CN107346543B - Blood vessel center line processing method and device, terminal and storage medium - Google Patents
Blood vessel center line processing method and device, terminal and storage medium Download PDFInfo
- Publication number
- CN107346543B CN107346543B CN201710470577.2A CN201710470577A CN107346543B CN 107346543 B CN107346543 B CN 107346543B CN 201710470577 A CN201710470577 A CN 201710470577A CN 107346543 B CN107346543 B CN 107346543B
- Authority
- CN
- China
- Prior art keywords
- branch
- point
- blood vessel
- pixel
- pixel points
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/04—Indexing scheme for image data processing or generation, in general involving 3D image data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
Abstract
The invention discloses a method and a device for processing a blood vessel center line, a terminal and a storage medium, and belongs to the field of medical image processing. The method comprises the following steps: sequentially detecting pixel points in the blood vessel three-dimensional model according to the arrangement sequence of the pixel points in the blood vessel three-dimensional model; if the number of associated pixel points of a currently detected first pixel point is larger than 1, determining the associated pixel points as first fork points of the first pixel point, wherein the associated pixel points are pixel points which are adjacent to the first pixel point and are not detected; and if the number of the associated pixel points of each pixel point on the branch where the first branch point is located is less than 2, and the total number of the pixel points on the branch where the first branch point is located is less than a first preset threshold value, determining the branch where the first branch point is located as a pseudo branch, and deleting the pseudo branch from the blood vessel three-dimensional model. The invention improves the accuracy of determining the center line of the blood vessel. The method is used for determining the center line of the blood vessel.
Description
Technical Field
The present invention relates to the field of medical image processing, and in particular, to a method and an apparatus for processing a blood vessel centerline, a terminal, and a storage medium.
Background
The vessel center line is a mathematical model which converts a vessel three-dimensional model into a spatial tree-shaped topological structure, and because some interference data may exist in data corresponding to the vessel three-dimensional model, the vessel center line determined according to the vessel center line can generate interference such as rings, noise points, pseudo branches and the like, and the interference can influence the accuracy of subsequent vessel image processing.
In the related art, a maximum path method is used to determine a blood vessel centerline, specifically: obtaining an initial blood vessel center line corresponding to the blood vessel three-dimensional model by adopting a thinning algorithm, determining a maximum path in the initial blood vessel center line, removing the maximum path, then continuously determining the maximum path in the initial blood vessel center line from which the maximum path is removed, and circularly executing the step until the number of pixel points included in the determined maximum path is less than a preset pixel point threshold value, wherein the pixel points included in all the maximum paths determined in the process form a final blood vessel center line. Noisy points and spurious branches in the original vessel centerline can be removed by the maximum path method.
However, when the total number of pixel points included in some correct branches in the initial vessel centerline is smaller than the preset threshold, the final vessel centerline obtained based on the maximum path method does not include the correct branches, and therefore, the accuracy of determining the vessel centerline by the related art is low.
Disclosure of Invention
In order to solve the problem of low accuracy of determining a blood vessel centerline in the related art, embodiments of the present invention provide a method and an apparatus for processing a blood vessel centerline, a terminal, and a storage medium. The technical scheme is as follows:
in a first aspect, a method for processing a vessel centerline is provided, the method comprising:
sequentially detecting pixel points in the blood vessel three-dimensional model according to the arrangement sequence of the pixel points in the blood vessel three-dimensional model;
if the number of associated pixel points of a currently detected first pixel point is larger than 1, determining the associated pixel points as first fork points of the first pixel point, wherein the associated pixel points are pixel points which are adjacent to the first pixel point and are not detected;
and if the number of the associated pixel points of each pixel point on the branch where the first branch point is located is less than 2, and the total number of the pixel points on the branch where the first branch point is located is less than a first preset threshold value, determining the branch where the first branch point is located as a pseudo branch, and deleting the pseudo branch from the blood vessel three-dimensional model.
In a second aspect, a device for processing a centerline of a blood vessel is provided, the device comprising:
the detection module is used for sequentially detecting the pixel points in the blood vessel three-dimensional model according to the arrangement sequence of the pixel points in the blood vessel three-dimensional model;
the pixel detection module is used for detecting whether the number of the associated pixels of the currently detected first pixel is larger than 1 or not;
and the pseudo branch determining module is used for determining the branch of the first branch point as a pseudo branch and deleting the pseudo branch from the blood vessel three-dimensional model if the number of the associated pixel points of each pixel point on the branch of the first branch point is less than 2 and the total number of the pixel points on the branch of the first branch point is less than a first preset threshold value.
In a third aspect, a storage medium is provided, the storage medium having stored therein instructions, which when run on a computer, cause the computer to execute the method for processing a blood vessel centerline provided in the first aspect.
In a fourth aspect, a terminal is provided, which includes a memory, a processor and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the processor implements the method for processing the blood vessel centerline provided in the first aspect.
The technical scheme provided by the embodiment of the invention has the following beneficial effects:
the embodiment of the invention provides a method and a device for processing a blood vessel center line, a terminal and a storage medium, when the total number of the pixel points on the branch where the first branch point is located is smaller than a first preset threshold value, whether the number of the associated pixel points of each pixel point on the branch where the first branch point is located is smaller than 2 or not is judged (namely whether the branch where the first branch point is located has a sub-branch or not is judged), and when the total number of the pixel points on the branch where the first branch point is located is less than a first preset threshold value and the branch where the first branch point is located does not include a sub-branch, the branch where the first branch point is located is determined as the pseudo branch, and compared with the related technology, the branch where the first branch point is located is further screened based on the total number of the included pixel points, so that the situation that the correct branch with the total number of the included pixel points smaller than the preset threshold value is mistakenly judged as the pseudo branch can be avoided, and the accuracy of determining the center line of the blood vessel is effectively improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a flowchart of a method for processing a blood vessel centerline according to an embodiment of the present invention;
FIG. 2 is a flow chart of another method for processing a vessel centerline according to an embodiment of the present invention;
FIG. 3 is a diagram illustrating a 26-neighborhood region provided by an embodiment of the present invention;
fig. 4-1 is a schematic diagram of arrangement of pixel points of a certain portion of a three-dimensional model of a blood vessel according to an embodiment of the present invention;
FIG. 4-2 is a schematic diagram of determining a centerline of a blood vessel according to information related to a first bifurcation point according to an embodiment of the present invention;
4-3 are schematic diagrams of a pseudo branch in a three-dimensional model of a blood vessel according to an embodiment of the present invention;
4-4 are diagrams of an algebraic model corresponding to that of FIGS. 4-3 according to embodiments of the present invention;
FIGS. 4-5 are schematic diagrams of algebraic models corresponding to noise sources according to embodiments of the present invention;
FIGS. 4-6 are schematic diagrams of correct branching in a three-dimensional model of a blood vessel provided by embodiments of the present invention;
FIGS. 4-7 are schematic diagrams of an algebraic model corresponding to FIGS. 4-6 according to an embodiment of the present invention;
FIGS. 4-8 are schematic views of a vascular ring in a three-dimensional model of a blood vessel according to an embodiment of the present invention;
FIGS. 4-9 are schematic diagrams of algebraic models corresponding to those shown in FIGS. 4-8 according to embodiments of the present invention;
FIG. 5 is a schematic illustration of a determined vessel centerline provided by an embodiment of the present invention;
FIG. 6-1 is a schematic structural diagram of a device for processing a centerline of a blood vessel according to an embodiment of the present invention;
fig. 6-2 is a schematic structural diagram of another blood vessel centerline processing device provided by the embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail with reference to the accompanying drawings.
With the continuous development of medical image three-dimensional imaging technology, the use of mathematical models to assist in diagnosing various vascular diseases becomes an important means. The vessel centerline is a mathematical model for converting a three-dimensional model of a vessel into a spatial tree-shaped topological structure, and is not only an important ring in quantitative analysis of images such as vessel classification, but also a basis for three-dimensional reconstruction of the vessel. Due to the fact that noise exists in the collected blood vessel data, the surface of the blood vessel is not smooth, even jagged and blood vessel rings occur, and interference data such as rings, noise points, pseudo branches and the like can occur on the generated blood vessel center line, and therefore it is important to accurately and quickly identify the interference data on the blood vessel center line. In view of this, an embodiment of the present invention provides a method for processing a blood vessel centerline, as shown in fig. 1, the method may include:
101, sequentially detecting pixel points in the blood vessel three-dimensional model according to the arrangement sequence of the pixel points in the blood vessel three-dimensional model.
The associated pixel point is a pixel point which is adjacent to the first pixel point and is not detected.
And 103, if the number of the associated pixel points of each pixel point on the branch where the first branch point is located is less than 2 and the total number of the pixel points on the branch where the first branch point is located is less than a first preset threshold value, determining the branch where the first branch point is located as a pseudo branch, and deleting the pseudo branch from the blood vessel three-dimensional model.
In summary, in the method for processing a blood vessel centerline according to the embodiment of the present invention, when the total number of pixel points on the branch where the first branch point is located is smaller than the first preset threshold, judging whether the number of the associated pixel points of each pixel point on the branch where the first branch point is located is less than 2 (namely judging whether the branch where the first branch point is located has a sub-branch), and when the total number of the pixel points on the branch where the first branch point is located is less than a first preset threshold value and the branch where the first branch point is located does not include a sub-branch, the branch where the first branch point is located is determined as the pseudo branch, and compared with the related technology, the branch where the first branch point is located is further screened based on the total number of the included pixel points, so that the situation that the correct branch with the total number of the included pixel points smaller than the preset threshold value is mistakenly judged as the pseudo branch can be avoided, and the accuracy of determining the center line of the blood vessel is effectively improved.
Fig. 2 is another blood vessel centerline processing method according to an embodiment of the present invention, as shown in fig. 2, the method may include:
Optionally, the process of sequentially detecting the pixel points in the three-dimensional model of the blood vessel according to the arrangement order of the pixel points in the three-dimensional model of the blood vessel may include: and sequentially detecting whether pixel points in the blood vessel three-dimensional model have associated pixel points or not according to the connectivity of pixel neighborhoods and the arrangement sequence of the pixel points in the blood vessel three-dimensional model by utilizing a breadth-first traversal algorithm, counting the number of the associated pixel points, adding 1 to the number of the pixel points on a branch where the associated pixel points are located when a first pixel point has only one associated pixel point, storing the coordinate values of the corresponding pixel points, and sequentially taking each pixel point in the associated pixel points as the first pixel point and detecting until the pixel points in the blood vessel three-dimensional model are all detected when the first pixel point has a plurality of associated pixel points. The relevant pixel points are pixel points which are adjacent to the first pixel points and are not detected, and the first pixel points are pixel points which are currently detected in the blood vessel three-dimensional model.
The pixel neighborhood may be 26 neighborhoods, where the 26 neighborhoods are neighborhoods in a three-dimensional concept, and include 9 neighborhoods on a previous layer of a pixel layer where a currently detected pixel is located, 9 neighborhoods on a next layer, and 8 other neighborhoods except for the current pixel in the pixel layer, and a schematic diagram of the pixel neighborhood includes reference to fig. 3, where a pixel identified as "x" in fig. 3 is a currently detected pixel, and a pixel identified as "○" is a 26 neighborhoods of the currently detected pixel.
It should be noted that after any pixel point in the three-dimensional model of the blood vessel is detected, the detected pixel point needs to be marked, for example: the detected pixel point can be marked as a flag, whether the pixel point adjacent to the first pixel point is an undetected pixel point or not can be judged through the mark, namely, if the pixel point adjacent to the first pixel point is marked, the pixel point is detected, and if the pixel point adjacent to the first pixel point is not marked, the pixel point is not detected.
Exemplarily, the arrangement of the pixel points of a certain part of the blood vessel three-dimensional model is as shown in fig. 4-1, and when the breadth-first traversal algorithm is utilized, the order of the pixel points in the blood vessel three-dimensional model is sequentially detected according to the arrangement order of the pixel points in the blood vessel three-dimensional model according to the connectivity of the 26 neighborhoods of the pixel points, please refer to the solid arrows in fig. 4-1.
It should be noted that, when detecting a pixel point in the three-dimensional model of a blood vessel, each pixel point may also be detected in sequence according to other traversal algorithms (e.g., depth-first traversal algorithm, etc.) and other neighborhoods of the pixel point (e.g., 4 neighborhoods and 8 neighborhoods in two dimensions, etc.), which is not specifically limited in the embodiment of the present invention.
The number of the associated pixel points of the currently detected first pixel point is greater than 1, which indicates that the first pixel point has a bifurcation point, so that the associated pixel point can be determined as the first bifurcation point of the first pixel point.
For example, referring to fig. 4-1, assuming that the currently detected pixel is a pixel filled with squares in the drawing, it can be seen from fig. 4-1 that there are 3 pixels (pixels filled with black in the drawing) adjacent to the pixel and not detected, and the 3 pixels are associated pixels of the currently detected first pixel, and then the 3 associated pixels can be determined as the first fork points of the first pixel.
And step 203, determining a blood vessel central line according to the relevant information of the first bifurcation point.
Through the processing of step 201 and step 202, the related information of the first bifurcation point may be obtained, and the related information may include: the number of the pixel points included in the branch where the first branch point is located and the corresponding coordinate values, whether the branch where the first branch point is located includes the sub-branch, the number of the included sub-branch, the coordinate values of the first pixel point of the sub-branch and other information, and whether the number of the associated pixel points of the first branch point and the associated pixel points thereof include the sub-branch. The number of the associated pixels of the first bifurcation point may be 0, 1, 2 or more, and the case of the branch where the associated pixels of the first bifurcation point are located may include: the branch where the associated pixel point is located has a sub-branch or does not have a sub-branch.
When the first branch point of one pixel point is detected, whether the first branch point is a noise point or not can be judged according to the relevant information of the first branch point, or whether the branch where the first branch point is located is one of a pseudo branch, a blood vessel ring or a correct branch in the three-dimensional model of the blood vessel or not is determined, and the identified noise point, the pseudo branch, the blood vessel ring or the correct branch are correspondingly processed according to the judgment result so as to obtain the center line of the blood vessel. Specifically, as shown in fig. 4-2, determining the centerline of the blood vessel according to the information about the first bifurcation point may include the following cases:
in the first case, if the number of associated pixel points of each pixel point on the branch where the first branch point is located is less than 2, and the total number of pixel points on the branch where the first branch point is located is less than a first preset threshold, the branch where the first branch point is located is determined as a pseudo branch, and the pseudo branch is deleted from the blood vessel three-dimensional model.
The number of the associated pixel points of each pixel point on the branch where the first branch point is located is less than 2, which indicates that the branch where the first branch point is located has no sub-branch; because the first preset threshold is usually set according to actual experience or actual needs, when the total number of the pixel points on the branch where the first branch point is located is smaller than the first preset threshold, it is indicated that the pixel points on the branch are not enough to form a complete branch, and therefore, the branch can be determined to be a pseudo branch, which affects the accuracy of subsequent image processing, and therefore, the pseudo branch needs to be deleted from the blood vessel three-dimensional model. Referring to FIGS. 4-3, the branches indicated by arrows are pseudo branches in the three-dimensional model of blood vessels, and FIGS. 4-4 are corresponding algebraic models.
For example, assuming that the first preset threshold is 8, referring to fig. 4-1, the branch where the first branch point is located is a branch in a dashed-line frame 1 in the figure, the number of associated pixel points of each pixel point on the branch is less than 2, and the total number of pixel points on the branch is 6, it may be determined that the branch is a pseudo branch, and the pseudo branch is deleted from the three-dimensional model of the blood vessel.
In the second case, if the first bifurcation point has no associated pixel point, the first bifurcation point is determined as a noise point, and the noise point is deleted from the blood vessel three-dimensional model.
When noise exists in the acquired blood vessel data, noise exists in a blood vessel three-dimensional model obtained by performing three-dimensional reconstruction on the acquired blood vessel data, the noise often occurs at a blood vessel bifurcation or a blood vessel branch unsmooth place, and the noise affects subsequent image processing procedures, for example: the classification judgment of the blood vessel included angle is over-classified or under-classified, so that noise points need to be deleted from the blood vessel three-dimensional model. Please refer to fig. 4-5, which are algebraic models corresponding to noise.
For example, referring to fig. 4-1, if there is no associated pixel point in the first bifurcation point in the dashed box 2, the first bifurcation point may be determined as a noise point, and the noise point may be deleted from the three-dimensional model of the blood vessel.
And in the third case, the correct branch is determined according to the related information of the first branch point, and the correct branch is reserved in the three-dimensional model of the blood vessel.
Optionally, according to different situations of the branch where the first branch point is located, the process of determining the correct branch may be implemented in at least the following two ways:
in a first implementation manner, if the total number of the pixel points on the branch where the first branch point is located is greater than a first preset threshold, the branch where the first branch point is located is determined as a correct branch of the blood vessel center line, and the correct branch is retained in the three-dimensional model of the blood vessel.
The total number of the pixel points on the branch where the first branch point is located is larger than a first preset threshold, which indicates that the pixel points on the branch can form a complete branch, and at this time, no matter whether the branch where the first branch point is located has a sub-branch (i.e. whether the number of the associated pixel points of the pixel points on the branch where the first branch point is located is larger than 2), the branch can be determined to be a correct branch of the blood vessel center line, and the correct branch can be kept in the blood vessel three-dimensional model. Referring to FIGS. 4-6, the branches shown in the boxes are correct branches in the three-dimensional model of the blood vessel, and the corresponding algebraic model is shown in the dashed boxes in FIGS. 4-7.
For example, assuming that the first preset threshold is 8, referring to fig. 4-1, the branch where the first branch point is located is a branch in a dashed-line frame 3 in the figure, the number of associated pixel points of each pixel point on the branch is less than 2, and the total number of pixel points on the branch is 11, it may be determined that the branch is a correct branch, and the correct branch is retained in the three-dimensional model of the blood vessel.
In a second implementation manner, if at least two associated pixel points exist in a certain pixel point on a branch where the first bifurcation point is located, the total number of the pixel points on the branch where at least one associated pixel point exists in the at least two associated pixel points is greater than a first preset threshold, and the number of the pixel points between the first bifurcation point and the certain pixel point is less than a second preset threshold, a branch formed by the pixel points between the first bifurcation point and the certain pixel point is determined as a correct branch of the blood vessel center line, and the correct branch is kept in the three-dimensional model of the blood vessel. The second preset threshold may be set according to actual needs, and may be equal to the first preset threshold or may not be equal to the first preset threshold.
At least two associated pixel points exist in a certain pixel point on the branch where the first branch point is located, and the situation that at least two sub-branches exist in the branch where the first branch point is located is shown; the total number of the pixel points on the branch where at least one associated pixel point is located is larger than a first preset threshold value, and the sub-branch is indicated to be a correct branch. Therefore, when at least two associated pixel points exist in a certain pixel point on a branch where the first bifurcation point is located, the total number of the pixel points on the branch where at least one associated pixel point is located is larger than a first preset threshold value, and the number of the pixel points between the first bifurcation point and the certain pixel point is smaller than a second preset threshold value, a branch formed by the pixel points between the first bifurcation point and the certain pixel point can be determined as a correct branch of the blood vessel center line, and the correct branch is reserved in the three-dimensional model of the blood vessel.
In practical application, the collected blood vessel data contains noise, which can cause the bifurcation of the center line of the blood vessel to easily displace, so that a plurality of bifurcations appear at the bifurcation, the number of pixel points included by the center line between the two bifurcations is less than a second preset threshold, and the center line between the two bifurcations is also a correct branch to be reserved, and can be determined by the second realizable mode. In order to distinguish from the correct branches in the first implementable manner described above, the correct branches determined in the first implementable manner are hereinafter referred to as first-type correct branches, and the correct branches determined in the second implementable manner are referred to as second-type correct branches. The process of determining whether the branch where the associated pixel point is located is a correct branch may be referred to in the first implementable manner as described above, and details thereof are not repeated herein. Referring to fig. 4-6, the branches shown by circles in the drawings are the second kind of correct branches in the three-dimensional model of the blood vessel, and the algebraic model corresponding to the second kind of correct branches at the largest circles in fig. 4-6 is shown by the dashed circles in fig. 4-7.
For example, assuming that the first preset threshold is 8, referring to fig. 4-1, there are three associated pixels in the pixel point C on the branch where the first branch point in the dashed-line frame 4 is located, two associated pixel points in the three associated pixel points have associated pixel points, and the total number of the pixel points on the branch where the two associated pixel points are located is 9 and 11, respectively, that is, the branch where the two pixel points are located is the first-type correct branch, the branch formed by the pixel points between the first branch point and the pixel point C (i.e., the branch formed by the pixel points in the solid-line frame in the figure) can be determined as the second-type correct branch of the blood vessel centerline, and the second-type correct branch is retained in the three-dimensional model of the blood vessel. Wherein, for the associated pixel point without the associated pixel point among the three associated pixel points of the pixel point C, the associated pixel point can be determined as a noise point according to the judgment in the second case, and the noise point is deleted from the blood vessel three-dimensional model, and the specific judgment process is not repeated here.
And in the fourth situation, judging the blood vessel ring in the blood vessel three-dimensional model, and reserving or deleting the branch corresponding to the blood vessel ring in the blood vessel three-dimensional model according to the judgment result.
In practical application, a blood vessel ring may also exist in the blood vessel three-dimensional model, as shown in fig. 4-1, a branch where a first pixel point in a dashed line frame 5 is located forms the blood vessel ring, because there are two intersection points between a branch corresponding to the blood vessel ring and a branch in the blood vessel three-dimensional model, when pixel points in the blood vessel three-dimensional model are sequentially detected according to a pixel neighborhood according to a distribution sequence of the pixel points in the blood vessel three-dimensional model, there must be an intersection point without a related pixel point in the two intersection points, that is, the blood vessel ring can be disconnected, and the disconnected blood vessel ring can be judged according to the above four conditions to determine whether the disconnected blood vessel ring is a noise point, a pseudo branch or a correct branch, and when the disconnected blood vessel ring is a correct branch, the disconnected blood vessel ring is retained in the blood vessel three-dimensional model, and when the disconnected blood vessel ring is a noise point or a pseudo branch, the disconnected vessel ring is deleted from the three-dimensional model of the vessel. Referring to FIGS. 4-8, the branches indicated by arrows are the blood vessel rings in the three-dimensional model of the blood vessel, and FIGS. 4-9 are the corresponding algebraic models.
For example, assuming that the first preset threshold is 8, two intersection points exist between the blood vessel ring in the dashed line frame 5 and the branch in the dashed line frame 0 in fig. 4-1, when the pixel point in the dashed line frame 0 is detected according to the sequence indicated by the solid arrow in the figure, both intersection points are determined as the branch points of two corresponding pixel points on the branch of the dashed line frame 0, and both intersection points are marked as flag, when the pixel point in the dashed line frame 5 is detected according to the sequence indicated by the solid arrow in the figure, the blood vessel ring can be regarded as a broken branch because the intersection point below is marked, and the total number of pixel points on the broken branch is 6, the broken blood vessel ring can be determined as a pseudo branch and deleted from the blood vessel three-dimensional model, and, when the next detection is performed with the pixel point in the dashed line frame 0 adjacent to the intersection point below as the starting point, the lower intersection point will be considered to be the first bifurcation point with no associated pixel points, and thus, the lower intersection point will be determined to be noisy and deleted.
After the blood vessel three-dimensional model part shown in fig. 4-1 is processed in the five situations, the determined blood vessel center line is shown in fig. 5, and as can be seen from the comparison between fig. 4-1 and fig. 5, after the processing, the noise points, rings and pseudo branches included in the blood vessel three-dimensional model shown in fig. 4-1 are removed, and the correct branches in fig. 4-1 are reserved. When the maximum path method is used to determine the centerline of the blood vessel in the related art, if the number of pixel points included in the centerline between two bifurcations is smaller than a second preset threshold, the centerline between the two bifurcations will be deleted. Since the centerline between two bifurcations is the centerline connecting the bifurcation points in the vessel centerline, which is the correct branch (i.e. the second kind of correct branch mentioned above) that is indispensable and needs to be preserved in the subsequent image processing, its deletion will seriously affect the accuracy of the determined vessel centerline. Therefore, compared with the related art, the method for processing the blood vessel center line provided by the embodiment of the invention can reserve the second type of correct branch, process the blood vessel ring, ensure the correctness and the integrity of the determined blood vessel center line as much as possible, improve the accuracy of the determined blood vessel center line and provide a good basis for subsequent image processing such as three-dimensional reconstruction of the blood vessel or classification of the blood vessel.
It should be noted that the method for processing a blood vessel centerline provided in the embodiment of the present invention can also process an initial blood vessel centerline obtained according to an algorithm such as a thinning algorithm, so as to identify a noise point, a pseudo branch, and a blood vessel loop in the initial blood vessel centerline, thereby obtaining a more accurate blood vessel centerline, and the process of identifying the noise point, the pseudo branch, and the blood vessel loop in the initial blood vessel centerline may refer to several cases in step 203, which is not described herein again.
In summary, in the method for processing a blood vessel centerline according to the embodiment of the present invention, when the total number of pixel points on the branch where the first branch point is located is smaller than the first preset threshold, judging whether the number of the associated pixel points of each pixel point on the branch where the first branch point is located is less than 2 (namely judging whether the branch where the first branch point is located has a sub-branch), and when the total number of the pixel points on the branch where the first branch point is located is less than a first preset threshold value and the branch where the first branch point is located does not include a sub-branch, the branch where the first branch point is located is determined as the pseudo branch, and compared with the related technology, the branch where the first branch point is located is further screened based on the total number of the included pixel points, so that the situation that the correct branch with the total number of the included pixel points smaller than the preset threshold value is mistakenly judged as the pseudo branch can be avoided, and the accuracy of determining the center line of the blood vessel is effectively improved.
It should be noted that, the order of the steps of the method for processing a blood vessel centerline provided in the embodiments of the present invention may be appropriately adjusted, and the steps may also be increased or decreased according to the circumstances, and any method that can be easily conceived by those skilled in the art within the technical scope of the present disclosure shall be covered by the protection scope of the present disclosure, and therefore, no further description is given.
An embodiment of the present invention provides a device for processing a blood vessel centerline, as shown in fig. 6-1, the device 600 may include:
the detection module 601 is configured to sequentially detect the pixels in the three-dimensional model according to the arrangement order of the pixels in the three-dimensional model.
The bifurcate point determining module 602 is configured to determine, if the number of associated pixel points of the currently detected first pixel point is greater than 1, the associated pixel point as a first bifurcate point of the first pixel point, where the associated pixel point is a pixel point that is adjacent to the first pixel point and is not detected.
A pseudo branch determining module 603, configured to determine, if the number of associated pixel points of each pixel point on the branch where the first branch point is located is less than 2, and the total number of pixel points on the branch where the first branch point is located is less than a first preset threshold, the branch where the first branch point is located as a pseudo branch, and delete the pseudo branch from the three-dimensional model of the blood vessel.
In summary, in the apparatus for processing a blood vessel centerline according to the embodiments of the present invention, when the total number of pixels on the branch where the first branch point is located is smaller than the first preset threshold, the pseudo-branch determining module determines whether the number of associated pixels of each pixel on the branch where the first branch point is located is smaller than 2 (i.e. determines whether the branch where the first branch point is located has a sub-branch), and when the total number of pixels on the branch where the first branch point is located is smaller than the first preset threshold and the branch where the first branch point is located does not include the sub-branch, determines the branch where the first branch point is located as a pseudo-branch, and compared with the related art, further filters the branch where the first branch point is located based on the total number of included pixels, so as to avoid a situation that a correct branch where the total number of included pixels is smaller than the preset threshold is erroneously determined as a pseudo-branch, the accuracy of determining the center line of the blood vessel is effectively improved.
Optionally, as shown in fig. 6-2, the apparatus 600 may further include:
and a noise determining module 604, configured to determine the first split point as a noise if the first split point does not have a related pixel point, and delete the noise from the three-dimensional model of the blood vessel.
Optionally, as shown in fig. 6-2, the apparatus 600 may further include:
a correct branch determining module 605, configured to determine, if the total number of pixel points on the branch where the first branch point is located is greater than a first preset threshold, the branch where the first branch point is located as a correct branch of the blood vessel centerline, and keep the correct branch in the three-dimensional model of the blood vessel.
Or, the correct branch determining module 605 is configured to determine, if at least two associated pixel points exist for a certain pixel point on a branch where the first branch point is located, the total number of pixel points on the branch where at least one associated pixel point exists among the at least two associated pixel points is greater than a first preset threshold, and the number of pixel points between the first branch point and the certain pixel point is less than a second preset threshold, a branch formed by pixel points between the first branch point and the certain pixel point as a correct branch of the blood vessel centerline, and keep the correct branch in the three-dimensional model of the blood vessel.
Optionally, the detection module 601 may be specifically configured to: and sequentially detecting the pixel points in the blood vessel three-dimensional model according to the arrangement sequence of the pixel points in the blood vessel three-dimensional model by using a breadth-first traversal algorithm and according to the connectivity of the pixel neighborhood.
Optionally, the pixel neighborhood is a 26 neighborhood.
In summary, in the apparatus for processing a blood vessel centerline according to the embodiments of the present invention, when the total number of pixels on the branch where the first branch point is located is smaller than the first preset threshold, the pseudo-branch determining module determines whether the number of associated pixels of each pixel on the branch where the first branch point is located is smaller than 2 (i.e. determines whether the branch where the first branch point is located has a sub-branch), and when the total number of pixels on the branch where the first branch point is located is smaller than the first preset threshold and the branch where the first branch point is located does not include the sub-branch, determines the branch where the first branch point is located as a pseudo-branch, and compared with the related art, further filters the branch where the first branch point is located based on the total number of included pixels, so as to avoid a situation that a correct branch where the total number of included pixels is smaller than the preset threshold is erroneously determined as a pseudo-branch, the accuracy of determining the center line of the blood vessel is effectively improved.
It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described apparatuses and modules may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The embodiment of the invention provides a storage medium, wherein the storage medium stores instructions, and when the storage medium runs on a computer, the storage medium enables the computer to execute the blood vessel centerline processing method provided by the embodiment of the invention.
The embodiment of the invention provides a terminal, which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein when the processor executes the computer program, the blood vessel center line processing method provided by the embodiment of the invention is realized.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (10)
1. A method of determining a centerline of a blood vessel, the method comprising:
sequentially detecting pixel points in the blood vessel three-dimensional model according to the arrangement sequence of the pixel points in the blood vessel three-dimensional model;
if the number of associated pixel points of a currently detected first pixel point is larger than 1, determining the associated pixel points as first fork points of the first pixel point, wherein the associated pixel points are pixel points which are adjacent to the first pixel point and are not detected;
and if the number of the associated pixel points of each pixel point on the branch where the first branch point is located is less than 2, and the total number of the pixel points on the branch where the first branch point is located is less than a first preset threshold value, determining the branch where the first branch point is located as a pseudo branch, and deleting the pseudo branch from the blood vessel three-dimensional model.
2. The method according to claim 1, wherein if the number of associated pixels of the currently detected first pixel is greater than 1, after determining the associated pixels as first fork points of the first pixel, further comprising:
and if the first branch point has no associated pixel point, determining the first branch point as a noise point, and deleting the noise point from the blood vessel three-dimensional model.
3. The method according to claim 1, wherein if the number of associated pixels of the currently detected first pixel is greater than 1, after determining the associated pixels as first fork points of the first pixel, further comprising:
if the total number of pixel points on the branch where the first branch point is located is larger than a first preset threshold value, determining the branch where the first branch point is located as a correct branch of the blood vessel center line, and keeping the correct branch in the blood vessel three-dimensional model;
or, if at least two associated pixel points exist in a certain pixel point on a branch where the first bifurcation point is located, the total number of the pixel points on the branch where at least one associated pixel point exists in the at least two associated pixel points is greater than a first preset threshold, and the number of the pixel points between the first bifurcation point and the certain pixel point is less than a second preset threshold, determining a branch formed by the pixel points between the first bifurcation point and the certain pixel point as a correct branch of the blood vessel center line, and keeping the correct branch in the blood vessel three-dimensional model.
4. The method according to any one of claims 1 to 3, wherein the sequentially detecting the pixel points in the blood vessel three-dimensional model according to the arrangement order of the pixel points in the blood vessel three-dimensional model comprises:
and sequentially detecting the pixel points in the blood vessel three-dimensional model according to the arrangement sequence of the pixel points in the blood vessel three-dimensional model by using a breadth-first traversal algorithm and according to the connectivity of the pixel neighborhood.
5. An apparatus for determining a centerline of a blood vessel, the apparatus comprising:
the detection module is used for sequentially detecting the pixel points in the blood vessel three-dimensional model according to the arrangement sequence of the pixel points in the blood vessel three-dimensional model;
the pixel detection module is used for detecting whether the number of the associated pixels of the currently detected first pixel is larger than 1 or not;
and the pseudo branch determining module is used for determining the branch of the first branch point as a pseudo branch and deleting the pseudo branch from the blood vessel three-dimensional model if the number of the associated pixel points of each pixel point on the branch of the first branch point is less than 2 and the total number of the pixel points on the branch of the first branch point is less than a first preset threshold value.
6. The apparatus of claim 5, further comprising:
and the noise point determining module is used for determining the first branch point as a noise point and deleting the noise point from the blood vessel three-dimensional model if the first branch point has no associated pixel point.
7. The apparatus of claim 5, further comprising:
a correct branch determining module, configured to determine, if the total number of pixel points on the branch where the first branch point is located is greater than a first preset threshold, the branch where the first branch point is located as a correct branch of a blood vessel centerline, and retain the correct branch in the three-dimensional model of the blood vessel;
or, the correct branch determining module is configured to determine, if at least two associated pixel points exist for a certain pixel point on a branch where the first branch point is located, a total number of pixel points on the branch where at least one associated pixel point exists among the at least two associated pixel points is greater than a first preset threshold, and a number of pixel points between the first branch point and the certain pixel point is less than a second preset threshold, a branch formed by pixel points between the first branch point and the certain pixel point as a correct branch of the blood vessel centerline, and retain the correct branch in the three-dimensional model of the blood vessel.
8. The apparatus according to any one of claims 5 to 7, wherein the detection module is specifically configured to:
and sequentially detecting the pixel points in the blood vessel three-dimensional model according to the arrangement sequence of the pixel points in the blood vessel three-dimensional model by using a breadth-first traversal algorithm and according to the connectivity of the pixel neighborhood.
9. A storage medium having instructions stored thereon, which when run on a computer, cause the computer to perform the method of determining a vessel centerline of any of claims 1 to 4.
10. A terminal comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor, when executing the computer program, implements the method for determining a vessel centerline according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710470577.2A CN107346543B (en) | 2017-06-20 | 2017-06-20 | Blood vessel center line processing method and device, terminal and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710470577.2A CN107346543B (en) | 2017-06-20 | 2017-06-20 | Blood vessel center line processing method and device, terminal and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107346543A CN107346543A (en) | 2017-11-14 |
| CN107346543B true CN107346543B (en) | 2020-02-07 |
Family
ID=60253321
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710470577.2A Active CN107346543B (en) | 2017-06-20 | 2017-06-20 | Blood vessel center line processing method and device, terminal and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107346543B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117495667B (en) * | 2023-12-29 | 2024-03-22 | 柏意慧心(杭州)网络科技有限公司 | Method, computing device, and medium for determining a vessel centerline |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101127085A (en) * | 2006-07-28 | 2008-02-20 | 索尼株式会社 | Image processing method and image processing device |
| CN101384211A (en) * | 2006-03-14 | 2009-03-11 | 奥林巴斯医疗株式会社 | Image analyzing device and image analyzing method |
| CN101393644A (en) * | 2008-08-15 | 2009-03-25 | 华中科技大学 | Hepatic portal vein tree modeling method and system thereof |
| CN101681511A (en) * | 2007-05-15 | 2010-03-24 | 索尼株式会社 | Registering device, checking device, program, and data structure |
| CN102663416A (en) * | 2012-03-20 | 2012-09-12 | 苏州迪凯尔医疗科技有限公司 | Segmentation method of viscera and internal blood vessels thereof in surgical planning system |
| CN104331702A (en) * | 2014-11-03 | 2015-02-04 | 黄辉 | Image-recognition-based fresh tea leaf furcation number recognition method |
-
2017
- 2017-06-20 CN CN201710470577.2A patent/CN107346543B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101384211A (en) * | 2006-03-14 | 2009-03-11 | 奥林巴斯医疗株式会社 | Image analyzing device and image analyzing method |
| CN101127085A (en) * | 2006-07-28 | 2008-02-20 | 索尼株式会社 | Image processing method and image processing device |
| CN101681511A (en) * | 2007-05-15 | 2010-03-24 | 索尼株式会社 | Registering device, checking device, program, and data structure |
| CN101393644A (en) * | 2008-08-15 | 2009-03-25 | 华中科技大学 | Hepatic portal vein tree modeling method and system thereof |
| CN102663416A (en) * | 2012-03-20 | 2012-09-12 | 苏州迪凯尔医疗科技有限公司 | Segmentation method of viscera and internal blood vessels thereof in surgical planning system |
| CN104331702A (en) * | 2014-11-03 | 2015-02-04 | 黄辉 | Image-recognition-based fresh tea leaf furcation number recognition method |
Non-Patent Citations (4)
| Title |
|---|
| 64层螺旋CT血管成像技术分析;马晓晖 等;《实用放射学杂志》;20070228;第23卷(第2期);154-156、164 * |
| Three-Dimensional Blood Vessel Quantification via Centerline Deformation;Dong-Goo Kang 等;《MEDICAL IMAGING》;20090331;第28卷(第3期);405-414 * |
| 一种方向链码扫描与跟踪的图像细化后期处理算法;瞿中 等;《计算机科学》;20150228;第42卷(第2期);292-295 * |
| 基于Canny 算子的农田线状工程地物自动提取方法;张超 等;《农业机械学报》;20150228;第46卷(第2期);270-275 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107346543A (en) | 2017-11-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111815599B (en) | Image processing method, device, equipment and storage medium | |
| KR102144706B1 (en) | Apparatus and method for detecting road based on convolutional neural network | |
| CN111768411B (en) | Coronary centerline extraction method, device, computer equipment and storage medium | |
| EP2860695B1 (en) | Method and apparatus for identifying noise in disparity depth image | |
| US8965132B2 (en) | Edge tracing with hysteresis thresholding | |
| CN108805180B (en) | Target object detection method and device | |
| KR101618996B1 (en) | Sampling method and image processing apparatus for estimating homography | |
| WO2014143891A1 (en) | Automated separation of binary overlapping trees | |
| CN113112490B (en) | Three-dimensional medical image mark point extraction method and system | |
| US20030083567A1 (en) | Medical imaging station with a function of extracting a path within a ramified object | |
| CN111667459A (en) | Medical sign detection method, system, terminal and storage medium based on 3D variable convolution and time sequence feature fusion | |
| CN111932495B (en) | Medical image detection method, device and storage medium | |
| CN107346543B (en) | Blood vessel center line processing method and device, terminal and storage medium | |
| CN114240969A (en) | Multi-line laser image defect segmentation method based on stripe multi-view convolution network | |
| CN112116585B (en) | Image removal tampering blind detection method, system, device and storage medium | |
| CN113269752A (en) | Image detection method, device terminal equipment and storage medium | |
| CN113313715A (en) | Method, device, apparatus and medium for segmenting cardiac artery blood vessel | |
| WO2007033228A2 (en) | Reducing false positives for automatic computerized detection of objects | |
| CN112418220A (en) | Single word detection method, device, equipment and medium | |
| CN116563305A (en) | Segmentation method and device for abnormal region of blood vessel and electronic equipment | |
| CN114612710A (en) | Image detection method, image detection device, computer equipment and storage medium | |
| CN114298999A (en) | Method for detecting vascular structure variation, readable storage medium, and program product | |
| CN107240101A (en) | Target area detection method and device, image partition method and device | |
| CN112750124A (en) | Model generation method, image segmentation method, model generation device, image segmentation device, electronic equipment and storage medium | |
| CN109657523B (en) | Driving region detection method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |