CN109118489A - Detect the method and system of intra-myocardial vessels - Google Patents
Detect the method and system of intra-myocardial vessels Download PDFInfo
- Publication number
- CN109118489A CN109118489A CN201811152412.1A CN201811152412A CN109118489A CN 109118489 A CN109118489 A CN 109118489A CN 201811152412 A CN201811152412 A CN 201811152412A CN 109118489 A CN109118489 A CN 109118489A
- Authority
- CN
- China
- Prior art keywords
- coronary artery
- dividing body
- image
- myocardium
- breaking part
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
- G06T2207/10012—Stereo images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
Abstract
The present invention provides a kind of coronary artery method for detecting position and systems, wherein this method comprises: obtaining multiple scan images of heart, and the 3-D image of the heart is generated based on scan image described in multiple；Extract the coronary artery dividing body and myocardium dividing body in the 3-D image；The first coronary artery dividing body is chosen, and at least one breaking part is determined based on the first coronary artery dividing body of selection；Judge whether the breaking part is located in the myocardium dividing body, if the breaking part is located in the myocardium dividing body, coronary artery is located in cardiac muscle；If the breaking part is not located in the myocardium dividing body, coronary artery is not located in the cardiac muscle.Since performance of the intramyocardial blood vessel on CT image is usually no signal, it is not easy to detect to be grown in intramyocardial coronary artery using CT scan.The application, to detect position coronarius, improves the accuracy of detection by judging that breaking part whether there is in myocardium dividing body.
Description
Technical field
The present invention relates to medical images and technical field of medical detection, examine in particular to a kind of coronary artery position
Survey method and system.
Background technique
Coronary artery is supplied with the artery of heart blood, arises from aortic root aortic sinus, is divided to or so two, row in
Heart surface.CT scan detection coronary artery growth position is generally used, due to performance of the intramyocardial blood vessel on CT image
Usually no signal, therefore, being grown in intramyocardial coronary artery using CT scan detection is more difficult thing.
Summary of the invention
In view of this, improving detection hat the purpose of the present invention is to provide a kind of coronary artery detection method and system
The accuracy of shape artery position.
In a first aspect, the embodiment of the invention provides a kind of coronary artery method for detecting position, comprising:
Multiple scan images of heart are obtained, and generate the 3-D image of the heart based on scan image described in multiple；
Extract the coronary artery dividing body and myocardium dividing body in the 3-D image；The first coronary artery dividing body is chosen, and is based on
The the first coronary artery dividing body chosen determines at least one breaking part；Judge whether the breaking part is located at the cardiac muscle segmentation
In vivo, if the breaking part is located in the myocardium dividing body, coronary artery is located in cardiac muscle；If the breaking part is not located at
In the cardiac muscle dividing body, then coronary artery is not located in the cardiac muscle.With reference to first aspect, the embodiment of the invention provides
The possible embodiment of the first of one side, wherein extract the coronary artery dividing body and the myocardium dividing body includes:
Based on the gray value of weight and the 3-D image in preset coronary artery neural network model, coronary artery spy is determined
Levy image；Based on the gray value of weight and the 3-D image in preset myocardium neural network model, determine that cardiac muscle is special
Levy image；The coronary artery characteristic image and the myocardial features image for being higher than predetermined confidence level are extracted, the hat is obtained
Shape artery segmentation body and the myocardium dividing body.With reference to first aspect, the embodiment of the invention provides second of first aspect
Possible embodiment, wherein the step of the first coronary artery dividing body of the selection, comprising: choose it is being connected to aorta,
Volume is greater than the second coronary artery dividing body of the first predetermined threshold；Obtain the second coronary artery dividing body edge first
First pixel coordinate of endpoint and the second pixel coordinate of the second endpoint beside the first end point；First pixel is sat
Mark and second pixel coordinate are converted to the first physical coordinates and the second physical coordinates；First physical coordinates and described the
Distance between two physical coordinates is greater than default constraint distance, and the body of the coronary artery dividing body where second pixel coordinate
Product is greater than the second predetermined threshold, and the coronary artery dividing body where second pixel coordinate is first coronary artery segmentation
Body, wherein first predetermined threshold is greater than second predetermined threshold.
With reference to first aspect, the embodiment of the invention provides the third possible embodiments of first aspect, wherein really
The step of fixed breaking part includes: to be scanned according to preset scanning sequency to the first coronary artery dividing body, is sentenced
First label of disconnected Current Scan pixel mark whether with the second of the multiple neighbor pixels being scanned before it is identical, if described
First label is identical as second label, then the pixel of Current Scan is not located at the edge of the breaking part；If described
One label is different from second label, then the pixel of Current Scan is located at the edge of the breaking part.
With reference to first aspect, the embodiment of the invention provides the 4th kind of possible embodiments of first aspect, wherein institute
State the step for judging whether the breaking part is located in the myocardium dividing body, comprising:
Reduce the confidence level of the breaking part；It is described if extracting the coronary artery dividing body in the breaking part
Breaking part is not in the cardiac muscle.
With reference to first aspect, the embodiment of the invention provides the 5th kind of possible embodiments of first aspect, wherein institute
State the step for judging whether the breaking part is located in the myocardium dividing body, further includes: obtain the breaking part edge one
4th pixel coordinate of the 4th endpoint of the third pixel coordinate and breaking part edge other end of the third endpoint at end；?
In the first coronary artery dividing body at the corresponding third pixel coordinate, the coronary artery of preset length is extracted；If institute
The coronary artery for stating extraction is not located in the myocardium dividing body, and the breaking part is located in the cardiac muscle；If the extraction
The coronary artery is located in the myocardium dividing body, and the breaking part is not located in the cardiac muscle.
The 5th kind of possible embodiment with reference to first aspect, the embodiment of the invention provides the 6th kind of first aspect
Possible embodiment, wherein judge whether the coronary artery of the extraction is located in the myocardium dividing body, comprising: obtain
5th pixel coordinate of the 5th endpoint of coronary artery edge one end of the preset length of the extraction and the extraction it is pre-
If the 6th pixel coordinate of the 6th endpoint of the coronary artery edge other end of length；Check that corresponding 5th pixel is sat
Mark and the 6th pixel coordinate whether in the myocardium dividing body, if the pixel coordinate in the myocardium dividing body,
The coronary artery for extracting preset length is located in the myocardium dividing body；If the pixel coordinate is not in the cardiac muscle segmentation
In body, the coronary artery for extracting preset length is not located in the myocardium dividing body.
Second aspect, the embodiment of the invention also provides a kind of coronary artery position detecting systems, which is characterized in that packet
Include: scan module generates the heart for obtaining multiple scan images of patient's heart, and based on multiple described scan images
3-D image；Image zooming-out module, for extracting the coronary artery dividing body in the 3-D image and myocardium dividing body；It visits
Module is surveyed, for choosing the first coronary artery dividing body, and at least one is determined based on the first coronary artery dividing body of selection
Breaking part；Judgment module, for judging whether the breaking part is located in the myocardium dividing body, if the breaking part is located at institute
It states in myocardium dividing body, then coronary artery is located in cardiac muscle；If the breaking part is not located in the myocardium dividing body, coronal
Artery is not located in the cardiac muscle.
In conjunction with second aspect, the embodiment of the invention provides the first possible embodiments of second aspect, wherein institute
Image zooming-out module is stated to be specifically used for: based in preset coronary artery neural network model weight and the 3-D image
Gray value, determine coronary artery characteristic image；Based on the weight and the three-dimensional in preset myocardium neural network model
The gray value of image determines myocardial features image；It extracts and is higher than the coronary artery characteristic image of predetermined confidence level and described
Myocardial features image obtains the coronary artery dividing body and the myocardium dividing body.
In conjunction with second aspect, the embodiment of the invention provides second of possible embodiments of second aspect, wherein institute
It states detecting module to be specifically used for: the first coronary artery dividing body is scanned according to preset scanning sequency, judgement is worked as
Preceding scanning element first label mark whether with the second of the multiple neighbor pixels being scanned before it is identical, if described first
Label is identical as second label, then the pixel of Current Scan is not located at the edge of the breaking part；If first mark
Note is different from second label, then the pixel of Current Scan is not present with the multiple neighbor pixels being scanned before and is connected to
Property, then the pixel of Current Scan is located at the edge of the breaking part.
Coronary artery method for detecting position provided in an embodiment of the present invention and system obtain multiple scan images of heart,
And the 3-D image of the heart is generated based on scan image described in multiple；Extract the coronary artery segmentation in the 3-D image
Body and myocardium dividing body；The first coronary artery dividing body is chosen, and is determined at least based on the first coronary artery dividing body of selection
One breaking part；Judge whether the breaking part is located in the myocardium dividing body, if the breaking part is located at the cardiac muscle point
It cuts in vivo, then coronary artery is located in cardiac muscle；If the breaking part is not located in the myocardium dividing body, coronary artery not position
In in the cardiac muscle.Conventionally, as performance of the intramyocardial blood vessel on CT image is usually no signal, because
This, being grown in intramyocardial coronary artery using CT scan detection is more difficult thing.And the application is disconnected by judgement
Place is split with the presence or absence of in myocardium dividing body, to detect position coronarius, improves the accurate of detection coronary artery position
Degree.
To enable the above objects, features and advantages of the present invention to be clearer and more comprehensible, preferred embodiment is cited below particularly, and cooperate
Appended attached drawing, is described in detail below.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only certain embodiments of the present invention, therefore is not construed as pair
The restriction of range for those of ordinary skill in the art without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings.
Fig. 1 shows the flow chart of coronary artery method for detecting position provided by the embodiment of the present invention；
Fig. 2 shows the coronary artery dividing bodies in extraction 3-D image provided by the embodiment of the present invention to divide with cardiac muscle
The flow chart of the method for body；
Fig. 3 shows the flow chart that the method for the first coronary artery dividing body is chosen provided by the embodiment of the present invention；
Fig. 4 shows the flow chart that the method for breaking part is determined provided by the embodiment of the present invention；
Fig. 5, which is shown, judges whether breaking part is located at the stream that cardiac muscle divides intracorporal method provided by the embodiment of the present invention
Cheng Tu；
Fig. 6 shows another kind provided by the embodiment of the present invention and judges whether breaking part is located at cardiac muscle and divides intracorporal side
The flow chart of method；
Fig. 7 show judge provided by the embodiment of the present invention coronary artery extracted whether be located at cardiac muscle divide it is intracorporal
The flow chart of method；
Fig. 8 shows a kind of structural schematic diagram of coronary artery position detecting system provided by the embodiment of the present 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
Middle attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is only
It is a part of the embodiment of the present invention, instead of all the embodiments.The present invention being usually described and illustrated herein in the accompanying drawings is real
The component for applying example can be arranged and be designed with a variety of different configurations.Therefore, of the invention to what is provided in the accompanying drawings below
The detailed description of embodiment is not intended to limit the range of claimed invention, but is merely representative of selected reality of the invention
Apply example.Based on the embodiment of the present invention, those skilled in the art institute obtained without making creative work
There are other embodiments, shall fall within the protection scope of the present invention.
The embodiment of the invention provides a kind of coronary artery method for detecting position and systems, as shown in Figure 1, specifically include with
Lower step S101~S104:
S101 obtains multiple scan images of heart, and the three-dimensional of the heart is generated based on scan image described in multiple
Image.
Heart is scanned using CT (Computed Tomography, CT scan), multiple two dimensions is obtained and sweeps
Trace designs picture.Wherein, image is using pixel as basic unit, and pixel refers to the basic coding of basic protochrome and its gray scale, usually with
Pixel per inch PPI (Pixels Per Inch, the number of pixels that per inch is possessed) is unit to indicate image resolution ratio
Size.In a program, two dimensional image is stored in the form of a two-dimensional array, and 3-D image is stored in the form of a three-dimensional array.
Specifically, first subscript in two-dimensional array refers to the row of array, and second subscript refers to the column of array；In image
In, the height of the line number correspondence image of array, and the width of columns correspondence image.
Therefore, coordinate (u, v) and the Current Scan image for obtaining each pixel in every scan image are w,
The coordinate (u, v, w) for collectively forming each pixel in 3-D image, which is sent in three-dimensional array and is stored,
Generate the 3-D image of heart.
S102 extracts coronary artery dividing body and myocardium dividing body in 3-D image.
Optionally, as shown in Fig. 2, specifically including following steps S201~S203 in step S102:
S201 is determined based on the gray value of weight and 3-D image in preset coronary artery neural network model
Coronary artery characteristic image.
3-D image is put into preset coronary artery neural network model, the gray value and training pattern of 3-D image
Obtained weight does operation, and the image generated of the prediction data based on output is coronary artery characteristic image.
S202 determines cardiac muscle based on the gray value of weight and 3-D image in preset myocardium neural network model
Characteristic image.
The weighted of weight and coronary artery neural network model obtained in training cardiac muscle neural network model, other
Step is same as above, and therefore, not repeat them here.
S203 extracts the coronary artery characteristic image and myocardial features image for being higher than predetermined confidence level, obtains coronary artery
Dividing body and myocardium dividing body.
When carrying out image zooming-out to coronary artery characteristic image and myocardial features image, same predetermined confidence can be used
Degree.
The binaryzation of image is to set 0 or 1 for the gray value of the pixel on image, that is, whole image is presented
Apparent black and white effect out.The gray level image of 256 brightness degrees chosen by predetermined confidence level to obtain still can be anti-
Reflect the whole binary image with local feature of image.The pixel that all gray scales are greater than or equal to predetermined confidence level is judged as belonging to
In certain objects, gray value 1,；Otherwise these pixels are excluded other than object area, gray value 0, indicate background
Or the object area of exception.In Digital Image Processing, bianry image is played a very important role, firstly, the two of image
Value is conducive to being further processed for image, becomes image simply, and data volume reduces, and can highlight interested target
Profile.Secondly, to carry out the processing and analysis of bianry image, a Binary Sketch of Grey Scale Image is first had to, binary image is obtained.
S103 chooses the first coronary artery dividing body, and determines at least one based on the first coronary artery dividing body of selection
A breaking part.
Optionally, as shown in figure 3, choosing the first coronary artery dividing body in step S103 specifically includes following steps S301
~S304:
S301 chooses the second coronary artery dividing body that be connected to aorta, volume is greater than the first predetermined threshold.
S302 is obtained beside the first pixel coordinate and the first end point of the second coronary artery dividing body edge first end point
The second endpoint the second pixel coordinate.
First pixel coordinate and the second pixel coordinate are converted to the first physical coordinates and the second physical coordinates by S303.
It is pixel coordinate system u-v-w of the origin foundation as unit of pixel by the image upper left corner.The abscissa u of pixel and vertical
Coordinate v is the columns and place line number where in its image array respectively.Since (u, v) only represents the columns and row of pixel
Number, and the not useful physical unit in the position of pixel in the picture shows, so, we will also establish with physical unit
The image coordinate system x-y-z that (such as millimeter) indicates.The intersection point of camera optical axis and the plane of delineation (is normally in the plane of delineation
At the heart, the principal point (principal point) of also referred to as image is defined as the origin O1 of the coordinate system, and x-axis is parallel with u axis, y
Axis is parallel with v axis, it is assumed that (u0, v0) represents coordinate of the O1 under u-v coordinate system, and dx and dy respectively indicate each pixel in horizontal axis
Physical size on x and longitudinal axis y, then coordinate of each pixel in u-v coordinate system in image and the seat in x-y coordinate system
All there is following relationship between mark, as shown in formula (1), formula (2), formula (3):
U=u/dx+v0 formula (1)
V=v/dy+v0 formula (2)
W=z/dz+v0 formula (3)
Wherein, it will be assumed that the unit in physical coordinates system is millimeter, then the unit of dx are as follows: millimeter/pixel.So x/
The unit of dx is exactly pixel, i.e., is all pixel as the unit of u.
S304, the first physical coordinates between the second physical coordinates at a distance from be greater than default constraint distance, and the second pixel is sat
The volume of coronary artery dividing body where marking is greater than the second predetermined threshold, the coronary artery dividing body where the second pixel coordinate
For the first coronary artery dividing body, wherein the first predetermined threshold is greater than the second predetermined threshold.
There are certain distances between first end point and the second endpoint, and the purpose of setting constraint distance is to reduce noise etc.
The interference of factor, the reliability of the first coronary artery dividing body guaranteed.
Optionally, as shown in figure 4, determining that breaking part specifically includes following steps S401~S402 in step S103:
S401 is scanned the first coronary artery dividing body according to preset scanning sequency.Wherein, preset scanning is suitable
Sequence can be for from left to right, from top to bottom.
S402 judges the first label of Current Scan pixel and the second label of the multiple neighbor pixels being scanned before
Whether identical, if the first label is identical as the second label, the pixel of Current Scan is not located at the edge of breaking part；If first
Label is different from the second label, then the pixel of Current Scan is located at the edge of breaking part.
Multiple regions are usually contained after piece image binary conversion treatment, need to extract them respectively by marking.
The simple and effective method in each region is to check the connectivity of each pixel pixel adjacent thereto in image after label segmentation.
In bianry image, the pixel value of background area is 0, and the pixel value of target area is 1.Assuming that the first coronary artery
Dividing body from left to right, is scanned from the top down, and pixel currently scanned to be marked to need to check it and before it
The connectivity for several neighbor pixels being scanned.There are 4 connections to be connected to two kinds of situations with 8, the present embodiment to 4 connection situations into
Row explanation.
Consider the situation of 4 connections.Image is scanned pixel-by-pixel.If current pixel value is 0, move to next
The position of scanning.If current pixel value is 1, checking two adjacent pixels of its left side and top, (the two pixels are bound to
It is scanned before current pixel).The combination of the two pixel values and label will consider there are four types of situation:
The first, their pixel value is all 0.One new label of the pixel is given at this time, indicates a new connected domain
Beginning.
Second, only one pixel value is 1 among them.The label that label=pixel value of current pixel is 1 at this time.
The third, their pixel value is all 1 and label is identical.The label of current pixel=label at this time.
4th kind, their pixel value is 1 and label is different.Lesser value therein is assigned to current pixel.
Later since another side trace back to region until pixel.Backtracking executes aforementioned four judgement step respectively again every time
Suddenly.It can guarantee that all connected domains are all labeled in this way to come out.Later again by assigning different colors to different labels
Or label is can be completed into plus frame in it.
S104, judges whether breaking part is located in myocardium dividing body, coronal dynamic if breaking part is located in myocardium dividing body
Arteries and veins is located in cardiac muscle；If breaking part is not located in myocardium dividing body, coronary artery is not located in cardiac muscle.
Optionally, as shown in figure 5, judge in step S104 breaking part whether be located in myocardium dividing body specifically include it is following
Step S501~S502:
S501 reduces the confidence level of breaking part.
S502, if extracting coronary artery dividing body in breaking part, breaking part is not in cardiac muscle.
Since the gray value in original 3-D image is lower, prevent the data of network output are using original confidence level from examining
It surveys, shows as breaking part in extracting obtained coronary artery dividing body image for the first time, lower confidence level is needed to be likely to
Obtain result.So when extracting coronary artery dividing body image, illustrating that this breaking part does not exist when the confidence level for reducing breaking part
In cardiac muscle, i.e., this section of coronary artery be not in cardiac muscle.
One preferred embodiment, the gray value of breaking part are 45, by confidence level from 60 be reduced to 30 after, the breaking part can be extracted
Image.
Further, as shown in fig. 6, judging whether breaking part is located in myocardium dividing body in step S104 and specifically further including
Following steps S601~S603:
S601 obtains the third pixel coordinate and the breaking part edge other end of the third endpoint of breaking part edge one end
The 4th endpoint the 4th pixel coordinate.
S602 in the first coronary artery dividing body at corresponding third pixel coordinate, extracts the coronal dynamic of preset length
Arteries and veins.
S603, if the coronary artery extracted is not located in myocardium dividing body, breaking part is located in cardiac muscle；If that extracts is coronal
Artery is located in myocardium dividing body, and breaking part is not located in cardiac muscle.
Since coronary artery neural network model calculates deviation or other reasons, lead to that coronary artery segmentation should be extracted
The parts of images of body, is shown as breaking part.In order to avoid this kind of situation, by judging the preset length beside breaking part
Coronary artery whether be in myocardium dividing body, to determine whether the breaking part is in myocardium dividing body.If coronary artery
Neural network model calculating is errorless, and the coronary artery of extracted preset length is not located in myocardium dividing body, and breaking part position
In in myocardium dividing body；If coronary artery neural network model calculates deviation, the coronary artery of extracted preset length is located at
In myocardium dividing body, then breaking part is not located in myocardium dividing body.Wherein, preset length can for the breaking part length 1/2 or
Person 1/3.
Still further, as shown in fig. 7, judging whether the coronary artery extracted is located in myocardium dividing body in step S603
Specifically include following steps S701~S702:
S701, obtain the 5th endpoint of coronary artery edge one end of the preset length of extraction the 5th pixel coordinate and
6th pixel coordinate of the 6th endpoint of the coronary artery edge other end of the preset length of extraction.
S702 checks corresponding 5th pixel coordinate and the 6th pixel coordinate whether in myocardium dividing body, if pixel is sat
It is marked in myocardium dividing body, the coronary artery for extracting preset length is located in myocardium dividing body；If pixel coordinate is not in cardiac muscle point
It cuts in body, the coronary artery for extracting preset length is not located in myocardium dividing body.
Coronary artery position detecting system provided by the embodiment of the present invention, Fig. 8 show the embodiment of the present invention and are provided
Coronary artery position detecting system structural schematic diagram, the system include scan module, image zooming-out module, detecting module and
Judgment module, scan module are used to obtain multiple scan images of heart, and the three-dimensional of heart is generated based on multiple scan images
Image；Image zooming-out module is used to extract coronary artery dividing body and myocardium dividing body in 3-D image；Detecting module is used for
The first coronary artery dividing body is chosen, and at least one breaking part is determined based on the first coronary artery dividing body of selection；Judgement
Module is for judging whether breaking part is located in myocardium dividing body, if breaking part is located in myocardium dividing body, coronary artery position
In in cardiac muscle；If breaking part is not located in myocardium dividing body, coronary artery is not located in cardiac muscle.
Image zooming-out module is specifically used for, based on the weight and three-dimensional figure in preset coronary artery neural network model
The gray value of picture determines coronary artery characteristic image；Based on the weight and three-dimensional figure in preset myocardium neural network model
The gray value of picture determines myocardial features image；Extract the coronary artery characteristic image and myocardial features figure for being higher than predetermined confidence level
Picture obtains coronary artery dividing body and myocardium dividing body.
3-D image is put into preset coronary artery neural network model, the gray value and training pattern of 3-D image
Obtained weight does operation, and the image generated of the prediction data based on output is coronary artery characteristic image.Training cardiac muscle
The weighted of weight obtained in neural network model and coronary artery neural network model, other steps are same as above, therefore are not existed
This is repeated.
When carrying out image zooming-out to coronary artery characteristic image and myocardial features image, same predetermined confidence can be used
Degree.
The binaryzation of image is to set 0 or 1 for the gray value of the pixel on image, that is, whole image is presented
Apparent black and white effect out.The gray level image of 256 brightness degrees chosen by predetermined confidence level to obtain still can be anti-
Reflect the whole binary image with local feature of image.The pixel that all gray scales are greater than or equal to predetermined confidence level is judged as belonging to
In certain objects, gray value 1；Otherwise these pixels are excluded other than object area, gray value 0, indicate background
Or the object area of exception.In Digital Image Processing, bianry image is played a very important role, firstly, the two of image
Value is conducive to being further processed for image, becomes image simply, and data volume reduces, and can highlight interested target
Profile.Secondly, to carry out the processing and analysis of bianry image, a Binary Sketch of Grey Scale Image is first had to, binary image is obtained.
Detecting module is specifically used for, and is scanned according to preset scanning sequency to the first coronary artery dividing body, judgement
Current Scan pixel first label mark whether with the second of the multiple neighbor pixels being scanned before it is identical, if first mark
Note is identical as the second label, then the pixel of Current Scan is not located at the edge of breaking part；If the first label marks not with second
Together, then connectivity is not present in the pixel of Current Scan and the multiple neighbor pixels being scanned before, then the pixel of Current Scan
Positioned at the edge of breaking part.
Multiple regions are usually contained after piece image binary conversion treatment, need to extract them respectively by marking.
The simple and effective method in each region is to check the connectivity of each pixel pixel adjacent thereto in image after label segmentation.
In bianry image, the pixel value of background area is 0, and the pixel value of target area is 1.Assuming that the first coronary artery
Dividing body from left to right, is scanned from the top down, and pixel currently scanned to be marked to need to check it and before it
The connectivity for several neighbor pixels being scanned.There are 4 connections to be connected to two kinds of situations with 8, the present embodiment to 4 connection situations into
Row explanation.
Consider the situation of 4 connections.Image is scanned pixel-by-pixel.If current pixel value is 0, move to next
The position of scanning.If current pixel value is 1, checking two adjacent pixels of its left side and top, (the two pixels are bound to
It is scanned before current pixel).The combination of the two pixel values and label will consider there are four types of situation:
The first, their pixel value is all 0.One new label of the pixel is given at this time, indicates a new connected domain
Beginning.
Second, only one pixel value is 1 among them.The label that label=pixel value of current pixel is 1 at this time.
The third, their pixel value is all 1 and label is identical.The label of current pixel=label at this time.
4th kind, their pixel value is 1 and label is different.Lesser value therein is assigned to current pixel.
Later since another side trace back to region until pixel.Backtracking executes aforementioned four judgement step respectively again every time
Suddenly.It can guarantee that all connected domains are all labeled in this way to come out.Later again by assigning different colors to different labels
Or label is can be completed into plus frame in it.
In embodiment provided by the present invention, it should be understood that disclosed device and method, it can be by others side
Formula is realized.The apparatus embodiments described above are merely exemplary, for example, the division of the unit, only one kind are patrolled
Function division is collected, there may be another division manner in actual implementation, in another example, multiple units or components can combine or can
To be integrated into another system, or some features can be ignored or not executed.Another point, shown or discussed is mutual
Coupling, direct-coupling or communication connection can be INDIRECT COUPLING or communication link by some communication interfaces, device or unit
It connects, can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
In addition, each functional unit in embodiment provided by the invention can integrate in one processing unit, it can also
To be that each unit physically exists alone, can also be integrated in one unit with two or more units.
It, can be with if the function is realized in the form of SFU software functional unit and when sold or used as an independent product
It is stored in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, server or network equipment etc.) it performs all or part of the steps of the method described in the various embodiments of the present invention.
And storage medium above-mentioned includes: that USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
The various media that can store program code such as reservoir (RAM, Random Access Memory), magnetic or disk.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, does not then need that it is further defined and explained in subsequent attached drawing, in addition, term " the
One ", " second ", " third " etc. are only used for distinguishing description, are not understood to indicate or imply relative importance.
Finally, it should be noted that embodiment described above, only a specific embodiment of the invention, to illustrate the present invention
Technical solution, rather than its limitations, scope of protection of the present invention is not limited thereto, although with reference to the foregoing embodiments to this hair
It is bright to be described in detail, those skilled in the art should understand that: anyone skilled in the art
In the technical scope disclosed by the present invention, it can still modify to technical solution documented by previous embodiment or can be light
It is readily conceivable that variation or equivalent replacement of some of the technical features；And these modifications, variation or replacement, do not make
The essence of corresponding technical solution is detached from the spirit and scope of technical solution of the embodiment of the present invention.Should all it cover in protection of the invention
Within the scope of.Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. a kind of coronary artery method for detecting position characterized by comprising
Multiple scan images of heart are obtained, and generate the 3-D image of the heart based on scan image described in multiple；
Extract the coronary artery dividing body and myocardium dividing body in the 3-D image；
The first coronary artery dividing body is chosen, and at least one breaking part is determined based on the first coronary artery dividing body of selection；
Judge whether the breaking part is located in the myocardium dividing body, if the breaking part is located in the myocardium dividing body,
Then coronary artery is located in cardiac muscle；If the breaking part is not located in the myocardium dividing body, coronary artery is not located at described
In cardiac muscle.
2. the method according to claim 1, wherein extracting the coronary artery dividing body and the cardiac muscle segmentation
Body includes:
Based on the gray value of weight and the 3-D image in preset coronary artery neural network model, determine coronal dynamic
Arteries and veins characteristic image；
Based on the gray value of weight and the 3-D image in preset myocardium neural network model, myocardial features figure is determined
Picture；
The coronary artery characteristic image and the myocardial features image for being higher than predetermined confidence level are extracted, is obtained described coronal dynamic
Arteries and veins dividing body and the myocardium dividing body.
3. the method according to claim 1, wherein the first coronary artery dividing body of the selection, comprising:
Choose the second coronary artery dividing body that be connected to aorta, volume is greater than the first predetermined threshold；
It obtains beside the first pixel coordinate and the first end point of the second coronary artery dividing body edge first end point
The second endpoint the second pixel coordinate；
First pixel coordinate and second pixel coordinate are converted into the first physical coordinates and the second physical coordinates；
It is greater than default constraint distance, and second picture at a distance from first physical coordinates are between second physical coordinates
In the case that the volume of coronary artery dividing body where plain coordinate is greater than the second predetermined threshold, where second pixel coordinate
Coronary artery dividing body be the first coronary artery dividing body, wherein to be greater than described second predetermined for first predetermined threshold
Threshold value.
4. the method according to claim 1, wherein the step of determining the breaking part includes: according to preset
Scanning sequency is scanned the first coronary artery dividing body, judges that the first of Current Scan pixel marks and swept before
The second of the multiple neighbor pixels retouched mark whether it is identical, if it is described first label it is identical as second label, currently
The pixel of scanning is not located at the edge of the breaking part；If first label is different from second label, currently sweep
The pixel retouched is located at the edge of the breaking part.
5. judging whether the breaking part is located at the cardiac muscle point the method according to claim 1, wherein described
Cut internal step, comprising:
Reduce the confidence level of the breaking part；
If extracting the coronary artery dividing body in the breaking part, the breaking part is not in the cardiac muscle.
6. judging whether the breaking part is located at the cardiac muscle point the method according to claim 1, wherein described
Cut internal step, further includes:
Obtain the third pixel coordinate and the breaking part edge other end of the third endpoint of breaking part edge one end
The 4th endpoint the 4th pixel coordinate；
In the first coronary artery dividing body at the corresponding third pixel coordinate, the coronal dynamic of preset length is extracted
Arteries and veins；
If the coronary artery of the extraction is not located in the myocardium dividing body, the breaking part is located in the cardiac muscle；If institute
The coronary artery for stating extraction is located in the myocardium dividing body, and the breaking part is not located in the cardiac muscle.
7. according to the method described in claim 6, it is characterized in that, judging whether the coronary artery of the extraction is located at the heart
In flesh dividing body, comprising:
Obtain the 5th pixel coordinate of the 5th endpoint of coronary artery edge one end of the preset length of the extraction and described
6th pixel coordinate of the 6th endpoint of the coronary artery edge other end of the preset length of extraction；
Corresponding 5th pixel coordinate and the 6th pixel coordinate are checked whether in the myocardium dividing body, if described
In the myocardium dividing body, the coronary artery for extracting preset length is located in the myocardium dividing body pixel coordinate；If
For the pixel coordinate not in the myocardium dividing body, the coronary artery for extracting preset length is not located at the cardiac muscle segmentation
In body.
8. a kind of coronary artery position detecting system characterized by comprising
Scan module generates the heart for obtaining multiple scan images of heart, and based on scan image described in multiple
3-D image；
Image zooming-out module, for extracting the coronary artery dividing body in the 3-D image and myocardium dividing body；
Detecting module is determined extremely for choosing the first coronary artery dividing body, and based on the first coronary artery dividing body of selection
A few breaking part；
Judgment module, for judging whether the breaking part is located in the myocardium dividing body, if the breaking part is positioned at described
In myocardium dividing body, then coronary artery is located in cardiac muscle；If the breaking part is not located in the myocardium dividing body, coronal dynamic
Arteries and veins is not located in the cardiac muscle.
9. system according to claim 8, which is characterized in that described image extraction module is specifically used for:
Based on the gray value of weight and the 3-D image in preset coronary artery neural network model, determine coronal dynamic
Arteries and veins characteristic image；
Based on the gray value of weight and the 3-D image in preset myocardium neural network model, myocardial features figure is determined
Picture；
The coronary artery characteristic image and the myocardial features image for being higher than predetermined confidence level are extracted, is obtained described coronal dynamic
Arteries and veins dividing body and the myocardium dividing body.
10. system according to claim 8, which is characterized in that the detecting module is specifically used for:
The first coronary artery dividing body is scanned according to preset scanning sequency, judges the first of Current Scan pixel
Label mark whether with the second of the multiple neighbor pixels being scanned before it is identical, if it is described first label with it is described second mark
Remember identical, then the pixel of Current Scan is not located at the edge of the breaking part；If first label and second label
Difference, then connectivity is not present with the multiple neighbor pixels being scanned before in the pixel of Current Scan, then the picture of Current Scan
Element is located at the edge of the breaking part.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811152412.1A CN109118489B (en) | 2018-09-29 | 2018-09-29 | Coronary artery position detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811152412.1A CN109118489B (en) | 2018-09-29 | 2018-09-29 | Coronary artery position detection method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109118489A true CN109118489A (en) | 2019-01-01 |
| CN109118489B CN109118489B (en) | 2020-12-11 |
Family
ID=64857604
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811152412.1A Active CN109118489B (en) | 2018-09-29 | 2018-09-29 | Coronary artery position detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109118489B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110680301A (en) * | 2019-09-18 | 2020-01-14 | 青岛市市立医院 | Coronary artery blood vessel flow measuring device and measuring method thereof |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130216110A1 (en) * | 2012-02-21 | 2013-08-22 | Siemens Aktiengesellschaft | Method and System for Coronary Artery Centerline Extraction |
| US20140355859A1 (en) * | 2010-08-12 | 2014-12-04 | Heartflow, Inc. | Method and system for patient-specific modeling of blood flow |
| CN105118056A (en) * | 2015-08-13 | 2015-12-02 | 重庆大学 | Coronary artery automatic extraction method based on three-dimensional morphology |
| CN106023202A (en) * | 2016-05-20 | 2016-10-12 | 苏州润心医疗科技有限公司 | Coronary artery fractional flow reserve calculation method based on heart CT image |
| US20170018116A1 (en) * | 2015-07-14 | 2017-01-19 | Siemens Medical Solutions Usa, Inc. | 3-d vessel tree surface reconstruction method |
| CN107330888A (en) * | 2017-07-11 | 2017-11-07 | 中国人民解放军第三军医大学 | Each chamber dividing method of dynamic heart based on CTA images |
| CN107545579A (en) * | 2017-08-30 | 2018-01-05 | 上海联影医疗科技有限公司 | A kind of cardiac segmentation method, equipment and storage medium |
| CN107563998A (en) * | 2017-08-30 | 2018-01-09 | 上海联影医疗科技有限公司 | Medical image cardiac image processing method |
| CN108171698A (en) * | 2018-02-12 | 2018-06-15 | 数坤（北京）网络科技有限公司 | A kind of method of automatic detection human heart Coronary Calcification patch |
-
2018
- 2018-09-29 CN CN201811152412.1A patent/CN109118489B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140355859A1 (en) * | 2010-08-12 | 2014-12-04 | Heartflow, Inc. | Method and system for patient-specific modeling of blood flow |
| US20160117816A1 (en) * | 2010-08-12 | 2016-04-28 | Heartflow, Inc. | Method and system for image processing to determine patient-specific blood flow characteristics |
| US20130216110A1 (en) * | 2012-02-21 | 2013-08-22 | Siemens Aktiengesellschaft | Method and System for Coronary Artery Centerline Extraction |
| US20170018116A1 (en) * | 2015-07-14 | 2017-01-19 | Siemens Medical Solutions Usa, Inc. | 3-d vessel tree surface reconstruction method |
| CN105118056A (en) * | 2015-08-13 | 2015-12-02 | 重庆大学 | Coronary artery automatic extraction method based on three-dimensional morphology |
| CN106023202A (en) * | 2016-05-20 | 2016-10-12 | 苏州润心医疗科技有限公司 | Coronary artery fractional flow reserve calculation method based on heart CT image |
| CN107330888A (en) * | 2017-07-11 | 2017-11-07 | 中国人民解放军第三军医大学 | Each chamber dividing method of dynamic heart based on CTA images |
| CN107545579A (en) * | 2017-08-30 | 2018-01-05 | 上海联影医疗科技有限公司 | A kind of cardiac segmentation method, equipment and storage medium |
| CN107563998A (en) * | 2017-08-30 | 2018-01-09 | 上海联影医疗科技有限公司 | Medical image cardiac image processing method |
| CN108171698A (en) * | 2018-02-12 | 2018-06-15 | 数坤（北京）网络科技有限公司 | A kind of method of automatic detection human heart Coronary Calcification patch |
Non-Patent Citations (6)
| Title |
|---|
| C. KUEHNEL等: "New analysis tools for the comprehensive assessment of the coronary arteries and myocardial viability in CT data sets", 《2008 COMPUTERS IN CARDIOLOGY》 * |
| MARIA VITTORIA CARUSO等: "Computational analysis of stenosis geometry effects on right coronary hemodynamics", 《2015 37TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC)》 * |
| 朱文博: "面向冠脉狭窄病变辅助诊断的图像处理关键技术研究", 《中国博士学位论文全文数据库 信息科技辑（月刊）》 * |
| 蒋瑾等: "影像学对心肌桥－壁血管的诊断与临床意义", 《实用医院临床杂志》 * |
| 香世杰: "肺结节计算机辅助诊断系统中分割算法研究及实现", 《中国优秀硕士学位论文全文数据库 医药卫生科技辑 （月刊 ）》 * |
| 黄久荣等: "双源CT冠状动脉成像诊断心肌桥的临床价值", 《实用医学临床杂志》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110680301A (en) * | 2019-09-18 | 2020-01-14 | 青岛市市立医院 | Coronary artery blood vessel flow measuring device and measuring method thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109118489B (en) | 2020-12-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3961484A1 (en) | Medical image segmentation method and device, electronic device and storage medium | |
| US8270696B2 (en) | Image slice segmentation using midpoints of contour anchor points | |
| US8447383B2 (en) | System and method for providing 2-dimensional computerized-tomography image corresponding to 2-dimensional ultrasound image | |
| CN108537784A (en) | A kind of CT figure pulmonary nodule detection methods based on deep learning | |
| US20130077870A1 (en) | Evaluation of edge direction information | |
| US11810293B2 (en) | Information processing device, information processing method, and computer program | |
| CN109753960A (en) | The underwater unnatural object detection method of isolated forest based on fractal theory | |
| CN106780495A (en) | Cardiovascular implantation support automatic detection and appraisal procedure and system based on OCT | |
| CN111160111B (en) | Human body key point detection method based on deep learning | |
| CN109977952A (en) | Candidate target detection method based on local maximum | |
| CN113112490A (en) | Three-dimensional medical image mark point extraction method and system | |
| CN109118489A (en) | Detect the method and system of intra-myocardial vessels | |
| KR100740031B1 (en) | Image processing method and contactless image input apparatus utilizing the method | |
| CN110580681A (en) | high-resolution cardiac motion pattern analysis device and method | |
| CN114445328A (en) | Medical image brain tumor detection method and system based on improved Faster R-CNN | |
| US8818124B1 (en) | Methods, apparatus, and systems for super resolution of LIDAR data sets | |
| CN109934906B (en) | Crude oil saturation acquisition method and device, computer equipment and storage medium | |
| CN115761882A (en) | Method, device and system for carrying and detecting contraband and storage medium | |
| JP7019104B2 (en) | Threshold learning method | |
| JP7382059B2 (en) | Image processing device, image processing method, and program | |
| JP6943357B2 (en) | Medical imaging device | |
| CN113643263A (en) | Identification method and system for upper limb bone positioning and forearm bone fusion deformity | |
| CN112634224A (en) | Focus detection method and device based on target image | |
| JP4346620B2 (en) | Image processing apparatus, image processing method, and image processing program | |
| Harikumar et al. | An effective approach to 3D stem modeling and branch-knot localization in multiscan TLS data |
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 | ||
| CP03 | Change of name, title or address |
Address after: 100120 rooms 303, 304, 305, 321 and 322, building 3, No. 11, Chuangxin Road, science and Technology Park, Changping District, Beijing Patentee after: Shukun (Beijing) Network Technology Co.,Ltd. Address before: Room 1801-156, 16 / F, building 1, yard 16, Guangshun South Street, Chaoyang District, Beijing Patentee before: SHUKUN (BEIJING) NETWORK TECHNOLOGY Co.,Ltd. |
|
| CP03 | Change of name, title or address |