CN116823806A - Automatic identification method, device, equipment and storage medium for coronary origin abnormality - Google Patents
Automatic identification method, device, equipment and storage medium for coronary origin abnormality Download PDFInfo
- Publication number
- CN116823806A CN116823806A CN202310924038.7A CN202310924038A CN116823806A CN 116823806 A CN116823806 A CN 116823806A CN 202310924038 A CN202310924038 A CN 202310924038A CN 116823806 A CN116823806 A CN 116823806A
- Authority
- CN
- China
- Prior art keywords
- distance
- coronary
- aortic
- segmentation
- sinus
- 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
- 230000005856 abnormality Effects 0.000 title claims abstract description 63
- 238000000034 method Methods 0.000 title claims abstract description 60
- 230000011218 segmentation Effects 0.000 claims abstract description 212
- 210000004351 coronary vessel Anatomy 0.000 claims abstract description 121
- 210000003291 sinus of valsalva Anatomy 0.000 claims abstract description 43
- 210000001367 artery Anatomy 0.000 claims description 6
- 210000003748 coronary sinus Anatomy 0.000 claims description 4
- 238000013135 deep learning Methods 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 210000004204 blood vessel Anatomy 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000002583 angiography Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 208000031225 myocardial ischemia Diseases 0.000 description 2
- 206010002383 Angina Pectoris Diseases 0.000 description 1
- 208000004652 Cardiovascular Abnormalities Diseases 0.000 description 1
- 208000024172 Cardiovascular disease Diseases 0.000 description 1
- 206010019280 Heart failures Diseases 0.000 description 1
- 206010042434 Sudden death Diseases 0.000 description 1
- 210000001765 aortic valve Anatomy 0.000 description 1
- 206010003119 arrhythmia Diseases 0.000 description 1
- 230000006793 arrhythmia Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000002872 contrast media Substances 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 208000010125 myocardial infarction Diseases 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000004091 panning Methods 0.000 description 1
- 210000004872 soft tissue Anatomy 0.000 description 1
- 206010042772 syncope Diseases 0.000 description 1
- 210000001519 tissue Anatomy 0.000 description 1
- 230000002792 vascular Effects 0.000 description 1
- 208000019553 vascular disease Diseases 0.000 description 1
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
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20021—Dividing image into blocks, subimages or windows
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (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 belongs to the technical field of medical image processing, and discloses an automatic identification method, device and equipment for coronary origin abnormality and a storage medium. The method comprises the following steps: determining an aortic segmentation binary image, a coronary multi-class segmentation map, an aortic sinus multi-class segmentation map and an aortic centerline according to the coronary CTA image; intercepting the aortic sinus multi-class segmentation map to obtain a maximum aortic cross section; respectively performing expansion processing on the left coronary artery segmentation map and the right coronary artery segmentation map, and determining that the distances from the left centroid of the left communicating domain and the right centroid of the right communicating domain to the maximum aortic cross section are respectively a first plane distance and a second plane distance based on the expanded left coronary artery segmentation map, the expanded right coronary artery segmentation map and the aortic segmentation binary map; and when the first plane distance or the second plane distance is larger than the preset distance, determining that the origin abnormality is high coronary artery. In this way, automatic identification of coronary origin anomalies can be determined.
Description
Technical Field
The invention relates to the technical field of medical image processing, in particular to an automatic identification method, device and equipment for coronary origin abnormality and a storage medium.
Background
Cardiovascular disease has become one of the major diseases threatening human life safety, and doctors assist in diagnosing various vascular diseases through vascular imaging technology. In clinic, diagnosis of cardiovascular abnormalities of coronary origin, which can vary from asymptomatic to angina, myocardial infarction to heart failure, arrhythmia to syncope and even sudden death, etc., is important, depending on whether myocardial ischemia can be caused and the extent of myocardial ischemia. In the traditional method, whether the origin of the coronary artery is abnormal or not is mainly judged by doctors manually, and the problem of low judging efficiency exists.
Disclosure of Invention
The invention mainly aims to provide an automatic identification method, device, equipment and storage medium for coronary origin abnormality, and aims to solve the technical problem that the judgment efficiency is low when the coronary origin abnormality is manually judged in the prior art.
To achieve the above object, the present invention provides an automated method for identifying abnormalities in coronary origin, the method comprising the steps of:
Acquiring a coronary artery CTA image of a first coronary artery;
determining an aortic segmentation binary image, a coronary multi-class segmentation image and an aortic sinus multi-class segmentation image of the first coronary according to the coronary CTA image, and extracting an aortic centerline based on the aortic segmentation binary image, wherein the coronary multi-class segmentation image comprises a left coronary segmentation image and a right coronary segmentation image;
performing expansion treatment on the left coronary segmentation map and the right coronary segmentation map respectively to obtain a new left coronary segmentation map and a new right coronary segmentation map;
intercepting the aortic sinus multi-class segmentation map by using a target plane to obtain a maximum aortic cross section, wherein the target plane is a plane perpendicular to the aortic center line;
determining a left connected domain and a right connected domain based on the new left coronary segmentation map, the new right coronary segmentation map and the aortic segmentation binary map, and determining a left centroid of the left connected domain and a right centroid of the right connected domain;
determining the distance from the left centroid to the maximum aortic cross section as a first planar distance, and determining the distance from the right centroid to the maximum aortic cross section as a second planar distance;
Judging whether the first plane distance or the second plane distance is larger than a preset distance;
and when the first plane distance or the second plane distance is larger than a preset distance, determining that the origin abnormality of the first coronary artery is a coronary artery high position.
Optionally, the maximum aortic cross section comprises a left Dou Ouyu, right sinus region and a nameless sinus region; wherein,,
after the judging whether the first plane distance or the second plane distance is greater than a preset distance, the method further comprises:
when the first plane distance or the second plane distance is not larger than a preset distance, projecting the left centroid onto the maximum aortic cross section to obtain a left projection point;
respectively determining the distances from the left projection point to the left sinus region, the right sinus region and the innominate sinus region as a first left distance, a second left distance and a third left distance;
judging whether the first left distance is the smallest distance among the first left distance, the second left distance and the third left distance;
if not, judging the minimum distance in the second left distance and the third left distance;
if the minimum distance is determined to be a second left distance, determining that the origin abnormality of the first coronary artery is that the left coronary artery originates from the right sinus;
If the minimum distance is determined to be the third left distance, determining that the origin abnormality of the first coronary artery is that the left crown originates from the innominate sinus.
Optionally, the maximum aortic cross section comprises a left Dou Ouyu, right sinus region and a nameless sinus region; wherein,,
after the judging whether the first plane distance or the second plane distance is greater than a preset distance, the method further comprises:
when the first plane distance or the second plane distance is not larger than a preset distance, projecting the right centroid onto the maximum aortic cross section to obtain a right projection point;
respectively determining the distances from the right projection point to the left sinus region, the right sinus region and the innominate sinus region as a first right distance, a second right distance and a third right distance;
judging whether the second right distance is the smallest distance among the first right distance, the second right distance and the third right distance;
if not, judging the minimum distance in the first right distance and the third right distance;
if the minimum distance is determined to be a first right distance, determining that the origin abnormality of the first coronary artery is that the right coronary artery originates from the left sinus;
if the minimum distance is determined to be the third right distance, determining that the origin abnormality of the first coronary artery is that the right crown originates from the innominate sinus.
Optionally, the expanding processing is performed on the left coronary segmented graph and the right coronary segmented graph to obtain a new left coronary segmented graph and a new right coronary segmented graph, which includes:
performing expansion processing on the left coronary artery segmentation map so that the intersection of the new left coronary artery segmentation map and the aortic segmentation binary image is not an empty set;
and performing expansion processing on the right coronary artery segmentation map so that the intersection of the new right coronary artery segmentation map and the aortic artery segmentation binary image is not an empty set.
Optionally, the method includes the step of intercepting the aortic sinus multi-class segmentation map with a target plane to obtain a maximum aortic cross section, where the target plane is a plane perpendicular to the aortic centerline, and includes:
intercepting the aortic sinus multi-class segmentation map by using a target plane to obtain a plurality of binary segmentation seg_N, wherein each seg_N corresponds to a coronary sinus cross-sectional area, and the target plane is a plane perpendicular to the aortic center line;
the seg_N corresponding to the maximum aortic cross-sectional area is taken as the maximum aortic cross-section.
Optionally, the aortic sinus multi-class segmentation map includes a left Dou Biaoqian, a right sinus label, and a nameless sinus label; wherein,,
After the seg_n corresponding to the maximum aortic cross-sectional area is taken as the maximum aortic cross-section, the method further comprises:
from the left Dou Biaoqian, right sinus tag, and the innominate Dou Biaoqian, a left Dou Ouyu, right sinus region, and innominate sinus region are determined on the maximum aortic cross-section.
Optionally, the extracting the aortic centerline based on the aortic segmentation binary map includes:
and extracting an aortic centerline through deep learning or image processing based on the aortic segmentation binary image.
In addition, in order to achieve the above object, the present invention also proposes an automated identification device of a coronary origin abnormality, the automated identification device of a coronary origin abnormality comprising:
the acquisition module is used for acquiring a coronary artery CTA image of the first coronary artery;
the acquisition module is used for determining an aortic segmentation binary image, a coronary multi-class segmentation image and an aortic sinus multi-class segmentation image of the first coronary according to the coronary CTA image, and extracting an aortic centerline based on the aortic segmentation binary image, wherein the coronary multi-class segmentation image comprises a left coronary segmentation image and a right coronary segmentation image;
the expansion module is used for respectively carrying out expansion processing on the left coronary segmentation map and the right coronary segmentation map to obtain a new left coronary segmentation map and a new right coronary segmentation map;
The determining module is further configured to intercept the aortic sinus multi-class segmentation map by using a target plane to obtain a maximum aortic cross section, where the target plane is a plane perpendicular to the aortic centerline;
the determining module is further configured to determine a left connected domain and a right connected domain based on the new left coronary segmentation map, the new right coronary segmentation map, and the aortic segmentation binary map, and determine a left centroid of the left connected domain and a right centroid of the right connected domain;
the determining module is further configured to determine that a distance from the left centroid to the maximum aortic cross section is a first planar distance, and determine that a distance from the right centroid to the maximum aortic cross section is a second planar distance;
the judging module is used for judging whether the first plane distance or the second plane distance is larger than a preset distance;
the determining module is further configured to determine that the origin anomaly of the first coronary artery is a coronary artery high position when it is determined that the first plane distance or the second plane distance is greater than a preset distance.
In addition, in order to achieve the above object, the present invention also proposes an automated identification apparatus of a coronary origin abnormality, the automated identification apparatus of a coronary origin abnormality comprising: a memory, a processor, and an automated identification program stored on the memory and executable on the processor for coronary origin anomalies, the automated identification program for coronary origin anomalies configured to implement the steps of the automated identification method for coronary origin anomalies as described above.
In addition, in order to achieve the above object, the present invention also proposes a storage medium having stored thereon an automated identification program of a coronary origin abnormality, which when executed by a processor, implements the steps of the automated identification method of a coronary origin abnormality as described above.
The invention provides an automatic identification method, device, equipment and storage medium for coronary origin abnormality, which are characterized in that a coronary artery CTA image of a first coronary artery is obtained; determining an aortic segmentation binary image, a coronary multi-class segmentation image and an aortic sinus multi-class segmentation image of the first coronary according to the coronary CTA image, and extracting an aortic centerline based on the aortic segmentation binary image, wherein the coronary multi-class segmentation image comprises a left coronary segmentation image and a right coronary segmentation image; performing expansion treatment on the left coronary segmentation map and the right coronary segmentation map respectively to obtain a new left coronary segmentation map and a new right coronary segmentation map; intercepting the aortic sinus multi-class segmentation map by using a target plane to obtain a maximum aortic cross section, wherein the target plane is a plane perpendicular to the aortic center line; determining a left connected domain and a right connected domain based on the new left coronary segmentation map, the new right coronary segmentation map and the aortic segmentation binary map, and determining a left centroid of the left connected domain and a right centroid of the right connected domain; determining the distance from the left centroid to the maximum aortic cross section as a first planar distance, and determining the distance from the right centroid to the maximum aortic cross section as a second planar distance; judging whether the first plane distance or the second plane distance is larger than a preset distance; and when the first plane distance or the second plane distance is larger than a preset distance, determining that the origin abnormality of the first coronary artery is a coronary artery high position. By the method, the coronary artery origin anomaly determination is not needed to be carried out on the acquired coronary artery angiography image manually by a doctor, the anomaly category of the coronary artery origin anomaly can be automatically identified and determined, the determination efficiency can be improved, and medical resources can be saved.
Drawings
FIG. 1 is a schematic diagram of an automated identification apparatus for coronary origin anomalies in a hardware operating environment in accordance with an embodiment of the present invention;
FIG. 2 is a flow chart of a first embodiment of an automated method for identifying coronary anomalies according to the present invention;
FIG. 3 is a flow chart of a second embodiment of an automated method for identifying coronary anomalies according to the present invention;
FIG. 4 is a flow chart of a third embodiment of an automated method for identifying coronary anomalies according to the present invention;
fig. 5 is a block diagram showing the construction of a first embodiment of an automated coronary origin anomaly identification device according to the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Referring to fig. 1, fig. 1 is a schematic structural diagram of an automated identification device for coronary origin anomaly of a hardware running environment according to an embodiment of the present invention.
As shown in fig. 1, the automated identification device of coronary origin anomalies may include: a processor 1001, such as a central processing unit (Central Processing Unit, CPU), a communication bus 1002, a user interface 1003, a network interface 1004, a memory 1005. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display, an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may further include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a Wireless interface (e.g., a Wireless-Fidelity (Wi-Fi) interface). The Memory 1005 may be a high-speed random access Memory (Random Access Memory, RAM) Memory or a stable nonvolatile Memory (NVM), such as a disk Memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above.
It will be appreciated by those skilled in the art that the structure shown in fig. 1 does not constitute a limitation of an automated identification device of abnormalities of coronary origin, and may include more or fewer components than illustrated, or certain components in combination, or a different arrangement of components.
As shown in fig. 1, an operating system, a network communication module, a user interface module, and an automated identification program of a coronary origin abnormality may be included in the memory 1005 as one storage medium.
In the automated identification device of coronary origin anomalies shown in fig. 1, the network interface 1004 is primarily used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001, the memory 1005 in the automatic identification apparatus of coronary origin abnormality of the present invention may be provided in the automatic identification apparatus of coronary origin abnormality which invokes the automatic identification program of coronary origin abnormality stored in the memory 1005 through the processor 1001 and performs the automatic identification method of coronary origin abnormality provided by the embodiment of the present invention.
Based on the hardware structure, the embodiment of the automatic identification method for the coronary origin abnormality is provided.
Referring to fig. 2, fig. 2 is a flowchart illustrating a first embodiment of an automated method for identifying coronary abnormalities according to the present invention.
In this embodiment, the automated method for identifying coronary origin abnormality includes the steps of:
step S10: a coronary CTA image of a first coronary artery is acquired.
It should be noted that, the execution body of the embodiment may be a computing service device with functions of data processing, network communication and program running, such as a mobile phone, a tablet computer, a personal computer, etc., or an electronic device or an automatic identification device of coronary origin abnormality capable of implementing the above functions. This embodiment and the following embodiments will be described below by taking an automatic identification device for coronary origin abnormality as an example.
It should be noted that, the coronary CTA image is obtained through CT blood vessel imaging, which is a very important part in CT clinical application, and conventional CT panning often has difficulty in displaying the coronary blood vessel due to the natural contrast difference between the coronary blood vessel and its background soft tissue. During CTA examination, contrast agent needs to be introduced to change the image contrast of the coronary blood vessel and the background tissue, so that the coronary blood vessel is highlighted. The coronary artery CTA image is a 3D image and has better three-dimensional information, three-dimensional spatial information of coronary vessels can be intuitively and stereoscopically presented by carrying out three-dimensional reconstruction on the coronary artery CTA image, and functional information such as 3DVR, vessel cross section, 3D MIP, face CPR, line CPR, slice images, CT-FFR and the like can be derived by the CTA image.
The coronary origin abnormality may be a coronary high position (i.e., the left coronary entrance point or the right coronary entrance point is located at a position further from the aortic sinus), or the left coronary may not originate from the left sinus, or the right coronary may not originate from the right sinus.
Step S20: determining an aortic segmentation binary image, a coronary multi-class segmentation image and an aortic sinus multi-class segmentation image of the first coronary according to the coronary CTA image, and extracting an aortic centerline based on the aortic segmentation binary image, wherein the coronary multi-class segmentation image comprises a left coronary segmentation image and a right coronary segmentation image.
The aortic sinus refers to the lumen between the valve and the aortic wall where the opposite arterial wall of the aortic valve bulges outward.
In a specific implementation, the coronary CTA image may be input into a first depth convolution network to obtain a main coronary segmentation binary image, where the first depth convolution network is a trained first depth convolution network, and a training process of the trained first depth convolution network specifically includes: inputting a large number of coronary artery CTA images into an initial first depth convolution network to obtain a plurality of predicted aortic segmentation binary images, continuously comparing the manually marked aortic segmentation binary images with the predicted aortic segmentation binary images, continuously feeding back the difference obtained by comparison to the initial first depth convolution neural network, so as to iteratively update network parameters of the initial first depth convolution network, obtain a trained first depth convolution network, and carrying out aortic segmentation according to the coronary artery CTA images through the first depth convolution network to obtain the aortic segmentation binary images.
In a specific implementation, the coronary CTA image can be input into a second depth convolution network to obtain a coronary multiclass segmentation map, wherein the second depth convolution network is a trained second depth convolution network, and the training process of the trained second depth convolution network specifically comprises the following steps of: inputting a large number of coronary artery CTA images into an initial second depth convolution network to obtain a plurality of predicted coronary artery multi-class segmentation graphs, wherein the predicted coronary artery multi-class segmentation graphs comprise background prediction labels, left coronary artery prediction labels and right coronary artery prediction labels, the manually marked coronary artery multi-class segmentation graphs comprise manually marked backgrounds, manually marked left coronary arteries and manually marked right coronary arteries, the manually marked coronary artery multi-class segmentation graphs are continuously compared with the predicted coronary artery multi-class segmentation graphs, and differences obtained through comparison are continuously fed back to the initial second depth convolution network, so that network parameters of the initial second depth convolution network are updated iteratively, a trained second depth convolution network is obtained, coronary artery multi-class segmentation graphs can be obtained through the second depth convolution network according to coronary artery CTA images.
In a specific implementation, the coronary CTA image can be input into a third depth convolution network to obtain an aortic sinus multi-class segmentation map, wherein the third depth convolution network is a trained third depth convolution network, and the training process of the trained third depth convolution network specifically comprises the following steps of: inputting a large number of coronary artery CTA images into an initial third depth convolution network to obtain a plurality of prediction aortic sinus multi-class segmentation maps, wherein the prediction coronary artery multi-class segmentation maps comprise left sinus prediction labels, right Dou Mai prediction labels and unknown sinus prediction labels, the artificial marked aortic sinus multi-class segmentation maps comprise artificial marked left sinuses, artificial marked right sinuses and artificial marked unknown sinuses, the artificial marked aortic sinus multi-class segmentation maps are continuously compared with the prediction aortic sinus multi-class segmentation maps, and differences obtained by comparison are continuously fed back to the initial third depth convolution network, so that network parameters of the initial third depth convolution network are updated iteratively, a trained third depth convolution network is obtained, aortic sinus segmentation can be carried out according to the coronary artery CTA images through the third depth convolution network, and the aortic sinus multi-class segmentation maps are obtained.
In an embodiment, the extracting the aortic centerline based on the aortic segmentation binary map includes:
and extracting an aortic centerline through deep learning or image processing based on the aortic segmentation binary image.
Step S30: and respectively performing expansion treatment on the left coronary artery segmentation map and the right coronary artery segmentation map to obtain a new left coronary artery segmentation map and a new right coronary artery segmentation map.
In an embodiment, the expanding the left coronary segmented graph and the right coronary segmented graph to obtain a new left coronary segmented graph and a new right coronary segmented graph includes:
performing expansion processing on the left coronary artery segmentation map so that the intersection of the new left coronary artery segmentation map and the aortic segmentation binary image is not an empty set;
and performing expansion processing on the right coronary artery segmentation map so that the intersection of the new right coronary artery segmentation map and the aortic artery segmentation binary image is not an empty set.
It should be noted that, the expansion processing is an image processing operation method, and the expansion processing of the left coronary segmented graph refers to expanding boundary points of the left coronary in the coronary multi-class segmented graph, that is, combining all background points in contact with the left coronary into the left coronary to expand the boundary of the left coronary to the outside, so as to obtain the left coronary segmented graph after the expansion processing; the expansion processing of the right coronary segmented graph refers to expansion of boundary points of the right coronary in the coronary multi-class segmented graph, namely, all background points in contact with the right coronary are combined into the right coronary, so that the boundary of the right coronary is expanded to the outside, and the expanded right coronary segmented graph is obtained.
Step S40: and intercepting the aortic sinus multi-class segmentation map by using a target plane to obtain a maximum aortic cross section, wherein the target plane is a plane perpendicular to the aortic center line.
In an embodiment, the capturing the aortic sinus multi-class segmentation map with a target plane to obtain a maximum aortic cross section, where the target plane is a plane perpendicular to the aortic centerline, includes:
intercepting the aortic sinus multi-class segmentation map by using a target plane to obtain a plurality of binary segmentation seg_N, wherein each seg_N corresponds to a coronary sinus cross-sectional area, and the target plane is a plane perpendicular to the aortic center line;
the seg_N corresponding to the maximum aortic cross-sectional area is taken as the maximum aortic cross-section.
Since the number of target planes is not limited to one, a plurality of truncated binary segments seg_n can be obtained by truncating the aortic sinus using the target planes, and the area corresponding to each binary segment seg_n is seg_s, and the plane corresponding to the largest seg_s can be defined as the largest aortic cross section.
In an embodiment, the aortic sinus multi-class segmentation map comprises a left Dou Biaoqian, a right sinus label, and a nameless sinus label; wherein,,
After the seg_n corresponding to the maximum aortic cross-sectional area is taken as the maximum aortic cross-section, the method further comprises:
from the left Dou Biaoqian, right sinus tag, and the innominate Dou Biaoqian, a left Dou Ouyu, right sinus region, and innominate sinus region are determined on the maximum aortic cross-section.
The left Dou Ouyu, right sinus region, and the innominate sinus region on the maximum aortic cross section may be determined according to the aortic sinus multi-class segmentation map including the left Dou Biaoqian, right sinus label, and innominate sinus label.
Step S50: and determining a left connected domain and a right connected domain based on the new left coronary segmentation map, the new right coronary segmentation map and the aortic segmentation binary map, and determining a left centroid of the left connected domain and a right centroid of the right connected domain.
The left connected region refers to a region where the new left coronary artery segmentation map intersects the aortic artery segmentation binary map, and the right connected region refers to a region where the new right coronary artery segmentation map intersects the aortic artery segmentation binary map.
Step S60: determining a distance from the left centroid to the maximum aortic cross section as a first planar distance and determining a distance from the right centroid to the maximum aortic cross section as a second planar distance.
Step S70: and judging whether the first plane distance or the second plane distance is larger than a preset distance.
The preset distance is set in advance.
Step S80: and when the first plane distance or the second plane distance is larger than a preset distance, determining that the origin abnormality of the first coronary artery is a coronary artery high position.
It should be noted that the coronary origin abnormality may be a coronary high position (i.e., a position where the left coronary entry point or the right coronary entry point is farther from the aortic sinus).
In particular implementations, whether the coronary origin is high may be determined by determining the distance of the left centroid to the largest aortic cross section or the distance of the right centroid to the largest aortic cross section.
The present embodiment is performed by acquiring a coronary CTA image of a first coronary artery; determining an aortic segmentation binary image, a coronary multi-class segmentation image and an aortic sinus multi-class segmentation image of the first coronary according to the coronary CTA image, and extracting an aortic centerline based on the aortic segmentation binary image, wherein the coronary multi-class segmentation image comprises a left coronary segmentation image and a right coronary segmentation image; performing expansion treatment on the left coronary segmentation map and the right coronary segmentation map respectively to obtain a new left coronary segmentation map and a new right coronary segmentation map; intercepting the aortic sinus multi-class segmentation map by using a target plane to obtain a maximum aortic cross section, wherein the target plane is a plane perpendicular to the aortic center line; determining a left connected domain and a right connected domain based on the new left coronary segmentation map, the new right coronary segmentation map and the aortic segmentation binary map, and determining a left centroid of the left connected domain and a right centroid of the right connected domain; determining the distance from the left centroid to the maximum aortic cross section as a first planar distance, and determining the distance from the right centroid to the maximum aortic cross section as a second planar distance; judging whether the first plane distance or the second plane distance is larger than a preset distance; and when the first plane distance or the second plane distance is larger than a preset distance, determining that the origin abnormality of the first coronary artery is a coronary artery high position. By the method, the coronary artery origin anomaly determination is not needed to be carried out on the acquired coronary artery angiography image manually by a doctor, the coronary artery origin anomaly can be automatically identified, the anomaly category of the coronary artery origin anomaly can be determined, the determination efficiency can be improved, and medical resources can be saved.
Referring to fig. 3, fig. 3 is a flowchart illustrating a method for automatically identifying coronary abnormalities according to a second embodiment of the present invention.
Based on the first embodiment described above, the maximum aortic cross section comprises left Dou Ouyu, right sinus region and innominate sinus region; wherein,,
the automated method for identifying coronary origin abnormality of the present embodiment further includes, after the step S80:
step S801: and when the first plane distance or the second plane distance is not larger than a preset distance, projecting the left projection point onto the maximum aortic cross section to obtain a new left projection point.
The left projection point is a projection point of the left centroid projected on the maximum aortic cross section.
Step S802: and respectively determining the distances from the left projection point to the left sinus region, the right sinus region and the innominate sinus region as a first left distance, a second left distance and a third left distance.
Step S803: and judging whether the first left distance is the smallest distance among the first left distance, the second left distance and the third left distance.
It will be appreciated that when the first left distance is the smallest of the first left distance, the second left distance, and the third left distance, it may be explained that the left crown originates from the left sinus, i.e., the origin of the left coronary artery is normal, and when the first left distance is not the smallest of the first left distance, the second left distance, and the third left distance, the left crown may originate from the right sinus or the innominate sinus, i.e., the origin of the left coronary artery is abnormal.
Step S804: if not, judging the minimum distance in the second left distance and the third left distance.
Step S805: and if the minimum distance is determined to be the second left distance, determining that the origin abnormality of the first coronary artery is that the left coronary artery originates from the right sinus.
Step S806: if the minimum distance is determined to be the third left distance, determining that the origin abnormality of the first coronary artery is that the left crown originates from the innominate sinus.
In the present embodiment, it is possible to automatically determine not only whether or not the origin of coronary artery is abnormal, but also to accurately determine the origin sinus of the left crown of the origin abnormality when determining that the origin of the left crown is abnormal.
Referring to fig. 4, fig. 4 is a flowchart illustrating a method for automatically identifying coronary abnormalities according to a second embodiment of the present invention.
Based on the first embodiment described above, the maximum aortic cross section comprises left Dou Ouyu, right sinus region and innominate sinus region; wherein,,
the automated method for identifying coronary origin abnormality of the present embodiment further includes, after the step S80:
step S901: and when the first plane distance or the second plane distance is not larger than a preset distance, projecting the right projection point onto the maximum aortic cross section to obtain a right projection point.
The right projection point is a projection point of the right centroid projected on the maximum aortic cross section.
Step S902: and respectively determining the distances from the right projection point to the left sinus region, the right sinus region and the innominate sinus region as a first right distance, a second right distance and a third right distance.
Step S903: and judging whether the second right distance is the smallest distance among the first right distance, the second right distance and the third right distance.
It will be appreciated that when the second right distance is the smallest of the first right distance, the second right distance, and the third right distance, it may be stated that the right origin is the right sinus, i.e., the origin of the right coronary artery is normal, and when the second right distance is not the smallest of the first right distance, the second right distance, and the third right distance, the right coronary artery may originate from the left sinus or the unknown sinus, i.e., the origin of the right coronary artery is abnormal.
Step S904: if not, judging the minimum distance in the first right distance and the third right distance.
Step S905: and if the minimum distance is determined to be the first right distance, determining that the origin abnormality of the first coronary artery is that the right coronary artery originates from the left sinus.
Step S906: if the minimum distance is determined to be the third right distance, determining that the origin abnormality of the first coronary artery is that the right crown originates from the innominate sinus.
In the present embodiment, it is possible to automatically determine not only whether or not the origin of coronary artery is abnormal, but also to accurately determine the origin sinus of the right crown having an origin abnormality when determining that the origin of the right crown is abnormal.
Furthermore, an embodiment of the present invention proposes a storage medium having stored thereon an automated identification program of a coronary origin anomaly, which when executed by a processor implements the steps of the automated identification method of a coronary origin anomaly as described above.
Referring to fig. 5, fig. 5 is a block diagram showing the construction of a first embodiment of an automated device for identifying coronary origin abnormalities according to the present invention.
As shown in fig. 5, an automated device for identifying coronary origin abnormality according to an embodiment of the present invention includes:
an acquisition module 10 for acquiring a coronary CTA image of a first coronary artery;
a determining module 20, configured to determine an aortic segmentation binary image, a coronary multi-class segmentation image, and an aortic sinus multi-class segmentation image of the first coronary, according to the coronary CTA image, and extract an aortic centerline based on the aortic segmentation binary image, where the coronary multi-class segmentation image includes a left coronary segmentation image and a right coronary segmentation image;
an expansion module 30, configured to perform expansion processing on the left coronary segmented graph and the right coronary segmented graph, respectively, to obtain a new left coronary segmented graph and a new right coronary segmented graph;
The determining module 20 is further configured to intercept the aortic sinus multi-class segmentation map with a target plane, to obtain a maximum aortic cross section, where the target plane is a plane perpendicular to the aortic centerline;
the determining module 20 is further configured to determine a left connected domain and a right connected domain based on the new left coronary segmentation map, the new right coronary segmentation map, and the aortic segmentation binary map, and determine a left centroid of the left connected domain and a right centroid of the right connected domain;
the determining module 20 is further configured to determine a distance from the left centroid to the maximum aortic cross section as a first planar distance, and determine a distance from the right centroid to the maximum aortic cross section as a second planar distance;
a judging module 40, configured to judge whether the first plane distance or the second plane distance is greater than a preset distance;
the determining module 20 is further configured to determine that the origin anomaly of the first coronary artery is a coronary artery high level when it is determined that the first plane distance or the second plane distance is greater than a preset distance.
It should be understood that the foregoing is illustrative only and is not limiting, and that in specific applications, those skilled in the art may set the invention as desired, and the invention is not limited thereto.
The present embodiment is performed by acquiring a coronary CTA image of a first coronary artery; determining an aortic segmentation binary image, a coronary multi-class segmentation image and an aortic sinus multi-class segmentation image of the first coronary according to the coronary CTA image, and extracting an aortic centerline based on the aortic segmentation binary image, wherein the coronary multi-class segmentation image comprises a left coronary segmentation image and a right coronary segmentation image; performing expansion treatment on the left coronary segmentation map and the right coronary segmentation map respectively to obtain a new left coronary segmentation map and a new right coronary segmentation map; intercepting the aortic sinus multi-class segmentation map by using a target plane to obtain a maximum aortic cross section, wherein the target plane is a plane perpendicular to the aortic center line; determining a left connected domain and a right connected domain based on the new left coronary segmentation map, the new right coronary segmentation map and the aortic segmentation binary map, and determining a left centroid of the left connected domain and a right centroid of the right connected domain; determining the distance from the left centroid to the maximum aortic cross section as a first planar distance, and determining the distance from the right centroid to the maximum aortic cross section as a second planar distance; judging whether the first plane distance or the second plane distance is larger than a preset distance; and when the first plane distance or the second plane distance is larger than a preset distance, determining that the origin abnormality of the first coronary artery is a coronary artery high position. By the method, the coronary artery origin anomaly determination is not needed to be carried out on the acquired coronary artery angiography image manually by a doctor, the anomaly category of the coronary artery origin anomaly can be automatically identified and determined, the determination efficiency can be improved, and medical resources can be saved.
In an embodiment, the maximum aortic cross section comprises a left Dou Ouyu, right sinus region, and nameless sinus region; wherein,,
the judging module 40 is further configured to:
when the first plane distance or the second plane distance is not larger than a preset distance, projecting the left centroid onto the maximum aortic cross section to obtain a left projection point;
respectively determining the distances from the left projection point to the left sinus region, the right sinus region and the innominate sinus region as a first left distance, a second left distance and a third left distance;
judging whether the first left distance is the smallest distance among the first left distance, the second left distance and the third left distance;
if not, judging the minimum distance in the second left distance and the third left distance;
if the minimum distance is determined to be a second left distance, determining that the origin abnormality of the first coronary artery is that the left coronary artery originates from the right sinus;
if the minimum distance is determined to be the third left distance, determining that the origin abnormality of the first coronary artery is that the left crown originates from the innominate sinus.
In an embodiment, the maximum aortic cross section comprises a left Dou Ouyu, right sinus region, and nameless sinus region; wherein,,
The judging module 40 is further configured to:
when the first plane distance or the second plane distance is not larger than a preset distance, projecting the right centroid onto the maximum aortic cross section to obtain a right projection point;
respectively determining the distances from the right projection point to the left sinus region, the right sinus region and the innominate sinus region as a first right distance, a second right distance and a third right distance;
judging whether the second right distance is the smallest distance among the first right distance, the second right distance and the third right distance;
if not, judging the minimum distance in the first right distance and the third right distance;
if the minimum distance is determined to be a first right distance, determining that the origin abnormality of the first coronary artery is that the right coronary artery originates from the left sinus;
if the minimum distance is determined to be the third right distance, determining that the origin abnormality of the first coronary artery is that the right crown originates from the innominate sinus.
In an embodiment, the expansion module 30 is further configured to:
performing expansion processing on the left coronary artery segmentation map so that the intersection of the new left coronary artery segmentation map and the aortic segmentation binary image is not an empty set;
And performing expansion processing on the right coronary artery segmentation map so that the intersection of the new right coronary artery segmentation map and the aortic artery segmentation binary image is not an empty set.
In an embodiment, the determining module 20 is further configured to:
intercepting the aortic sinus multi-class segmentation map by using a target plane to obtain a plurality of binary segmentation seg_N, wherein each seg_N corresponds to a coronary sinus cross-sectional area, and the target plane is a plane perpendicular to the aortic center line;
the seg_N corresponding to the maximum aortic cross-sectional area is taken as the maximum aortic cross-section.
In an embodiment, the aortic sinus multi-class segmentation map comprises a left Dou Biaoqian, a right sinus label, and a nameless sinus label; wherein,,
the determining module 20 is further configured to:
from the left Dou Biaoqian, right sinus tag, and the innominate Dou Biaoqian, a left Dou Ouyu, right sinus region, and innominate sinus region are determined on the maximum aortic cross-section.
In an embodiment, the determining module 20 is further configured to:
and extracting an aortic centerline through deep learning or image processing based on the aortic segmentation binary image.
It should be noted that the above-described working procedure is merely illustrative, and does not limit the scope of the present invention, and in practical application, a person skilled in the art may select part or all of them according to actual needs to achieve the purpose of the embodiment, which is not limited herein.
In addition, technical details not described in detail in this embodiment may refer to the automatic identification method of coronary origin abnormality provided in any embodiment of the present invention, which is not described herein.
Furthermore, it should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. Read Only Memory)/RAM, magnetic disk, optical disk) and including several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method according to the embodiments of the present invention.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (10)
1. An automated method for identifying a coronary origin abnormality, the automated method comprising:
acquiring a coronary artery CTA image of a first coronary artery;
determining an aortic segmentation binary image, a coronary multi-class segmentation image and an aortic sinus multi-class segmentation image of the first coronary according to the coronary CTA image, and extracting an aortic centerline based on the aortic segmentation binary image, wherein the coronary multi-class segmentation image comprises a left coronary segmentation image and a right coronary segmentation image;
performing expansion treatment on the left coronary segmentation map and the right coronary segmentation map respectively to obtain a new left coronary segmentation map and a new right coronary segmentation map;
intercepting the aortic sinus multi-class segmentation map by using a target plane to obtain a maximum aortic cross section, wherein the target plane is a plane perpendicular to the aortic center line;
Determining a left connected domain and a right connected domain based on the new left coronary segmentation map, the new right coronary segmentation map and the aortic segmentation binary map, and determining a left centroid of the left connected domain and a right centroid of the right connected domain;
determining the distance from the left centroid to the maximum aortic cross section as a first planar distance, and determining the distance from the right centroid to the maximum aortic cross section as a second planar distance;
judging whether the first plane distance or the second plane distance is larger than a preset distance;
and when the first plane distance or the second plane distance is larger than a preset distance, determining that the origin abnormality of the first coronary artery is a coronary artery high position.
2. The method of claim 1, wherein the maximum aortic cross section comprises a left Dou Ouyu, a right sinus region, and a nameless sinus region; wherein,,
after the judging whether the first plane distance or the second plane distance is greater than a preset distance, the method further comprises:
when the first plane distance or the second plane distance is not larger than a preset distance, projecting the left centroid onto the maximum aortic cross section to obtain a left projection point;
Respectively determining the distances from the left projection point to the left sinus region, the right sinus region and the innominate sinus region as a first left distance, a second left distance and a third left distance;
judging whether the first left distance is the smallest distance among the first left distance, the second left distance and the third left distance;
if not, judging the minimum distance in the second left distance and the third left distance;
if the minimum distance is determined to be a second left distance, determining that the origin abnormality of the first coronary artery is that the left coronary artery originates from the right sinus;
if the minimum distance is determined to be the third left distance, determining that the origin abnormality of the first coronary artery is that the left crown originates from the innominate sinus.
3. The method of claim 1, wherein the maximum aortic cross section comprises a left Dou Ouyu, a right sinus region, and a nameless sinus region; wherein,,
after the judging whether the first plane distance or the second plane distance is greater than a preset distance, the method further comprises:
when the first plane distance or the second plane distance is not larger than a preset distance, projecting the right centroid onto the maximum aortic cross section to obtain a right projection point;
Respectively determining the distances from the right projection point to the left sinus region, the right sinus region and the innominate sinus region as a first right distance, a second right distance and a third right distance;
judging whether the second right distance is the smallest distance among the first right distance, the second right distance and the third right distance;
if not, judging the minimum distance in the first right distance and the third right distance;
if the minimum distance is determined to be a first right distance, determining that the origin abnormality of the first coronary artery is that the right coronary artery originates from the left sinus;
if the minimum distance is determined to be the third right distance, determining that the origin abnormality of the first coronary artery is that the right crown originates from the innominate sinus.
4. The method of claim 1, wherein the expanding the left and right coronary segmented maps to obtain a new left and right coronary segmented map, respectively, comprises:
performing expansion processing on the left coronary artery segmentation map so that the intersection of the new left coronary artery segmentation map and the aortic segmentation binary image is not an empty set;
and performing expansion processing on the right coronary artery segmentation map so that the intersection of the new right coronary artery segmentation map and the aortic artery segmentation binary image is not an empty set.
5. The method of claim 1, wherein the taking the aortic sinus multi-class segmentation map with a target plane results in a maximum aortic cross-section, wherein the target plane is a plane perpendicular to the aortic centerline, comprising:
intercepting the aortic sinus multi-class segmentation map by using a target plane to obtain a plurality of binary segmentation seg_N, wherein each seg_N corresponds to a coronary sinus cross-sectional area, and the target plane is a plane perpendicular to the aortic center line;
the seg_N corresponding to the maximum aortic cross-sectional area is taken as the maximum aortic cross-section.
6. The method of claim 5, wherein the aortic sinus multi-class segmentation map comprises a left Dou Biaoqian, a right sinus label, and a nameless sinus label; wherein,,
after the seg_n corresponding to the maximum aortic cross-sectional area is taken as the maximum aortic cross-section, the method further comprises:
from the left Dou Biaoqian, right sinus tag, and the innominate Dou Biaoqian, a left Dou Ouyu, right sinus region, and innominate sinus region are determined on the maximum aortic cross-section.
7. The method of claim 1, wherein the extracting an aortic centerline based on the aortic segmentation binary map comprises:
And extracting an aortic centerline through deep learning or image processing based on the aortic segmentation binary image.
8. An automated identification apparatus for coronary origin abnormality, characterized in that the automated identification apparatus for coronary origin abnormality comprises:
the acquisition module is used for acquiring a coronary artery CTA image of the first coronary artery;
the determining module is used for determining an aortic segmentation binary image, a coronary multi-class segmentation image and an aortic sinus multi-class segmentation image of the first coronary according to the coronary CTA image, and extracting an aortic centerline based on the aortic segmentation binary image, wherein the coronary multi-class segmentation image comprises a left coronary segmentation image and a right coronary segmentation image;
the expansion module is used for respectively carrying out expansion processing on the left coronary segmentation map and the right coronary segmentation map to obtain a new left coronary segmentation map and a new right coronary segmentation map;
the determining module is further configured to intercept the aortic sinus multi-class segmentation map by using a target plane to obtain a maximum aortic cross section, where the target plane is a plane perpendicular to the aortic centerline;
the determining module is further configured to determine a left connected domain and a right connected domain based on the new left coronary segmentation map, the new right coronary segmentation map, and the aortic segmentation binary map, and determine a left centroid of the left connected domain and a right centroid of the right connected domain;
The determining module is further configured to determine that a distance from the left centroid to the maximum aortic cross section is a first planar distance, and determine that a distance from the right centroid to the maximum aortic cross section is a second planar distance;
the judging module is used for judging whether the first plane distance or the second plane distance is larger than a preset distance;
the determining module is further configured to determine that the origin anomaly of the first coronary artery is a coronary artery high position when it is determined that the first plane distance or the second plane distance is greater than a preset distance.
9. An automated identification apparatus for coronary origin abnormalities, said apparatus comprising: a memory, a processor and an automated identification program stored on the memory and executable on the processor for coronary origin anomalies, the automated identification program for coronary origin anomalies being configured to implement the steps of the automated identification method for coronary origin anomalies according to any one of claims 1 to 7.
10. A storage medium having stored thereon an automated identification program of a coronary origin anomaly, which when executed by a processor, implements the steps of the automated identification method of a coronary origin anomaly of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310924038.7A CN116823806A (en) | 2023-07-26 | 2023-07-26 | Automatic identification method, device, equipment and storage medium for coronary origin abnormality |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310924038.7A CN116823806A (en) | 2023-07-26 | 2023-07-26 | Automatic identification method, device, equipment and storage medium for coronary origin abnormality |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116823806A true CN116823806A (en) | 2023-09-29 |
Family
ID=88124187
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310924038.7A Pending CN116823806A (en) | 2023-07-26 | 2023-07-26 | Automatic identification method, device, equipment and storage medium for coronary origin abnormality |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116823806A (en) |
-
2023
- 2023-07-26 CN CN202310924038.7A patent/CN116823806A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7569843B2 (en) | Method and system for analyzing intracranial blood vessels | |
| CN102245082B (en) | Image display apparatus, control method thereof and image processing system | |
| US10950204B2 (en) | Diagnosis support apparatus and diagnosis support method | |
| Xian et al. | Main coronary vessel segmentation using deep learning in smart medical | |
| EP3741288A1 (en) | Diagnosis support device, learning device, diagnosis support method, learning method, and program | |
| CN112967284B (en) | Vascular image segmentation analysis method, device, equipment and storage medium | |
| US11783481B2 (en) | Identifying vessel occlusions using spatial patterns | |
| Isgum et al. | Automatic detection of calcifications in the aorta from CT scans of the abdomen1: 3D computer-aided diagnosis | |
| US20220277455A1 (en) | Methods and Systems for Determining Coronary Hemodynamic Characteristic(s) That is Predictive of Myocardial Infarction | |
| CN115115657A (en) | Focus segmentation method and device, electronic device and storage medium | |
| Maragna et al. | Artificial intelligence based multimodality imaging: a new frontier in coronary artery disease management | |
| CN113469963B (en) | Pulmonary artery image segmentation method and device | |
| JP2009301254A (en) | Image processing device, method and program | |
| US11200978B2 (en) | Information processing apparatus, information processing method, and non-transitory computer-readable storage medium | |
| CN116823806A (en) | Automatic identification method, device, equipment and storage medium for coronary origin abnormality | |
| US11335002B2 (en) | Deviation detection device, method, and program | |
| US11295448B1 (en) | Concurrent display of hemodynamic parameters and damaged brain tissue | |
| KR20230127762A (en) | Device and method for detecting lesions of disease related to body component that conveyes fluid from medical image | |
| CN108984587B (en) | Information processing apparatus, information processing method, information processing system, and storage medium | |
| US11776121B2 (en) | Method and apparatus for providing information needed for diagnosis of lymph node metastasis of thyroid cancer | |
| CN114820591B (en) | Image processing method, image processing apparatus, electronic device, and medium | |
| Chen et al. | Deep learning-based automatic left atrial appendage filling defects assessment on cardiac computed tomography for clinical and subclinical atrial fibrillation patients | |
| Ammann et al. | Multilevel comparison of deep learning models for function quantification in cardiovascular magnetic resonance: On the redundancy of architectural variations | |
| US20230036757A1 (en) | Concurrent display of hemodynamic parameters and damaged brain tissue | |
| JP7151464B2 (en) | Lung image processing program, lung image processing method and lung image processing system |
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 |