CN109118489B - Coronary artery position detection method and system - Google Patents
Coronary artery position detection method and system Download PDFInfo
- Publication number
- CN109118489B CN109118489B CN201811152412.1A CN201811152412A CN109118489B CN 109118489 B CN109118489 B CN 109118489B CN 201811152412 A CN201811152412 A CN 201811152412A CN 109118489 B CN109118489 B CN 109118489B
- Authority
- CN
- China
- Prior art keywords
- coronary artery
- fracture
- myocardial
- pixel
- preset
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—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
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention provides a coronary artery position detection method and a system, wherein the method comprises the following steps: obtaining a plurality of scan images of a heart and generating a three-dimensional image of the heart based on the plurality of scan images; extracting a coronary artery partition body and a myocardial partition body in the three-dimensional image; selecting a first coronary artery partition body, and determining at least one fracture part based on the selected first coronary artery partition body; judging whether the fracture is located in the myocardial segmentation body, if so, locating the coronary artery in the myocardium; if the fracture is not located within the myocardial segment, then the coronary artery is not located within the myocardium. Since the appearance of blood vessels in the myocardium on CT images is usually non-signal, coronary arteries growing in the myocardium are not easily detected using CT scanning. The position of the coronary artery is detected by judging whether the fracture part exists in the myocardial segmentation body, and the detection accuracy is improved.
Description
Technical Field
The invention relates to the technical field of medical images and medical detection, in particular to a coronary artery position detection method and system.
Background
The coronary artery is the artery supplying blood to the heart, originates in the aortic sinus at the root of the aorta, divides into two branches, and runs on the surface of the heart. The position of coronary artery growth is generally detected by using CT scanning, and because the representation of blood vessels in the heart muscle on CT images is generally without signals, the detection of coronary arteries growing in the heart muscle by using CT scanning is difficult.
Disclosure of Invention
In view of the above, the present invention provides a method and a system for detecting coronary artery, which improve the accuracy of detecting the position of the coronary artery.
In a first aspect, an embodiment of the present invention provides a coronary artery position detection method, including:
obtaining a plurality of scan images of a heart and generating a three-dimensional image of the heart based on the plurality of scan images; extracting a coronary artery partition body and a myocardial partition body in the three-dimensional image; selecting a first coronary artery partition body, and determining at least one fracture part based on the selected first coronary artery partition body; judging whether the fracture is located in the myocardial segmentation body, if so, locating the coronary artery in the myocardium; if the fracture is not located within the myocardial segment, then the coronary artery is not located within the myocardium. With reference to the first aspect, an embodiment of the present invention provides a first possible implementation manner of the first aspect, wherein extracting the coronary artery partition and the myocardial partition includes: determining a coronary artery characteristic image based on the weight in a preset coronary artery neural network model and the gray value of the three-dimensional image; determining a myocardial feature image based on the weight in a preset myocardial neural network model and the gray value of the three-dimensional image; and extracting the coronary artery characteristic image and the myocardial characteristic image which are higher than a preset confidence coefficient to obtain the coronary artery segmentation body and the myocardial segmentation body. With reference to the first aspect, an embodiment of the present invention provides a second possible implementation manner of the first aspect, where the step of selecting a first coronary artery partition includes: selecting a second coronary artery partition body which is communicated with the aorta and has the volume larger than a first preset threshold value; acquiring a first pixel coordinate of a first endpoint at the edge of the second coronary artery partition body and a second pixel coordinate of a second endpoint beside the first endpoint; converting the first pixel coordinate and the second pixel coordinate into a first physical coordinate and a second physical coordinate; the distance between the first physical coordinate and the second physical coordinate is greater than a preset constraint distance, the volume of the coronary artery partition body where the second pixel coordinate is located is greater than a second preset threshold value, the coronary artery partition body where the second pixel coordinate is located is the first coronary artery partition body, and the first preset threshold value is greater than the second preset threshold value.
With reference to the first aspect, an embodiment of the present invention provides a third possible implementation manner of the first aspect, where the step of determining the fracture includes: scanning the first coronary artery segmentation body according to a preset scanning sequence, judging whether a first mark of a current scanning pixel is the same as second marks of a plurality of scanned neighbor pixels, and if the first mark is the same as the second marks, not positioning the current scanning pixel at the edge of the fracture; if the first mark is different from the second mark, the currently scanned pixel is located at the edge of the fracture.
With reference to the first aspect, an embodiment of the present invention provides a fourth possible implementation manner of the first aspect, wherein the step of determining whether the fracture is located in the myocardial segment includes:
reducing the confidence level of the fracture; if the coronary artery segment is extracted at the fracture, the fracture is not in the myocardium.
With reference to the first aspect, an embodiment of the present invention provides a fifth possible implementation manner of the first aspect, where the step of determining whether the fracture is located in the myocardial segment further includes: acquiring a third pixel coordinate of a third endpoint at one end of the edge of the fracture and a fourth pixel coordinate of a fourth endpoint at the other end of the edge of the fracture; extracting a coronary artery with a preset length at the corresponding third pixel coordinate in the first coronary artery partition body; if the extracted coronary artery is not located within the myocardial segment, the fracture is located within the myocardium; if the extracted coronary artery is located within the myocardial segment, the fracture is not located within the myocardium.
With reference to the fifth possible implementation manner of the first aspect, an embodiment of the present invention provides a sixth possible implementation manner of the first aspect, where the determining whether the extracted coronary artery is located in the myocardium segmentation body includes: acquiring a fifth pixel coordinate of a fifth endpoint at one end of the extracted preset-length coronary artery edge and a sixth pixel coordinate of a sixth endpoint at the other end of the extracted preset-length coronary artery edge; checking whether the corresponding fifth pixel coordinate and the sixth pixel coordinate are in the myocardial partition body, if the pixel coordinate is in the myocardial partition body, the extracted coronary artery with the preset length is positioned in the myocardial partition body; if the pixel coordinate is not in the myocardium segmentation body, the coronary artery with the preset length is not located in the myocardium segmentation body.
In a second aspect, an embodiment of the present invention further provides a coronary artery position detection system, including: a scanning module for obtaining a plurality of scan images of a heart of a patient and generating a three-dimensional image of the heart based on the plurality of scan images; the image extraction module is used for extracting a coronary artery segmentation body and a myocardial segmentation body in the three-dimensional image; the detection module is used for selecting a first coronary artery partition body and determining at least one fracture part based on the selected first coronary artery partition body; the judging module is used for judging whether the fracture is positioned in the myocardial segmentation body or not, and if the fracture is positioned in the myocardial segmentation body, the coronary artery is positioned in the myocardium; if the fracture is not located within the myocardial segment, then the coronary artery is not located within the myocardium.
With reference to the second aspect, an embodiment of the present invention provides a first possible implementation manner of the second aspect, where the image extraction module is specifically configured to: determining a coronary artery characteristic image based on the weight in a preset coronary artery neural network model and the gray value of the three-dimensional image; determining a myocardial feature image based on the weight in a preset myocardial neural network model and the gray value of the three-dimensional image; and extracting the coronary artery characteristic image and the myocardial characteristic image which are higher than a preset confidence coefficient to obtain the coronary artery segmentation body and the myocardial segmentation body.
With reference to the second aspect, an embodiment of the present invention provides a second possible implementation manner of the second aspect, where the detection module is specifically configured to: scanning the first coronary artery segmentation body according to a preset scanning sequence, judging whether a first mark of a current scanning pixel is the same as second marks of a plurality of scanned neighbor pixels, and if the first mark is the same as the second marks, not positioning the current scanning pixel at the edge of the fracture; if the first marker is different from the second marker, the currently scanned pixel has no connectivity with a plurality of adjacent pixels scanned previously, and the currently scanned pixel is located at the edge of the fracture.
According to the coronary artery position detection method and system provided by the embodiment of the invention, a plurality of scanning images of a heart are obtained, and a three-dimensional image of the heart is generated based on the plurality of scanning images; extracting a coronary artery partition body and a myocardial partition body in the three-dimensional image; selecting a first coronary artery partition body, and determining at least one fracture part based on the selected first coronary artery partition body; judging whether the fracture is located in the myocardial segmentation body, if so, locating the coronary artery in the myocardium; if the fracture is not located within the myocardial segment, then the coronary artery is not located within the myocardium. In the prior art, since the representation of the blood vessels in the myocardium on CT images is usually signal-free, it is difficult to detect the coronary arteries growing in the myocardium using CT scanning. The position of the coronary artery is detected by judging whether the fracture part exists in the myocardial segmentation body, so that the accuracy of detecting the position of the coronary artery is improved.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
Fig. 1 shows a flowchart of a coronary artery position detection method provided by an embodiment of the invention;
FIG. 2 is a flow chart of a method for extracting coronary artery segmentations and myocardial segmentations in a three-dimensional image according to an embodiment of the invention;
FIG. 3 is a flow chart illustrating a method for selecting a first coronary artery partition according to an embodiment of the present invention;
FIG. 4 illustrates a flow chart of a method of determining a fracture provided by an embodiment of the present invention;
FIG. 5 is a flow chart illustrating a method of determining whether a fracture is located within a myocardial segment as provided by an embodiment of the present invention;
FIG. 6 is a flow chart illustrating another method for determining whether a fracture is located within a myocardial segment according to an embodiment of the present invention;
FIG. 7 illustrates a flow chart of a method of determining whether an extracted coronary artery is located within a myocardial segment as provided by an embodiment of the present invention;
fig. 8 is a schematic structural diagram illustrating a coronary artery position detection system according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present invention without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the invention provides a method and a system for detecting a coronary artery position, which specifically comprise the following steps S101-S104 as shown in FIG. 1:
s101, obtaining a plurality of scanning images of a heart, and generating a three-dimensional image of the heart based on the plurality of scanning images.
The heart is scanned by CT (Computed Tomography) to obtain a plurality of two-dimensional scan images. The image is based on Pixels, which refer to basic codes of basic original pigments and their gray levels, and the resolution of the image is usually expressed in units of PPI (pixel Per Inch, the number of Pixels Per Inch) of Pixels. In the program, the two-dimensional image is stored in a two-dimensional array form, and the three-dimensional image is stored in a three-dimensional array form. Specifically, the first subscript in the two-dimensional array refers to the row of the array, and the second subscript refers to the column of the array; in the image, the number of rows of the array corresponds to the height of the image, and the number of columns corresponds to the width of the image.
Therefore, the coordinates (u, v) of each pixel in each scanned image and the current scanned image are w, which jointly form the coordinates (u, v, w) of each pixel in the three-dimensional image, and the pixel coordinates are sent to the three-dimensional array for storage, so as to generate the three-dimensional image of the heart.
S102, extracting a coronary artery segmentation body and a myocardial segmentation body in the three-dimensional image.
Optionally, as shown in fig. 2, the step S102 specifically includes the following steps S201 to S203:
s201, determining a coronary artery characteristic image based on the weight in the preset coronary artery neural network model and the gray value of the three-dimensional image.
And (3) placing the three-dimensional image into a preset coronary artery neural network model, calculating the gray value of the three-dimensional image and the weight obtained by the training model, and generating an image based on the output prediction data, namely the coronary artery characteristic image.
S202, determining a myocardial feature image based on the weight in the preset myocardial neural network model and the gray value of the three-dimensional image.
The weights obtained in training the myocardial neural network model are different from those of the coronary neural network model, and other steps are the same, so that the detailed description is omitted here.
And S203, extracting the coronary artery characteristic image and the myocardial characteristic image which are higher than the preset confidence coefficient to obtain a coronary artery segmentation body and a myocardial segmentation body.
The same predetermined confidence may be employed in image extraction of the coronary artery feature image and the myocardial feature image.
The binarization of the image is to set the gray value of a pixel point on the image to be 0 or 1, that is, the whole image presents an obvious black and white effect. The 256 brightness level gray scale image is selected by a preset confidence degree to obtain a binary image which can still reflect the whole and local characteristics of the image. All pixels with the gray levels larger than or equal to the preset confidence coefficient are judged to belong to the specific object, and the gray level value of the pixels is 1; otherwise, the pixel points are excluded from the object region, the gray value is 0, and the background or the exceptional object region is represented. In digital image processing, a binary image plays a very important role, and firstly, the binarization of the image is beneficial to further processing of the image, so that the image is simple, the data volume is reduced, and the outline of an interested target can be highlighted. Secondly, the processing and analysis of the binary image are carried out, firstly, the gray level image is binarized to obtain a binarized image.
S103, selecting a first coronary artery segmentation body, and determining at least one fracture part based on the selected first coronary artery segmentation body.
Optionally, as shown in fig. 3, the selecting the first coronary artery partition in step S103 specifically includes the following steps S301 to S304:
s301, selecting a second coronary artery segmentation body which is communicated with the aorta and has the volume larger than a first preset threshold value.
S302, a first pixel coordinate of a first endpoint at the edge of a second coronary artery segmentation body and a second pixel coordinate of a second endpoint beside the first endpoint are obtained.
S303, converting the first pixel coordinate and the second pixel coordinate into a first physical coordinate and a second physical coordinate.
And establishing a pixel coordinate system u-v-w by taking the upper left corner of the image as an origin and taking a pixel as a unit. The abscissa u and the ordinate v of a pixel are the number of columns and the number of rows in the image array, respectively. Since (u, v) represents only the number of columns and rows of pixels and the location of the pixels in the image is not expressed in physical units, we also establish the image coordinate system x-y-z in physical units (e.g., millimeters). An intersection point of an optical axis of the camera and an image plane (generally located at the center of the image plane, also called a principal point (principal point) of the image) is defined as an origin O1 of the coordinate system, an x axis is parallel to a u axis, a y axis is parallel to a v axis, and assuming that (u0, v0) represents coordinates of O1 in the u-v coordinate system, dx and dy represent physical dimensions of each pixel on a horizontal axis x and a vertical axis y, respectively, then the following relationships exist between coordinates of each pixel in the image in the u-v coordinate system and coordinates in the x-y coordinate system, as shown in formula (1), formula (2) and formula (3):
u = u/dx + v0 equation (1)
v = v/dy + v0 formula (2)
w = z/dz + v0 formula (3)
Where we assume the unit in the physical coordinate system is mm, then dx is in mm/pixel. Then the unit of x/dx is a pixel, i.e., a pixel as the unit of u.
S304, the distance between the first physical coordinate and the second physical coordinate is larger than a preset constraint distance, the volume of the coronary artery segmentation body where the second pixel coordinate is located is larger than a second preset threshold value, the coronary artery segmentation body where the second pixel coordinate is located is a first coronary artery segmentation body, and the first preset threshold value is larger than the second preset threshold value.
The first end point and the second end point have a certain distance, and the constraint distance is set for reducing the interference of factors such as noise and the like and ensuring the reliability of the obtained first coronary artery segmentation body.
Optionally, as shown in fig. 4, the determining the fracture in step S103 specifically includes the following steps S401 to S402:
s401, scanning the first coronary artery segmentation body according to a preset scanning sequence. The preset scanning sequence can be from left to right and from top to bottom.
S402, judging whether a first mark of a current scanning pixel is the same as second marks of a plurality of scanned neighbor pixels, if so, not positioning the current scanning pixel at the edge of the fracture; if the first mark is different from the second mark, the currently scanned pixel is located at the edge of the fracture.
An image after binarization processing often contains a plurality of areas which need to be extracted respectively through marks. A simple and effective way to mark regions in a segmented image is to check the connectivity of each pixel to its neighbors.
In the binary image, the pixel value of the background region is 0, and the pixel value of the target region is 1. Assuming that the first coronary segment is scanned from left to right, top to bottom, marking the pixel currently being scanned requires checking its connectivity to the several neighbor pixels scanned before it. There are two cases of 4 communication and 8 communication, and the present embodiment describes the case of 4 communication.
Consider the case of 4 connectivity. The image is scanned pixel by pixel. If the current pixel value is 0, the scanning position is moved to the next scanning position. If the current pixel has a value of 1, two adjacent pixels to its left and top (which must be scanned before the current pixel) are examined. There are four cases of combinations of these two pixel values and labels to consider:
first, their pixel values are all 0. At this point the pixel is given a new label indicating the start of a new connected component.
Second, only one pixel value in between them is 1. The label of the current pixel at this time = the label of the pixel value 1.
Third, they all have a pixel value of 1 and are labeled the same. The label of the current pixel at this time = the label.
Fourth, they have a pixel value of 1 and are labeled differently. The smaller value of which is assigned to the current pixel.
And then back from the other edge to the starting pixel of the region. And executing the four judging steps respectively every time of backtracking. This ensures that all connected domains are marked. And then different colors are given to different marks or the marks are added with frames to finish the marking.
S104, judging whether the fracture is positioned in the myocardial partition body, and if the fracture is positioned in the myocardial partition body, positioning the coronary artery in the myocardium; if the fracture is not located in the heart muscle segment, the coronary artery is not located in the heart muscle.
Alternatively, as shown in fig. 5, the step S104 of determining whether the fracture is located in the myocardial segment specifically includes the following steps S501 to S502:
s501, the confidence of the fracture is reduced.
S502, if the coronary artery segment is extracted at the fracture, the fracture is not in the myocardium.
Because the gray value in the original three-dimensional image is low, the data output by the network cannot be detected by adopting the original confidence coefficient, and the result can be obtained only by needing lower confidence coefficient when the image of the coronary artery segmentation body obtained by the first extraction is represented as a fracture. Therefore, when the confidence of the fracture is reduced and the coronary artery segmentation body image is extracted, the fracture is not in the myocardium, namely the segment of coronary artery is not in the myocardium.
In a preferred embodiment, the grey scale value of the fracture is 45, and the image of the fracture can be extracted after the confidence is reduced from 60 to 30.
Further, as shown in fig. 6, the step S104 of determining whether or not the fracture is located in the myocardial segment may specifically include the following steps S601 to S603:
s601, obtaining a third pixel coordinate of a third endpoint at one end of the edge of the fracture and a fourth pixel coordinate of a fourth endpoint at the other end of the edge of the fracture.
S602, extracting the coronary artery with the preset length at the corresponding third pixel coordinate in the first coronary artery partition body.
S603, if the extracted coronary artery is not positioned in the myocardial segmentation body, the fracture position is positioned in the myocardium; if the extracted coronary artery is located in the myocardial segment, the fracture is not located in the myocardium.
Due to the calculation deviation of the coronary artery neural network model or other reasons, the partial image of the extracted coronary artery segmentation body is displayed as a fracture. To avoid this, it is determined whether the fracture is within the myocardium segmentation body by determining whether a preset length of coronary artery beside the fracture is within the myocardium segmentation body. If the calculation of the coronary artery neural network model is correct, the extracted coronary artery with the preset length is not positioned in the myocardial segmentation body, and the fracture part is positioned in the myocardial segmentation body; if the deviation is calculated by the coronary artery neural network model, the extracted coronary artery with the preset length is positioned in the myocardial segmentation body, and the fracture part is not positioned in the myocardial segmentation body. Wherein the predetermined length may be 1/2 or 1/3 of the length of the break.
Still further, as shown in fig. 7, the step S603 of determining whether the extracted coronary artery is located in the myocardium divided body specifically includes the following steps S701 to S702:
s701, acquiring a fifth pixel coordinate of a fifth endpoint at one end of the extracted preset-length coronary artery edge and a sixth pixel coordinate of a sixth endpoint at the other end of the extracted preset-length coronary artery edge.
S702, checking whether the corresponding fifth pixel coordinate and the sixth pixel coordinate are in the myocardium segmentation body, and if the pixel coordinates are in the myocardium segmentation body, extracting a coronary artery with a preset length to be positioned in the myocardium segmentation body; if the pixel coordinate is not in the myocardium segmentation body, extracting that the coronary artery with the preset length is not in the myocardium segmentation body.
Fig. 8 shows a schematic structural diagram of the coronary artery position detection system provided in the embodiment of the present invention, where the system includes a scanning module, an image extraction module, a detection module, and a determination module, the scanning module is configured to obtain multiple scanning images of a heart, and generate a three-dimensional image of the heart based on the multiple scanning images; the image extraction module is used for extracting a coronary artery segmentation body and a myocardial segmentation body in the three-dimensional image; the detection module is used for selecting a first coronary artery partition body and determining at least one fracture part based on the selected first coronary artery partition body; the judging module is used for judging whether the fracture position is located in the myocardial segmentation body, and if the fracture position is located in the myocardial segmentation body, the coronary artery is located in the myocardium; if the fracture is not located in the heart muscle segment, the coronary artery is not located in the heart muscle.
The image extraction module is specifically used for determining a coronary artery feature image based on the weight in the preset coronary artery neural network model and the gray value of the three-dimensional image; determining a myocardial feature image based on the weight in the preset myocardial neural network model and the gray value of the three-dimensional image; and extracting the coronary artery characteristic image and the myocardial characteristic image which are higher than the preset confidence coefficient to obtain a coronary artery segmentation body and a myocardial segmentation body.
And (3) placing the three-dimensional image into a preset coronary artery neural network model, calculating the gray value of the three-dimensional image and the weight obtained by the training model, and generating an image based on the output prediction data, namely the coronary artery characteristic image. The weights obtained in training the myocardial neural network model are different from those of the coronary neural network model, and other steps are the same, so that the detailed description is omitted here.
The same predetermined confidence may be employed in image extraction of the coronary artery feature image and the myocardial feature image.
The binarization of the image is to set the gray value of a pixel point on the image to be 0 or 1, that is, the whole image presents an obvious black and white effect. The 256 brightness level gray scale image is selected by a preset confidence degree to obtain a binary image which can still reflect the whole and local characteristics of the image. All pixels with the gray levels larger than or equal to the preset confidence coefficient are judged to belong to the specific object, and the gray level value of the pixels is 1; otherwise, the pixel points are excluded from the object region, the gray value is 0, and the background or the exceptional object region is represented. In digital image processing, a binary image plays a very important role, and firstly, the binarization of the image is beneficial to further processing of the image, so that the image is simple, the data volume is reduced, and the outline of an interested target can be highlighted. Secondly, the processing and analysis of the binary image are carried out, firstly, the gray level image is binarized to obtain a binarized image.
The detection module is specifically configured to scan the first coronary artery segmentation body according to a preset scanning order, determine whether a first mark of a currently scanned pixel is the same as second marks of a plurality of previously scanned neighboring pixels, and if the first mark is the same as the second marks, determine that the currently scanned pixel is not located at an edge of a fracture; if the first marker is different from the second marker, the currently scanned pixel has no connectivity with a plurality of previously scanned neighboring pixels, and the currently scanned pixel is located at the edge of the fracture.
An image after binarization processing often contains a plurality of areas which need to be extracted respectively through marks. A simple and effective way to mark regions in a segmented image is to check the connectivity of each pixel to its neighbors.
In the binary image, the pixel value of the background region is 0, and the pixel value of the target region is 1. Assuming that the first coronary segment is scanned from left to right, top to bottom, marking the pixel currently being scanned requires checking its connectivity to the several neighbor pixels scanned before it. There are two cases of 4 communication and 8 communication, and the present embodiment describes the case of 4 communication.
Consider the case of 4 connectivity. The image is scanned pixel by pixel. If the current pixel value is 0, the scanning position is moved to the next scanning position. If the current pixel has a value of 1, two adjacent pixels to its left and top (which must be scanned before the current pixel) are examined. There are four cases of combinations of these two pixel values and labels to consider:
first, their pixel values are all 0. At this point the pixel is given a new label indicating the start of a new connected component.
Second, only one pixel value in between them is 1. The label of the current pixel at this time = the label of the pixel value 1.
Third, they all have a pixel value of 1 and are labeled the same. The label of the current pixel at this time = the label.
Fourth, they have a pixel value of 1 and are labeled differently. The smaller value of which is assigned to the current pixel.
And then back from the other edge to the starting pixel of the region. And executing the four judging steps respectively every time of backtracking. This ensures that all connected domains are marked. And then different colors are given to different marks or the marks are added with frames to finish the marking.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments provided by the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus once an item is defined in one figure, it need not be further defined and explained in subsequent figures, and moreover, the terms "first", "second", "third", etc. are used merely to distinguish one description from another and are not to be construed as indicating or implying relative importance.
Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present invention, which are used for illustrating the technical solutions of the present invention and not for limiting the same, and the protection scope of the present invention is not limited thereto, although the present invention is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the present invention in its spirit and scope. Are intended to be covered by the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (7)
1. A coronary artery position detection method, comprising:
obtaining a plurality of scan images of a heart and generating a three-dimensional image of the heart based on the plurality of scan images;
extracting a coronary artery partition body and a myocardial partition body in the three-dimensional image;
selecting a first coronary artery partition body, and determining at least one fracture part based on the selected first coronary artery partition body;
judging whether the fracture is located in the myocardial segmentation body, if so, locating the coronary artery in the myocardium; if the fracture is not located within the myocardial segment, then the coronary artery is not located within the myocardium;
the extracting the coronary artery partition and the myocardial partition includes:
determining a coronary artery characteristic image based on the weight in a preset coronary artery neural network model and the gray value of the three-dimensional image;
determining a myocardial feature image based on the weight in a preset myocardial neural network model and the gray value of the three-dimensional image;
extracting the coronary artery characteristic image and the myocardial characteristic image which are higher than a preset confidence coefficient to obtain a coronary artery segmentation body and a myocardial segmentation body;
the selecting the first coronary artery segmentation body comprises the following steps:
selecting a second coronary artery partition body which is communicated with the aorta and has the volume larger than a first preset threshold value;
acquiring a first pixel coordinate of a first endpoint at the edge of the second coronary artery partition body and a second pixel coordinate of a second endpoint beside the first endpoint;
converting the first pixel coordinate and the second pixel coordinate into a first physical coordinate and a second physical coordinate;
and under the condition that the distance between the first physical coordinate and the second physical coordinate is greater than a preset constraint distance and the volume of the coronary artery segmentation body where the second pixel coordinate is located is greater than a second preset threshold, the coronary artery segmentation body where the second pixel coordinate is located is the first coronary artery segmentation body, wherein the first preset threshold is greater than the second preset threshold.
2. The method of claim 1, wherein the step of determining the fracture comprises: scanning the first coronary artery segmentation body according to a preset scanning sequence, judging whether a first mark of a current scanning pixel is the same as second marks of a plurality of scanned neighbor pixels, and if the first mark is the same as the second marks, not positioning the current scanning pixel at the edge of the fracture; if the first mark is different from the second mark, the currently scanned pixel is located at the edge of the fracture.
3. The method of claim 1, wherein the step of determining whether the fracture is located within the myocardium segmentation comprises:
reducing the confidence level of the fracture;
if the coronary artery segment is extracted at the fracture, the fracture is not in the myocardium.
4. The method of claim 1, wherein the step of determining whether the fracture is located within the myocardium segmentation further comprises:
acquiring a third pixel coordinate of a third endpoint at one end of the edge of the fracture and a fourth pixel coordinate of a fourth endpoint at the other end of the edge of the fracture;
extracting a coronary artery with a preset length at the corresponding third pixel coordinate in the first coronary artery partition body;
if the extracted coronary artery is not located within the myocardial segment, the fracture is located within the myocardium; if the extracted coronary artery is located within the myocardial segment, the fracture is not located within the myocardium.
5. The method of claim 4, wherein determining whether the extracted coronary artery is located within the myocardium segmentation comprises:
acquiring a fifth pixel coordinate of a fifth endpoint at one end of the extracted preset-length coronary artery edge and a sixth pixel coordinate of a sixth endpoint at the other end of the extracted preset-length coronary artery edge;
checking whether the corresponding fifth pixel coordinate and the sixth pixel coordinate are in the myocardial partition body, if the pixel coordinate is in the myocardial partition body, the extracted coronary artery with the preset length is positioned in the myocardial partition body; if the pixel coordinate is not in the myocardium segmentation body, the coronary artery with the preset length is not located in the myocardium segmentation body.
6. A coronary artery position detection system, comprising:
a scanning module for obtaining a plurality of scan images of a heart and generating a three-dimensional image of the heart based on the plurality of scan images;
the image extraction module is used for extracting a coronary artery segmentation body and a myocardial segmentation body in the three-dimensional image;
the detection module is used for selecting a first coronary artery partition body and determining at least one fracture part based on the selected first coronary artery partition body;
the judging module is used for judging whether the fracture is positioned in the myocardial segmentation body or not, and if the fracture is positioned in the myocardial segmentation body, the coronary artery is positioned in the myocardium; if the fracture is not located within the myocardial segment, then the coronary artery is not located within the myocardium;
the image extraction module is specifically configured to:
determining a coronary artery characteristic image based on the weight in a preset coronary artery neural network model and the gray value of the three-dimensional image;
determining a myocardial feature image based on the weight in a preset myocardial neural network model and the gray value of the three-dimensional image;
extracting the coronary artery characteristic image and the myocardial characteristic image which are higher than a preset confidence coefficient to obtain a coronary artery segmentation body and a myocardial segmentation body;
the detection module, when selecting the first coronary artery partition body, comprises:
selecting a second coronary artery partition body which is communicated with the aorta and has the volume larger than a first preset threshold value;
acquiring a first pixel coordinate of a first endpoint at the edge of the second coronary artery partition body and a second pixel coordinate of a second endpoint beside the first endpoint;
converting the first pixel coordinate and the second pixel coordinate into a first physical coordinate and a second physical coordinate;
and under the condition that the distance between the first physical coordinate and the second physical coordinate is greater than a preset constraint distance and the volume of the coronary artery segmentation body where the second pixel coordinate is located is greater than a second preset threshold, the coronary artery segmentation body where the second pixel coordinate is located is the first coronary artery segmentation body, wherein the first preset threshold is greater than the second preset threshold.
7. The system of claim 6, wherein the detection module is specifically configured to:
scanning the first coronary artery segmentation body according to a preset scanning sequence, judging whether a first mark of a current scanning pixel is the same as second marks of a plurality of scanned neighbor pixels, and if the first mark is the same as the second marks, not positioning the current scanning pixel at the edge of the fracture; if the first marker is different from the second marker, the currently scanned pixel has no connectivity with a plurality of adjacent pixels scanned previously, and the currently scanned pixel is located at the edge of the fracture.
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 CN109118489A (en) | 2019-01-01 |
| CN109118489B true 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) |
Families Citing this family (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 (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8315812B2 (en) * | 2010-08-12 | 2012-11-20 | Heartflow, Inc. | Method and system for patient-specific modeling of blood flow |
| US9129417B2 (en) * | 2012-02-21 | 2015-09-08 | Siemens Aktiengesellschaft | Method and system for coronary artery centerline extraction |
| US9934566B2 (en) * | 2015-07-14 | 2018-04-03 | Siemens Healthcare Gmbh | 3-D vessel tree surface reconstruction method |
-
2018
- 2018-09-29 CN CN201811152412.1A patent/CN109118489B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
|---|
| Computational analysis of stenosis geometry effects on right coronary hemodynamics;Maria Vittoria Caruso等;《2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)》;20151105;981-984 * |
| New analysis tools for the comprehensive assessment of the coronary arteries and myocardial viability in CT data sets;C. Kuehnel等;《2008 Computers in Cardiology》;20090113;733-736 * |
| 双源CT冠状动脉成像诊断心肌桥的临床价值;黄久荣等;《实用医学临床杂志》;20080930;第5卷(第5期);53-54 * |
| 影像学对心肌桥－壁血管的诊断与临床意义;蒋瑾等;《实用医院临床杂志》;20130131;第10卷(第1期);169-171 * |
| 肺结节计算机辅助诊断系统中分割算法研究及实现;香世杰;《中国优秀硕士学位论文全文数据库 医药卫生科技辑 （月刊 ）》;20111215;第2011年卷(第12期);E072-36 * |
| 面向冠脉狭窄病变辅助诊断的图像处理关键技术研究;朱文博;《中国博士学位论文全文数据库 信息科技辑（月刊）》;20170215;第2017年卷(第2期);I138-181 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109118489A (en) | 2019-01-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8447383B2 (en) | System and method for providing 2-dimensional computerized-tomography image corresponding to 2-dimensional ultrasound image | |
| US8787647B2 (en) | Image matching device and patient positioning device using the same | |
| CN100401978C (en) | Integrated image registration for cardiac nuclear magnetic resonance data perfusion | |
| US9949643B2 (en) | Automatic visualization of regional functional parameters of left ventricle from cardiac imaging | |
| EP2091004A2 (en) | Correcting for geometrical perspective distortion | |
| US11810293B2 (en) | Information processing device, information processing method, and computer program | |
| CN104700062A (en) | Method and equipment for identifying two-dimension code | |
| CN102754128A (en) | Marker identification and processing in x-ray images | |
| JP4964171B2 (en) | Target region extraction method, apparatus, and program | |
| CN102770752A (en) | Method for tracking X-ray markers in serial CT projection images | |
| CN100473141C (en) | Image angle detection device and scan line interpolation device having the same | |
| CN113112490B (en) | Three-dimensional medical image mark point extraction method and system | |
| CN111932552B (en) | Aorta modeling method and device | |
| CN109118489B (en) | Coronary artery position detection method and system | |
| CN114445499A (en) | Checkerboard angular point automatic extraction method, system, equipment and medium | |
| CN114445498A (en) | Depth camera calibration method, system, device and medium | |
| CN116957935A (en) | Side-scan sonar stripe image stitching method based on path line constraint | |
| JP6546385B2 (en) | IMAGE PROCESSING APPARATUS, CONTROL METHOD THEREOF, AND PROGRAM | |
| CN107615333B (en) | Image speckle processing method | |
| JP7019104B2 (en) | Threshold learning method | |
| CN112545566A (en) | Fetal neck diaphragmatic layer measuring method and device | |
| JP7480997B2 (en) | Image processing device, image processing method, and program | |
| JP4346620B2 (en) | Image processing apparatus, image processing method, and image processing program | |
| EP4270311A1 (en) | Image identification program, image identification method, image identification device | |
| CN201927054U (en) | Corrected figure searching device based on dynamic template |
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 | ||
| 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. |