the candidate sharp bends, the sharp bend area corresponding to the center line of the blood vessel is determined. The determination of whether the contours within the area of ​​sharp bends corresponding to the center line of the blood vessel intersect and / or are sparse includes: The contour within the area of ​​sharp bends corresponding to the center line of the blood vessel is rotated around the tangent of the center line to obtain a closed three-dimensional volume space. The closed three-dimensional space is filled to obtain the filling volume corresponding to the closed three-dimensional space; Determine whether there are overlapping elements in the filling body corresponding to the closed three-dimensional space. If there are, determine that the determination result is the contour intersection in the area of ​​the sharp bend corresponding to the blood vessel centerline. The determination of whether the contours within the area of ​​sharp bends corresponding to the center line of the blood vessel intersect and / or are sparse includes: In the area of ​​sharp turns, a first contour is obtained, and the normal vector of the contour plane of the first contour at the center of the contour is determined. In the area of ​​sharp turns, a second contour is obtained, and the vector from the contour point on the second contour to the contour center of the first contour is determined. Determine the dot product of the normal vector and the vector; If all the values ​​in the dot product of the normal vector and the vector are simultaneously positive or simultaneously negative, then the judgment result is determined to be that the contours in the area of ​​the sharp bend corresponding to the blood vessel centerline do not intersect. If each value in the inner product of the normal vector and the vector is both positive and negative, then the determination result is that the contour intersects within the region of the sharp bend corresponding to the center line of the blood vessel.

2. The method according to claim 1, characterized in that, The determination of the region with an excessively sharp bend corresponding to the centerline of the blood vessel includes: A spatial curve fitting is performed on the centerline points along the blood vessel centerline to obtain the centerline curve function; Determine the point where the second derivative of the centerline curve function is zero; Determine the radius of curvature of the centerline curve function at the point where the second derivative is zero; If the radius of curvature of the centerline curve function at the point where the second derivative is zero is less than the radius of curvature threshold, then the point where the second derivative of the centerline curve function is zero is determined as a candidate point of sharp turning. The sharp bend region corresponding to the centerline of the blood vessel is determined based on the candidate sharp bend points.

3. The method according to claim 1, characterized in that, The determination of whether the contours within the area of ​​sharp bends corresponding to the center line of the blood vessel intersect and / or are sparse includes: Determine the average lumen diameter of the region with sharp bends corresponding to the centerline of the blood vessel. Based on the average lumen diameter of the region with sharp bends corresponding to the center line of the blood vessel, it is determined whether the contour within the region with sharp bends corresponding to the center line of the blood vessel is sparse.

4. The method according to claim 3, characterized in that, Determining the average lumen diameter of the region with sharp bends corresponding to the centerline of the blood vessel includes: Loft the contour of the region with a sharp bend corresponding to the centerline of the blood vessel to obtain the bend region model; The model of the turning area is filled with volume, and the volume of the area with sharp turns is determined based on the model after the volume filling process. Based on the volume of the sharp bend region, the lumen diameter of the sharp bend region is determined segment by segment. The average lumen diameter is determined based on the lumen diameter of each segment.

5. The method according to claim 3, characterized in that, The step of determining whether the contour within the sharply bend region corresponding to the vessel centerline is sparse, based on the average lumen diameter of the region, includes: If the distance between adjacent contours in the region of sharp bends corresponding to the center line of the blood vessel is greater than the average lumen diameter, then the contours in the region of sharp bends corresponding to the center line of the blood vessel are determined to be sparse. If the distance between adjacent contours in the area of ​​sharp bends corresponding to the center line of the blood vessel is less than a preset ratio of the average lumen diameter, then the contours in the area of ​​sharp bends corresponding to the center line of the blood vessel are determined to be dense.

6. The method according to claim 1, characterized in that, The contours within the sharp turning area are processed based on the judgment results to obtain an optimized contour set, including: If the judgment result is that the contours intersect within the area of ​​excessively sharp turns, then rotate the intersecting contours within the area of ​​excessively sharp turns so that the normal vector of the intersecting contours within the area of ​​excessively sharp turns is the same as the normal vector of the adjacent contours, thus obtaining the contour optimization set.

7. The method according to claim 1, characterized in that, The contours within the sharp turning area are processed based on the judgment results to obtain an optimized contour set, including: If the judgment result is that the contours in the area of ​​sharp turns are sparse, then the average contour of the adjacent contours is inserted at the middle position of the adjacent contours in the area of ​​sharp turns to obtain the contour optimization set. Alternatively, if the result indicates that the contours are dense within the area of ​​sharp turns, then delete the contour with the smallest distance product among adjacent contours within the area of ​​sharp turns to obtain the optimized contour set.

8. A device for generating a lumen model, characterized in that, The apparatus is used to perform the lumen model generation method as described in any one of claims 1-7, comprising: The vessel centerline acquisition module is used to acquire the vessel centerline of the image to be processed. The sharp bend detection module is used to determine the sharp bend area corresponding to the center line of the blood vessel, and to determine whether the contours within the sharp bend area corresponding to the center line of the blood vessel intersect and / or are sparse. The contour optimization module is used to process the contours in the area of ​​sharp turns based on the judgment results, and obtain the contour optimization set. The lumen model generation module is used to perform interpolation processing on the contour optimization set to obtain the lumen model.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and a memory communicatively connected to the at least one processor; The memory stores a computer program that can be executed by the at least one processor, which is then executed by the at least one processor to enable the at least one processor to perform the lumen model generation method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the lumen model generation method according to any one of claims 1-7.

Images