Vascular reconstruction method and device and computer equipment

Abstract

The invention discloses a blood vessel reconstruction method and device and computer equipment, and relates to the technical field of image processing. After the computer equipment obtains original angiography data, the original angiography data can be input into the blood vessel reconstruction model, and a target blood vessel image is obtained. 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. According to the method, the computer equipment can reconstruct the target blood vessel image of which the pixel value of the blood vessel region is remarkably enhanced and the pixel value of the first non-blood vessel region is remarkably suppressed based on the original angiography data. And the original angiography data can be obtained only through single scanning, so that compared with the related technology, secondary scanning is effectively avoided, the scanning time is shortened, the scanning efficiency is improved, and the radiation dose of the scanned object is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to a blood vessel reconstruction method and device, and computer equipment. Background Art

[0002] Computed tomography (CT) equipment usually needs to continuously acquire images of blood vessels without contrast agent enhancement and images of blood vessels with contrast agent enhancement, so that the computer equipment can suppress non-vascular tissues such as bones and muscles in the images of blood vessels without contrast agent enhancement through registration subtraction technology, so as to enhance the contrast between non-vascular areas and vascular areas in the images of blood vessels without contrast agent enhancement, thereby achieving high-definition imaging of blood vessels.

[0003] However, since it is necessary to obtain images of blood vessels without contrast agent enhancement and images of blood vessels after contrast agent enhancement, the scan object needs to be scanned multiple times, resulting in a long scanning time, low efficiency, and a large radiation dose to the scanned patient. Summary of the invention

[0004] The present invention provides a blood vessel reconstruction method and device, and a computer device, which can solve the problem in the related art that the scanning object needs to be scanned multiple times, resulting in a long scanning time, low efficiency, and a large radiation dose to the scanned patient. The technical solution is as follows:

[0005] In one aspect, a method for vascular reconstruction is provided, the method comprising:

[0006] Obtaining raw angiography data;

[0007] Inputting the original angiography data into the vascular reconstruction model to obtain the target vascular image;

[0008] 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.

[0009] Optionally, the method further includes:

[0010] Acquire multiple sample data, each sample data includes sample original angiography data and a sample target blood vessel image, the pixel value of the blood vessel area in the sample target blood vessel image is greater than the pixel value of the non-blood vessel area in the sample target blood vessel image, and the sample target blood vessel image is obtained by registering and subtracting the sample original angiography data and the sample original non-contrast data corresponding to the sample original angiography data;

[0011] A vascular reconstruction model is obtained by training multiple sample data.

[0012] Optionally, a registration deviation between the sample original angiography data and the sample original non-angiography data is less than a first preset value.

[0013] Optionally, the method further includes:

[0014] If there is a second non-blood vessel area that can be optimized in the target blood vessel image, reducing the pixel value of the second non-blood vessel area;

[0015] The pixel value of the blood vessel area in the target blood vessel image is less than or equal to the pixel value of the second non-blood vessel area before processing, and the pixel value of the blood vessel area in the target blood vessel image is greater than the pixel value of the second non-blood vessel area after processing.

[0016] Optionally, the method further includes:

[0017] Obtaining angiographic images;

[0018] The angiography image and the target blood vessel image are input into the blood vessel segmentation model to obtain the blood vessel segmentation result.

[0019] Optionally, the method further includes:

[0020] The original angiography data were normalized.

[0021] On the other hand, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the blood vessel reconstruction method described in the above aspect is implemented.

[0022] On the other hand, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the vascular reconstruction method described in the above aspects is implemented.

[0023] In another aspect, a vascular reconstruction device is provided, comprising:

[0024] An acquisition module, used for acquiring original angiography data;

[0025] A processing module, used for inputting the original angiography data into the vascular reconstruction model to obtain a target vascular image;

[0026] 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.

[0027] In summary, the embodiments of the present invention provide a blood vessel reconstruction method and apparatus, and a computer device. After acquiring the original angiography data, the computer device can input the original angiography data into the 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. Moreover, the original angiography data can be obtained with only a single scan. Compared with the related art, it effectively avoids secondary scanning, shortens the scanning time, improves the scanning efficiency, and reduces the radiation dose to the scanned object.

[0028] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 is a flow chart of a blood vessel reconstruction method provided by an embodiment of the present invention;

[0030] Figure 2 is a flow chart of another vascular reconstruction method provided by an embodiment of the present invention;

[0031] Figure 3 is a comparison diagram of a solution S1 and a solution S2 provided in an embodiment of the present invention;

[0032] Figure 4 is a comparison diagram of another solution S1 and solution S2 provided in an embodiment of the present invention;

[0033] Figure 5 is a comparison diagram of a solution S1 and a solution S3 provided in an embodiment of the present invention;

[0034] Figure 6 is a schematic diagram of a fused image provided by an embodiment of the present invention;

[0035] Figure 7 is a schematic diagram of obtaining a blood vessel segmentation result based on a blood vessel segmentation model provided by an embodiment of the present invention;

[0036] Figure 8 is a schematic diagram of a target blood vessel image provided by an embodiment of the present invention;

[0037] Fig. 9 is a schematic diagram of another target blood vessel image provided by an embodiment of the present invention;

[0038] Fig.10 is a schematic diagram of a target processed image for batch printing provided by an embodiment of the present invention;

[0039] Fig.11 is a structural schematic diagram of a computer device provided by an embodiment of the present invention;

[0040] Fig.12 It is a block diagram of a blood vessel reconstruction device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0041] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.

[0042] Computed tomography angiography (CTA) and computed tomography venography (CTV) are non-invasive imaging technologies that play an important role in the diagnosis of vascular disease progression with their unique technical advantages. Through high-precision X-ray tomography and advanced image processing technology, CTA / CTV can clearly display the fine structure and pathological conditions inside the blood vessels, including the thickness of the blood vessel wall, the formation of plaques, and the degree of stenosis. This enables doctors to accurately determine the type and degree of vascular disease and provides a strong basis for patients to develop personalized treatment plans. CTA / CTV has fast scanning speed and high imaging efficiency, which greatly improves the efficiency of diagnosis and treatment and reduces the waiting time and discomfort of patients. The fast imaging process also means that doctors can obtain diagnostic results faster, so as to formulate treatment plans in time and gain valuable treatment time for patients. In addition, CTA / CTV uses advanced scanning equipment and image processing algorithms to create high-quality three-dimensional vascular images, intuitively showing the morphology, direction and blood flow of blood vessels. These detailed image information not only helps doctors accurately diagnose vascular diseases, but also provides precise guidance for surgical navigation and interventional treatments.

[0043] The grayscale intensity of bones and enhanced blood vessels in CTA images / CTV images is similar, which restricts the visualization and accurate analysis of blood vessels. Currently, CT-digital subtraction angiography (DSA) is an advanced medical imaging examination method that combines DSA and CT technology. During the CTA / CTV scanning process, the CT device needs to continuously obtain the image series of blood vessels without contrast agent enhancement and the image of blood vessels after contrast agent enhancement. After that, the computer equipment can use the subtraction technology to suppress the non-vascular tissues such as bones and muscles in the image of blood vessels without contrast agent enhancement, so as to enhance the contrast between non-vascular areas and vascular areas in the image of blood vessels without contrast agent enhancement, and realize high-definition imaging of blood vessels. Through the enhanced image of blood vessels without contrast agent enhancement, the direction, morphology and pathological conditions of blood vessels can be intuitively seen.

[0044] Figure 1 is a flow chart of a blood vessel reconstruction method provided by an embodiment of the present invention, which is applied to a computer device such as Figure 1 As shown, the method includes:

[0045] Step 101: Acquire original angiography data.

[0046] The computer device may obtain original angiography data. The original angiography data may be original angiography data obtained by reconstructing the radiation attenuation signal of the scanned part of the target object using the CT enhanced scanning technology of the CT device, which retains the complete CT examination scanning information. Alternatively, the original angiography data may be an image obtained by converting the original angiography data, which may be referred to as an original angiography image.

[0047] Step 102: Input the original angiography data into the vascular reconstruction model to obtain a target vascular image.

[0048] After acquiring the original angiography data, the computer device can input the original angiography data into the blood vessel reconstruction model to obtain the target blood vessel image.

[0049] 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. The first non-blood vessel area refers to an area in the non-blood vessel area of ​​the target blood vessel image where the pixel value is less than the pixel value of the blood vessel area. The first non-blood vessel area may be all non-blood vessel areas in the target blood vessel image or part of the non-blood vessel areas in the target blood vessel image.

[0050] In summary, an embodiment of the present invention provides a blood vessel reconstruction method, in which a computer device can input the original angiography data into a blood vessel reconstruction model after acquiring the original angiography data to obtain a target blood vessel image. 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 computer device can reconstruct a target blood vessel image in which the pixel value of the blood vessel region is significantly enhanced and the pixel value of the first non-blood vessel region is significantly suppressed based on the original angiography data. Moreover, the original angiography data can be obtained with only a single scan. Compared with the related art, the secondary scan is effectively avoided, the scanning time is shortened, the scanning efficiency is improved, and the radiation dose to the scanned object is reduced.

[0051] Figure 2 is a flow chart of another vascular reconstruction method provided by an embodiment of the present invention, which is applied to a computer device, such as Figure 2 As shown, the method may include:

[0052] Step 201: Acquire original angiography data.

[0053] The computer device may obtain original angiography data. The original angiography data may be original angiography data obtained by reconstructing the radiation attenuation signal of the scanned part of the target object using the CT enhanced scanning technology of the CT device, which retains the complete CT examination scanning information. Alternatively, the original angiography data may be an image obtained by converting the original angiography data, which may be referred to as an original angiography image.

[0054] Optionally, the original angiography data may be a data sequence, and correspondingly, the original angiography image may be an image sequence, that is, the original angiography image includes a plurality of slice images, and the plurality of slice images constitute a 3-dimensional (dimension, D) image. Alternatively, the original angiography data may be a frame of data, and correspondingly, the original angiography image may be a frame of image.

[0055] In an embodiment of the present invention, after the CT device scans and obtains the original angiography data, the original angiography data can be stored in a first storage device. The original angiography data is stored in the first storage device in a unified data form (for example, raw data or imaging sequence, etc.), and the first storage device can be a hard disk or a memory, etc. A subsequent computer device can obtain the original angiography data from the first storage device. In the case where the original angiography data is an original angiography image, the computer device can convert the original angiography data to obtain an original angiography image.

[0056] Step 202: normalize the original angiography data.

[0057] After acquiring the original angiography data, the computer device may perform normalization processing on the original angiography data. Optionally, the computer device may also filter out noise in the original angiography data.

[0058] Step 203: input the original angiography data into the blood vessel reconstruction model to obtain a target blood vessel image.

[0059] After normalizing the original angiography data, the computer device can input the normalized original angiography data into the vascular reconstruction model to obtain a target vascular image, which can be a frame image or an image sequence, and the image sequence constitutes a 3D image. By normalizing the original angiography data, it can be ensured that the normalized original angiography data meets the input requirements of the vascular reconstruction model.

[0060] Among them, the vascular reconstruction model can be a deep neural network model. For example, the vascular reconstruction model can be a U-shaped regression neural network. The vascular reconstruction model can be used to suppress the pixel values ​​of all non-vascular areas in the original angiography data. All non-vascular areas can include the in vivo non-vascular areas and the in vitro non-vascular areas of the scanned object, and the in vivo non-vascular areas can at least include one or more of the areas where bones are located, the areas where calcifications are located, the areas where coils are located, and the areas where metal clips are located. The in vitro non-vascular areas can at least include: the areas where the bed board is located, the areas where the patches are located, the areas where the metal is located, the areas where the catheters are located, the areas where the wires are located, and the areas where the head fixator is located. One or more. The metal can be a metal foreign body. The area where the patch is located can be the area where the electrode patch is located, and the area where the catheter is located is the area where the catheter inserted into the scanned object is located.

[0061] The target blood vessel image may be a grayscale 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. In addition, the difference 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 greater than the difference threshold, that is, the contrast between the blood vessel region in the target blood vessel image and the first non-blood vessel region is higher.

[0062] The first non-vascular area refers to an area in the non-vascular area of ​​the target vascular image where the pixel value is smaller than the pixel value of the vascular area. The first non-vascular area may be all non-vascular areas in the target vascular image or part of the non-vascular areas in the target vascular image.

[0063] Optionally, the pixel value of the first non-vascular area in the target vascular image is less than a second preset value. In this case, the pixel value of the first non-vascular area in the target vascular image is low, and the first non-vascular area in the displayed target vascular image is almost invisible, thereby effectively suppressing the display of the second non-vascular area in the target vascular image, ensuring that the blood vessels in the displayed target vascular image have high clarity, and further ensuring that the contrast between the blood vessel area and the first non-vascular area in the target vascular image is high.

[0064] The method for determining a target blood vessel image based on a blood vessel reconstruction model provided in an embodiment of the present invention is hereinafter referred to as Scheme S1. In the related art, in one implementation method (i.e., Scheme S2), a computer device may register and subtract an original contrast image and an original non-contrast image to obtain a target blood vessel image.

[0065] from Figure 3 It can be seen that the target blood vessel image determined by scheme S1 can achieve the same effect as the target blood vessel image determined by scheme S2.

[0066] from Figure 4 It can be seen that the bone brightness of the circled area in the target blood vessel image determined by solution S2 is higher, and the circled area is the area where the original contrast image and the original non-contrast image are poorly registered. However, the bone brightness of the circled area in the target blood vessel image determined by solution S1 is lower. It can be seen that the target blood vessel image determined by solution S1 is better than the target blood vessel image determined by solution S2.

[0067] By adopting the method for determining the target blood vessel image provided by the embodiment of the present invention, only a single enhanced CT scan is required to obtain the original angiography data, and based on the original angiography data, a target blood vessel image in which the pixel value of the blood vessel region is significantly enhanced and the pixel value of the first non-blood vessel region is significantly suppressed can be reconstructed. Moreover, the target blood vessel image is superior to the target blood vessel image reconstructed by the scheme S2, thereby effectively avoiding a second scan while enhancing the contrast between the blood vessel region and the first non-blood vessel region, shortening the scanning time, improving the scanning efficiency, and reducing the radiation dose to the scanned object.

[0068] In the related art, in another implementation (ie, solution S3), a computer device may segment the original angiography image to remove the bone structure and obtain a target blood vessel image.

[0069] from Figure 5 It can be seen that the soft tissue brightness of the circled area in the target blood vessel image determined by solution S3 is higher, while the bone brightness of the circled area in the target blood vessel image determined by solution S1 is lower. It can be seen that the target blood vessel image determined by solution S1 is better than the target blood vessel image determined by solution S3.

[0070] Compared with solution S3, the blood vessels in the target blood vessel image determined by the method provided in the embodiment of the present invention are displayed more clearly, small blood vessels are displayed more completely, and there is no cutting effect of blood vessel edges or bone edges caused by segmentation.

[0071] In the embodiment of the present invention, the computer device can acquire a plurality of sample data, and train the plurality of sample data to obtain a blood vessel reconstruction model.

[0072] Each sample data may include sample original angiography data and a sample target blood vessel image, the pixel value of the blood vessel area in the sample target blood vessel image is greater than the pixel value of the non-blood vessel area in the sample target blood vessel image, and the sample target blood vessel image is obtained by registering and subtracting the sample original angiography data and the sample original non-contrast data corresponding to the sample original angiography data. In addition, the registration deviation of the sample original angiography data and the sample original non-contrast data is less than a first preset value, and the computer device may pre-store the first preset value.

[0073] When the sample original angiography data is sample original angiography data, the original angiography data in step 201 is original angiography data. When the sample original angiography data is a sample original angiography image, the original angiography data in step 201 is an original angiography image.

[0074] It is understandable that in the process of acquiring the sample original angiography data and the sample original non-contrast data corresponding to the sample original angiography data, since the sample scanning object needs to be scanned twice, if the sample scanning object moves during the scanning of the sample original angiography data or the sample original non-contrast data, then during the registration process, there will be a registration deviation between the sample original angiography data and the sample original non-contrast data. And the greater the amplitude of the movement of the sample scanning object, the greater the registration deviation.

[0075] In an embodiment of the present invention, in the process of constructing a vascular reconstruction model, the registration deviation between the sample original angiography data and the sample original non-contrast data used is less than a first preset value, that is, the registration deviation between the sample original angiography data and the sample original non-contrast data is small, thereby ensuring the accuracy of the constructed vascular reconstruction model.

[0076] Step 204: If there is a second non-blood vessel area that can be optimized in the target blood vessel image, reduce the pixel value of the second non-blood vessel area.

[0077] After the computer device processes all non-vascular regions in the original angiography data through the vascular reconstruction model to obtain the target vascular image, the suppression of the non-vascular regions in the original angiography data by the vascular reconstruction model is not thorough enough, resulting in the pixel values ​​of some non-vascular regions in the target vascular image are still high, so it can be detected whether there is a second non-vascular region that can be optimized in the target vascular image. If there is a second non-vascular region that can be optimized in the target vascular image, the pixel value of the second non-vascular region can be reduced. In this case, the first non-vascular region is a part of the non-vascular region in the target vascular image. If there is a second non-vascular region that can be optimized in the target vascular image, step 205 can be performed. In this case, the first non-vascular region is all non-vascular regions in the target vascular image.

[0078] The pixel value of the blood vessel area in the target blood vessel image is less than or equal to the pixel value of the second non-blood vessel area before processing, and the pixel value of the blood vessel area in the target blood vessel image is greater than the pixel value of the second non-blood vessel area after processing. The difference between the pixel value of the blood vessel area in the target blood vessel image and the pixel value of the second non-blood vessel area after processing is less than the difference threshold. The second non-blood vessel area may include an in vivo non-blood vessel area that can be optimized and an in vitro non-blood vessel area that can be optimized, that is, the second non-blood vessel area includes an area that needs to be further optimized in all non-blood vessel areas in the target blood vessel image.

[0079] After the target vascular image is obtained based on the vascular reconstruction model, the pixel value of the optimizable second non-vascular area is reduced so that the pixel value of the vascular area in the target vascular image is greater than the pixel value of the processed second non-vascular area, thereby ensuring that the brightness of all non-vascular areas in the target vascular image is low, thereby ensuring that the contrast between the vascular area and the non-vascular area in the target vascular image is high.

[0080] After reducing the pixel value of the second non-blood vessel area in the target blood vessel image, the pixel value of the second non-blood vessel area in the target blood vessel image is less than the second preset value. In this case, the pixel value of the non-blood vessel area in the target blood vessel image is low, and the second non-blood vessel area in the displayed target blood vessel image is almost invisible, thereby effectively suppressing the display of the second non-blood vessel area in the target blood vessel image, ensuring that the blood vessel clarity in the displayed target blood vessel image is high, and further ensuring that the contrast between the blood vessel area and the second non-blood vessel area in the target blood vessel image is high.

[0081] In an embodiment of the present invention, the computer device may input the target blood vessel image into an optimizable non-blood vessel region determination model, thereby obtaining an optimizable second non-blood vessel region in the target blood vessel image output by the optimizable non-blood vessel region determination model.

[0082] The computer device may acquire a plurality of first training data, each of which 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-blood vessel region in each sample target blood vessel image may include at least one of a bed plate region, a patch region, a metal region, and a bone region.

[0083] Step 205: Acquire a blood vessel angiography image, and input the blood vessel angiography image and the target blood vessel image into a blood vessel segmentation model to obtain a blood vessel segmentation result.

[0084] After reducing the pixel value of the second non-vascular region, the computer device can obtain a blood vessel angiography image, and input the blood vessel angiography image and the target blood vessel image into a blood vessel segmentation model to obtain a blood vessel segmentation result.

[0085] The angiography image may be a computed tomography angiography (CTA) image. The blood vessel segmentation result only displays blood vessels, and in the blood vessel segmentation result, only the pixel value of the blood vessel is greater than 0, and the pixel value of non-blood vessel is 0.

[0086] The vascular 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 vascular image, a sample angiography image, and a sample vascular segmentation result corresponding to the sample target vascular image and the sample angiography image.

[0087] refer to Figure 6 , the computer device can fuse the sample target blood vessel image and the sample angiography image to obtain Figure 6 In the fused image shown, the yellow area in the fused image is a blood vessel in the sample target blood vessel image. The computer device can extract a sample blood vessel segmentation result from the fused image in response to a blood vessel segmentation operation. The blood vessel segmentation operation can be a selection operation for key points of the blood vessel in the fused image. Selecting the key points of the blood vessel based on the fused image can reduce the difficulty of selecting the key points of the blood vessel, ensure the accuracy of the selection of the key points of the blood vessel, and further ensure the accuracy of the constructed blood vessel segmentation model.

[0088] refer to Figure 7 The computer device can input the target blood vessel image 01 and the angiography image 02 into the blood vessel segmentation model 10 to obtain the blood vessel segmentation result 03 output by the blood vessel segmentation model 10. Different colors in the blood vessel segmentation result 03 represent different types of blood vessels.

[0089] Optionally, after the computer device inputs the angiography image and the target blood vessel image into the blood vessel segmentation model and obtains the blood vessel segmentation result, it can also use traditional morphological algorithms and threshold algorithms to optimize the blood vessel segmentation result through the target blood vessel image, thereby ensuring the continuity of the blood vessels in the blood vessel segmentation result, and then the blood vessel measurement and analysis can be performed based on the optimized blood vessel segmentation result.

[0090] Optionally, the computer device can extract the blood vessel centerline, perform blood vessel curved planar reconstruction (CPR) analysis and measure blood vessel parameters based on the blood vessel segmentation result, and the accuracy of the analysis result can be improved based on the blood vessel segmentation result.

[0091] In an embodiment of the present invention, the target vessel image can be loaded into a post-processing application separately for inspection and visualization. After determining the target vessel image, the computer device can use a post-processing 3D or multiplanar reconstruction (MPR) application to load and display the target vessel image, thereby clearly displaying the angiographic vessel through virtual reality (VR) technology or maximum intensity projection (MIP) technology. Combining tools such as resection, bounding box or crosshair rotation can facilitate doctors to inspect the target vessel from the best position and quickly screen for vascular diseases.

[0092] refer to Figure 8 , the computer device can use VR technology to load and display the target blood vessel image, where the three grayscale images on the left are the 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. Fig. 9 , the computer device can use MIP technology to load and display the target blood vessel image, Fig. 9 The image shown is a MIP image of the target blood vessel image.

[0093] In the embodiment of the present invention, the doctor can also extract the blood vessel based on the image obtained by merging the angiography image and the target blood vessel image, thereby reducing the post-processing operations of the blood vessel extraction.

[0094] The computer equipment can also print the target area of ​​the target blood vessel image according to the batch processing parameters preset by the user. The target blood vessel image is automatically displayed at multiple angles according to the number of films, which is convenient for one-click film typesetting and report printing. Fig.10 In order to intercept the blood vessels in the Willis circle area, the preset number of slices is 4 and the rotation angle is 360 degrees for batch processing VR visualization results.

[0095] It should be noted that the computer device executing steps 201 to 204 (hereinafter referred to as the first computer device) and the computer device executing step 205 (hereinafter referred to as the second computer device) may be the same device or different devices.

[0096] In the case where the first computer device and the second computer device are different devices, after determining the target blood vessel image, the first computer device may store the target blood vessel image in the second storage device. Afterwards, the second computer device may obtain the target blood vessel image from the second storage device and execute step 205.

[0097] The target vascular image determined by the embodiment of the present invention can be sent to a post-processing workstation (i.e., a second computer device), and the post-processing workstation can perform vascular inspection, extraction, and analysis based on the target vascular image. Visualization can assist doctors in quickly reading films, screening vascular lesions, and batch processing display and printing reports according to user preset parameters. The reconstructed vascular sequence is exported to a post-processing application for vascular disease inspection and vascular index analysis.

[0098] In summary, an embodiment of the present invention provides a blood vessel reconstruction method, in which a computer device can input the original angiography data into a blood vessel reconstruction model after acquiring the original angiography data to obtain a target blood vessel image. 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 computer device can reconstruct a target blood vessel image in which the pixel value of the blood vessel region is significantly enhanced and the pixel value of the first non-blood vessel region is significantly suppressed based on the original angiography data. Moreover, the original angiography data can be obtained with only a single scan. Compared with the related art, the secondary scan is effectively avoided, the scanning time is shortened, the scanning efficiency is improved, and the radiation dose to the scanned object is reduced.

[0099] An embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the vascular reconstruction method described in the above embodiment is implemented. For example, Figure 1 or Figure 2 The vascular reconstruction method is shown.

[0100] Fig.11 is a schematic diagram of the structure of a computer device provided by an embodiment of the present invention, such as Fig.11 As shown, 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. When the processor 1102 executes the computer program, the blood vessel reconstruction method described in the above embodiment is implemented. Figure 1 or Figure 2 The vascular reconstruction method is shown.

[0101] Fig.12 is a block diagram of a vascular reconstruction device provided by an embodiment of the present invention, such as Fig.12 As shown, the device comprises:

[0102] An acquisition module 1202 is used to acquire original angiography data;

[0103] Processing module 1203, used for inputting the original angiography data into the vascular reconstruction model to obtain a target vascular image;

[0104] 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.

[0105] Optionally, the acquisition module 1202 is further configured to:

[0106] Acquire multiple sample data, each sample data includes sample original angiography data and a sample target blood vessel image, the pixel value of the blood vessel area in the sample target blood vessel image is greater than the pixel value of the non-blood vessel area in the sample target blood vessel image, and the sample target blood vessel image is obtained by registering and subtracting the sample original angiography data and the sample original non-contrast data corresponding to the sample original angiography data;

[0107] A vascular reconstruction model is obtained by training multiple sample data.

[0108] Optionally, a registration deviation between the sample original angiography data and the sample original non-angiography data is less than a first preset value.

[0109] Optionally, the processing module 1203 is further configured to:

[0110] If there is a second non-blood vessel area that can be optimized in the target blood vessel image, reducing the pixel value of the second non-blood vessel area;

[0111] The pixel value of the blood vessel area in the target blood vessel image is less than or equal to the pixel value of the second non-blood vessel area before processing, and the pixel value of the blood vessel area in the target blood vessel image is greater than the pixel value of the second non-blood vessel area after processing.

[0112] Optionally, the processing module 1203 is further configured to:

[0113] Obtaining angiographic images;

[0114] The angiography image and the target blood vessel image are input into the blood vessel segmentation model to obtain the blood vessel segmentation result.

[0115] Optionally, the processing module 1203 is further configured to:

[0116] The original angiography data were normalized.

[0117] In summary, an embodiment of the present invention provides a vascular reconstruction device, which, after acquiring the original angiography data, can input the original angiography data into a vascular reconstruction model to obtain a target vascular image. Among them, the pixel value of the vascular area in the target vascular image is greater than the pixel value of the first non-vascular area in the target vascular image. That is, the computer device can reconstruct a target vascular image in which the pixel value of the vascular area is significantly enhanced and the pixel value of the first non-vascular area is significantly suppressed based on the original angiography data. Moreover, the original angiography data can be obtained with only a single scan. Compared with the related art, it effectively avoids secondary scanning, shortens the scanning time, improves the scanning efficiency, and reduces the radiation dose to the scanned object.

[0118] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection portion with one or more wirings (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0119] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0120] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0121] In the description of the present invention, it is to be understood that the terms “center”, “longitudinal”, “lateral”, “length”, “width”, “thickness”, “up”, “down”, “front”, “back”, “left”, “right”, “vertical”, “horizontal”, “top”, “bottom”, “inside”, “outside”, “clockwise”, “counterclockwise”, “axial”, “radial”, “circumferential”, etc., indicating orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0122] In addition, the terms "first", "second", etc. used in the embodiments of the present invention are only used for descriptive purposes and should not be understood as indicating or implying relative importance, or implicitly indicating the number of technical features indicated in the present embodiment. Therefore, the features defined by the terms "first", "second", etc. in the embodiments of the present invention can explicitly or implicitly indicate that the embodiment includes at least one of the features. In the description of the present invention, the word "multiple" means at least two or two or more, such as two, three, four, etc., unless otherwise clearly and specifically defined in the embodiments.

[0123] In the present invention, unless otherwise clearly specified or limited in the embodiments, the terms "installed", "connected", "connected" and "fixed" etc. in the embodiments should be understood in a broad sense. For example, the connection can be a fixed connection, a detachable connection, or an integrated connection. It can be understood that it can also be a mechanical connection, an electrical connection, etc.; of course, it can also be a direct connection, or an indirect connection through an intermediate medium, or it can be the internal connection of two elements, or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to the specific implementation situation.

[0124] In the present invention, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may mean that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. Moreover, a first feature being "above", "above" or "above" a second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. A first feature being "below", "below" or "below" a second feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is lower in level than the second feature.

[0125] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A method for vascular reconstruction, characterized in that: The method comprises: Obtaining raw angiography data; Inputting the original angiography data into a vascular reconstruction model to obtain a target vascular image; 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.

2. The method according to claim 1, characterized in that The method further comprises: Acquire a plurality of sample data, each of the sample data comprising sample original angiography data and a sample target vascular image, wherein the pixel value of the vascular region in the sample target vascular image is greater than the pixel value of the non-vascular region in the sample target vascular image, and the sample target vascular image is obtained by registering and subtracting the sample original angiography data and the sample original non-contrast data corresponding to the sample original angiography data; The blood vessel reconstruction model is obtained by training a plurality of the sample data.

3. The method according to claim 2, characterized in that The registration deviation between the sample original angiography data and the sample original non-angiography data is less than a first preset value.

4. The method according to any one of claims 1 to 3, characterized in that: The method further comprises: If there is a second non-blood vessel area that can be optimized in the target blood vessel image, reducing the pixel value of the second non-blood vessel area; The pixel value of the blood vessel area in the target blood vessel image is less than or equal to the pixel value of the second non-blood vessel area before processing, and the pixel value of the blood vessel area in the target blood vessel image is greater than the pixel value of the second non-blood vessel area after processing.

5. The method according to claim 4, characterized in that A pixel value of the first non-blood vessel area and a pixel value of the second non-blood vessel area in the target blood vessel image are both smaller than a second preset value.

6. The method according to any one of claims 1 to 3, characterized in that: The method further comprises: Obtaining angiographic images; The angiography image and the target blood vessel image are input into a blood vessel segmentation model to obtain a blood vessel segmentation result.

7. The method according to any one of claims 1 to 3, characterized in that: The method further comprises: The original angiography data is normalized.

8. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the blood vessel reconstruction method according to any one of claims 1 to 7 is implemented.

9. A computer device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the blood vessel reconstruction method according to any one of claims 1 to 7 is implemented.

10. A vascular reconstruction device, characterized in that: The device comprises: An acquisition module, used for acquiring original angiography data; A processing module, used for inputting the original angiography data into a blood vessel reconstruction model to obtain a target blood vessel image; 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.

Images