CN109754397B - Blood vessel section center path extraction method and device, terminal equipment and storage medium - Google Patents
Blood vessel section center path extraction method and device, terminal equipment and storage medium Download PDFInfo
- Publication number
- CN109754397B CN109754397B CN201910004369.2A CN201910004369A CN109754397B CN 109754397 B CN109754397 B CN 109754397B CN 201910004369 A CN201910004369 A CN 201910004369A CN 109754397 B CN109754397 B CN 109754397B
- Authority
- CN
- China
- Prior art keywords
- point
- path
- blood vessel
- central
- image
- 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
Abstract
The embodiment of the invention provides a method and a device for extracting a central path of a blood vessel section, terminal equipment and a storage medium. The invention discloses a method for extracting a central path of a blood vessel section, which comprises the following steps: the method comprises the steps of obtaining a CTA image, and position information of a starting point and position information of an ending point of a blood vessel section input by a user; determining a mask image according to the CTA image, and determining a source distance field value of each voxel point in the mask image relative to a source point according to the mask image, wherein the source point is the starting point or the ending point; determining the shortest path between the starting point and the ending point according to the position information of the starting point, the position information of the ending point and the source distance field value of at least one voxel point relative to the source point; correcting the shortest path by using a tubular model and a CTA image to obtain corrected central points; and determining the central path of the blood vessel section according to the corrected central points. The embodiment of the invention can realize the rapid extraction of the central path of the target blood vessel section.
Description
Technical Field
The embodiment of the invention relates to a medical image processing technology, in particular to a method and a device for extracting a central path of a blood vessel section, a terminal device and a storage medium.
Background
Medical Imaging diagnosis refers to the study of interaction between a certain medium (such as X-rays, electromagnetic fields, ultrasonic waves, etc.) and a human body, and the structure and density of internal tissues and organs of the human body are expressed in an image mode for a diagnostician to judge according to information provided by the image, so as to diagnose the health condition of the human body. Mainly including fluoroscopy, radiograph, Computed Tomography (CT), Magnetic Resonance Imaging (MRI), ultrasound, digital subtraction, angiography, and the like.
CT angiography (CTA) is performed by injecting a contrast agent into a vein of a subject, scanning the blood vessel (artery and vein) during the time when the concentration of the contrast agent reaches the highest peak value through blood circulation of the human body, and reconstructing a three-dimensional image (CTA image) of the blood vessel by post-processing at a workstation. For CTA images, blood vessel extraction and visualization are effective means for data analysis and processing, and play a very important role in the diagnosis and treatment of vascular diseases. For example, a doctor is often interested in a blood vessel segment where a blood vessel stenosis is located, and needs to extract a central path of the blood vessel segment, so as to perform blood vessel analysis, such as measuring the stenosis degree thereof. For the extraction method of the center path of a specific vessel segment, usually the whole vessel tree is extracted, and then from the extracted vessel tree path, the vessel segment path of interest is found by using the graph structure.
However, the above-mentioned method for extracting the blood vessel segment path extracts many central paths other than the interested part, and the extraction process takes a long time.
Disclosure of Invention
The embodiment of the invention provides a method and a device for extracting a central path of a blood vessel section, terminal equipment and a storage medium, which are used for realizing the rapid extraction of the central path of a target blood vessel section.
In a first aspect, an embodiment of the present invention provides a method for extracting a central path of a blood vessel segment, including: the method comprises the steps of obtaining a CTA image, and position information of a starting point and position information of an ending point of a blood vessel section input by a user; determining a mask image of the CTA image from the CTA image; determining a source distance field value of each voxel point in the mask image relative to a source point according to the mask image, wherein the source point is the starting point or the ending point; determining the shortest path between the starting point and the ending point according to the position information of the starting point, the position information of the ending point and the source distance field value of at least one voxel point relative to the source point; correcting the shortest path by using a tubular model and the CTA image to obtain corrected central points; and determining the central path of the blood vessel section according to the corrected central points.
With reference to the first aspect, in a possible implementation manner of the first aspect, the correcting the shortest path by using the tubular model and the CTA image to obtain corrected central points includes: respectively establishing tubular models by taking at least one path point of the shortest path as a central point along the direction of the shortest path, matching each tubular model with the CTA image, and adjusting the central point position, the radius and the direction of each tubular model; and taking the position of the center point of each adjusted tubular model as the corrected center point.
With reference to the first aspect or one possible implementation manner of the first aspect, in another possible implementation manner of the first aspect, the establishing a tubular model with at least one path point of the shortest path as a central point along the direction of the shortest path, matching each tubular model with the CTA image, and adjusting the central point position, the radius, and the direction of each tubular model includes: starting from the starting point, taking the starting point as a central point, building a tubular model, matching the tubular model with the CTA image, adjusting the central point position, the radius and the direction of the tubular model, selecting a next path point along a first blood vessel tracking direction, updating the central point by the next path point, executing the steps of building the tubular model, matching the tubular model with the CTA image, and adjusting the central point position, the radius and the direction of the tubular model until the selected next path point exceeds the end point; or, starting from the termination point, establishing a tubular model by taking the termination point as a central point, matching the tubular model with the CTA image, adjusting the central point position, the radius and the direction of the tubular model, selecting a next path point along a second blood vessel tracking direction, updating the central point by the next path point, executing the steps of establishing the tubular model, matching the tubular model with the CTA image, and adjusting the central point position, the direction and the radius of the tubular model until the selected next path point exceeds the starting point; or, starting from the starting point and the ending point respectively, taking the starting point and the ending point as central points respectively, building two tubular models, matching the two tubular models with the CTA image, adjusting the central point position, the radius and the direction of the two tubular models, selecting the next path point along the first blood vessel tracking direction and the second blood vessel tracking method respectively, updating the central point with the two next path points respectively, executing the steps of building the two tubular models, matching the two tubular models with the CTA image, and adjusting the central point position, the direction and the radius of the two tubular models until the position areas of the two next path points selected along the first blood vessel tracking direction and the second blood vessel tracking direction are overlapped.
With reference to the first aspect or any one of the possible implementations of the first aspect, in another possible implementation of the first aspect, the radius of the tubular model established with the next waypoint as the central point is the radius of the tubular model after the previous adjustment.
With reference to the first aspect or any one of the possible implementations of the first aspect, in another possible implementation of the first aspect, the method further includes: generating first index information, second index information and third index information according to information of three dimensions in the mask image, wherein the first index information comprises the number of voxel points in each layer of the mask image in the first dimension direction, the second index information comprises the number of voxel points in each second dimension direction in each layer of the mask image, and the third index information comprises the position of each voxel point in the mask image in the third dimension direction; and associating the first index information, the second index information and the third index information with a one-dimensional array, wherein the one-dimensional array stores the source distance field value of each pixel point of the mask image.
With reference to the first aspect or any one of the possible implementations of the first aspect, in another possible implementation of the first aspect, the determining a shortest path between the starting point and the ending point according to the position information of the starting point, the position information of the ending point, and a source distance field value of at least one voxel point includes: acquiring a source distance field value of each voxel point in the blood vessel section from the one-dimensional array according to the position information of the starting point, the position information of the ending point, the first index information, the second index information and the third index information; inputting the position information of the starting point, the position information of the ending point and the source distance field value of each voxel point in the blood vessel section into a shortest path algorithm, and outputting a shortest path between the starting point and the ending point.
With reference to the first aspect or any one of the possible implementations of the first aspect, in another possible implementation of the first aspect, the determining a mask image of the CTA image from the CTA image includes: and performing threshold segmentation on the CTA image to obtain the mask image.
In a second aspect, an embodiment of the present invention provides an apparatus for extracting a central path of a blood vessel segment, including: the acquisition module is used for acquiring a CTA image, and position information of a starting point and position information of an end point of a blood vessel section input by a user; a mask image module for determining a mask image of the CTA image from the CTA image, a source distance field determining module for determining a source distance field value of each voxel point in the mask image relative to a source point from the mask image, the source point being the starting point or the ending point; the shortest path determining module is used for determining the shortest path between the starting point and the ending point according to the position information of the starting point, the position information of the ending point and a source distance field value of at least one voxel point relative to a source point; the correction module is used for correcting the shortest path by using a tubular model and the CTA image to obtain corrected central points; and the central path determining module is used for determining the central path of the blood vessel section according to the corrected central points.
In a third aspect, an embodiment of the present invention provides a terminal device, where the terminal device includes: a processor, a memory, a transceiver; the transceiver is coupled to the processor, and the processor controls transceiving action of the transceiver; wherein the memory is to store computer-executable program code, the program code comprising instructions; the instructions, when executed by the processor, cause the terminal device to perform the method of any of the first aspects.
In a fourth aspect, an embodiment of the present invention provides a computer storage medium having a computer program or instructions stored thereon, wherein the computer program or instructions, when executed by a processor or a computer, implement the method according to any one of the first aspect.
The blood vessel segment center path extraction method, the blood vessel segment center path extraction device, the terminal device and the storage medium of the embodiment of the invention determine a mask image of a blood vessel segment according to a CTA image by obtaining the CTA image, position information of a starting point and position information of an end point of the blood vessel segment input by a user, determine a source distance field value of each voxel point in the mask image relative to a source point according to the mask image, determine a shortest path between the starting point and the end point according to the position information of the starting point, the position information of the end point and the source distance field value of at least one voxel point relative to the source point, correct the shortest path by using a tubular model and the CTA image, obtain corrected central points, and determine the center path of the blood vessel segment according to the corrected central points. The shortest path of the target blood vessel section is determined by combining the source distance field according to the starting point and the end point of the blood vessel section input by the user, and the shortest path is corrected by using the tubular model to extract the central path, so that the central path of the target blood vessel section can be quickly extracted, the target blood vessel section is analyzed, for example, the stenosis degree of the target blood vessel section is measured, and the accuracy and the scientificity of medical diagnosis are improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a schematic diagram of an application scenario according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of another application scenario of the present invention;
FIG. 3 is a flowchart of a first embodiment of a method for extracting a central path of a blood vessel segment according to the present invention;
FIG. 4 is a flowchart of a second embodiment of the method for extracting a central path of a blood vessel segment according to the present invention;
FIG. 5 is a flowchart of a first implementation of step 204 according to an embodiment of the invention;
FIG. 6 is a flowchart of a second mode of step 204 according to an embodiment of the present invention;
FIG. 7 is a flowchart of a third embodiment of step 204;
FIG. 8 is a flow chart of a manner of storing source range field values in accordance with an embodiment of the present invention;
FIG. 9 is a schematic view of a first embodiment of the apparatus for extracting the central path of a vessel segment according to the present invention;
fig. 10 is a schematic structural diagram of a first embodiment of a terminal device unit according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The terms "first," "second," and the like in the description and in the claims, and in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are, for example, capable of operation in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Reference herein to a "CTA image" specifically refers to a three-dimensional tomographic image acquired by Computed Tomography (CT) angiography. Which may be a three-dimensional tomographic image that is acquired by scanning with a CT imaging system and post-processed by a workstation (e.g., a computer). The CTA images may be stored and transmitted in Digital Imaging and Communications in Medicine (DICOM), an international standard for medical images and related information that defines a medical image format for data exchange that meets clinical requirements in quality.
The voxel points referred to herein refer to true (true) voxel points in the mask image, and are not discussed herein with respect to false (false) voxel points in the mask image.
Fig. 1 is a schematic diagram of an application scenario according to an embodiment of the present invention, as shown in fig. 1, the application scenario includes a terminal device and a CTA image acquisition device, the CTA image acquisition device may include the CT imaging system and the workstation as described above, the workstation sends a CTA image to the terminal device, and the terminal device implements the blood vessel segment center path extraction method according to the embodiment of the present invention to realize fast extraction of a center path of a target blood vessel segment, so as to analyze the target blood vessel segment, for example, measure stenosis degree thereof, and improve accuracy and scientificity of medical diagnosis.
Fig. 2 is a schematic diagram of another application scenario of the embodiment of the present invention, as shown in fig. 2, the application scenario includes a terminal device and a storage system, the storage system is configured to store a CTA image acquired by a CTA image acquisition device, and the terminal device implements the blood vessel segment center path extraction method of the embodiment of the present invention to realize fast extraction of a center path of a target blood vessel segment, so as to analyze the target blood vessel segment, for example, measure stenosis degree thereof, and improve accuracy and scientificity of medical diagnosis.
The Terminal device according to the embodiment of the present invention may also be referred to as a Terminal (Terminal), a User Equipment (UE), a Mobile Station (MS), a Mobile Terminal (MT), or the like. The terminal device may be a computer (PC), a mobile phone (mobile phone), a tablet computer (Pad), a computer with wireless transceiving function, and so on.
Fig. 3 is a flowchart of a first blood vessel section center path extraction method according to an embodiment of the present invention, where an execution main body of the present embodiment may be an extraction device of a blood vessel section center path, and the extraction device of the blood vessel section center path may be the terminal device or an internal chip of the terminal device, as shown in fig. 3, the method of the present embodiment may include:
step 101, CTA image, and the position information of the starting point and the position information of the ending point of the blood vessel segment input by the user are obtained.
The position information of the start point and the position information of the end point of the blood vessel segment input by the user may be generated according to the start point and the end point clicked by the user in the two-dimensional view displayed on the terminal device, and specifically, the start point and the end point in the two-dimensional view may be converted into the start point and the end point in the three-dimensional data volume, and the position information of the start point and the position information of the end point input by the user may be obtained.
Step 102, a mask image of the CTA image is determined from the CTA image.
The mask image is a binary image composed of 0 and 1, the 1-value region in the binary image is a target region to be processed, for example, a blood vessel in the present embodiment, and the 0-value region is a region not required to participate in processing, for example, a bone, a muscle, and the like.
It should be noted that the CTA image includes bones, muscles, blood vessels, and the like, and a mask image of the CTA image is obtained by processing the CTA image, and the mask image of the CTA image is used to reflect a region of interest (e.g., blood vessels). To ensure that the start and end points of the user input can find the correct center path at any position on the vessel, the mask image is the same size as the CTA image.
Step 103, according to the mask image, determining a source distance field value of each voxel point in the mask image relative to a source point, wherein the source point is a starting point or an end point.
In the embodiments of the present invention, the Distance field is referred to as a source Distance (DFS) field, and the source Distance field value may be calculated by using a Chamfer Distance (Chamfer Distance), a euclidean Distance, a block Distance, or the like, where a connection weight value of each voxel may be integer to accelerate the calculation of the source Distance field.
And 104, determining the shortest path between the starting point and the ending point according to the position information of the starting point, the position information of the ending point and the source distance field value of at least one voxel point relative to the source point.
The source distance field value of the at least one voxel point relative to the source point may be a source distance field value of a plurality of voxel points between the start point and the end point relative to the source point, or may be a source distance field value of all voxel points relative to the source point.
The position information of the starting point, the position information of the ending point, and the source distance field value of at least one voxel point may be input into a shortest path algorithm, and a shortest path between the starting point and the ending point is output, where the shortest path algorithm may be a Dijkstra algorithm, a Bellman-Ford algorithm, a Floyd algorithm, an SPFA algorithm, or the like.
The shortest path may include a plurality of path points, which may be denoted as RA,P1,.....,PN,PB，PADenotes a starting point A, PBIndicating the termination point B.
And 105, correcting the shortest path by using a tubular model and the CTA image to obtain corrected central points.
The shortest path obtained in step 104 is further corrected by using a tubular model tracking method to avoid that the center path of the extracted blood vessel segment is close to the blood vessel wall, which is not enough for the blood vessel analysis.
And 106, determining the central path of the blood vessel section according to the corrected central points.
And combining the corrected central points in sequence to obtain a central path of the blood vessel section between the starting point and the end point, namely the central path of the target blood vessel section interested by the user.
It should be noted that the center path may also be interpolated by using a B-spline function to obtain a center path at a voxel level.
In this embodiment, a CTA image, position information of a start point and position information of an end point of a blood vessel segment input by a user are obtained, a mask image of the CTA image is determined according to the CTA image, a source distance field value of each voxel point in the mask image relative to a source point is determined according to the mask image, a shortest path between the start point and the end point is determined according to the position information of the start point, the position information of the end point and the source distance field value of at least one voxel point relative to the source point, the shortest path is corrected by using a tubular model and the CTA image, each corrected central point is obtained, and a central path of the blood vessel segment is determined according to each corrected central point. The shortest path of the target blood vessel section is determined by combining the source distance field according to the starting point and the end point of the blood vessel section input by the user, and the shortest path is corrected by using the tubular model to extract the central path, so that the central path of the target blood vessel section can be quickly extracted, the target blood vessel section is analyzed, for example, the stenosis degree of the target blood vessel section is measured, and the accuracy and the scientificity of medical diagnosis are improved.
The following describes in detail the technical solution of the embodiment of the method shown in fig. 3, using several specific embodiments.
Fig. 4 is a flowchart of a second embodiment of the method for extracting a central path of a blood vessel segment according to the present invention, and as shown in fig. 4, the method of this embodiment may include:
step 201, CTA image, the position information of the starting point and the position information of the ending point of the blood vessel section input by the user are obtained.
Step 202 determines a mask image for the CTA image from the CTA image.
Step 203, determining a source distance field value of each voxel point in the mask image relative to a source point according to the mask image, wherein the source point is the starting point or the ending point.
And 204, determining the shortest path between the starting point and the ending point according to the position information of the starting point, the position information of the ending point and the source distance field value of at least one voxel point relative to the source point.
For a detailed explanation of step 201 to step 204, refer to step 101 to step 104 in the embodiment shown in fig. 3, which is not described herein again.
Step 205, respectively establishing tubular models by taking at least one path point of the shortest path as a central point along the shortest path direction, matching each tubular model with the CTA image, and adjusting the central point position, the radius and the direction of each tubular model.
Wherein, the direction of the shortest path can be determined according to the path point on the shortest path. Matching the tubular model established according to the path points with the actual image (the CTA image), specifically adjusting the position, the radius and the direction of the central point of the tubular model by using an LM (Levenberg-Marquard) algorithm, calculating the error between the adjusted tubular model and the actual image (the CTA image), and taking the parameter (the position, the radius and the direction of the central point) with the minimum error as the parameter of the adjusted tubular model within a certain iteration number, namely the position, the radius and the direction of the central point of the adjusted tubular model.
The tubular model may be established with one or more path points of the shortest path as a center, wherein the path points used for establishing the tubular model may be selected in a manner that, after the tubular model is adjusted once, the path points of the shortest path are selected to establish the tubular model by combining the adjusted center point position and the path points on the shortest path.
And step 206, taking the position of the center point of each adjusted tubular model as each corrected center point.
And taking the positions of the center points of the adjusted tubular models as the corrected center points, and combining the center points in sequence to obtain the center path of the blood vessel section between the starting point and the ending point, namely the center path of the target blood vessel section interested by the user.
And step 207, determining the central path of the blood vessel section according to the corrected central points.
For an explanation of step 207, refer to step 106 in the embodiment shown in fig. 3, which is not described herein again.
In this embodiment, a CTA image, position information of a start point and position information of an end point of a blood vessel segment input by a user are obtained, a mask image of the CTA image is determined according to the CTA image, a source distance field value of each voxel point in the mask image relative to a source point is determined according to the mask image, a shortest path between the start point and the end point is determined according to the position information of the start point, the position information of the end point and the source distance field value of at least one voxel point relative to the source point, a tubular model is established along a blood vessel tracking direction by respectively using at least one path point of the shortest path as a center point, each tubular model is matched with the CTA image, the center point position, the radius and the direction of each tubular model are adjusted, and the center point position of each adjusted tubular model is used as each corrected center point, the central path of the target blood vessel section is rapidly extracted, so that the target blood vessel section is analyzed, for example, the stenosis degree is measured, and the accuracy and the scientificity of medical diagnosis are improved.
Optionally, the tubular model established according to the path point is matched with the actual image (the CTA image), and the tubular model is adjusted to obtain the radius, the center point position and the direction of the current blood vessel segment, and obtain the segmentation result of the current blood vessel segment, where the current blood vessel segment is one of the blood vessel segments between the start point and the end point, for example, PAAnd PnThe vessel segment in between. Due to the adoption of the tracking adjustment mode of the tubular model, the central path can be well extracted at the blood vessel adhesion part, and the treatment effect is better at some light blood vessels.
As an explanation of the above step 205, the above step 205 can be implemented in the following three different ways.
Fig. 5 is a flowchart of a first mode of step 205 in the embodiment of the present invention, and as shown in fig. 5, in this embodiment, on the basis of the foregoing embodiment, the first mode of step 205 is explained, and the method in this embodiment may include:
step 301, starting from a starting point, the starting point is taken as a central point.
In particular, it can be taken from a starting point PAVessel tracking is started.
Wherein the initial point (P)A) In the direction of blood vessel VA＝Pi-PAAnd i is any one of K points after the point A, and can be determined according to the adjustment step length.
The starting point radius may be calculated as: calculating an initial point (P) on the XY plane, YZ plane, and ZX plane of the data volumeA) And (4) taking the radius corresponding to the maximum roundness as the initial point radius according to the radius and roundness-like information of the located blood vessel.
Step 302, building a tubular model with the central point.
And in the first iteration process, establishing a tubular model by using the starting point, the direction and the radius. And step 303 is performed.
N (N)>1) In the secondary iteration process, the central point is updated by the following path point, the Radius can be the Radius of the blood vessel section matched with the previous path point, and the direction is V-Pm+i-PmThus, a tubular model is established. And step 303 is performed to match the next vessel segment.
Step 303, matching the tubular model with the CTA image, and adjusting the position of the central point of the tubular model.
Step 304, selecting a next waypoint along the first vessel tracking direction.
The selection mode of the next path point is as follows: assuming that the iteration step is step factor Radius, where Radius is the Radius of the previous iteration, and the central point before the previous unadjusted is pKGo through PK+1,Pk+2,.....,PN,PBSatisfy | | | Pm-PKP with | | approximately equal to stepmAs the next path point, i.e. the center point of the next vessel segment。
Step 305, determining whether the next waypoint exceeds the termination point, if not, performing step 306, and if so, performing step 206 of the embodiment shown in fig. 4.
And if the next path point exceeds the termination point, taking the position of the center point of each adjusted tubular model as each corrected center point.
Step 306, updating the center point with the next path point, and returning to execute step 302.
In this embodiment, the next path point is selected according to the iteration step length, and the tubular model is established with the next path point as the center, and the radius of the tubular model is adjusted before, so that the convergence speed of the algorithm can be increased.
Fig. 6 is a flowchart of a second mode of step 205 in the embodiment of the present invention, and as shown in fig. 6, in the present embodiment, on the basis of the foregoing embodiment, the second mode of step 205 is explained, and the method in the present embodiment may include:
step 401, starting from the ending point, taking the ending point as a central point.
This embodiment differs from the embodiment shown in fig. 5 in that the vessel tracking and adjustment is performed from the termination point to the starting point.
Step 402, building a tubular model with the central point.
And step 403, matching the tubular model with the CTA image, and adjusting the position of the central point of the tubular model.
Step 404, selecting a next waypoint along the second vessel tracking direction.
Step 405, determine whether the next waypoint exceeds the starting point, if not, go to step 406, and if so, go to step 206 of the embodiment shown in fig. 4.
Step 406, updating the center point with the next path point, and returning to execute step 402.
In this embodiment, the next path point is selected according to the iteration step length, and the tubular model is established with the next path point as the center, and the radius of the tubular model is adjusted before, so that the convergence speed of the algorithm can be increased.
Fig. 7 is a flowchart of a third mode of step 205 in the embodiment of the present invention, and as shown in fig. 7, in this embodiment, on the basis of the foregoing embodiment, the third mode of step 205 is explained, and the method in this embodiment may include:
step 501, starting from a starting point and an end point respectively, the starting point and the end point are taken as two central points respectively.
The present embodiment differs from the embodiments shown in fig. 5 and 6 in that the vessel tracking and adjustment are performed starting from the termination point and the starting point in parallel.
Step 502, two tubular models are established with two central points respectively.
And 503, respectively matching the two tubular models with the CTA image, and adjusting the positions of the central points of the two tubular models.
Step 504, selecting the next waypoint along the first vessel tracking direction and the second vessel tracking method, respectively.
Step 505, determining whether the position areas of the two next waypoints selected along the first blood vessel tracking direction and the second blood vessel tracking direction overlap, if not, performing step 506, and if so, performing step 206 of the embodiment shown in fig. 4.
When the tracking areas of the starting point and the ending point are overlapped, the tracking is finished, and the adjusted central points generated in the tracking processes of the starting point and the ending point are combined in sequence, so that the path between the starting point and the ending point can be obtained.
Step 506, update two center points with two next path points, and return to step 502.
In this embodiment, the next path point is selected from the two directions according to the iteration step length, and the tubular model is established with the next path point as the center, and the radius of the tubular model is adjusted before, so that the convergence speed of the algorithm can be further improved.
Fig. 8 is a flowchart of a storage manner of a source distance field value according to an embodiment of the present invention, and as shown in fig. 8, on the basis of the foregoing embodiment, the method of this embodiment may further include:
step 601, generating first index information, second index information and third index information according to information of three dimensions in the mask image.
The first index information comprises the number of voxel points in each layer of mask image in the first dimension direction, the second index information comprises the number of voxel points in each second dimension direction in each layer of mask image, and the third index information comprises the position of each voxel point in the mask image in the third dimension direction.
Taking three dimensions of x, y and z as an example, traversing the mask image, counting the number of 1(True) in each layer of mask image in the z direction to obtain first index information, counting the number of 1(True) in each line of y direction mask image in each XY layer image to obtain second index information, and counting the position information of all 1 voxel points in the mask image in the x direction to obtain third index information. Assuming that the mask image is a 512 × 300 image in which 10000 dots are True, the size of the first index information is 300 × 1, the size of the second index information is 512 × 300, the size of the third index information is 10000 × 1, and each line in the third index information is x-direction position information of one voxel.
Step 602, associating the first index information, the second index information and the third mask information with a one-dimensional array, wherein the one-dimensional array stores source distance field values of each individual pixel point of the mask image.
The first index information, the second index information, and the third index information are associated with the one-dimensional array, and the specific association manner may be index association, that is, an index is determined according to the first index information, the second index information, and the third index information, and the index corresponds to each element in the one-dimensional array, which is 10000 × 1 as explained in the above example. The one-dimensional array stores the source distance field values of each pixel point of the mask image.
For three-dimensional images, if the mask image is taken as a whole, much space is occupied in opening up memory. The storage mode of the embodiment of the invention can save the memory space of data storage.
On the basis of the storage manner, the implementation manner of the above step 204 in the embodiment of the present invention may be: acquiring a source distance field value of each voxel point in the blood vessel section from the one-dimensional array according to the position information of the starting point, the position information of the ending point, the first index information, the second index information and the third index information; inputting the position information of the starting point, the position information of the ending point and the source distance field value of each voxel point in the blood vessel section into a shortest path algorithm, and outputting a shortest path between the starting point and the ending point.
Based on the first index information, the second index information and the third index information, the position of the true element in the three-dimensional data of the mask image in the one-dimensional data can be quickly found. For example, given a point (x, y, z), the value of z, y can be quickly located to the lowest (Lowx) position and the highest (highx) position in the third index by the first index information and the second index information, and then located to the index position in the one-dimensional array by the bisection method and the value of x, thereby obtaining the source distance field value of the given point.
In this embodiment, through the first index information, the second index information, the third index information, and the one-dimensional array, the memory space for data storage can be saved, and the fast search of the source distance field value of the corresponding position point can be realized.
Fig. 9 is a schematic diagram of a first embodiment of an apparatus for extracting a central path of a blood vessel segment according to the present invention, where the apparatus is part or all of a terminal device, and the terminal device may be a smart phone, a tablet computer, a PC, or the like, and as shown in fig. 9, the apparatus includes:
the obtaining module 91 is configured to obtain the CTA image, and the position information of the start point and the position information of the end point of the blood vessel segment input by the user.
A mask image module 92 for determining a mask image for the CTA image from the CTA image
A source distance field determining module 93, configured to determine, according to the mask image, a source distance field value of each voxel point in the mask image with respect to a source point, where the source point is the start point or the end point;
a shortest path determining module 94, configured to determine a shortest path between the starting point and the ending point according to the position information of the starting point, the position information of the ending point, and a source distance field value of at least one voxel point relative to a source point;
a correction module 95, configured to correct the shortest path by using a tubular model and the CTA image, and obtain corrected central points;
and a central path determining module 96, configured to determine a central path of the blood vessel segment according to the corrected central points.
Optionally, the correction module 95 is configured to: respectively establishing tubular models by taking at least one path point of the shortest path as a central point along the direction of the shortest path, matching each tubular model with the CTA image, and adjusting the central point position, the radius and the direction of each tubular model; and taking the position of the center point of each adjusted tubular model as each corrected center point.
Optionally, the correction module 95 is configured to: starting from the starting point, taking the starting point as a central point, building a tubular model, matching the tubular model with the CTA image, adjusting the central point position, the radius and the direction of the tubular model, selecting a next path point along a first blood vessel tracking direction, updating the central point by the next path point, executing the steps of building the tubular model, matching the tubular model with the CTA image, and adjusting the central point position, the radius and the direction of the tubular model until the selected next path point exceeds the end point; or, starting from the termination point, establishing a tubular model by taking the termination point as a central point, matching the tubular model with the CTA image, adjusting the central point position, the radius and the direction of the tubular model, selecting a next path point along a second blood vessel tracking direction, updating the central point by the next path point, executing the steps of establishing the tubular model, matching the tubular model with the CTA image, and adjusting the central point position, the radius and the direction of the tubular model until the selected next path point exceeds the starting point; or, starting from the starting point and the ending point respectively, taking the starting point and the ending point as central points respectively, building two tubular models, matching the two tubular models with the CTA image, adjusting the central point position, the radius and the direction of the two tubular models, selecting the next path point along the first blood vessel tracking direction and the second blood vessel tracking method respectively, updating the central point with the two next path points respectively, executing the steps of building the two tubular models, matching the two tubular models with the CTA image, and adjusting the central point position, the radius and the direction of the two tubular models until the position areas of the two next path points selected along the first blood vessel tracking direction and the second blood vessel tracking direction are overlapped.
Optionally, the radius of the tubular model established with the next path point as the central point is the radius of the tubular model after the previous adjustment.
The device further comprises: a storage module 97, where the storage module 97 is configured to generate first index information, second index information, and third index information according to information of three dimensions in the mask image, where the first index information includes the number of voxel points in each layer of the mask image in a first dimension direction, the second index information includes the number of voxel points in each layer of the mask image in each second dimension direction, and the third index information includes the position of each voxel point in the mask image in the third dimension direction; and associating the first index information, the second index information and the third index information with a one-dimensional array, wherein the one-dimensional array stores the source distance field value of each pixel point of the mask image.
Optionally, the shortest path determining module 94 is configured to obtain a source distance field value of each voxel point in the blood vessel segment from the one-dimensional array according to the position information of the starting point, the position information of the ending point, the first index information, the second index information, and the third index information; inputting the position information of the starting point, the position information of the ending point and the source distance field value of each voxel point in the blood vessel section into a shortest path algorithm, and outputting a shortest path between the starting point and the ending point.
Optionally, the mask image module 92 is configured to perform threshold segmentation on the CTA image to obtain the mask image.
The blood vessel section center path extraction device provided by the embodiment of the present invention can be used for executing the blood vessel section center path extraction method, and the content and effect thereof can refer to the method section, which is not described again in the embodiment of the present invention.
Fig. 10 is a schematic structural diagram of a first embodiment of a terminal device unit according to the present invention, and as shown in fig. 10, a server according to the present embodiment includes: a processor 211, a memory 212, a transceiver 213, and a bus 214. Wherein the processor 211, the memory 212 and the transceiver 213 are connected to each other through a bus 214. The bus 214 may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus 214 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in FIG. 10, but this is not intended to represent only one bus or type of bus.
In terms of hardware implementation, the functional modules shown in fig. 9 above may be embedded in the processor 211 of the terminal device or may be independent of the processor.
The transceiver 213 may include a mixer or the like as necessary for radio frequency communication. The processor 211 may include at least one of a Central Processing Unit (CPU), a Digital Signal Processor (DSP), a Microcontroller (MCU), an Application Specific Integrated Circuit (ASIC), or a Field Programmable Gate Array (FPGA).
The memory 212 is used for storing program instructions, and the processor 211 is used for calling the program instructions in the memory 212 to execute the above scheme.
The program instructions may be embodied in the form of software functional units and may be sold or used as a stand-alone product, and the memory 212 may be any form of computer readable storage medium. Based on such understanding, all or part of the technical solutions of the present application may be embodied in the form of a software product, which includes several instructions to enable a computer device, specifically, the processor 211, to execute all or part of the steps of the apparatus for executing business operations in various embodiments of the present application. And the aforementioned computer-readable storage media comprise: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The terminal device described above in this embodiment may be configured to execute the technical solutions in the above method embodiments, and the implementation principles and technical effects are similar, where the functions of each device may refer to corresponding descriptions in the method embodiments, and are not described herein again.
An embodiment of the present invention further provides a computer storage medium, including: computer instructions for implementing a method of vessel segment center path extraction as described. The content and effect of the method can refer to the method part, and the embodiment of the invention is not repeated.
An embodiment of the present invention provides a computer program product, including: computer instructions for implementing a method of vessel segment center path extraction as described. The content and effect of the method can refer to the method part, and the embodiment of the invention is not repeated.
Those of ordinary skill in the art will understand that: all or a portion of the steps of implementing the above-described method embodiments may be performed by hardware associated with program instructions. The program may be stored in a computer-readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (9)
1. A method for extracting a central path of a blood vessel section is characterized by comprising the following steps:
the method comprises the steps of obtaining a CTA image, and position information of a starting point and position information of an ending point of a blood vessel section input by a user;
determining a mask image of the CTA image from the CTA image;
determining a source distance field value of each voxel point in the mask image relative to a source point according to the mask image, wherein the source point is the starting point or the ending point;
determining the shortest path between the starting point and the ending point according to the position information of the starting point, the position information of the ending point and the source distance field value of at least one voxel point relative to the source point;
correcting the shortest path by using a tubular model and the CTA image to obtain corrected central points;
determining the central path of the blood vessel section according to the corrected central points;
the method further comprises the following steps:
generating first index information, second index information and third index information according to information of three dimensions in the mask image, wherein the first index information comprises the number of voxel points in each layer of the mask image in the first dimension direction, the second index information comprises the number of voxel points in each second dimension direction in each layer of the mask image, and the third index information comprises the position of each voxel point in the mask image in the third dimension direction;
and associating the first index information, the second index information and the third index information with a one-dimensional array, wherein the one-dimensional array stores the source distance field value of each pixel point of the mask image.
2. The method of claim 1, wherein the correcting the shortest path using the tubular model and the CTA image to obtain corrected center points comprises:
respectively establishing tubular models by taking at least one path point of the shortest path as a central point along the direction of the shortest path, matching each tubular model with the CTA image, and adjusting the central point position, the radius and the direction of each tubular model;
and taking the position of the center point of each adjusted tubular model as each corrected center point.
3. The method of claim 2, wherein the establishing a tubular model with at least one path point of the shortest path as a center point along the shortest path direction, respectively, matching each tubular model with the CTA image, and adjusting the center point position, the radius and the direction of each tubular model comprises:
starting from the starting point, taking the starting point as a central point, building a tubular model, matching the tubular model with the CTA image, adjusting the central point position, the radius and the direction of the tubular model, selecting a next path point along a first blood vessel tracking direction, updating the central point by the next path point, executing the steps of building the tubular model, matching the tubular model with the CTA image, and adjusting the central point position, the radius and the direction of the tubular model until the selected next path point exceeds the end point; alternatively, the first and second electrodes may be,
starting from the termination point, establishing a tubular model by taking the termination point as a central point, matching the tubular model with the CTA image, adjusting the central point position, the radius and the direction of the tubular model, selecting a next path point along a second blood vessel tracking direction, updating the central point by the next path point, executing the steps of establishing the tubular model, matching the tubular model with the CTA image, and adjusting the central point position, the radius and the direction of the tubular model until the selected next path point exceeds the starting point; alternatively, the first and second electrodes may be,
respectively starting from the starting point and the ending point, respectively taking the starting point and the ending point as central points, establishing two tubular models, matching the two tubular models with the CTA image, adjusting the central point position, the radius and the direction of the two tubular models, respectively selecting the next path point along the first blood vessel tracking direction and the second blood vessel tracking direction, respectively updating the central points with the two next path points, executing the steps of establishing the two tubular models, matching the two tubular models with the CTA image, and adjusting the central point position, the radius and the direction of the two tubular models until the position areas of the two next path points selected along the first blood vessel tracking direction and the second blood vessel tracking direction are overlapped.
4. The method of claim 3, wherein the radius of the tubular model created with the following one of the waypoints as the center point is the radius of the tubular model after the previous adjustment.
5. The method of claim 1, wherein determining the shortest path between the start point and the end point according to the position information of the start point, the position information of the end point, and a source distance field value of at least one voxel point comprises:
acquiring a source distance field value of each voxel point in the blood vessel section from the one-dimensional array according to the position information of the starting point, the position information of the ending point, the first index information, the second index information and the third index information;
inputting the position information of the starting point, the position information of the ending point and the source distance field value of each voxel point in the blood vessel section into a shortest path algorithm, and outputting a shortest path between the starting point and the ending point.
6. The method of any one of claims 1 to 3, wherein said determining a mask image for the CTA image from the CTA image comprises:
and performing threshold segmentation on the CTA image to obtain the mask image.
7. An apparatus for extracting a central path of a vessel segment, comprising:
the acquisition module is used for acquiring a CTA image, and position information of a starting point and position information of an end point of a blood vessel section input by a user;
a mask image module to determine a mask image of the CTA image from the CTA image;
a source distance field determining module, configured to determine, according to the mask image, a source distance field value of each voxel point in the mask image with respect to a source point, where the source point is the start point or the end point;
the shortest path determining module is used for determining the shortest path between the starting point and the ending point according to the position information of the starting point, the position information of the ending point and a source distance field value of at least one voxel point relative to a source point;
the correction module is used for correcting the shortest path by using a tubular model and the CTA image to obtain corrected central points;
a central path determining module, configured to determine a central path of the blood vessel segment according to the corrected central points;
the storage module is used for generating first index information, second index information and third index information according to information of three dimensions in the mask image, wherein the first index information comprises the number of voxel points in each layer of the mask image in a first dimension direction, the second index information comprises the number of voxel points in each layer of the mask image in each second dimension direction, and the third index information comprises the position of each voxel point in the mask image in the third dimension direction; and associating the first index information, the second index information and the third index information with a one-dimensional array, wherein the one-dimensional array stores the source distance field value of each pixel point of the mask image.
8. A terminal device, characterized in that the terminal device comprises: a processor, a memory, a transceiver; the transceiver is coupled to the processor, and the processor controls transceiving action of the transceiver;
wherein the memory is to store computer-executable program code, the program code comprising instructions; the instructions, when executed by the processor, cause the terminal device to perform the method of any of claims 1 to 6.
9. A computer storage medium having stored thereon a computer program or instructions for implementing the method of any one of claims 1 to 6 when executed by a processor or computer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910004369.2A CN109754397B (en) | 2019-01-03 | 2019-01-03 | Blood vessel section center path extraction method and device, terminal equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910004369.2A CN109754397B (en) | 2019-01-03 | 2019-01-03 | Blood vessel section center path extraction method and device, terminal equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109754397A CN109754397A (en) | 2019-05-14 |
| CN109754397B true CN109754397B (en) | 2021-02-09 |
Family
ID=66405190
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910004369.2A Active CN109754397B (en) | 2019-01-03 | 2019-01-03 | Blood vessel section center path extraction method and device, terminal equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109754397B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111640124B (en) * | 2020-05-25 | 2023-06-02 | 浙江同花顺智能科技有限公司 | Blood vessel extraction method, device, equipment and storage medium |
| CN113888690B (en) * | 2021-10-19 | 2022-08-12 | 柏意慧心(杭州)网络科技有限公司 | Method, apparatus and medium for determining a target segment in a blood vessel |
| CN114708259B (en) * | 2022-05-24 | 2022-08-16 | 深圳市铱硙医疗科技有限公司 | CTA (computed tomography angiography) -based head and neck vascular stenosis detection method, device, equipment and medium |
| CN115778554B (en) * | 2023-01-09 | 2023-05-26 | 深圳市精锋医疗科技股份有限公司 | Catheter robot, registration method thereof and readable storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108133478A (en) * | 2018-01-11 | 2018-06-08 | 苏州润心医疗器械有限公司 | A kind of method for extracting central line of coronary artery vessel |
| CN108961390A (en) * | 2018-06-08 | 2018-12-07 | 华中科技大学 | Real-time three-dimensional method for reconstructing based on depth map |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101551862B (en) * | 2009-05-13 | 2011-06-01 | 西安电子科技大学 | An extraction method of blood vessel centerline based on boundary distance field |
| CN116051580A (en) * | 2017-05-09 | 2023-05-02 | 上海联影医疗科技股份有限公司 | Blood vessel separation method and system |
| CN108805871B (en) * | 2018-06-14 | 2021-06-25 | 艾瑞迈迪医疗科技（北京）有限公司 | Blood vessel image processing method and device, computer equipment and storage medium |
-
2019
- 2019-01-03 CN CN201910004369.2A patent/CN109754397B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108133478A (en) * | 2018-01-11 | 2018-06-08 | 苏州润心医疗器械有限公司 | A kind of method for extracting central line of coronary artery vessel |
| CN108961390A (en) * | 2018-06-08 | 2018-12-07 | 华中科技大学 | Real-time three-dimensional method for reconstructing based on depth map |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109754397A (en) | 2019-05-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109754397B (en) | Blood vessel section center path extraction method and device, terminal equipment and storage medium | |
| CN106600609B (en) | Spine segmentation method and system in medical image | |
| CN109741344A (en) | Blood vessel segmentation method, apparatus, medical imaging equipment and storage medium | |
| EP2365471B1 (en) | Diagnosis assisting apparatus, coronary artery analyzing method and recording medium having a coronary artery analzying program stored therein | |
| CN111325759B (en) | Vessel segmentation method, apparatus, computer device, and readable storage medium | |
| CN108701354A (en) | Identify the method and system of area-of-interest profile in ultrasonoscopy | |
| CN110853082B (en) | Medical image registration method, device, electronic equipment and computer storage medium | |
| JP2007506531A (en) | System and method for three-dimensional reconstruction of tubular organs | |
| CN111340756B (en) | Medical image lesion detection merging method, system, terminal and storage medium | |
| CN110378982B (en) | Reconstructed image processing method, device, equipment and storage medium | |
| CN110619635B (en) | Hepatocellular carcinoma magnetic resonance image segmentation system and method based on deep learning | |
| CN111904379B (en) | Scanning method and device for multi-mode medical equipment | |
| CN113662573B (en) | Mammary gland focus positioning method, device, computer equipment and storage medium | |
| CN113159040B (en) | Method, device and system for generating medical image segmentation model | |
| CN110473226B (en) | Training method of image processing network, computer device and readable storage medium | |
| CN113876345B (en) | Method, apparatus, electronic device, and storage medium for identifying ischemic penumbra | |
| CN111627023B (en) | Method and device for generating coronary artery projection image and computer readable medium | |
| CN108876783B (en) | Image fusion method and system, medical equipment and image fusion terminal | |
| CN113177953B (en) | Liver region segmentation method, liver region segmentation device, electronic equipment and storage medium | |
| CN111062998B (en) | Image reconstruction method, device, CT system and storage medium | |
| CN114299096A (en) | Outline delineation method, device, equipment and storage medium | |
| CN112489046B (en) | AI auxiliary measurement volume compensation method and device for flexible scanning image | |
| US10467497B2 (en) | System and method for providing assistance in surgery in presence of tissue deformation | |
| CN113469875B (en) | Light attenuation image synthesis method, device, terminal equipment and storage medium | |
| CN112419309B (en) | Medical image phase determination method, apparatus, computer device and storage medium |
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 |