CN116740164A - Method, apparatus and storage medium for extracting a vessel centerline - Google Patents
Method, apparatus and storage medium for extracting a vessel centerline Download PDFInfo
- Publication number
- CN116740164A CN116740164A CN202310712883.8A CN202310712883A CN116740164A CN 116740164 A CN116740164 A CN 116740164A CN 202310712883 A CN202310712883 A CN 202310712883A CN 116740164 A CN116740164 A CN 116740164A
- Authority
- CN
- China
- Prior art keywords
- point
- points
- blood vessel
- bifurcation
- searching
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 57
- 210000004204 blood vessel Anatomy 0.000 claims abstract description 76
- 238000010276 construction Methods 0.000 claims abstract description 57
- 238000012216 screening Methods 0.000 claims abstract description 6
- 238000000605 extraction Methods 0.000 claims description 18
- 238000009499 grossing Methods 0.000 claims description 13
- 230000004044 response Effects 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 abstract description 19
- 238000004458 analytical method Methods 0.000 abstract description 11
- 238000004422 calculation algorithm Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 10
- 230000009286 beneficial effect Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000001514 detection method Methods 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000002792 vascular Effects 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 239000000470 constituent Substances 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000000877 morphologic effect Effects 0.000 description 2
- 238000004445 quantitative analysis Methods 0.000 description 2
- 230000002194 synthesizing effect Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000009960 carding Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 208000019553 vascular disease Diseases 0.000 description 1
Classifications
-
- 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
-
- 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
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- 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
-
- 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
- G06T2207/30172—Centreline of tubular or elongated structure
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Geometry (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- General Health & Medical Sciences (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The present disclosure discloses a method, apparatus and storage medium for extracting a vessel centerline. The method comprises the following steps: extracting skeleton feature points of blood vessels; screening bifurcation points and edge construction points from skeleton feature points; taking the bifurcation point as a searching starting point of one round, taking the point meeting the ending condition as a searching end point of one round, searching the bifurcation point and the edge construction point, and generating a blood vessel center line segment according to a searching track of one round so as to form a plurality of blood vessel center line segments; and connecting the bifurcation points to connect a number of vessel centerline segments into a vessel centerline. According to the method provided by the embodiment of the disclosure, the bifurcation points and the edge construction points can be searched point by point, so that a blood vessel central line segment is formed based on the search track of each round, and further the completed blood vessel central line is synthesized, and the analysis and calculation of the three-dimensional blood vessel structure are facilitated.
Description
Technical Field
The present disclosure relates generally to the field of medical image processing technology. More particularly, the present disclosure relates to a method, apparatus, and storage medium for extracting a vessel centerline.
Background
The three-dimensional blood vessel center line is the basis of analysis and calculation of the three-dimensional blood vessel structure, and the traditional calculation method of the three-dimensional blood vessel center line can be divided into two types according to the processing object, namely a calculation mode based on a binarized image, and a calculation mode based on three-dimensional unstructured grid data.
The binary image mask is used for extracting the skeleton based on the binary image, and the obtained vascular skeleton is used as a vascular central line. However, the vessel centerline obtained in this way is often discrete several points or line segments, and a global, complete vessel centerline cannot be formed, resulting in a limited analysis and calculation of the three-dimensional vessel structure.
In view of this, it is desirable to provide a blood vessel centerline extraction scheme to form a complete and continuous blood vessel centerline, which can provide both global data of the blood vessel centerline and segmented data of the blood vessel centerline, thereby enriching the data dimension of three-dimensional blood vessel structure analysis and calculation and enhancing the effect of three-dimensional blood vessel structure analysis and calculation.
Disclosure of Invention
To address at least one or more of the technical problems mentioned above, the present disclosure proposes a vessel centerline extraction scheme in various aspects.
In a first aspect, the present disclosure provides a method for extracting a vessel centerline comprising: extracting skeleton feature points of blood vessels; screening bifurcation points and edge construction points from skeleton feature points; taking the bifurcation point as a searching starting point of one round, taking the point meeting the ending condition as a searching end point of one round, searching the bifurcation point and the edge construction point, and generating a blood vessel center line segment according to a searching track of one round so as to form a plurality of blood vessel center line segments; and connecting the bifurcation points to connect a number of vessel centerline segments into a vessel centerline.
In some embodiments, wherein searching for bifurcation points and edge construction points and generating a vessel centerline segment according to a round of search trajectory comprises: searching a current point; and responding to that the neighborhood position of the current point has only one unsearched edge construction point, after updating the current point into the unsearched edge construction point, returning to the step of searching the current point until the ending condition is met, and connecting the searched points in the current round to form a blood vessel central line segment.
In some embodiments, wherein the end condition comprises at least one of the following conditions: the neighbor position of the current point is not provided with an unsearched edge construction point; and the current point is another bifurcation point that is distinct from the search start point in the current round.
In some embodiments, wherein after connecting the points searched in the current round, the method further comprises: responding to the searching end point as the bifurcation point, taking the searching end point as a searching start point of a new round and searching for the new round until all bifurcation points are searched; or in response to the searching end point being an edge construction point, randomly selecting an unsearched branch point from the branch points as a new round of searching start point, and searching for a new round until all branch points are searched.
In some embodiments, wherein screening bifurcation points and edge construction points from skeleton feature points using neighborhood relationships comprises: responding to more than 3 skeleton feature points in the neighborhood positions of the current skeleton feature points, and recognizing the current skeleton feature points as bifurcation points; and in response to the fact that 2 skeleton feature points exist in the neighborhood positions of the current skeleton feature point, recognizing the current skeleton feature point as an edge construction point.
In some embodiments, wherein connecting the bifurcation point comprises: each branch point is connected to another branch point that is closest to it.
In some embodiments, wherein after forming the plurality of vessel centerline segments, the method further comprises: and carrying out smoothing treatment on the plurality of blood vessel center line segments so as to connect the blood vessel center line segments after the smoothing treatment into a blood vessel center line when the bifurcation points are connected.
In some embodiments, wherein after connecting the bifurcation point, the method further comprises: calculating the minimum distance between each point on the blood vessel central line and the blood vessel boundary point by point to obtain the preliminary estimated radius of the blood vessel at each point; and performing offset compensation based on the preliminary estimated radius to obtain a theoretical radius of the blood vessel at each point.
In some embodiments, wherein extracting skeletal feature points of the blood vessel comprises: acquiring a binarized image of a blood vessel; and performing skeleton extraction based on the mask of the binarized image to obtain skeleton feature points of the blood vessel.
In some embodiments, the neighborhood positions employ 26 neighborhood positions.
In some embodiments, wherein during the smoothing process, the bifurcation point on the vessel centerline segment does not perform the smoothing process.
In a second aspect, the present disclosure provides an electronic device for extracting a vessel centerline comprising: a processor; and a memory storing program instructions for extracting a vessel centerline, which when executed by the processor, cause the electronic device to implement the method according to any one of the first aspects.
In a third aspect, the present disclosure provides a computer-readable storage medium having stored thereon computer-readable instructions for extracting a vessel centerline, which when executed by one or more processors, implement the method according to any one of the first aspects.
By the method for extracting the blood vessel center line provided by the above, the embodiment of the disclosure extracts the bifurcation point and the edge construction point in the skeleton feature point, searches point by point, and the search track of each round can form an edge, namely a blood vessel center line segment, and then connects the bifurcation points to obtain the completed blood vessel center line. The blood vessel center line obtained by the method provided by the embodiment of the disclosure is complete, smooth and communicated, rather than discrete multiple points or line segments, which is more beneficial to three-dimensional blood vessel structure analysis and calculation and is more beneficial to completing the accurate identification of blood vessel diseases.
Drawings
The above, as well as additional purposes, features, and advantages of exemplary embodiments of the present disclosure will become readily apparent from the following detailed description when read in conjunction with the accompanying drawings. Several embodiments of the present disclosure are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings and in which like reference numerals refer to similar or corresponding parts and in which:
FIG. 1 is a schematic diagram of a vessel centerline segment output by a conventional three-dimensional vessel centerline calculation method;
FIG. 2 illustrates an exemplary flowchart of a method of extracting a vessel centerline in accordance with some embodiments of the present disclosure;
FIG. 3 illustrates an example diagram of skeleton feature points of some embodiments of the present disclosure;
FIG. 4 illustrates an exemplary flowchart of a search method for extracting a vessel centerline in accordance with some embodiments of the present disclosure;
FIG. 5 illustrates an exemplary flowchart of a method of extracting a vessel centerline in accordance with further embodiments of the present disclosure;
FIG. 6 illustrates an exemplary flowchart of a method of calculating a vessel radius in accordance with further embodiments of the present disclosure;
fig. 7 shows an exemplary block diagram of the electronic device of an embodiment of the present disclosure.
Detailed Description
The following description of the embodiments of the present disclosure will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the disclosure. Based on the embodiments in this disclosure, all other embodiments that may be made by those skilled in the art without the inventive effort are within the scope of the present disclosure.
It should be understood that the terms "comprises" and "comprising," when used in this specification and the claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the present disclosure is for the purpose of describing particular embodiments only, and is not intended to be limiting of the disclosure. As used in the specification and claims of this disclosure, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should be further understood that the term "and/or" as used in the present disclosure and claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
As used in this specification and the claims, the term "if" may be interpreted as "when..once" or "in response to a determination" or "in response to detection" depending on the context. Similarly, the phrase "if a determination" or "if a [ described condition or event ] is detected" may be interpreted in the context of meaning "upon determination" or "in response to determination" or "upon detection of a [ described condition or event ]" or "in response to detection of a [ described condition or event ]".
Specific embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.
Exemplary application scenarios
The three-dimensional blood vessel center line is the basis of three-dimensional blood vessel structure analysis and calculation, and has important significance for blood vessel topological structure expression and blood vessel quantitative analysis. How to realize an accurate and rapid vessel centerline extraction algorithm is a concern in the field of medical images.
The accurate extraction of the blood vessel center line has a plurality of difficulties, namely, the blood vessel image usually contains a complex background, image noise and other tissue and organ interference exist, and the blood vessel is changeable in form and complex in topology, so that the difficulty of extracting the blood vessel center line is improved.
In the traditional three-dimensional blood vessel central line calculation method, a central line calculation mode based on a binary image exists, skeleton extraction is carried out on a binary image mask of a blood vessel, and then the obtained blood vessel skeleton is used as a blood vessel central line. However, the vessel centerline obtained in this way is often a discrete number of points or line segments as shown in fig. 1, and a global, complete vessel centerline cannot be formed, resulting in a limitation in three-dimensional vessel structure analysis and calculation.
Exemplary extraction protocol
In view of this, the embodiments of the present disclosure provide a blood vessel centerline extraction scheme, which is more advantageous for three-dimensional blood vessel structure analysis and calculation by searching bifurcation points and edge construction points point by point, thereby forming a blood vessel centerline segment based on the search track of each round, and thus synthesizing the completed blood vessel centerline.
Fig. 2 illustrates an exemplary flowchart of a method 200 of extracting a vessel centerline according to some embodiments of the present disclosure.
As shown in fig. 2, in step S201, skeleton feature points of a blood vessel are extracted.
Skeleton extraction refers to the process that after a part of points in a binary image are removed, the retained points can still keep the original shape, so that the skeleton of the image is formed. The skeleton feature points are points of the skeleton constituting the image, and can be classified into end points, bifurcation points, edge construction points and the like according to the positions of the skeleton, for example, the bifurcation points are points of the skeleton at positions where branches start to form, and the edge construction points are points of one skeleton edge except for the end points at two ends.
In the present embodiment, skeleton feature points may be extracted by performing the steps of:
acquiring a binarized image of a blood vessel;
and performing skeleton extraction based on a mask of the binarized image to obtain skeleton feature points of the blood vessel.
The algorithm adopted in the skeleton extraction operation may be Zhang-Suen refinement algorithm or other skeleton extraction algorithm, so as to maintain connectivity and topology of skeleton feature points, for example: in practical application, the skeleton can also be extracted by adopting a three-dimensional medium-surface/axis refinement algorithm.
It will be appreciated that the above skeleton extraction algorithm is only one example of an algorithm applicable to the present embodiment, and does not constitute the only limitation of the present disclosure.
In step S202, branch points and edge structure points are selected from the skeleton feature points.
In this embodiment, the bifurcation point and the edge construction point may be screened out by a neighborhood judgment manner, specifically, step S202 judges the type to which the current skeleton feature point belongs according to the skeleton feature point distribution situation on 26 neighborhood positions of the current skeleton feature point.
Illustratively, the determination process of the type to which the skeleton feature point belongs is as follows:
responding to more than 3 skeleton feature points in the neighborhood positions of the current skeleton feature points, and recognizing the current skeleton feature points as bifurcation points;
and in response to the fact that 2 skeleton feature points exist in the neighborhood positions of the current skeleton feature point, the current skeleton feature point is considered to be an edge construction point.
FIG. 3 illustrates an example diagram of skeleton feature points of some embodiments of the present disclosure, as shown in FIG. 3, where at least 3 other skeleton feature points exist in a neighborhood of a bifurcation point, illustrating that at least two branches of the skeleton may be formed from the skeleton feature points, i.e., the skeleton feature points are bifurcation points; there are only 2 other skeleton feature points in the neighborhood of the edge construction point, which means that the skeleton feature point is located on one edge and only located on the one edge, that is, the skeleton feature point is the edge construction point.
In step S203, the bifurcation point and the edge construction point are searched, and a blood vessel centerline segment is generated in accordance with a round of search trajectory.
Specifically, step S203 searches for the bifurcation point and the edge structure point by taking the bifurcation point as a search start point of one round and taking a point satisfying the end condition as a search end point of one round, and generates a blood vessel center line segment according to a search track of one round after one round of search is completed, thereby forming a plurality of blood vessel center line segments.
It will be understood that, in step S202, a set of points to be searched, which is formed by bifurcation points and edge construction points, is formed, and in step S203, the points in the set of points to be searched are searched point by point, and each round of searching points form a blood vessel central line segment.
The complete vessel centerline is often a vessel centerline network, which can be considered to be composed of a plurality of sides of different lengths, each side can have two bifurcation points as the starting point and the ending point, and there is a part of sides that have one bifurcation point and one ending point as the starting point and the ending point, so that the side construction point can be searched point by point along one side to the other bifurcation point or the ending point with one bifurcation point as the searching starting point, and since one side can be considered to be formed by connecting innumerable points, a line can be constructed according to the searching track of one round to be taken as a vessel centerline.
In some embodiments, the end condition includes at least one of the following conditions: there is no unsearched edge construction point in the neighborhood of the current point and the current point is another bifurcation point which is different from the search starting point in the current round. The fact that no unsearched edge construction point exists in the neighborhood position of the current point indicates that the search touch reaches an end point in the skeleton feature point, and the end point is the end point of one edge. Wherein the current point is another branch point different from the search starting point in the current round, and the current search edge is described as taking the two branch points as the starting point and the end point respectively.
Further, after multiple rounds of searching are performed by taking each bifurcation point as a searching starting point, multiple lines can be constructed by multiple rounds of searching tracks, and then a plurality of blood vessel center line segments are formed.
It should be noted that, in the searching process, when the branch point is extracted as the searching start point, a random extraction manner or an ordered extraction manner may be adopted, which is not limited only herein.
According to the embodiment, the edge searching is completed in a point-by-point searching mode, carding of a plurality of blood vessel center line segments can be completed on the premise that skeleton feature points are not omitted, small-range continuous blood vessel center line segments are formed through integration of small-range discrete points, and then the small-range continuous blood vessel center line segments are integrated into a global continuous blood vessel center line through subsequent steps.
In step S204, the bifurcation point is connected to connect several vessel centerline segments into a vessel centerline.
The plurality of vessel centerline segments obtained in step S203 may be regarded as a plurality of branches led out from the branch points, and thus the plurality of vessel centerline segments may be connected to a vessel centerline by determining the connection relationship between the branch points.
When the branch points are connected, the connection relationship between the branch points needs to avoid forming a local loop, so that the connection relationship between the branch points can be determined by using the constraint condition of the shortest distance, thereby realizing the connection at the branch points.
In particular, when connecting the branch points, each branch point may be connected to another branch point that is closest thereto, thereby avoiding the formation of a local loop between the branch points.
Further, in actual application, the following may exist: for the branches Q, W, R and T, the branch point closest to the branch point Q is W and the branch point closest to the branch point W is Q, the branch point closest to the branch point R is T and the branch point closest to the branch point T is R, and after the connection is completed, the vessel centerline QW and the vessel centerline RT are still separated. In order to ensure complete communication between the vessel centerline segments, the number of connected domains formed by the skeleton feature points may be identified after step S204 is performed, and when the number of connected domains is 1, it is indicated that a completely connected vessel centerline network has been formed, then a global vessel centerline may be output, and when the number of connected domains is more than 1, assuming that the number of connected domains is 2, the branch points closest to the 2 connected domains are connected to form a completely connected vessel centerline network.
It should be understood that the above-described method for determining connectivity of a vascular central line network is only an example provided in this embodiment, and in practical applications, other methods for determining network connectivity are also applicable to the present disclosure, and will not be described herein.
In order to facilitate understanding of the blood vessel centerline extraction method shown in the foregoing embodiments, the present disclosure provides a search method for extracting a blood vessel centerline as shown in fig. 4 to explain the execution of the above-described step S203 in detail.
Fig. 4 illustrates an exemplary flowchart of a search method 400 for extracting a vessel centerline according to some embodiments of the present disclosure, it being understood that the search method for extracting a vessel centerline is one specific implementation of step S203 described previously, and thus the features described previously in connection with fig. 2 may be similarly applied thereto.
In step S401, the current point is searched for.
The current point is a point serving as a search center under the current opportunity, namely the point which is accessed by the current round, and if the current opportunity is halfway of one round of search, the current point is an edge construction point.
In step S402, it is determined whether the current point satisfies the end condition.
In the present embodiment, the end condition includes at least one of the following conditions: there is no unsearched edge construction point in the neighborhood of the current point and the current point is another bifurcation point which is different from the search starting point in the current round.
If the current point does not meet the ending condition, at this time, there is only one unsearched edge construction point in the neighborhood of the current point, and after executing step S403, the process returns to execute step S401;
if the current point satisfies the end condition, step S404 is executed.
In step S403, the current point is updated to an unsearched edge construction point on the neighborhood position.
In this embodiment, step S403 corresponds to orderly moving the access node along the direction in which the searched point points to the non-searched point, where the moving track is the searching track of the current round.
In step S404, the points searched for in the current round are connected to form a vessel centerline segment.
In order to facilitate understanding of the above-described process, the above-described search process is described below in connection with skeleton feature points shown in fig. 3.
Assuming that the edge construction point A is searched currently, that is, the current point is the edge construction point A, 26 neighborhood positions of the edge construction point A are judged, and only one unsearched edge construction point B is found, the search center is modified to be the edge construction point B at the moment, that is, the current point is updated to be the edge construction point B, the 26 neighborhood positions of the edge construction point B are continuously judged, only one unsearched edge construction point C and one searched edge construction point A are found, the condition that the end condition is not met is met, and therefore the search center is continuously modified to be the edge construction point C until the bifurcation point D is searched, the end condition is met, and the search of the edge AD is completed.
In addition, there is a case that the branch point E is used as a searching starting point, the edge construction point F and the edge construction point G are sequentially searched, when the current point is the edge construction point G, no unsearched edge construction point exists in 26 neighborhood positions of the edge construction point G, which means that the currently searched edge takes the branch point and the end point as the starting point and the end point, so that another branch point cannot be searched, another ending condition is met, and the search of the edge EG is completed.
Each time a search for an edge is completed, it is indicated that a round of search is completed, and a new round of search needs to be started. When a new search is started, the starting point of the search can be determined according to the following manner:
and firstly, responding to the searching end point as the bifurcation point, taking the searching end point as a searching start point of a new round and searching for the new round until all bifurcation points are searched.
And secondly, responding to the searching end point as an edge construction point, randomly selecting an unsearched branch point from branch points as a new searching start point, and searching for a new round until all branch points are searched.
In the first case described above, if the previous search ends at a branch point, another branch of the branch point may be searched for with this branch point as the search start point.
In the second case described above, the previous round of searching ends at the edge construction point, indicating that the branch has reached an end point in the skeleton feature point, where there is no branch to continue searching down, so that it is necessary to re-extract a new round of searching starting point from the unsearched branch point, where the new round of searching starting point can be determined in a randomly selected manner.
When all bifurcation points are searched, and all vessel center line segments forming a vessel center line network are searched, the step of searching point by point is finished, and the step of synthesizing the vessel center line segments into a vessel center line is executed.
Since the fluent line is formed by connecting a plurality of points, the method for extracting the blood vessel central line provided by the disclosure forms the blood vessel central line segment based on a limited number of search points, and therefore, the fluency of the line is insufficient, and in order to overcome the fluency problem, the fluent blood vessel central line can be formed through smoothing. Fig. 5 illustrates an exemplary flowchart of a method 500 of extracting a vessel centerline in accordance with further embodiments of the present disclosure.
As shown in fig. 5, in step S501, skeleton feature points of a blood vessel are extracted.
In this embodiment, the content of step S501 is identical to step S201 in the previous embodiment, and a detailed description is omitted here.
In step S502, branch points and edge structure points are selected from the skeleton feature points.
In this embodiment, the content of step S502 is identical to step S202 in the previous embodiment, and a detailed description is omitted here.
In step S503, the bifurcation point and the edge construction point are searched, and a blood vessel centerline segment is generated in accordance with a round of search trajectory.
In this embodiment, the content of step S503 is identical to step S203 in the previous embodiment, and a detailed description is omitted here.
In step S504, a plurality of vessel centerline segments are smoothed.
There are a variety of smoothing algorithms in practical applications, such as neighborhood averaging, median filtering, and boundary preservation, among others. Those skilled in the art will appreciate that the disclosed embodiments are not limited in the smoothing algorithm employed.
Further, since the connection relationship between the branch points is complicated, the characteristic of the branch points is changed to cause the connection relationship to be changed once it is changed, so that the branch points on the blood vessel center line segment do not perform the smoothing process in order to secure the stability of the blood vessel center line network.
In step S505, the bifurcation point is connected, and the smoothed vessel centerline segment is connected to the vessel centerline.
Step S505 may determine a connection relationship with the shortest distance, thereby realizing the connection at the bifurcation point. In particular, each branch point may be connected to another branch point that is closest thereto, thereby avoiding the formation of a local loop between branch points.
In the present disclosure, after a global vessel centerline network is synthesized by connecting bifurcation points, the IDs of each point in the network are unique and determined, so that the points can be re-selected, and then the vessel centerline segments can be re-intercepted by both points.
Further, after the bifurcation point is connected, the vessel radius corresponding to each point on the vessel centerline segment may be calculated point by point.
Fig. 6 illustrates an exemplary flowchart of a method 600 of calculating a vessel radius according to further embodiments of the present disclosure.
As shown in fig. 6, in step S601, the minimum distance from each point on the vessel centerline to the vessel boundary is calculated point by point to obtain a preliminary estimated radius of the vessel at each point.
In this embodiment, step S601 may perform calculation of a preliminary estimated radius of a blood vessel for a global blood vessel centerline, or may rapidly extract a blood vessel centerline segment between two positioning points by selecting points, and then calculate a preliminary estimated radius of a blood vessel corresponding to each point on the blood vessel centerline segment.
In step S602, offset compensation is performed based on the preliminary estimated radius to obtain the theoretical radius of the blood vessel at each point.
In this embodiment, the offset may be determined by performing numerical statistics based on the historical data of the preliminary estimated radius and the corresponding real data, and reducing the radius calculation error by offset compensation, so that the theoretical radius of the blood vessel is closer to the real radius.
In practical application, calculating the theoretical radius of the blood vessel can assist in completing three-dimensional modeling of the blood vessel, thereby further assisting quantitative analysis of morphological characteristics of the blood vessel, being beneficial to completing accurate screening of vascular diseases and the like.
In summary, the embodiments of the present disclosure provide a method for extracting a blood vessel centerline, which can perform a point-by-point search by using bifurcation points and edge construction points in skeleton feature points, thereby completing the search of edges in the skeleton, forming a plurality of blood vessel centerline segments, and obtaining a global blood vessel centerline by connecting bifurcation points. The global blood vessel center line is more beneficial to three-dimensional blood vessel structure analysis and calculation and is more beneficial to completing the accurate identification of blood vessel diseases.
Further, the embodiment of the disclosure provides a method for extracting a blood vessel center line, which processes a plurality of blood vessel center line segments obtained by using a smoothing algorithm, so that the smoothness of the blood vessel center line segments is improved, the extracted blood vessel center line is more fit with a real blood vessel center line, and the accuracy is higher.
The embodiment of the disclosure can also calculate the radius of the blood vessel at the central point of each blood vessel based on the obtained blood vessel central line, further provide more dimensional parameters for three-dimensional modeling of the blood vessel, improve the accuracy of morphological characteristics of the blood vessel model, and further improve the reliability of analysis and calculation results of the three-dimensional blood vessel structure.
Corresponding to the foregoing functional embodiments, an electronic device as shown in fig. 7 is also provided in the embodiments of the present disclosure. Fig. 7 shows an exemplary block diagram of an electronic device 700 of an embodiment of the disclosure.
An electronic device 700 shown in fig. 7, comprising: a processor 710; and a memory 720 having stored thereon executable program instructions for extracting a vessel centerline, which when executed by the processor 710, cause the electronic device to implement any of the methods as described above.
In the electronic apparatus 700 of fig. 7, only constituent elements related to the present embodiment are shown. Thus, it will be apparent to those of ordinary skill in the art that: the electronic device 700 may also include common constituent elements that are different from those shown in fig. 7.
Processor 710 may control the operation of electronic device 700. For example, the processor 710 controls the operation of the electronic device 700 by executing programs stored in the memory 720 on the electronic device 700. The processor 710 may be implemented by a Central Processing Unit (CPU), an Application Processor (AP), an artificial intelligence processor chip (IPU), etc. provided in the electronic device 700. However, the present disclosure is not limited thereto. In this embodiment, the processor 710 may be implemented in any suitable manner. For example, the processor 710 may take the form of, for example, a microprocessor or processor, and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), a programmable logic controller, and an embedded microcontroller, among others.
Memory 720 may be used to store hardware for various data, instructions that are processed in electronic device 700. For example, the memory 720 may store processed data and data to be processed in the electronic device 700. Memory 720 may store data sets that have been processed or to be processed by processor 710. Further, the memory 720 may store applications, drivers, etc. to be driven by the electronic device 700. For example: memory 720 may store various programs related to skeleton extraction, neighborhood searching, and the like, to be performed by processor 710. The memory 720 may be a DRAM, but the present disclosure is not limited thereto. Memory 720 may include at least one of volatile memory or non-volatile memory. The nonvolatile memory may include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), flash memory, phase change RAM (PRAM), magnetic RAM (MRAM), resistive RAM (RRAM), ferroelectric RAM (FRAM), and the like. Volatile memory can include Dynamic RAM (DRAM), static RAM (SRAM), synchronous DRAM (SDRAM), PRAM, MRAM, RRAM, ferroelectric RAM (FeRAM), and the like. In an embodiment, the memory 720 may include at least one of a Hard Disk Drive (HDD), a Solid State Drive (SSD), a high density flash memory (CF), a Secure Digital (SD) card, a Micro-secure digital (Micro-SD) card, a Mini-secure digital (Mini-SD) card, an extreme digital (xD) card, a cache (cache), or a memory stick.
In summary, specific functions implemented by the memory 720 and the processor 710 of the electronic device 700 provided in the embodiments of the present disclosure may be explained in comparison with the foregoing embodiments of the present disclosure, and may achieve the technical effects of the foregoing embodiments, which will not be repeated herein.
Alternatively, the present disclosure may also be embodied as a non-transitory machine-readable storage medium (or computer-readable storage medium, or machine-readable storage medium) having stored thereon computer program instructions (or computer program, or computer instruction code) for extracting a vessel centerline, which, when executed by a processor of an electronic device (or electronic device, server, etc.), cause the processor to perform part or all of the steps of the above-described method according to the present disclosure.
While various embodiments of the present disclosure have been shown and described herein, it will be obvious to those skilled in the art that such embodiments are provided by way of example only. Numerous modifications, changes, and substitutions will occur to those skilled in the art without departing from the spirit and scope of the present disclosure. It should be understood that various alternatives to the embodiments of the disclosure described herein may be employed in practicing the disclosure. The appended claims are intended to define the scope of the disclosure and are therefore to cover all equivalents or alternatives falling within the scope of these claims.
Claims (13)
1. A method for extracting a vessel centerline, comprising:
extracting skeleton feature points of blood vessels;
screening bifurcation points and edge construction points from the skeleton feature points;
taking the bifurcation point as a searching starting point of one round, taking the point meeting the ending condition as a searching end point of one round, searching the bifurcation point and the edge construction point, and generating a blood vessel center line segment according to a searching track of one round so as to form a plurality of blood vessel center line segments; and
the bifurcation is connected to connect the plurality of vessel centerline segments into a vessel centerline.
2. The method of claim 1, wherein searching for the bifurcation point and the edge construction point and generating a vessel centerline segment according to a round of search trajectory comprises:
searching a current point; and
and in response to that the neighborhood position of the current point has only one unsearched edge construction point, after updating the current point to the unsearched edge construction point, returning to the step of searching the current point until the ending condition is met, and connecting the searched points in the current turn to form a blood vessel center line segment.
3. The method according to claim 1 or 2, wherein the end condition comprises at least one of the following conditions:
the neighbor position of the current point is not provided with an unsearched edge construction point; and
the current point is another bifurcation point that is distinguished from the search start point in the current round.
4. A method according to claim 3, wherein after connecting the points searched in the current round, the method further comprises:
responding to the searching terminal point as a bifurcation point, taking the searching terminal point as a searching starting point of a new round and searching for the new round until all bifurcation points are searched; or (b)
And responding to the searching end point as an edge construction point, randomly selecting an unsearched branch point from the branch points as a new searching start point, and searching for a new round until all branch points are searched.
5. The method of claim 1, wherein screening bifurcation points and edge construction points from the skeletal feature points using neighborhood relationships comprises:
responding to more than 3 skeleton feature points in the neighborhood positions of the current skeleton feature points, and recognizing the current skeleton feature points as bifurcation points; and
and in response to the fact that 2 skeleton feature points exist in the neighborhood positions of the current skeleton feature point, the current skeleton feature point is considered to be an edge construction point.
6. The method of claim 1, wherein connecting the bifurcation point comprises:
each branch point is connected to another branch point that is closest to it.
7. The method of claim 1, wherein after forming a plurality of vessel centerline segments, the method further comprises:
and carrying out smoothing treatment on the plurality of blood vessel center line segments so as to connect the blood vessel center line segments after the smoothing treatment into the blood vessel center line when the bifurcation point is connected.
8. The method of claim 1, wherein after connecting the bifurcation point, the method further comprises:
calculating the minimum distance between each point on the blood vessel center line and the blood vessel boundary point by point to obtain the preliminary estimated radius of the blood vessel at each point; and
and performing offset compensation based on the preliminary estimated radius to obtain the theoretical radius of the blood vessel at each point.
9. The method of claim 1, wherein extracting skeletal feature points of a blood vessel comprises:
acquiring a binarized image of a blood vessel; and
and performing skeleton extraction based on the mask of the binarized image to obtain skeleton feature points of the blood vessel.
10. The method of claim 2 or 5, wherein the neighborhood positions employ 26 neighborhood positions.
11. The method of claim 6, wherein during the smoothing, a bifurcation point on a centerline segment of a blood vessel does not perform the smoothing.
12. An electronic device for extracting a vessel centerline, comprising:
a processor; and
a memory storing program instructions for extracting a vessel centerline, which when executed by the processor, cause the electronic device to implement the method according to any one of claims 1-11.
13. A computer-readable storage medium having stored thereon computer-readable instructions for extracting a vessel centerline, which when executed by one or more processors, implement the method of any of claims 1-11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310712883.8A CN116740164A (en) | 2023-06-15 | 2023-06-15 | Method, apparatus and storage medium for extracting a vessel centerline |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310712883.8A CN116740164A (en) | 2023-06-15 | 2023-06-15 | Method, apparatus and storage medium for extracting a vessel centerline |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116740164A true CN116740164A (en) | 2023-09-12 |
Family
ID=87902473
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310712883.8A Pending CN116740164A (en) | 2023-06-15 | 2023-06-15 | Method, apparatus and storage medium for extracting a vessel centerline |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116740164A (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090322749A1 (en) * | 2007-01-23 | 2009-12-31 | Dtherapeutics, Llc | Systems and methods for extracting a curve-skeleton from a volumetric image of a vessel |
| US20100189333A1 (en) * | 2009-01-28 | 2010-07-29 | Thomas Beck | Method and branching determination device for determining a branching point within a hollow organ |
| CN103247073A (en) * | 2013-04-18 | 2013-08-14 | 北京师范大学 | Three-dimensional brain blood vessel model construction method based on tree structure |
| CN104318557A (en) * | 2014-10-17 | 2015-01-28 | 重庆大学 | Vascular skeleton line reconstruction and precise vessel diameter calculation method |
| CN104361626A (en) * | 2014-09-29 | 2015-02-18 | 北京理工大学 | Subcutaneous vein three-dimensional reconstruction method based on hybrid matching strategy |
| CN112884826A (en) * | 2021-03-26 | 2021-06-01 | 北京阅影科技有限公司 | Method and device for extracting center line of blood vessel |
| CN115731232A (en) * | 2022-12-07 | 2023-03-03 | 沈阳东软智能医疗科技研究院有限公司 | Blood vessel image processing method and device, readable storage medium and electronic equipment |
| CN115778554A (en) * | 2023-01-09 | 2023-03-14 | 深圳市精锋医疗科技股份有限公司 | Catheter robot, registration method thereof and readable storage medium |
| CN115953636A (en) * | 2023-03-10 | 2023-04-11 | 南京博视医疗科技有限公司 | Blood vessel grading method, blood vessel tortuosity calculation method and device |
| CN116090364A (en) * | 2022-12-30 | 2023-05-09 | 杭州脉流科技有限公司 | Method for obtaining coronary blood flow reserve fraction based on CTA image and readable storage medium |
-
2023
- 2023-06-15 CN CN202310712883.8A patent/CN116740164A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090322749A1 (en) * | 2007-01-23 | 2009-12-31 | Dtherapeutics, Llc | Systems and methods for extracting a curve-skeleton from a volumetric image of a vessel |
| US20100189333A1 (en) * | 2009-01-28 | 2010-07-29 | Thomas Beck | Method and branching determination device for determining a branching point within a hollow organ |
| CN103247073A (en) * | 2013-04-18 | 2013-08-14 | 北京师范大学 | Three-dimensional brain blood vessel model construction method based on tree structure |
| CN104361626A (en) * | 2014-09-29 | 2015-02-18 | 北京理工大学 | Subcutaneous vein three-dimensional reconstruction method based on hybrid matching strategy |
| CN104318557A (en) * | 2014-10-17 | 2015-01-28 | 重庆大学 | Vascular skeleton line reconstruction and precise vessel diameter calculation method |
| CN112884826A (en) * | 2021-03-26 | 2021-06-01 | 北京阅影科技有限公司 | Method and device for extracting center line of blood vessel |
| CN115731232A (en) * | 2022-12-07 | 2023-03-03 | 沈阳东软智能医疗科技研究院有限公司 | Blood vessel image processing method and device, readable storage medium and electronic equipment |
| CN116090364A (en) * | 2022-12-30 | 2023-05-09 | 杭州脉流科技有限公司 | Method for obtaining coronary blood flow reserve fraction based on CTA image and readable storage medium |
| CN115778554A (en) * | 2023-01-09 | 2023-03-14 | 深圳市精锋医疗科技股份有限公司 | Catheter robot, registration method thereof and readable storage medium |
| CN115953636A (en) * | 2023-03-10 | 2023-04-11 | 南京博视医疗科技有限公司 | Blood vessel grading method, blood vessel tortuosity calculation method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110648529B (en) | Vehicle driving track rendering method, device, equipment and storage medium | |
| CN107067409A (en) | A kind of blood vessel separation method and system | |
| CN102903115B (en) | A kind of extracting method of centerline of tubular object | |
| WO2022199403A1 (en) | Blood vessel centerline extraction method and apparatus | |
| CN109710708B (en) | Electronic map mapping method and device | |
| US20110069866A1 (en) | Image processing apparatus and method | |
| CN108335284A (en) | A kind of coronary artery vessel centerline matching process and system | |
| CN104851126B (en) | Threedimensional model dividing method and device based on generalized cylinder | |
| JP7250166B2 (en) | Image segmentation method and device, image segmentation model training method and device | |
| CN110892255B (en) | Image processing apparatus, method and storage medium for detecting defect from image | |
| JP2008250999A (en) | Object tracing method, object tracing device and object tracing program | |
| CN112560962B (en) | Gesture matching method and device for bone animation, electronic equipment and storage medium | |
| CN114332291A (en) | Oblique photography model building outer contour rule extraction method | |
| CN110507415A (en) | The path simulation method and device that microtubular is virtually intervened | |
| CN108994838A (en) | The relationship calculation method and system of robot location and planning path | |
| CN110992481B (en) | Building white mold consistency merging method based on nearest connecting line | |
| KR102189811B1 (en) | Method and Apparatus for Completing Knowledge Graph Based on Convolutional Learning Using Multi-Hop Neighborhoods | |
| CN116740164A (en) | Method, apparatus and storage medium for extracting a vessel centerline | |
| Tan et al. | Saliency detection by deep network with boundary refinement and global context | |
| CN114299057A (en) | Method for extracting blood vessel center line and storage medium | |
| CN112308857B (en) | Method and device for determining center line of blood vessel and readable storage medium | |
| CN116524548B (en) | Vascular structure information extraction method, device and storage medium | |
| WO2018068196A1 (en) | Method and device for tracking ridge line of blood vessel | |
| CN115953636B (en) | Blood vessel grading method, blood vessel tortuosity calculating method and device | |
| CN116958308A (en) | Correction method for intersection boundary line and related 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 |