CN116051738A - Method for reconstructing coronary artery blood vessel model based on CTA image and readable storage medium - Google Patents
Method for reconstructing coronary artery blood vessel model based on CTA image and readable storage medium Download PDFInfo
- Publication number
- CN116051738A CN116051738A CN202211721485.4A CN202211721485A CN116051738A CN 116051738 A CN116051738 A CN 116051738A CN 202211721485 A CN202211721485 A CN 202211721485A CN 116051738 A CN116051738 A CN 116051738A
- Authority
- CN
- China
- Prior art keywords
- path point
- branch
- coronary artery
- coronary
- central path
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/03—Recognition of patterns in medical or anatomical images
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The application relates to a method and a readable storage medium for reconstructing a coronary artery blood vessel model based on CTA images, wherein the method comprises the following steps: acquiring three-dimensional image data of coronary artery CTA; extracting a first center path point and radius information along the first center path point from the three-dimensional image data; correcting the first central path point to obtain a corrected second central path point and the radius information along the second central path point; identifying a left crown system and a right crown system, and removing interference branches according to the identification result; and generating curve data according to the second central path point, traversing the second central path point, generating a vascular pipeline by combining the radius information, and obtaining a reconstructed coronary artery vascular model after combining. The method provided by the application can automatically reconstruct a coronary artery blood vessel model and automatically complete the identification of a left coronary system and a right coronary system of a coronary artery by extracting and correcting the central line and the radius along the coronary artery.
Description
Technical Field
The present application relates to the field of medical image processing, and in particular, to a method and readable storage medium for reconstructing a coronary artery vessel model based on CTA images.
Background
Coronary atherosclerotic heart disease (coronary heart disease) is one of the diseases with highest worldwide morbidity and mortality, and the number of deaths caused by coronary heart disease is over 2000 ten thousand per year. With the continuous improvement of living standard, the onset age of heart disease is continuously younger.
CTA imaging technology (CT angiography) has the advantages of no need of hospitalization, no invasiveness and the like, and coronary artery CTA is often used for preliminary screening clinically. Has higher clinical value for diagnosing and eliminating coronary heart disease, and can accurately divide blood vessels to facilitate the further diagnosis of doctors.
However, in practical research application, a manual or semi-automatic method is often adopted to segment blood vessels, so that a recognition result is obtained, the repeatability is not strong, and time and labor are wasted.
Disclosure of Invention
In view of the above, it is desirable to provide a method for reconstructing a coronary artery blood vessel model based on CTA images.
The method for reconstructing the coronary artery blood vessel model based on the CTA image comprises the following steps:
acquiring three-dimensional image data of coronary artery CTA;
extracting a first center path point and radius information along the first center path point from the three-dimensional image data;
correcting the first central path point to obtain a corrected second central path point and the radius information along the second central path point;
identifying a left crown system and a right crown system, and removing interference branches according to the identification result;
and generating curve data according to the second central path point, traversing the second central path point, generating a vascular pipeline by combining the radius information, and obtaining a reconstructed coronary artery vascular model after combining.
Optionally, correcting the first central path point to obtain a corrected second central path point, specifically including:
sequentially obtaining two-dimensional sections along the first central path point based on the three-dimensional image data, wherein the two-dimensional sections comprise a blood vessel section and peripheral images thereof;
for any two-dimensional plane, setting a search range according to the first central path point in the plane, and positioning the vessel wall according to a vessel CT threshold;
and if the pixel point with the largest CT value in the search range is smaller than the blood vessel CT threshold value or the pixel point with the smallest CT value in the search range is larger than the calcification CT threshold value, correcting the corresponding first central path point into the blood vessel wall, mapping the first central path point into the three-dimensional image data, and obtaining a corrected second central path point.
Optionally, based on the three-dimensional image data, sequentially obtaining two-dimensional sections along the first central path point specifically includes:
for any first central path point, obtaining tangential vector, normal vector and auxiliary normal vector of the curve of the first central path point;
and obtaining a cutting matrix of the first center path point according to the tangent vector, the normal vector and the auxiliary normal vector and the three-dimensional coordinates of the first center path point, so as to obtain a two-dimensional tangent plane of the first center path point.
Optionally, the vascular CT threshold is obtained by multiplying an average CT value of the aorta by a first preset coefficient, and the calcification CT threshold is obtained by multiplying an average CT value of the aorta by a second preset coefficient;
setting a search range according to the first central path point in the plane, specifically including:
and setting a search range by taking the first central path point as a circle center and through a preset radius.
Optionally, the identifying the right crown system includes performing the following operations according to the second center waypoint information:
establishing an identification coordinate system based on the three-dimensional image data, wherein the identification coordinate system comprises: an X axis pointing from the right to the left, a Y axis pointing from the front to the back, a Z axis pointing from the bottom to the top;
taking the coronary artery with the longest span along the Y axis as an alternative right coronary artery trunk;
if the Y-axis coordinate of the tail end of the alternative right crown trunk is larger than the opening of the right crown trunk, the alternative right crown trunk is confirmed to be the right crown trunk, otherwise, the coronary artery with the longest trend span along the X-axis is taken as the right crown trunk.
Optionally, the identifying the left crown system includes identifying a left anterior descending branch and a left circumflex branch, and specifically includes:
obtaining a first portion and a second portion from which the left main branch is removed, the first portion including a left anterior descending branch and its side branches, the second portion including a left circumflex branch and its side branches;
selecting, as the left anterior descending branch, the coronary artery having the largest span, or the longest span on the Y-axis, from the first portion;
the coronary artery with the largest span, or the longest span in the Z axis, is selected from the second portion as the left circumflex.
Optionally, the identifying the left crown system includes identifying a left main support, including:
and obtaining the rest coronary artery excluding the identified right coronary artery system, wherein the rest coronary artery comprises a left main branch, a left anterior descending branch, a left circumflex branch and a side branch, and the left main branch is identified and obtained according to the superposition condition of the left anterior descending branch and the left circumflex branch before identification.
Optionally, the removing the interference branch specifically includes:
obtaining the rest side branches and the side branch trunks to which the rest side branches belong according to the right crown trunks, the left main branch, the left anterior descending branch and the left convolution branch which are obtained through recognition:
if the remaining side branch is parallel to the main branch of the side branch to which the remaining side branch belongs, removing the remaining side branch;
and if the included angle between the extending direction of the remaining side branch and the extending direction of the main body of the side branch to which the remaining side branch belongs is larger than a preset angle, removing the remaining side branch.
Optionally, the method comprises the steps of obtaining a reconstructed coronary artery blood vessel model after merging, and specifically comprises the following steps:
combining to obtain an initial blood vessel model;
converting the initial vessel model into image data along a second central path point after the interference branch is deleted, and taking the image data as the input of a first level set;
sequentially denoising and gradient calculating the three-dimensional image data according to the initial blood vessel model to obtain image edge features, wherein the image edge features are used as the input of a second level set;
combining the first level set and the second level set, and finding a segmentation edge by using an active contour model based on a partial differential equation to obtain an image sequence along a second central path point;
and carrying out surface reconstruction on the image sequence to obtain a reconstructed coronary artery blood vessel model.
The present application also provides a readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method of CTA image-based coronary vessel model reconstruction described herein.
The method for reconstructing the coronary artery blood vessel model based on the CTA image has at least the following effects:
according to the coronary artery blood vessel model reconstruction method based on the CTA image, the central line and the line radius of the coronary artery, namely the second central path point and the radius information, are obtained through extraction and correction, the reconstruction of the coronary artery blood vessel model can be automatically achieved, and the accuracy of the coronary artery blood vessel model reconstruction is guaranteed through the corrected central line.
The identification of the left coronary system and the right coronary system of the coronary artery can be automatically completed, manual identification and marking are not needed, and the working efficiency is improved.
The method and the device generate the vascular pipeline by utilizing the radius information before correction, and are closer to the real form of the coronary vessel compared with the method and the device for obtaining the reconstructed coronary vessel model by custom input of the radius information.
Drawings
FIG. 1 is a flow chart of a method for reconstructing a coronary vessel model based on CTA images according to an embodiment of the present application;
FIG. 2 is an internal block diagram of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
An embodiment of the present application provides a method for reconstructing a coronary artery blood vessel model based on CTA image, including steps S100 to S500:
in step S100, three-dimensional image data (coronary CT angiography) of the coronary artery CTA is acquired.
Step S200, extracting a first center path point and radius information along the first center path point from the three-dimensional image data. The extraction method can be implemented by using a convolutional neural network which is completed by training.
Step S300, correcting the first central path point, and obtaining corrected second central path point and radius information along the second central path point.
Step S300 is capable of correcting the initial center-waypoint data, and if part of the first center-waypoints in step S200 are not located in the coronary lumen (due to the deviation extracted in step S200), correcting the initial center-waypoint data, correcting the first-waypoints that deviate from the lumen into the coronary lumen.
Step S300 specifically includes steps S310 to S330. Wherein:
step S310, based on the three-dimensional image data, sequentially obtaining two-dimensional sections along a first central path point, wherein the two-dimensional sections comprise a blood vessel section and peripheral images thereof;
step S310 specifically includes steps S311 to S330. Wherein:
step S311, for any one first central path point, obtaining a tangent vector, a normal vector and a secondary normal vector of a curve where the first central path point is located;
before step S310, the first center path points may be sequentially connected into a curve and smoothed for a plurality of times, and the smoothed first center path points may be used to execute step S310.
Step S312, obtaining a cutting matrix of the first center path point according to the tangent vector, the normal vector and the auxiliary normal vector and the three-dimensional coordinates of the first center path point, and further obtaining a two-dimensional tangent plane of the first center path point.
Namely, a cutting matrix at each first center path point is calculated according to the tangent vector, the normal vector, the auxiliary normal vector and the three-dimensional coordinates of the point, and a two-dimensional tangent plane of the image is cut at the point by using the cutting matrix.
Step S320, setting a search range according to a first central path point in any two-dimensional plane, and positioning a vessel wall according to a vessel CT threshold;
further, setting a search range according to a first center path point in a plane specifically includes: and setting a search range by taking the first central path point as a circle center and through a preset radius. The preset radius may be, for example, 1.5mm.
In step S330, if the pixel point with the largest CT value in the search range is smaller than the vessel CT threshold, or the pixel point with the smallest CT value in the search range is larger than the calcification CT threshold, the corresponding first center path point is corrected to the vessel wall and mapped to the three-dimensional image data, so as to obtain the corrected second center path point.
In step S330, a vascular CT threshold is obtained based on the mean CT value of the aorta multiplied by a first preset coefficient, and a calcified CT threshold is obtained based on the mean CT value of the aorta multiplied by a second preset coefficient.
The first preset coefficient may be, for example, 1.0 to 1.1. The second preset coefficient may be, for example, 1.2. Searching a pixel point with the maximum HU value in the searching range, and correcting the two-dimensional coordinate of the pixel point on the two-dimensional section into a blood vessel if the HU value of the pixel point is smaller than a set threshold value (blood vessel CT threshold value). Searching a pixel point with the minimum HU value in the searching range, and correcting the two-dimensional coordinate of the pixel point on the two-dimensional section into a blood vessel if the HU value of the pixel point is larger than a set threshold value (blood vessel CT threshold value).
After the correction is completed, the correction result is transformed into a corresponding three-dimensional coordinate system of the original three-dimensional image, and the original center path point coordinates are updated (the first center path point coordinates are updated) according to the correction result. If the above condition is not triggered, the coordinates of the original first center path point do not need to be corrected. And traversing all the first central path points to finish correction and obtain corrected second central path points.
Step S400 includes identifying a left crown system (step S420), identifying a right crown system (step S410), and removing the interfering branch according to the identification result (step S430). The step uses the second central waypoint information to segment the blood vessel in combination with the anatomical feature.
The step S400 further includes: dividing all the second central path points into two parts, and judging that each part belongs to a left crown system or a right crown system according to the coordinates of the second central path points at the position of the coronary artery opening. After the judgment is completed, the following steps S410 to S430 are performed. It will be appreciated that the present method is only able to distinguish between the left or right crown systems before performing S410-S420, but cannot identify the sub-portions that the left or right crown system includes, i.e., the named right crown trunk, left main branch, left anterior descending branch, and left circumflex branch are temporarily unidentified.
Wherein, step S410, identifying the right crown system includes performing the following operations according to the second center waypoint information:
in step S411, an identification coordinate system is established based on the three-dimensional image data, the identification coordinate system includes: an X axis pointing from the right to the left, a Y axis pointing from the front to the back, a Z axis pointing from the bottom to the top;
step S412, taking the coronary artery with the longest span along the Y axis as an alternative right coronary artery trunk;
in step S413, if the Y-axis coordinate of the end of the right crown trunk is greater than the opening of the right crown trunk, the right crown trunk is identified as the right crown trunk, otherwise, the coronary artery with the longest span along the X-axis is used as the right crown trunk.
Specifically, the sagittal position is taken as the X axis, the coronal position is taken as the Y axis, the transverse position is taken as the Z axis, the range of each branch of the right coronal position on the Y axis and the Z axis is calculated, and the projection of each branch of the right coronal position on the plane vertical to the X axis is calculated. The root with the largest span along the Y axis is found as the alternative right crown trunk. Comparing the Y-axis coordinate of the tail end of the alternative right crown trunk with the Y-axis coordinate of the right crown opening point, and determining the right crown trunk if the coordinate of the tail end of the alternative trunk is larger than the coordinate of the right crown opening point. Otherwise, searching the branch with the largest X-direction span as the right crown trunk.
Step S420, the left crown system is identified, including identifying the left primary branch (step S421), and identifying the left anterior descending branch and the left circumflex branch (step S422).
Step S421, the identification of the left main support specifically comprises: the remaining coronary arteries excluding the identified right coronary system are obtained, the remaining coronary arteries including the left main branch, the left anterior descending branch, the left circumflex branch, and the lateral branches, and the left main branch is identified and obtained according to the superposition condition of the left anterior descending branch and the left circumflex branch before identification.
Step S422, identifying the left anterior descending branch and the left circumflex branch, specifically includes: (1) Obtaining a first portion and a second portion from which the left main branch is removed, the first portion including a left anterior descending branch and its side branches, the second portion including a left circumflex branch and its side branches; (2) Selecting the coronary artery with the largest span or the longest span on the Y axis from the first part as the left anterior descending branch; (3) The coronary artery with the largest span, or the longest span in the Z-axis, is selected from the second portion as the left circumflex.
Specifically, all branches of the left crown system are removed from the left main branch, and the remaining branches are divided into two parts. The first part contains the left anterior descending branch LAD and its side branches (part A), and the second part contains the left circumflex branch LCX and its side branches (part B). The left anterior descending branch is determined from the first section according to the length of each branch (longest length) or the span on the Y-axis (longest span). The one with the largest span on the Z axis is selected from the second part to be determined as the left circumflex.
Step S430, removing the interference branch, specifically includes: according to the identified right crown trunk, left main branch, left anterior descending branch and left convolution branch, obtaining the rest side branch and the side branch trunk (the side branch trunk refers to the right crown trunk, left main branch, left anterior descending branch and left convolution branch), for one rest side branch: if the remaining side branch is parallel to the main branch of the side branch to which the remaining side branch belongs, removing the remaining side branch; and if the included angle between the extending direction of the remaining side branch and the extending direction of the main body of the side branch to which the remaining side branch belongs is larger than a preset angle, removing the remaining side branch.
The predetermined angle may be, for example, one hundred twenty degrees. In the process of removing the interference branches, the method further comprises the step of reordering the sequence of the occurrence of each side branch (the rest side branch) on the trunk of the opposite side branch. In this step, the included angle between each side branch and the trunk to which it belongs is determined. If the lateral branch direction vector and the trunk direction vector are nearly parallel, the lateral branch is deleted. And deleting the side branch if the included angle between the side branch direction vector and the trunk direction vector is larger than a preset value. In step S430, the venous branch interference is removed.
Step S500, generating curve data according to the second central path point, traversing the second central path point, generating a vascular pipeline by combining radius information (step S510), and obtaining a reconstructed coronary artery vascular model after combination (step S520).
Step S510 specifically includes: curve data is generated according to the second central path point, and a pipeline with a set radius size is generated by sweeping along each curve (generating one by traversing the central path point). The radius is set as the above radius information.
Step S520, obtaining a reconstructed coronary artery blood vessel model after merging, which specifically comprises the following steps:
step S521, obtaining an initial blood vessel model after merging;
step S522, converting the initial vessel model into image data along a second central path point after the interference branch is deleted, and taking the image data as the input of a first level set;
step S523, denoising and gradient calculation are sequentially carried out on the three-dimensional image data according to the initial vessel model, so that image edge characteristics are obtained, and the image edge characteristics are used as the input of a second level set;
step S524, combining the first level set and the second level set, and finding a segmentation edge by using an active contour model based on a partial differential equation to obtain an image sequence along a second center path point; each image in the image sequence has a positive target contour, a zero boundary and a negative target contour.
And step S525, carrying out surface reconstruction on the image sequence to obtain a reconstructed coronary artery blood vessel model.
Specifically, the multiple ducts generated by the multiple curves are combined to finally become an initial duct model (initial vessel model) of the entire coronary tree. The pipeline model data is utilized to convert to image data as input to a first initial level set. According to the existing initial pipeline profile, denoising and gradient calculation of the original three-dimensional image data are utilized to obtain potential image edge characteristics, and the potential image edge characteristics are used as another input of the second level set. And (5) extending inwards/outwards, finding out the segmentation edges, and finally obtaining the image sequence corresponding to the blood vessel along the central line path. And (3) carrying out surface reconstruction on the image sequence by using a marching cube algorithm to obtain a coronary artery blood vessel model consisting of the blood vessel of interest.
According to the coronary artery blood vessel model reconstruction method based on the CTA image, the central line and the line radius of the coronary artery, namely the second central path point and the radius information, are obtained through extraction and correction, the reconstruction of the coronary artery blood vessel model can be automatically achieved, the identification of the left coronary system and the right coronary system of the coronary artery can be automatically identified, manual identification and marking are not needed, and the working efficiency is improved.
The coronary artery blood vessel model obtained by reconstruction in each embodiment of the application has a smooth surface, vein interference branches are removed, original complex manual pretreatment operation is replaced, and the repeatability of the result is greatly improved. The blood vessel model can be automatically reconstructed, the time and labor cost are reduced, and the further diagnosis of doctors is facilitated.
It should be understood that at least a portion of each step in the flowchart of fig. 1 may include a plurality of sub-steps or phases, which are not necessarily performed at the same time, but may be performed at different times, and the order of execution of the sub-steps or phases is not necessarily sequential, but may be performed in turn or alternately with other steps or at least a portion of the sub-steps or phases of other steps.
In one embodiment, a computer device is provided, which may be a terminal, and the internal structure of which may be as shown in fig. 2. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program, when executed by a processor, implements a method for reconstruction of a coronary vessel model based on CTA images. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
In one embodiment, a computer device is provided comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program performing the steps of:
step S100, three-dimensional image data of coronary artery CTA is obtained;
step S200, extracting a first center path point and radius information along the first center path point from the three-dimensional image data;
step S300, correcting the first central path point to obtain a corrected second central path point and radius information along the second central path point;
step S400, identifying a left crown system and a right crown system, and removing interference branches according to the identification result;
and S500, generating curve data according to the second central path point, traversing the second central path point, generating a vascular pipeline by combining radius information, and merging to obtain a reconstructed coronary artery vascular model.
In one embodiment, a readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:
step S100, three-dimensional image data of coronary artery CTA is obtained;
step S200, extracting a first center path point and radius information along the first center path point from the three-dimensional image data;
step S300, correcting the first central path point to obtain a corrected second central path point and radius information along the second central path point;
step S400, identifying a left crown system and a right crown system, and removing interference branches according to the identification result;
and S500, generating curve data according to the second central path point, traversing the second central path point, generating a vascular pipeline by combining radius information, and merging to obtain a reconstructed coronary artery vascular model.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the various embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description. When technical features of different embodiments are embodied in the same drawing, the drawing can be regarded as a combination of the embodiments concerned also being disclosed at the same time.
The above examples merely represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application is to be determined by the claims appended hereto.
Claims (10)
1. A method for reconstructing a coronary vessel model based on CTA images, comprising:
acquiring three-dimensional image data of coronary artery CTA;
extracting a first center path point and radius information along the first center path point from the three-dimensional image data;
correcting the first central path point to obtain a corrected second central path point and the radius information along the second central path point;
identifying a left crown system and a right crown system, and removing interference branches according to the identification result;
and generating curve data according to the second central path point, traversing the second central path point, generating a vascular pipeline by combining the radius information, and obtaining a reconstructed coronary artery vascular model after combining.
2. The method for reconstructing a CTA image-based coronary vessel model according to claim 1, wherein correcting the first central waypoint to obtain a corrected second central waypoint specifically comprises:
sequentially obtaining two-dimensional sections along the first central path point based on the three-dimensional image data, wherein the two-dimensional sections comprise a blood vessel section and peripheral images thereof;
for any two-dimensional plane, setting a search range according to the first central path point in the plane, and positioning the vessel wall according to a vessel CT threshold;
and if the pixel point with the largest CT value in the search range is smaller than the blood vessel CT threshold value or the pixel point with the smallest CT value in the search range is larger than the calcification CT threshold value, correcting the corresponding first central path point into the blood vessel wall, mapping the first central path point into the three-dimensional image data, and obtaining a corrected second central path point.
3. The CTA image-based coronary vessel model reconstruction method according to claim 2, wherein a two-dimensional section along the first center path point is sequentially obtained based on the three-dimensional image data, specifically comprising:
for any first central path point, obtaining tangential vector, normal vector and auxiliary normal vector of the curve of the first central path point;
and obtaining a cutting matrix of the first center path point according to the tangent vector, the normal vector and the auxiliary normal vector and the three-dimensional coordinates of the first center path point, so as to obtain a two-dimensional tangent plane of the first center path point.
4. The method of CTA image-based coronary vessel model reconstruction according to claim 2, wherein the vessel CT threshold is obtained by multiplying an average CT value based on the aorta by a first preset coefficient, and wherein the calcification CT threshold is obtained by multiplying an average CT value based on the aorta by a second preset coefficient;
setting a search range according to the first central path point in the plane, specifically including:
and setting a search range by taking the first central path point as a circle center and through a preset radius.
5. The method of CTA image-based coronary vessel model reconstruction of claim 1, wherein the identifying a right coronary system includes, based on the second center waypoint information:
establishing an identification coordinate system based on the three-dimensional image data, wherein the identification coordinate system comprises: an X axis pointing from the right to the left, a Y axis pointing from the front to the back, a Z axis pointing from the bottom to the top;
taking the coronary artery with the longest span along the Y axis as an alternative right coronary artery trunk;
if the Y-axis coordinate of the tail end of the alternative right crown trunk is larger than the opening of the right crown trunk, the alternative right crown trunk is confirmed to be the right crown trunk, otherwise, the coronary artery with the longest trend span along the X-axis is taken as the right crown trunk.
6. The method for reconstructing a CTA image-based coronary vessel model according to claim 5, wherein said identifying a left coronary system comprises identifying a left anterior descending branch and a left circumflex branch, comprising:
obtaining a first portion and a second portion from which the left main branch is removed, the first portion including a left anterior descending branch and its side branches, the second portion including a left circumflex branch and its side branches;
selecting, as the left anterior descending branch, the coronary artery having the largest span, or the longest span on the Y-axis, from the first portion;
the coronary artery with the largest span, or the longest span in the Z axis, is selected from the second portion as the left circumflex.
7. The method for reconstructing a CTA image-based coronary vessel model according to claim 6, wherein said identifying a left coronary system comprises identifying a left main stent, in particular comprising:
and obtaining the rest coronary artery excluding the identified right coronary artery system, wherein the rest coronary artery comprises a left main branch, a left anterior descending branch, a left circumflex branch and a side branch, and the left main branch is identified and obtained according to the superposition condition of the left anterior descending branch and the left circumflex branch before identification.
8. The method for reconstructing a CTA image-based coronary vessel model according to claim 6, wherein said removing the interfering branches comprises:
obtaining the rest side branches and the side branch trunks to which the rest side branches belong according to the right crown trunks, the left main branch, the left anterior descending branch and the left convolution branch which are obtained through recognition:
if the remaining side branch is parallel to the main branch of the side branch to which the remaining side branch belongs, removing the remaining side branch;
and if the included angle between the extending direction of the remaining side branch and the extending direction of the main body of the side branch to which the remaining side branch belongs is larger than a preset angle, removing the remaining side branch.
9. The method for reconstructing a CTA image-based coronary artery blood vessel model according to claim 1, wherein the method for obtaining the reconstructed coronary artery blood vessel model after the merging comprises the following steps:
combining to obtain an initial blood vessel model;
converting the initial vessel model into image data along a second central path point after the interference branch is deleted, and taking the image data as the input of a first level set;
sequentially denoising and gradient calculating the three-dimensional image data according to the initial blood vessel model to obtain image edge features, wherein the image edge features are used as the input of a second level set;
combining the first level set and the second level set, and finding a segmentation edge by using an active contour model based on a partial differential equation to obtain an image sequence along a second central path point;
and carrying out surface reconstruction on the image sequence to obtain a reconstructed coronary artery blood vessel model.
10. A readable storage medium having stored thereon a computer program, characterized in that the computer program when executed by a processor realizes the steps of the method for reconstructing a CTA image based coronary vessel model according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211721485.4A CN116051738A (en) | 2022-12-30 | 2022-12-30 | Method for reconstructing coronary artery blood vessel model based on CTA image and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211721485.4A CN116051738A (en) | 2022-12-30 | 2022-12-30 | Method for reconstructing coronary artery blood vessel model based on CTA image and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116051738A true CN116051738A (en) | 2023-05-02 |
Family
ID=86123126
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211721485.4A Pending CN116051738A (en) | 2022-12-30 | 2022-12-30 | Method for reconstructing coronary artery blood vessel model based on CTA image and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116051738A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117036640A (en) * | 2023-10-10 | 2023-11-10 | 杭州脉流科技有限公司 | Coronary artery blood vessel model reconstruction method, device, equipment and storage medium |
| CN117058328A (en) * | 2023-10-11 | 2023-11-14 | 杭州脉流科技有限公司 | Coronary vessel tree classification method, apparatus, storage medium and program product |
-
2022
- 2022-12-30 CN CN202211721485.4A patent/CN116051738A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117036640A (en) * | 2023-10-10 | 2023-11-10 | 杭州脉流科技有限公司 | Coronary artery blood vessel model reconstruction method, device, equipment and storage medium |
| CN117036640B (en) * | 2023-10-10 | 2023-12-19 | 杭州脉流科技有限公司 | Coronary artery blood vessel model reconstruction method, device, equipment and storage medium |
| CN117058328A (en) * | 2023-10-11 | 2023-11-14 | 杭州脉流科技有限公司 | Coronary vessel tree classification method, apparatus, storage medium and program product |
| CN117058328B (en) * | 2023-10-11 | 2024-01-09 | 杭州脉流科技有限公司 | Coronary vessel tree classification method, apparatus, storage medium and program product |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111292314B (en) | Coronary artery segmentation method, device, image processing system and storage medium | |
| US20230104173A1 (en) | Method and system for determining blood vessel information in an image | |
| CN116051738A (en) | Method for reconstructing coronary artery blood vessel model based on CTA image and readable storage medium | |
| CN109478327B (en) | Method for automatic detection of systemic arteries in Computed Tomography Angiography (CTA) of arbitrary field of view | |
| CN111161241B (en) | Liver image identification method, electronic equipment and storage medium | |
| CN116090364A (en) | Method for obtaining coronary blood flow reserve fraction based on CTA image and readable storage medium | |
| CN109712163B (en) | Coronary artery extraction method, device, image processing workstation and readable storage medium | |
| CN109727242B (en) | Blood vessel center line extraction method, device, computer equipment and storage medium | |
| CN113674279B (en) | Coronary artery CTA image processing method and device based on deep learning | |
| CN112308846B (en) | Blood vessel segmentation method and device and electronic equipment | |
| KR20190084380A (en) | Method for extracting vascular structure in 2d x-ray angiogram, computer readable medium and apparatus for performing the method | |
| JP2018134393A (en) | Method and apparatus for segmentation of blood vessels | |
| CN110796670A (en) | Dissection method and device for dissecting artery | |
| CN110782489B (en) | Image data matching method, device and equipment and computer readable storage medium | |
| JP6458166B2 (en) | MEDICAL IMAGE PROCESSING METHOD, DEVICE, SYSTEM, AND PROGRAM | |
| CN111429438A (en) | Method and device for extracting blood vessel center line and heart coronary artery tree and storage medium | |
| CN113889238B (en) | Image identification method and device, electronic equipment and storage medium | |
| Liu et al. | Robust optimization-based coronary artery labeling from X-ray angiograms | |
| CN111312374A (en) | Medical image processing method, device, storage medium and computer equipment | |
| Cercos-Pita et al. | NASAL-Geom, a free upper respiratory tract 3D model reconstruction software | |
| CN117036530A (en) | Cross-modal data-based coronary artery fractional flow reserve prediction method and device | |
| Zhu et al. | Minimum average-cost path for real time 3d coronary artery segmentation of ct images | |
| CN111798468B (en) | Image processing method and device, storage medium and electronic terminal | |
| CN113962957A (en) | Medical image processing method, bone image processing method, device and equipment | |
| CN114209344A (en) | Collateral circulation state evaluation method and device, storage medium and electronic equipment |
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 |