CN113450322A - Method and device for judging origin abnormality of coronary artery - Google Patents
Method and device for judging origin abnormality of coronary artery Download PDFInfo
- Publication number
- CN113450322A CN113450322A CN202110692227.7A CN202110692227A CN113450322A CN 113450322 A CN113450322 A CN 113450322A CN 202110692227 A CN202110692227 A CN 202110692227A CN 113450322 A CN113450322 A CN 113450322A
- Authority
- CN
- China
- Prior art keywords
- coronary
- artery
- position information
- aorta
- coronary artery
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 210000004351 coronary vessel Anatomy 0.000 title claims abstract description 300
- 230000005856 abnormality Effects 0.000 title claims abstract description 76
- 238000000034 method Methods 0.000 title claims abstract description 49
- 210000000709 aorta Anatomy 0.000 claims abstract description 152
- 238000002586 coronary angiography Methods 0.000 claims abstract description 142
- 210000001367 artery Anatomy 0.000 claims abstract description 73
- 230000002159 abnormal effect Effects 0.000 claims abstract description 29
- 210000003291 sinus of valsalva Anatomy 0.000 claims description 89
- 210000001147 pulmonary artery Anatomy 0.000 claims description 66
- 230000004044 response Effects 0.000 claims description 21
- 238000001514 detection method Methods 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 abstract description 5
- 238000002583 angiography Methods 0.000 description 15
- 238000013528 artificial neural network Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 6
- 230000000747 cardiac effect Effects 0.000 description 5
- 238000002591 computed tomography Methods 0.000 description 5
- 210000002376 aorta thoracic Anatomy 0.000 description 4
- 238000003745 diagnosis Methods 0.000 description 4
- 239000008280 blood Substances 0.000 description 3
- 210000004369 blood Anatomy 0.000 description 3
- 210000004204 blood vessel Anatomy 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 210000000038 chest Anatomy 0.000 description 2
- 238000009499 grossing Methods 0.000 description 2
- 238000002595 magnetic resonance imaging Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 206010061060 Congenital coronary artery malformation Diseases 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 210000003484 anatomy Anatomy 0.000 description 1
- 210000000702 aorta abdominal Anatomy 0.000 description 1
- 210000001765 aortic valve Anatomy 0.000 description 1
- 208000014387 congenital coronary artery anomaly Diseases 0.000 description 1
- 239000002872 contrast media Substances 0.000 description 1
- 201000011639 coronary artery anomaly Diseases 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 210000002837 heart atrium Anatomy 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 210000005240 left ventricle Anatomy 0.000 description 1
- 210000004072 lung Anatomy 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000002685 pulmonary effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 210000000115 thoracic cavity Anatomy 0.000 description 1
- 230000032258 transport Effects 0.000 description 1
- 210000002620 vena cava superior Anatomy 0.000 description 1
- 230000002861 ventricular Effects 0.000 description 1
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
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/20—Drawing from basic elements, e.g. lines or circles
- G06T11/203—Drawing of straight lines or curves
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10088—Magnetic resonance imaging [MRI]
-
- 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
- G06T2207/30048—Heart; Cardiac
-
- 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 embodiment of the disclosure provides a method and a device for judging origin abnormality of coronary artery, wherein the method comprises the following steps: detecting a coronary angiography image, and acquiring artery position information in the coronary angiography image, wherein the artery position information at least comprises position information of an aorta and a central line of the coronary artery, the position information of the aorta is used for defining a region of the aorta in the coronary angiography image, and the central line is a curve representing the topological structure of the coronary artery; determining keypoints in the coronary angiography image based on the artery position information; and determining the origin abnormal condition of the coronary artery based on the position relation of the artery position information and the key point. The method can automatically determine the origin abnormal condition of the coronary artery, has quick calculation time and clear and convenient judgment, and is used for assisting a doctor in diagnosing the coronary artery.
Description
Technical Field
The present disclosure relates to the field of medical image processing technologies, and in particular, to a method and an apparatus for determining origin abnormality of coronary artery.
Background
The coronary artery is an artery for supplying blood to the heart and is divided into a left coronary artery and a right coronary artery, the main trunk of the coronary artery walks on the surface of the heart, the coronary artery is not a branch blood vessel, but is divided into a plurality of branches step by step like a trunk, and the branches wrap the whole heart. The coronary artery anatomical abnormality can be the inconsistency of the number, origin, running, termination and structure of the coronary arteries with the normal anatomical structure, namely the coronary artery anatomical abnormality can be considered. Among them, the abnormality of origin of coronary artery can be classified into coronary artery origin from pulmonary artery, coronary artery origin from aorta, sinus ostium origin abnormality, and multi-sinus origin.
In recent years, due to the widespread use of a means for non-invasively examining coronary arteries, examination of abnormality of coronary arteries has become convenient and easy. The method can be used for identifying the cardiac structures such as coronary arteries, aortic sinuses and the like by means of equipment such as CT (Computed Tomography) or MRI (Magnetic Resonance Imaging), the cardiac structures and the like are presented to doctors in a 3D mode, and the doctors judge images by combining own experiences.
Disclosure of Invention
In view of the above, the embodiments of the present disclosure provide a method and an apparatus for determining origin abnormality of at least one coronary artery.
In a first aspect, a method for determining origin abnormality of coronary artery is provided, the method comprising:
detecting a coronary angiography image, and acquiring artery position information in the coronary angiography image, wherein the artery position information at least comprises position information of an aorta and a central line of the coronary artery, the position information of the aorta is used for defining a region of the aorta in the coronary angiography image, and the central line is a curve representing the topological structure of the coronary artery;
determining keypoints in the coronary angiography image based on the artery position information;
and determining the origin abnormal condition of the coronary artery based on the position relation of the artery position information and the key point.
In a second aspect, there is provided an apparatus for determining origin abnormality of coronary artery, the apparatus including:
a detection module, configured to detect a coronary angiography image, and acquire artery position information in the coronary angiography image, where the artery position information includes at least position information of an aorta and a centerline of a coronary artery, the position information of the aorta is used to define a region of the aorta in the coronary angiography image, and the centerline is a curve representing a topology of the coronary artery;
a keypoint determination module for determining keypoints in the coronary angiography image based on the artery position information;
and the judging module is used for determining the origin abnormal condition of the coronary artery based on the position relation between the artery position information and the key point.
In a third aspect, an electronic device is provided, which includes a memory for storing computer instructions executable on a processor, and the processor is configured to implement the method for determining origin abnormality of coronary artery according to any embodiment of the present disclosure when executing the computer instructions.
In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, and the program, when executed by a processor, implements the method for determining origin abnormality of coronary artery according to any one of the embodiments of the present disclosure.
According to the method for judging origin abnormality of coronary artery provided by the technical scheme of the embodiment of the disclosure, the origin abnormality of the coronary artery can be automatically determined according to the position information of the aorta, the central line of the coronary artery and other artery position information on the obtained coronary artery angiography image, the key point is determined according to the artery position information, and the position relation between the artery position information and the key point, so that the calculation time is fast, the judgment is clear and convenient, and the diagnosis of a doctor on the coronary artery can be assisted.
Drawings
In order to more clearly illustrate one or more embodiments of the present disclosure or technical solutions in related arts, the drawings used in the description of the embodiments or related arts will be briefly described below, it is obvious that the drawings in the description below are only some embodiments described in one or more embodiments of the present disclosure, and other drawings can be obtained by those skilled in the art without inventive exercise.
Fig. 1 is a flowchart illustrating a method for determining origin abnormality of coronary artery according to an embodiment of the present disclosure;
FIG. 1A is an image of a certain cross-section in a coronary angiography image shown in an embodiment of the present disclosure;
FIG. 1B is a schematic diagram illustrating artery location information in a coronary angiography image according to an embodiment of the present disclosure;
fig. 1C is a schematic diagram of ascending aorta and pulmonary arteries in a coronary angiography image shown in an embodiment of the present disclosure;
fig. 1D is a schematic diagram illustrating a three-dimensional coronary artery segmentation in accordance with an embodiment of the present disclosure;
FIG. 1E is a schematic illustration of the aortic sinus in a coronary angiography image, shown in an embodiment of the present disclosure;
fig. 2 is a block diagram of an origin abnormality determination apparatus for coronary arteries according to an embodiment of the present disclosure;
fig. 3 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present disclosure.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present specification. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the specification, as detailed in the appended claims.
The terminology used in the description herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the description. As used in this specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It should be understood that although the terms first, second, third, etc. may be used herein to describe various information, these information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, the first information may also be referred to as second information, and similarly, the second information may also be referred to as first information, without departing from the scope of the present specification. The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination", depending on the context.
Abnormalities of coronary origin can be divided into coronary origin in the pulmonary arteries, coronary origin in the aorta, abnormalities of ostial origin and multi-sinus origin. Among them, the abnormality of sinus ostium can be further classified into the Left circumflex brance (LCX) abnormality originating from Right aortic sinus, the Left Coronary Artery (LCA) abnormality originating from Right aortic sinus, and the Right Coronary Artery (RCA) abnormality originating from Left aortic sinus.
Coronary artery origin is one of serious congenital coronary artery malformations, and mainly originates from pulmonary artery relatively frequently as LCA abnormality, RCA abnormality originates from pulmonary artery, LAD (Left anterior descending) or LCX abnormality originates from pulmonary artery, and coronary artery abnormality originates from right pulmonary artery is rare.
The coronary artery originates from any branch of the aortic digit RCA, LCA or LCX at a location outside the aortic sinus, including the high-level ostium, the low-level ostium and from the aortic sinus junction. Among these, the most common is the high-level opening. The coronary artery high position opening means that the opening of the left and right coronary arteries is obviously 1.0cm higher than the aortic sinus at the position of the ascending aorta.
The origin of the sinus ostia abnormality is mainly that LCA or other branches open into the right aortic sinus and RCA opens into the left aortic sinus. The origin of LCX in the right aortic sinus is a relatively common abnormality of origin.
The origin of multiple sinuses means that RCA and conical branches originate from the right aortic sinus simultaneously, or LCX and LAD originate from the left aortic sinus simultaneously.
As can be seen, the origin abnormality of the coronary artery is complex, and in view of this, the embodiments of the present disclosure provide at least one method for determining origin abnormality of the coronary artery, so as to perform comprehensive, accurate and fast determination on the origin of the coronary artery, assist a doctor in diagnosing the coronary artery, and help the doctor complete a coronary artery CT blood vessel imaging diagnosis report.
As shown in fig. 1, fig. 1 is a flowchart illustrating a method for determining origin abnormality of coronary artery according to an embodiment of the present disclosure, which may be performed by any computing-capable device, for example, a terminal device or a server or other processing device, and includes the following steps:
in step 102, a coronary angiography image is detected, and artery position information in the coronary angiography image is acquired.
In this embodiment, the coronary angiography image may be a three-dimensional CT cardiac angiography image of the subject. Before cardiac CT is performed on a subject, a contrast agent may be injected into the subject, a chest or a whole body of the subject is scanned by a scanning device, a coronary artery angiography image of the chest of the subject is obtained, and a cardiac structure of the subject, such as a coronary artery, an aorta, a pulmonary artery, an atrium, and a ventricle, may be displayed in the coronary artery angiography image. Fig. 1A shows an image of a certain cross section in a coronary angiography image.
The artery position information at least includes position information of an aorta and a center line of a coronary artery, and may further include position information of an aortic sinus, position information of a pulmonary artery, and the like. The position information of the aorta is used to define a region of the aorta in the coronary angiography image, and may be coordinate position information. The centerline is a curve that characterizes the topology of the coronary artery. The centerline coincides with the connectivity of the coronary arteries in space. Specifically, the centerline may be a curve along any portion of the coronary artery, for example, a curve along the center of the coronary artery, or a curve along the outer wall of the coronary artery.
The detection method of the coronary angiography image is not limited in this embodiment, and for example, the coronary angiography image may be detected by a neural network method, or may be detected by other methods.
Fig. 1B is a schematic diagram of artery position information in a coronary angiography image, where fig. 1B shows a position of artery position information determined by detecting the coronary angiography image on the transverse slice image shown in fig. 1A, where a region indicated by reference symbol L is a left sinus, a region indicated by reference symbol R is a right sinus, a region indicated by reference symbol a is an ascending aorta, a region indicated by reference symbol B is a pulmonary artery, and a bar-shaped region in a frame is a coronary artery.
In step 104, based on the artery location information, keypoints in the coronary angiography image are determined.
The key points in the coronary angiogram can be the starting points of the coronary arteries or can be points on the centerline. For example, the point where the centerline is connected with the root of the aorta can be determined as the starting point of the coronary artery according to the position information of the centerline and the aorta; for example, each point on the centerline can be directly determined as a key point according to the centerline.
In this embodiment, when the center line includes a left center line of the left coronary artery and a right center line of the right coronary artery, based on the position information of the center line and the aorta, a point where the left center line is connected to the root of the aorta may be determined as a left starting point of the left coronary artery, and a point where the right center line is connected to the root of the aorta may be determined as a right starting point of the right coronary artery.
The key points can also be determined by the skilled person as desired.
In step 106, the origin abnormality of the coronary artery is determined based on the position relationship between the artery position information and the key point.
According to the position relation between different artery position information and different key points, the origin abnormal conditions of different coronary arteries can be determined. The following examples are given to illustrate the determination process of the origin abnormal condition of four coronary arteries, and in practical implementation, the four determination processes in the following examples may be sequentially performed, or may be performed by one or more examples arbitrarily selected by those skilled in the art, and the present embodiment does not limit the specific order of execution.
In example one, based on the positional relationship of the artery location information to the keypoints, it may be determined whether the originating abnormality of the coronary artery is a multi-sinus origin. Wherein the key points in the coronary angiography image include each point on the centerline and a starting point of the coronary artery, comprising the following processes:
and determining a connected domain based on the position relation between the position information of the aorta and each point on the central line, wherein the connected domain is a connected domain formed by the points on the central line which are crossed with the region of the aorta.
In a specific implementation, a point in the region of the aorta among the points on the centerline may be regarded as a point on the centerline intersecting the region of the aorta, and a connected domain composed of these points may be determined as a connected domain; alternatively, a neighborhood of points on the centerline where the region of the aorta intersects with the region of the aorta may be regarded as points on the centerline where the region of the aorta intersects with the region of the aorta, and a connected component of these points may be determined as a connected component. The neighborhood range of the present embodiment may be four neighborhoods, eight neighborhoods, twenty-six neighborhoods, and so on.
In response to the number of connected domains being greater than a preset threshold, determining origin abnormality of the coronary artery, and the origin abnormality type being multi-sinus origin.
Preferably, the preset threshold is 2. If the number of the connected domains is larger than the preset threshold value, the coronary artery branches are originated from the aortic sinus more than the normal number, the origin abnormality of the coronary artery of the detected object is determined, and the origin abnormality type is the origin of the multi-sinus.
Or, in response to the number of connected domains being equal to a preset threshold value and the connected domains containing the starting points of the coronary arteries, determining that the origin number of the coronary arteries is normal.
If the number of the connected domains is equal to the preset threshold value and the starting point of the coronary artery is in the connected domains, the origin number of the coronary artery is normal, and of course, the origin abnormal conditions of other coronary arteries besides the origin of the multiple sinuses can exist at the moment. Wherein the starting points of the coronary arteries include a left starting point of the left coronary artery and a right starting point of the right coronary artery.
The example can automatically judge the connection condition of the coronary artery and the aorta, thereby accurately and efficiently determining whether the origin abnormal condition of the coronary artery is the origin of the multiple sinuses.
In example two, based on the position relationship of the artery position information and the key point, it can be determined whether the origin abnormal condition of the coronary artery is that the coronary artery originates from the aorta. Wherein the key point in the coronary angiography image comprises a starting point of the coronary artery, the artery position information further comprises position information of an aortic sinus, and the position information of the aortic sinus is used for defining a region of the aortic sinus in the coronary angiography image, and the method comprises the following steps:
determining an origin anomaly of the coronary artery in response to the starting point of the coronary artery being in a de-sinus region of the aorta, and the type of origin anomaly being that the coronary artery originates from the aorta.
Wherein the sinus removed region of the aorta is the aortic region not including the aortic sinus. The aortic sinus includes left, right and posterior sinuses, and the aorta mainly includes ascending aorta, aortic arch, thoracic aorta and abdominal aorta, and the sinus removed region of the aorta in this example may be specifically the sinus removed region of the ascending aorta in the aorta.
The starting points of the coronary artery comprise a left starting point of the left coronary artery and a right starting point of the right coronary artery, if any one or two of the starting points are in the sinus removing area of the aorta, or the neighborhood range of the left and right starting points is crossed with the sinus removing area of the aorta, the coronary artery is connected with the sinus removing area of the aorta, the origin abnormality of the coronary artery of the detected object is determined, and the origin abnormality type is that the coronary artery originates from the aorta.
Alternatively, the coronary artery is determined not to originate from the aorta in response to the starting point of the coronary artery not being in the sinus removed region of the aorta, indicating that the coronary artery is not connected to the sinus removed region of the aorta. Of course, there may be abnormal originating situations in which the coronary artery originates from other coronary arteries besides the aorta.
The example can automatically judge the connection condition of the coronary artery and the sinus removing area of the aorta, so as to accurately and efficiently determine whether the origin abnormal condition of the coronary artery is that the coronary artery originates from the aorta.
In example three, based on the position relationship of the artery position information and the key point, it can be determined whether the origin abnormal condition of the coronary artery is that the coronary artery originates from the pulmonary artery. Wherein the key point in the coronary angiography image comprises a starting point of the coronary artery, the artery position information further comprises position information of a pulmonary artery, and the position information of the pulmonary artery is used for defining a region of the pulmonary artery in the coronary angiography image, and the method comprises the following steps:
in response to the starting point of the coronary artery being in a region of a pulmonary artery, determining an origin anomaly of the coronary artery, and the origin anomaly type being that the coronary artery originates from a pulmonary artery.
In a specific implementation, if a point in the region of the pulmonary artery exists in the left and right starting points or the neighborhood range of the left and right starting points intersects with the region of the pulmonary artery, it is indicated that the coronary artery is connected with the pulmonary artery, and the origin abnormality of the coronary artery is determined, and the origin abnormality type is that the coronary artery originates from the pulmonary artery.
Or, in response to the starting point of the coronary artery not being in the region of the pulmonary artery, indicating that there is no connection between the coronary artery and the pulmonary artery, determining that the coronary artery does not originate from the pulmonary artery. Of course, there may be abnormal originating coronary arteries originating from coronary arteries other than the pulmonary artery.
The example can automatically judge the connection condition of the coronary artery and the pulmonary artery, so as to accurately and efficiently determine whether the origin abnormal condition of the coronary artery is that the coronary artery originates from the pulmonary artery.
In example four, based on the position relationship of the artery position information and the key point, it may be determined whether the originating abnormal condition of the coronary artery is a sinus ostium originating abnormality. Wherein, the key points in the coronary angiography image comprise a left starting point of a left coronary artery and a right starting point of a right coronary artery, the artery position information further comprises left sinus position information and right sinus position information, the left sinus position information is used for limiting a region of the left sinus in the aortic sinus in the coronary angiography image, the right sinus position information is used for limiting a region of the right sinus in the aortic sinus in the coronary angiography image, the center line comprises a left center line of the left coronary artery and a right center line of the right coronary artery, and the processing comprises the following steps:
in response to the right origin point being in the region of the left sinus or the left origin point being in the region of the right sinus, determining an origin anomaly of the coronary artery, and the origin anomaly type being an ostium origin anomaly.
In a specific implementation, if the right starting point is in the region of the left sinus or the neighborhood range of the right starting point intersects with the region of the left sinus, it is indicated that the right starting point is connected with the left sinus, and the origin abnormality of the coronary artery is determined, where the RCA abnormality originates from the left sinus of the aorta, that is, the origin abnormality type is sinus ostia origin abnormality.
Or, if the left starting point is in the region of the right sinus or the neighborhood range of the left starting point intersects with the region of the right sinus, the left starting point is connected with the right sinus, the origin abnormality of the coronary artery is determined, the LCA abnormality originates from the right aortic sinus, namely, the origin abnormality type is sinus ostium origin abnormality.
Alternatively, in response to the right origin being in the region of the right sinus and the left origin being in the region of the left sinus, the coronary ostia originate normally. Of course, there may be abnormal originating conditions of coronary arteries other than the abnormal originating condition of sinus ostia of coronary arteries.
The example can automatically judge the connection condition of the left and right initial points of the coronary artery and the left and right sinuses, thereby accurately and efficiently determining whether the origin abnormal condition of the coronary artery is the sinus ostium origin abnormal condition.
According to the method for judging origin abnormality of coronary artery provided by the technical scheme of the embodiment of the disclosure, the origin abnormality condition of the coronary artery can be automatically determined according to the position relation between the artery position information and the key point by detecting the position information of the aorta, such as the position information of the coronary artery on the obtained coronary artery angiography image, the center line of the coronary artery and the like and determining the key point according to the artery position information, the calculation time is short, and the judgment is clear and convenient; furthermore, the origin abnormal conditions of the four coronary arteries, namely the coronary artery origin from the pulmonary artery, the coronary artery origin from the aorta, the sinus ostium origin abnormality and the multi-sinus origin, can be determined according to requirements, the types are comprehensive, and the diagnosis of the coronary artery by a doctor can be assisted.
In one embodiment, a coronary angiography image may be detected through a neural network, and artery location information in the coronary angiography image may be acquired. In the following, a manner of acquiring different artery position information by detecting through a neural network is described in the above embodiments, it should be noted that the present embodiment does not limit an execution sequence of each example, and may be executed by arbitrarily selecting one or more examples that are required by a person skilled in the art.
In this embodiment, different neural networks may be selected for the identification of the artery position information of different key tissues in the heart, and the coronary angiography image may be an image after sampling and preprocessing, so as to facilitate neural network processing.
In an example, for the position information of the aorta, the aorta in the coronary angiography image may be identified through an aorta identification network, resulting in a coronary angiography image marking the position information of the aorta.
For example, the aorta recognition network is trained in advance, the coronary angiography image is input to the aorta recognition network, and the position information of the aorta in the coronary angiography image or the coronary angiography image in which the position information of the aorta is marked may be output.
In practical implementation, the position information of the aorta may also be specifically position information of an ascending aorta in the aorta, and the coronary angiography image may be identified by using an ascending aorta identification network, so as to perform more accurate determination. The ascending aorta originates from the left ventricle, is located between the pulmonary trunk and the superior vena cava, runs as an aortic arch from the anterior-superior-right to the posterior of the 2 nd thoracic rib joint on the right side, and generally originates from the root of the ascending aorta to the left and right coronary arteries. Fig. 1C shows an image of a certain transverse section in a coronary angiography image, in which the region indicated by reference character a is the ascending aorta.
In an example, for a centerline of a coronary artery, a coronary artery in a coronary angiography image may be identified through a coronary artery detection network to obtain coronary artery position information in the coronary angiography image. Then, based on the coronary artery position information, a centerline of a coronary artery is determined.
For example, a coronary artery detection network is trained in advance, a coronary artery angiography image is input to the coronary artery detection network, and coronary artery position information in the coronary artery angiography image or a coronary artery angiography image in which the coronary artery position information is labeled may be output. The coronary artery is an artery for supplying blood to the heart and is divided into a left coronary artery and a right coronary artery, the main trunk of the coronary artery runs on the surface of the heart, and the coronary artery is not a branch blood vessel but is divided into a plurality of branches step by step like a trunk and wraps the whole heart. Fig. 1D shows a three-dimensional coronary artery segmentation diagram, where the symbol C is the left coronary artery and D is the right coronary artery.
The centerline is a curve that characterizes the topology of the coronary arteries, and coincides with the connectivity of the coronary arteries in space. Specifically, the centerline may be a curve along any portion of the coronary artery, for example, a curve along the center of the coronary artery, or a curve along the outer wall of the coronary artery.
In this example, the coronary artery in the coronary angiography image determined by the coronary artery position information may be subjected to image processing to extract the left centerline of the left coronary artery and the right centerline of the right coronary artery. For example, the centerline of the coronary artery can be obtained by performing image processing algorithms such as thinning and smoothing for a plurality of iterations to remove the burr in the image. For another example, the speed of image processing can be increased by performing image processing algorithms such as fast thinning and smoothing by a GPU (graphics processing unit) device.
In an example, for the position information of the aortic sinus, the aortic sinus in the coronary angiography image may be identified through the first aortic sinus identification network, and the coronary angiography image marking the position information of the aortic sinus is obtained.
For example, the first aortic sinus recognition network may be trained in advance, the coronary angiography image may be input to the first aortic sinus recognition network, the position information of the aortic sinus in the coronary angiography image may be output, or the coronary angiography image in which the position information of the aortic sinus is marked may be output.
The aortic sinus is the lumen between the valve and the aortic wall opposite the aortic valve, bulging outward from the arterial wall. The aortic sinus can be divided into the left, right and posterior sinuses. The coronary arteries typically open to the aortic sinus. The upper bound of the aortic sinus is curved. Typically, the left and right coronary arteries open into the left and right sinuses, respectively, with the vast majority opening in the middle of the sinuses 1/3. The position information of the aortic sinus may include position information of the left sinus and the right sinus, and may further include position information of the posterior sinus. Fig. 1E is a schematic diagram of the aortic sinus in a coronary angiography image, in which the region denoted by L is the left sinus, the region denoted by R is the right sinus, and the region denoted by N is the posterior sinus.
In another example, for the region information of the aorta, the aortic sinus in the coronary angiography image marked with the position information of the aorta may also be identified through the second aortic sinus identification network, so as to obtain the coronary angiography image marked with the position information of the aortic sinus, where the position information of the aortic sinus includes the left sinus position information and the right sinus position information.
For example, the second aortic sinus recognition network may be trained in advance, and the coronary angiography image output by the above-described aortic recognition network and labeled with the position information of the aorta may be input to the second aortic sinus recognition network to obtain the position information of the aortic sinus in the coronary angiography image, or the coronary angiography image labeled with the position information of the aortic sinus may be output.
In one example, the pulmonary artery identification network identifies the pulmonary artery in the coronary angiography image, and the coronary angiography image which marks the position information of the pulmonary artery is obtained.
For example, a pulmonary artery identification network is trained in advance, and a coronary angiography image may be input to the pulmonary artery identification network to output the position information of the pulmonary artery in the coronary angiography image or output the coronary angiography image in which the position information of the pulmonary artery is marked.
The pulmonary artery, which is a thick and short trunk that transports venous blood to the lungs, emanates from the right ventricular pulmonary artery cone and then to the lower side of the aortic arch. Fig. 1B shows an image of a certain transverse section in a coronary angiography image, in which the region indicated by reference numeral B is a pulmonary artery.
In the embodiment, a coronary angiography image is detected through a neural network, so that the artery position information in the coronary angiography image is obtained, and the information required for judging the origin abnormality of the coronary artery can be efficiently and accurately obtained; the key points are determined through the artery position information, the origin abnormal condition of the coronary artery can be automatically determined according to the position relation between the artery position information and the key points, the calculation time is faster, and the judgment is clear and convenient; furthermore, the origin abnormal conditions of the four coronary arteries, namely the coronary artery origin from the pulmonary artery, the coronary artery origin from the aorta, the sinus ostium origin abnormality and the multi-sinus origin, can be determined according to requirements, the types are comprehensive, and the diagnosis of the coronary artery by a doctor can be assisted.
The following describes the above neural network training methods, but the present embodiment does not limit the specific network structure of each neural network, for example, a net network structure may be used, and a VNet network structure or a 3D-Unet network structure may also be used.
The method for pre-training the aorta recognition network comprises the following steps:
and identifying the aorta in the coronary angiography sample image by using an aorta identification network to obtain the position information of the aorta in the coronary angiography sample image. Wherein the coronary angiography sample image is a coronary angiography image in which the position information of the aorta has been labeled.
And determining the network loss according to the difference between the position information of the aorta in the acquired coronary angiography sample image and the position information of the aorta marked in the coronary angiography sample image.
And adjusting network parameters of the aorta recognition network according to the network loss optimization.
Method for pre-training a coronary artery detection network:
and identifying the coronary artery in the coronary artery angiography sample image by using a coronary artery detection network, and acquiring the position information of the coronary artery in the coronary artery angiography sample image. Wherein the coronary angiography sample image is a coronary angiography image in which position information of coronary arteries has been labeled.
And determining the network loss according to the difference between the position information of the coronary artery in the acquired coronary artery angiography sample image and the position information of the coronary artery marked in the coronary artery angiography sample image.
And optimizing and adjusting network parameters of the coronary artery detection network according to the network loss.
A method of pre-training a first aortic sinus recognition network:
and identifying the aortic sinus in the coronary angiography sample image by using a first aortic sinus identification network, and acquiring the position information of the aortic sinus in the coronary angiography sample image. The coronary angiography sample image is a coronary angiography image marked with position information of the aortic sinus, and the position information of the aortic sinus comprises left sinus position information and right sinus position information.
And determining the network loss according to the difference between the position information of the aortic sinus in the acquired coronary angiography sample image and the position information of the aortic sinus marked in the coronary angiography sample image.
And adjusting network parameters of the first aortic sinus recognition network according to the network loss optimization.
A method of pre-training a second aortic sinus recognition network:
and identifying the aortic sinus in the coronary angiography sample image by using a second aortic sinus identification network, and acquiring the position information of the aortic sinus in the coronary angiography sample image. The coronary angiography sample image is a coronary angiography image marked with position information of an aortic sinus and an aorta, and the position information of the aortic sinus comprises left sinus position information and right sinus position information.
And determining the network loss according to the difference between the position information of the aortic sinus in the acquired coronary angiography sample image and the position information of the aortic sinus marked in the coronary angiography sample image.
And adjusting the network parameters of the second aortic sinus recognition network according to the network loss optimization.
The method for pre-training the pulmonary artery identification network comprises the following steps:
and identifying the pulmonary artery in the coronary angiography sample image by using a pulmonary artery identification network to obtain the position information of the pulmonary artery in the coronary angiography sample image. The coronary angiography sample image is a coronary angiography image in which position information of the pulmonary artery has been labeled.
And determining the network loss according to the difference between the position information of the pulmonary artery in the acquired coronary angiography sample image and the position information of the pulmonary artery marked in the coronary angiography sample image.
And optimizing and adjusting network parameters of the pulmonary artery identification network according to the network loss.
In practical implementation, when the neural network adjusts the network parameters according to the network loss, the network parameters of the neural network can be adjusted through back propagation. And when a network iteration ending condition is reached, ending the network training, wherein the ending condition can be that the iteration reaches a certain number of times or the loss value is less than a certain threshold value.
The calculated related information in any embodiment of the present disclosure, for example, the position information of the coronary artery, the aorta (or the ascending aorta), the pulmonary artery, and the aortic sinus in the artery position information, the center line, and the starting points of the left and right coronary arteries in the key points, etc. can be displayed and edited through a UI (User Interface), displayed through a 2D, 3D image, a curve, a graph, etc., where the points and lines can be manually edited and corrected, curved surface unfolding and drawing can be performed on the coronary artery, the aorta (or the ascending aorta), the pulmonary artery, and the aortic sinus, the related parameters of the coronary artery, the aorta (or the ascending aorta), the pulmonary artery, and the aortic sinus can be displayed, and the output result can be printed, reported, and saved.
Fig. 2 is a block diagram of an apparatus for determining origin abnormality of coronary artery according to an embodiment of the present disclosure, which may be disposed on any computing-capable device, such as a terminal device or a server or other processing device, and includes: a detection module 21, a key point determination module 22 and a judgment module 23.
A detecting module 21, configured to detect a coronary angiography image, and acquire artery position information in the coronary angiography image, where the artery position information includes at least position information of an aorta and a centerline of the coronary artery, the position information of the aorta is used to define a region of the aorta in the coronary angiography image, and the centerline is a curve representing a topology of the coronary artery.
A keypoint determination module 22 for determining keypoints in the coronary angiography image based on the artery position information.
And the judging module 23 is configured to determine an origin abnormal condition of the coronary artery based on the position relationship between the artery position information and the key point.
According to the device for judging origin abnormality of coronary artery provided by the technical scheme of the embodiment of the disclosure, the origin abnormality of coronary artery can be automatically determined according to the position information of the aorta, the central line of the coronary artery and other artery position information on the obtained coronary artery angiography image, the key point is determined according to the artery position information, and the position relation between the artery position information and the key point, so that the calculation time is fast, and the judgment is clear and convenient.
In one example, the keypoints in the coronary angiographic image include points on the centerline and the starting point of the coronary artery.
The key point determining module 22 is specifically configured to: and determining the point where the central line is connected with the root of the aorta as the starting point of the coronary artery based on the position information of the central line and the aorta.
The determining module 23 is specifically configured to: determining a connected domain based on the position relation between the position information of the aorta and each point on the central line, wherein the connected domain is a connected domain formed by the points on the central line which are crossed with the region of the aorta; in response to the number of connected domains being greater than a preset threshold, determining origin abnormality of the coronary artery, and the origin abnormality type being multi-sinus origin.
In one example, the key points in the coronary angiography image include starting points of the coronary arteries, and the artery position information further includes position information of an aortic sinus, which is used to define a region of the aortic sinus in the coronary angiography image.
The key point determining module 22 is specifically configured to: and determining the point where the central line is connected with the root of the aorta as the starting point of the coronary artery based on the position information of the central line and the aorta.
The determining module 23 is specifically configured to: in response to the starting point of the coronary artery being in a sinus removed region of the aorta, determining an origin anomaly of the coronary artery, and the origin anomaly type being that the coronary artery originates from the aorta, the sinus removed region of the aorta being a region of the aorta that does not contain the aortic sinus.
In one example, the key point in the coronary angiography image includes a start point of the coronary artery, and the artery position information further includes position information of a pulmonary artery, which is used to define a region of the pulmonary artery in the coronary angiography image.
The key point determining module 22 is specifically configured to: and determining the point where the central line is connected with the root of the aorta as the starting point of the coronary artery based on the position information of the central line and the aorta.
The determining module 23 is specifically configured to: in response to the starting point of the coronary artery being in a region of a pulmonary artery, determining an origin anomaly of the coronary artery, and the origin anomaly type being that the coronary artery originates from a pulmonary artery.
In one example, the keypoints in the coronary angiography image comprise a left start point of a left coronary artery and a right start point of a right coronary artery, the artery position information further comprises left sinus position information and right sinus position information, the left sinus position information is used for defining a region of the left sinus in an aortic sinus in the coronary angiography image, the right sinus position information is used for defining a region of the right sinus in the aortic sinus in the coronary angiography image, and the center line comprises a left center line of the left coronary artery and a right center line of the right coronary artery;
the key point determining module 22 is specifically configured to: and determining the point where the left central line is jointed with the root of the aorta as the left starting point of the left coronary artery and determining the point where the right central line is jointed with the root of the aorta as the right starting point of the right coronary artery based on the position information of the central line and the aorta.
The determining module 23 is specifically configured to: in response to the right origin point being in the region of the left sinus, determining an originating abnormality of the coronary artery, and the originating abnormality type being an ostium originating abnormality.
In an example, the detection module 21 is specifically configured to: and identifying the aorta in the coronary angiography image through an aorta identification network to obtain the coronary angiography image for marking the position information of the aorta. Through a coronary artery detection network, identifying processing is carried out on coronary arteries in a coronary artery angiography image, and coronary artery position information in the coronary artery angiography image is obtained. Based on the coronary artery location information, a centerline of a coronary artery is determined.
In an example, the detecting module 21 may be further configured to: and identifying the pulmonary artery in the coronary angiography image through a pulmonary artery identification network to obtain the coronary angiography image marking the position information of the pulmonary artery. And identifying the aortic sinus in the coronary angiography image through a first aortic sinus identification network to obtain the coronary angiography image for marking the position information of the aortic sinus. Or, the second aortic sinus identification network identifies the aortic sinus in the coronary angiography image marked with the position information of the aorta, and obtains the coronary angiography image marked with the position information of the aortic sinus.
The implementation process of the functions and actions of each module in the above device is specifically described in the implementation process of the corresponding step in the above method, and is not described herein again.
The embodiment of the present disclosure further provides an electronic device, as shown in fig. 3, the electronic device includes a memory 31 and a processor 32, where the memory 31 is used to store computer instructions executable on the processor, and the processor 32 is used to implement the method for determining origin abnormality of coronary artery according to any embodiment of the present disclosure when executing the computer instructions.
The embodiments of the present disclosure also provide a computer program product, which includes a computer program/instruction, when being executed by a processor, to implement the method for determining origin abnormality of coronary artery according to any one of the embodiments of the present disclosure.
The embodiments of the present disclosure also provide a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the method for determining origin abnormality of coronary artery according to any one of the embodiments of the present disclosure.
For the device embodiments, since they substantially correspond to the method embodiments, reference may be made to the partial description of the method embodiments for relevant points. The above-described embodiments of the apparatus are merely illustrative, wherein the modules described as separate parts may or may not be physically separate, and the parts displayed as modules may or may not be physical modules, may be located in one place, or may be distributed on a plurality of network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution in the specification. One of ordinary skill in the art can understand and implement it without inventive effort.
The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
Other embodiments of the present description will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This specification is intended to cover any variations, uses, or adaptations of the specification following, in general, the principles of the specification and including such departures from the present disclosure as come within known or customary practice within the art to which the specification pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the specification being indicated by the following claims.
It will be understood that the present description is not limited to the precise arrangements described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present description is limited only by the appended claims.
The above description is only a preferred embodiment of the present disclosure, and should not be taken as limiting the present disclosure, and any modifications, equivalents, improvements, etc. made within the spirit and principle of the present disclosure should be included in the scope of the present disclosure.
Claims (14)
1. A method for determining origin abnormality of a coronary artery, the method comprising:
detecting a coronary angiography image, and acquiring artery position information in the coronary angiography image, wherein the artery position information at least comprises position information of an aorta and a central line of the coronary artery, the position information of the aorta is used for defining a region of the aorta in the coronary angiography image, and the central line is a curve representing the topological structure of the coronary artery;
determining keypoints in the coronary angiography image based on the artery position information;
and determining the origin abnormal condition of the coronary artery based on the position relation of the artery position information and the key point.
2. The method of claim 1, wherein the keypoints in the coronary angiography image comprise points on the centerline;
the determining the origin abnormal condition of the coronary artery based on the position relation of the artery position information and the key point comprises the following steps:
determining a connected domain based on the position relation between the position information of the aorta and each point on the central line, wherein the connected domain is a connected domain formed by the points on the central line which are crossed with the region of the aorta;
in response to the number of connected domains being greater than a preset threshold, determining origin abnormality of the coronary artery, and the origin abnormality type being multi-sinus origin.
3. The method of claim 1, wherein the key points in the coronary angiography image comprise starting points of the coronary arteries, the artery location information further comprises location information of an aortic sinus, the location information of the aortic sinus being used to define a region of the aortic sinus in the coronary angiography image;
the determining of keypoints in the coronary angiography image based on the artery position information comprises:
determining a point where the centerline is connected with the root of the aorta as a starting point of the coronary artery based on the position information of the centerline and the aorta;
the determining the origin abnormal condition of the coronary artery based on the position relation of the artery position information and the key point comprises the following steps:
in response to the starting point of the coronary artery being in a sinus removed region of the aorta, determining an origin anomaly of the coronary artery, and the origin anomaly type being that the coronary artery originates from the aorta, the sinus removed region of the aorta being a region of the aorta that does not contain the aortic sinus.
4. The method of claim 1, wherein the key points in the coronary angiography image comprise starting points of the coronary arteries, the artery position information further comprises position information of pulmonary arteries, and the position information of the pulmonary arteries is used for defining areas of the pulmonary arteries in the coronary angiography image;
the determining of keypoints in the coronary angiography image based on the artery position information comprises:
determining a point where the centerline is connected with the root of the aorta as a starting point of the coronary artery based on the position information of the centerline and the aorta;
the determining the origin abnormal condition of the coronary artery based on the position relation of the artery position information and the key point comprises the following steps:
in response to the starting point of the coronary artery being in a region of a pulmonary artery, determining an origin anomaly of the coronary artery, and the origin anomaly type being that the coronary artery originates from a pulmonary artery.
5. The method of claim 1, wherein the keypoints in the angiographic image comprise a left start point of a left coronary artery and a right start point of a right coronary artery, the artery location information further comprising left sinus location information defining a region of the left sinus in the aortic sinus in the angiographic image and right sinus location information defining a region of the right sinus in the aortic sinus in the angiographic image, the centerlines comprising a left centerline of the left coronary artery and a right centerline of the right coronary artery;
the determining of keypoints in the coronary angiography image based on the artery position information comprises:
determining a point where the left centerline is joined with the root of the aorta as a left starting point of the left coronary artery and a point where the right centerline is joined with the root of the aorta as a right starting point of the right coronary artery based on the position information of the centerline and the aorta;
the determining the origin abnormal condition of the coronary artery based on the position relation of the artery position information and the key point comprises the following steps:
in response to the right origin point being in the region of the left sinus or the left origin point being in the region of the right sinus, determining an origin anomaly of the coronary artery, and the origin anomaly type being an ostium origin anomaly.
6. The method of claim 1, wherein the detecting the coronary angiography image to obtain artery position information in the coronary angiography image comprises:
identifying and processing the aorta in the coronary angiography image through an aorta identification network to obtain a coronary angiography image for marking the position information of the aorta;
identifying and processing coronary arteries in a coronary angiography image through a coronary artery detection network, and acquiring coronary artery position information in the coronary angiography image;
based on the coronary artery location information, a centerline of a coronary artery is determined.
7. An apparatus for determining origin abnormality of a coronary artery, the apparatus comprising:
a detection module, configured to detect a coronary angiography image, and acquire artery position information in the coronary angiography image, where the artery position information includes at least position information of an aorta and a centerline of a coronary artery, the position information of the aorta is used to define a region of the aorta in the coronary angiography image, and the centerline is a curve representing a topology of the coronary artery;
a keypoint determination module for determining keypoints in the coronary angiography image based on the artery position information;
and the judging module is used for determining the origin abnormal condition of the coronary artery based on the position relation between the artery position information and the key point.
8. The apparatus of claim 7, wherein the keypoints in the coronary angiography image comprise respective points on the centerline and starting points of the coronary arteries;
the key point determining module is specifically configured to:
determining a point where the centerline is connected with the root of the aorta as a starting point of the coronary artery based on the position information of the centerline and the aorta;
the judgment module is specifically configured to:
determining a connected domain based on the position relation between the position information of the aorta and each point on the central line, wherein the connected domain is a connected domain formed by the points on the central line which are crossed with the region of the aorta;
in response to the number of connected domains being greater than a preset threshold, determining origin abnormality of the coronary artery, and the origin abnormality type being multi-sinus origin.
9. The apparatus of claim 7, wherein the key point in the coronary angiography image comprises a starting point of the coronary artery, the artery position information further comprises position information of an aortic sinus, and the position information of the aortic sinus is used for defining a region of the aortic sinus in the coronary angiography image;
the key point determining module is specifically configured to:
determining a point where the centerline is connected with the root of the aorta as a starting point of the coronary artery based on the position information of the centerline and the aorta;
the judgment module is specifically configured to:
in response to the starting point of the coronary artery being in a sinus removed region of the aorta, determining an origin anomaly of the coronary artery, and the origin anomaly type being that the coronary artery originates from the aorta, the sinus removed region of the aorta being a region of the aorta that does not contain the aortic sinus.
10. The apparatus of claim 7, wherein the key point in the coronary angiography image comprises a starting point of the coronary artery, and the artery position information further comprises position information of a pulmonary artery, the position information of the pulmonary artery being used to define a region of the pulmonary artery in the coronary angiography image;
the key point determining module is specifically configured to:
determining a point where the centerline is connected with the root of the aorta as a starting point of the coronary artery based on the position information of the centerline and the aorta;
the judgment module is specifically configured to:
in response to the starting point of the coronary artery being in a region of a pulmonary artery, determining an origin anomaly of the coronary artery, and the origin anomaly type being that the coronary artery originates from a pulmonary artery.
11. The apparatus of claim 7, wherein the keypoints in the angiographic image comprise a left start point of a left coronary artery and a right start point of a right coronary artery, the artery location information further comprising left sinus location information defining a region of the left sinus in the aortic sinus in the angiographic image and right sinus location information defining a region of the right sinus in the aortic sinus in the angiographic image, the centerlines comprising a left centerline of the left coronary artery and a right centerline of the right coronary artery;
the key point determining module is specifically configured to:
determining a point where the left centerline is joined with the root of the aorta as a left starting point of the left coronary artery and a point where the right centerline is joined with the root of the aorta as a right starting point of the right coronary artery based on the position information of the centerline and the aorta;
the judgment module is specifically configured to:
in response to the right origin point being in the region of the left sinus, determining an originating abnormality of the coronary artery, and the originating abnormality type being an ostium originating abnormality.
12. The apparatus of claim 7,
the detection module is specifically configured to:
identifying and processing the aorta in the coronary angiography image through an aorta identification network to obtain a coronary angiography image for marking the position information of the aorta;
identifying and processing coronary arteries in a coronary angiography image through a coronary artery detection network, and acquiring coronary artery position information in the coronary angiography image;
based on the coronary artery location information, a centerline of a coronary artery is determined.
13. An electronic device, comprising a memory for storing computer instructions executable on a processor, the processor being configured to implement the method of any one of claims 1 to 6 when executing the computer instructions.
14. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110692227.7A CN113450322A (en) | 2021-06-22 | 2021-06-22 | Method and device for judging origin abnormality of coronary artery |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110692227.7A CN113450322A (en) | 2021-06-22 | 2021-06-22 | Method and device for judging origin abnormality of coronary artery |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113450322A true CN113450322A (en) | 2021-09-28 |
Family
ID=77812165
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110692227.7A Pending CN113450322A (en) | 2021-06-22 | 2021-06-22 | Method and device for judging origin abnormality of coronary artery |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113450322A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114041761A (en) * | 2021-10-27 | 2022-02-15 | 北京医准智能科技有限公司 | Method and device for judging origin of coronary artery and computer readable medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006068350A (en) * | 2004-09-03 | 2006-03-16 | Toshiba Corp | Medical image display method, medical image displaying device and program for medical image displaying |
| US20130216110A1 (en) * | 2012-02-21 | 2013-08-22 | Siemens Aktiengesellschaft | Method and System for Coronary Artery Centerline Extraction |
| CN110428420A (en) * | 2018-09-05 | 2019-11-08 | 深圳科亚医疗科技有限公司 | The method, apparatus and medium of flowing information coronarius are determined based on the coronary artery CT angiographic image of patient |
| CN111369525A (en) * | 2020-03-02 | 2020-07-03 | 联影智能医疗科技(北京)有限公司 | Image analysis method, apparatus and storage medium |
| CN111383259A (en) * | 2020-03-02 | 2020-07-07 | 联影智能医疗科技(北京)有限公司 | Image analysis method, computer device, and storage medium |
| CN111681211A (en) * | 2020-05-18 | 2020-09-18 | 沈阳先进医疗设备技术孵化中心有限公司 | Blood vessel image processing method and device |
| CN112132882A (en) * | 2019-11-19 | 2020-12-25 | 苏州润迈德医疗科技有限公司 | Method and device for extracting blood vessel central line from coronary artery two-dimensional contrast image |
| CN112652052A (en) * | 2020-12-15 | 2021-04-13 | 山东大学 | Coronary artery three-dimensional reconstruction method and system based on blood vessel branch registration |
| CN112674872A (en) * | 2020-12-22 | 2021-04-20 | 中国人民解放军陆军军医大学 | Aorta complex anatomical feature measuring method |
-
2021
- 2021-06-22 CN CN202110692227.7A patent/CN113450322A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006068350A (en) * | 2004-09-03 | 2006-03-16 | Toshiba Corp | Medical image display method, medical image displaying device and program for medical image displaying |
| US20130216110A1 (en) * | 2012-02-21 | 2013-08-22 | Siemens Aktiengesellschaft | Method and System for Coronary Artery Centerline Extraction |
| CN110428420A (en) * | 2018-09-05 | 2019-11-08 | 深圳科亚医疗科技有限公司 | The method, apparatus and medium of flowing information coronarius are determined based on the coronary artery CT angiographic image of patient |
| CN112132882A (en) * | 2019-11-19 | 2020-12-25 | 苏州润迈德医疗科技有限公司 | Method and device for extracting blood vessel central line from coronary artery two-dimensional contrast image |
| CN111369525A (en) * | 2020-03-02 | 2020-07-03 | 联影智能医疗科技(北京)有限公司 | Image analysis method, apparatus and storage medium |
| CN111383259A (en) * | 2020-03-02 | 2020-07-07 | 联影智能医疗科技(北京)有限公司 | Image analysis method, computer device, and storage medium |
| CN111681211A (en) * | 2020-05-18 | 2020-09-18 | 沈阳先进医疗设备技术孵化中心有限公司 | Blood vessel image processing method and device |
| CN112652052A (en) * | 2020-12-15 | 2021-04-13 | 山东大学 | Coronary artery three-dimensional reconstruction method and system based on blood vessel branch registration |
| CN112674872A (en) * | 2020-12-22 | 2021-04-20 | 中国人民解放军陆军军医大学 | Aorta complex anatomical feature measuring method |
Non-Patent Citations (2)
| Title |
|---|
| MARCOS DANILLO PEIXOTO OLIVEIRA ET AL.: "Anomalous origin of the left coronary artery from the right sinus: an interesting and very rare coronary anomaly circulation", 《JOURNAL OF XIANGYA MEDICINE》 * |
| 罗立镇 等: "双源CT在先天性冠状动脉起源异常的临床应用", 《中国医学创新》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114041761A (en) * | 2021-10-27 | 2022-02-15 | 北京医准智能科技有限公司 | Method and device for judging origin of coronary artery and computer readable medium |
| CN114041761B (en) * | 2021-10-27 | 2022-12-09 | 北京医准智能科技有限公司 | Method, device and computer readable medium for judging origin of coronary artery |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11576626B2 (en) | Systems and methods for numerically evaluating vasculature | |
| CN102663824B (en) | The method and system that heart in cardiac computer fault imaging volume separates | |
| CN114820654A (en) | Blood vessel segmentation method, blood vessel segmentation device, medical imaging equipment and storage medium | |
| US8422753B2 (en) | Method and system for automatic extraction of personalized left atrium models | |
| US20120069017A1 (en) | Method and System for Efficient Extraction of a Silhouette of a 3D Mesh | |
| CN111553887A (en) | Method and device for obtaining evaluation information of bridge blood vessels | |
| CN109740602A (en) | Pulmonary artery phase vessel extraction method and system | |
| CN110353639B (en) | Blood supply area quantification method and system based on blood vessel enhanced radiography | |
| CN113222974B (en) | Automatic evaluation method and device for side branch circulation | |
| CN113450322A (en) | Method and device for judging origin abnormality of coronary artery | |
| Karim et al. | Left atrium segmentation for atrial fibrillation ablation | |
| Cárdenes et al. | 3D modeling of coronary artery bifurcations from CTA and conventional coronary angiography | |
| Zheng et al. | Model-driven centerline extraction for severely occluded major coronary arteries | |
| CN115775219A (en) | Medical image segmentation method, system, electronic device, and medium | |
| CN113139961B (en) | Method and device for determining dominant type of coronary artery | |
| Zhong et al. | Segmentation and removal of pulmonary arteries, veins and left atrial appendage for visualizing coronary and bypass arteries | |
| US11922621B2 (en) | Automatic frame selection for 3D model construction | |
| EP4107697B1 (en) | Methods and systems for cardiac chamber imaging | |
| Taeprasartsit et al. | System for definition of the central-chest vasculature | |
| RU2576816C1 (en) | Method for determination of left atrial myocardium contours on mr images using multi-planar reconstructions | |
| CN116051592A (en) | Coronary artery dominant type judging method, system, device and storage medium | |
| Karima et al. | Automatic Segmentation of the Left Atrium | |
| CN115881277A (en) | Computer-implemented method, evaluation system, computer program for evaluating a three-dimensional angiography dataset | |
| Garreau et al. | Abilities of cardiac MSCT imaging to provide useful anatomical and functional information for Cardiac Resynchronization Therapy optimization |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20240205 Address after: 110167 No. 177-1 Innovation Road, Hunnan District, Shenyang City, Liaoning Province Applicant after: Shenyang Neusoft Medical Systems Co.,Ltd. Country or region after: China Address before: Room 336, 177-1, Chuangxin Road, Hunnan New District, Shenyang City, Liaoning Province Applicant before: Shenyang advanced medical equipment Technology Incubation Center Co.,Ltd. Country or region before: China |
|
| TA01 | Transfer of patent application right |