CN113487604A - Corresponding point recommendation method and device, computer readable storage medium and processor - Google Patents
Corresponding point recommendation method and device, computer readable storage medium and processor Download PDFInfo
- Publication number
- CN113487604A CN113487604A CN202110876228.7A CN202110876228A CN113487604A CN 113487604 A CN113487604 A CN 113487604A CN 202110876228 A CN202110876228 A CN 202110876228A CN 113487604 A CN113487604 A CN 113487604A
- Authority
- CN
- China
- Prior art keywords
- point
- vessel contour
- blood vessel
- corresponding point
- contour
- 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.)
- Granted
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
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
-
- 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
- G06T2207/20068—Projection on vertical or horizontal image axis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Image Analysis (AREA)
Abstract
The application provides a corresponding point recommendation method, a corresponding point recommendation device, a computer readable storage medium and a processor. The method comprises the steps of obtaining a first 2D blood vessel contour and a second 2D blood vessel contour, wherein the first 2D blood vessel contour and the second 2D blood vessel contour are obtained under different shooting angles; determining a first point on the second 2D vessel contour in response to a first predetermined operation by the user; determining a second point on the second 2D vessel contour in response to a second predetermined operation by the user; determining a first corresponding point matching the first point, the first corresponding point being located on the first 2D vessel contour; a second corresponding point is determined that matches the second point, the second corresponding point being located on the first 2D vessel contour. The proposal realizes the recommendation of the corresponding point through two times of scheduled operation. Compared with the scheme that four points need to be clicked in the prior art, the method is simple to operate. The complexity of human-computer interaction is reduced, the efficiency is improved, and more accurate input is provided for subsequent three-dimensional reconstruction.
Description
Technical Field
The present application relates to the field of medical images, and in particular, to a method and an apparatus for recommending a corresponding point, a computer-readable storage medium, and a processor.
Background
In the research of analyzing the cardiovascular and cerebrovascular vessels based on DSA image auxiliary technology, the required key flow is as follows: blood vessel segmentation, light source correction, blood vessel three-dimensional reconstruction, quantitative analysis and the like. And (4) vessel segmentation, namely enhancing the DSA image to highlight the vessel edge, increasing the difference between the foreground vessel and the background image, and further segmenting the target vessel. The light source correction is to make the corresponding points of the two outlines in the projection plane have a corresponding relationship by the space transformation of the light source. And (3) three-dimensional reconstruction of the blood vessel, namely restoring the two corrected two-dimensional projection images into a three-dimensional model to restore the space structure. Quantitative analysis, which is to calculate and analyze the three-dimensional model to obtain the clinically required key parameters of the blood vessel, such as the stenosis rate of the blood vessel, for evaluating the severity of the disease of the patient.
Between the two steps of light source correction and three-dimensional reconstruction of the blood vessel, an operator needs to click by a mouse to carry out human-computer interaction to obtain two-dimensional blood vessel images as input of three-dimensional reconstruction, the operator reconstructs the blood vessel with any length and any branch according to actual requirements, and respectively clicks the starting point and the ending point of the blood vessel to be reconstructed in the two-dimensional blood vessel images, so that four points are needed to be clicked. Namely, in the prior art, if three-dimensional reconstruction of a blood vessel is required, four points need to be clicked, and the operation is complex.
Disclosure of Invention
The application mainly aims to provide a corresponding point recommendation method and device, a computer readable storage medium and a processor, so as to solve the problem that in the prior art, four points need to be clicked in the process of performing three-dimensional reconstruction of a blood vessel by adopting two-dimensional blood vessel images, and the operation is complex.
In order to achieve the above object, according to an aspect of the present application, there is provided a correspondence point recommending method including: acquiring a first 2D blood vessel contour and a second 2D blood vessel contour, wherein the first 2D blood vessel contour and the second 2D blood vessel contour are obtained at different shooting angles; determining a first point on the second 2D vessel contour in response to a first predetermined operation by a user; determining a second point on the second 2D vessel contour in response to a second predetermined operation by the user; determining a first corresponding point matching the first point, the first corresponding point located on the first 2D vessel contour; determining a second corresponding point that matches the second point, the second corresponding point located on the first 2D vessel contour.
Optionally, the first 2D vessel contour lies in a first plane, the second 2D vessel contour lies in a second plane, and determining a first corresponding point matching the first point includes: projecting the first 2D blood vessel contour to the second plane to obtain a first projected 2D blood vessel contour; determining a first projected correspondence point matching the first point, the first projected correspondence point being located on the first projected 2D vessel contour; and projecting the first projection corresponding point back to the first plane to obtain the first corresponding point.
Optionally, determining a first projection corresponding point matching the first point includes: and determining the corresponding point of the first projection matched with the first point by adopting a robust point set registration algorithm.
Optionally, projecting the first 2D vessel contour into the second plane to obtain a first projected 2D vessel contour, including: projecting the first 2D blood vessel contour to a preset three-dimensional space by taking a first light source as a reference to obtain a first projection contour, wherein the first light source corresponds to the first 2D blood vessel contour; and projecting the first projection contour into the second plane by taking a second correction light source as a reference to obtain the first projection 2D blood vessel contour, wherein the second correction light source is a light source corrected by a second light source, and the second light source corresponds to the second 2D blood vessel contour.
Optionally, projecting the first projection corresponding point back into the first plane to obtain the first corresponding point, including: projecting the first projection corresponding point to the preset three-dimensional space by taking the second correction light source as a reference to obtain a first projection point; and projecting the first projection point into the first plane by taking the first light source as a reference to obtain the first corresponding point.
Optionally, the first projected 2D vessel contour has an intersection with the second 2D vessel contour.
Optionally, obtaining the first 2D vessel contour comprises: acquiring a first 2D blood vessel image; and processing the first 2D blood vessel image by adopting a level set segmentation algorithm and a fast marching algorithm to obtain the first 2D blood vessel contour.
According to another aspect of the present application, there is provided a correspondence point recommending apparatus including: the acquisition unit is used for acquiring a first 2D blood vessel contour and a second 2D blood vessel contour, wherein the first 2D blood vessel contour and the second 2D blood vessel contour are obtained at different shooting angles; a first determination unit for determining a first point on the second 2D vessel contour in response to a first predetermined operation by a user; a second determining unit for determining a second point on the second 2D vessel contour in response to a second predetermined operation by the user; a third determining unit, configured to determine a first corresponding point that matches the first point, where the first corresponding point is located on the first 2D vessel contour; a fourth determining unit, configured to determine a second corresponding point that matches the second point, where the second corresponding point is located on the first 2D blood vessel contour.
According to yet another aspect of the application, a computer-readable storage medium is provided, comprising a stored program, wherein the program, when executed, controls an apparatus in which the computer-readable storage medium is located to perform any of the methods.
According to yet another aspect of the application, a processor for running a program is provided, wherein the program when running performs any of the methods.
By applying the technical scheme of the application, the recommendation of the corresponding points is realized by acquiring the first 2D blood vessel contour and the second 2D blood vessel contour, determining a first point on the second 2D blood vessel contour in response to the first preset operation of a user, determining a second point on the second 2D blood vessel contour in response to the second preset operation of the user, automatically matching a first corresponding point corresponding to the first point, and automatically matching a second corresponding point corresponding to the second point. The recommendation of the corresponding point is realized through two times of the predetermined operation. Compared with the scheme that four points need to be clicked in the prior art, the method is simple to operate. The complexity of human-computer interaction is reduced, the efficiency is improved, and more accurate input is provided for subsequent three-dimensional reconstruction.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the application and, together with the description, serve to explain the application and are not intended to limit the application. In the drawings:
FIG. 1 shows a flow chart of a correspondence point recommendation method according to an embodiment of the application;
FIG. 2 illustrates a schematic diagram of a specific corresponding point recommendation method according to an embodiment of the present application;
fig. 3 shows a corresponding point recommendation device according to an embodiment of the application.
Detailed Description
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used may be interchanged under appropriate circumstances such that embodiments of the application described herein may be used. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It will be understood that when an element such as a layer, film, region, or substrate is referred to as being "on" another element, it can be directly on the other element or intervening elements may also be present. Also, in the specification and claims, when an element is described as being "connected" to another element, the element may be "directly connected" to the other element or "connected" to the other element through a third element.
For convenience of description, some terms or expressions referred to in the embodiments of the present application are explained below:
robust point set Registration (RPM): the algorithm is initialized to assign a registration parameter between 0 and 1 to any group of corresponding points, a numerical value represents the degree to which the group of points is a corresponding point, a numerical value of 1 indicates that the group of points is confirmed to be a group of corresponding points, and the registration parameter converges to two values of 0 or 1 through multiple iterations of the algorithm.
As introduced in the background art, in the prior art, four points need to be clicked in the process of performing three-dimensional reconstruction of a blood vessel by using two-dimensional blood vessel images, the operation is complex, and in order to solve the problem that four points need to be clicked in the process of performing three-dimensional reconstruction of a blood vessel by using two-dimensional blood vessel images, the operation is complex, embodiments of the present application provide a corresponding point recommendation method, an apparatus, a computer-readable storage medium, and a processor.
According to an embodiment of the application, a corresponding point recommendation method is provided.
Fig. 1 is a flowchart of a corresponding point recommendation method according to an embodiment of the present application. Fig. 2 is a schematic diagram of a specific corresponding point recommendation method according to an embodiment of the present application. As shown in fig. 1 and 2, the method comprises the steps of:
step S101, acquiring a first 2D blood vessel contour l1And a second 2D vessel profile l2The first 2D blood vessel contour and the second 2D blood vessel contour are blood vessel contours obtained under different shooting angles;
step S102, responding to the first predetermined operation of the user, and setting the second 2D blood vessel contour l2Upper determination first point P1;
step S103, responding to the second predetermined operation of the user, and setting the second 2D blood vessel contour l2Upper determination second point P2;
step S104, determining a first corresponding point P11 matching the first point P1, the first corresponding point P11 being located on the first 2D blood vessel contour l1The above step (1);
step S105, determining a second corresponding point P21 matching the second point P2, the second corresponding point P21 being located on the first 2D blood vessel contour l1The above.
In particular, the scheme is suitable for coronary vessels, craniocerebral vessels and other blood vessels.
Specifically, the first predetermined operation may be a click operation, and the click operation includes a single click or a double click operation. Of course, operations other than the click operation may be possible.
Specifically, the second predetermined operation may be a click operation, and the click operation includes a single click or a double click operation. Of course, operations other than the click operation may be possible.
Specifically, the user makes one click on the second 2D vessel contour, determining the first point. And then automatically matching a first corresponding point corresponding to the first point. The user then clicks again on the second 2D vessel contour, determining a second point. And then automatically matching a second corresponding point corresponding to the second point. And the recommendation of the corresponding point is realized through two clicking operations.
In the above scheme, the recommendation of the corresponding points is implemented by acquiring a first 2D blood vessel contour and a second 2D blood vessel contour, determining a first point on the second 2D blood vessel contour in response to a first predetermined operation of a user, determining a second point on the second 2D blood vessel contour in response to a second predetermined operation of the user, automatically matching a first corresponding point corresponding to the first point, and automatically matching a second corresponding point corresponding to the second point. The recommendation of the corresponding point is realized through two times of the predetermined operation. Compared with the scheme that four points need to be clicked in the prior art, the method is simple to operate. The complexity of human-computer interaction is reduced, the efficiency is improved, and more accurate input is provided for subsequent three-dimensional reconstruction.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.
In one embodiment of the present application, as shown in fig. 2, the first 2D blood vessel profile l1Is located on a first plane m1Inner, the second 2D vessel profile l2Located in a second plane m2And determining a first corresponding point P11 matching the first point P1, including: the first 2D blood vessel profile l is obtained1Projected to the second plane m2In the interior, a first projected 2D vessel contour l is obtained1'; determining a first projected corresponding point P12 matching the first point P1, the first projected corresponding point P12 being located on the first projected 2D blood vessel contour l1' above; projecting the first projection corresponding point P12 back to the first plane m1The first corresponding point P11 is obtained.
In one embodiment of the present application, as shown in fig. 2, determining a first projected corresponding point P12 that matches the first point P1 includes: and determining the corresponding point of the first projection matched with the first point by adopting a robust point set registration algorithm. Commonly used registration methods include rigid transformation-based registration methods and feature point-based registration methods. In the registration method based on rigid transformation (i.e. transformation such as translation, rotation, scaling, etc.), for the "L" type data, there is a case where the information of the overlapped part is missing in a certain projection direction. Feature-basedThe registration method of points (i.e. corners, boundaries, etc.) cannot guarantee successful registration under the condition that feature points are missing or the form of the image is not obvious. The robust point set registration algorithm in the scheme can realize the second 2D blood vessel outline l2Point of interest and first projected 2D vessel contour l1The one-to-one correspondence of points on the' can be realized (namely, each point has the corresponding point, the situation of no solution can not occur), the situation of information loss can not occur, and the successful registration can also be realized under the situation of feature point loss or image form unobvious.
In addition, compared with an epipolar constraint registration method, the robust point set registration algorithm simplifies the registration process and improves the efficiency. The epipolar line is the intersection line of the plane formed by the two light sources and the center point of the blood vessel and the projection plane. The basic principle of the epipolar constraint registration method is as follows: and (3) taking the intersection point of the polar line and the target, if only one intersection point exists, directly obtaining the recommended corresponding point, and if the intersection point is not unique, judging by using other methods for assistance, wherein the process is complex. The robust point set registration algorithm in the scheme adopts the idea of point set registration, simplifies the registration process and improves the efficiency.
In one embodiment of the present application, the first 2D vessel profile l is shown in FIG. 21Projected to the second plane m2In the interior, a first projected 2D vessel contour l is obtained1', includes: with a first light source S1Taking the first 2D blood vessel profile l as a reference1Projecting the first image into a predetermined three-dimensional space to obtain a first projection profile vessel1The first light source S1And the first 2D blood vessel profile l1Corresponding; with a second correction of the light source S2' As a reference, the first projection profile vessel1Projected to the second plane m2Obtaining the first projected 2D blood vessel contour l1', the second correction light source S2' is a light source corrected for a second light source corresponding to the second 2D vessel contour. Corrected by a single point light source, a second plane m2Second 2D vessel contour l in2Point of interest and first projected 2D vessel contour l1There is a correspondence relationship between points onIncludes the coincidence of the corresponding points of the group or the arrangement of the corresponding points of the group on a polar line. The second 2D vessel contour l can be obtained by adopting a robust point set registration algorithm2And the first projection 2D blood vessel contour l1' all correspondence of points above. The accuracy of matching corresponding points is ensured.
Specifically, the second correction light source in this application is the light source after correcting the second light source, does not correct first light source, and based on the recommendation that single-point correction realized during this application promptly, single-point correction only has a set of corresponding point information, and it is less to correct information than the single-point in the multiple spot, provides more the degree of difficulty for corresponding point recommendation operation on next step. According to the scheme, corresponding point recommendation under single-point correction can be achieved, corresponding point recommendation under multi-point correction can also be achieved naturally, and the recommendation principle is the same.
In one embodiment of the present application, as shown in fig. 2, the first projection corresponding point P12 is projected back to the first plane m1Obtaining the first corresponding point P11 includes: using the second correction light source S2' as a reference, the first projection corresponding point P12 is projected into the predetermined three-dimensional space to obtain a first projection point P13; with the first light source S1Projecting the first projected point P13 to the first plane m as a reference1The first corresponding point P11 is obtained.
In an embodiment of the present application, as shown in fig. 2, the first projected 2D blood vessel profile l1' with the second 2D vessel profile l2There is an intersection point Q. Specifically, since the second correction light source in the present solution is a light source corrected by the second light source, the first projection 2D blood vessel contour and the second 2D blood vessel contour have an intersection point, that is, the intersection point is formed before the corresponding point matching is performed. The information of the intersection points can be directly utilized during matching, the intersection points are located on the first projection 2D blood vessel contour and the second 2D blood vessel contour at the same time, namely a group of corresponding points (under the condition that one intersection point exists) are known to have a certain corresponding relation, the known conditions are increased, the calculation of unknown data is reduced, and the matching accuracy is ensured, so that the more the intersection points are, the more the corresponding point recommendation result is accurate.
In an embodiment of the present application, acquiring the first 2D blood vessel contour includes: acquiring a first 2D blood vessel image; and processing the first 2D blood vessel image by adopting a level set segmentation algorithm and a fast marching algorithm to obtain the first 2D blood vessel contour. The level set segmentation algorithm is used for segmenting the first 2D blood vessel image, and the fast marching algorithm is used for extracting the central line of the first 2D blood vessel image. The first 2D blood vessel contour can be extracted from the first 2D blood vessel image through a flat set segmentation algorithm and a fast marching algorithm.
The embodiment of the present application further provides a corresponding point recommending device, and it should be noted that the corresponding point recommending device according to the embodiment of the present application may be used to execute the corresponding point recommending method provided by the embodiment of the present application. The following describes a corresponding point recommendation device provided in an embodiment of the present application.
Fig. 3 is a schematic diagram of a corresponding point recommending apparatus according to an embodiment of the present application. As shown in fig. 3, the apparatus includes:
an acquiring unit 10 configured to acquire a first 2D blood vessel contour and a second 2D blood vessel contour, where the first 2D blood vessel contour and the second 2D blood vessel contour are obtained at different imaging angles;
a first determining unit 20, configured to determine a first point on the second 2D blood vessel contour in response to a first predetermined operation by a user;
a second determining unit 30, configured to determine a second point on the second 2D blood vessel contour in response to a second predetermined operation by the user;
a third determining unit 40 configured to determine a first corresponding point that matches the first point, where the first corresponding point is located on the first 2D blood vessel contour;
a fourth determining unit 50, configured to determine a second corresponding point that matches the second point, where the second corresponding point is located on the first 2D blood vessel contour.
In the above scheme, the obtaining unit obtains a first 2D blood vessel contour and a second 2D blood vessel contour, the first determining unit determines a first point on the second 2D blood vessel contour in response to a first predetermined operation of a user, the second determining unit determines a second point on the second 2D blood vessel contour in response to a second predetermined operation of the user, the third determining unit automatically matches a first corresponding point corresponding to the first point, and the fourth determining unit automatically matches a second corresponding point corresponding to the second point, so as to implement recommendation of the corresponding points. The recommendation of the corresponding point is realized through two times of the predetermined operation. Compared with the scheme that four points need to be clicked in the prior art, the method is simple to operate. The complexity of human-computer interaction is reduced, the efficiency is improved, and more accurate input is provided for subsequent three-dimensional reconstruction.
In an embodiment of the present application, the first 2D blood vessel contour is located in a first plane, the second 2D blood vessel contour is located in a second plane, and the third determining unit includes a projection module, a determining module, and a projection module, where the projection module is configured to project the first 2D blood vessel contour into the second plane to obtain a first projected 2D blood vessel contour; the determining module is configured to determine a first projection corresponding point matched with the first point, where the first projection corresponding point is located on the first projection 2D blood vessel contour; the projection module is used for projecting the first projection corresponding point back to the first plane to obtain the first corresponding point.
In an embodiment of the application, the determining module is further configured to determine the first projection corresponding point matched with the first point by using a robust point set registration algorithm.
In an embodiment of the present application, the projection module includes a first projection submodule and a second projection submodule, where the first projection submodule is configured to project the first 2D blood vessel contour into a predetermined three-dimensional space with a first light source as a reference, so as to obtain a first projection contour, and the first light source corresponds to the first 2D blood vessel contour; the second projection submodule is configured to project the first projection profile into the second plane with reference to a second correction illuminant, which is an illuminant corrected by a second illuminant corresponding to the second 2D blood vessel profile, to obtain the first projected 2D blood vessel profile.
In an embodiment of the application, the projection module includes a third projection submodule and a fourth projection submodule, where the third projection submodule is configured to project the first projection corresponding point into the predetermined three-dimensional space with the second correction light source as a reference, so as to obtain a first projection point; the fourth projection submodule is configured to project the first projection point into the first plane with reference to the first light source, so as to obtain the first corresponding point.
In an embodiment of the present application, the acquiring unit includes an acquiring module and a processing module, wherein the acquiring module is configured to acquire a first 2D blood vessel image; the processing module is used for processing the first 2D blood vessel image by adopting a level set segmentation algorithm and a fast marching algorithm to obtain the first 2D blood vessel contour.
The corresponding point recommending device comprises a processor and a memory, the acquiring unit, the first determining unit, the second determining unit, the third determining unit, the fourth determining unit and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.
The processor comprises a kernel, and the kernel calls the corresponding program unit from the memory. The kernel can be set to be one or more, and the method for recommending the corresponding points is simplified by adjusting the parameters of the kernel.
The memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip.
The embodiment of the invention provides a computer-readable storage medium, which comprises a stored program, wherein when the program runs, a device where the computer-readable storage medium is located is controlled to execute the corresponding point recommendation method.
The embodiment of the invention provides a processor, which is used for running a program, wherein the corresponding point recommendation method is executed when the program runs.
The embodiment of the invention provides equipment, which comprises a processor, a memory and a program which is stored on the memory and can run on the processor, wherein when the processor executes the program, at least the following steps are realized:
step S101, acquiring a first 2D blood vessel contour and a second 2D blood vessel contour, wherein the first 2D blood vessel contour and the second 2D blood vessel contour are obtained at different shooting angles;
step S102, responding to a first preset operation of a user, and determining a first point on the second 2D blood vessel contour;
step S103, determining a second point on the second 2D blood vessel contour in response to a second predetermined operation of the user;
step S104 of determining a first corresponding point that matches the first point, the first corresponding point being located on the first 2D vessel contour;
step S105, determining a second corresponding point matched with the second point, where the second corresponding point is located on the first 2D blood vessel contour.
The device herein may be a server, a PC, a PAD, a mobile phone, etc.
The present application further provides a computer program product adapted to perform a program of initializing at least the following method steps when executed on a data processing device:
step S101, acquiring a first 2D blood vessel contour and a second 2D blood vessel contour, wherein the first 2D blood vessel contour and the second 2D blood vessel contour are obtained at different shooting angles;
step S102, responding to a first preset operation of a user, and determining a first point on the second 2D blood vessel contour;
step S103, determining a second point on the second 2D blood vessel contour in response to a second predetermined operation of the user;
step S104 of determining a first corresponding point that matches the first point, the first corresponding point being located on the first 2D vessel contour;
step S105, determining a second corresponding point matched with the second point, where the second corresponding point is located on the first 2D blood vessel contour.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.
Examples
The embodiment relates to a specific corresponding point recommendation method, and the corresponding point recommendation principle is shown in fig. 2, and the method comprises the following steps:
step S1: obtaining a first 2D vessel contour l1And a second 2D vessel profile l2First 2D vessel contour l1Is located on a first plane m1Inner, second 2D vessel contour l2Located in a second plane m2Internal;
step S2: with a first light source S1Taking the first plane m as a reference1First 2D vessel contour l in1Projecting the first image into a predetermined three-dimensional space to obtain a first projection profile vessel1To correct the light source S by the second correction2' As a reference, the first projection profile vessel1Projected to the second plane m2Obtaining the first projected 2D blood vessel contour l1', first projection 2D vessel contour l1' with a second 2D vessel profile l2An intersection point Q is formed;
step S3: at the second 2D vessel contour l2Clicking the first point P1, determining a first projection corresponding point P12 corresponding to the first point P1 by a robust point set registration method, and correcting the light source S by the second correction light source S2' as a reference, the first projection corresponding point P12 is projected into the predetermined three-dimensional space to obtain a first projection point P13; with the first light source S1Projecting the first projected point P13 to the first plane m as a reference1Obtaining the first corresponding point P11;
step S4: at the second 2D vessel contour l2Clicking the first point P2 upwards, and determining a second corresponding point P21 by the same method as the step S3;
step S5: the first point P1, the first corresponding point P11, the first point P2, the second corresponding point P21, and more sets of corresponding points are used for subsequent three-dimensional reconstruction.
According to the scheme, the accurate recommendation of the corresponding points is realized, and the time and the complexity of man-machine interaction are reduced.
From the above description, it can be seen that the above-described embodiments of the present application achieve the following technical effects:
1) the corresponding point recommendation method comprises the steps of obtaining a first 2D blood vessel contour and a second 2D blood vessel contour, determining a first point on the second 2D blood vessel contour in response to a first preset operation of a user, determining a second point on the second 2D blood vessel contour in response to a second preset operation of the user, automatically matching a first corresponding point corresponding to the first point, automatically matching a second corresponding point corresponding to the second point, and realizing recommendation of the corresponding points. The recommendation of the corresponding point is realized through two times of the predetermined operation. Compared with the scheme that four points need to be clicked in the prior art, the method is simple to operate. The complexity of human-computer interaction is reduced, the efficiency is improved, and more accurate input is provided for subsequent three-dimensional reconstruction.
2) The corresponding point recommendation device comprises an acquisition unit, a first determining unit, a second determining unit, a third determining unit and a fourth determining unit, wherein the acquisition unit acquires a first 2D blood vessel contour and a second 2D blood vessel contour, the first determining unit determines a first point on the second 2D blood vessel contour in response to a first preset operation of a user, the second determining unit determines a second point on the second 2D blood vessel contour in response to a second preset operation of the user, the third determining unit automatically matches a first corresponding point corresponding to the first point, and the fourth determining unit automatically matches a second corresponding point corresponding to the second point, so that recommendation of the corresponding points is realized. The recommendation of the corresponding point is realized through two times of the predetermined operation. Compared with the scheme that four points need to be clicked in the prior art, the method is simple to operate. The complexity of human-computer interaction is reduced, the efficiency is improved, and more accurate input is provided for subsequent three-dimensional reconstruction.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (10)
1. A corresponding point recommendation method is characterized by comprising the following steps:
acquiring a first 2D blood vessel contour and a second 2D blood vessel contour, wherein the first 2D blood vessel contour and the second 2D blood vessel contour are obtained at different shooting angles;
determining a first point on the second 2D vessel contour in response to a first predetermined operation by a user;
determining a second point on the second 2D vessel contour in response to a second predetermined operation by the user;
determining a first corresponding point matching the first point, the first corresponding point located on the first 2D vessel contour;
determining a second corresponding point that matches the second point, the second corresponding point located on the first 2D vessel contour.
2. The method of claim 1, wherein the first 2D vessel contour lies in a first plane and the second 2D vessel contour lies in a second plane, and wherein determining a first corresponding point that matches the first point comprises:
projecting the first 2D blood vessel contour to the second plane to obtain a first projected 2D blood vessel contour;
determining a first projected correspondence point matching the first point, the first projected correspondence point being located on the first projected 2D vessel contour;
and projecting the first projection corresponding point back to the first plane to obtain the first corresponding point.
3. The method of claim 2, wherein determining a first projected correspondent point that matches the first point comprises:
and determining the corresponding point of the first projection matched with the first point by adopting a robust point set registration algorithm.
4. The method according to claim 2, wherein projecting the first 2D vessel contour into the second plane resulting in a first projected 2D vessel contour comprises:
projecting the first 2D blood vessel contour to a preset three-dimensional space by taking a first light source as a reference to obtain a first projection contour, wherein the first light source corresponds to the first 2D blood vessel contour;
and projecting the first projection contour into the second plane by taking a second correction light source as a reference to obtain the first projection 2D blood vessel contour, wherein the second correction light source is a light source corrected by a second light source, and the second light source corresponds to the second 2D blood vessel contour.
5. The method of claim 4, wherein projecting the first projected correspondent point back into the first plane, resulting in the first correspondent point, comprises:
projecting the first projection corresponding point to the preset three-dimensional space by taking the second correction light source as a reference to obtain a first projection point;
and projecting the first projection point into the first plane by taking the first light source as a reference to obtain the first corresponding point.
6. The method according to claim 2, characterized in that the first projected 2D vessel contour has an intersection point with the second 2D vessel contour.
7. The method of claim 1, wherein obtaining the first 2D vessel contour comprises:
acquiring a first 2D blood vessel image;
and processing the first 2D blood vessel image by adopting a level set segmentation algorithm and a fast marching algorithm to obtain the first 2D blood vessel contour.
8. A correspondence point recommending apparatus, characterized by comprising:
the acquisition unit is used for acquiring a first 2D blood vessel contour and a second 2D blood vessel contour, wherein the first 2D blood vessel contour and the second 2D blood vessel contour are obtained at different shooting angles;
a first determination unit for determining a first point on the second 2D vessel contour in response to a first predetermined operation by a user;
a second determining unit for determining a second point on the second 2D vessel contour in response to a second predetermined operation by the user;
a third determining unit, configured to determine a first corresponding point that matches the first point, where the first corresponding point is located on the first 2D vessel contour;
a fourth determining unit, configured to determine a second corresponding point that matches the second point, where the second corresponding point is located on the first 2D blood vessel contour.
9. A computer-readable storage medium, comprising a stored program, wherein the program, when executed, controls an apparatus in which the computer-readable storage medium is located to perform the method of any one of claims 1 to 7.
10. A processor, characterized in that the processor is configured to run a program, wherein the program when running performs the method of any of claims 1 to 7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110876228.7A CN113487604B (en) | 2021-07-30 | 2021-07-30 | Corresponding point recommendation method and device, computer readable storage medium and processor |
| CN202211655071.6A CN116012315A (en) | 2021-07-30 | 2021-07-30 | Corresponding point recommending device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110876228.7A CN113487604B (en) | 2021-07-30 | 2021-07-30 | Corresponding point recommendation method and device, computer readable storage medium and processor |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211655071.6A Division CN116012315A (en) | 2021-07-30 | 2021-07-30 | Corresponding point recommending device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113487604A true CN113487604A (en) | 2021-10-08 |
| CN113487604B CN113487604B (en) | 2023-02-10 |
Family
ID=77944961
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110876228.7A Active CN113487604B (en) | 2021-07-30 | 2021-07-30 | Corresponding point recommendation method and device, computer readable storage medium and processor |
| CN202211655071.6A Pending CN116012315A (en) | 2021-07-30 | 2021-07-30 | Corresponding point recommending device |
Family Applications After (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211655071.6A Pending CN116012315A (en) | 2021-07-30 | 2021-07-30 | Corresponding point recommending device |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN113487604B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012228533A (en) * | 2012-07-09 | 2012-11-22 | Toshiba Corp | Image display device |
| CN111009032A (en) * | 2019-12-04 | 2020-04-14 | 浙江理工大学 | Blood vessel three-dimensional reconstruction method based on improved epipolar line constraint matching |
| US20200388050A1 (en) * | 2017-06-01 | 2020-12-10 | Shanghai Jiaotong University | Method and System for Indexing Blood Vessel Corresponding Positional Relations in Multi-Angle Angiography |
-
2021
- 2021-07-30 CN CN202110876228.7A patent/CN113487604B/en active Active
- 2021-07-30 CN CN202211655071.6A patent/CN116012315A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012228533A (en) * | 2012-07-09 | 2012-11-22 | Toshiba Corp | Image display device |
| US20200388050A1 (en) * | 2017-06-01 | 2020-12-10 | Shanghai Jiaotong University | Method and System for Indexing Blood Vessel Corresponding Positional Relations in Multi-Angle Angiography |
| CN111009032A (en) * | 2019-12-04 | 2020-04-14 | 浙江理工大学 | Blood vessel three-dimensional reconstruction method based on improved epipolar line constraint matching |
Non-Patent Citations (2)
| Title |
|---|
| SHAO-YA GUAN 等: "A Review of Point Feature Based Medical Image Registration", 《CHINESE JOURNAL OF MECHANICAL ENGINEERING》 * |
| 吕鹏等: "心血管三维重建的拓扑匹配方法", 《生物医学工程学杂志》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116012315A (en) | 2023-04-25 |
| CN113487604B (en) | 2023-02-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Murez et al. | Atlas: End-to-end 3d scene reconstruction from posed images | |
| US20180061046A1 (en) | Skin lesion segmentation using deep convolution networks guided by local unsupervised learning | |
| CN108475424B (en) | Method, apparatus and system for 3D face tracking | |
| CN108124489B (en) | Information processing method, apparatus, cloud processing device and computer program product | |
| US20170161884A1 (en) | Work-piece defect inspection via optical images and ct images | |
| CN110023989A (en) | A kind of generation method and device of sketch image | |
| US10970906B2 (en) | Filling in an entity within a video | |
| CN113674203A (en) | Defect detection model training method and device and defect detection method and device | |
| CN109903246B (en) | Method and device for detecting image change | |
| CN113487604B (en) | Corresponding point recommendation method and device, computer readable storage medium and processor | |
| US10970905B2 (en) | Filling in an entity within an image | |
| Hu et al. | Semantic object reconstruction via casual handheld scanning | |
| CN110717969A (en) | Shadow generation method and device | |
| US20220152935A1 (en) | Real-time monitoring of additive manufacturing | |
| CN115049683A (en) | Method and device for delineating radiotherapy image target area, processor and electronic equipment | |
| CN113269806B (en) | Method, device and processor for measuring blood flow inside blood vessel | |
| CN113012204B (en) | Registration method, registration device, storage medium and processor for multi-mode image | |
| CN115984455A (en) | Image processing method, device and equipment | |
| CN115359108A (en) | Depth prediction method and system based on defocusing under guidance of focal stack reconstruction | |
| US11621078B2 (en) | Pre-processing whole slide images in cognitive medical pipelines | |
| CN113935895A (en) | Medical image processing method and device, storage medium and processor | |
| US20220404819A1 (en) | Real-time reconfiguration of additive manufacturing | |
| CN116071375B (en) | Image segmentation method and device, storage medium and electronic equipment | |
| JP2020109630A (en) | Method and system for creating cut mask from 3d surface mesh | |
| US20230326028A1 (en) | Utilizing machine learning models to generate refined depth maps with segmentation mask guidance |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |