Blood vessel image segmentation method, device, equipment, medium and program product

Abstract

The invention relates to the field of medical image processing, and provides a blood vessel image segmentation method, device and equipment, a medium and a program product. The method comprises the following steps: acquiring a to-be-segmented blood vessel image; obtaining a plurality of blood vessel segmentation parameters in response to the parameter selection operation; and processing the to-be-segmented blood vessel image based on each blood vessel segmentation parameter to obtain a blood vessel image segmentation result. According to the method, the to-be-segmented blood vessel image is automatically processed through the plurality of blood vessel segmentation parameters obtained through the parameter selection operation of the user, so that the corresponding image segmentation result is obtained, and compared with a mode of manually removing an interference region, the operation is short in time consumption and high in operation efficiency.

Description

Technical Field

[0001] The present application relates to the technical field of medical image processing, and in particular to a method, device, equipment, medium and program product for segmenting a vascular image. Background Art

[0002] At present, in order to make a more intuitive observation of the vascular scanning data obtained based on the drug-free angiography method, it is usually necessary to use the maximum density projection technology to generate a three-dimensional perspective image corresponding to the vascular scanning data.

[0003] However, since there are often some interference areas in the vascular scanning data caused by the stacked fat tissue on the back, the skull, veins, eyeballs and other parts, before analyzing the vascular status represented by the three-dimensional perspective image, it is often necessary to manually remove the interference areas in the three-dimensional perspective image through multi-angle and multi-directional rotation and cropping operations. The overall operation process is time-consuming and has low operating efficiency. Summary of the invention

[0004] Based on this, it is necessary to provide a blood vessel image segmentation method, device, equipment, medium and program product with short time consumption and high operation efficiency to address the above technical problems.

[0005] In a first aspect, the present application provides a method for segmenting a blood vessel image, which includes: obtaining a blood vessel image to be segmented; obtaining a number of blood vessel segmentation parameters in response to a parameter selection operation; and processing the blood vessel image to be segmented based on each of the blood vessel segmentation parameters to obtain a blood vessel image segmentation result.

[0006] In one of the embodiments, in response to a parameter selection operation, a number of blood vessel segmentation parameters are obtained, including: displaying a parameter configuration interface; the parameter configuration interface includes a first configuration area and a second configuration area; in response to a scanning orientation configuration operation performed in the first configuration area, a number of image orientation configuration parameters are obtained; in response to a splitting form selection operation performed in the second configuration area, an image splitting indication parameter is obtained.

[0007] In one of the embodiments, the image segmentation indication parameter is used to determine the blood vessel location displayed in the blood vessel image segmentation result; in response to the scanning orientation configuration operation performed in the first configuration area, a number of image orientation configuration parameters are obtained, including: in response to the scanning orientation configuration operation performed in the first configuration area, a rotation angle configuration parameter corresponding to at least one scanning orientation is obtained, and the number of blood vessel image segmentations corresponding to the at least one scanning orientation is obtained.

[0008] In one of the embodiments, the scanning orientation includes at least one of a transverse axis, a sagittal axis, and a coronal axis; the processing of the vascular image to be segmented based on each of the vascular segmentation parameters to obtain a vascular image segmentation result includes: performing maximum density projection processing on the vascular image to be segmented based on the rotation angle configuration parameters to obtain the vascular image segmentation result corresponding to the number of vascular image segmentations.

[0009] In one of the embodiments, the obtaining of the blood vessel image to be segmented includes: inputting the preprocessed blood vessel scan image into a blood vessel segmentation network model to obtain a first segmentation result including segmentation masks corresponding to multiple target regions; wherein the segmentation mask includes a blood vessel segmentation mask and a region segmentation mask; based on each of the target regions, merging the blood vessel segmentation mask and the region segmentation mask in the first segmentation result after upsampling processing to obtain a second segmentation result; based on each of the target regions, splitting the second segmentation result to obtain the blood vessel image to be segmented.

[0010] In one embodiment, the vascular scanning image is composed of three-dimensional image data obtained by time-of-flight magnetic resonance angiography; the preprocessing includes at least one of downsampling processing and brightness normalization processing; the second segmentation result is split based on each of the target areas to obtain the vascular image to be segmented, including: based on each of the target areas, determining the area to be adjusted in the second segmentation result and the splitting range corresponding to the second segmentation result; setting the grayscale value of the area to be adjusted to the target value to obtain the second segmentation result after grayscale adjustment; splitting the second segmentation result after grayscale adjustment according to the splitting range to obtain the vascular image to be segmented.

[0011] In a second aspect, the present application also provides a vascular image segmentation device. The device includes: an image acquisition module to be segmented, used to acquire a vascular image to be segmented; a vascular segmentation parameter acquisition module, used to acquire a number of vascular segmentation parameters in response to a parameter selection operation; and a vascular image segmentation result output module, used to process the vascular image to be segmented based on each of the vascular segmentation parameters to obtain a vascular image segmentation result.

[0012] In a third aspect, the present application also provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program: obtaining a blood vessel image to be segmented; in response to a parameter selection operation, obtaining a number of blood vessel segmentation parameters; based on each of the blood vessel segmentation parameters, processing the blood vessel image to be segmented to obtain a blood vessel image segmentation result.

[0013] In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented: obtaining a blood vessel image to be segmented; in response to a parameter selection operation, obtaining a number of blood vessel segmentation parameters; and processing the blood vessel image to be segmented based on each of the blood vessel segmentation parameters to obtain a blood vessel image segmentation result.

[0014] In a fifth aspect, the present application also provides a computer program product. The computer program product includes a computer program, which implements the following steps when executed by a processor: obtaining a blood vessel image to be segmented; obtaining a number of blood vessel segmentation parameters in response to a parameter selection operation; and processing the blood vessel image to be segmented based on each of the blood vessel segmentation parameters to obtain a blood vessel image segmentation result.

[0015] The above-mentioned vascular image segmentation method, device, equipment, medium and program product automatically process the vascular image to be segmented through a number of vascular segmentation parameters obtained by the user's parameter selection operation, thereby obtaining the corresponding image segmentation result. Compared with the manual removal of interference areas, this operation is time-saving and has high operating efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a flow chart of a blood vessel image segmentation method in one embodiment;

[0017] Figure 2 A schematic diagram of a process for obtaining blood vessel segmentation parameters in one embodiment;

[0018] Figure 3 A schematic diagram of a parameter configuration interface in an embodiment;

[0019] Figure 4 A schematic diagram of a parameter configuration interface in another embodiment;

[0020] Figure 5 is a schematic diagram of a process for obtaining a blood vessel image to be segmented in one embodiment;

[0021] Figure 6 is a schematic diagram of a process of obtaining a blood vessel image to be segmented in another embodiment;

[0022] Figure 7 is a schematic diagram of performing blood vessel image segmentation in one embodiment;

[0023] Figure 8 is a schematic diagram of modules of a blood vessel image segmentation device in one embodiment;

[0024] Fig. 9 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0027] In one embodiment, Figure 1 As shown, a blood vessel image segmentation method is provided, and the method is applied to a computer device as an example for description, comprising the following steps:

[0028] Step S100, obtaining a blood vessel image to be segmented.

[0029] Specifically, the vascular images to be segmented include multiple original two-dimensional images after segmenting different types of vascular images. For example, when the vascular scan image is a vascular scan image of the transverse axis of the neck, each image may include a carotid artery image and a vertebral artery image. At this time, the carotid artery image and the vertebral artery image in each image are segmented to obtain multiple carotid artery images and multiple vertebral artery images, and use them as vascular images to be segmented. It can be understood that the vascular images to be segmented may include different types of vascular images and images of tissues surrounding the blood vessels, and it is better that the images of tissues surrounding the blood vessels do not affect the vascular images. By acquiring the vascular images to be segmented, different types of vascular images can be obtained after combining them in different ways.

[0030] Step S200, in response to the parameter selection operation, a number of blood vessel segmentation parameters are obtained.

[0031] Specifically, the user can perform parameter selection operations through the user operation interface, and the computer device will generate corresponding vascular segmentation parameters after detecting the corresponding operation. The vascular segmentation parameters are used to determine the orientation of the image display, the image segmentation form, etc. For example, the orientation of the image display can be a coronal cross section or a transverse cross section, etc., and the image segmentation form can be a vascular combination display or a vascular segmentation display, etc. It can be understood that each displayed image has a vascular segmentation parameter, so the number of vascular segmentation parameters can be multiple.

[0032] Step S300 : processing the blood vessel image to be segmented based on each blood vessel segmentation parameter to obtain a blood vessel image segmentation result.

[0033] Specifically, after obtaining the vascular segmentation parameters, the corresponding combination processing is performed according to the acquired image to be segmented according to the corresponding vascular segmentation parameters, so as to obtain the vascular image segmentation result that meets the vascular segmentation parameters. For example, the vascular segmentation parameters are set to the coronary carotid artery image. After screening out the corresponding image and processing it, the corresponding vascular image segmentation result, that is, the coronary carotid artery image, will be displayed. Compared with the operation of manually removing the interference area to observe the corresponding vascular image, the above operation takes less time and has high operation efficiency.

[0034] In one embodiment, Figure 2 As shown, in step S200, in response to the parameter selection operation, a number of blood vessel segmentation parameters are obtained, including:

[0035] Step S210, displaying a parameter configuration interface.

[0036] Specifically, when the computer device detects that the user wants to select parameters, the parameter configuration interface will be displayed on the user operation interface. For example, the user inputs a parameter configuration instruction through the user operation interface, and after the computer device detects the parameter configuration instruction, the corresponding parameter configuration interface will be displayed. The parameter configuration interface in this embodiment includes a first configuration area and a second configuration area, which are used to configure the scanning direction and the split form respectively.

[0037] Step S220: acquiring a number of image orientation configuration parameters in response to the scanning orientation configuration operation performed in the first configuration area.

[0038] Specifically, after the user performs a scanning orientation configuration operation in the first configuration area through the user operation interface, the computer device can obtain a number of image orientation configuration parameters, and the image orientation configuration parameters are used to determine the scanning orientation when the image is displayed.

[0039] Step S230: acquiring image splitting indication parameters in response to the splitting form selection operation performed in the second configuration area.

[0040] Specifically, after the user performs a splitting form selection operation in the second configuration area through the user operation interface, the computer device can obtain the corresponding image splitting indication parameter, and the image splitting indication parameter is used to determine the blood vessel part displayed in the blood vessel image segmentation result. For example, when the blood vessel image to be segmented includes a carotid artery image and a vertebral artery image of the neck, when the splitting form is split, the carotid artery image and the vertebral artery image are split and displayed as two images respectively, and when the splitting form is combined, the carotid artery image and the vertebral artery image are combined and displayed in one image.

[0041] In one embodiment, in step S220, in response to the scanning orientation configuration operation performed in the first configuration area, a number of image orientation configuration parameters are obtained, including: in response to the scanning orientation configuration operation performed in the first configuration area, a rotation angle configuration parameter corresponding to at least one scanning orientation and a number of blood vessel image segmentations corresponding to at least one scanning orientation are obtained.

[0042] Specifically, when the user configures the scanning orientation through the first configuration area in the parameter configuration interface, the computer device can obtain the rotation angle configuration parameters corresponding to the scanning orientation and the corresponding number of vascular image segmentations. In one embodiment, the scanning orientation includes at least one of the transverse axis, sagittal, and coronal positions, and the corresponding rotation angle configuration parameters can display the corresponding image with a certain rotation angle, and the image of each scanning orientation also has a corresponding number of vascular image segmentations. For example, the coronal image includes the image of the carotid artery and the image of the vertebral artery. At this time, the corresponding number of vascular image segmentations is 2.

[0043] Specific examples, such as Figure 3 As shown, it is a parameter configuration interface displayed in an embodiment, the first configuration area is the MIP area, which is used to perform scanning orientation configuration operations, wherein three buttons of transverse axis, sagittal and coronal are displayed, and the user can select at least one of them. The second configuration area is the smart cropping area, which is used to perform splitting form selection operations. Figure 3 In the image processing, the user selects the coronal position and the neck split. After the computer device obtains the corresponding image orientation configuration parameters and image split indication parameters, the coronary carotid artery image and the coronary vertebral artery image are displayed on the display interface. Figure 4As shown, it is a parameter configuration interface displayed in another embodiment. The user selects the coronary plane and the neck, indicating that the neck vascular image does not need to be split. At this time, only the coronary plane image of the neck is displayed, and the carotid artery and the vertebral artery are displayed in one image. In some other embodiments, the second configuration area can also be set to "display all". At this time, all the split and unsplit images of the coronary plane will be displayed. Through the vascular image segmentation method of the embodiment of the present application, the user can conveniently select the image to be displayed, and can split the display. Compared with the manual removal of interference areas, this operation takes less time and has high operating efficiency.

[0044] In one embodiment, in step S300, the vascular image to be segmented is processed based on each vascular segmentation parameter to obtain a vascular image segmentation result, including: based on the rotation angle configuration parameter, the vascular image to be segmented is subjected to maximum density projection processing to obtain a vascular image segmentation result corresponding to the number of vascular image segmentations.

[0045] Specifically, the rotation angle configuration parameter is used to determine the images with specific angles in the vascular images to be segmented that need to be screened out. For example, the rotation angle configuration parameter is set to screen out the vascular images in the coronary position. At this time, all the images collected from the coronary position are screened out from the vascular images to be segmented. Then, the screened images are subjected to maximum intensity projection (MIP) processing to obtain vascular image segmentation results corresponding to the number of vascular image segmentations. For example, the screened images collected in the coronary position include carotid artery images and vertebral artery images. At this time, the number of vascular image segmentations is 2, and the corresponding vascular image segmentation results are the coronary carotid artery images and the coronary vertebral artery images.

[0046] In one embodiment, Figure 5 As shown, in step S100, obtaining a blood vessel image to be segmented includes:

[0047] Step S110 , inputting the preprocessed blood vessel scanning image into a blood vessel segmentation network model to obtain a first segmentation result including segmentation masks corresponding to each of a plurality of target regions.

[0048] Specifically, the vascular scanning image can be an original image obtained by CT (Computed Tomography) or MR (Magnetic Resonance) scanning, which is generally a two-dimensional image in the transverse axial position. In one embodiment, the vascular scanning image is composed of three-dimensional image data obtained by time-of-flight magnetic resonance angiography (TOF-MRA). The vascular scanning image is then preprocessed so that the preprocessed image meets the image input requirements of the vascular segmentation network model. In one embodiment, the preprocessing includes at least one of downsampling processing and brightness normalization processing. Finally, the preprocessed vascular scanning image is input into the vascular segmentation network model to identify, classify and segment the vascular scanning image.

[0049] It is understandable that the training image of the neural network can be contrast agent dynamic enhanced vascular imaging, TOF image, etc.; the training of the neural network can adapt to vascular images of various orientations, and can adapt to contrast agent and non-contrast agent enhanced images. In one embodiment, the training samples include 3D contrast agent enhanced images and 3D TOF images (generated by 3D TOF sequence), so that the network model trained can process vascular enhanced images and TOF images. Optionally, considering the positional existence area of ​​3D contrast agent enhanced images and 3D TOF images, the image can be rotated. In one embodiment, considering that the TOF sequence is a 2DTOF sequence, the sample for model training selects 3DCEMRA (contrast agent enhanced image), and the contrast agent enhanced image can be rotated to a specific angle during the training process, and then the sample data and standard sample data are input for preprocessing to obtain multiple two-dimensional training samples; in the embodiment of the present application, the model trained by contrast agent enhanced samples can be applicable to non-contrast enhanced vascular images (2DTOF), and the training model has high accuracy in identifying blood vessels.

[0050] The blood vessel segmentation network model can adopt image segmentation models such as U-Net, V-Net and VB-Net, and the trained blood vessel segmentation network model can be obtained by training the corresponding image segmentation model with a pre-labeled training set. It can be understood that the blood vessel segmentation network model can segment different types of blood vessels and the surrounding areas where the blood vessels are located, so as to obtain a first segmentation result containing segmentation masks corresponding to multiple target areas, wherein the segmentation mask includes a blood vessel segmentation mask and a regional segmentation mask.

[0051] In one embodiment, the vascular segmentation network model can output the carotid artery region (excluding the carotid artery), the vertebral artery region (excluding the vertebral artery), the carotid artery and the vertebral artery. The vascular region and the region excluding the blood vessel are segmented separately, and the corresponding region is subsequently merged with the blood vessel for upsampling. In this case, the model training labels of the vascular segmentation network model include four labels: carotid artery, carotid artery region, vertebral artery, and vertebral artery region. The neural network is trained according to the correlation between the corresponding blood vessels and regions, and the model extracted by the training has higher stability. At this time, there are two target regions, namely the carotid artery region and the vertebral artery region. Correspondingly, the segmentation mask in the carotid artery region includes the carotid artery region segmentation mask (excluding the carotid artery) and the carotid artery segmentation mask, and the segmentation mask in the vertebral artery region includes the vertebral artery region segmentation mask (excluding the vertebral artery) and the vertebral artery segmentation mask.

[0052] Step S120 , based on each target region, the blood vessel segmentation mask and the region segmentation mask in the first segmentation result after upsampling processing are merged to obtain a second segmentation result.

[0053] Specifically, after obtaining the first segmentation result through the vascular segmentation network model, the first segmentation result is upsampled to restore and decode the abstract features to the size of the original image, and then the segmentation masks corresponding to the target area are merged to obtain a merged second segmentation result. For example, when the segmentation masks are the carotid artery region segmentation mask, the vertebral artery region segmentation mask, the carotid artery vessel segmentation mask, and the vertebral artery vessel segmentation mask, respectively, since the carotid artery region includes the carotid artery and the vertebral artery region includes the vertebral artery, the carotid artery region segmentation mask and the carotid artery vessel segmentation mask are merged into one carotid artery mask, and the vertebral artery region segmentation mask and the vertebral artery vessel segmentation mask are merged into one vertebral artery mask, thereby obtaining a merged second segmentation result. The segmentation mask in the second segmentation result only includes a larger carotid artery mask (including the carotid artery) and a vertebral artery mask (including the vertebral artery). It can be understood that in some other embodiments, the vascular segmentation network model can also directly output the carotid artery mask and the vertebral artery mask, and the segmentation masks do not need to be merged at this time. In this embodiment, by the step of merging the segmentation masks, a mature and well-trained blood vessel segmentation network model can be used, thereby improving the utilization rate of the model.

[0054] Step S130 : splitting the second segmentation result based on each target area to obtain a blood vessel image to be segmented.

[0055] Specifically, the second segmentation result is finally segmented according to each target area to obtain a vascular image to be segmented. For example, the merged second segmentation result includes a carotid artery mask and a vertebral artery mask, as well as a corresponding vascular scan image. The vascular scan image is segmented according to the carotid artery mask and the vertebral artery mask to obtain a vascular image to be segmented including an image of the area around the carotid artery and an image of the area around the vertebral artery.

[0056] In one embodiment, Figure 6 As shown, in step S130, based on each target area, the second segmentation result is segmented to obtain a blood vessel image to be segmented, including:

[0057] Step S131: Based on each target area, determine the area to be adjusted in the second segmentation result and the segmentation range corresponding to the second segmentation result.

[0058] Specifically, the second segmentation result includes a mask of the merged target area. At this time, the area to be adjusted in the second segmentation result and the segmentation range corresponding to the second segmentation result are determined in the blood vessel scanning image, and the segmentation range is related to the type of the target area. For example, the determined target area is the area around the carotid artery and the area around the vertebral artery. At this time, the area to be adjusted is the area outside these two areas, and the segmentation range is the range where the area around the carotid artery is located and the range where the area around the vertebral artery is located.

[0059] Step S132, setting the grayscale value of the area to be adjusted as the target value, and obtaining a second segmentation result after grayscale adjustment.

[0060] Specifically, after the area to be adjusted is determined, the grayscale value of the area to be adjusted is set as the target value, thereby obtaining the second segmentation result after grayscale adjustment. Generally, the target value is set to zero, at which time, except for the image in the target area, the other areas are all black.

[0061] Step S133 , segmenting the grayscale-adjusted second segmentation result according to the segmentation range to obtain a blood vessel image to be segmented.

[0062] Specifically, after the grayscale adjustment is completed, the second segmentation result is segmented according to the segmentation range to obtain the vascular image to be segmented. For example, the target area includes the area around the carotid artery and the area around the vertebral artery. At this time, the segmentation range is divided into the area around the carotid artery and the area around the vertebral artery. After the segmentation, the vascular image to be segmented including only the image around the carotid artery and the image around the vertebral artery can be obtained respectively.

[0063] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0064] The following is a detailed description of the image processing process in the blood vessel image segmentation method of the present application using a specific embodiment. Figure 7 As shown, the vascular scan image is a three-dimensional image data obtained by time-of-flight magnetic resonance angiography, and its size is: 512*466*259. First, the vascular scan image is downsampled to reduce its size to: 192*224*128, and then the brightness is normalized and input into the trained vascular segmentation network model, which is obtained by training the VB-NET neural network. After the vascular segmentation network model is processed, the first segmentation result is output, and the segmentation masks are the carotid artery region segmentation mask, the vertebral artery region segmentation mask, the carotid artery vascular segmentation mask and the vertebral artery vascular segmentation mask. Then, the first segmentation result is upsampled and the mask is merged to obtain a second segmentation result, which includes a carotid artery mask and a vertebral artery mask. Then, the area to be adjusted is determined by the second segmentation result, and the grayscale value of the area to be adjusted is set to 0, and then the obtained image is segmented according to the segmentation range of the carotid artery mask and the vertebral artery mask, so as to obtain a vascular image to be segmented including the area around the carotid artery and the area around the vertebral artery. Then, MIP is performed on multiple images of the area around the carotid artery and the area around the vertebral artery to obtain a reconstructed image, which is used as the vascular image segmentation result. Then, vascular images at different angles can be obtained through operations such as rotation. The user can input the corresponding operation instructions through the user operation interface, and the computer device will display the corresponding vascular image segmentation result after receiving the instructions.

[0065] Based on the same inventive concept, the embodiment of the present application also provides a vascular image segmentation device for implementing the vascular image segmentation method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more vascular image segmentation device embodiments provided below can refer to the limitations on the vascular image segmentation method above, and will not be repeated here.

[0066] In one embodiment, Figure 8 As shown, a blood vessel image segmentation device is provided, including: an image acquisition module 410 to be segmented, a blood vessel segmentation parameter acquisition module 420 and a blood vessel image segmentation result output module 430, wherein: the image acquisition module 410 to be segmented is used to acquire the blood vessel image to be segmented; the blood vessel segmentation parameter acquisition module 420 is used to obtain a number of blood vessel segmentation parameters in response to a parameter selection operation; the blood vessel image segmentation result output module 430 is used to process the blood vessel image to be segmented based on each blood vessel segmentation parameter to obtain a blood vessel image segmentation result.

[0067] In one embodiment, the blood vessel segmentation parameter acquisition module 420 is also used to display a parameter configuration interface; the parameter configuration interface includes a first configuration area and a second configuration area; in response to a scanning orientation configuration operation performed in the first configuration area, a number of image orientation configuration parameters are acquired; in response to a splitting form selection operation performed in the second configuration area, image splitting indication parameters are acquired.

[0068] In one embodiment, the image segmentation indication parameter is used to determine the blood vessel location displayed in the blood vessel image segmentation result; the blood vessel segmentation parameter acquisition module 420 is also used to respond to the scanning orientation configuration operation performed in the first configuration area, to obtain the rotation angle configuration parameter corresponding to at least one scanning orientation, and the number of blood vessel image segmentations corresponding to at least one scanning orientation.

[0069] In one embodiment, the scanning orientation includes at least one of the transverse axis, the sagittal axis, and the coronal axis; the vascular image segmentation result output module 430 is also used to perform maximum density projection processing on the vascular image to be segmented based on the rotation angle configuration parameters to obtain a vascular image segmentation result corresponding to the number of vascular image segmentations.

[0070] In one embodiment, the image acquisition module 410 to be segmented is also used to input the preprocessed blood vessel scan image into the blood vessel segmentation network model to obtain a first segmentation result including segmentation masks corresponding to multiple target areas; wherein the segmentation mask includes a blood vessel segmentation mask and a region segmentation mask; based on each target area, the blood vessel segmentation mask and the region segmentation mask in the first segmentation result after upsampling processing are merged to obtain a second segmentation result; based on each target area, the second segmentation result is split to obtain a blood vessel image to be segmented.

[0071] In one embodiment, the vascular scanning image is composed of three-dimensional image data obtained by time-of-flight magnetic resonance angiography; the preprocessing includes at least one of downsampling processing and brightness normalization processing; the image acquisition module 410 to be segmented is also used to set the grayscale value of the area to be adjusted to the target value to obtain a second segmentation result after grayscale adjustment; according to the segmentation range, the second segmentation result after grayscale adjustment is segmented to obtain the vascular image to be segmented.

[0072] Each module in the above-mentioned blood vessel image segmentation device can be implemented in whole or in part by software, hardware or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0073] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Fig. 9 As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a vascular image segmentation method is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a button, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0074] Those skilled in the art will understand that Fig. 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0075] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0076] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0077] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0078] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0079] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0080] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A blood vessel image segmentation method, characterized in that: The method comprises: Acquire a blood vessel image to be segmented; In response to the parameter selection operation, obtaining a number of blood vessel segmentation parameters; Based on each of the blood vessel segmentation parameters, the blood vessel image to be segmented is processed to obtain a blood vessel image segmentation result.

2. The method according to claim 1, characterized in that In response to the parameter selection operation, a number of blood vessel segmentation parameters are obtained, including: Displaying a parameter configuration interface; the parameter configuration interface includes a first configuration area and a second configuration area; In response to a scanning orientation configuration operation performed in the first configuration area, acquiring a number of image orientation configuration parameters; In response to the splitting form selection operation performed in the second configuration area, an image splitting indication parameter is obtained.

3. The method according to claim 2, characterized in that The image segmentation indication parameter is used to determine the blood vessel location displayed in the blood vessel image segmentation result; The step of acquiring a plurality of image orientation configuration parameters in response to the scanning orientation configuration operation performed in the first configuration area includes: In response to the scanning orientation configuration operation performed in the first configuration area, a rotation angle configuration parameter corresponding to at least one scanning orientation and a number of blood vessel image segmentations corresponding to the at least one scanning orientation are acquired.

4. The method according to claim 3, characterized in that The scanning orientation includes at least one of a transverse orientation, a sagittal orientation, and a coronal orientation; The step of processing the blood vessel image to be segmented based on each of the blood vessel segmentation parameters to obtain a blood vessel image segmentation result includes: Based on the rotation angle configuration parameter, maximum density projection processing is performed on the blood vessel image to be segmented to obtain the blood vessel image segmentation result corresponding to the number of blood vessel image segmentations.

5. The method according to any one of claims 1 to 4, characterized in that The step of acquiring the blood vessel image to be segmented comprises: Inputting the preprocessed blood vessel scan image into a blood vessel segmentation network model to obtain a first segmentation result including segmentation masks corresponding to a plurality of target regions, wherein the segmentation masks include a blood vessel segmentation mask and a region segmentation mask; Based on each of the target regions, respectively merging the blood vessel segmentation mask and the region segmentation mask in the first segmentation result after upsampling processing to obtain a second segmentation result; The second segmentation result is split based on each of the target areas to obtain the blood vessel image to be segmented.

6. The method according to claim 5, characterized in that The blood vessel scanning image is composed of three-dimensional image data obtained by time-of-flight magnetic resonance angiography; the preprocessing includes at least one of downsampling processing and brightness normalization processing; The step of splitting the second segmentation result based on each of the target regions to obtain the blood vessel image to be segmented includes: Based on each of the target areas, determining a region to be adjusted in the second segmentation result and a segmentation range corresponding to the second segmentation result; The grayscale value of the area to be adjusted is set to a target value to obtain a second segmentation result after grayscale adjustment; The grayscale-adjusted second segmentation result is segmented according to the segmentation range to obtain the blood vessel image to be segmented.

7. A blood vessel image segmentation device, characterized in that: The device comprises: An image acquisition module to be segmented is used to acquire a blood vessel image to be segmented; A blood vessel segmentation parameter acquisition module, used for acquiring a number of blood vessel segmentation parameters in response to a parameter selection operation; The blood vessel image segmentation result output module is used to process the blood vessel image to be segmented based on each of the blood vessel segmentation parameters to obtain a blood vessel image segmentation result.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images