[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

CN111145160B - Method, device, server and medium for determining coronary artery branches where calcified regions are located - Google Patents

Method, device, server and medium for determining coronary artery branches where calcified regions are located Download PDF

Info

Publication number
CN111145160B
CN111145160B CN201911384603.5A CN201911384603A CN111145160B CN 111145160 B CN111145160 B CN 111145160B CN 201911384603 A CN201911384603 A CN 201911384603A CN 111145160 B CN111145160 B CN 111145160B
Authority
CN
China
Prior art keywords
image
heart
processed
determining
coronary
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201911384603.5A
Other languages
Chinese (zh)
Other versions
CN111145160A (en
Inventor
王晓东
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai United Imaging Healthcare Co Ltd
Original Assignee
Shanghai United Imaging Healthcare Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shanghai United Imaging Healthcare Co Ltd filed Critical Shanghai United Imaging Healthcare Co Ltd
Priority to CN201911384603.5A priority Critical patent/CN111145160B/en
Publication of CN111145160A publication Critical patent/CN111145160A/en
Application granted granted Critical
Publication of CN111145160B publication Critical patent/CN111145160B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
    • G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
    • G06T7/344—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods involving models
    • 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
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • 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
    • G06T2207/20092—Interactive image processing based on input by user
    • G06T2207/20104—Interactive definition of region of interest [ROI]
    • 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
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Medical Informatics (AREA)
  • Quality & Reliability (AREA)
  • Radiology & Medical Imaging (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Apparatus For Radiation Diagnosis (AREA)
  • Image Analysis (AREA)

Abstract

The embodiment of the invention discloses a method, a device, a server and a storage medium for determining coronary branches where calcified regions are located, wherein the method comprises the following steps: acquiring an image to be processed, and registering a heart model obtained in advance on the image to be processed to obtain a first preprocessed image, wherein the image to be processed comprises a calcified region; obtaining a heart chamber model corresponding to the image to be processed based on the first preprocessing image; and determining the target coronary branch where the calcified region is located according to the target cavity where the calcified region is located in the heart cavity model and the probability value that the calcified region is located on at least one candidate coronary branch in the target cavity. The technical scheme of the embodiment of the invention solves the technical problem that in the prior art, a worker is required to determine which coronary artery the calcification point is positioned on according to experience, and has a certain error, and realizes the technical effect of rapidly and accurately determining the target coronary artery to which the calcification point belongs.

Description

Method, device, server and medium for determining coronary artery branches where calcified regions are located
Technical Field
The embodiment of the invention relates to the technical field of medical treatment, in particular to a method, a device, a server and a storage medium for determining coronary branches where calcified regions are located.
Background
Coronary artery disease has become the disease with the highest mortality rate worldwide. With the development of medical imaging technology, cardiac CT imaging is increasingly being used for the detection of coronary artery disease. Cardiac CT scanning is mainly two ways, enhanced scanning and non-enhanced scanning, respectively. Non-enhanced scanning, also known as panning, requires the injection of contrast media, and the flow of blood containing contrast media exhibits high brightness in CT, which is primarily used to view vascular lumens, heart chambers, and myocardial perfusion. But is not sufficiently sensitive to vascular calcification because the CT values of the vessel lumen overlap with those of calcified plaque during coronary enhanced scanning and cannot be fully distinguished. Therefore, looking at coronary calcifications typically employs CT pan-scan images. Calcification score calculations based on calcified plaque detection are also required on CT pan-scan images. However, this brings a new problem that on CT scan images, the lumen of the blood vessel is not developed, and is difficult to distinguish from muscle tissue, and it is impossible to determine on which coronary artery the detected calcified plaque is located, and it is necessary for the doctor to check and recognize in order according to experience.
In the prior art, a worker determines which coronary artery the calcification point is located on according to experience, and certain error exists.
Disclosure of Invention
The embodiment of the invention provides a method, a device, a server and a medium for determining coronary branches where calcified areas are located, so as to achieve the technical effect of rapidly and accurately determining target coronary arteries where calcified points are located.
In a first aspect, an embodiment of the present invention provides a method for determining a coronary branch in which a calcified region is located, where the method includes:
acquiring an image to be processed, and registering with a heart standard model to obtain a first preprocessing image, wherein the image to be processed comprises a calcified region;
processing the heart standard model based on the first processed image to obtain a heart model corresponding to the image to be processed;
calculating a probability value of at least one coronary artery to be candidate in the heart model of the calcified region;
and determining the target coronary artery associated with the calcified region according to the probability value.
In a second aspect, an embodiment of the present invention further provides a device for determining a coronary branch where a calcified region is located, where the device includes:
an image preprocessing module for acquiring an image to be processed, and registering the image with a heart standard model to obtain a first preprocessed image, wherein the image to be processed comprises a calcified region
The heart model determining module is used for processing the heart standard model based on the first preprocessing image and acquiring a heart model corresponding to the image to be processed;
the probability value calculation module is used for calculating the probability value of at least one coronary artery to be candidate in the heart model of the calcified region;
and the coronary branch determining module is used for determining the target coronary associated with the calcified region according to the probability value.
In a third aspect, an embodiment of the present invention further provides a server, where the server includes:
one or more processors;
storage means for storing one or more programs,
when the one or more programs are executed by the one or more processors, the one or more processors implement a method for determining a coronary branch where a calcified region is located according to any one of the embodiments of the invention.
In a fourth aspect, embodiments of the present invention also provide a storage medium containing computer-executable instructions, which when executed by a computer processor, are configured to perform a method of determining a coronary branch in which a calcified region is located according to any of the embodiments of the present invention.
According to the technical scheme, the image to be processed is acquired and registered with the heart standard model to obtain a first preprocessed image, wherein the image to be processed comprises a calcified region; processing a heart standard model based on the first processing image, and acquiring a heart model corresponding to the image to be processed; calculating the probability value of at least one coronary artery to be candidate in the heart model of the calcified region; the method and the device have the advantages that the target coronary artery associated with the calcified region is determined according to the probability value, the technical problem that in the prior art, a worker is required to determine which coronary artery the calcified point is located on according to experience, and certain errors exist is solved, and the technical effect of rapidly and accurately determining the target coronary artery to which the calcified point belongs is achieved.
Drawings
In order to more clearly illustrate the technical solution of the exemplary embodiments of the present invention, a brief description is given below of the drawings required for describing the embodiments. It is obvious that the drawings presented are only drawings of some of the embodiments of the invention to be described, and not all the drawings, and that other drawings can be made according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a method for determining branches of a coronary artery in which calcified regions are located according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a method for determining branches of coronary artery in which calcified regions are located according to a second embodiment of the present invention;
FIG. 3 is a flowchart illustrating a method for determining branches of coronary artery in which calcified regions are located according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of a device for determining coronary branches where calcified regions are located according to a fourth embodiment of the present invention;
fig. 5 is a schematic diagram of a server structure according to a fifth embodiment of the present invention.
Detailed Description
The invention is described in further detail below with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting thereof. It should be further noted that, for convenience of description, only some, but not all of the structures related to the present invention are shown in the drawings.
Example 1
Fig. 1 is a flowchart of a method for determining a coronary branch where a calcified region is located according to an embodiment of the present invention, where the method may be implemented by a device for determining a coronary branch where a calcified region is located, and the device may be implemented in software and/or hardware.
As shown in fig. 1, the method of this embodiment includes:
s110, acquiring an image to be processed, and registering with the heart standard model to obtain a first preprocessed image, wherein the image to be processed comprises a calcified region.
For the sake of clarity of description of the technical solution of this embodiment, the portion to be scanned may be described by taking the heart as an example.
The original image obtained after the part to be scanned is used as the image to be processed. The scanned site may be the heart or other site, etc. Correspondingly, the heart model is obtained by acquiring a plurality of historical heart images in advance and processing the historical heart images. The heart model is used for processing the image to be processed mentioned in the present embodiment, that is, the heart model is a model that performs preliminary processing on the image to be processed. The image processed by the heart model can realize the segmentation of each cavity. The image after the preliminary processing by the heart model may be used as the first pre-processed image.
Specifically, the image to be processed is obtained, a heart standard model obtained through training in advance can be registered to the image to be processed by adopting methods such as registration or generalized Hough transformation, so that a registered image is obtained, and the registered image is used as a first preprocessing image.
It should be noted that, before the heart standard model is configured to the image to be processed, the image to be processed needs to be acquired. Optionally, acquiring a flat scan image corresponding to the target scan site; determining calcified areas in the pan-scan image according to preset conditions; and taking the scanned image of the calcified region as an image to be processed.
The image to be processed is a non-enhanced flat scan image, and since there is no bone structure in the region of the heart, pixels having CT values greater than 130HU may be regarded as calcification points. The calcification points are segmented, the noise area with very small volume is removed, and the rest area is the calcified area.
The target scan site may be understood as a focal site, i.e. a heart site. The preset condition may be whether the pixel value in the pan image is higher than 130HU. If the pixel point is higher than 130HU, the pixel point is used as a calcification point, and correspondingly, the area where the calcification point is located is a calcification area. The image to be processed is an image comprising calcified regions.
Specifically, a scanning image of the heart part is acquired in a flat scanning manner and is used as a flat scanning image. And determining pixel values of all pixel points in the plain scan image, taking the pixel points with the pixel values higher than a preset value as calcification points, and taking the area where the calcification points are located as a calcification area. If the scanned image comprises a calcified region, taking the image comprising the calcified region as an image to be processed; if the scanned image does not include calcified regions, the swept image may not be processed.
S120, processing the heart standard model based on the first preprocessing image, and acquiring a heart model corresponding to the image to be processed.
Wherein the first pre-processed image includes a left ventricle of the heart, a right ventricle, and a calcified region located in the first pre-processed image. The first preprocessed image may be processed using a live contour algorithm to obtain a heart chamber model corresponding to the image to be processed. A heart chamber model may be understood as a model corresponding to each chamber in the heart.
Specifically, the first preprocessed image may be processed by using a moving contour algorithm, so as to obtain a heart model corresponding to the image to be processed.
Obtaining a heart model corresponding to the image to be processed based on the first preprocessing image, including: gridding the first preprocessing image, and acquiring at least one grid point to be adjusted of the cavity edge of the heart standard model corresponding to the first preprocessing image; inputting grid points to be adjusted into a pre-trained cavity edge classifier to obtain probability values of the preset cavity edge positions of the grid points to be adjusted on the image to be processed; and deforming the edges of the chambers corresponding to each chamber according to the probability value to obtain a heart model corresponding to the image to be processed. The gridding processing refers to dividing the first preprocessed image into at least one grid according to a preset rule. And taking the intersection points of the grid lines as grid points, and taking the grid points corresponding to the edges of each chamber in the heart standard model as the grid points to be adjusted. Since the heart chamber edge is formed by lines, a plurality of grid points can be included correspondingly, and the grid points on the chamber edge line are taken as grid points to be adjusted. The number of at least one grid point to be adjusted may be one, two or more, and the number of specific grid points is related to a preset dividing rule and an edge line of the chamber, which is not limited herein. The cavity edge classifier is trained in advance and is used for determining probability values of grid points to be adjusted at certain cavity edge positions and configuring images to be processed.
Specifically, a preset dividing rule is adopted to divide the first preprocessed image into at least one grid, and each grid point on the edge of each cavity is determined and used as the grid point to be adjusted. And inputting the grid points to be adjusted into a pre-trained cavity edge classifier, and determining the probability value of each grid point at the preset cavity edge position. And iteratively adjusting the edges of the cavity to the corresponding edges according to the obtained probability values, so as to realize the segmentation of each cavity under the flat scanning image and obtain a heart model corresponding to the image to be processed.
S130, calculating a probability value of at least one coronary artery to be candidate in the heart model of the calcified region.
Among these, the coronary artery to be candidate may be understood as a branch of the coronary artery where the calcified region may be located.
In particular, since a heart model corresponding to the image to be processed has been obtained, which heart model comprises the individual chambers, from the heart model and the calcified regions, the probability values of the calcified regions on the individual branches of the coronary artery to be selected can be determined.
And S140, determining target coronary artery associated with the calcified region according to the probability value.
Wherein the coronary artery where the calcified region is located is taken as the target coronary artery.
On the basis of step S130, probability values for calcification points in the respective coronary arteries may be determined. And taking the coronary corresponding to the highest probability value as the target coronary.
Optionally, the probability value of each candidate coronary branch of the calcified region is calculated, and the candidate coronary branch with the highest probability value is used as the target coronary branch.
That is, probability values of the calcified region on the respective candidate coronary branches in the heart chamber are determined, respectively, and the candidate coronary branch having the highest probability value is taken as the target coronary branch.
According to the technical scheme, the image to be processed is acquired and registered with the heart standard model to obtain a first preprocessed image, wherein the image to be processed comprises a calcified region; processing a heart standard model based on the first processing image, and acquiring a heart model corresponding to the image to be processed; calculating the probability value of at least one coronary artery to be candidate in the heart model of the calcified region; the method and the device have the advantages that the target coronary artery associated with the calcified region is determined according to the probability value, the technical problem that in the prior art, a worker is required to determine which coronary artery the calcified point is located on according to experience, and certain errors exist is solved, and the technical effect of rapidly and accurately determining the target coronary artery to which the calcified point belongs is achieved.
Example two
Before determining which coronary artery branch the calcified region in the image to be processed is located, a heart standard model and a chamber classifier corresponding to each chamber are also required to be determined, so that the image to be processed is registered based on the heart standard model to obtain a heart model, and the target coronary artery to which the calcified region belongs is determined according to the heart model. Fig. 2 is a flowchart of a method for determining branches of a coronary artery in which a calcified region is located according to a second embodiment of the present invention.
As shown in fig. 2, the method includes:
s210, acquiring a plurality of historical heart images as a plurality of current registration sample images, and marking key information in the current registration samples, wherein the key information comprises the edges of each actual chamber of the heart.
The plurality of historical heart images not only comprise images of patients, but also comprise images of non-patients, namely images of coronary branches to which calcified areas are determined to belong, and images of areas without calcified areas. And taking the plurality of historical heart images as sample images to be trained, namely, the current registration sample images. In order to improve the accuracy of the heart model obtained by final training, as many sample images to be trained as possible can be acquired. The key information in the current registration sample includes: each chamber of the heart is actually a chamber edge, and each coronary branch in the chamber.
Specifically, a plurality of historical heart images are acquired, the actual chamber edges of all chambers in the historical heart images and coronary branches of all chambers are marked, and the images obtained at the moment are used as current registration sample images.
Illustratively, 20 historical cardiac images are acquired and marked in the left atrium, the right atrium, each coronary artery in the left atrium, and each coronary artery in the right atrium of the historical cardiac images, and the marked 20 historical cardiac images are taken as current registered sample images.
S220, selecting one current registration sample image from a plurality of current registration sample images as a reference sample image, taking the rest current registration sample images as sample images to be registered, and registering the reference sample image with each sample image to be registered according to the key information respectively to generate at least one preliminary registration sample image.
Specifically, one of the current registered sample images is selected as a reference sample image, and then the other images in the current registered sample image are taken as sample images to be registered. And registering the reference sample image with the sample image to be registered respectively according to the key information in the reference sample image and the key information in the sample image to be registered, so as to generate at least one preliminary registered sample image.
For example, there are 20 current registered sample images, each image is marked, an image with the number of 1 can be selected as a reference sample image, and images with the numbers of 2-20 are selected as sample images to be registered. And registering the actual edge lines of each chamber in the reference sample image with the number of 1 with the sample images to be registered with the number of 2-20 respectively to obtain 20 registered primary registered sample images.
S230, gridding each actual chamber edge in the preliminary registration sample image to obtain at least one actual chamber edge grid point, and determining the average chamber edge of the preliminary registration sample image according to the coordinates of each actual chamber edge grid point of the reference sample image and the sample image to be registered in the preliminary registration sample image.
Specifically, a preset algorithm is adopted to carry out gridding treatment on the edges of each actual cavity in the preliminary registration sample image, and at least one grid point is obtained. Accordingly, the actual chamber edge grid points corresponding to the marked individual chambers can also be obtained. And determining the average cavity edge grid of the preliminary sample image according to the reference sample image in the preliminary registration sample image and the coordinates of each actual edge grid point of the sample image to be registered. That is, the grid points are averaged for the chamber edges in each preliminary sample image to obtain an averaged heart chamber edge grid.
Illustratively, gridding the preliminary registration sample image to obtain grid points of the edges of the actual chambers, and averaging coordinates corresponding to the grid points of the edges of the actual chambers and the grid points of the edges of the chambers in the reference sample image to obtain average chamber edge grids of the preliminary sample image.
And S240, taking a plurality of the preliminary registration sample images as a plurality of current registration sample images, repeatedly executing the operation of selecting the reference sample images to perform image registration to obtain an average chamber edge until the average chamber edge of the target registration sample image is determined, and determining a heart standard model according to the average chamber edge of the target registration sample image.
The reference image is used as a target registration sample image, namely the number of the current reference image is a number, and the corresponding target registration sample image is a number. A heart model can be understood as an image that is processed with the edges of each chamber of the target registration sample image.
For example, taking the image with the number of 2 as a reference image, taking the rest images as current registration sample images, repeatedly executing S210 to S230 to obtain at least one preliminary registration sample image, and then averaging the at least one preliminary registration sample image to obtain an average cavity edge grid of the preliminary sample image corresponding to the number of 2. The images numbered 3 and 4 … 20 are sequentially taken as reference images, and the rest images are taken as current registration sample images, so that an average chamber edge grid of the preliminary sample image corresponding to the number 3, an average chamber edge grid … of the preliminary sample image corresponding to the number 4 and an average chamber edge grid of the preliminary sample image corresponding to the number 20 are respectively generated. And processing the average cavity edge grids of all the obtained preliminary sample images to obtain a heart standard model.
Determining a heart standard model from the average chamber edge of the target registered sample image in this embodiment includes: determining each coronary branch of the target registration sample image according to the position of each coronary branch marked in the target registration sample image relative to a heart model; a heart model is determined from each coronary branch of the target registered sample image and the average chamber edge.
After obtaining the heart model, calculating the position and distribution area of each coronary artery in the heart model of each registered image, namely, preliminarily registering the position and distribution area of each coronary artery branch marked in the sample image relative to the heart model, and recording the coronary artery branches existing in the distance near the edge grid points of the heart chamber.
After the heart model is obtained, it is also necessary to determine heart chamber classifiers corresponding to the respective chambers in the heart model. Optionally, acquiring a plurality of historical heart images as a plurality of training samples, and marking the edges of each actual chamber of the heart in the training samples; inputting a plurality of marked training samples into a pre-established machine learning model to obtain a chamber edge classifier corresponding to each actual chamber; the heart chamber edge classifier is used for determining probability values of the edges of each chamber in the image to be tested and processing the edges of each chamber according to the probability values.
It can be understood that: according to the marked heart chamber edges in each preliminary sample image, machine learning can be adopted for training to obtain classifiers of each chamber edge in the heart chamber, each classifier can identify the probability that each pixel point is positioned at a certain chamber edge on an unlabeled image. The advantage of determining the respective chamber classifier is that the image to be processed can be registered with the heart model.
According to the technical scheme, the image to be processed is acquired and registered with the heart standard model to obtain a first preprocessed image, wherein the image to be processed comprises a calcified region; processing a heart standard model based on the first processing image, and acquiring a heart model corresponding to the image to be processed; calculating the probability value of at least one coronary artery to be candidate in the heart model of the calcified region; the method and the device have the advantages that the target coronary artery associated with the calcified region is determined according to the probability value, the technical problem that in the prior art, a worker is required to determine which coronary artery the calcified point is located on according to experience, and certain errors exist is solved, and the technical effect of rapidly and accurately determining the target coronary artery to which the calcified point belongs is achieved.
Example III
As a preferred embodiment of the foregoing embodiments, fig. 3 is a flowchart of a method for determining a coronary artery branch where a calcified region is located according to an embodiment of the present invention.
As shown in fig. 3, the method of this embodiment includes:
s301, training data are read in.
A certain amount of training data is selected, optionally thousands or tens of thousands, etc. Training data may be understood as cardiac scan images.
In order to obtain a heart model, the size and resolution of the heart image should be uniform.
Specifically, a preset number of training sample images are acquired to train a heart standard model.
S302, marking the heart chamber and the coronary artery.
The left ventricle, right ventricle, left atrium, right atrium, pulmonary root, aortic root, etc. structures of the heart may be marked on each heart image prior to training data. Meanwhile, marking coronary artery, mainly comprising a left coronary artery trunk, an anterior descending branch, a gyrus branch, a blunt edge branch and a diagonal branch; right coronary artery, anterior descending branch, sharp edge branch, etc.
It should be noted that, in this embodiment, only the heart chambers and the coronary arteries to be marked are listed, but not limited to the above.
S303, generating an average model of the heart chamber.
Wherein the average model of the heart chamber can be understood as a standard model of the heart.
Specifically, each acquired cardiac image is registered to obtain at least one registered image. Gridding the marked heart chamber edge on each registered image, and averaging the points on each grid according to each configuration image to obtain an averaged heart chamber edge grid, so as to generate an average model of the heart chamber.
For example, the number of heart images is twenty, the first image is taken as a reference, and the second image to the twentieth image are registered to the first image, so as to obtain twenty registered images. And respectively carrying out gridding treatment on the edges of each cavity of the twenty registered images to obtain edge grid points corresponding to the edges of each cavity. And determining coordinates of the edge grid points in a space rectangular coordinate system, optionally, respectively determining coordinates of all the edge grid points in twenty images, and averaging the coordinates of the edge grid points at the same position to obtain the average heart chamber edge grid points.
In order to obtain an average model of the heart, a second image is taken as a reference, a third image is registered on the second image respectively to obtain twenty registered images, the twenty registered images are divided into at least one grid in the same mode, the grids of the same position points are averaged, and the average heart chamber edge grid points are obtained. From this, twenty sets of averaged heart chamber edge grid points are obtained. That is, the images can be registered with twenty images as references, respectively, to obtain the grid of the edge of each chamber of the heart after the average of the twenty images. And then, the twenty averaged heart chamber edge grids are averaged to obtain a heart standard model.
S304, marking the coronary area on the cavity model.
The regions of the coronary artery are marked on the heart standard model, the positions and distribution areas of the marked coronary artery regions corresponding to the heart standard model are calculated, and coronary artery branches existing near the edge grid points of each heart chamber are recorded.
S305, training the classifier according to the chamber boundary to obtain each chamber classifier.
And training the marked heart chamber edges on each image by adopting machine learning to obtain each chamber edge classifier corresponding to each chamber. Each chamber classifier can be used to identify probability values for each pixel point at a certain chamber edge on an unlabeled image.
S306, inputting the data after registering the heart model into a chamber classifier, and determining the distribution area of each coronary artery.
And acquiring an image to be tested, and optionally acquiring a heart image of a certain user. Registering the heart image to a heart model obtained by training in advance to obtain a registered image. Gridding the registered image to obtain at least one grid. Wherein at least one grid includes edge grid points for each chamber. The image after gridding treatment is input into a pre-trained cavity classifier, the maximum probability value of the grid on each cavity edge line in the normal direction of the grid can be obtained, and the registered image is deformed according to the probability value to obtain the cavity edge grid attached to the edge of the actual image.
S307, determining the coronary artery where the calcification points are located.
After the chamber iteration deformation is completed, the region of the coronary distribution may be determined.
It should be noted that, in the practical application process, there may be a case where the calcified region is located on two different coronary artery distribution regions, and it is not possible to accurately determine on which coronary artery the calcified region is located. Therefore, it is possible to determine the probability value of each calcified region being located in a certain coronary artery, and to set the coronary artery corresponding to the probability value higher as the target coronary artery, that is, the calcified region being located on the coronary artery.
According to the technical scheme, the image to be processed is acquired and registered with the heart standard model to obtain a first preprocessed image, wherein the image to be processed comprises a calcified region; processing a heart standard model based on the first processing image, and acquiring a heart model corresponding to the image to be processed; calculating the probability value of at least one coronary artery to be candidate in the heart model of the calcified region; the method and the device have the advantages that the target coronary artery associated with the calcified region is determined according to the probability value, the technical problem that in the prior art, a worker is required to determine which coronary artery the calcified point is located on according to experience, and certain errors exist is solved, and the technical effect of rapidly and accurately determining the target coronary artery to which the calcified point belongs is achieved.
Example IV
Fig. 4 is a device for determining branches of coronary artery in which calcified regions are located, provided in a fourth embodiment of the present invention, where the device includes: an image preprocessing module 410, a heart model determination module 420, a probability value calculation module 430, and a coronary branch determination module 440.
The image preprocessing module 410 is configured to acquire an image to be processed, and register the image with the heart standard model to obtain a first preprocessed image, where the image to be processed includes a calcified region; a heart model determining module 420, configured to process the heart standard model based on the first processed image, and obtain a heart model corresponding to the image to be processed; a probability value calculation module 430 for calculating a probability value of at least one coronary artery to be candidate in the heart model for the calcified region; a coronary branch determination module 440 for determining a target coronary associated with the calcified region based on the probability value.
On the basis of the technical scheme, the image preprocessing module further comprises:
the gridding unit is used for gridding the first preprocessing image and acquiring at least one grid point to be adjusted of the cavity edge of the heart standard model corresponding to the first preprocessing image;
The probability value determining unit is used for inputting the grid points to be adjusted into a pre-trained cavity edge classifier to obtain probability values of the preset cavity edge positions of the grid points to be adjusted on the image to be processed;
and the heart chamber determining unit is used for deforming the chamber edge corresponding to each chamber according to the probability value to obtain a heart model corresponding to the image to be processed.
On the basis of the above technical solutions, the probability value determining unit is further configured to:
and respectively calculating probability values of the calcified regions in the coronary arteries to be selected, and taking the coronary artery to be selected corresponding to the coronary artery to be selected with the highest probability value as a target coronary artery.
Based on the above technical solutions, before the image preprocessing module is configured to acquire the image to be processed, the image preprocessing module is further configured to:
acquiring a flat scanning image corresponding to a target scanning part;
determining calcified areas in the pan-scan image according to preset conditions;
and taking the scanned image of the calcified region as the image to be processed.
On the basis of the technical schemes, the device further comprises:
acquiring a plurality of historical heart images as a plurality of current registration sample images, and marking key information in the current registration samples, wherein the key information comprises the edges of each actual chamber of the heart;
Selecting one current registration sample image from a plurality of current registration sample images as a reference sample image, taking the rest current registration sample images as sample images to be registered, and registering the reference sample image with each sample image to be registered according to the key information respectively to generate at least one preliminary registration sample image;
gridding each actual chamber edge in the preliminary registration sample image to obtain at least one actual chamber edge grid point, and determining an average chamber edge of the preliminary registration sample image according to coordinates of each actual chamber edge grid point of the reference sample image and the sample image to be registered in the preliminary registration sample image;
and taking the plurality of preliminary registration sample images as a plurality of current registration sample images, repeatedly executing the operation of selecting the reference sample images to perform image registration to obtain an average chamber edge until the average chamber edge of the target registration sample image is determined, and determining a heart chamber standard model according to the average chamber edge of the target registration sample image.
On the basis of the above technical solutions, the key information includes coronary branches of the heart, and the determining a heart standard model according to an average chamber edge of the target registration sample image includes:
Determining each coronary branch of the target registration sample image according to the position of each coronary branch marked in the target registration sample image relative to a heart standard model;
a heart standard model is determined from each coronary branch of the target registered sample image and the average chamber edge.
On the basis of the technical schemes, the device further comprises:
the system comprises a training sample acquisition unit, a processing unit and a processing unit, wherein the training sample acquisition unit is used for acquiring a plurality of historical heart images as a plurality of training samples and marking the edges of each actual chamber of the heart in the training samples;
the chamber edge classifier unit is used for inputting a plurality of marked training samples into a pre-established machine learning model to obtain a chamber edge classifier corresponding to each actual chamber;
the heart chamber edge classifier is used for registering the image to be processed.
According to the technical scheme, the image to be processed is acquired and registered with the heart standard model to obtain a first preprocessed image, wherein the image to be processed comprises a calcified region; processing a heart standard model based on the first processing image, and acquiring a heart model corresponding to the image to be processed; calculating the probability value of at least one coronary artery to be candidate in the heart model of the calcified region; the method and the device have the advantages that the target coronary artery associated with the calcified region is determined according to the probability value, the technical problem that in the prior art, a worker is required to determine which coronary artery the calcified point is located on according to experience, and certain errors exist is solved, and the technical effect of rapidly and accurately determining the target coronary artery to which the calcified point belongs is achieved.
The device for determining the coronary artery branch of the calcified region provided by the embodiment of the invention can execute the method for determining the coronary artery branch of the calcified region provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
It should be noted that each unit and module included in the above apparatus are only divided according to the functional logic, but not limited to the above division, so long as the corresponding functions can be implemented; in addition, the specific names of the functional units are also only for distinguishing from each other, and are not used to limit the protection scope of the embodiments of the present invention.
Example five
Fig. 5 is a schematic structural diagram of a server according to a fifth embodiment of the present invention. Fig. 5 shows a block diagram of an exemplary server 50 suitable for use in implementing the embodiments of the present invention. The server 50 shown in fig. 5 is merely an example, and should not be construed as limiting the functionality and scope of use of embodiments of the present invention.
As shown in fig. 5, the server 50 is in the form of a general purpose computing server. The components of server 50 may include, but are not limited to: one or more processors or processing units 501, a system memory 502, and a bus 503 that connects the various system components (including the system memory 502 and processing units 501).
Bus 503 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures. By way of example, and not limitation, such architectures include Industry Standard Architecture (ISA) bus, micro channel architecture (MAC) bus, enhanced ISA bus, video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.
Server 50 typically includes a variety of computer system readable media. Such media can be any available media that is accessible by server 50 and includes both volatile and nonvolatile media, removable and non-removable media.
The system memory 502 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM) 504 and/or cache memory 505. The server 50 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 506 may be used to read from or write to non-removable, nonvolatile magnetic media (not shown in FIG. 5, commonly referred to as a "hard disk drive"). Although not shown in fig. 5, a magnetic disk drive for reading from and writing to a removable non-volatile magnetic disk (e.g., a "floppy disk"), and an optical disk drive for reading from or writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In such cases, each drive may be coupled to bus 503 through one or more data medium interfaces. Memory 502 may include at least one program product having a set (e.g., at least one) of program modules configured to carry out the functions of embodiments of the invention.
A program/utility 508 having a set (at least one) of program modules 507 may be stored, for example, in memory 502, such program modules 507 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment. Program modules 507 typically perform the functions and/or methods of the described embodiments of the invention.
The server 50 may also communicate with one or more external servers 509 (e.g., keyboard, pointing server, display 510, etc.), with one or more servers that enable users to interact with the server 40, and/or with any server (e.g., network card, modem, etc.) that enables the server 50 to communicate with one or more other computing servers. Such communication may occur through an input/output (I/O) interface 511. Also, the server 50 may communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN) and/or a public network, such as the Internet, via a network adapter 512. As shown, network adapter 512 communicates with other modules of server 50 via bus 503. It should be appreciated that although not shown in fig. 5, other hardware and/or software modules may be used in connection with server 50, including, but not limited to: microcode, server drives, redundant processing units, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.
The processing unit 501 executes various functional applications and data processing by running a program stored in the system memory 502, for example, to implement the method for determining the coronary branch where the calcified region is located provided in the embodiment of the present invention.
Example five
A fifth embodiment of the invention also provides a storage medium containing computer-executable instructions for performing a method of determining a coronary branch in which a calcified region is located when executed by a computer processor.
The method comprises the following steps:
acquiring an image to be processed, and registering with a heart standard model to obtain a first preprocessing image, wherein the image to be processed comprises a calcified region;
processing the heart standard model based on the first processed image to obtain a heart model corresponding to the image to be processed;
calculating a probability value of at least one coronary artery to be candidate in the heart model of the calcified region;
and determining the target coronary artery associated with the calcified region according to the probability value. The computer storage media of embodiments of the invention may take the form of any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for embodiments of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).
Note that the above is only a preferred embodiment of the present invention and the technical principle applied. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, while the invention has been described in connection with the above embodiments, the invention is not limited to the embodiments, but may be embodied in many other equivalent forms without departing from the spirit or scope of the invention, which is set forth in the following claims.

Claims (10)

1. A method of determining branches of a coronary artery in which a calcified region is located, comprising:
acquiring an image to be processed, and registering with a heart standard model to obtain a first preprocessing image, wherein the image to be processed comprises a calcified region;
processing the heart standard model by adopting a movable contour algorithm based on the first preprocessing image to obtain a heart model corresponding to the image to be processed;
calculating a probability value of at least one coronary artery to be candidate in the heart model of the calcified region;
And determining the target coronary artery associated with the calcified region according to the probability value.
2. The method according to claim 1, wherein the processing the heart standard model based on the first pre-processed image, obtaining a heart model corresponding to the image to be processed, comprises:
performing gridding processing on the first preprocessing image, and acquiring at least one grid point to be adjusted of the cavity edge of the heart standard model corresponding to the first preprocessing image;
inputting the grid points to be adjusted into a pre-trained cavity edge classifier to obtain probability values of the positions of the grid points to be adjusted at the preset cavity edge positions on the image to be processed;
and deforming the edges of the chambers corresponding to each chamber according to the probability value to obtain a heart model corresponding to the image to be processed.
3. The method of claim 1, wherein the determining the target coronary associated with the calcified region from the probability values comprises:
and respectively calculating probability values of the calcified regions in the coronary arteries to be selected, and taking the coronary artery to be selected corresponding to the coronary artery to be selected with the highest probability value as a target coronary artery.
4. The method of claim 1, wherein prior to the acquiring the image to be processed, further comprising:
acquiring a flat scanning image corresponding to a target scanning part;
determining calcified areas in the pan-scan image according to preset conditions;
and taking the scanned image of the calcified region as the image to be processed.
5. The method as recited in claim 1, further comprising:
acquiring a plurality of historical heart images as a plurality of current registration sample images, and marking key information in the current registration samples, wherein the key information comprises the edges of each actual chamber of the heart;
selecting one current registration sample image from a plurality of current registration sample images as a reference sample image, taking the rest current registration sample images as sample images to be registered, and registering the reference sample image with each sample image to be registered according to the key information respectively to generate at least one preliminary registration sample image;
gridding each actual chamber edge in the preliminary registration sample image to obtain at least one actual chamber edge grid point, and determining an average chamber edge of the preliminary registration sample image according to coordinates of each actual chamber edge grid point of the reference sample image and the sample image to be registered in the preliminary registration sample image;
And taking the plurality of preliminary registration sample images as a plurality of current registration sample images, repeatedly executing the operation of selecting the reference sample images to perform image registration to obtain an average chamber edge until the average chamber edge of the target registration sample image is determined, and determining a heart standard model according to the average chamber edge of the target registration sample image.
6. The method of claim 5, wherein the critical information comprises coronary branches of the heart;
the determining a heart standard model from the average chamber edge of the target registration sample image comprises:
determining each coronary branch of the target registration sample image according to the position of each coronary branch marked in the target registration sample image relative to a heart standard model;
a heart standard model is determined from each coronary branch of the target registered sample image and the average chamber edge.
7. The method as recited in claim 2, further comprising:
acquiring a plurality of historical heart images as a plurality of training samples, and marking the edges of each actual chamber of the heart in the training samples;
inputting a plurality of marked training samples into a pre-established machine learning model to obtain a chamber edge classifier corresponding to each actual chamber;
The cavity edge classifier is used for registering the image to be processed.
8. A device for determining the branching of the coronary artery in which a calcified region is located, comprising:
the image preprocessing module is used for acquiring an image to be processed, registering the image with the heart standard model to obtain a first preprocessed image, wherein the image to be processed comprises a calcified region;
the heart model determining module is used for processing the heart standard model by adopting a movable contour algorithm based on the first preprocessing image to obtain a heart model corresponding to the image to be processed;
the probability value calculation module is used for calculating the probability value of at least one coronary artery to be candidate in the heart model of the calcified region;
and the coronary branch determining module is used for determining the target coronary associated with the calcified region according to the probability value.
9. A server, the server comprising:
one or more processors;
storage means for storing one or more programs,
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of determining a coronary branch where a calcified region is located as recited in any one of claims 1-7.
10. A storage medium containing computer executable instructions for performing the method of determining the branches of the coronary artery where a calcified region is located according to any one of claims 1-7 when executed by a computer processor.
CN201911384603.5A 2019-12-28 2019-12-28 Method, device, server and medium for determining coronary artery branches where calcified regions are located Active CN111145160B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911384603.5A CN111145160B (en) 2019-12-28 2019-12-28 Method, device, server and medium for determining coronary artery branches where calcified regions are located

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911384603.5A CN111145160B (en) 2019-12-28 2019-12-28 Method, device, server and medium for determining coronary artery branches where calcified regions are located

Publications (2)

Publication Number Publication Date
CN111145160A CN111145160A (en) 2020-05-12
CN111145160B true CN111145160B (en) 2023-06-30

Family

ID=70521328

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911384603.5A Active CN111145160B (en) 2019-12-28 2019-12-28 Method, device, server and medium for determining coronary artery branches where calcified regions are located

Country Status (1)

Country Link
CN (1) CN111145160B (en)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111612756B (en) * 2020-05-18 2023-03-21 中山大学 Coronary artery specificity calcification detection method and device
CN112927275B (en) * 2021-02-22 2022-03-01 北京安德医智科技有限公司 Image processing method and device, electronic equipment and storage medium
CN113506331A (en) * 2021-06-29 2021-10-15 武汉联影智融医疗科技有限公司 Method, apparatus, computer device and storage medium for registering tissue and organ
CN113139959B (en) * 2021-05-17 2021-10-01 北京安德医智科技有限公司 Method and device for obtaining myocardial bridge image, electronic equipment and storage medium
CN115429298A (en) * 2021-06-01 2022-12-06 数坤(北京)网络科技股份有限公司 Method, device and computer readable medium for calculating calcium score

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2009144697A1 (en) * 2008-04-17 2009-12-03 Paieon Inc. Method and apparatus for navigating a therapeutic device to a location
CN101853376A (en) * 2010-02-10 2010-10-06 西安理工大学 Computer aided detection method for microcalcification in mammograms
CN103337096A (en) * 2013-07-19 2013-10-02 东南大学 Coronary artery CT (computed tomography) contrastographic image calcification point detecting method
EP2808844A2 (en) * 2013-05-31 2014-12-03 Siemens Aktiengesellschaft Segmentation of a calcified blood vessel
CN109559303A (en) * 2018-11-22 2019-04-02 广州达美智能科技有限公司 Recognition methods, device and the computer readable storage medium of calcification point
CN109658407A (en) * 2018-12-27 2019-04-19 上海联影医疗科技有限公司 Methods of marking, device, server and the storage medium of coronary artery pathological changes
CN109829896A (en) * 2019-01-14 2019-05-31 中国科学院苏州生物医学工程技术研究所 The micro-calcification clusters automatic testing method of digital galactophore tomography X image based on multi-domain characteristics

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9547894B2 (en) * 2013-10-08 2017-01-17 Toshiba Medical Systems Corporation Apparatus for, and method of, processing volumetric medical image data
CN104091346B (en) * 2014-07-24 2017-02-15 东南大学 Full-automatic CT image coronary artery calcification score calculating method
CN106097298B (en) * 2016-05-27 2019-08-20 中国人民解放军第三军医大学 The coronary artery automatic segmentation and anatomic landmarks method divided based on spherical space
CN108171698B (en) * 2018-02-12 2020-06-09 数坤（北京）网络科技有限公司 Method for automatically detecting human heart coronary calcified plaque
CN109288536B (en) * 2018-09-30 2021-01-29 数坤（北京）网络科技有限公司 Method, device and system for obtaining classification of coronary artery calcification area
CN109389592B (en) * 2018-09-30 2021-01-26 数坤（北京）网络科技有限公司 Method, device and system for calculating coronary artery calcification score

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2009144697A1 (en) * 2008-04-17 2009-12-03 Paieon Inc. Method and apparatus for navigating a therapeutic device to a location
CN101853376A (en) * 2010-02-10 2010-10-06 西安理工大学 Computer aided detection method for microcalcification in mammograms
EP2808844A2 (en) * 2013-05-31 2014-12-03 Siemens Aktiengesellschaft Segmentation of a calcified blood vessel
CN103337096A (en) * 2013-07-19 2013-10-02 东南大学 Coronary artery CT (computed tomography) contrastographic image calcification point detecting method
CN109559303A (en) * 2018-11-22 2019-04-02 广州达美智能科技有限公司 Recognition methods, device and the computer readable storage medium of calcification point
CN109658407A (en) * 2018-12-27 2019-04-19 上海联影医疗科技有限公司 Methods of marking, device, server and the storage medium of coronary artery pathological changes
CN109829896A (en) * 2019-01-14 2019-05-31 中国科学院苏州生物医学工程技术研究所 The micro-calcification clusters automatic testing method of digital galactophore tomography X image based on multi-domain characteristics

Also Published As

Publication number Publication date
CN111145160A (en) 2020-05-12

Similar Documents

Publication Publication Date Title
CN111145160B (en) Method, device, server and medium for determining coronary artery branches where calcified regions are located
US10614599B2 (en) Anatomy segmentation through low-resolution multi-atlas label fusion and corrective learning
US8867822B2 (en) Model-based coronary artery calcium scoring
US20220207742A1 (en) Image segmentation method, device, equipment and storage medium
US11508061B2 (en) Medical image segmentation with uncertainty estimation
US8948484B2 (en) Method and system for automatic view planning for cardiac magnetic resonance imaging acquisition
CN112465834B (en) Blood vessel segmentation method and device
CN112861961B (en) Pulmonary blood vessel classification method and device, storage medium and electronic equipment
CN111640124B (en) Blood vessel extraction method, device, equipment and storage medium
CN111062963A (en) Blood vessel extraction method, system, device and storage medium
CN113889238B (en) Image identification method and device, electronic equipment and storage medium
CN117373070B (en) Method and device for labeling blood vessel segments, electronic equipment and storage medium
CN112634309A (en) Image processing method, image processing device, electronic equipment and storage medium
CN111568451A (en) Exposure dose adjusting method and system
CN112419340B (en) Cerebrospinal fluid segmentation model generation method, application method and device
CN112529919B (en) System and method for generating bullseye chart generation of a subject's heart
CN113888566B (en) Target contour curve determination method and device, electronic equipment and storage medium
CN112950734B (en) Coronary reconstruction method, device, electronic equipment and storage medium
US11935234B2 (en) Method for detecting abnormality, non-transitory computer-readable recording medium storing program for detecting abnormality, abnormality detection apparatus, server apparatus, and method for processing information
CN114037830A (en) Training method for enhanced image generation model, image processing method and device
CN115439423A (en) CT image-based identification method, device, equipment and storage medium
CN115578484A (en) Blood vessel image processing method and device, electronic equipment and readable storage medium
US11295451B2 (en) Robust pulmonary lobe segmentation
CN113205459B (en) Motion correction of angiographic images for 3D reconstruction of coronary arteries
CN115511773B (en) Blood vessel center line extraction method, device, equipment and readable storage medium

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
CB02 Change of applicant information
CB02 Change of applicant information

Address after: 201807 Shanghai City, north of the city of Jiading District Road No. 2258

Applicant after: Shanghai Lianying Medical Technology Co.,Ltd.

Address before: 201807 Shanghai City, north of the city of Jiading District Road No. 2258

Applicant before: SHANGHAI UNITED IMAGING HEALTHCARE Co.,Ltd.

GR01 Patent grant
GR01 Patent grant