CN116012315A - Corresponding point recommending device - Google Patents
Corresponding point recommending device Download PDFInfo
- Publication number
- CN116012315A CN116012315A CN202211655071.6A CN202211655071A CN116012315A CN 116012315 A CN116012315 A CN 116012315A CN 202211655071 A CN202211655071 A CN 202211655071A CN 116012315 A CN116012315 A CN 116012315A
- Authority
- CN
- China
- Prior art keywords
- point
- blood vessel
- projection
- contour
- corresponding point
- 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
- 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
Abstract
The application provides a corresponding point recommending device. The device comprises: the acquisition unit is used for acquiring the first 2D blood vessel profile and the second 2D blood vessel profile; a first determining unit for selecting a first point on the second 2D vessel contour in response to a first predetermined operation acting on the second 2D vessel contour, and selecting a second point on the second 2D vessel contour in response to a second predetermined operation acting on the second 2D vessel contour; a second determining unit configured to determine a first corresponding point matching the first point and a second corresponding point matching the second point; the second determining unit is further configured to: and determining a first projection corresponding point matched with the first point by adopting a robust point set registration algorithm, and projecting the first projection corresponding point back into the first plane to obtain the first corresponding point. The scheme realizes the recommendation of the corresponding point through two preset operations. Compared with the scheme that four points need to be clicked in the prior art, the method is simple to operate.
Description
The scheme is a divisional application based on a case of a Chinese patent office, application number 2021108762287, application name corresponding point recommending method, device, computer readable storage medium and processor which are filed in 2021, 7 and 30 days.
Technical Field
The application relates to the field of medical imaging, in particular to a corresponding point recommending device.
Background
In the study of analyzing the cardiovascular and cerebrovascular based on the DSA image auxiliary technology, the key flow is as follows: vessel segmentation, light source correction, three-dimensional reconstruction of the vessel, quantitative analysis and the like. The blood vessel segmentation is to enhance the DSA image to highlight the edge of the blood vessel, increase the difference between the foreground blood vessel and the background image, and further segment the target blood vessel. The light source correction is to make the corresponding points of two contours in the projection plane have a corresponding relationship through the space transformation of the light source. The three-dimensional reconstruction of the blood vessel is to restore two corrected two-dimensional projection images into a three-dimensional model and restore a space structure. Quantitative analysis is to calculate and analyze a three-dimensional model to obtain critical parameters of blood vessels required clinically, such as the stenosis rate of blood vessels, and the critical parameters are used for evaluating the severity of the illness of patients.
Between the two steps of light source correction and three-dimensional reconstruction of the blood vessel, an operator needs to perform man-machine interaction through clicking a mouse to obtain two-dimensional blood vessel images, the two-dimensional blood vessel images are used as input of three-dimensional reconstruction, the operator reconstructs blood vessels with any length and any branch according to actual requirements, and four points need to be clicked in total by clicking a starting point and an ending point of the blood vessel to be reconstructed in the two-dimensional blood vessel images respectively. In the prior art, if three-dimensional reconstruction of the blood vessel is needed, four points need to be clicked, and the operation is complex.
Disclosure of Invention
The main object of the present application is to provide a corresponding point recommendation device, so as to solve the problem that in the prior art, four points need to be clicked in the process of 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 one aspect of the present application, there is provided a corresponding point recommending apparatus, including:
the device comprises an acquisition unit, a first processing unit and a second processing unit, wherein the acquisition unit is used for acquiring a first 2D blood vessel contour and a second 2D blood vessel contour, the first 2D blood vessel contour is positioned in a first plane, the second 2D blood vessel contour is positioned in a second plane, a light source corresponding to the first 2D blood vessel contour is a first light source, and a light source corresponding to the second 2D blood vessel contour is a second light source; the first 2D blood vessel contour and the second 2D blood vessel contour are blood vessel contours obtained under different shooting angles;
a first determining unit for selecting a first point on the second 2D vessel contour in response to a first predetermined operation acting on the second 2D vessel contour, and for selecting a second point on the second 2D vessel contour in response to a second predetermined operation acting on the second 2D vessel contour;
a second determining unit, configured to determine a first corresponding point matched with the first point and a second corresponding point matched with the second point, where the first corresponding point and the second corresponding point are both located on the first 2D blood vessel contour;
the second determining unit is further configured to: determining a first projection corresponding point matched with the first point by adopting a robust point set registration algorithm, wherein the first projection corresponding point is positioned on a first projection 2D blood vessel contour, the first projection 2D blood vessel contour is a contour of the first 2D blood vessel contour projected in the second plane, the first 2D blood vessel contour is obtained based on the first light source and a second correction light source, and the second correction light source is a light source corrected for the second light source; and projecting the first projection corresponding point back into the first plane to obtain the first corresponding point.
Optionally, the second determining unit includes: the projection module is used for projecting the first 2D blood vessel contour into the second plane to obtain a first projected 2D blood vessel contour, wherein the projection module comprises: the first projection submodule is used for projecting the first 2D blood vessel contour into a preset three-dimensional space by taking the first light source as a reference to obtain a first projection contour; and the second projection sub-module is used for projecting the first projection contour into the second plane by taking the second correction light source as a reference to obtain the first projection 2D blood vessel contour.
Optionally, the second determining unit includes: the projection module is used for projecting the first projection corresponding point back into the first plane to obtain the first corresponding point; the projection module includes: the third projection sub-module is used for projecting the first projection corresponding point into a preset three-dimensional space by taking the second correction light source as a reference to obtain a first projection point; and the fourth projection sub-module is used for 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 acquiring unit includes: the acquisition module is used for acquiring a first 2D blood vessel image; and 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 outline.
Optionally, the first projected 2D vessel profile has an intersection with the second 2D vessel profile.
Optionally, the first 2D vessel profile and the second 2D vessel profile are coronary vessel profiles.
Optionally, the first predetermined operation is a click operation, and the second predetermined operation is a click operation.
By the technical scheme, the first 2D blood vessel outline and the second 2D blood vessel outline are obtained, then the first point is determined on the second 2D blood vessel outline in response to the first preset operation of the user, the second point is determined on the second 2D blood vessel outline in response to the second preset operation of the user, then the first corresponding point corresponding to the first point is automatically matched, the second corresponding point corresponding to the second point is automatically matched, and recommendation of the corresponding points is achieved. Recommendation of the corresponding point is achieved through two preset operations. Compared with the scheme that four points need to be clicked in the prior art, the method is simple to operate. The complexity of man-machine interaction is reduced, the efficiency is improved, and more accurate input is provided for subsequent three-dimensional reconstruction.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and 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 do not constitute an undue limitation to the application. In the drawings:
FIG. 1 illustrates a corresponding point recommendation method flow diagram according to an embodiment of the present application;
FIG. 2 illustrates a specific correspondence point recommendation method schematic diagram in accordance with an embodiment of the present application;
fig. 3 shows a schematic diagram of a corresponding point recommending apparatus according to an embodiment of the present application.
Detailed Description
It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be combined with each other. The present application will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
In order to make the present application solution better understood by those skilled in the art, the following description will be made in detail and with reference to the accompanying drawings in the embodiments of the present application, it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, shall fall within the scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate in order to describe the embodiments of the present application described herein. 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. Furthermore, in the description and in the 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, the following will describe some terms or terms related to the embodiments of the present application:
robust point set registration (Robust point matching (RPM)): the algorithm is initialized to assign registration parameters between 0 and 1 to any group of corresponding points, the numerical value represents the degree that the group of points are corresponding points, the numerical value of 1 indicates that the group of points are confirmed to be one group of corresponding points, the algorithm is used for carrying out multiple iterations, and the registration parameters are converged to two values of 0 or 1.
As described in the background art, in the prior art, four points need to be clicked in the process of three-dimensional reconstruction of a blood vessel by adopting 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 three-dimensional reconstruction of a blood vessel by adopting two-dimensional blood vessel images as described above, the embodiment of the application provides a corresponding point recommending method, a device, 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 correspondence 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 vessel contour l 1 And a second 2D vessel profile 2 The first 2D vessel contour and the second 2D vessel contourThe blood vessel profile is obtained under different shooting angles;
step S102, responding to the first preset operation of the user, and obtaining the second 2D blood vessel contour l 2 Determining a first point P1;
step S103, responding to the second preset operation of the user, and obtaining the second 2D blood vessel contour l 2 Determining a second point P2;
step S104 of determining a first corresponding point P11 matching the first point P1, the first corresponding point P11 being located in the first 2D vessel contour l 1 Applying;
step S105 of determining a second corresponding point P21 matching the second point P2, the second corresponding point P21 being located in the first 2D vessel contour l 1 And (3) upper part.
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 including a single click or a double click operation. Of course, operations other than the click operation may be used.
Specifically, the second predetermined operation may be a click operation including a single click or a double click operation. Of course, operations other than the click operation may be used.
Specifically, the user makes one click on the second 2D vessel contour, determining the first point. The first corresponding point corresponding to the first point is then automatically matched. The user then clicks again on the second 2D vessel contour, determining a second point. And then automatically matches a second corresponding point corresponding to the second point. The recommendation of the corresponding point is realized through two clicking operations.
In the above scheme, by acquiring the first 2D blood vessel contour and the second 2D blood vessel contour, then 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, then automatically matching a first corresponding point corresponding to the first point, and automatically matching a second corresponding point corresponding to the second point, recommendation of the corresponding points is achieved. Recommendation of the corresponding point is achieved through two preset operations. Compared with the scheme that four points need to be clicked in the prior art, the method is simple to operate. The complexity of man-machine 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 other than that illustrated herein.
In one embodiment of the present application, as shown in fig. 2, the first 2D vessel profile l 1 Lying in a first plane m 1 In, the second 2D vessel contour l 2 Lying in a second plane m 2 In the step, a first corresponding point P11 matching the first point P1 is determined, including: contour of the first 2D vessel 1 Projected to the second plane m 2 In, a first projection 2D vessel contour l is obtained 1 'A'; determining a first projection corresponding point P12 matching the first point P1, the first projection corresponding point P12 being located in the first projection 2D vessel contour l 1 'upper'; projecting the first projection corresponding point P12 back to the first plane m 1 The first corresponding point P11 is obtained.
In one embodiment of the present application, as shown in fig. 2, determining the first projection 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. Common registration methods include rigid transformation-based registration methods and feature point-based registration methods. The registration method based on rigid transformation (i.e., transformation such as translation, rotation, and scaling) may result in the loss of information of overlapping portions in a certain projection direction with respect to the "L" data. The registration method based on the feature points (namely the corner points, the boundaries and the like) cannot ensure successful registration under the condition that the feature points are missing or the image is not obvious in shape. The robust point set registration algorithm in the scheme can realize the second 2D vessel contour l 2 The points on the first projection and the first projection 2D vessel contour l 1 ' one-to-one correspondence of points on (i.eEach point has a corresponding point, the condition of no solution does not occur), the condition of information deletion does not occur, and successful registration can be realized under the condition of feature point deletion or unobvious image morphology.
In addition, compared with the polar constraint registration method, the robust point set registration algorithm simplifies the registration process and improves the efficiency. The epipolar line is the intersection 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 polar constraint registration method is as follows: if the intersection point of the line and the target is only one, the recommended corresponding point is directly obtained, and if the intersection point is not unique, the judgment is still assisted by other methods, and 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, as shown in fig. 2, the first 2D vessel profile l is described above 1 Projected to the second plane m 2 In, a first projection 2D vessel contour l is obtained 1 ' comprising: with a first light source S 1 Taking the first 2D blood vessel contour l as a reference 1 Projecting into a preset three-dimensional space to obtain a first projection profile vessel 1 The first light source S 1 And the first 2D blood vessel contour l 1 Corresponding to the above; with a second correcting light source S 2 ' taking the first projection contour vessel as a reference 1 Projected to the second plane m 2 In, the first projection 2D vessel contour l is obtained 1 ' the second correction light source S 2 ' is a light source corrected for a second light source corresponding to the second 2D vessel profile. Through single point light source correction, the second plane m 2 Second 2D vessel profile in 2 The points on the first projection and the first projection 2D vessel contour l 1 The points on' have a correspondence relationship, which includes that the set of corresponding points coincide or that the set of corresponding points are on one epipolar line. A second 2D vessel contour l can be obtained by using a robust point set registration algorithm 2 And a first projection 2D vessel contour l 1 ' all correspondence of upper points. The accuracy of matching the corresponding points is ensured.
Specifically, the second correction light source in the application is a light source corrected by the second light source, and the first light source is not corrected, namely, recommendation based on single-point correction is realized in the application, single-point correction only has one group of corresponding point information, and compared with the case that the single-point correction information is less in the case of multi-point correction, the method and the device provide greater difficulty for recommending operation of the next corresponding point. The corresponding point recommendation under the single point correction can be realized by the scheme, and the corresponding point recommendation under the multi-point correction can be naturally realized, so that 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 m 1 The first corresponding point P11 is obtained by: with the second correction light source S 2 Taking' as a reference, projecting the first projection corresponding point P12 into the preset three-dimensional space to obtain a first projection point P13; with the first light source S 1 Projecting the first projection point P13 to the first plane m 1 The first corresponding point P11 is obtained.
In one embodiment of the present application, as shown in fig. 2, the first projection 2D vessel profile l 1 ' and the second 2D vessel profile l described above 2 There 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, an intersection point exists between the first projected 2D blood vessel contour and the second 2D blood vessel contour, that is, the intersection point is formed before the corresponding point is matched. The information of the intersection point can be directly utilized during matching, the intersection point is located on the first projection 2D blood vessel contour and the second projection 2D blood vessel contour at the same time, namely, a group of corresponding points (under the condition of one intersection point) are known to have a certain corresponding relation, the known condition is increased, the calculation of unknown data is reduced, and the accuracy of matching 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 profile includes: acquiring a first 2D 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 outline. The level set segmentation algorithm is used for carrying out segmentation processing on the first 2D blood vessel image, and the fast traveling algorithm is used for carrying out center line extraction processing on the first 2D blood vessel image. The first 2D vessel contour may be extracted from the first 2D vessel image by a flat set segmentation algorithm and a fast marching algorithm.
The embodiment of the application also provides a corresponding point recommending device, and the corresponding point recommending device can be used for executing the corresponding point recommending method provided by the embodiment of the application. The following describes a corresponding point recommending device provided in the 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 acquisition unit 10 that acquires a first 2D blood vessel contour and a second 2D blood vessel contour, the first 2D blood vessel contour and the second 2D blood vessel contour being blood vessel contours obtained at different imaging angles;
a first determining unit 20 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 30 for determining 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 matching the first point, where the first corresponding point is located on the first 2D blood vessel contour;
a fourth determining unit 50 for determining a second corresponding point matching the second point, the second corresponding point being located on the first 2D vessel contour.
In the above scheme, the acquiring unit acquires the first 2D blood vessel contour and the second 2D blood vessel contour, the first determining unit determines the first point on the second 2D blood vessel contour in response to a first predetermined operation of the user, the second determining unit determines the 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 the first corresponding point corresponding to the first point, and the fourth determining unit automatically matches the second corresponding point corresponding to the second point, so that recommendation of the corresponding point is realized. Recommendation of the corresponding point is achieved through two preset operations. Compared with the scheme that four points need to be clicked in the prior art, the method is simple to operate. The complexity of man-machine interaction is reduced, the efficiency is improved, and more accurate input is provided for subsequent three-dimensional reconstruction.
In one 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 used for determining a first projection corresponding point matched with the first point, and the first projection corresponding point is positioned on the first projection 2D blood vessel contour; the projection module is used for projecting the first projection corresponding point back into the first plane to obtain the first corresponding point.
In an embodiment of the present application, the determining module is further configured to determine the first projection corresponding point that matches the first point by using a robust point set registration algorithm.
In one 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 based on a first light source to obtain a first projection contour, and the first light source corresponds to the first 2D blood vessel contour; the second projection submodule is used for projecting the first projection outline into the second plane by taking a second correction light source as a reference to obtain the first projection 2D blood vessel outline, the second correction light source is a light source corrected by the second light source, and the second light source corresponds to the second 2D blood vessel outline.
In one embodiment of the present application, the projection module includes a third projection sub-module and a fourth projection sub-module, where the third projection sub-module is configured to project the first projection corresponding point into the predetermined three-dimensional space with the second correction light source as a reference, to obtain a first projection point; the fourth projection submodule is used for projecting the first projection point into the first plane by taking the first light source as a reference to obtain the first corresponding point.
In one embodiment of the present application, the acquiring unit includes an acquiring module and a processing module, where 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 outline.
The corresponding point recommending device comprises a processor and a memory, wherein the acquiring unit, the first determining unit, the second determining unit, the third determining unit, the fourth determining unit and the like are all stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.
The processor includes a kernel, and the kernel fetches the corresponding program unit from the memory. The kernel can be provided with one or more than one, and the method for recommending the corresponding point is simplified by adjusting kernel parameters.
The memory may include volatile memory, random Access Memory (RAM), and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM), among other forms in computer readable media, the memory including 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, equipment 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 recommending method is executed when the program runs.
The embodiment of the invention provides equipment, which comprises a processor, a memory and a program stored in the memory and capable of running on the processor, wherein the processor realizes at least the following steps when executing the program:
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 blood vessel contours obtained under 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 outline;
step S103, responding to a second preset operation of the user, and determining a second point on the second 2D blood vessel outline;
step S104, determining a first corresponding point matched with the first point, wherein the first corresponding point is positioned on the first 2D blood vessel contour;
step S105, determining a second corresponding point matching the second point, where the second corresponding point is located on the first 2D vessel contour.
The device herein may be a server, PC, PAD, cell phone, etc.
The present application also provides a computer program product adapted to perform a program initialized with 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 blood vessel contours obtained under 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 outline;
step S103, responding to a second preset operation of the user, and determining a second point on the second 2D blood vessel outline;
step S104, determining a first corresponding point matched with the first point, wherein the first corresponding point is positioned on the first 2D blood vessel contour;
step S105, determining a second corresponding point matching the second point, where the second corresponding point is located on the first 2D vessel contour.
It will be appreciated by those skilled in the art that 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 flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations 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 one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, etc., such as Read Only Memory (ROM) or flash RAM. 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 storage media for a computer 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, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
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 one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises an element.
Examples
The embodiment relates to a specific corresponding point recommending method, and the corresponding point recommending principle is shown in fig. 2, and the method comprises the following steps:
step S1: acquiring a first 2D vessel contour l 1 And a second 2D vessel profile 2 First 2D vessel contour l 1 Lying in a first plane m 1 In, second 2D vessel profile l 2 Lying in a second plane m 2 An inner part;
step S2: in the first placeA light source S 1 Taking the first plane m as a reference 1 First 2D vessel profile/in 1 Projecting into a preset three-dimensional space to obtain a first projection profile vessel 1 With a second correcting light source S 2 ' taking the first projection contour vessel as a reference 1 Projected to the second plane m 2 In, the first projection 2D vessel contour l is obtained 1 ' first projection 2D vessel contour l 1 ' and second 2D vessel profile l 2 Has an intersection point Q;
step S3: in the second 2D vessel profile l 2 Clicking the first point P1, determining a first projection corresponding point P12 corresponding to the first point P1 by adopting a robust point set registration method, and using the second correction light source S 2 Taking' as a reference, projecting the first projection corresponding point P12 into the preset three-dimensional space to obtain a first projection point P13; with the first light source S 1 Projecting the first projection point P13 to the first plane m 1 Obtaining the first corresponding point P11;
step S4: in the second 2D vessel profile l 2 Clicking on the first point P2, and determining a second corresponding point P21 by adopting the same method as that of the step S3;
step S5: the first point P1, the first corresponding point P11, the first point P2, the second corresponding point P21 and further sets of corresponding points are used for subsequent three-dimensional reconstruction.
The scheme realizes accurate recommendation of the corresponding points and reduces time and complexity of man-machine interaction.
From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:
1) According to the corresponding point recommending method, through acquiring the first 2D blood vessel outline and the second 2D blood vessel outline, then responding to the first preset operation of a user, determining a first point on the second 2D blood vessel outline, responding to the second preset operation of the user, determining a second point on the second 2D blood vessel outline, then automatically matching a first corresponding point corresponding to the first point, automatically matching a second corresponding point corresponding to the second point, and recommending the corresponding points. Recommendation of the corresponding point is achieved through two preset operations. Compared with the scheme that four points need to be clicked in the prior art, the method is simple to operate. The complexity of man-machine interaction is reduced, the efficiency is improved, and more accurate input is provided for subsequent three-dimensional reconstruction.
2) According to the corresponding point recommending device, the acquiring unit acquires the first 2D blood vessel outline and the second 2D blood vessel outline, the first determining unit determines the first point on the second 2D blood vessel outline in response to the first preset operation of the user, the second determining unit determines the second point on the second 2D blood vessel outline in response to the second preset operation of the user, the third determining unit automatically matches the first corresponding point corresponding to the first point, and the fourth determining unit automatically matches the second corresponding point corresponding to the second point to achieve the recommendation of the corresponding point. Recommendation of the corresponding point is achieved through two preset operations. Compared with the scheme that four points need to be clicked in the prior art, the method is simple to operate. The complexity of man-machine interaction is reduced, the efficiency is improved, and more accurate input is provided for subsequent three-dimensional reconstruction.
The foregoing description is only of the preferred embodiments of the present application and is not intended to limit the same, but rather, various modifications and variations may be made by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.
Claims (7)
1. A correspondence point recommendation device, characterized by comprising:
the device comprises an acquisition unit, a first processing unit and a second processing unit, wherein the acquisition unit is used for acquiring a first 2D blood vessel contour and a second 2D blood vessel contour, the first 2D blood vessel contour is positioned in a first plane, the second 2D blood vessel contour is positioned in a second plane, a light source corresponding to the first 2D blood vessel contour is a first light source, and a light source corresponding to the second 2D blood vessel contour is a second light source; the first 2D blood vessel contour and the second 2D blood vessel contour are blood vessel contours obtained under different shooting angles;
a first determining unit for selecting a first point on the second 2D vessel contour in response to a first predetermined operation acting on the second 2D vessel contour, and for selecting a second point on the second 2D vessel contour in response to a second predetermined operation acting on the second 2D vessel contour;
a second determining unit, configured to determine a first corresponding point matched with the first point and a second corresponding point matched with the second point, where the first corresponding point and the second corresponding point are both located on the first 2D blood vessel contour;
the second determining unit is further configured to: determining a first projection corresponding point matched with the first point by adopting a robust point set registration algorithm, wherein the first projection corresponding point is positioned on a first projection 2D blood vessel contour, the first projection 2D blood vessel contour is a contour of the first 2D blood vessel contour projected in the second plane, the first 2D blood vessel contour is obtained based on the first light source and a second correction light source, and the second correction light source is a light source corrected for the second light source; and projecting the first projection corresponding point back into the first plane to obtain the first corresponding point.
2. The apparatus according to claim 1, wherein the second determining unit includes:
the projection module is used for projecting the first 2D blood vessel contour into the second plane to obtain a first projected 2D blood vessel contour, wherein the projection module comprises:
the first projection submodule is used for projecting the first 2D blood vessel contour into a preset three-dimensional space by taking the first light source as a reference to obtain a first projection contour;
and the second projection sub-module is used for projecting the first projection contour into the second plane by taking the second correction light source as a reference to obtain the first projection 2D blood vessel contour.
3. The apparatus according to claim 1, wherein the second determining unit includes:
the projection module is used for projecting the first projection corresponding point back into the first plane to obtain the first corresponding point;
the projection module includes:
the third projection sub-module is used for projecting the first projection corresponding point into a preset three-dimensional space by taking the second correction light source as a reference to obtain a first projection point;
and the fourth projection sub-module is used for projecting the first projection point into the first plane by taking the first light source as a reference to obtain the first corresponding point.
4. The apparatus according to claim 1, wherein the acquisition unit includes:
the acquisition module is used for acquiring a first 2D blood vessel image;
and 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 outline.
5. The apparatus of any one of claims 1 to 4, wherein the first projected 2D vessel profile has an intersection with the second 2D vessel profile.
6. The device of any one of claims 1 to 4, wherein the first 2D vessel profile and the second 2D vessel profile are coronary vessel profiles.
7. The apparatus of any one of claims 1 to 4, wherein the first predetermined operation is a click operation and the second predetermined operation is a click operation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211655071.6A CN116012315A (en) | 2021-07-30 | 2021-07-30 | Corresponding point recommending device |
Applications Claiming Priority (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 |
Related Parent Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110876228.7A Division CN113487604B (en) | 2021-07-30 | 2021-07-30 | Corresponding point recommendation method and device, computer readable storage medium and processor |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116012315A true CN116012315A (en) | 2023-04-25 |
Family
ID=77944961
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211655071.6A Pending CN116012315A (en) | 2021-07-30 | 2021-07-30 | Corresponding point recommending device |
| CN202110876228.7A Active CN113487604B (en) | 2021-07-30 | 2021-07-30 | Corresponding point recommendation method and device, computer readable storage medium and processor |
Family Applications After (1)
| 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 |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN116012315A (en) |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5269232B2 (en) * | 2012-07-09 | 2013-08-21 | 株式会社東芝 | Image display device |
| CN107233106A (en) * | 2017-06-01 | 2017-10-10 | 上海交通大学 | Blood vessel correspondence position relation search method and system under multi-angle radiography |
| CN111009032B (en) * | 2019-12-04 | 2023-09-19 | 浙江理工大学 | Vascular three-dimensional reconstruction method based on improved epipolar line constraint matching |
-
2021
- 2021-07-30 CN CN202211655071.6A patent/CN116012315A/en active Pending
- 2021-07-30 CN CN202110876228.7A patent/CN113487604B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113487604A (en) | 2021-10-08 |
| CN113487604B (en) | 2023-02-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Murez et al. | Atlas: End-to-end 3d scene reconstruction from posed images | |
| CN112652011B (en) | Extraction method and extraction device of target blood vessel and computer-readable storage medium | |
| Li et al. | Fast guided global interpolation for depth and motion | |
| US10614599B2 (en) | Anatomy segmentation through low-resolution multi-atlas label fusion and corrective learning | |
| Moulon et al. | Adaptive structure from motion with a contrario model estimation | |
| CN108124489B (en) | Information processing method, apparatus, cloud processing device and computer program product | |
| CN110023989A (en) | A kind of generation method and device of sketch image | |
| CN113487604B (en) | Corresponding point recommendation method and device, computer readable storage medium and processor | |
| CN116894844A (en) | Hip joint image segmentation and key point linkage identification method and device | |
| Hu et al. | Semantic object reconstruction via casual handheld scanning | |
| CN113012204B (en) | Registration method, registration device, storage medium and processor for multi-mode image | |
| CN110717969A (en) | Shadow generation method and device | |
| Manam et al. | Correspondence reweighted translation averaging | |
| 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 | |
| Zisler et al. | Discrete tomography by continuous multilabeling subject to projection constraints | |
| CN113935895A (en) | Medical image processing method and device, storage medium and processor | |
| CN113034683A (en) | Method and device for determining true and false of blood vessel central line and truncation position | |
| JP2022553658A (en) | Method and system for segmenting images | |
| CN116071375B (en) | Image segmentation method and device, storage medium and electronic equipment | |
| Cambra et al. | A generic tool for interactive complex image editing | |
| US20220404819A1 (en) | Real-time reconfiguration of additive manufacturing | |
| CN115953440B (en) | Registration method and device of medical image, storage medium and electronic equipment | |
| Zhu et al. | ALRe: Outlier detection for guided refinement |
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 |