CN109754397A - Extracting method, device, terminal device and the storage medium of vessel segment center path - Google Patents
Extracting method, device, terminal device and the storage medium of vessel segment center path Download PDFInfo
- Publication number
- CN109754397A CN109754397A CN201910004369.2A CN201910004369A CN109754397A CN 109754397 A CN109754397 A CN 109754397A CN 201910004369 A CN201910004369 A CN 201910004369A CN 109754397 A CN109754397 A CN 109754397A
- Authority
- CN
- China
- Prior art keywords
- point
- path
- image
- starting point
- tubular
- 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.)
- Granted
Links
Abstract
The embodiment of the present invention provides extracting method, device, terminal device and the storage medium of a kind of vessel segment center path.The extracting method of vessel segment center path of the invention, comprising: obtain the location information of the starting point of CTA image, the vessel segment that user inputs and the location information of terminating point；Mask image is determined according to CTA image, source distance field value of each tissue points relative to source point in mask image is determined according to mask image, the source point is the starting point or the terminating point；Source distance field value according to the location information of starting point, the location information of terminating point and at least one tissue points relative to source point, determines the shortest path between starting point and terminating point；Shortest path is corrected using tubular model and CTA image, each central point after obtaining correction；The center path of the vessel segment is determined according to each central point after the correction.The rapidly extracting of the center path to target blood section may be implemented in the embodiment of the present invention.
Description
Technical field
The present embodiments relate to Medical Image Processing more particularly to a kind of extraction sides of vessel segment center path
Method, device, terminal device and storage medium.
Background technique
Medical image (Medical Imaging) diagnosis is research by means of certain medium (such as X-ray, electromagnetic field, super
Sound wave etc.) it interacts with human body, inside of human body histoorgan structure, density are showed with imaging modality, cured for diagnosis
Teacher judges according to the information that image provides, to diagnose to human health status.Main includes perspective, radioactive ray
Piece, CT scan (Computed Tomography, CT), magnetic resonance imaging (Magnetic Resonance
Imaging, MRI), ultrasound, Digital Subtraction, angiography etc..
CT angiography (CT angiography, CTA) refers to is rapidly injected a kind of contrast medium from the vein of examinee,
By blood circulation of human body, it is scanned in the time that contrast medium concentrations reach peak-peak in blood vessel (artery and vein),
Post-processing through work station reconstructs the 3 D stereoscopic image (CTA image) of blood vessel.For CTA image, the extraction of blood vessel and can
It is data analysis and the effective means handled depending on changing, plays very important work during diagnosing and treating vascular diseases
With.For example, doctor is often interested in vessel segment where hemadostewnosis position, need to extract the Center Road of the part blood vessel
Diameter, thus carry out vessels analysis, such as measure its narrowness etc..For the extracting method of the center path of particular blood vessel section, lead to
It is often extracted for entire vascular tree, then from the vascular tree path of extraction, finds interested blood vessel using graph structure
Section path.
However, the extracting method in above-mentioned vessel segment path, can extract the center path other than many interesting parts, extract
It is longer that process expends the time.
Summary of the invention
The embodiment of the present invention provides extracting method, device, terminal device and the storage medium of a kind of vessel segment center path,
To realize the rapidly extracting to the center path of target blood section.
In a first aspect, the embodiment of the present invention provides a kind of extracting method of vessel segment center path, comprising: obtain CTA figure
The location information of the starting point for the vessel segment that picture, user input and the location information of terminating point；Institute is determined according to the CTA image
State the mask image of CTA image；Determine that each tissue points are relative to source point in the mask image according to the mask image
Source distance field value, the source point are the starting point or the terminating point；According to the location information of the starting point, the termination
The location information and source distance field value of at least one tissue points relative to source point of point, determine the starting point and the terminating point
Between shortest path；The shortest path is corrected using tubular model and the CTA image, it is each after obtaining correction
A central point；The center path of the vessel segment is determined according to each central point after the correction.
With reference to first aspect, described using tubular model and described in a kind of possible implementation of first aspect
CTA image is corrected the shortest path, each central point after obtaining correction, comprising: along the shortest path
Direction, respectively centered at least one path point of the shortest path point establish tubular model, by each tubular model with
The CTA image is matched, and center position, radius and the direction of each tubular model are adjusted；By each pipe adjusted
The center position of shape model is as the central point after correction.
With reference to first aspect or a kind of possible implementation of first aspect, in the alternatively possible reality of first aspect
In existing mode, the direction along the shortest path, respectively centered at least one path point of the shortest path
Point establishes tubular model, and each tubular model is matched with the CTA image, adjusts the center point of each tubular model
It sets, radius and direction, comprising: since the starting point, point, establishes tubular model centered on the starting point, will be described
Tubular model is matched with the CTA image, adjusts center position, radius and the direction of the tubular model, along
One blood vessel tracks direction and chooses next path point, updates the central point with next path point, tubulose is established in execution
Model matches the tubular model with the CTA image, adjust the center position of the tubular model, radius and
The step of direction, until the next path point chosen exceeds the terminating point；Alternatively, since the terminating point, with described
Point, establishes tubular model centered on terminating point, and the tubular model is matched with the CTA image, adjusts the tubulose
Next path point is chosen along the second blood vessel tracking direction, with described next in center position, radius and the direction of model
Path point updates the central point, and execution establishes tubular model, the tubular model is matched with the CTA image, adjusts
The step of center position of the whole tubular model, direction, radius, until the next path point chosen exceeds the starting
Point；Alternatively, the point centered on the starting point and ending point, builds respectively respectively since the starting point and the terminating point
Two tubular models are found, described two tubular models are matched with the CTA image, adjust described two tubular models
Center position, radius and direction track direction along the first blood vessel and the second blood vessel method for tracing choose next road respectively
Diameter point updates the central point respectively with two next path points, and two tubular models are established in execution, by described two tubuloses
The step of model is matched with the CTA image, adjusts center position, direction and the radius of described two tubular models,
Until the two next path point positions tracking direction along the first blood vessel and being chosen along the second blood vessel tracking direction
Region overlapping.
With reference to first aspect or any possible implementation of first aspect, in the alternatively possible of first aspect
In implementation, the radius that the tubular model of foundation is put centered on next path point is preceding primary tubular model adjusted
Radius.
With reference to first aspect or any possible implementation of first aspect, in the alternatively possible of first aspect
In implementation, the method also includes: according to the information of three dimensions in the mask image, generate the first index information,
Second index information and third index information, first index information include body in first every layer of dimension direction mask image
The number of vegetarian refreshments, the second index information include the number of tissue points in each second dimension direction in every layer of mask image, the
Three index informations include in the mask image each tissue points in the position in third dimension direction；By the first index letter
Breath, second index information and the third index information, are associated with one-dimension array, cover described in storage in the one-dimension array
The source distance field value of each tissue points of film image.
With reference to first aspect or any possible implementation of first aspect, in the alternatively possible of first aspect
It is described according to the location information of the starting point, the location information of the terminating point and at least one tissue points in implementation
Source distance field value, determine the shortest path between the starting point and the terminating point, comprising: according to the position of the starting point
Confidence breath, the location information of the terminating point, first index information, second index information and third index information,
From the source distance field value for obtaining each tissue points in the vessel segment in the one-dimension array；The position of the starting point is believed
It ceases, the source distance field value of each tissue points inputs shortest path first in the location information and the vessel segment of the terminating point
In, export the shortest path between the starting point and the terminating point.
With reference to first aspect or any possible implementation of first aspect, in the alternatively possible of first aspect
In implementation, the mask image that the CTA image is determined according to the CTA image, comprising: to the CTA image into
Row threshold division obtains the mask image.
Second aspect, the embodiment of the present invention provide a kind of extraction element of vessel segment center path, comprising: module is obtained,
For obtaining the location information of the starting point of the vessel segment of CTA image, user's input and the location information of terminating point；Mask image
Module, for determining the mask image of the CTA image, source distance field determining module, for according to institute according to the CTA image
It states mask image and determines source distance field value of each tissue points relative to source point in the mask image, the source point is described rises
Initial point or the terminating point；Shortest path determining module, for the position according to the location information of the starting point, the terminating point
Confidence breath and source distance field value of at least one tissue points relative to source point, determine between the starting point and the terminating point
Shortest path；Correction module obtains school for being corrected using tubular model and the CTA image to the shortest path
Each central point after just；Center path determining module, for determining the blood vessel according to each central point after the correction
The center path of section.
The third aspect, the embodiment of the present invention provide a kind of terminal device, which is characterized in that the terminal device includes: place
Manage device, memory, transceiver；The transceiver couples to the processor, the processor controls the transmitting-receiving of the transceiver
Movement；Wherein, the memory includes instruction for storing computer executable program code, said program code；When described
When processor executes described instruction, described instruction makes the terminal device execute the described in any item methods of first aspect.
Fourth aspect, the embodiment of the present invention provide a kind of computer storage medium, are stored thereon with computer program or refer to
It enables, which is characterized in that when the computer program or instruction are executed by processor or computer, realize as first aspect is any
Method described in.
Extracting method, device, terminal device and the storage medium of the vessel segment center path of the embodiment of the present invention, by obtaining
The location information of the starting point for the vessel segment for taking CTA image, user to input and the location information of terminating point, scheme according to the CTA
Mask image as determining the CTA image, determines that each tissue points are opposite in the mask image according to the mask image
In the source distance field value of source point, according to the location information of the starting point, the location information and at least one body of the terminating point
Source distance field value of the vegetarian refreshments relative to source point, determines the shortest path between the starting point and the terminating point, uses tubulose
Model and the CTA image are corrected the shortest path, each central point after obtaining correction, after the correction
Each central point determine the center path of the vessel segment.Due to the starting point and termination of the vessel segment inputted according to user
Point is determined the shortest path of target blood section in conjunction with source distance field, and is corrected using tubular model to shortest path, to mention
Center path is taken, the rapidly extracting of the center path to target blood section may be implemented, to divide target blood section
Analysis, such as measure its narrowness etc., improve the accuracy and science of medical diagnosis.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this hair
Bright some embodiments for those of ordinary skill in the art without any creative labor, can be with
It obtains other drawings based on these drawings.
Fig. 1 is a kind of schematic diagram of application scenarios of the embodiment of the present invention；
Fig. 2 is the schematic diagram of another application scenarios of the embodiment of the present invention；
Fig. 3 is the flow chart of the extracting method embodiment one of vessel segment center path of the invention；
Fig. 4 is the flow chart of the extracting method embodiment two of vessel segment center path of the invention；
Fig. 5 is the flow chart of the mode one of the step 204 of the embodiment of the present invention；
Fig. 6 is the flow chart of the mode two of the step 204 of the embodiment of the present invention；
Fig. 7 is the flow chart of the mode three of the step 204 of the embodiment of the present invention；
Fig. 8 is the flow chart of the storage mode of the source distance field value of the embodiment of the present invention；
Fig. 9 is the schematic diagram of the extraction element embodiment one of vessel segment center path of the invention；
Figure 10 is the structural schematic diagram of terminal device portion embodiment one of the invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.
Description and claims of this specification and term " first " in above-mentioned attached drawing, " second ", etc. (if deposited
) it is to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should be understood that use in this way
Data are interchangeable under appropriate circumstances, so that the embodiment of the present invention described herein for example can be in addition to illustrating herein
Or the sequence other than those of description is implemented.In addition, term " includes " and " having " and their any deformation, it is intended that
Cover it is non-exclusive include, for example, containing the process, method, system, product or equipment of a series of steps or units need not limit
In step or unit those of is clearly listed, but may include be not clearly listed or for these process, methods, produce
The other step or units of product or equipment inherently.
" CTA image " involved in this paper refers specifically to the three-dimensional obtained by computed tomography (CT) angiography
Fault image.It can be through CT imaging system scanning collection, and reconstruct by work station (for example, computer) post-processing
Three-dimension disclocation image.The CTA image can be with digital imaging and communications in medicine (Digital Imaging and
Communications in Medicine, DICOM) format stored and transmitted, and DICOM is medical image and relevant information
International standard, it defines the Medical Image Format that can be used for data exchange that quality is able to satisfy clinical needs.
Tissue points involved in this paper, refer to be in mask image true (true) tissue points, for being in mask image
The tissue points of false (false) are not discussed herein.
Fig. 1 is a kind of schematic diagram of application scenarios of the embodiment of the present invention, as shown in Figure 1, the application scenarios include terminal
Equipment and CTA image capture device, the CTA image capture device may include CT imaging system as described above and work station,
CTA image is sent to terminal device by work station, the vessel segment Center Road which passes through the execution embodiment of the present invention
The extracting method of diameter, to realize the rapidly extracting to the center path of target blood section, so that target blood section is analyzed,
Such as measure its narrowness etc., improve the accuracy and science of medical diagnosis.
Fig. 2 is the schematic diagram of another application scenarios of the embodiment of the present invention, as shown in Fig. 2, the application scenarios include eventually
End equipment and storage system, the storage system are used to store the CTA image of CTA image capture device acquisition, and the terminal device is logical
The extracting method for executing the vessel segment center path of the embodiment of the present invention is crossed, to realize to the fast of the center path of target blood section
Speed is extracted, so that target blood section is analyzed, such as measures its narrowness etc., improve the accuracy and science of medical diagnosis
Property.
The terminal device of the embodiment of the present invention is referred to as terminal (Terminal), user equipment (user
Equipment, UE), mobile station (mobile station, MS), mobile terminal (mobile terminal, MT) etc..Terminal is set
It is standby to can be computer (PC), mobile phone (mobile phone), tablet computer (Pad), computer with radio transmission-receiving function etc..
Fig. 3 is the flow chart of the extracting method embodiment one of vessel segment center path of the invention, the execution of the present embodiment
Main body can be the extraction element of vessel segment center path, and the extraction element of the vessel segment center path can be above-mentioned terminal and set
Standby or terminal device inside chip, as shown in figure 3, the method for the present embodiment may include:
The location information of the starting point for the vessel segment that step 101, acquisition CTA image, user input and the position of terminating point
Information.
Wherein, user input vessel segment the location information of starting point and the location information of terminating point can be according to
The starting point and ending point clicked in the two dimension view that family is shown on the terminal device generates, and specifically can be will be in two dimension view
Starting point and ending point be converted to the starting point and ending point in 3D data volume, obtain the position of the starting point of user's input
The location information of information and terminating point.
Step 102, the mask image that CTA image is determined according to CTA image.
Wherein, the binary picture that mask images are made of 0 and 1,1 value region in the binary picture be to
The target area of processing, for example, the blood vessel of the present embodiment, 0 value region is the region without participating in processing, for example, bone, muscle
Deng.
It should be noted that CTA image includes bone, muscle, blood vessel etc., the mask image of CTA image is schemed to the CTA
As carrying out processing acquisition, the mask image of the CTA image is for reflecting area-of-interest (such as blood vessel).In order to ensure user is defeated
The starting point and ending point entered can find correct center path at any position on blood vessel, the mask image it is big
It is small identical as the size of CTA image.
Step 103, according to the mask image, determine each tissue points in the mask image relative to source point source away from
It leaves the theatre value, the source point is starting point or terminating point.
Wherein, according to mask image, each tissue points are calculated to starting point or the distance of terminating point, the embodiment of the present invention
The distance field is known as source distance field (distance from source, DFS), the calculation of source distance field value can use
Chamfering distance (Chamfer Distance), Euclidean distance or city block distance etc., wherein the connection weight weight values of each tissue points can
To use integer, with the calculating of acceleration source distance field.
Step 104, according to the location information of the starting point, the location information of the terminating point and at least one tissue points
Relative to the source distance field value of source point, the shortest path between the starting point and the terminating point is determined.
At least one tissue points can be multiple between starting point and ending point relative to the source distance field value of source point
Source distance field value of the tissue points relative to source point, is also possible to source distance field value of all tissue points relative to source point.
Wherein it is possible to by the location information of the starting point, the location information of the terminating point and at least one tissue points
Source distance field value be input in shortest path first, export starting point and ending point between shortest path, the shortest path
Algorithm can be dijkstra's algorithm, bellman-ford algorithm, Floyd algorithm and SPFA algorithm etc..
The shortest path may include multiple path points, can be expressed as RA,P1,…..,PN,PB, PA, indicate starting point
A, PBIndicate terminating point B.
Step 105 is corrected the shortest path using tubular model and the CTA image, after obtaining correction
Each central point.
The shortest path that step 104 obtains further is corrected using the mode that tubular model is tracked, to avoid mentioning
The center path of the vessel segment taken is not enough to carry out vessels analysis close to vascular wall.
Step 106, the center path that the vessel segment is determined according to each central point after the correction.
Wherein, each central point after correction is successively merged, then between available starting point and ending point
The center path of the interested target blood section of the center path of vessel segment, i.e. user.
It should be noted that B-spline function can also be used to carry out interpolation to the center path, to obtain voxel level
Center path.
The present embodiment, the location information and terminating point of the starting point of the vessel segment by obtaining CTA image, user's input
Location information determines the mask image of CTA image according to CTA image, is determined according to mask image each in the mask image
Source distance field value of the tissue points relative to source point, according to the location information of the starting point, the terminating point location information and
Source distance field value of at least one tissue points relative to source point, determines the shortest path between the starting point and the terminating point
Diameter is corrected the shortest path using tubular model and the CTA image, each central point after obtaining correction, root
The center path of the vessel segment is determined according to each central point after the correction.Due to of the vessel segment inputted according to user
Initial point and terminating point, determine the shortest path of target blood section in conjunction with source distance field, and using tubular model to shortest path into
Row correction, to extract center path, may be implemented the rapidly extracting of the center path to target blood section, thus to target blood
Pipeline section is analyzed, such as measure its narrowness etc., improve the accuracy and science of medical diagnosis.
Several specific embodiments are used below, and the technical solution of embodiment of the method shown in Fig. 3 is described in detail.
Fig. 4 is the flow chart of the extracting method embodiment two of vessel segment center path of the invention, as shown in figure 4, this reality
The method for applying example may include:
The location information of the starting point for the vessel segment that step 201, acquisition CTA image, user input and the position of terminating point
Information.
Step 202, the mask image that CTA image is determined according to CTA image.
Step 203, according to the mask image, determine each tissue points in the mask image relative to source point source away from
It leaves the theatre value, the source point is the starting point or terminating point.
Step 204, according to the location information of the starting point, the location information of the terminating point and at least one tissue points
Relative to the source distance field value of source point, the shortest path between the starting point and the terminating point is determined.
Wherein, the specific explanations of step 201 to step 204 illustrate to may refer to the step 101 of embodiment illustrated in fig. 3 to step
Rapid 104, details are not described herein again.
Step 205, along shortest path direction, respectively centered at least one path point of the shortest path point build
Vertical tubular model, each tubular model is matched with the CTA image, adjust each tubular model center position,
Radius and direction.
Wherein, the direction of shortest path can be determined according to the path point on shortest path.By what is established according to path point
Tubular model is matched with real image (above-mentioned CTA image), and LM (Levenberg-Marquard) calculation specifically can be used
Method adjusts center position, radius size and the direction of tubular model, calculates tubular model adjusted and real image is (above-mentioned
CTA image) between error, take in certain the number of iterations, the smallest parameter of error (center position, radius size and direction)
As the parameter of tubular model adjusted, i.e., center position, radius size and the direction of tubular model adjusted.
Tubular model can be established centered on one or more path points of the shortest path respectively, wherein for building
The selection mode of the path point of vertical tubular model can be, after a tubular model adjusts, with center position adjusted,
Tubular model is established in conjunction with the path point that the path point on shortest path chooses a shortest path.
Step 206, using the center position of each tubular model adjusted as correction after each central point.
Using the center position of each tubular model adjusted as each central point after correction, successively closed
And the then center path of the vessel segment between available starting point and ending point, the i.e. interested target blood section of user
Center path.
Step 207, the center path that the vessel segment is determined according to each central point after the correction.
Wherein, the explanation of step 207 may refer to the step 106 of embodiment illustrated in fig. 3, and details are not described herein again.
The present embodiment, the location information and terminating point of the starting point of the vessel segment by obtaining CTA image, user's input
Location information determines the mask image of CTA image according to CTA image, according to the mask image, determines in the mask image
Source distance field value of each tissue points relative to source point is believed according to the position of the location information of the starting point, the terminating point
Breath and source distance field value of at least one tissue points relative to source point, determine most short between the starting point and the terminating point
Path, along blood vessel tracking direction, point establishes tubular model centered at least one path point of the shortest path respectively,
Each tubular model is matched with the CTA image, adjusts center position, radius and the direction of each tubular model,
Using the center position of each tubular model adjusted as each central point after correction, realize in target blood section
The rapidly extracting of heart road diameter, so that target blood section is analyzed, such as measures its narrowness etc., improve the standard of medical diagnosis
True property and science.
Optionally, it is matched, is adjusted with real image (above-mentioned CTA image) by the tubular model established according to path point
Whole tubular model, radius, center position and the direction of available blood vessels present section can also obtain point of blood vessels present section
Cut result, wherein blood vessels present section is one section in the vessel segment between starting point and ending point, for example, PAAnd PnBetween blood vessel
Section.Due to the above-mentioned tracking adjustment mode using tubular model, allows and extracts center path well at the blood vessel place of being adhered,
And some preferable than treatment effect at thin blood vessel.
Explanation to above-mentioned steps 205, above-mentioned steps 205 can have following three kinds of different implementations.
Fig. 5 is the flow chart of the mode one of the step 205 of the embodiment of the present invention, as shown in figure 5, the present embodiment is in above-mentioned reality
On the basis of applying example, the mode one of step 205 is explained, the method for the present embodiment may include:
Step 301, since starting point, by point centered on starting point.
Specifically, can be from starting point PAStart to carry out blood vessel tracking.
Wherein, initial point (PA) at blood vessel direction be VA=Pi-PA, i is times to take one in K point after A point, can
To be determined according to adjusting step.
The calculation of starting point radius can be with are as follows: calculates just in the X/Y plane of data volume, YZ plane, ZX plane respectively
Initial point (PA) where blood vessel radius and like circularity information, take like the corresponding radius of circularity maximum as initial point radius.
Step 302 establishes tubular model with central point.
In first time iterative process, tubular model is established with the starting point, direction and radius.And execute step 303.
In N (N > 1) secondary iterative process, central point is updated with next path point, radius can match to be previous
Obtain vessel segment radius Radius, direction V=Pm+i-Pm, tubular model is established with this.And step 303 is executed, it is next to this
Vessel segment is matched.
Step 303 matches tubular model with CTA image, adjusts the center position of tubular model.
Step 304 chooses next path point along the first blood vessel tracking direction.
Wherein, the selection mode of next path point are as follows: assuming that iteration step length is step=factor*Radius, wherein
Radius be preceding an iteration radius size, it is assumed that it is previous do not adjust before central point be pK, traverse PK+1,
Pk+2,.....,PN,PB, meet | | Pm-PK| | the P of ≈ stepmAs next path point, i.e., the central point of next vessel segment.
Step 305 judges whether next path point exceeds terminating point, if it is not, 306 are thened follow the steps, if so, executing
The step 206 of above-mentioned embodiment illustrated in fig. 4.
If next path point exceeds terminating point, using the center position of each tubular model adjusted as school
Each central point after just.
Step 306 updates central point with next path point, and returns to step 302.
The present embodiment chooses next path point, the tubulose established centered on next path point according to iteration step length
Model, the radius of the tubular model, can be with boosting algorithm convergence rates using preceding primary radius adjusted.
Fig. 6 is the flow chart of the mode two of the step 205 of the embodiment of the present invention, as shown in fig. 6, the present embodiment is in above-mentioned reality
On the basis of applying example, the mode two of step 205 is explained, the method for the present embodiment may include:
Step 401, since terminating point, by point centered on terminating point.
The difference of the present embodiment and embodiment illustrated in fig. 5 is, since terminating point, to starting point carry out blood vessel tracking and
Adjustment.
Step 402 establishes tubular model with central point.
Step 403 matches tubular model with CTA image, adjusts the center position of tubular model.
Step 404 chooses next path point along the second blood vessel tracking direction.
Step 405 judges whether next path point exceeds starting point, if it is not, 406 are thened follow the steps, if so, executing
The step 206 of above-mentioned embodiment illustrated in fig. 4.
Step 406 updates central point with next path point, and returns to step 402.
The present embodiment chooses next path point, the tubulose established centered on next path point according to iteration step length
Model, the radius of the tubular model, can be with boosting algorithm convergence rates using preceding primary radius adjusted.
Fig. 7 is the flow chart of the mode three of the step 205 of the embodiment of the present invention, as shown in fig. 7, the present embodiment is in above-mentioned reality
On the basis of applying example, the mode three of step 205 is explained, the method for the present embodiment may include:
Step 501, respectively since starting point and ending point, respectively with starting point and ending point for two central points.
The present embodiment and the difference of Fig. 5, embodiment illustrated in fig. 6 be, since terminating point and starting point are parallel, carries out blood
Pipe tracking and adjustment.
Step 502 with two central points establishes two tubular models respectively.
Step 503 respectively matches two tubular models with CTA image, adjusts the central point of two tubular models
Position.
Step 504 chooses next path point along the first blood vessel tracking direction and the second blood vessel method for tracing respectively.
Step 505, judge along the first blood vessel track direction and along the second blood vessel tracking direction choose two it is next
Whether a path point position region is overlapped, if it is not, 506 are thened follow the steps, if so, executing above-mentioned embodiment illustrated in fig. 4
Step 206.
When the overlapping of starting point and ending point trace regions, then completion is tracked, after the adjustment that the two tracing process is generated
Central point successively merge, then the path between starting point and ending point can be obtained.
Step 506 with two next path points updates two central points respectively, and returns to step 502.
The present embodiment chooses next path point according to iteration step length respectively from both direction, respectively with next path
The tubular model established centered on point, the radius of the tubular model can be promoted further using preceding primary radius adjusted
Algorithm the convergence speed.
Fig. 8 is the flow chart of the storage mode of the source distance field value of the embodiment of the present invention, as shown in figure 8, the present embodiment exists
On the basis of above-described embodiment, the method for the present embodiment can also include:
Step 601, according to the information of three dimensions in mask image, generate the first index information, the second index information and
Third index information.
Wherein, first index information includes the number of tissue points in first every layer of dimension direction mask image, the
Two index informations include the number of tissue points in each second dimension direction in every layer of mask image, and third index information includes
Position of each tissue points in third dimension direction in the mask image.
It is illustrated with three dimensions for tri- dimensions of x, y and z, traverses mask image, count every layer of the direction z exposure mask
Number in image for 1 (True) counts the direction every row y exposure mask figure in each XY tomographic image to get to the first index information
As in number be the number of 1 (True) to get to the second index information, count in mask image promising 1 tissue points the side x
To location information, obtain third index information.Assuming that mask image is the image of 512*512*300, wherein there is 10000 points
For True, then the size of first index information is 300*1, and the size of second index information is 512*300, third index letter
The size of breath is 10000*1, the location information in the direction x of one tissue points of each behavior in third index information.
Step 602, by first index information, the second index information and the third mask information, with one-dimension array
It is associated with, the source distance field value of each tissue points of the mask image is stored in the one-dimension array.
It by the first index information, the second index information and third index information, is associated with one-dimension array, specific interrelational form
It can be index association, i.e., determined and indexed according to the first index information, the second index information and third index information, index and one
Each element in dimension group is corresponding, is further explained explanation with the example above, which is 10000*1.This is one-dimensional
The source distance field value of each tissue points of mask image is stored in array.
For 3-D image, if mask image takes whole image, it will be occupied very in terms of opening up memory
More spaces.The above-mentioned storage mode of the embodiment of the present invention can save the memory headroom of data storage.
On the basis of the storage mode, the achievable modes of above-mentioned steps of the embodiment of the present invention 204 can be with are as follows: according to rising
The location information of initial point, the location information of terminating point, the first index information, the second index information and third index information, from institute
State the source distance field value that each tissue points in the vessel segment are obtained in one-dimension array；By the location information of the starting point, institute
It states in the source distance field value input shortest path first of each tissue points in the location information and the vessel segment of terminating point, output
Shortest path between the starting point and the terminating point.
Based on above-mentioned first index information, the second index information and third index information, exposure mask figure can be quickly found
Element in the three-dimensional data of picture for true is in the position of one-dimensional data.Such as given (x, y, z) is a bit, by z, y value passes through
First index information, the second index information can quickly navigate to the minimum position (Lowx) and highest in third index
(hightx) position, then the index position in one-dimension array is navigated to by dichotomy and x value, thus obtain the source of set point away from
It leaves the theatre value.
The present embodiment passes through the first index information, the second index information and third index information and one-dimension array, Ke Yijie
The memory headroom of data storage is saved, and the quick lookup of the source distance field value of corresponding position point may be implemented.
Fig. 9 is the schematic diagram of the extraction element embodiment one of vessel segment center path of the invention, and wherein the device is eventually
Some or all of end equipment, the terminal device can be smart phone, tablet computer, PC etc., as shown in figure 9, the device packet
It includes:
Module 91 is obtained, the location information and terminating point of the starting point of the vessel segment for obtaining CTA image, user's input
Location information.
Mask image module 92, for determining the mask image of the CTA image according to the CTA image
Source distance field determining module 93, for determining each tissue points in the mask image according to the mask image
Relative to the source distance field value of source point, the source point is the starting point or terminating point；
Shortest path determining module 94, for the location information according to the location information of the starting point, the terminating point
Source distance field value at least one tissue points relative to source point, determines the shortest path between the starting point and the terminating point
Diameter；
Correction module 95 obtains school for being corrected using tubular model and the CTA image to the shortest path
Each central point after just；
Center path determining module 96, for determining the center of the vessel segment according to each central point after the correction
Path.
Optionally, correction module 95 is used for: along the direction of shortest path, respectively with the shortest path at least one
Point establishes tubular model centered on path point, and each tubular model is matched with the CTA image, adjusts each tubular mold
Center position, radius and the direction of type；Using the center position of each tubular model adjusted as each after correction
Central point.
Optionally, correction module 95 is used for: since the starting point, point, establishes tubulose centered on the starting point
Model matches the tubular model with the CTA image, adjust the center position of the tubular model, radius and
Direction chooses next path point along the first blood vessel tracking direction, updates the central point with next path point, hold
Row establishes tubular model, and the tubular model is matched with the CTA image, adjusts the center point of the tubular model
It sets, radius and the step of direction, until the next path point chosen exceeds the terminating point；Alternatively, being opened from the terminating point
Begin, point, establishes tubular model centered on the terminating point, and the tubular model is matched with the CTA image, adjusts
Next path point is chosen along the second blood vessel tracking direction, with institute in center position, radius and the direction of the tubular model
It states next path point and updates the central point, tubular model is established in execution, and the tubular model and the CTA image are carried out
The step of matching, adjusting center position, radius and the direction of the tubular model, until the next path point chosen exceeds
The starting point；Alternatively, respectively since the starting point and the terminating point, respectively it is with the starting point and ending point
Heart point establishes two tubular models, and described two tubular models are matched with the CTA image, adjust described two pipes
Center position, radius and the direction of shape model track direction along the first blood vessel and the second blood vessel method for tracing are chosen respectively
Next path point updates the central point respectively with two next path points, and two tubular models are established in execution, will be described
Two tubular models are matched with the CTA image, adjust center position, radius and the direction of described two tubular models
The step of, until the two next path point institutes tracking direction along the first blood vessel and being chosen along the second blood vessel tracking direction
It is overlapped in the band of position.
Optionally, the radius that the tubular model of foundation is put centered on next path point is preceding primary tubulose adjusted
The radius of model.
Described device further include: memory module 97, memory module 97 are used for according to three dimensions in the mask image
Information, generates the first index information, the second index information and third index information, and first index information includes first dimension
The number of tissue points in the mask image of every layer of direction is spent, the second index information includes each second dimension in every layer of mask image
The number of tissue points in direction, third index information include in the mask image each tissue points in third dimension direction
Position；By first index information, second index information and the third index information, it is associated with one-dimension array, institute
State the source distance field value that each tissue points of the mask image are stored in one-dimension array.
Optionally, shortest path determining module 94 is used for the position according to the location information of the starting point, the terminating point
Confidence breath, first index information, second index information and the third index information, are obtained from the one-dimension array
Take the source distance field value of each tissue points in the vessel segment；By the position of the location information of the starting point, the terminating point
In information and vessel segment in the source distance field value input shortest path first of each tissue points, the starting point and the end are exported
Shortest path between stop.
Optionally, mask image module 92 obtains the mask image for carrying out Threshold segmentation to the CTA image.
The extraction element of vessel segment center path provided in an embodiment of the present invention can be used for executing above-mentioned vessel segment center
The extracting method in path, content and effect can refer to method part, and the embodiment of the present invention repeats no more this.
Figure 10 is the structural schematic diagram of terminal device portion embodiment one of the invention, as shown in Figure 10, the clothes of the present embodiment
Business device, comprising: processor 211, memory 212, transceiver 213 and bus 214.Wherein, processor 211,212 and of memory
Transceiver 213 is connected with each other by bus 214.Wherein, bus 214 can be Peripheral Component Interconnect standard (Peripheral
Component Interconnect, PCI) bus or expanding the industrial standard structure (Extended Industry Standard
Architecture, EISA) bus etc..Above-mentioned bus 214 can be divided into address bus, data/address bus, control bus etc..For just
It is only indicated with a thick line in expression, Figure 10, it is not intended that an only bus or a type of bus.
In hardware realization, each functional module shown in figure 9 above can be embedded in the form of hardware or independently of end
In the processor 211 of end equipment.
The transceiver 213 may include the necessary radio communication device such as frequency mixer.The processor 211 may include
Central processing unit (Central Processing Unit, CPU), digital signal processor (digital signal
Processor, DSP), microcontroller (Microcontroller Unit, MCU), specific integrated circuit (Application
Specific Integrated Circuit, ASIC) or field programmable gate array (Field-Programmable
At least one of Gate Array, FPGA).
Memory 212 is for storing program instruction, and processor 211 is for calling the program instruction in memory 212 to execute
Above scheme.
Described program instruction can be realized in the form of SFU software functional unit and can sell or make as independent product
With the memory 212 can be any form of computer-readable storage medium.Based on this understanding, the application
The all or part of technical solution can be embodied in the form of software products, including some instructions are used so that a calculating
Machine equipment specifically can be processor 211, in each embodiment of Lai Zhihang the application the whole of the executive device of business operation or
Part steps.And computer readable storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (Read-Only
Memory, ROM), random access memory (Random Access Memory, RAM), magnetic or disk etc. is various to deposit
Store up the medium of program code.
The above-described terminal device of the present embodiment can be used for executing the technical solution in above-mentioned each method embodiment,
That the realization principle and technical effect are similar is similar for it, wherein the function of each device can be with reference to describing accordingly in embodiment of the method, this
Place repeats no more.
The embodiment of the present invention also provides a kind of computer storage medium, comprising: computer instruction, the computer instruction are used
In the extracting method for realizing vessel segment center path as mentioned.Its content and effect can refer to method part, and the present invention is implemented
Example repeats no more this.
The embodiment of the present invention provides a kind of computer program product, comprising: computer instruction, the computer instruction are used for
Realize the extracting method of vessel segment center path as mentioned.Its content and effect can refer to method part, the embodiment of the present invention
This is repeated no more.
Those of ordinary skill in the art will appreciate that: realize that all or part of the steps of above-mentioned each method embodiment can lead to
The relevant hardware of program instruction is crossed to complete.Program above-mentioned can be stored in a computer readable storage medium.The journey
When being executed, execution includes the steps that above-mentioned each method embodiment to sequence；And storage medium above-mentioned include: ROM, RAM, magnetic disk or
The various media that can store program code such as person's CD.
Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations；To the greatest extent
Pipe present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: its according to
So be possible to modify the technical solutions described in the foregoing embodiments, or to some or all of the technical features into
Row equivalent replacement；And these are modified or replaceed, various embodiments of the present invention technology that it does not separate the essence of the corresponding technical solution
The range of scheme.
Claims (10)
1. a kind of extracting method of vessel segment center path characterized by comprising
Obtain the location information of the starting point of CTA image, the vessel segment that user inputs and the location information of terminating point；
The mask image of the CTA image is determined according to the CTA image；
Source distance field value of each tissue points relative to source point, the source in the mask image are determined according to the mask image
Point is the starting point or the terminating point；
According to the location information of the starting point, the location information of the terminating point and at least one tissue points relative to source point
Source distance field value, determines the shortest path between the starting point and the terminating point；
The shortest path is corrected using tubular model and the CTA image, each central point after obtaining correction；
The center path of the vessel segment is determined according to each central point after the correction.
2. the method according to claim 1, wherein described use tubular model and the CTA image to described
Shortest path is corrected, each central point after obtaining correction, comprising:
Along the direction of the shortest path, point establishes tubulose centered at least one path point of the shortest path respectively
Model matches each tubular model with the CTA image, adjust the center position of each tubular model, radius and
Direction；
Using the center position of each tubular model adjusted as each central point after correction.
3. according to the method described in claim 2, it is characterized in that, the direction along the shortest path, respectively with institute
State point centered at least one path point of shortest path and establish tubular model, by each tubular model and the CTA image into
Row matching, adjusts center position, radius and the direction of each tubular model, comprising:
Since the starting point, point, establishes tubular model centered on the starting point, by the tubular model with it is described
CTA image is matched, and center position, radius and the direction of the tubular model are adjusted, and tracks direction along the first blood vessel
Next path point is chosen, the central point is updated with next path point, tubular model is established in execution, by the tubulose
The step of model is matched with the CTA image, adjusts center position, radius and the direction of the tubular model, until
The next path point chosen exceeds the terminating point；Alternatively,
Since the terminating point, point, establishes tubular model centered on the terminating point, by the tubular model with it is described
CTA image is matched, and center position, radius and the direction of the tubular model are adjusted, and tracks direction along the second blood vessel
Next path point is chosen, the central point is updated with next path point, tubular model is established in execution, by the tubulose
The step of model is matched with the CTA image, adjusts center position, radius and the direction of the tubular model, until
The next path point chosen exceeds the starting point；Alternatively,
Respectively since the starting point and the terminating point, the point centered on the starting point and ending point, establishes two respectively
Described two tubular models are matched with the CTA image, adjust the center of described two tubular models by a tubular model
Point position, radius and direction, track direction along the first blood vessel and the second blood vessel method for tracing choose next path point respectively,
The central point is updated with two next path points respectively, two tubular models are established in execution, by described two tubular models
The step of being matched with the CTA image, adjusting center position, radius and the direction of described two tubular models, until
The two next path point positions region tracking direction along the first blood vessel and being chosen along the second blood vessel tracking direction
Overlapping.
4. according to the method described in claim 3, it is characterized in that, putting the tubular model of foundation centered on next path point
Radius be preceding primary tubular model adjusted radius.
5. method according to any one of claims 1 to 4, which is characterized in that the method also includes:
According to the information of three dimensions in the mask image, the first index information, the second index information and third index are generated
Information, first index information include the number of tissue points in first every layer of dimension direction mask image, the second index letter
Breath includes the number of tissue points in each second dimension direction in every layer of mask image, and third index information includes the exposure mask
Position of each tissue points in third dimension direction in image；
By first index information, second index information and the third index information, it is associated with one-dimension array, it is described
The source distance field value of each tissue points of the mask image is stored in one-dimension array.
6. according to the method described in claim 5, it is characterized in that, the location information according to the starting point, the end
The location information of stop and the source distance field value of at least one tissue points, determine between the starting point and the terminating point most
Short path, comprising:
According to the location information of the starting point, the location information of the terminating point, first index information, second rope
Fuse breath and the third index information, from the source distance field for obtaining each tissue points in the vessel segment in the one-dimension array
Value；
By the location information of the starting point, the terminating point location information and the vessel segment in each tissue points source away from
Value of leaving the theatre inputs in shortest path first, exports the shortest path between the starting point and the terminating point.
7. method according to any one of claims 1 to 4, which is characterized in that described according to CTA image determination
The mask image of CTA image, comprising:
Threshold segmentation is carried out to the CTA image, obtains the mask image.
8. a kind of extraction element of vessel segment center path characterized by comprising
Module is obtained, the location information of the starting point of the vessel segment for obtaining CTA image, user's input and the position of terminating point
Information；
Mask image module, for determining the mask image of the CTA image according to the CTA image；
Source distance field determining module, for determining that each tissue points are relative to source in the mask image according to the mask image
The source distance field value of point, the source point are the starting point or the terminating point；
Shortest path determining module, for according to the location information of the starting point, the location information of the terminating point and at least
Source distance field value of one tissue points relative to source point, determines the shortest path between the starting point and the terminating point；
Correction module, for being corrected using tubular model and the CTA image to the shortest path, after obtaining correction
Each central point；
Center path determining module, for determining the center path of the vessel segment according to each central point after the correction.
9. a kind of terminal device, which is characterized in that the terminal device includes: processor, memory, transceiver；The transmitting-receiving
Device is coupled to the processor, and the processor controls the transmitting-receiving movement of the transceiver；
Wherein, the memory includes instruction for storing computer executable program code, said program code；When the place
When managing device execution described instruction, described instruction makes the terminal device execute method as described in any one of claim 1 to 7.
10. a kind of computer storage medium is stored thereon with computer program or instruction, which is characterized in that when the computer
When program or instruction are executed by processor or computer, method as described in any one of claim 1 to 7 is realized.
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 true CN109754397A (en) | 2019-05-14 |
| CN109754397B 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) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111640124A (en) * | 2020-05-25 | 2020-09-08 | 浙江同花顺智能科技有限公司 | Blood vessel extraction method, device, equipment and storage medium |
| CN113888690A (en) * | 2021-10-19 | 2022-01-04 | 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 |
| CN114708259A (en) * | 2022-05-24 | 2022-07-05 | 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 |
| 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 |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101551862A (en) * | 2009-05-13 | 2009-10-07 | 西安电子科技大学 | An extraction method of blood vessel centerline based on boundary distance field |
| CN107067409A (en) * | 2017-05-09 | 2017-08-18 | 上海联影医疗科技有限公司 | A kind of blood vessel separation method and system |
| 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 |
| CN108805871A (en) * | 2018-06-14 | 2018-11-13 | 艾瑞迈迪医疗科技（北京）有限公司 | Blood-vessel image processing method, device, computer equipment and storage medium |
| 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 |
-
2019
- 2019-01-03 CN CN201910004369.2A patent/CN109754397B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101551862A (en) * | 2009-05-13 | 2009-10-07 | 西安电子科技大学 | An extraction method of blood vessel centerline based on boundary distance field |
| CN107067409A (en) * | 2017-05-09 | 2017-08-18 | 上海联影医疗科技有限公司 | A kind of blood vessel separation method and system |
| 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 |
| CN108805871A (en) * | 2018-06-14 | 2018-11-13 | 艾瑞迈迪医疗科技（北京）有限公司 | Blood-vessel image processing method, device, computer equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| KARL KRISSIAN 等: "Model Based Detection of tubular structures in 3Dimages", 《COMPUTER VISION AND IMAGE UNDERSTANDING》 * |
| 王振东: "肺实质分割与管腔路径提取算法的设计与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111640124A (en) * | 2020-05-25 | 2020-09-08 | 浙江同花顺智能科技有限公司 | Blood vessel extraction method, device, equipment and storage medium |
| CN113888690A (en) * | 2021-10-19 | 2022-01-04 | 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 |
| CN114708259A (en) * | 2022-05-24 | 2022-07-05 | 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 |
| 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 |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109754397B (en) | 2021-02-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109754397A (en) | Extracting method, device, terminal device and the storage medium of vessel segment center path | |
| CN111008984B (en) | Automatic contour line drawing method for normal organ in medical image | |
| EP3552550B1 (en) | Machine-learning based contrast agent administration | |
| CN107038728B (en) | Contour automated determination based on iterative reconstruction | |
| US20200320697A1 (en) | Method, system, and device for lung lobe segmentation, model training, model construction and segmentation | |
| CN102715906B (en) | Method and system for 3D cardiac motion estimation from single scan of c-arm angiography | |
| EP2620909B1 (en) | Method, system and computer readable medium for automatic segmentation of a medical image | |
| CN107203741A (en) | Vessel extraction method, device and its system | |
| Grove et al. | From CT to NURBS: contour fitting with B-spline curves | |
| JP2019500960A (en) | Coronary aneurysm segmentation with cardiac model guide | |
| CN116503607B (en) | CT image segmentation method and system based on deep learning | |
| US8050470B2 (en) | Branch extension method for airway segmentation | |
| US20120209108A1 (en) | System and Method for Treatment Planning of Organ Disease at the Functional and Anatomical Levels | |
| CN106952264B (en) | Method and device for cutting three-dimensional medical target | |
| CN113012118B (en) | Image processing method and image processing apparatus | |
| CN113192069A (en) | Semantic segmentation method and device for tree structure in three-dimensional tomography image | |
| Torrents-Barrena et al. | TTTS-STgan: stacked generative adversarial networks for TTTS fetal surgery planning based on 3D ultrasound | |
| CN115300809B (en) | Image processing method and device, computer equipment and storage medium | |
| CN109410170A (en) | Image processing method, device and equipment | |
| Kock et al. | Hepatic artery segmentation with 3D convolutional neural networks | |
| CN111161241B (en) | Liver image identification method, electronic equipment and storage medium | |
| CN110364238B (en) | Machine learning based contrast management | |
| US20240070855A1 (en) | Method and System of Calculating the Cross-section Area and Included Angle of Three-dimensional Blood Vessel Branch | |
| KR20240007124A (en) | How to generate rare medical images to train deep learning algorithms | |
| Prakash et al. | Deep learning-based head and neck segmentation in CT angiography |
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 |