CN119251383A - Vascular reconstruction method and device, and computer equipment - Google Patents

Abstract

The present invention discloses a blood vessel reconstruction method and device, and a computer device, and relates to the field of image processing technology. After acquiring the original angiography data, the computer device can input the original angiography data into a blood vessel reconstruction model to obtain a target blood vessel image. Among them, the pixel value of the blood vessel area in the target blood vessel image is greater than the pixel value of the first non-blood vessel area in the target blood vessel image. That is, the computer device can reconstruct a target blood vessel image in which the pixel value of the blood vessel area is significantly enhanced and the pixel value of the first non-blood vessel area is significantly suppressed based on the original angiography data. And the original angiography data can be obtained with only a single scan. Compared with the related technology, it effectively avoids secondary scanning, shortens the scanning time, improves the scanning efficiency, and reduces the radiation dose to the scanned object.

Description

Vascular reconstruction method and device and computer equipment

Technical Field

The present invention relates to the field of image processing technologies, and in particular, to a method and apparatus for reconstructing a blood vessel, and a computer device.

Background

A computed tomography (computed tomography, CT) apparatus typically requires sequential acquisition of an image of a vessel that is not contrast enhanced and an image of the vessel that is contrast enhanced such that the computer apparatus suppresses non-vascular tissue, such as bone, muscle, in the image of the vessel that is not contrast enhanced by a registration subtraction technique to enhance the contrast between non-vascular and vascular regions in the image of the vessel that is not contrast enhanced, enabling high definition imaging of the vessel.

However, since an image of a blood vessel not enhanced by the contrast agent and an image of a blood vessel enhanced by the contrast agent need to be acquired, a plurality of scans are required to be performed on a scanned object, resulting in longer scanning time, lower efficiency and larger radiation dose to a scanned patient.

Disclosure of Invention

The invention provides a vascular reconstruction method, a vascular reconstruction device and computer equipment, which can solve the problems of longer scanning time, lower efficiency and larger radiation dose to a scanned patient caused by the need of scanning a scanned object for multiple times in the related technology. The technical scheme is as follows:

in one aspect, a method of vascular reconstruction is provided, the method comprising:

Acquiring original angiography data;

inputting the original angiography data into a vascular reconstruction model to obtain a target vascular image;

Wherein the pixel value of the blood vessel region in the target blood vessel image is greater than the pixel value of the first non-blood vessel region in the target blood vessel image.

Optionally, the method further comprises:

Acquiring a plurality of sample data, wherein each sample data comprises sample original angiography data and sample target angiography images, the pixel value of a vascular region in each sample target angiography image is larger than that of a non-vascular region in each sample target angiography image, and each sample target angiography image is obtained by registering and subtracting the sample original angiography data and the sample original non-angiography data corresponding to the sample original angiography data;

Training a plurality of sample data to obtain a vascular reconstruction model.

Optionally, the registration deviation of the sample raw angiographic data from the sample raw non-angiographic data is smaller than a first preset value.

Optionally, the method further comprises:

If the optimized second non-vascular region exists in the target vascular image, reducing the pixel value of the second non-vascular region;

The pixel value of the blood vessel region in the target blood vessel image is smaller than or equal to the pixel value of the second non-blood vessel region before processing, and the pixel value of the blood vessel region in the target blood vessel image is larger than the pixel value of the second non-blood vessel region after processing.

Optionally, the method further comprises:

Acquiring an angiographic image;

And inputting the angiography image and the target vessel image into a vessel segmentation model to obtain a vessel segmentation result.

Optionally, the method further comprises:

normalization processing is carried out on the original angiography data.

In another aspect, a computer readable storage medium is provided, on which a computer program is stored, which when executed by a processor implements the vascular reconstruction method according to the above aspect.

In yet another aspect, a computer device is provided, including a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the vascular reconstruction method of the above aspect when executing the computer program.

In yet another aspect, there is provided a vascular reconstruction device, the device comprising:

the acquisition module is used for acquiring original angiography data;

The processing module is used for inputting the original angiography data into the vascular reconstruction model to obtain a target vascular image;

Wherein the pixel value of the blood vessel region in the target blood vessel image is greater than the pixel value of the first non-blood vessel region in the target blood vessel image.

In summary, the embodiment of the invention provides a vascular reconstruction method, a vascular reconstruction device and a computer device, wherein after original angiography data are acquired by the computer device, the original angiography data can be input into a vascular reconstruction model to obtain a target vascular image. Wherein the pixel value of the blood vessel region in the target blood vessel image is greater than the pixel value of the first non-blood vessel region in the target blood vessel image. I.e. the computer device can reconstruct a target vessel image based on the original angiographic data with significantly enhanced pixel values of the vessel region and significantly suppressed pixel values of the first non-vessel region. And the original angiography data can be obtained only through single scanning, compared with the related art, the method has the advantages of effectively avoiding secondary scanning, shortening the scanning time, improving the scanning efficiency and reducing the radiation dose to a scanned object.

Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.

Drawings

FIG. 1 is a flow chart of a method for revascularization provided by an embodiment of the invention;

FIG. 2 is a flow chart of another method for revascularization provided by an embodiment of the invention;

FIG. 3 is a diagram showing a comparison of the scheme S1 and the scheme S2 according to the embodiment of the present invention;

FIG. 4 is a diagram showing another embodiment S1 and S2 according to the present invention;

FIG. 5 is a diagram showing a comparison of the scheme S1 and the scheme S3 according to the embodiment of the present invention;

FIG. 6 is a schematic diagram of a fused image provided by an embodiment of the present invention;

FIG. 7 is a schematic diagram of obtaining a blood vessel segmentation result based on a blood vessel segmentation model according to an embodiment of the present invention;

FIG. 8 is a schematic diagram of a target vessel image according to an embodiment of the present invention;

FIG. 9 is a schematic illustration of another target vessel image provided by an embodiment of the present invention;

FIG. 10 is a schematic illustration of a target process image for batch printing according to an embodiment of the present invention;

FIG. 11 is a schematic diagram of a computer device according to an embodiment of the present invention;

fig. 12 is a block diagram of a vascular reconstruction device according to an embodiment of the present invention.

Detailed Description

Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative and intended to explain the present invention and should not be construed as limiting the invention.

Computed tomography arterial angiography (computed tomography angiography, CTA) and computed tomography venous angiography (computed tomography venography, CTV) are non-invasive imaging techniques, which play an important role in the diagnosis of vascular disease progression with their unique technical advantages. By high-precision X-ray tomography and advanced image processing technology, CTA/CTV can clearly show the fine structure and pathological conditions in blood vessels, including the thickness of blood vessel walls, plaque formation, stenosis degree and the like. The doctor can accurately judge the type and degree of vascular diseases, and provides powerful basis for patients to develop personalized treatment schemes. The CTA/CTV scanning speed is high, the imaging efficiency is high, the diagnosis and treatment efficiency is greatly improved, and the waiting time and uncomfortable feeling of a patient are reduced. The rapid imaging process also means that the doctor can acquire the diagnostic results faster, thereby making a treatment plan in time and competing for valuable treatment time for the patient. In addition, the CTA/CTV can create high-quality three-dimensional blood vessel images by using advanced scanning equipment and image processing algorithms, and visually display the morphology, trend and blood flow condition of the blood vessels. The detailed image information not only helps doctors to accurately diagnose vascular diseases, but also provides accurate guidance for surgical navigation and interventional therapy.

The gray scale intensity of the skeleton and the enhanced blood vessel display in the CTA image/CTV image is similar, and the visualization and the accurate analysis of the blood vessel are restricted. At present, CT-digital subtraction angiography (digital subtraction angiography, DSA) is an advanced medical image examination method which combines DSA and CT technologies. In the CTA/CTV scanning process, a CT device is required to continuously acquire an image column of a blood vessel which is not reinforced by contrast agent and an image of the blood vessel which is reinforced by the contrast agent. The computer equipment can then register subtraction technology to inhibit bones, muscles and other non-vascular tissues in the image of the blood vessel which is not enhanced by the contrast agent, so as to enhance the contrast between the non-vascular region and the vascular region in the image of the blood vessel which is not enhanced by the contrast agent, and realize high-definition imaging of the blood vessel. The trend, the morphology and the pathological change of the blood vessel can be intuitively seen through the image of the blood vessel which is enhanced by the enhanced blood vessel and not enhanced by the contrast agent.

Fig. 1 is a flowchart of a vascular reconstruction method according to an embodiment of the present invention, applied to a computer device, as shown in fig. 1, where the method includes:

step 101, acquiring original angiography data.

The computer device may acquire raw angiographic data. The original angiography data can be original angiography data obtained by reconstructing a radiation attenuation signal scanned by a scanning part of a target object by CT equipment through a CT enhanced scanning technology, and the original angiography data can retain complete CT examination scanning information. Or the original angiographic data may be an image obtained by converting the original angiographic data, which may be referred to as an original angiographic image.

Step 102, inputting the original angiography data into a vascular reconstruction model to obtain a target vascular image.

After the original angiography data is acquired by the computer equipment, the original angiography data can be input into a vascular reconstruction model to obtain a target vascular image.

Wherein the pixel value of the blood vessel region in the target blood vessel image is greater than the pixel value of the first non-blood vessel region in the target blood vessel image. The first non-blood vessel region refers to a region in which the pixel value of the non-blood vessel region of the target blood vessel image is smaller than the pixel value of the blood vessel region, and the first non-blood vessel region can be all non-blood vessel regions in the target blood vessel image or part of non-blood vessel regions in the target blood vessel image.

In summary, the embodiment of the present invention provides a method for reconstructing a blood vessel, in which after acquiring original angiography data, a computer device may input the original angiography data into a vascular reconstruction model to obtain a target vascular image. Wherein the pixel value of the blood vessel region in the target blood vessel image is greater than the pixel value of the first non-blood vessel region in the target blood vessel image. I.e. the computer device can reconstruct a target vessel image based on the original angiographic data with significantly enhanced pixel values of the vessel region and significantly suppressed pixel values of the first non-vessel region. And the original angiography data can be obtained only through single scanning, compared with the related art, the method has the advantages of effectively avoiding secondary scanning, shortening the scanning time, improving the scanning efficiency and reducing the radiation dose to a scanned object.

Fig. 2 is a flowchart of another vascular reconstruction method according to an embodiment of the present invention, applied to a computer device, as shown in fig. 2, where the method may include:

Step 201, acquiring original angiography data.

The computer device may acquire raw angiographic data. The original angiography data can be original angiography data obtained by reconstructing a radiation attenuation signal scanned by a scanning part of a target object by CT equipment through a CT enhanced scanning technology, and the original angiography data can retain complete CT examination scanning information. Or the original angiographic data may be an image obtained by converting the original angiographic data, which may be referred to as an original angiographic image.

Alternatively, the original angiographic data may be a data sequence and, correspondingly, the original angiographic image may be an image sequence, i.e. the original angiographic image comprises a plurality of slice images, which constitute a 3-dimensional (D) image. Or the original angiographic data may be a frame of data and, correspondingly, the original angiographic image may be a frame of image.

In the embodiment of the present invention, after the CT apparatus scans to obtain the original contrast data, the original contrast data may be stored in the first storage device. The original contrast data is stored in a first storage device in a unified data form (for example, raw data or an imaging sequence, etc.), and the first storage device can be a hard disk or a memory, etc. The subsequent computer device may retrieve the raw contrast data from the first storage device. In the case where the raw angiographic data is a raw angiographic image, the computer device may convert the raw angiographic data to obtain the raw angiographic image.

Step 202, normalizing the original angiography data.

After acquiring the original angiography data, the computer device may normalize the original angiography data. Optionally, the computer device may also filter out noise in the original angiographic data.

And 203, inputting the original angiography data into a vascular reconstruction model to obtain a target vascular image.

After the normalization processing is performed on the original angiography data, the computer device can input the normalized original angiography data into a vascular reconstruction model to obtain a target vascular image, wherein the target vascular image can be a frame image or an image sequence, and the image sequence forms a 3D image. By carrying out normalization processing on the original angiography data, the normalized original angiography data can be ensured to meet the input requirement of a vascular reconstruction model.

The vessel reconstruction model may be a deep neural network model. For example, the vessel reconstruction model may be a U-shaped recurrent neural network. The pixel values of all non-vascular areas in the original angiography data can be suppressed by adopting the vascular reconstruction model. The all non-vascular regions may include in vivo non-vascular regions and in vitro non-vascular regions of the scanned subject, and the in vivo non-vascular regions may include at least one or more of regions of bone, calcification, coil, and metal clip. The non-vascular region in the body may include at least one or more of a region in which the couch plate is located, a region in which the patch is located, a region in which the metal is located, a region in which the catheter is located, a region in which the wire is located, and a region in which the head anchor is located. The metal may be a metallic foreign body. The area where the patch is located may be an area where the electrode patch is located, and the area where the catheter is located is an area where the catheter inserted into the scanning object is located.

The target blood vessel image may be a gray scale image, and the pixel value of the blood vessel region in the target blood vessel image is greater than the pixel value of the first non-blood vessel region in the target blood vessel image, that is, the brightness of the blood vessel region in the target blood vessel image is higher, and the brightness of the first non-blood vessel region is lower. And the difference value between the pixel value of the blood vessel region in the target blood vessel image and the pixel value of the first non-blood vessel region is larger than a difference threshold, namely the contrast ratio between the blood vessel region in the target blood vessel image and the first non-blood vessel region is higher.

The first non-blood vessel region refers to a region in which the pixel value of the non-blood vessel region of the target blood vessel image is smaller than the pixel value of the blood vessel region, and the first non-blood vessel region can be all non-blood vessel regions in the target blood vessel image or part of non-blood vessel regions in the target blood vessel image.

Optionally, the pixel value of the first non-vascular region in the target vascular image is smaller than the second preset value, in this case, the pixel value of the first non-vascular region in the target vascular image is lower, and the first non-vascular region in the displayed target vascular image is hardly visible at this time, so that the display of the second non-vascular region in the target vascular image is effectively inhibited, the vascular definition in the displayed target vascular image is ensured to be higher, and the contrast ratio between the vascular region and the first non-vascular region in the target vascular image is ensured to be higher.

In the following, the method for determining a target blood vessel image based on a blood vessel reconstruction model provided by the embodiment of the present invention is referred to as a scheme S1, and in the related art, in one implementation manner (i.e., the scheme S2), a computer device may register and subtract an original contrast image and an original non-contrast image, so as to obtain the target blood vessel image.

It can be seen from fig. 3 that the target blood vessel image determined using the scheme S1 can achieve the same effect as the target blood vessel image determined using the scheme S2.

As can be seen from fig. 4, the circled area in the target vessel image determined by the scheme S2 has a higher bone brightness, and the circled area is an area where the registration of the original contrast image and the original non-contrast image is poor. Whereas the brightness of the bones of the circled area in the target vessel image determined by the scheme S1 is lower. It can be seen that the target vessel image determined using scheme S1 is superior to the target vessel image determined using scheme S2.

By adopting the method for determining the target blood vessel image, provided by the embodiment of the invention, the original contrast data can be obtained by only enhancing CT scanning once, and the target blood vessel image with obviously enhanced pixel values of the blood vessel region and obviously inhibited pixel values of the first non-blood vessel region can be reconstructed based on the original contrast data. Moreover, the target blood vessel image is superior to the target blood vessel image reconstructed by adopting the scheme S2, so that the contrast ratio of a blood vessel region and a first non-blood vessel region is enhanced, secondary scanning is effectively avoided, the scanning time length is shortened, the scanning efficiency is improved, and the radiation dose to a scanning object is reduced.

In another implementation (i.e., scenario S3), the computer device may segment the original contrast image to remove bone structures and obtain the target vessel image.

As can be seen from fig. 5, the soft tissue brightness of the circled area in the target vessel image determined using the scheme S3 is high. Whereas the brightness of the bones of the circled area in the target vessel image determined by the scheme S1 is lower. It can be seen that the target blood vessel image determined using the scheme S1 is superior to the target blood vessel image determined using the scheme S3.

Compared with the scheme S3, the method provided by the embodiment of the invention has the advantages that the display of the blood vessels in the target blood vessel image is clearer, the display of the tiny blood vessels is more complete, and the cutting effect of the blood vessel edges or bone edges caused by segmentation does not exist.

In the embodiment of the invention, the computer equipment can acquire a plurality of sample data and train the plurality of sample data to obtain the vascular reconstruction model.

Each sample data may include sample original angiography data and a sample target vascular image, where a pixel value of a vascular region in the sample target vascular image is greater than a pixel value of a non-vascular region in the sample target vascular image, and the sample target vascular image is obtained by performing registration subtraction on the sample original angiography data and sample original non-angiography data corresponding to the sample original angiography data. And, the registration deviation of the original angiography data of the sample and the original non-angiography data of the sample is smaller than a first preset value, which can be stored in advance in the computer device.

In case the sample raw angiography data is the sample raw angiography data, the raw angiography data in step 201 is the raw angiography data. In case the sample raw angiographic data is a sample raw angiographic image, the raw angiographic data in step 201 is a raw angiographic image.

It will be appreciated that in acquiring the sample raw angiographic data, and the sample raw non-contrast data corresponding to the sample raw angiographic data, since two scans of the sample scan object are required, if the sample scan object moves during scanning of the sample raw angiographic data or the sample raw non-contrast data, there is a registration deviation between the sample raw angiographic data and the sample raw non-contrast data during registration. And the larger the amplitude of the sample scan object motion, the larger the registration deviation.

In the embodiment of the invention, in the process of constructing the vascular reconstruction model, the registration deviation of the adopted sample original angiography data and the sample original non-angiography data is smaller than a first preset value, namely, the registration deviation of the sample original angiography data and the sample original non-angiography data is smaller, so that the accuracy of the constructed vascular reconstruction model can be ensured.

Step 204, if there is an optimizable second non-vascular region in the target vascular image, decreasing the pixel value of the second non-vascular region.

After the computer equipment processes all the non-vascular regions in the original angiography data through the vascular reconstruction model to obtain a target vascular image, the pixel values of part of the non-vascular regions in the target vascular image are still higher due to the fact that the inhibition processing of the non-vascular regions in the original angiography data is not thorough by adopting the vascular reconstruction model, so that whether an optimizable second non-vascular region exists in the target vascular image can be detected. If there is an optimizable second non-vascular region in the target vascular image, the pixel values of the second non-vascular region may be reduced, in which case the first non-vascular region is a partial non-vascular region in the target vascular image. If there is an optimizable second non-vascular region in the target vascular image, step 205 may be performed, in which case the first non-vascular region is all non-vascular regions in the target vascular image.

The pixel value of the blood vessel region in the target blood vessel image is smaller than or equal to the pixel value of the second non-blood vessel region before processing, and the pixel value of the blood vessel region in the target blood vessel image is larger than the pixel value of the second non-blood vessel region after processing. The difference between the pixel values of the blood vessel region in the target blood vessel image and the pixel values of the processed second non-blood vessel region is less than a difference threshold. The second non-vascular region may comprise an optimizable in vivo non-vascular region and an optimizable in vitro non-vascular region, i.e. the second non-vascular region comprises a region of the target vessel image which is to be further optimized in all non-vascular regions.

After the target blood vessel image is obtained based on the blood vessel reconstruction model, the pixel value of the optimized second non-blood vessel region is reduced, so that the pixel value of the blood vessel region in the target blood vessel image is larger than the pixel value of the processed second non-blood vessel region, the brightness of all the non-blood vessel regions in the target blood vessel image can be ensured to be lower, and the contrast ratio of the blood vessel region and the non-blood vessel region in the target blood vessel image is ensured to be higher.

And after the pixel value of the second non-blood vessel region in the target blood vessel image is reduced, the pixel value of the second non-blood vessel region in the target blood vessel image is smaller than a second preset value. In this case, the pixel value of the non-blood vessel region in the target blood vessel image is low, and the second non-blood vessel region in the displayed target blood vessel image is hardly visible at this time, so that the display of the second non-blood vessel region in the target blood vessel image is effectively suppressed, the higher blood vessel definition in the displayed target blood vessel image is ensured, and the higher contrast between the blood vessel region and the second non-blood vessel region in the target blood vessel image is ensured.

In the embodiment of the invention, the computer equipment can input the target blood vessel image into the optimized non-blood vessel region determining model so as to obtain the optimized second non-blood vessel region in the target blood vessel image output by the optimized non-blood vessel region determining model.

The computer device may acquire a plurality of first training data, each first training data may include a sample target blood vessel image and an optimizable non-blood vessel region in the sample target blood vessel image, and train the plurality of first training data to obtain an optimizable non-blood vessel region determination model. The optimizable non-vascular region in each sample target vessel image may include at least one of a couch plate region, a patch region, a metal region, and a bone region.

Step 205, acquiring an angiography image, and inputting the angiography image and the target vessel image into a vessel segmentation model to obtain a vessel segmentation result.

After the pixel value of the second non-vascular region is reduced, the computer device may acquire an angiographic image, and input the angiographic image and the target vascular image into a vascular segmentation model, to obtain a vascular segmentation result.

Wherein the angiographic image may be a computed tomography angiographic (computed topography angiography, CTA) image. Only blood vessels are displayed in the blood vessel segmentation result, and the pixel value of only blood vessels is larger than 0 and the pixel value of non-blood vessels is 0.

The vessel segmentation model may be a deep neural network model, which may be trained using a plurality of second training data, each of which may include a sample target vessel image, a sample angiographic image, and a sample vessel segmentation result corresponding to the sample target vessel image and the sample angiographic image.

Referring to fig. 6, the computer device may fuse the sample target blood vessel image and the sample angiography image to obtain a fused image shown in fig. 6, a yellow region in the fused image is a blood vessel in the sample target blood vessel image, and the computer device may extract a sample blood vessel segmentation result from the fused image in response to the blood vessel segmentation operation. Wherein the vessel segmentation operation may be a selection operation for a key point of a vessel in the fused image. The key points of the blood vessel are selected based on the fusion image, so that the difficulty in selecting the key points of the blood vessel can be reduced, the accuracy in selecting the key points of the blood vessel is ensured, and the accuracy of the constructed blood vessel segmentation model is further ensured.

Referring to fig. 7, the computer device may input a target blood vessel image 01 and an angiographic image 02 into the blood vessel segmentation model 10, resulting in a blood vessel segmentation result 03 output by the blood vessel segmentation model 10. Wherein different colors in the vessel segmentation result 03 characterize different types of vessels.

Optionally, after inputting the angiographic image and the target vessel image into the vessel segmentation model to obtain a vessel segmentation result, the computer device may further optimize the vessel segmentation result by using a conventional morphological algorithm and a threshold algorithm through the target vessel image, thereby ensuring continuity of vessels in the vessel segmentation result, and then may perform vessel measurement and analysis based on the optimized vessel segmentation result.

Optionally, the computer device may extract a vessel centerline based on the vessel segmentation result, perform a vessel curved plane reconstruction (Curved Planar Reformation, CPR) analysis, measure a vessel parameter, and the like, and based on the vessel segmentation result, the accuracy of the analysis result may be improved.

In the embodiment of the invention, the target blood vessel image can be independently loaded to a post-processing application for examination and visualization. After determining the target vessel image, the computer device may employ a post-processing 3D or multi-planar reconstruction (multiplanar reformation, MPR) application to load display the target vessel image, thereby displaying the contrast vessel in a clear manner by Virtual Reality (VR) techniques or maximum intensity projection (maximum intensity projection, MIP) techniques. The combination of the cutting tool, the bounding box tool or the cross line rotating tool and the like can facilitate a doctor to check a target blood vessel from an optimal position and quickly screen the vascular diseases.

Referring to fig. 8, the computer device may display the target blood vessel image using VR technology loading, wherein the three gray scale images on the left are images of the target blood vessel image in the transverse, sagittal and coronal positions, and the color image on the right is the VR image of the target blood vessel image. Referring to fig. 9, the computer device may load and display a target blood vessel image using MIP technology, and the image shown in fig. 9 is a MIP map of the target blood vessel image.

In the embodiment of the invention, the doctor can also extract the blood vessel based on the image obtained by fusing the angiographic image and the target blood vessel image, thereby reducing the post-processing operation of blood vessel extraction.

The computer device may also print the target area of the target vessel image according to batch parameters preset by the user. And automatically displaying images of the target blood vessel image at a plurality of angles according to the number of sheets, so that one-key film typesetting and report printing are facilitated. FIG. 10 is a batch VR visualization result with a preset number of patches of 4 and a 360 degree rotation angle, taken from a Willis loop area vessel.

The computer device (hereinafter, may be referred to as a first computer device) that performs steps 201 to 204 and the computer device (hereinafter, may be referred to as a second computer device) that performs step 205 may be the same device or may be different devices.

In the case where the first computer device and the second computer device are different devices, the first computer device may store the target blood vessel image into the second storage device after determining the target blood vessel image. Thereafter, the second computer device may obtain the target vessel image from the second storage device and perform step 205.

The target blood vessel image determined by the embodiment of the invention can be sent to a post-processing workstation (namely a second computer device), and the post-processing workstation can perform blood vessel inspection, extraction and analysis based on the target blood vessel image. Through visualization, a doctor can be assisted to read the film quickly, the vascular lesions are screened, and batch display and report printing are performed according to preset parameters of a user. The reconstructed vascular sequence is exported to post-processing applications for vascular disease examination and analysis of vascular indices.

In summary, the embodiment of the present invention provides a method for reconstructing a blood vessel, in which after acquiring original angiography data, a computer device may input the original angiography data into a vascular reconstruction model to obtain a target vascular image. Wherein the pixel value of the blood vessel region in the target blood vessel image is greater than the pixel value of the first non-blood vessel region in the target blood vessel image. I.e. the computer device can reconstruct a target vessel image based on the original angiographic data with significantly enhanced pixel values of the vessel region and significantly suppressed pixel values of the first non-vessel region. And the original angiography data can be obtained only through single scanning, compared with the related art, the method has the advantages of effectively avoiding secondary scanning, shortening the scanning time, improving the scanning efficiency and reducing the radiation dose to a scanned object.

An embodiment of the present invention provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the vascular reconstruction method described in the above embodiment. Such as the vascular reconstruction method shown in fig. 1 or fig. 2.

Fig. 11 is a schematic structural diagram of a computer device according to an embodiment of the present invention, and as shown in fig. 11, the computer device may include a memory 1101, a processor 1102, and a computer program stored in the memory 1101 and executable on the processor 1102, where the processor 1102 executes the computer program to implement the vascular reconstruction method described in the foregoing embodiment. Such as the vascular reconstruction method shown in fig. 1 or fig. 2.

Fig. 12 is a block diagram of a vascular reconstruction device according to an embodiment of the present invention, as shown in fig. 12, the device includes:

an acquisition module 1202 for acquiring raw angiography data;

a processing module 1203, configured to input the original angiography data into a vascular reconstruction model, so as to obtain a target vascular image;

Wherein the pixel value of the blood vessel region in the target blood vessel image is greater than the pixel value of the first non-blood vessel region in the target blood vessel image.

Optionally, the acquiring module 1202 is further configured to:

Acquiring a plurality of sample data, wherein each sample data comprises sample original angiography data and sample target angiography images, the pixel value of a vascular region in each sample target angiography image is larger than that of a non-vascular region in each sample target angiography image, and each sample target angiography image is obtained by registering and subtracting the sample original angiography data and the sample original non-angiography data corresponding to the sample original angiography data;

Training a plurality of sample data to obtain a vascular reconstruction model.

Optionally, the registration deviation of the sample raw angiographic data from the sample raw non-angiographic data is smaller than a first preset value.

Optionally, the processing module 1203 is further configured to:

If the optimized second non-vascular region exists in the target vascular image, reducing the pixel value of the second non-vascular region;

The pixel value of the blood vessel region in the target blood vessel image is smaller than or equal to the pixel value of the second non-blood vessel region before processing, and the pixel value of the blood vessel region in the target blood vessel image is larger than the pixel value of the second non-blood vessel region after processing.

Optionally, the processing module 1203 is further configured to:

Acquiring an angiographic image;

And inputting the angiography image and the target vessel image into a vessel segmentation model to obtain a vessel segmentation result.

Optionally, the processing module 1203 is further configured to:

normalization processing is carried out on the original angiography data.

In summary, the embodiment of the present invention provides a vascular reconstruction device, which can input original angiography data into a vascular reconstruction model after acquiring the original angiography data, so as to obtain a target vascular image. Wherein the pixel value of the blood vessel region in the target blood vessel image is greater than the pixel value of the first non-blood vessel region in the target blood vessel image. I.e. the computer device can reconstruct a target vessel image based on the original angiographic data with significantly enhanced pixel values of the vessel region and significantly suppressed pixel values of the first non-vessel region. And the original angiography data can be obtained only through single scanning, compared with the related art, the method has the advantages of effectively avoiding secondary scanning, shortening the scanning time, improving the scanning efficiency and reducing the radiation dose to a scanned object.

It should be noted that the logic and/or steps represented in the flowcharts or otherwise described herein, for example, may be considered as a ordered listing of executable instructions for implementing logical functions, and may be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include an electrical connection (an electronic device) having one or more wires, a portable computer diskette (a magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.

It is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of techniques known in the art, discrete logic circuits with logic gates for implementing logic functions on data signals, application specific integrated circuits with appropriate combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.

In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings are merely for convenience in describing the present invention and simplifying the description, and do not indicate or imply that the device or element being referred to must have a specific orientation, be configured and operated in a specific orientation, and therefore should not be construed as limiting the present invention.

Furthermore, the terms "first," "second," and the like, as used in embodiments of the present invention, are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or as implying any particular number of features in the present embodiment. Thus, a feature of an embodiment of the invention that is defined by terms such as "first," "second," etc., may explicitly or implicitly indicate that at least one such feature is included in the embodiment. In the description of the present invention, the word "plurality" means at least two or more, for example, two, three, four, etc., unless explicitly defined otherwise in the embodiments.

In the present invention, unless explicitly stated or limited otherwise in the examples, the terms "mounted," "connected," and "fixed" as used in the examples should be interpreted broadly, e.g., the connection may be a fixed connection, a removable connection, or an integral, it should be understood that the connection may be a mechanical connection, an electrical connection, or the like, or of course, the connection may be direct, or indirect, through an intermediary, or may be a communication between two elements, or an interaction relationship between two elements. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art according to specific embodiments.

In the present invention, unless expressly stated or limited otherwise, a first feature "up" or "down" a second feature may be the first and second features in direct contact, or the first and second features in indirect contact via an intervening medium. Moreover, a first feature being "above," "over" and "on" a second feature may be a first feature being directly above or obliquely above the second feature, or simply indicating that the first feature is level higher than the second feature. The first feature being "under", "below" and "beneath" the second feature may be the first feature being directly under or obliquely below the second feature, or simply indicating that the first feature is less level than the second feature.

While embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the invention, and that variations, modifications, alternatives and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the invention.

Claims (10)

1. A method of revascularization, the method comprising:

Acquiring original angiography data;

inputting the original angiography data into a vascular reconstruction model to obtain a target vascular image;

wherein, the pixel value of the blood vessel area in the target blood vessel image is larger than the pixel value of the first non-blood vessel area in the target blood vessel image.

2. The method according to claim 1, wherein the method further comprises:

Acquiring a plurality of sample data, wherein each sample data comprises sample original angiography data and a sample target angiography image, the pixel value of a vascular region in the sample target angiography image is larger than that of a non-vascular region in the sample target angiography image, and the sample target angiography image is obtained by registering and subtracting the sample original angiography data and the sample original non-angiography data corresponding to the sample original angiography data;

training a plurality of sample data to obtain the vascular reconstruction model.

3. The method of claim 2, wherein a registration deviation of the sample raw angiographic data from the sample raw non-angiographic data is less than a first preset value.

4. A method according to any one of claims 1 to 3, wherein the method further comprises:

if the optimized second non-blood vessel region exists in the target blood vessel image, reducing the pixel value of the second non-blood vessel region;

The pixel value of the blood vessel region in the target blood vessel image is smaller than or equal to the pixel value of the second non-blood vessel region before processing, and the pixel value of the blood vessel region in the target blood vessel image is larger than the pixel value of the second non-blood vessel region after processing.

5. The method of claim 4, wherein the pixel values of the first non-vascular region and the pixel values of the second non-vascular region in the target vascular image are both less than a second preset value.

6. A method according to any one of claims 1 to 3, wherein the method further comprises:

Acquiring an angiographic image;

inputting the angiography image and the target blood vessel image into a blood vessel segmentation model to obtain a blood vessel segmentation result.

7. A method according to any one of claims 1 to 3, wherein the method further comprises:

and normalizing the original angiography data.

8. A computer-readable storage medium, characterized in that a computer program is stored thereon, which computer program, when being executed by a processor, implements the vascular reconstruction method according to any one of claims 1 to 7.

9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the vascular reconstruction method according to any one of claims 1 to 7 when the computer program is executed by the processor.

10. A vascular reconstruction device, the device comprising:

the acquisition module is used for acquiring original angiography data;

the processing module is used for inputting the original angiography data into a vascular reconstruction model to obtain a target vascular image;

wherein, the pixel value of the blood vessel area in the target blood vessel image is larger than the pixel value of the first non-blood vessel area in the target blood vessel image.