CN115187598B - Method, apparatus, system, device and medium for processing angiography image - Google Patents
Method, apparatus, system, device and medium for processing angiography image Download PDFInfo
- Publication number
- CN115187598B CN115187598B CN202211098848.3A CN202211098848A CN115187598B CN 115187598 B CN115187598 B CN 115187598B CN 202211098848 A CN202211098848 A CN 202211098848A CN 115187598 B CN115187598 B CN 115187598B
- Authority
- CN
- China
- Prior art keywords
- image
- contour
- blood vessel
- target blood
- angiographic
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
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
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration by the use of local operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- 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
-
- 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 discloses a method, a device, a system, equipment and a medium for processing an angiography image, and belongs to the field of image processing. The method comprises the following steps: acquiring an angiographic image; extracting the central line of a target blood vessel in an angiography image; filtering the angiography image under the guidance of the central line to obtain an image filtering result; and performing first image segmentation based on the image filtering result to obtain a first contour of the target blood vessel. The above method alleviates the bulging phenomenon on the contour of the blood vessel.
Description
Technical Field
The present application relates to the field of image processing, and in particular, to a method, an apparatus, a system, a device, and a medium for processing an angiography image.
Background
Angiography is a technique for assisting in examining blood vessels, and an angiographic image is obtained by X-ray irradiation after a developer is injected into a blood vessel. Since the X-ray cannot penetrate the developer, the obtained angiographic image can accurately reflect the position and degree of the vascular lesion. In the related art, an angiographic image is generally generated by a DSA (Digital Subtraction Angiography) technique, which is a gold standard currently used for displaying coronary arteries, and shows a refined vascular structure.
In the related art, in order to segment a target blood vessel from an angiographic image, pixel points with pixel values larger than a threshold are determined as pixel points of the target blood vessel, so as to extract the contour of the target blood vessel.
However, the contour of the target blood vessel extracted by the related art may have a bulge phenomenon at the bifurcation of the blood vessel, the junction of multiple bifurcations may contain a large number of pixel points whose pixel values are greater than the threshold, and the bulge phenomenon is an obvious inaccurate contour segmentation phenomenon.
Disclosure of Invention
The application provides a method, a device, a system, equipment and a medium for processing an angiography image, which can relieve the bulge phenomenon on the outline of a blood vessel.
According to an aspect of the present application, there is provided a method of processing an angiographic image, the method comprising:
acquiring an angiographic image;
extracting the central line of a target blood vessel in an angiography image;
filtering the angiography image under the guidance of the central line to obtain an image filtering result;
and performing first image segmentation based on the image filtering result to obtain a first contour of the target blood vessel.
According to an aspect of the present application, there is provided an apparatus for processing an angiographic image, the apparatus comprising:
an acquisition module for acquiring an angiographic image;
the extraction module is used for extracting the central line of a target blood vessel in the angiography image;
the filtering module is used for carrying out filtering operation on the angiography image under the guidance of the central line to obtain an image filtering result;
and the segmentation module is used for carrying out first image segmentation based on the image filtering result to obtain a first contour of the target blood vessel.
According to one aspect of the application, a system for processing an angiography image is provided, and comprises a shooting device of the angiography image, a server and a viewing terminal of the angiography image;
the shooting equipment is used for shooting the angiography image and sending the angiography image to the server;
the server is used for executing the processing method of the angiography image and sending the processed angiography image to the viewing terminal;
and the viewing terminal is used for displaying the processed angiography image.
According to one aspect of the application, a system for processing an angiographic image is provided, the system comprising a device for capturing the angiographic image and a device for processing the angiographic image;
a photographing apparatus for photographing an angiographic image and transmitting the angiographic image to a processing apparatus;
a processing device for performing the processing method of the angiographic image as above, and displaying the processed angiographic image.
According to another aspect of the present application, there is provided a computer device storing a computer program which is loaded and executed by a processor to implement the processing method of an angiographic image as above.
According to another aspect of the present application, there is provided a computer readable storage medium storing a computer program, which is loaded and executed by a processor to implement the processing method of an angiographic image as above.
According to another aspect of the application, a computer program product or computer program is provided, comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to cause the computer device to execute the processing method of the angiographic image.
The beneficial effects brought by the technical scheme provided by the embodiment of the application at least comprise:
the angiography image is filtered under the guidance of the central line of the target blood vessel, and the first image segmentation is carried out on the filtering result to obtain the first contour of the target blood vessel, so that the accuracy of the contour of the blood vessel obtained by segmentation is improved. In the above process, the center line of the target blood vessel participates in the process of extracting the contour of the target blood vessel, and the center line plays a role of constraining the contour of the target blood vessel as the venation of the target blood vessel.
In the method for extracting the contour based on the pixel value threshold value provided by the related art, the bulge phenomenon is most likely to exist at the bifurcation part of the target blood vessel, and the central line used in the method has a constraint effect on the contour of the target blood vessel, so that the bulge contracts towards the center due to the constraint effect, the volume of the bulge is removed or reduced, and the bulge phenomenon is relieved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the description below are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
FIG. 1 is a schematic diagram of an angiographic image processing system provided by an exemplary embodiment of the present application;
FIG. 2 is a schematic diagram of an angiographic image processing system provided by another exemplary embodiment of the present application;
FIG. 3 is a schematic diagram of a processing framework for angiographic images provided by an exemplary embodiment of the present application;
FIG. 4 is a flow chart of a method of processing an angiographic image according to an exemplary embodiment of the present application;
FIG. 5 is a flow chart of a method of processing an angiographic image according to another exemplary embodiment of the present application;
FIG. 6 is a schematic illustration of an initial angiographic image provided by an exemplary embodiment of the present application;
FIG. 7 is a schematic illustration of a first contour of a target vessel provided by an exemplary embodiment of the present application;
FIG. 8 is a schematic illustration of a centerline of a target vessel provided by an exemplary embodiment of the present application;
FIG. 9 is a flow chart of a second contour of a target vessel provided by an exemplary embodiment of the present application;
FIG. 10 is a schematic diagram of an angiographic image predicted by a deep learning network according to an exemplary embodiment of the present application;
FIG. 11 is a schematic diagram of an angiographic image based on a pixel value thresholding segmentation as provided in an exemplary embodiment of the present application;
FIG. 12 is a schematic illustration of an offset corrected angiographic image provided by an exemplary embodiment of the present application;
FIG. 13 is a flow chart of a method of processing angiographic images provided by yet another exemplary embodiment of the present application;
FIG. 14 is a schematic diagram comparing a second profile to a third profile provided by an exemplary embodiment of the present application;
fig. 15 is a block diagram of a configuration of an apparatus for processing an angiographic image according to an exemplary embodiment of the present application;
fig. 16 shows a block diagram of a computer device provided in an exemplary embodiment of the present application.
Detailed Description
To make the objects, technical solutions and advantages of the present application more clear, embodiments of the present application will be described in further detail below with reference to the accompanying drawings.
Fig. 1 shows a schematic diagram of a system for processing angiographic images according to an exemplary embodiment of the present application. The system comprises a capturing device 110 of an angiographic image, a server 120 and a viewing terminal 130 of said angiographic image. Optionally, the capturing device 110 is a DSA device, and the DSA device is configured to subtract the non-contrast blood vessel image and the contrast blood vessel image to obtain an angiography image with the structure other than the blood vessel removed. The photographing apparatus 110 also transmits the angiographic image to the server 120. The server 120 is configured to process the angiographic image and to transmit the processed angiographic image to the viewing terminal 130. The viewing terminal 130 is used to display the processed angiographic image. Optionally, the viewing terminal 130 is a terminal used by a doctor; optionally, the viewing terminal 130 is a printing terminal for angiographic images.
Optionally, the server includes at least one of a server, a plurality of servers, a cloud computing platform, and a virtualization center. Optionally, the device type of the viewing terminal includes: at least one of a laptop portable computer, a desktop computer, a printer, a smartphone, a smartwatch, a vehicle terminal, a wearable device, a smart television, a tablet computer, an e-book reader, an MP3 player, and an MP4 player. Optionally, an operating system platform (windows or Linux) is run on the terminal.
Fig. 2 shows a schematic diagram of a system for processing angiographic images according to another exemplary embodiment of the present application. The system comprises a device 110 for recording angiographic images and a device 220 for processing angiographic images. Optionally, the capturing device 110 is a DSA device, and the DSA device is configured to subtract the non-contrast blood vessel image and the contrast blood vessel image to obtain an angiography image with the structure other than the blood vessel removed. The photographing apparatus 110 also transmits the angiographic image to the processing apparatus 220. The processing device 220 is used for processing the angiographic image and displaying the processed angiographic image. Optionally, the processing device 220 is a terminal device used by a doctor; optionally, the processing device 220 is a printing device for angiographic images.
Optionally, the types of the processing device 220 include: at least one of a laptop portable computer, a desktop computer, a printer, a smartphone, a smartwatch, a vehicle terminal, a wearable device, a smart television, a tablet, an ebook reader, an MP3 player, and an MP4 player. Optionally, an operating system platform (windows or Linux) runs on the processing device 220.
Fig. 3 is a schematic diagram illustrating a processing framework of an angiographic image according to an exemplary embodiment of the present application, which is exemplified by the server 120 shown in fig. 1 or the processing device 220 shown in fig. 2.
The process frame 300 includes: acquiring an initial angiographic image 301; the centerline of the target blood vessel in the initial angiographic image 301 is extracted, the angiographic image 302 is the angiographic image after the centerline extraction, and the image 302-1 is an enlarged schematic view of the target blood vessel, from which the centerline of the target blood vessel can be seen.
After the central line is extracted, filtering operation is performed on the angiography image 302 under the guidance of the central line to obtain an image filtering result, first image segmentation is performed on the image filtering result to obtain a first contour of the target blood vessel, the angiography image 303 is a contrast image obtained after the first image segmentation, and the image 303-1 is an enlarged schematic diagram of the target blood vessel, so that the first contour of the target blood vessel can be seen.
Fig. 4 shows a flowchart of a processing method of an angiographic image according to an exemplary embodiment of the present application, which is exemplified by the server 120 shown in fig. 1 or the processing device 220 shown in fig. 2. The method comprises the following steps.
At step 410, an angiographic image is acquired.
Angiographic image: refers to an electronic image obtained by an angiographic technique. Alternatively, the Angiography techniques include a DSA technique, a CTA (Computed Tomography Angiography) technique, and an MRA (Magnetic Resonance Angiography) technique.
The target vessel refers to the vessel segment to be segmented of interest in the present application, rather than the entire vessel segment to be treated as is commonly employed in the related art. The target vessel may be a vessel with a larger radius, a vessel with a smaller radius, a vessel with a bifurcation, etc. The centerline is the choroid of the target vessel, with most of the characteristics of the target vessel.
And 430, performing filtering operation on the angiography image under the guidance of the central line to obtain an image filtering result.
In one embodiment, a filtering guide direction is determined and obtained based on the central line, and filtering operation is performed on the angiography image under the guidance of the filtering guide direction to obtain an image filtering result. Optionally, the filtering guidance direction is a tangential direction of the pixel point on the center line, and the filtering guidance direction is a normal direction of the pixel point on the center line.
In one embodiment, the filtering operation is an operation of filtering based on a filter operator. Optionally, the filtering guiding direction is used as the direction of a filtering operator; and filtering the angiography image based on the filtering operator to obtain an image filtering result.
In one embodiment, the filtering operation is used to enhance line-like features of the angiographic image and/or edge features of the angiographic image. The linear feature refers to a feature of a linear structure of the entire angiogram of the angiogram, and the edge feature refers to a feature of an edge structure of the entire angiogram of the angiogram.
In one embodiment, the filter operator comprises an orthogonal filter operator. Carrying out orthogonal filtering on the angiography image based on an orthogonal filtering operator to obtain an image filtering result; the orthogonal filter operators comprise a first filter operator and a second filter operator, the first filter operator and the second filter operator are orthogonal to each other, the first filter operator is used for enhancing linear features of the angiography image, and the second filter operator is used for enhancing edge features of the angiography image. The first filter operator constitutes the real (complex) part of the quadrature filter operator and the second filter operator constitutes the imaginary (complex) part of the quadrature filter operator; alternatively, the first filter operator constitutes the (complex) imaginary part of the quadrature filter operator and the second filter operator constitutes the (complex) real part of the quadrature filter operator.
In one embodiment, the filtering guiding direction determined based on the central line is used as the direction of a filtering operator, and the filtering operator and the angiography image are subjected to convolution operation to obtain an image filtering result. Optionally, the image filtering result is an angiographic image obtained after filtering, or image data (which may be represented in a form of a matrix or the like) of the angiographic image obtained after filtering.
Optionally, the first image segmentation comprises a level set method. The level set method is an implicit method for representing curves, and the core idea is to represent a target curve of n dimensions by adopting a zero level set of a level set function of n +1 dimensions, wherein n is a positive integer. For example, a zero level set of a three-dimensional level set function is used to represent a two-dimensional target curve.
The level set energy functional is an energy functional (a function of the function is called a functional) constructed based on a level set function, the level set energy functional is used for obtaining a zero level set when the zero level set of the level set function is reduced to be a target curve, the level set energy functional generally comprises an internal force item and an external force item, the internal force item represents the strength of a pixel value of an internal pixel point of the target curve to a boundary pixel point, the external force item represents the strength of the pixel value of the external pixel point of the target curve to the boundary pixel point, when the internal force item is balanced with the external force item, the level set energy functional obtains a minimum value, and the zero level set at the moment is reduced to be the target curve.
In one embodiment, a level set energy functional of an image filtering result is constructed, and through continuous evolution and iteration of a zero level set, when an internal force item and an external force item on the level set energy functional reach balance, the zero level set is obtained, and then the first contour of a target blood vessel can be obtained.
In summary, the angiography image is filtered under the guidance of the center line of the target blood vessel, and the first image segmentation is performed on the filtering result to obtain the first contour of the target blood vessel, so that the accuracy of the blood vessel contour obtained by segmentation is improved. In the above process, the center line of the target blood vessel participates in the process of extracting the contour of the target blood vessel, and the center line plays a role of constraining the contour of the target blood vessel as the venation of the target blood vessel.
In the method for extracting the contour based on the pixel value threshold value provided by the related art, the bulge phenomenon is most likely to exist at the bifurcation part of the target blood vessel, and the central line used in the method has a constraint effect on the contour of the target blood vessel, so that the bulge contracts towards the center due to the constraint effect, the volume of the bulge is removed or reduced, and the bulge phenomenon is relieved.
Fig. 5 shows a flowchart of a processing method of an angiographic image according to an exemplary embodiment of the present application, which is exemplified by the server 120 shown in fig. 1 or the processing device 220 shown in fig. 2. The method comprises the following steps.
At step 510, an angiographic image is acquired.
Angiographic image: refers to an electronic image obtained by an angiographic technique. With combined reference to fig. 6, fig. 6 illustrates an angiographic image provided by an exemplary embodiment of the present application.
The target vessel refers to the vessel segment to be segmented of interest in the present application, rather than the entire vessel segment to be treated as is commonly employed in the related art. The target vessel may be a vessel with a larger radius, a vessel with a smaller radius, a vessel with a bifurcation, etc. Optionally, to ensure the effect of performing the first image segmentation subsequently, the target blood vessel obtained by the second image segmentation is a continuous blood vessel, that is, the second contour does not have a fracture. Referring to fig. 7 in combination, the enclosing line 701 shown in fig. 7 is a second contour of the target blood vessel.
In one embodiment, performing a second image segmentation on the angiographic image to obtain a second contour of the target vessel comprises at least one of the following ways.
And carrying out image segmentation on the angiography image based on the pixel value threshold value to obtain a second contour of the target blood vessel.
And carrying out image segmentation on the angiography image based on a region growing mode to obtain a second contour of the target blood vessel.
And carrying out image segmentation on the angiography image based on a region splitting and aggregating mode to obtain a second contour of the target blood vessel.
And carrying out image segmentation on the angiography image based on the offset correction mode to obtain a second contour of the target blood vessel.
And carrying out image segmentation on the angiography image based on an edge detection mode to obtain a second contour of the target blood vessel.
And step 530, extracting the central line of the target blood vessel based on the second contour.
In the case of extracting the second contour, a center line of the second contour is also extracted. The centerline is the venation of the target vessel and therefore has most of the characteristics of the target vessel. Referring to fig. 8 in combination, the line with cross mark shown in fig. 8 is the center line of the second contour, the pixel point a in fig. 8 is the initial pixel point of the center line, and the pixel point B is the final pixel point of the center line.
In one embodiment, the shortest path method is used to extract the center line of the target blood vessel. After the initial pixel point and the termination pixel point of the target blood vessel are determined, the shortest path obtained by gradient descent or positive gradient descent extraction is the central line. The method for extracting the center line by adopting the shortest path has the advantages of high extraction speed, simple operation and high quality of the extracted center line.
In one embodiment, the centerline of the target vessel is extracted by using a distance transformation method. The basic meaning of distance transformation is to calculate the shortest distance from a non-zero pixel point to a zero pixel point in an image. Optionally, binarizing the angiography image obtained after the first image is segmented to obtain a binary image of the angiography image, displaying a region where the target blood vessel is located as white (non-zero pixel points), displaying a region outside the target blood vessel as black (zero pixel points), performing distance transformation on the binary image, and setting the value of each pixel point on the binary image after the distance transformation as the distance from the pixel point to the nearest zero pixel point. And determining the pixel points with the maximum pixel values after the distance conversion, and sequentially connecting the pixel points with the maximum pixel values to obtain the central line of the target blood vessel. And the central line is extracted by adopting a distance conversion mode, so that the pixel points on the central line are ensured to be the points with the maximum pixel values, and the central line is clear and accurate.
And 540, performing filtering operation on the angiography image under the guidance of the central line to obtain an image filtering result.
In one embodiment, a filtering guide direction is determined and obtained based on the central line, and filtering operation is performed on the angiography image under the guidance of the filtering guide direction to obtain an image filtering result.
Optionally, determining the tangential direction of the pixel points on the central line, and taking the tangential direction as a filtering guide direction; optionally, the normal direction of the pixel point on the central line is determined, and the normal direction is used as a filtering guide direction.
In one embodiment, a target direction range is determined based on the central line, and filtering operation is performed on the angiography image, wherein the target direction range is a direction range of a filtering operator corresponding to the filtering operation. For example, from the approximate trend of the center line, the target direction range is determined to be (15 ° or 30 °), and the corresponding filter result is calculated when the direction of the filter operator is (15 ° or 30 °). Alternatively, the calculation of the direction is based on a counterclockwise rotation of the horizontal axis.
In one embodiment, the filtering operation is used to enhance line-like features of the angiographic image and/or edge features of the angiographic image. The linear features refer to features of the linear structures of the entire angiogram, and the edge features refer to features of the edge structures of the entire angiogram.
In one embodiment, the filtering operation is an operation of filtering based on a filter operator. Optionally, a tangent method of a pixel point on the central line is used as a direction of a filtering operator, and filtering is performed on the angiographic image based on the filtering operator to obtain an image filtering result. The filtering operator pertinently enhances the linear characteristics and the edge characteristics of the pixel points on the central line in the tangential direction.
Optionally, the filtering operation is a quadrature filtering operation. The orthogonal filtering operation is an operation of filtering based on an orthogonal filter operator. Optionally, the orthogonal filter operator includes a first filter operator and a second filter operator, where the first filter operator and the second filter operator are orthogonal to each other, the first filter operator is used to enhance a linear feature of the angiographic image, and the second filter operator is used to enhance an edge feature of the angiographic image. The first filter operator constitutes the real (complex) part of the quadrature filter operator and the second filter operator constitutes the imaginary (complex) part of the quadrature filter operator; alternatively, the first filter operator constitutes the imaginary (complex) part of the quadrature filter operator and the second filter operator constitutes the real (complex) part of the quadrature filter operator.
In one embodiment, the filtering guiding direction obtained by determining the central line is used as the direction of a filtering operator, and the filtering operator and the angiography image are subjected to convolution operation to obtain an image filtering result. Optionally, the image filtering result is an angiography image obtained after filtering, or image data (which may be represented in a matrix or the like) of the angiography image obtained after filtering.
Optionally, the first image segmentation comprises a level set method. In one embodiment, after constructing the level set energy functional of the image filtering result, the second contour is taken as an initial curve of the level set energy functional; then, controlling the level set energy functional to continuously iterate operation; when the horizontal set energy functional takes a minimum value, a first contour of the target vessel is obtained. The second contour is used as the initial curve of the level set energy functional, so that the iteration efficiency of the level set energy functional is improved, namely the first contour can be approximated within a very fast iteration number, and compared with the prior art in which a randomly generated initial circle or initial rectangle is used as the initial contour, the second contour is closer to the true blood vessel contour.
In one embodiment, a level set energy functional of an image filtering result is constructed, and through continuous evolution and iteration of a zero level set, when an internal force item and an external force item on the level set energy functional reach balance, the zero level set is obtained, and then a first contour of a target blood vessel can be obtained. Schematically, fig. 9 shows a surrounding line 901, which is a first contour of the target blood vessel.
In summary, a second contour (initial contour) of the target blood vessel is obtained through second image segmentation, a center line of the target blood vessel is extracted based on the second contour, the angiography image is filtered under the guidance of the filtering guidance direction determined on the center line, and the filtering result is subjected to first image segmentation, so that the accuracy of the blood vessel contour obtained through segmentation is improved. In the above process, the center line of the target blood vessel participates in the process of extracting the contour of the target blood vessel, and the center line plays a role of constraining the contour of the target blood vessel as the venation of the target blood vessel.
In the method for extracting the contour based on the pixel value threshold value provided by the related art, the bulge phenomenon is most likely to exist at the bifurcation part of the target blood vessel, and the central line used in the method generates a constraint force on the contour of the target blood vessel, so that the bulge contracts towards the center by the constraint force, the volume of the bulge is further removed or reduced, and the bulge phenomenon is relieved.
Moreover, because of the influence of the heart beat in the process of angiography, motion artifacts exist in an angiography image, and vessels at a narrow position may be blurred, however, the method for extracting the contour based on the pixel value threshold provided by the related art cannot solve the blurring problem, the orthogonal filtering of the application enhances linear features and edge features of the angiography image, further highlights the contour of a target vessel, and the contour of the vessels at the narrow position becomes more accurate.
Based on the alternative embodiment shown in fig. 4, steps 430 and 440 may be replaced with steps S1-S4 described below (or, based on the alternative embodiment shown in fig. 5, steps 540 and 550 may be replaced with steps S1-S4 described below).
Step S1: the direction of the filter operator of the angiographic image is determined based on the centerline.
And the filter operator is a mathematical expression used for carrying out filtering operation on the angiography image. Optionally, the tangential direction of the pixel point on the central line is used as the direction of the filtering operator. Optionally, the normal direction of the pixel point on the central line is used as the direction of the filtering operator. Optionally, a target direction range is determined based on the central line, and filtering operation is performed on the angiography image, where the target direction range is a direction range of a filtering operator corresponding to the filtering operation. For example, from the approximate trend of the center line, the target direction range is determined to be (15 ° or 30 °), and the corresponding filter result is calculated when the direction of the filter operator is (15 ° or 30 °).
Optionally, the filter operator is a forward filter operator, the forward filter operator includes a first filter operator and a second filter operator, the first filter operator and the second filter operator are orthogonal to each other, the first filter operator is used to enhance a linear feature of the angiographic image, and the second filter operator is used to enhance an edge feature of the angiographic image. The first filter operator constitutes the real (complex) part of the quadrature filter operator and the second filter operator constitutes the imaginary (complex) part of the quadrature filter operator; alternatively, the first filter operator constitutes the (complex) imaginary part of the quadrature filter operator and the second filter operator constitutes the (complex) real part of the quadrature filter operator.
Step S2: the filter operator is introduced as a local phase analysis term into the level set energy functional of the angiographic image.
And the local phase analysis item refers to an item used for representing the filtering guide direction corresponding to the central line in the constructed level set energy functional. The local phase analysis term characterizes the filtering operation in the filter guideline direction. Optionally, the local phase analysis term characterizes a filtering operation in a tangential direction of the centerline.
And step S3: when the level set energy functional iterates to obtain the minimum value, the zero level set function of the angiography image is obtained.
Optionally, when the level set energy functional iteration obtains a minimum value, that is, when an internal force term and an external force term in the level set energy functional reach a balance, a zero level set function of the angiography image is obtained.
And step S4: the zero level set function is identified as the first contour of the target vessel.
When the level set energy functional obtains the minimum value, the curve represented by the zero level set function is the first contour of the target blood vessel.
In conclusion, the method realizes that the filtering operator is introduced into the level set energy functional, the angiographic image is processed based on the constructed complete mathematical expression, and the complete mathematical expression can realize the best overall effect of (filtering + image segmentation).
In an alternative embodiment, as shown in fig. 5, step 520 provides a plurality of methods for segmenting the second image, and the various segmentation methods will be described in detail below.
An image segmentation method based on an artificial intelligence model.
Optionally, step 520 may be replaced with: predicting the probability of pixel points on the angiogram image belonging to the target blood vessel through an artificial intelligence model; determining pixel points of which the probability belongs to the first value interval as pixel points of the target blood vessel; and obtaining a second contour of the target blood vessel based on the pixel points of the edge position of the target blood vessel.
Wherein, the first value interval is a preset value interval. And the second contour obtained by segmentation has continuity by setting the first value interval.
In one embodiment, the angiographic image is input into a deep learning network, the deep learning network outputs a probability map of the angiographic image, and the pixel value of each point on the probability map is the probability that the pixel belongs to the pixel in the target vessel, so that the pixel predicted to belong to the target vessel on the probability map is brighter the higher the probability, and the pixel predicted to belong to the target vessel is darker the lower the probability. Therefore, the boundary of the target blood vessel will show a gradual light-dark distribution on the probability map. And then according to a preset first pixel value threshold, determining pixel points with pixel values larger than the first pixel value threshold from the probability map, determining the pixel points as pixel points of the target blood vessel, and further according to the pixel points at the edge position of the target blood vessel, obtaining a second outline of the target blood vessel.
It should be noted that, when the first pixel value threshold is set, it is required that the obtained first contour is a continuous contour, and there is no fracture on the second contour. The selection of the threshold is therefore of great importance, and the threshold needs to be adjusted continuously to obtain a continuous second contour of the target vessel. Schematically, fig. 10 shows a schematic view of a blood vessel obtained by an angiography image through a deep learning network.
The image segmentation method based on the artificial intelligence model overcomes the technical defects of the prior art when the image segmentation is carried out only by using the artificial intelligence model once, the blood vessel obtained by using the artificial intelligence model once is thicker in the narrow position, and multiple times of training are needed to adjust model parameters if more fine contours are to be segmented. In other words, compared with the image segmentation based on the artificial intelligence model in the related art, the image segmentation based on the artificial intelligence model is simple and convenient to operate and faster in contour extraction speed.
An image segmentation method based on pixel value threshold.
Optionally, step 520 may be replaced with: confirming the pixel points of which the pixel values on the angiography image belong to the second value range as the pixel points of the target blood vessel; and obtaining a second contour of the target blood vessel based on the pixel points of the edge position of the target blood vessel. The second value interval is a preset value interval, and the second contour obtained by segmentation has continuity through setting the second value interval.
In one embodiment, according to the pixel values of the pixel points on the angiography image, the pixel points with the pixel values smaller than the second pixel value threshold are determined as the pixel points of the target blood vessel; and then the second contour of the target blood vessel can be obtained according to the pixel points of the edge position of the target blood vessel. By adopting the method to carry out image segmentation, segmentation calculation can be simplified, the segmentation difficulty is reduced, and the efficiency is improved.
It should be noted that, when the second pixel value threshold is set, it is required that the obtained second contour is a continuous contour, and there is no fracture on the second contour. The selection of the threshold is therefore of great importance, and the threshold needs to be adjusted continuously to obtain a continuous second contour of the target vessel. Schematically, part (a) of fig. 11 shows a complete image obtained by segmenting the angiography image based on the pixel value threshold, part (B) of fig. 11 shows a segmented target blood vessel, and an image 1101 is an enlarged schematic diagram of the target blood vessel in part (B) of fig. 11. The image 1101 shows the centerline extracted based on the second contour, when the segmentation of the second contour of the target vessel at the stenosis position is coarser. In the image 1101, the pixel point a is an initial pixel point of the center line, and the pixel point B is a final pixel point of the center line.
And carrying out image segmentation based on a region growing method.
The core idea of the segmentation method based on region growing is as follows: firstly, determining basic pixel points, starting from the basic pixel points, drawing the pixel points which are around the basic pixel points and have the same properties (grey values, colors, lines and the like) as the basic pixel points into the current region, then diverging again by the drawn new pixel points, and so on until no other pixel points can be drawn into the current region.
And carrying out image segmentation based on a region splitting and aggregating method.
The core idea of the method based on the region splitting aggregation is as follows: firstly, the same image is divided for a plurality of times to obtain a plurality of regions, each region has respective properties (gray value, color, texture and the like), and adjacent regions belonging to the same properties in the plurality of regions are polymerized until adjacent regions with the same properties do not exist finally.
And performing image segmentation based on the mode of offset rectification.
The core idea of the offset correction is as follows: when part of blood vessels in the target blood vessel are in a brighter area of the whole image, reducing pixel values of pixel points in the part of blood vessels; and when part of blood vessels in the target blood vessel are in a darker area of the whole image, increasing the pixel values of pixel points in the part of blood vessels. Based on this, it is possible to solve the problem of pixel value imbalance and to improve the difference between the foreground part and the background part in the angiographic image. Schematically, part (a) of fig. 12 shows an angiographic image after offset correction, part (B) of fig. 12 shows a target blood vessel after offset correction, and an image 1201 is an enlarged schematic view of the target blood vessel in part (B) of fig. 12. The image 1201 shows the centerline extracted based on the second contour, where the segmentation of the second contour of the target blood vessel at the stenosis position is coarser and the boundary line of the second contour is coarser. In the image 1201, the pixel point a is an initial pixel point of the center line, and the pixel point B is a final pixel point of the center line.
Image segmentation method based on edge detection.
The core idea of the image segmentation method based on edge detection is as follows: firstly, calculating each pixel point in the image through an edge detection operator, judging the output of each pixel point according to a determined criterion, and judging whether the pixel point is an edge point. Then, boundary points of the image are removed, edge break points are filled, and finally the edge points are connected into lines to finish image segmentation.
The above provides multiple ways of second image segmentation, the contour of the target blood vessel can be extracted more quickly through the second image segmentation and the first image segmentation, and when the first image segmentation indicates image segmentation based on a level set segmentation algorithm, the iterative computation process of a level set energy functional is accelerated by the second contour obtained by the second image segmentation, that is, the speed of extracting the first contour is accelerated.
Fig. 13 shows a flowchart of a method for processing an angiographic image according to an exemplary embodiment of the present application, which includes the following steps.
Angiographic image: refers to an electronic image obtained by an angiographic technique. With combined reference to fig. 6, fig. 6 illustrates an initial angiographic image for subsequent image processing as provided by an exemplary embodiment of the present application.
In step 1302, a second contour of the target vessel in the angiographic image is extracted.
In one embodiment, the angiographic image is segmented by a deep learning network and a second contour of the target vessel is extracted. Schematically, fig. 10 shows blood vessels in an angiographic image output by a deep learning network.
In one embodiment, a threshold-based image segmentation method segments an angiographic image and extracts a second contour of a target vessel. Schematically, fig. 11 (B) shows a second contour of the target blood vessel obtained by the threshold-based image segmentation method.
In one embodiment, an image-based offset correction method segments an angiographic image and extracts a second contour of a target vessel. Schematically, part (B) of fig. 12 shows a second contour of the target blood vessel obtained by the region-based offset correction method.
And step 1303, determining initial pixel points and termination pixel points of the central line.
In one embodiment, the start pixel point is the start point of the blood vessel of interest (target blood vessel), and the end pixel point is the end point of the blood vessel of interest (target blood vessel). Illustratively, the pixel a in the portion (B) of fig. 11 is an initial pixel, and the pixel B is a final pixel. The pixel a in the portion (B) of fig. 12 is the start pixel, and the pixel B is the end pixel.
In one embodiment, the centerline of the target vessel is extracted by a Fast Marching algorithm (Fast Marching). The fast marching algorithm is simple to use, and the central line of the target blood vessel is conveniently and fast extracted. In one embodiment, the tangential direction of each pixel point on the center line is also determined.
In one embodiment, a level set energy functional of the angiographic image after the coarse contour of the target vessel is segmented is constructed. In one embodiment, the angiographic image after the rough contour of the target blood vessel is segmented is subjected to a quadrature filtering operation. The orthogonal filtering is composed of two parts, namely peak extraction filtering and edge extraction filtering, wherein the peak extraction filtering is more sensitive to the linear structure of the image, namely the filtering response value of the linear structure of the image is larger, and the edge extraction filtering is more sensitive to the edge structure of the image, namely the filtering response value of the edge structure of the image is larger. The peak extraction filtering and the edge extraction filtering are orthogonal to each other and form the real and imaginary parts of the complex number, and the above analysis is called local phase analysis. The advantage of the orthogonal filtering is that image enhancement is performed without depending on the pixel values of the image, but the orthogonal filtering can only obtain the response in a single direction, that is, only the linear region or the edge region in a certain direction can be enhanced, and only the response of the linear structure or the edge structure in a certain direction can be obtained. If the requirement of enhancing the linear structure or the edge structure of the whole image in different directions is met, the filtering operator of orthogonal filtering needs to be rotated step by step, and then the filtering operator and the angiography image are subjected to convolution operation, so that the enhancement of the whole image in the linear region and the edge region can be obtained. However, rotating the filter operator stepwise increases the computational load of quadrature filtering. Based on the method, the central line is used for guiding local phase analysis, response of linear or edge regions in a specific direction is processed in a targeted mode, and the efficiency of image processing can be greatly improved.
In step 1306, a first contour of the target blood vessel is extracted.
In one embodiment, the orthogonal filter operator obtained in step 1305 is introduced into the level set energy functional, in the process of solving the level set energy functional, the initial contour of the target blood vessel obtained in step 1302 is further derived, and when the internal force item and the external force item in the level set energy functional reach balance, the obtained zero level set function is the first contour of the output target blood vessel.
In an embodiment, after the first contour is extracted, the pixel points on the first contour are further converted into sub-pixel points, so as to obtain a third contour of the target blood vessel. Schematically, part (a) of fig. 14 shows an angiographic image before conversion, and part (B) of fig. 14 shows an angiographic image after conversion. An image 1401 is an enlarged schematic view of the target blood vessel in part (a) of fig. 14, and an image 1402 is an enlarged schematic view of the target blood vessel in part (B) of fig. 14. Image 1401 shows a first contour of a target blood vessel. Image 1402 shows a third contour of the target vessel. It can be seen that the first contour is rough, there are more jagged edges on the first contour, the third contour is more accurate in segmentation, and the boundary is smoother.
In conclusion, the method also realizes that the pixel points on the first contour are converted into the sub-pixel points, so that the third contour of the target blood vessel is obtained, and the sawtooth edge on the first contour is smoothed.
Fig. 15 is a block diagram illustrating a configuration of an apparatus for processing an angiographic image according to an exemplary embodiment of the present application, and the apparatus includes the following modules.
The acquiring module 1501 is configured to acquire an angiography image.
An extraction module 1502 is configured to extract a centerline of a target vessel in an angiographic image.
And the filtering module 1503 is configured to perform a filtering operation on the angiography image under the guidance of the center line to obtain an image filtering result.
The segmentation module 1504 is configured to perform a first image segmentation based on the image filtering result to obtain a first contour of the target blood vessel.
In an optional embodiment, the filtering module 1503 is further configured to determine a derived filtering guidance direction based on the center line; and carrying out filtering operation on the angiography image under the guidance of the filtering guidance direction to obtain an image filtering result.
In an alternative embodiment, the filtering operation is an operation of filtering based on a filtering operator. The filtering module 1503, configured to use the filtering direction as a direction of a filtering operator; and filtering the angiography image based on the filtering operator to obtain an image filtering result.
In an alternative embodiment, the filter operator comprises an orthogonal filter operator; the filtering module 1503 is further configured to perform orthogonal filtering on the angiography image based on an orthogonal filtering operator to obtain an image filtering result; the orthogonal filter operators comprise a first filter operator and a second filter operator, the first filter operator and the second filter operator are orthogonal to each other, the first filter operator is used for enhancing linear features of the angiography image, and the second filter operator is used for enhancing edge features of the angiography image.
In an optional embodiment, the filtering module 1503 is further configured to determine a tangential direction of a pixel point on the centerline, and use the tangential direction as a filtering guidance direction. In an optional embodiment, the filtering module 1503 is further configured to determine a normal direction of a pixel point on the center line, and use the normal direction as a filtering guidance direction.
In an alternative embodiment, the segmentation module 1504 is further configured to construct a level set energy functional of the image filtering result; and obtaining a first contour of the target blood vessel under the condition that the horizontal set energy functional iterates to obtain a minimum value.
In an optional embodiment, the extracting module 1502 is further configured to perform a second image segmentation on the angiography image to obtain a second contour of the target blood vessel; and extracting the central line of the target blood vessel based on the second contour.
In an alternative embodiment, the segmentation module 1504 is further configured to construct a level set energy functional of the image filtering result; taking the second contour as an initial curve of the level set energy functional; and obtaining a first contour of the target blood vessel under the condition that the horizontal set energy functional iterates to obtain a minimum value.
In an alternative embodiment, the filtering module 1503 and the segmentation module 1504 are further configured to determine the direction of a filter operator of the angiographic image based on the centerline; introducing a filtering operator into a level set energy functional of the angiography image as a local phase analysis item, wherein the local phase analysis item represents the filtering operation of the angiography image; obtaining a zero level set function of the angiography image under the condition that the level set energy functional is iterated to obtain a minimum value; the zero level set function is identified as the first contour of the target vessel.
In an optional embodiment, the extracting module 1502 is further configured to predict, through an artificial intelligence model, a probability that a pixel point on the angiography image belongs to the target blood vessel; determining the pixel points with the probability reaching the probability threshold value as the pixel points of the target blood vessel; and obtaining a second contour of the target blood vessel based on the pixel points of the edge position of the target blood vessel.
In an optional embodiment, the extracting module 1502 is further configured to perform image segmentation on the angiography image based on the pixel value threshold to obtain a second contour of the target blood vessel.
In an optional embodiment, the extracting module 1502 is further configured to perform image segmentation on the angiography image based on a region growing manner to obtain a second contour of the target blood vessel.
In an optional embodiment, the extracting module 1502 is further configured to perform image segmentation on the angiography image based on a region splitting and aggregating manner, so as to obtain a second contour of the target blood vessel.
In an optional embodiment, the extracting module 1502 is further configured to perform image segmentation on the angiography image based on an offset correction manner to obtain a second contour of the target blood vessel.
In an optional embodiment, the extracting module 1502 is further configured to perform image segmentation on the angiography image based on an edge detection manner to obtain a second contour of the target blood vessel.
In an alternative embodiment, the apparatus further includes a conversion module 1505. The converting module 1505 is configured to convert the pixel points on the first contour into sub-pixel points to obtain a third contour of the target blood vessel.
In summary, the angiography image is filtered under the guidance of the center line of the target blood vessel, and the first image segmentation is performed on the filtering result to obtain the first contour of the target blood vessel, so that the accuracy of the blood vessel contour obtained by segmentation is improved. In the above process, the center line of the target blood vessel participates in the process of extracting the contour of the target blood vessel, and the center line plays a role of constraining the contour of the target blood vessel as the venation of the target blood vessel.
In the method for extracting the contour based on the pixel value threshold value provided by the related art, the bulge phenomenon is most likely to exist at the bifurcation part of the target blood vessel, and the central line used in the method has a constraint effect on the contour of the target blood vessel, so that the bulge contracts towards the center due to the constraint effect, the volume of the bulge is removed or reduced, and the bulge phenomenon is relieved.
FIG. 16 is a schematic diagram of a computer device provided by one embodiment of the present application. The computer device runs a processing system for angiographic images as shown in fig. 1 or fig. 2. Specifically, the method comprises the following steps: the computer apparatus 1600 includes a Central Processing Unit (CPU) 1601, a system Memory 1604 including a Random Access Memory (RAM) 1602 and a Read-Only Memory (ROM) 1603, and a system bus 1605 connecting the system Memory 1604 and the CPU 1601. The computer device 1600 also includes a basic Input/Output system (I/O system) 1606, which facilitates transfer of information between various devices within the computer, and a mass storage device 1607 for storing an operating system 1613, application programs 1614, and other program modules 1615.
The basic input/output system 1606 includes a display 1608 for displaying information and an input device 1609 such as a mouse, keyboard, etc. for user input of information. Wherein a display 1608 and an input device 1609 are connected to the central processing unit 1601 by way of an input/output controller 1610 which is connected to the system bus 1605. The basic input/output system 1606 may also include an input/output controller 1610 for receiving and processing input from a number of other devices, such as a keyboard, mouse, or electronic stylus. Similarly, an input/output controller 1610 may also provide output to a display screen, a printer, or other type of output device.
The mass storage device 1607 is connected to the central processing unit 1601 by a mass storage controller (not shown) connected to the system bus 1605. The mass storage device 1607 and its associated computer-readable media provide non-volatile storage for the server 1600. That is, the mass storage device 1607 may include a computer-readable medium (not shown) such as a hard disk or a Compact Disc-Only Memory (CD-ROM) drive.
Without loss of generality, computer readable media may comprise computer storage media and communication media. Computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Computer storage media include RAM, ROM, erasable Programmable Read-Only Memory (EPROM), electrically Erasable Programmable Read-Only Memory (EEPROM), flash Memory or other solid state Memory technology, CD-ROM, digital Versatile Disks (DVD), or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices. Of course, those skilled in the art will appreciate that computer storage media is not limited to the foregoing. The system memory 1604 and mass storage device 1607 described above may be collectively referred to as memory.
According to various embodiments of the application, the server 1600 may also operate with remote computers connected to a network, such as the Internet. That is, the server 1600 may be connected to the network 1611 through a network interface unit 1612 coupled to the system bus 1605, or the network interface unit 1612 may be used to connect to other types of networks and remote computer systems (not shown).
The present application further provides a computer-readable storage medium having stored therein at least one instruction, at least one program, code set, or set of instructions, which is loaded and executed by a processor to implement the method of processing angiographic images provided by the above-described method embodiments.
A computer program product or computer program is provided that includes computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions to enable the computer device to execute the processing method of the angiography image provided by the method embodiment.
The above-mentioned serial numbers of the embodiments of the present application are merely for description and do not represent the merits of the embodiments.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The above description is only exemplary of the present application and should not be taken as limiting, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims (12)
1. A method of processing an angiographic image, the method comprising:
acquiring the angiography image;
extracting a central line of a target blood vessel in the angiography image;
determining a direction of a filter operator of the angiographic image based on the centerline;
introducing the filter operator into a level set energy functional of the angiographic image as a local phase analysis term, the local phase analysis term characterizing a filtering operation of the angiographic image;
obtaining a zero level set function of the angiographic image under the condition that the level set energy functional iterates to obtain a minimum value;
identifying the zero level set function as a first contour of the target vessel.
2. The method of claim 1, wherein the filter operator comprises an orthogonal filter operator; the orthogonal filter operators comprise a first filter operator and a second filter operator, the first filter operator and the second filter operator are orthogonal to each other, the first filter operator is used for enhancing linear features of the angiography image, and the second filter operator is used for enhancing edge features of the angiography image.
3. The method of claim 1, wherein determining the orientation of a filter operator of the angiographic image based on the centerline comprises:
determining the tangential direction of the pixel points on the central line, and taking the tangential direction as the direction of the filtering operator;
alternatively, the first and second electrodes may be,
and determining the normal direction of the pixel point on the central line, and taking the normal direction as the direction of the filter operator.
4. The method of any one of claims 1 to 3, wherein said extracting a centerline of a target vessel in said angiographic image comprises:
performing second image segmentation on the angiography image to obtain a second contour of the target blood vessel;
and extracting the central line of the target blood vessel based on the second contour.
5. The method of claim 4, wherein said performing a second image segmentation on said angiographic image resulting in a second contour of said target vessel comprises:
predicting the probability of pixel points on the angiography image belonging to the target blood vessel through an artificial intelligence model;
determining the pixel points of which the probability reaches a probability threshold value as the pixel points of the target blood vessel;
and obtaining a second contour of the target blood vessel based on the pixel points of the edge position of the target blood vessel.
6. The method of claim 4, wherein performing a second image segmentation on the angiographic image to obtain a second contour of the target vessel comprises at least one of:
performing image segmentation on the angiography image based on a pixel value threshold value to obtain a second contour of the target blood vessel;
carrying out image segmentation on the angiography image based on a region growing mode to obtain a second contour of the target blood vessel;
carrying out image segmentation on the angiography image based on a region splitting and aggregating mode to obtain a second contour of the target blood vessel;
carrying out image segmentation on the angiography image based on an offset correction mode to obtain a second contour of the target blood vessel;
and carrying out image segmentation on the angiography image based on an edge detection mode to obtain a second contour of the target blood vessel.
7. The method of any of claims 1 to 3, further comprising:
and converting the pixel points on the first contour into sub-pixel points to obtain a third contour of the target blood vessel.
8. An apparatus for processing an angiographic image, the apparatus comprising:
an acquisition module for acquiring the angiographic image;
the extraction module is used for extracting the central line of a target blood vessel in the angiography image;
the filtering module and the segmentation module are used for determining the direction of a filtering operator of the angiography image based on the central line; introducing the filter operator into a level set energy functional of the angiographic image as a local phase analysis term, the local phase analysis term characterizing a filtering operation of the angiographic image; obtaining a zero level set function of the angiographic image under the condition that the level set energy functional iterates to obtain a minimum value; identifying the zero level set function as a first contour of the target vessel.
9. An angiographic image processing system, comprising a device for capturing said angiographic image, a server and a viewing terminal for said angiographic image;
the shooting device is used for shooting the angiography image and sending the angiography image to the server;
the server is used for executing the processing method of the angiography image according to any one of claims 1 to 7 and sending the processed angiography image to the viewing terminal;
and the viewing terminal is used for displaying the processed angiography image.
10. An angiographic image processing system, characterized in that said system comprises a device for capturing said angiographic image and a device for processing said angiographic image;
the shooting device is used for shooting the angiography image and sending the angiography image to the processing device;
the processing device for performing the method of processing an angiographic image according to any of claims 1 to 7 and displaying the processed angiographic image.
11. A computer device, characterized in that it stores a computer program which is loaded and executed by a processor to implement the method of processing an angiographic image according to any one of claims 1 to 7.
12. A computer-readable storage medium, in which a computer program is stored which is loaded and executed by a processor to implement the method of processing an angiographic image according to any one of claims 1 to 7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211098848.3A CN115187598B (en) | 2022-09-09 | 2022-09-09 | Method, apparatus, system, device and medium for processing angiography image |
| CN202211468930.0A CN116051457A (en) | 2022-09-09 | 2022-09-09 | Angiographic image processing method, angiographic image processing device, angiographic image processing system, angiographic image processing equipment and angiographic image processing medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211098848.3A CN115187598B (en) | 2022-09-09 | 2022-09-09 | Method, apparatus, system, device and medium for processing angiography image |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211468930.0A Division CN116051457A (en) | 2022-09-09 | 2022-09-09 | Angiographic image processing method, angiographic image processing device, angiographic image processing system, angiographic image processing equipment and angiographic image processing medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115187598A CN115187598A (en) | 2022-10-14 |
| CN115187598B true CN115187598B (en) | 2023-02-03 |
Family
ID=83522978
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211468930.0A Pending CN116051457A (en) | 2022-09-09 | 2022-09-09 | Angiographic image processing method, angiographic image processing device, angiographic image processing system, angiographic image processing equipment and angiographic image processing medium |
| CN202211098848.3A Active CN115187598B (en) | 2022-09-09 | 2022-09-09 | Method, apparatus, system, device and medium for processing angiography image |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211468930.0A Pending CN116051457A (en) | 2022-09-09 | 2022-09-09 | Angiographic image processing method, angiographic image processing device, angiographic image processing system, angiographic image processing equipment and angiographic image processing medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN116051457A (en) |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5713748B2 (en) * | 2011-03-24 | 2015-05-07 | 株式会社東芝 | Plaque region extraction method and apparatus |
| CN102982547B (en) * | 2012-11-29 | 2016-07-27 | 北京师范大学 | The local movable contour model cardiovascular and cerebrovascular vessel dividing method of auto-initiation |
| CN105160660B (en) * | 2015-08-17 | 2017-12-01 | 中国科学院苏州生物医学工程技术研究所 | Active contour vessel extraction method and system based on multiple features Gauss curve fitting |
| CN111681224A (en) * | 2020-06-09 | 2020-09-18 | 上海联影医疗科技有限公司 | Method and device for acquiring blood vessel parameters |
| CN111899267A (en) * | 2020-07-24 | 2020-11-06 | 哈尔滨理工大学 | Retina blood vessel segmentation algorithm based on level set |
| CN112184888A (en) * | 2020-10-10 | 2021-01-05 | 深圳睿心智能医疗科技有限公司 | Three-dimensional blood vessel modeling method and device |
| CN112652011B (en) * | 2020-12-25 | 2023-04-14 | 北京阅影科技有限公司 | Extraction method and extraction device of target blood vessel and computer-readable storage medium |
| CN115359077A (en) * | 2022-05-27 | 2022-11-18 | 天津远景科技服务有限公司 | Method and device for determining black blood vessel model |
-
2022
- 2022-09-09 CN CN202211468930.0A patent/CN116051457A/en active Pending
- 2022-09-09 CN CN202211098848.3A patent/CN115187598B/en active Active
Non-Patent Citations (2)
| Title |
|---|
| Frangi based multi-scale level sets for retinal vascular segmentation;Jinzhu Yang等;《Computer Methods and Programs in Biomedicine》;20201231;全文 * |
| 利用脊线检测实现视网膜图像血管中心线的精确提取;陈骥等;《重庆大学学报》;20110815(第08期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116051457A (en) | 2023-05-02 |
| CN115187598A (en) | 2022-10-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10229499B2 (en) | Skin lesion segmentation using deep convolution networks guided by local unsupervised learning | |
| CN110188760B (en) | Image processing model training method, image processing method and electronic equipment | |
| US20230237841A1 (en) | Occlusion Detection | |
| Zhang et al. | Segment graph based image filtering: Fast structure-preserving smoothing | |
| US20150003725A1 (en) | Depth constrained superpixel-based depth map refinement | |
| CN108694719B (en) | Image output method and device | |
| US8781187B2 (en) | Methods, apparatuses, and computer program products for identifying a region of interest within a mammogram image | |
| CN110176010B (en) | Image detection method, device, equipment and storage medium | |
| CN107871319B (en) | Method and device for detecting beam limiter area, X-ray system and storage medium | |
| US11908183B2 (en) | Image analysis and processing pipeline with real-time feedback and autocapture capabilities, and visualization and configuration system | |
| US11720745B2 (en) | Detecting occlusion of digital ink | |
| CN112529913A (en) | Image segmentation model training method, image processing method and device | |
| CN111951154A (en) | Method and device for generating picture containing background and medium | |
| US9292921B2 (en) | Method and system for contrast inflow detection in 2D fluoroscopic images | |
| CN113469963B (en) | Pulmonary artery image segmentation method and device | |
| US10127672B2 (en) | Separation of foreground and background in medical images | |
| US10395773B2 (en) | Automatic characterization of Agatston score from coronary computed tomography | |
| Al Shehhi et al. | An automatic cognitive graph-based segmentation for detection of blood vessels in retinal images | |
| CN115187598B (en) | Method, apparatus, system, device and medium for processing angiography image | |
| Wang et al. | Adaptive shape prior in graph cut segmentation | |
| CN116245832B (en) | Image processing method, device, equipment and storage medium | |
| JP2003303346A (en) | Method, device and program for tracing target, and recording medium recording the program | |
| CN115661322B (en) | Face texture image generation method and device | |
| CN115131361A (en) | Training of target segmentation model, focus segmentation method and device | |
| US11200708B1 (en) | Real-time color vector preview generation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |