CN113822923A - Method, apparatus and medium for acquiring target sectional image of blood vessel - Google Patents
Method, apparatus and medium for acquiring target sectional image of blood vessel Download PDFInfo
- Publication number
- CN113822923A CN113822923A CN202111106508.6A CN202111106508A CN113822923A CN 113822923 A CN113822923 A CN 113822923A CN 202111106508 A CN202111106508 A CN 202111106508A CN 113822923 A CN113822923 A CN 113822923A
- Authority
- CN
- China
- Prior art keywords
- coordinate system
- blood vessel
- plane coordinate
- tangent
- vector
- 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
- G06T7/50—Depth or shape recovery
- G06T7/55—Depth or shape recovery from multiple images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/20—Finite element generation, e.g. wire-frame surface description, tesselation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/08—Indexing scheme for image data processing or generation, in general involving all processing steps from image acquisition to 3D model generation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
Embodiments of the present disclosure relate to a method, apparatus, and medium for acquiring a target sectional image of a blood vessel. According to the method, a three-dimensional mesh model of the blood vessel is generated based on a plurality of successive axial tomographic images of the blood vessel so as to determine a centerline of the blood vessel on the three-dimensional mesh model; establishing an initial tangent plane coordinate system based on a plurality of continuous axial tomography images; identifying a midpoint of a target section of the vessel on the centerline to determine a tangent vector of the centerline on the midpoint; based on the tangent vector, transforming the initial tangent plane coordinate system into a target tangent plane coordinate system; generating a tomographic image of the target tangent plane by using multi-plane reconstruction based on the target tangent plane coordinate system and the plurality of continuous axial tomographic images. Therefore, accurate and detailed section images of any target position of the blood vessel can be obtained, and the requirements on the space imagination ability and professional ability of a user are avoided.
Description
Technical Field
Embodiments of the present disclosure relate generally to the field of medical image processing, and more particularly, to a method, apparatus, and medium for acquiring a target sectional image of a blood vessel.
Background
With the development of Computed Tomography (CT) image post-processing technology, it has been widely applied in the scenes of clinical examination of vascular diseases, clinical treatment of vascular diseases, stent implantation surgery, etc. to help identify and treat problematic vessels such as aortic dissection vasculopathy, coronary artery lesions, mesenteric vascular embolism, etc. Particularly, by utilizing the CT image post-processing technology, the blood vessel shape can be visually presented, the artery trunk, branch and surrounding tissues of the blood vessel can be clearly and fully displayed, so that a doctor can quickly and accurately find the position of the blood vessel lesion and observe the artery stenosis degree, and meanwhile, the doctor can perform more detailed observation aiming at the local lesion position.
At present, a blood vessel image is reconstructed by using CT image post-processing methods such as Volume Rendering (VR), Maximum Intensity Projection (MIP), Multi-planar reconstruction (MPR), and the like, but these methods are either complex to implement, cannot provide clear and detailed image information of a target section of a blood vessel, or require a user to have certain professional ability and sufficient space imagination ability to accurately judge an expected observation angle and a midpoint position of the blood vessel, so that a real section image of the blood vessel at any position cannot be acquired.
Therefore, it is necessary to provide an easily implemented technique for acquiring a target sectional image of a blood vessel, so that an accurate and detailed sectional image of any target position of the blood vessel can be provided, a user can view medical images of the blood vessel from multiple angles in a targeted manner without having a space imagination capability, and the problem of errors caused by artificial determination of an observation angle is avoided.
Disclosure of Invention
In view of the above problems, the present disclosure provides a method and device for obtaining a target sectional image of a blood vessel, which are easy to implement, and can obtain an accurate and detailed sectional image of any target position of the blood vessel without requiring the spatial imagination and professional ability of a user.
According to a first aspect of the present disclosure, there is provided a method for acquiring a target sectional image of a blood vessel, comprising: generating a three-dimensional mesh model of a blood vessel based on a plurality of successive axial tomographic images of the blood vessel so as to determine a centerline of the blood vessel on the three-dimensional mesh model; establishing an initial tangent plane coordinate system based on the plurality of continuous axial tomography images; identifying a midpoint of a target tangent plane of the vessel on the midline to determine a tangent vector of the midline at the midpoint; transforming the initial tangent plane coordinate system into a target tangent plane coordinate system based on the tangent vector; and generating a tomographic image of the target tangent plane using multi-plane reconstruction based on the target tangent plane coordinate system and the plurality of consecutive axial tomographic images.
According to a second aspect of the present disclosure, there is provided a computing device comprising: at least one processor; and a memory communicatively coupled to the at least one processor; the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of the first aspect of the disclosure.
In a third aspect of the present disclosure, a non-transitory computer readable storage medium is provided having stored thereon computer instructions for causing the computer to perform the method of the first aspect of the present disclosure.
In some embodiments, establishing an initial tangent plane coordinate system based on the plurality of consecutive axial tomographic images comprises: determining a central point of a three-dimensional image data set as an origin of the initial tangent plane coordinate system, wherein the three-dimensional image data set is formed by overlapping the plurality of continuous axial tomography images; and establishing the initial tangential plane coordinate system based on the determined origin, wherein a horizontal axis and a vertical axis of the initial tangential plane coordinate system are established on a plane parallel to a plane on which each axial tomographic image is located, and a vertical axis of the initial tangential plane coordinate system is perpendicular to the horizontal axis and the vertical axis.
In some embodiments, determining a center point of the three-dimensional image dataset as the origin of the initial tangent plane coordinate system comprises: determining an origin, a lateral extension, a longitudinal extension and a vertical extension of the three-dimensional image dataset; and determining an origin of the initial tangent plane coordinate system based on the origin, the lateral extension range, the longitudinal extension range, and the vertical extension range of the three-dimensional image data set.
In some embodiments, determining a tangent vector of the midline at the midpoint comprises: respectively taking a first point and a second point at the left side and the right side of the middle point on the middle line; determining a first vector from the second point to the first point, a second vector from the second point to the midpoint, and a third vector from the midpoint to the first point; and determining the tangent vector based on the first vector, the second vector, and the third vector.
In some embodiments, transforming the initial tangent plane coordinate system to a target tangent plane coordinate system based on the tangent vector comprises: rotating and translating the initial tangent plane coordinate system based on the tangent vector such that a vertical axis of a transformed initial tangent plane coordinate system is parallel to the tangent vector and an origin of the transformed initial tangent plane coordinate system coincides with the midpoint, the transformed initial tangent plane coordinate system corresponding to the target tangent plane coordinate system.
In some embodiments, rotating and translating the initial tangent plane coordinate system based on the tangent vector such that a vertical axis of the transformed initial tangent plane coordinate system is parallel to the tangent vector and an origin of the transformed initial tangent plane coordinate system coincides with the midpoint comprises: projecting the tangent vector on a first plane to determine a second tangent vector, the first plane being defined by a horizontal axis and a vertical axis of the initial tangent plane coordinate system; determining a first included angle between the second tangent vector and the vertical axis; projecting the tangent vector on a second plane to determine a third tangent vector, the second plane being defined by a longitudinal axis of the initial tangent plane coordinate system and the vertical axis; determining a second included angle between the third tangent vector and the vertical axis; rotating the initial tangent plane coordinate system counterclockwise around the longitudinal axis by the first included angle so as to determine a second coordinate system; rotating the second coordinate system counterclockwise around the transverse axis by the second included angle so as to determine a third coordinate system; and translating the origin of the third coordinate system to the midpoint.
In some embodiments, the vessel comprises a main vessel and a plurality of branch vessels, and generating the centerline of the vessel on the three-dimensional mesh model comprises generating a first centerline of the main vessel and a plurality of second centerlines of the plurality of branch vessels on the three-dimensional mesh model.
In some embodiments, generating a three-dimensional mesh model of a blood vessel based on a plurality of sequential axial tomographic images of the blood vessel comprises: segmenting a blood vessel region from each of the plurality of continuous axial tomographic images based on a trained deep learning model, the deep learning model including a convolutional neural network model or a three-dimensional Unet network model, and the trained deep learning model being trained based on a plurality of continuous sample axial tomographic images labeled with the blood vessel region; and generating a three-dimensional mesh model of the blood vessel based on the blood vessel region.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.
Drawings
The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. In the drawings, like or similar reference characters designate like or similar elements.
Fig. 1 shows a schematic diagram of a system 100 for implementing a method for acquiring a target sectional image of a blood vessel according to an embodiment of the present invention.
Fig. 2 shows a flow chart of a method 200 for acquiring a target sectional image of a blood vessel according to an embodiment of the present disclosure.
FIG. 3 shows a flow chart of a method 300 for establishing an initial tangent coordinate system based on a plurality of consecutive axial tomographic images.
Fig. 4 shows an illustrative schematic diagram for establishing an initial tangent plane coordinate system based on a plurality of successive axial tomographic images.
Fig. 5 shows an illustrative diagram for determining the tangent vector of the midline at the midpoint.
Fig. 6 shows an illustrative schematic diagram for transforming an initial tangent plane coordinate system to a target tangent plane coordinate system based on tangent vectors.
Fig. 7 shows a flow diagram of a method 700 for rotating and translating an initial tangent plane coordinate system based on tangent vectors.
FIG. 8 shows an illustrative schematic for generating a tomographic image of a target slice in accordance with an embodiment of the present disclosure.
Fig. 9 shows a block diagram of an electronic device 900 according to an embodiment of the disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
The term "include" and variations thereof as used herein is meant to be inclusive in an open-ended manner, i.e., "including but not limited to". Unless specifically stated otherwise, the term "or" means "and/or". The term "based on" means "based at least in part on". The terms "one example embodiment" and "one embodiment" mean "at least one example embodiment". The term "another embodiment" means "at least one additional embodiment". The terms "first," "second," and the like may refer to different or the same object. Other explicit and implicit definitions are also possible below.
As described above, it is common to reconstruct a blood vessel image by using a CT image post-processing method such as Volume Rendering (VR), Maximum Intensity Projection (MIP), multi-planar reconstruction (MPR), or the like, so as to observe each part of the blood vessel. However, these methods have certain disadvantages.
Volume Rendering (VR) is a very complicated image reconstruction method that implements a virtual illumination effect by setting CT values of all voxels to have different transparencies while using Surface Shaded Display (SSD), and displays a three-dimensional spatial structure using different Gray scales (Gray scales) or Pseudo colors (Pseudo colors). The blood vessel reconstructed by the method has smooth surface and strong spatial stereoscopic impression, can display the surface form of the aneurysm and the spatial relation of the surrounding structure in a three-dimensional way, and can realize the observation of the position of the aneurysm, the form of the aneurysm body and the aneurysm neck, the form of the arterial interlayer, the anatomical relation, the tearing condition and the form of the intima and the like of the blood vessel at any angle through rotating the reconstructed image at any angle. However, the blood vessels obtained by this method are rough in display and various detailed features of the blood vessels cannot be clearly displayed, so that the requirement of practical use cannot be met frequently.
Maximum Intensity Projection (MIP) is performed by compressing the volumetric data and then projecting the brightest (maximum intensity) structures onto a two-dimensional plane. Because the method adopts the superposition projection, the generated image can not reflect the depth relation of the structure, so that the blood vessel image reconstructed by the method is difficult to identify the true and false lumen difference of the blood vessel aortic dissection, and the detailed characteristics of thrombus formation, torn intima flap and the like in the lumen can not be clearly observed.
Multi-plane reconstruction (MPR) is a two-dimensional image processing method of superimposing all axial position images within a scanning range to perform post-processing to obtain any one of a coronal, sagittal, transverse and oblique planes of a human tissue organ (for example, a blood vessel in the present disclosure), by which a new tomographic image can be arbitrarily generated without repeated scanning. The MPR has the advantages of simplicity, rapidness and the like, and the characteristics of aortic aneurysm, interlayer affected range, inner membrane valve details, true and false cavity size, intracavity thrombus, tube wall calcification displacement and the like of a blood vessel can be clearly displayed by utilizing a reconstructed blood vessel image, so that the MPR also has great value in the aspect of judging aortic arch blood vessel affected. On one hand, the multi-plane reconstruction technology can be used for rapidly reconstructing images of coronary positions and vector positions of blood vessels by directly overlapping axial position two-dimensional images (namely, two-dimensional images of axial positions) of the blood vessels, so that professionals can observe blood vessels and focus positions of patients in a three-view mode. On the other hand, the multi-plane reconstruction can also be used for reconstructing a two-dimensional plane image of the blood vessel at any angle inclined position based on the axial position two-dimensional image of the blood vessel, so as to provide more observation flexibility for a user, but the method is very complex to implement. Both of these methods of multiplanar reconstruction involve the reconstruction process from a two-dimensional image to a two-dimensional image, and are therefore susceptible to the limitations of unknown (non-visualized) spatial structures, making it difficult for a user to accurately determine the desired viewing angle and midpoint position based thereon, and thus to obtain an optimal blood vessel sectional image.
To at least partially solve one or more of the above problems and other potential problems, example embodiments of the present disclosure propose an easily implemented method for acquiring an image of a target sectional plane of a blood vessel, which fully utilizes the advantage that MPR can arbitrarily generate a new tomographic image, and can also automatically generate an optimal viewing plane image of the sectional plane of the blood vessel by providing a midpoint of the target sectional plane of the blood vessel and a tangent of a centerline of the blood vessel on the midpoint using a three-dimensional mesh model of the blood vessel. The method disclosed by the invention realizes the presentation process from the two-dimensional data to the three-dimensional model and then to the two-dimensional image, thereby directly avoiding the limitation of the reconstruction process from the two-dimensional image to the two-dimensional image in the original MPR method. Specifically, the method comprises the following steps: generating a three-dimensional mesh model of a blood vessel based on a plurality of successive axial tomographic images of the blood vessel so as to determine a centerline of the blood vessel on the three-dimensional mesh model; establishing an initial tangent plane coordinate system based on the plurality of continuous axial tomography images; identifying a midpoint of a target tangent plane of the vessel on the midline to determine a tangent vector of the midline at the midpoint; transforming the initial tangent plane coordinate system into a target tangent plane coordinate system based on the tangent vector; and generating a tomographic image of the target tangent plane based on the target tangent plane coordinate system and the plurality of continuous axial tomographic images by using multi-plane reconstruction. In this way, it is possible to provide an accurate and clear sectional image of an arbitrary target position of a blood vessel without requiring the spatial imagination and expertise of the user.
Fig. 1 shows a schematic diagram of a system 100 for implementing a method for acquiring a target sectional image of a blood vessel according to an embodiment of the present invention. As shown in fig. 1, system 100 includes a computing device 110, a network 120, and a tomography device 130. The computing device 110 and the tomography device 130 may interact data via a network 120 (e.g., the internet). In the present disclosure, the tomography apparatus 130 may provide a tomography service to a blood vessel, for example, so as to obtain an axial (or axial) tomographic image of the blood vessel. It should be understood that the tomographic image is a two-dimensional image, and the displayed content is an image of a certain section of the body, and thus in the present disclosure, the tomographic image of the blood vessel is an image of a section of the blood vessel. The image obtained by CT tomography is a tomographic image of an axial plane, and tomographic images of other angles can be obtained by a multi-plane recombination technology. The computing device 110 may communicate with the tomography device 130 via the network 120 to enable acquisition of axial tomographic images. The computing device 110 may include at least one processor 112 and at least one memory 114 coupled to the at least one processor 112, the memory 114 having stored therein instructions 116 executable by the at least one processor 112, the instructions 116 when executed by the at least one processor 112 performing the method 200 as described below. Note that herein, the computing device 110 may be part of the tomography device 130 or may be separate from the tomography device 130. The specific structure of the computing device 110 or the tomography device 130 may be described below, for example, in conjunction with fig. 9.
Fig. 2 shows a flow chart of a method 200 for acquiring a target sectional image of a blood vessel according to an embodiment of the present disclosure. The method 200 may be performed by the computing device 110 as shown in FIG. 1, or may be performed at the electronic device 900 shown in FIG. 9. It should be understood that method 200 may also include additional blocks not shown and/or may omit blocks shown, as the scope of the present disclosure is not limited in this respect.
In step 202, the computing device 110 generates a three-dimensional mesh model of the blood vessel based on a plurality of successive axial tomographic images of the blood vessel to determine a centerline of the blood vessel on the three-dimensional mesh model.
Generating a three-dimensional mesh model of the blood vessel based on a plurality of successive axial tomographic images of the blood vessel can be realized by means of image segmentation. Image segmentation refers to dividing an image into several regions and extracting an anatomical structure or a region of interest (in this disclosure, a blood vessel region) in the image. In some embodiments of the present disclosure, image segmentation based on a depth learning model may be utilized to extract vessel regions from each of a plurality of consecutive axial tomographic images, and then generate a three-dimensional mesh model of the vessel based on these vessel regions. The deep learning model can be a convolution neural network model and can also be a three-dimensional Unet network model.
Thus, in some embodiments, generating a three-dimensional mesh model of a blood vessel based on a plurality of consecutive axial tomographic images of the blood vessel may include segmenting a blood vessel region from each of the plurality of consecutive axial tomographic images based on a trained depth learning model trained based on a plurality of consecutive sample axial tomographic images labeled with the blood vessel region; and generating a three-dimensional mesh model of the blood vessel based on the blood vessel region.
In some embodiments, the vessel includes a main vessel and a plurality of branch vessels, and generating the centerline of the vessel on the three-dimensional mesh model includes generating a first centerline of the main vessel and a plurality of second centerlines of the plurality of branch vessels on the three-dimensional mesh model. The first neutral line and each second neutral line may be implemented by various methods, and may be neutral line generation methods known in the art or neutral line generation methods to be developed in the future.
At step 204, the computing device 110 establishes an initial tangent coordinate system based on the plurality of consecutive axial tomographic images. In the present disclosure, the initial tangential plane coordinate system is a three-dimensional space coordinate system established based on the set of axial tomographic images, and includes three axes of a horizontal axis, a vertical axis and a vertical axis, such as the X-axis, the Y-axis and the Z-axis of the initial tangential plane coordinate system shown in fig. 4. Since it is relatively simple to establish the initial tangent plane coordinate system based on the axial tomographic image, the initial tangent plane coordinate system can serve as a transition for accurately and quickly determining the target tangent plane coordinate system. Step 204 is described in further detail below in conjunction with fig. 3 and 4.
At step 206, the computing device 110 identifies a midpoint of the target tangent plane of the vessel on the centerline to determine a tangent vector of the centerline on the midpoint. For example, in the example shown in FIG. 5, the midpoint of the target slice is P0The determined tangent vector is N.
It will be appreciated that any selected point on the midline is the midpoint of a tangent plane to the vessel. Thus, in the present disclosure, a desired viewing site for a vessel may be determined by identifying the midpoint of the target tangent plane directly on the midline of the vessel.
In addition, in the present disclosure, a tangent vector of the midline of the blood vessel at the identified midpoint can be regarded as a direction from the focal point of the observation camera to the lens position of the camera, i.e., an optimal observation angle, so that the optimal observation angle can be automatically determined without the need for an observer to select the observation angle with naked eyes in the disclosure, thereby facilitating observation of the morphology of the blood vessel and the characteristics of the lesion.
That is, in the present disclosure, by determining a centerline of a blood vessel on a three-dimensional mesh model of the blood vessel, a desired observation point can be directly selected on the centerline to restrict the observation point to a preferred range, thereby contributing to more accurately determining the observation angle of the blood vessel.
In some embodiments, determining a tangent vector to the midline at the midpoint may comprise the sub-steps of: in the midline (e.g., midline S is shown in FIG. 5 as including midpoint P0A portion of (c)) an upper midpoint (e.g., point P in fig. 50) Respectively, take the first point (such as point P in FIG. 5)1) And a second point (e.g., point P in FIG. 5)2) (ii) a Determining a first vector (e.g., P) from the second point to the first point2P1) A second vector from the second point to the midpoint (e.g., P)2P0) And a third vector (e.g., P) from the midpoint to the first point0P1) (ii) a And determining a tangent vector (e.g., N in fig. 5) based on the first vector, the second vector, and the third vector. For example, by calculating a first vector P2P1Second vector P2P0And a third vector P0P1As the mean vector of the vessel's midline at midpoint P0The tangent vector N.
At step 208, the computing device 110 transforms the initial tangent plane coordinate system to the target tangent plane coordinate system based on the tangent vectors determined at step 206.
In some embodiments, the initial tangent plane coordinate system is transformed such that the longitudinal axis of the transformed target tangent plane coordinate system coincides with the tangent vector determined in step 206. For example, in some embodiments, the initial tangential plane coordinate system may be rotated and translated based on the tangential vector determined in step 206 such that the vertical axis of the transformed initial tangential plane coordinate system is parallel to the tangential vector and the origin of the transformed initial tangential plane coordinate system coincides with the midpoint identified in step 206 to obtain the desired target tangential plane coordinate system, i.e., the initial tangential plane coordinate system transformed in this way corresponds to the target tangential plane coordinate system. This will be described in further detail below in conjunction with fig. 6 and 7.
In step 210, the computing device 110 generates a tomographic image of the target slice using multi-plane reconstruction based on the target slice coordinate system and the plurality of consecutive axial tomographic images.
It should be appreciated that the plane defined by the horizontal and vertical axes of the target slice coordinate system in the present disclosure is coplanar with the target slice, and thus the tomographic image of the target slice may be determined based in part on the target slice coordinate system.
Further, in the present disclosure, the sequential stacking of these axial tomographic images in order can constitute a three-dimensional image data set, which can be regarded as a voxel set. In addition, the coordinate information of the target tangent plane can be obtained through a multi-plane reconstruction technology, the coordinate information has corresponding voxel points in the three-dimensional image data set, and the voxel points are recombined to generate the sectional image of the target tangent plane. As shown in fig. 8, an illustrative diagram is shown for converting an initial tangent plane coordinate system to a target tangent plane coordinate system and then generating a tomographic image of the target tangent plane using multi-plane reconstruction. Fig. 8 can help to more intuitively recognize the generation process of the tomographic image of the target slice.
In some embodiments, after the tomographic image of the target tangent plane is generated, gaussian smoothing processing (also referred to as gaussian blurring processing) may be further performed on the tomographic image to obtain a smoother tomographic image of the target tangent plane. Gaussian smoothing is typically used to reduce image noise and to reduce the level of detail. From the mathematical point of view, the gaussian blurring process of the image is to convolute the image with a normal distribution. Gaussian blur is a low pass filter for an image, since the fourier transform of a gaussian function is another gaussian function. Therefore, in the present disclosure, by performing gaussian smoothing processing on the generated tomographic image, a smoother target sectional tomographic image can be obtained, thereby contributing more to the positioning of the subsequent lesion region.
In the present disclosure, after the tomographic image of the target sectional plane is obtained, information such as the diameter and the circumference of the blood vessel on the target sectional plane may be determined based on the tomographic image and displayed on the tomographic image. Based on such diameter and circumference information, vessel morphology and lesion characteristics can be advantageously determined.
FIG. 3 shows a flow diagram of a method 300 for establishing an initial tangent coordinate system based on a plurality of consecutive axial tomographic images in accordance with an embodiment of the present disclosure. The method 300 may be performed by the computing device 110 as shown in FIG. 1, or may be performed at the electronic device 900 shown in FIG. 9. It should be understood that method 300 may also include additional blocks not shown and/or may omit blocks shown, as the scope of the disclosure is not limited in this respect.
In step 302, a center point of a three-dimensional image data set, which is formed by superimposing a plurality of consecutive axial tomographic images, is determined to serve as an origin of an initial tangential coordinate system.
As mentioned before, the tangent vector of the midline of the blood vessel at the identified midpoint is the optimal viewing angle, so determining the center point of the three-dimensional image data set as the origin of the initial tangent plane coordinate system in the present disclosure will help to more quickly determine the target tangent plane coordinate system associated with this optimal viewing angle.
Specifically, step 302 may include determining an origin, a lateral extension, a longitudinal extension, and a vertical extension of the three-dimensional image data set, and determining an origin of the initial tangent coordinate system based on the origin, the lateral extension, the longitudinal extension, and the vertical extension of the three-dimensional image data set.
For example, in some embodiments, the location of the origin of the initial tangent plane coordinate system may be calculated based on the following equation (1).
O[i]＝Origin[i]+0.5*(Extent[2*i]+Extent[2*i+1])*Spacing[i] (1)
Wherein i is 0,1, 2; O0-O2 may represent an abscissa, an ordinate, and an ordinate of an origin of the initial tangent plane coordinate system in a coordinate system of the three-dimensional image data set, respectively; origin [0] -Origin [2] denotes the abscissa, ordinate and ordinate of the Origin of the three-dimensional image dataset in the coordinate system of the three-dimensional image dataset, e.g. Origin [0] to Origin [2] are all 0 in the example shown in fig. 4; extent [0] and Extent [1] represent the lateral Extent of the three-dimensional image data set along the negative and positive half axes, respectively, of its coordinate system's horizontal axis, so the Extent from Extent [0] to Extent [1] can represent the lateral Extent of the three-dimensional image data set, both in voxels, where Extent [0] is smaller than Extent [1], e.g., Extent [0] is 0 in the example shown in FIG. 4; extent [2] and Extent [3] represent the longitudinal extension of the three-dimensional image data set along the negative and positive half axes, respectively, of its coordinate system's longitudinal axis, so that the extension from Extent [2] to Extent [3] can represent the longitudinal extension of the three-dimensional image data set, both in voxels, where Extent [2] is smaller than Extent [3], e.g. Extent [2] is 0 in the example shown in FIG. 4; extend [4] and extend [5] represent the vertical extension distance of the three-dimensional image data set along the negative half axis and the positive half axis of its coordinate system vertical axis, respectively, so that the extension from extend [4] to extend [5] can represent the vertical extension of the three-dimensional image data set, both in voxels, where extend [4] is smaller than extend [5], e.g. extend [4] is 0 in the example shown in fig. 4; spacing [0] -Spacing [1] may represent the horizontal, vertical and vertical dimensions of the voxel, respectively.
It should be appreciated that a Voxel (Voxel) is an abbreviation of a volumetric Pixel (Volume Pixel), which is conceptually analogous to a Pixel, the smallest unit of a two-dimensional space. Pixels are usually used in image data of two-dimensional computer images, and volume pixels are three-dimensional equivalent terms of pixels, which are the minimum units of digital data in three-dimensional space segmentation, and are usually applied in the fields of three-dimensional imaging, scientific data, medical images, and the like.
At step 304, based on the origin determined at step 302, an initial tangential plane coordinate system is established in which a horizontal axis (X axis shown in fig. 4) and a vertical axis (Y axis shown in fig. 4) of the initial tangential plane coordinate system are established on a plane (base plane shown in fig. 4) parallel to a plane on which each axial tomographic image is located, and a vertical axis (Z axis shown in fig. 4) of the initial tangential plane coordinate system is perpendicular to the horizontal axis and the vertical axis.
By adopting the above means, the present disclosure facilitates accurate and fast establishment of a subsequent target tangent plane coordinate system by establishing an initial tangent plane coordinate system as a transition.
Fig. 7 shows a flow diagram of a method 700 for rotating and translating an initial tangent plane coordinate system based on tangent vectors. The method 700 may be performed by the computing device 110 as shown in FIG. 1, or may be performed at the electronic device 900 shown in FIG. 9. It should be understood that method 700 may also include additional blocks not shown and/or may omit blocks shown, as the scope of the present disclosure is not limited in this respect.
At step 702, the tangent vector (i.e., the tangent vector determined at step 206) is projected onto a first plane (e.g., plane OXZ as shown in fig. 6 and 8) defined by a horizontal axis (e.g., the X-axis as shown in fig. 6 and 8) and a vertical axis (e.g., the Z-axis as shown in fig. 6 and 8) of an initial tangent coordinate system (e.g., coordinate system xyz as shown in fig. 6 and 8) to determine a second tangent vector.
At step 704, a first angle between the second tangent vector and a vertical axis (e.g., the Z axis as shown in fig. 6 and 8) of the initial tangent plane coordinate system is determined.
In some embodiments, the first included angle may be calculated by the following equation (2):
wherein alpha represents a first angle,
a second tangential vector is represented, which is,
representing the vertical axis of the initial tangent plane coordinate system.
At step 706, the tangent vectors are projected onto a second plane defined by the vertical axis and the vertical axis of the initial tangent coordinate system to determine a third tangent vector.
At step 708, a second angle between the third tangent vector and the vertical axis is determined.
In some embodiments, the second angle can be calculated by the following equation (3):
wherein beta represents a second angle of inclusion,
a third tangential vector is represented, which is,
representing the vertical axis of the initial tangent plane coordinate system.
At step 710, the initial tangential coordinate system is rotated counterclockwise about its longitudinal axis by the first angle determined at step 704 to determine a second coordinate system.
In some embodiments, the rotation of the initial tangent coordinate system counterclockwise about its longitudinal axis by the first angle may be achieved based on the following rotation matrix (4).
Wherein R isYRepresenting the rotation matrix and alpha the first angle.
At step 712, the second coordinate system is rotated counterclockwise about the horizontal axis of the initial tangential plane coordinate system by the second angle determined at step 708 to determine a third coordinate system.
For example, a counterclockwise rotation of the second coordinate system by the second angle around the horizontal axis of the initial tangent plane coordinate system may be achieved based on the following rotation matrix (5).
Wherein R isXDenotes a rotation matrix and β denotes a second angle.
At step 714, the origin of the third coordinate system is translated to the midpoint (i.e., the midpoint identified at step 206, here denoted as O '), thereby determining the target tangent plane coordinate system (e.g., the coordinate system O ' X ' Y ' Z ' shown in fig. 6 and 8).
By adopting the means, the method can quickly and accurately convert the initial tangent plane coordinate system into the target tangent plane coordinate system.
FIG. 9 illustrates a schematic block diagram of an example electronic device 900 that can be used to implement embodiments of the present disclosure. For example, computing device 110 as shown in fig. 1 may be implemented by electronic device 900. As shown, electronic device 900 includes a Central Processing Unit (CPU)901 that can perform various appropriate actions and processes in accordance with computer program instructions stored in a Read Only Memory (ROM)902 or loaded from a storage unit 908 into a Random Access Memory (RAM) 903. In the random access memory 903, various programs and data required for the operation of the electronic device 900 can also be stored. The central processing unit 901, the read only memory 902 and the random access memory 903 are connected to each other by a bus 904. An input/output (I/O) interface 905 is also connected to bus 904.
A number of components in the electronic device 900 are connected to the input/output interface 905, including: an input unit 906 such as a keyboard, a mouse, a microphone, and the like; an output unit 907 such as various types of displays, speakers, and the like; a storage unit 908 such as a magnetic disk, optical disk, or the like; and a communication unit 909 such as a network card, a modem, a wireless communication transceiver, and the like. The communication unit 909 allows the device 900 to exchange information/data with other devices through a computer network such as the internet and/or various telecommunication networks.
The various processes and processes described above, such as methods 200, 300, and 700, may be performed by central processing unit 901. For example, in some embodiments, methods 200, 300, and 700 may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 908. In some embodiments, some or all of the computer program may be loaded and/or installed onto device 900 via read only memory 902 and/or communications unit 909. When the computer program is loaded into the random access memory 903 and executed by the central processing unit 901, one or more of the actions of the methods 200 and 300 described above may be performed. The present disclosure relates to methods, apparatuses, systems, electronic devices, computer-readable storage media and/or computer program products. The computer program product may include computer-readable program instructions for performing various aspects of the present disclosure.
The computer readable storage medium may be a tangible device that can hold and store the instructions for use by the instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic memory device, a magnetic memory device, an optical memory device, an electromagnetic memory device, a semiconductor memory device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a Static Random Access Memory (SRAM), a portable compact disc read-only memory (CD-ROM), a Digital Versatile Disc (DVD), a memory stick, a floppy disk, a mechanical coding device, such as punch cards or in-groove projection structures having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media as used herein is not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., optical pulses through a fiber optic cable), or electrical signals transmitted through electrical wires.
The computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to a respective computing/processing device, or to an external computer or external storage device via a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers and/or edge computing devices. The network adapter card or network interface in each computing/processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in the respective computing/processing device.
The computer program instructions for carrying out operations of the present disclosure may be assembler instructions, Instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, the electronic circuitry that can execute the computer-readable program instructions implements aspects of the present disclosure by utilizing the state information of the computer-readable program instructions to personalize the electronic circuitry, such as a programmable logic circuit, a Field Programmable Gate Array (FPGA), or a Programmable Logic Array (PLA).
Various aspects of the present disclosure are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.
These computer-readable program instructions may be provided to a processing unit of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processing unit of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer-readable program instructions may also be stored in a computer-readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer-readable medium storing the instructions comprises an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.
The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
Having described embodiments of the present disclosure, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terms used herein were chosen in order to best explain the principles of the embodiments, the practical application, or technical improvements to the techniques in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (10)
1. A method for obtaining a target sectional image of a blood vessel, comprising:
generating a three-dimensional mesh model of a blood vessel based on a plurality of successive axial tomographic images of the blood vessel so as to determine a centerline of the blood vessel on the three-dimensional mesh model;
establishing an initial tangent plane coordinate system based on the plurality of continuous axial tomography images;
identifying a midpoint of a target tangent plane of the vessel on the midline to determine a tangent vector of the midline at the midpoint;
transforming the initial tangent plane coordinate system into a target tangent plane coordinate system based on the tangent vector; and
generating a tomographic image of the target tangent plane using a multi-plane reconstruction based on the target tangent plane coordinate system and the plurality of consecutive axial tomographic images.
2. The method of claim 1, wherein establishing an initial tangent plane coordinate system based on the plurality of consecutive axial tomographic images comprises:
determining a central point of a three-dimensional image data set as an origin of the initial tangent plane coordinate system, wherein the three-dimensional image data set is formed by overlapping the plurality of continuous axial tomography images; and
establishing the initial tangential plane coordinate system based on the determined origin, wherein a horizontal axis and a vertical axis of the initial tangential plane coordinate system are established on a plane parallel to a plane on which each axial tomographic image is located, and a vertical axis of the initial tangential plane coordinate system is perpendicular to the horizontal axis and the vertical axis.
3. The method of claim 2, determining a center point of a three-dimensional image dataset as an origin of the initial tangential coordinate system comprising:
determining an origin, a lateral extension, a longitudinal extension and a vertical extension of the three-dimensional image dataset; and
determining an origin of the initial tangent plane coordinate system based on the origin, the lateral extension, the longitudinal extension, and the vertical extension of the three-dimensional image dataset.
4. The method of claim 1, wherein determining a tangent vector of the midline at the midpoint comprises:
respectively taking a first point and a second point at the left side and the right side of the middle point on the middle line;
determining a first vector from the second point to the first point, a second vector from the second point to the midpoint, and a third vector from the midpoint to the first point; and
determining the tangent vector based on the first vector, the second vector, and the third vector.
5. The method of claim 1, wherein transforming the initial tangent plane coordinate system to a target tangent plane coordinate system based on the tangent vector comprises:
rotating and translating the initial tangent plane coordinate system based on the tangent vector such that a vertical axis of a transformed initial tangent plane coordinate system is parallel to the tangent vector and an origin of the transformed initial tangent plane coordinate system coincides with the midpoint, the transformed initial tangent plane coordinate system corresponding to the target tangent plane coordinate system.
6. The method of claim 5, wherein rotating and translating the initial tangent plane coordinate system based on the tangent vector such that a vertical axis of a transformed initial tangent plane coordinate system is parallel to the tangent vector and an origin of the transformed initial tangent plane coordinate system coincides with the midpoint comprises:
projecting the tangent vector on a first plane to determine a second tangent vector, the first plane being defined by a horizontal axis and a vertical axis of the initial tangent plane coordinate system;
determining a first included angle between the second tangent vector and the vertical axis;
projecting the tangent vector on a second plane to determine a third tangent vector, the second plane being defined by a longitudinal axis of the initial tangent plane coordinate system and the vertical axis;
determining a second included angle between the third tangent vector and the vertical axis;
rotating the initial tangent plane coordinate system counterclockwise around the longitudinal axis by the first included angle so as to determine a second coordinate system;
rotating the second coordinate system counterclockwise around the transverse axis by the second included angle so as to determine a third coordinate system; and
translating an origin of the third coordinate system to the midpoint.
7. The method of claim 1, wherein the blood vessel comprises a main artery blood vessel and a plurality of branch blood vessels, and generating a centerline of the blood vessel on the three-dimensional mesh model comprises generating a first centerline of the main artery blood vessel and a plurality of second centerlines of the plurality of branch blood vessels on the three-dimensional mesh model.
8. The method of claim 1, wherein generating a three-dimensional mesh model of a blood vessel based on a plurality of sequential axial tomographic images of the blood vessel comprises:
segmenting a blood vessel region from each of the plurality of continuous axial tomographic images based on a trained deep learning model, the deep learning model including a convolutional neural network model or a three-dimensional Unet network model, and the trained deep learning model being trained based on a plurality of continuous sample axial tomographic images labeled with the blood vessel region; and
generating a three-dimensional mesh model of the blood vessel based on the blood vessel region.
9. A computing device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor;
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-8.
10. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111106508.6A CN113822923A (en) | 2021-09-22 | 2021-09-22 | Method, apparatus and medium for acquiring target sectional image of blood vessel |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111106508.6A CN113822923A (en) | 2021-09-22 | 2021-09-22 | Method, apparatus and medium for acquiring target sectional image of blood vessel |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113822923A true CN113822923A (en) | 2021-12-21 |
Family
ID=78915033
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111106508.6A Pending CN113822923A (en) | 2021-09-22 | 2021-09-22 | Method, apparatus and medium for acquiring target sectional image of blood vessel |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113822923A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114897780A (en) * | 2022-04-12 | 2022-08-12 | 南通大学 | MIP sequence-based mesenteric artery blood vessel reconstruction method |
| CN116152437A (en) * | 2023-02-13 | 2023-05-23 | 北京医智影科技有限公司 | Applicator reconstruction method, apparatus, electronic device, and computer-readable storage medium |
| CN117274557A (en) * | 2023-11-20 | 2023-12-22 | 首都师范大学 | Data enhancement method and device for three-dimensional image, electronic equipment and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110021053A (en) * | 2019-04-16 | 2019-07-16 | 河北医科大学第二医院 | A kind of image position method, device, storage medium and equipment based on coordinate conversion |
| CN112150600A (en) * | 2020-09-24 | 2020-12-29 | 上海联影医疗科技股份有限公司 | Volume reconstruction image generation method, device and system and storage medium |
-
2021
- 2021-09-22 CN CN202111106508.6A patent/CN113822923A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110021053A (en) * | 2019-04-16 | 2019-07-16 | 河北医科大学第二医院 | A kind of image position method, device, storage medium and equipment based on coordinate conversion |
| CN112150600A (en) * | 2020-09-24 | 2020-12-29 | 上海联影医疗科技股份有限公司 | Volume reconstruction image generation method, device and system and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 欧阳自鹏: "冠状动脉立体定量评估关键技术研究", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114897780A (en) * | 2022-04-12 | 2022-08-12 | 南通大学 | MIP sequence-based mesenteric artery blood vessel reconstruction method |
| CN116152437A (en) * | 2023-02-13 | 2023-05-23 | 北京医智影科技有限公司 | Applicator reconstruction method, apparatus, electronic device, and computer-readable storage medium |
| CN116152437B (en) * | 2023-02-13 | 2024-02-02 | 中国医学科学院北京协和医院 | Applicator reconstruction method, apparatus, electronic device, and computer-readable storage medium |
| CN117274557A (en) * | 2023-11-20 | 2023-12-22 | 首都师范大学 | Data enhancement method and device for three-dimensional image, electronic equipment and storage medium |
| CN117274557B (en) * | 2023-11-20 | 2024-03-26 | 首都师范大学 | Data enhancement method and device for three-dimensional image, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10867436B2 (en) | Systems and methods for reconstruction of 3D anatomical images from 2D anatomical images | |
| CN113822923A (en) | Method, apparatus and medium for acquiring target sectional image of blood vessel | |
| CN109409503B (en) | Neural network training method, image conversion method, device, equipment and medium | |
| Tang et al. | Semiautomatic carotid lumen segmentation for quantification of lumen geometry in multispectral MRI | |
| US7339586B2 (en) | Method and system for mesh-to-image registration using raycasting | |
| CN111798451A (en) | 3D guide wire tracking method and device based on blood vessel 3D/2D matching | |
| CN111476791B (en) | Image processing method, image processing apparatus, and non-transitory computer readable medium | |
| CN113160189A (en) | Blood vessel center line extraction method, device, equipment and storage medium | |
| CN111369675B (en) | Three-dimensional visual model reconstruction method and device based on lung nodule pleural projection | |
| CN112419484A (en) | Three-dimensional blood vessel synthesis method and system, coronary artery analysis system and storage medium | |
| CN112669247A (en) | Priori guidance type network for multitask medical image synthesis | |
| US8077954B2 (en) | System and method for image processing | |
| Wang et al. | Liver surface reconstruction for image guided surgery | |
| CN117529273A (en) | System and method for reconstructing 3D images from ultrasound images and camera images | |
| CN113888566B (en) | Target contour curve determination method and device, electronic equipment and storage medium | |
| CN114897756A (en) | Model training method, medical image fusion method, device, equipment and medium | |
| US11189030B2 (en) | Method and device for determining liver segments in a medical image | |
| WO2021030995A1 (en) | Inferior vena cava image analysis method and product based on vrds ai | |
| CN111627023B (en) | Method and device for generating coronary artery projection image and computer readable medium | |
| CN109035353B (en) | Blood vessel straightening curved surface recombination method based on CT image multi-plane reconstruction | |
| CN116993805A (en) | Intraoperative residual organ volume estimation system oriented to operation planning assistance | |
| CN115147360B (en) | Plaque segmentation method and device, electronic equipment and readable storage medium | |
| CN112884879B (en) | Method for providing a two-dimensional unfolded image of at least one tubular structure | |
| CN114399527A (en) | Method and device for unsupervised depth and motion estimation of monocular endoscope | |
| CN113902912A (en) | CBCT image processing method, neural network system creation method, and device |
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 |