Vascular Image Segmentation Method, Electronic Device, and Storage Medium

Abstract

The present invention provides a method for vascular image segmentation, an electronic device, and a storage medium. The method for vascular image segmentation includes: obtaining a vascular image to be segmented; segmenting the vascular image to be segmented by using an adaptive threshold segmentation method to obtain a first vascular segmentation image; performing a first processing on the first vascular segmentation image to remove non-vascular regions in the first vascular segmentation image and obtain a second vascular segmentation image; repairing the second vascular segmentation image by using an adaptive region growing method to obtain a third vascular segmentation image; performing a second processing on the third vascular segmentation image to remove non-vascular regions in the third vascular segmentation image and obtain a vascular mask image; and performing a logical AND operation on the vascular mask image and the vascular image to be segmented to obtain a final vascular image. The present invention can effectively segment the vascular region, not only reducing the cumbersome operations of human-computer interaction, but also effectively improving the segmentation efficiency of the image.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and particularly relates to a method for segmenting blood vessel images, an electronic device, and a storage medium. Background Art

[0002] Vascular diseases, especially cardiovascular diseases, have become one of the main diseases threatening human life safety. During the operation, doctors use vascular imaging techniques to assist in diagnosing various vascular diseases, such as calcification, aortic dissection, aneurysm, etc.

[0003] Vascular imaging techniques include computed tomography angiography (CTA), magnetic resonance angiography (MRA), etc. The vascular imaging obtains three-dimensional images, which not only contain vascular tissues but also other tissues around the blood vessels (bones, fat, muscles, lung tissues, etc.), and cannot provide accurate diagnosis for doctors. Therefore, extracting the entire vascular region from the three-dimensional image and displaying the morphology of the blood vessels with three-dimensional display technology will improve the diagnostic accuracy of doctors.

[0004] Although there are already many vascular segmentation techniques, the vascular segmentation problem is still a very challenging task. Currently, the vascular segmentation methods mainly rely on manual and semi-automatic methods. The existing semi-automatic vascular segmentation methods can be roughly divided into two categories: top-down and bottom-up. The existing vascular segmentation methods mainly have the following problems:

[0005] 1. The manual vascular segmentation method requires a large amount of time and effort.

[0006] 2. The top-down semi-automatic segmentation method requires manual input of seed points as the starting condition, and then iteratively merges adjacent regions based on the target error to finally generate an image. Since this method requires manual input of seed point information and continuous interactive selection of seed points to achieve image segmentation, there will be manually uncontrollable errors in the segmentation results.

[0007] 3. The bottom-up semi-automatic segmentation method uses a tubular detection filter to segment blood vessels. Although this method does not require manual input of initialization information, it has a large computational cost, is greatly affected by noise, and cannot obtain a complete vascular structure in regions with low contrast. Summary of the Invention

[0008] The purpose of the present invention is to provide a method for segmenting blood vessel images, an electronic device, and a storage medium, which can effectively reduce the cumbersome operations of human-computer interaction and improve the image segmentation efficiency.

[0009] To achieve the above object, the present invention provides a method for segmenting blood vessel images, including:

[0010] Obtain a blood vessel image to be segmented;

[0011] The adaptive threshold segmentation method is used to segment the to-be-segmented blood vessel image to obtain a first blood vessel segmentation image;

[0012] The first blood vessel segmentation image is subjected to a first processing to remove non-blood vessel regions in the first blood vessel segmentation image, and a second blood vessel segmentation image is obtained;

[0013] The adaptive region growing method is used to repair the second blood vessel segmentation image to obtain a third blood vessel segmentation image;

[0014] The third blood vessel segmentation image is subjected to a second processing to remove non-blood vessel regions in the third blood vessel segmentation image, and a blood vessel mask image is obtained;

[0015] A logical AND operation is performed on the blood vessel mask image and the to-be-segmented blood vessel image to obtain a final blood vessel image.

[0016] Optionally, before segmenting the to-be-segmented blood vessel image by the adaptive threshold segmentation method, the blood vessel image segmentation method includes: selecting a plurality of key points on the to-be-segmented blood vessel image;

[0017] The step of segmenting the to-be-segmented blood vessel image by the adaptive threshold segmentation method includes:

[0018] Determining a first upper limit value and a first lower limit value according to the pixel values of the plurality of key points;

[0019] Segmenting the to-be-segmented blood vessel image according to the first upper limit value and the first lower limit value.

[0020] Optionally, the step of determining a first upper limit value and a first lower limit value according to the pixel values of the plurality of key points includes:

[0021] Statistically analyzing the pixel values of the plurality of key points to determine a maximum pixel value and a minimum pixel value;

[0022] Determining a first upper limit value and a first lower limit value according to the maximum pixel value and the minimum pixel value;

[0023] Among them, the calculation formulas for the first upper limit value and the first lower limit value are as follows:

[0024] T max1 =P max *(1+α)

[0025] T min1 =P min *(1-α)

[0026] In the formula, T max1 is the first upper limit value, Pmax The maximum pixel value, T min1 is the first lower limit value, P min is the minimum pixel value, α is the first adjustment factor, and the value of α ranges from 0 to 1.

[0027] Optionally, the first processing of the first vascular segmentation image to remove non-vascular regions in the first vascular segmentation image and obtain a second vascular segmentation image includes:

[0028] Performing a morphological erosion operation on the first vascular segmentation image to separate the vascular region from the non-vascular region;

[0029] Using the key point as a seed point, performing a connected component analysis on the first vascular segmentation image after the morphological erosion operation, and taking the connected component corresponding to the key point as the vascular region;

[0030] Performing a morphological dilation operation on the vascular region to obtain a second vascular segmentation image.

[0031] Optionally, the first processing of the first vascular segmentation image to remove non-vascular regions in the first vascular segmentation image and obtain a second vascular segmentation image includes:

[0032] Calculating the gradient of the vascular image to be segmented to obtain a gradient image;

[0033] Performing regression processing on strong edge pixel points and weak edge pixel points in the gradient image to obtain a first image;

[0034] Performing a logical AND operation on the first image and the first vascular segmentation image to obtain a second image;

[0035] Using the key point as a seed point, performing a connected component analysis on the second image to obtain a third image containing the vascular region, where the connected component corresponding to the key point is taken as the vascular region;

[0036] Performing a morphological dilation operation on the vascular region in the third image to obtain a fourth image;

[0037] Performing a logical AND operation on the fourth image and the first vascular segmentation image to obtain a second vascular segmentation image.

[0038] Optionally, the vascular image to be segmented is a CTA image, and the calculating the gradient of the vascular image to be segmented to obtain a gradient image includes:

[0039] Performing a truncation process on the vascular image to be segmented to adjust the pixel values of each pixel point in the vascular image to be segmented within a preset range;

[0040] Linearly scale the pixel values of the to-be-segmented blood vessel image after truncation processing to scale the pixel values of the to-be-segmented blood vessel image to the range of 0 - 255;

[0041] Perform gradient calculation on the to-be-segmented blood vessel image with pixel values scaled to the range of 0 - 255 to obtain a gradient image.

[0042] Optionally, the method of using the adaptive region growing method to repair the second blood vessel segmentation image to obtain a third blood vessel segmentation image includes:

[0043] Perform a logical AND operation on the second blood vessel segmentation image and the to-be-segmented blood vessel image to obtain a fifth image;

[0044] Respectively use the adaptive region growing method to repair the regions between every two adjacent key points in the fifth image;

[0045] Add the region growing results of each region to obtain a third blood vessel segmentation image.

[0046] Optionally, the method of respectively using the adaptive region growing method to repair the regions between every two adjacent key points in the second blood vessel segmentation image includes:

[0047] Determine a second upper limit value and a second lower limit value according to the pixel values of the multiple key points;

[0048] According to the second upper limit value and the second lower limit value, respectively use the region growing method to repair the regions between every two adjacent key points in the fifth image.

[0049] Optionally, the method of performing a second process on the third blood vessel segmentation image to remove non-blood vessel regions in the third blood vessel segmentation image includes:

[0050] Perform hole filling on the third blood vessel segmentation image;

[0051] Perform a morphological opening operation on the third blood vessel segmentation image after hole filling;

[0052] Perform connected component analysis on the third blood vessel segmentation image after the morphological opening operation to remove non-blood vessel regions.

[0053] To solve the above technical problems, the present invention also provides an electronic device, including a processor and a memory, and a computer program is stored on the memory. When the computer program is executed by the processor, the above-mentioned blood vessel image segmentation method is implemented.

[0054] To solve the above technical problems, the present invention further provides a readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the above-mentioned blood vessel image segmentation method is implemented.

[0055] Compared with the prior art, the blood vessel image segmentation method, electronic device and storage medium provided by the present invention have the following advantages: The present invention obtains a blood vessel image to be segmented; then uses an adaptive threshold segmentation method to segment the blood vessel image to be segmented to obtain a first blood vessel segmentation image; then performs a first process on the first blood vessel segmentation image to remove non-blood vessel regions in the first blood vessel segmentation image to obtain a second blood vessel segmentation image; then uses an adaptive region growing method to repair the second blood vessel segmentation image to obtain a third blood vessel segmentation image; then performs a second process on the third blood vessel segmentation image to remove non-blood vessel regions in the third blood vessel segmentation image to obtain a blood vessel mask image; finally, performs a logical AND operation on the blood vessel mask image and the blood vessel image to be segmented to obtain a final blood vessel image. It can be seen that the present invention can effectively segment the blood vessel region through the adaptive threshold segmentation method, the first process, the adaptive region growing method and the second process, which not only reduces the cumbersome operations of human-computer interaction, but also can effectively improve the image segmentation efficiency. In addition, the image segmentation algorithm of the present invention has strong versatility and realizes an end-to-end algorithm process, which can better assist doctors to improve the accuracy of diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 It is a schematic flowchart of the blood vessel image segmentation method in an embodiment of the present invention;

[0057] Figure 2 It is a schematic diagram of the selection positions of key points in a specific example of the present invention;

[0058] Figure 3a It is a schematic cross-sectional view of the blood vessel image to be segmented after preprocessing in a specific example of the present invention;

[0059] Figure 3b It is a schematic cross-sectional view of the first blood vessel segmentation image in a specific example of the present invention;

[0060] Figure 3c It is a schematic cross-sectional view of the gradient image in a specific example of the present invention;

[0061] Figure 3d It is a schematic cross-sectional view of the first image in a specific example of the present invention;

[0062] Figure 3e It is a schematic cross-sectional view of the second image in a specific example of the present invention;

[0063] Figure 3f Schematic cross-sectional view of the third image in a specific example of the present invention;

[0064] Figure 3g Schematic cross-sectional view of the fourth image in a specific example of the present invention;

[0065] Figure 3h Schematic cross-sectional view of the second blood vessel segmentation image in a specific example of the present invention;

[0066] Figure 4 Schematic display view of the final blood vessel image in a specific example of the present invention;

[0067] Figure 5 Schematic block diagram of an electronic device in an embodiment of the present invention;

[0068] Wherein, the reference numerals are as follows:

[0069] Key points - A, B, C, D, E, F;

[0070] Processor - 101; Communication interface - 102; Memory - 103; Communication bus - 104. Detailed implementation manners

[0071] The following further elaborates on the blood vessel image segmentation method, electronic device, and storage medium proposed by the present invention in conjunction with the appended Figures 1 to 5 drawings and specific implementation manners. According to the following description, the advantages and features of the present invention will be clearer. It should be noted that the drawings are in a very simplified form and all use non-precise scales, only for the purpose of facilitating and clearly assisting in explaining the embodiments of the present invention. In order to make the objectives, features, and advantages of the present invention more obvious and understandable, please refer to the drawings. It should be noted that the structures, scales, sizes, etc. shown in the drawings of this specification are only used to cooperate with the content disclosed in the specification for those skilled in this technology to understand and read, and are not used to limit the limiting conditions for the implementation of the present invention. Any modification of the structure, change in the proportional relationship, or adjustment of the size, in the case of being the same or similar to the effects that the present invention can produce and the objectives that can be achieved, should still fall within the scope covered by the technical content disclosed by the present invention.

[0072] It should be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprising", "including" or any other variant thereof are intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the element.

[0073] The core idea of the present invention is to provide a blood vessel image segmentation method, an electronic device and a storage medium, which can effectively reduce the cumbersome operations of human-computer interaction and improve the image segmentation efficiency.

[0074] It should be noted that the electronic device in the embodiment of the present invention may be a personal computer, a mobile terminal, etc., and the mobile terminal may be a hardware device such as a mobile phone, a tablet computer, etc. with various operating systems.

[0075] To achieve the above idea, the present invention provides a blood vessel image segmentation method. Please refer to Figure 1 , which schematically shows a flowchart of the blood vessel image segmentation method provided by an embodiment of the present invention. As Figure 1 shown, the blood vessel image segmentation method includes the following steps:

[0076] Step S100: Obtain the blood vessel image to be segmented.

[0077] In the present invention, the blood vessel image to be segmented may be a CTA (Computed Tomography Angiography) image, an MRA (Magnetic Resonance Angiography) image, or other medical images. The blood vessel image to be segmented can be collected by an image acquisition device, such as imaging devices like CT and MRI, can also be obtained by collecting through the Internet, or can be obtained by scanning with a scanning device. The size of the blood vessel image to be segmented can be set according to specific circumstances, and the present invention does not limit this. For example, the size of the blood vessel image to be segmented can be 512×512×130 pixels.

[0078] Step S200: Segment the blood vessel image to be segmented by using an adaptive threshold segmentation method to obtain a first blood vessel segmentation image.

[0079] Thus, by using the adaptive threshold segmentation method to segment the to-be-segmented blood vessel image, a first blood vessel segmentation image with a black background (pixel value of 0) and a target area (including the blood vessel area) being white (pixel value of 1) can be obtained.

[0080] Further, in order to improve the segmentation effect of the adaptive threshold segmentation, before performing step S200, the blood vessel image segmentation method further includes: selecting a plurality of key points on the to-be-segmented blood vessel image.

[0081] Correspondingly, the using of the adaptive threshold segmentation method to segment the to-be-segmented blood vessel image includes:

[0082] Determining a first upper limit value and a first lower limit value according to the pixel values of the plurality of key points;

[0083] Segmenting the to-be-segmented blood vessel image according to the first upper limit value and the first lower limit value.

[0084] Among them, the selection of the key points can be made according to the specific anatomical characteristics of the blood vessels to be segmented. For example, when the blood vessels to be segmented are aortic blood vessels, please refer to Figure 2 , which schematically shows a schematic diagram of the selection positions of the key points in a specific example of the present invention. As Figure 2 shown, according to the anatomical characteristics of the aortic blood vessels, six key points can be selected on the to-be-segmented blood vessel image, namely key point A, key point B, key point C, key point D, key point E, and key point F. Among them, key point A is near the ascending aorta, key point B is between the abdominal aorta and the common iliac artery, key point C is near the bifurcation of the left external iliac artery and the left internal iliac artery, key point D is near the bifurcation of the right external iliac artery and the right internal iliac artery, key point E is in the left femoral artery area, and key point F is in the right femoral artery area.

[0085] Thus, by calculating the first upper limit value and the first lower limit value according to the pixel values of the plurality of key points, and then according to the first upper limit value and the first lower limit value, setting the pixel points whose pixel values in the to-be-segmented blood vessel image are between the first upper limit value and the first lower limit value to white (i.e., setting the pixel value to 1), and setting the pixel points whose pixel values are less than the first lower limit value or greater than the first upper limit value to black (i.e., setting the pixel value to 0), a first blood vessel segmentation image with a black background and a target area (including the blood vessel area) being white can be obtained more simply and efficiently. In addition, by selecting a plurality of key points as initial conditions at one time to segment and extract the blood vessel area image, the present invention not only reduces the number of interactions, but also improves the overall segmentation efficiency.

[0086] Specifically, the determining of the first upper limit value and the first lower limit value according to the pixel values of the plurality of key points includes:

[0087] Statistically analyze the pixel values of the multiple key points to determine the maximum pixel value and the minimum pixel value;

[0088] Determine a first upper limit value and a first lower limit value according to the maximum pixel value and the minimum pixel value.

[0089] Among them, the calculation formulas for the first upper limit value and the first lower limit value are as follows:

[0090] T max1 = P max *(1 + α)

[0091] T min1 = P min *(1 - α)

[0092] In the formula, T max1 is the first upper limit value, P max is the maximum pixel value, T min1 is the first lower limit value, P min is the minimum pixel value, α is the first adjustment factor, and the value range of α is 0 to 1.

[0093] It should be noted that, as understood by those skilled in the art, the value of α can be set according to specific circumstances. For example, when the blood vessel image to be segmented is a CTA image, the value of α is 0.3. In addition, it should be noted that in the above calculation formulas for the first upper limit value and the first lower limit value, the pixel value of the key point refers to the pixel value of the key point in the blood vessel image to be segmented (preferably the preprocessed blood vessel image to be segmented). For example, when the blood vessel image to be segmented is a CTA image, the pixel value of the key point refers to the CT value of the key point in the CTA image, that is, the HU value.

[0094] In order to further improve the segmentation effect of the blood vessel image, before segmenting the blood vessel image to be segmented by using the adaptive threshold segmentation method, the blood vessel image segmentation method includes:

[0095] Preprocess the blood vessel image to be segmented to remove the noise information in the blood vessel image to be segmented.

[0096] Correspondingly, the specific step S200 is: Segment the preprocessed blood vessel image to be segmented by using the adaptive threshold segmentation method to obtain a first blood vessel segmentation image.

[0097] Thus, by preprocessing the blood vessel image to be segmented, the noise information in the blood vessel image to be segmented can be effectively removed, laying a good foundation for subsequent operations. Specifically, a Gaussian filter can be used to filter the blood vessel image to be segmented to remove the noise information in the blood vessel image to be segmented.

[0098] Please refer to Figure 3a and Figure 3b , where Figure 3a schematically shows a cross-sectional view of the preprocessed blood vessel image to be segmented in a specific example of the present invention; Figure 3b schematically shows a cross-sectional view of the first blood vessel segmentation image in a specific example of the present invention. As Figure 3a and Figure 3b shown, by performing the above preprocessing process on the blood vessel image to be segmented, different tissue organs can be more clearly highlighted, and the blood vessels can be more prominently displayed, thereby further improving the segmentation effect of adaptive threshold segmentation.

[0099] Step S300: Perform a first process on the first blood vessel segmentation image to remove the non-blood vessel regions in the first blood vessel segmentation image and obtain a second blood vessel segmentation image.

[0100] Specifically, in one embodiment, the performing a first process on the first blood vessel segmentation image to remove the non-blood vessel regions in the first blood vessel segmentation image and obtain a second blood vessel segmentation image includes:

[0101] Performing a morphological erosion operation on the first blood vessel segmentation image to separate the blood vessel region from the non-blood vessel region;

[0102] Taking the key point as a seed point, performing a connected component analysis on the first blood vessel segmentation image after the morphological erosion operation, and taking the connected component corresponding to the key point as the blood vessel region;

[0103] Performing a morphological dilation operation on the blood vessel region to obtain a second blood vessel segmentation image.

[0104] Thus, by performing a morphological erosion operation on the first vascular segmentation image, the connection between the vascular region and the non-vascular region (such as the bone region) can be completely disconnected. The morphological parameters of the morphological erosion operation can be set according to specific circumstances, for example, set to 5. By using the key points as seed points and performing a connected component analysis on the first vascular segmentation image after the morphological erosion operation, the non-vascular region can be further removed, and only the vascular region is retained. By performing a morphological dilation operation on the vascular region, the entire vascular region can be included, thereby obtaining a second vascular segmentation image containing the complete vascular region. The morphological parameters of the morphological dilation operation can be set according to specific circumstances, for example, set to 5.

[0105] In another embodiment, the first processing of the first vascular segmentation image to remove the non-vascular region in the first vascular segmentation image and obtain a second vascular segmentation image includes:

[0106] Calculating the gradient of the vascular image to be segmented to obtain a gradient image;

[0107] Performing regression processing on the strong edge pixel points and weak edge pixel points in the gradient image to obtain a first image;

[0108] Performing a logical AND operation on the first image and the first vascular segmentation image to obtain a second image;

[0109] Using the key points as seed points and performing a connected component analysis on the second image to obtain a third image containing the vascular region, where the connected component corresponding to the key points is used as the vascular region;

[0110] Performing a morphological dilation operation on the vascular region in the third image to obtain a fourth image;

[0111] Performing a logical AND operation on the fourth image and the first vascular segmentation image to obtain a second vascular segmentation image.

[0112] Specifically, a Gaussian convolution can be used to calculate the gradient of the vascular image to be segmented (preferably the preprocessed vascular image to be segmented). The Gaussian kernel parameters of the Gaussian convolution can be set according to specific circumstances, for example, can be set to 0.1. Thus, by calculating the gradient of the vascular image to be segmented (preferably the preprocessed vascular image to be segmented), the gradient value of each pixel point in the vascular image to be segmented (preferably the preprocessed vascular image to be segmented) can be calculated. Thus, the edges can be extracted according to the gradient values of each pixel point to obtain a gradient image. Please refer to Figure 3c , which schematically shows a cross-sectional view of the gradient image in a specific example of the present invention, as Figure 3cAs shown, by performing gradient calculation on the to-be-segmented blood vessel image (preferably the preprocessed to-be-segmented blood vessel image), the edge (i.e., contour) of the blood vessel can be effectively found. By performing regression processing on the strong edge pixel points and weak edge pixel points in the gradient image, that is, setting the strong edge pixel points to black (i.e., setting the pixel value to 0) and setting the weak edge pixel points to white (i.e., setting the pixel value to 1), a first image is obtained. Please refer to Figure 3d , which schematically shows a schematic diagram of the first image in a specific example of the present invention, as Figure 3d shown, by performing a logistic regression transformation on the gradient image, the contour boundary information of the blood vessel region can be further strengthened. Please continue to refer to Figure 3e , which schematically shows a schematic diagram of the second image in a specific example of the present invention. As Figure 3e shown, by performing a logical AND operation on the first image and the first blood vessel segmentation image (multiplying the pixel values of each pixel point in the first image by the pixel values of the corresponding pixel points in the first blood vessel segmentation image), non-blood vessel regions can be further removed. Please continue to refer to Figure 3f , which schematically shows a schematic diagram of the third image in a specific example of the present invention. As Figure 3f shown, by using key points as seed points and performing connected component analysis on the second image, non-blood vessel regions can be further removed while retaining the blood vessel region. Please continue to refer to Figure 3g , which schematically shows a schematic diagram of the fourth image in a specific example of the present invention. As Figure 3g shown, by performing a morphological dilation operation on the blood vessel region in the third image, the blood vessel region can be included. Among them, the morphological parameters of the morphological dilation operation can be set according to specific circumstances, for example, set to 5. Please continue to refer to Figure 3h , which schematically shows a schematic diagram of the second blood vessel segmentation image in a specific example of the present invention. As Figure 3h shown, by performing a logical AND operation on the fourth image and the first blood vessel segmentation image (multiplying the pixel values of each pixel point in the fourth image by the pixel values of the corresponding pixel points in the first blood vessel segmentation image), non-blood vessel regions can be further removed to further improve the segmentation effect of the blood vessel image segmentation method provided by the present invention and lay a good foundation for obtaining high-quality blood vessel images.

[0113] Further, when the to-be-segmented blood vessel image is a CTA image, the performing gradient calculation on the to-be-segmented blood vessel image to obtain a gradient image includes:

[0114] Perform a truncation process on the to-be-segmented blood vessel image (preferably the preprocessed to-be-segmented blood vessel image) to adjust the pixel values of each pixel point in the to-be-segmented blood vessel image to within a preset range;

[0115] Perform linear scaling on the pixel values of the to-be-segmented blood vessel image after the truncation process to scale the pixel values of the to-be-segmented blood vessel image to the range of 0 - 255;

[0116] Perform gradient calculation on the to-be-segmented blood vessel image whose pixel values are scaled to the range of 0 - 255 to obtain a gradient image.

[0117] Thus, by performing a truncation process on the to-be-segmented blood vessel image (preferably the preprocessed to-be-segmented blood vessel image), the pixel values of each pixel point in the to-be-segmented blood vessel image (preferably the preprocessed to-be-segmented blood vessel image) can be adjusted to within a preset range, such as within the range of 0 - 800. In specific operations, the pixel values of pixel points within the range of 0 - 800 can be kept unchanged, the pixel values of pixel points less than 0 can be set to 0, and the pixel values of pixel points greater than 800 can be set to 800. Finally, by performing linear scaling on the pixel values of the to-be-segmented blood vessel image after the truncation process, the pixel values of each pixel point in the to-be-segmented blood vessel image (preferably the preprocessed to-be-segmented blood vessel image) can be scaled to the range of 0 - 255. Specifically, the following formula can be used for linear scaling of pixel values:

[0118] P i '=(P i / 800)*255

[0119] In the formula, P i is the pixel value of pixel point i in the to-be-segmented blood vessel image (preferably the preprocessed to-be-segmented blood vessel image) after the truncation process, and P i ’ is the pixel value of the pixel point i in the to-be-segmented blood vessel image (preferably the preprocessed to-be-segmented blood vessel image) after linear scaling.

[0120] Step S400: Use the adaptive region growing method to repair the second blood vessel segmentation image to obtain a third blood vessel segmentation image.

[0121] Thus, by using the adaptive region growing method to repair the second blood vessel segmentation image, the segmentation effect of the blood vessel image segmentation method provided by the present invention can be further improved, laying a better foundation for obtaining a high-quality blood vessel image.

[0122] Specifically, the using the adaptive region growing method to repair the second blood vessel segmentation image to obtain a third blood vessel segmentation image includes:

[0123] Perform a logical AND operation on the second blood vessel segmentation image and the blood vessel image to be segmented to obtain a fifth image;

[0124] Use the adaptive region growing method to repair the region between every two adjacent key points in the fifth image respectively;

[0125] Add up the region growing results of each of the regions to obtain a third blood vessel segmentation image.

[0126] Thus, by performing a logical AND operation on the second blood vessel segmentation image and the blood vessel image to be segmented (preferably the preprocessed blood vessel image to be segmented) (multiplying the pixel values of each pixel point in the second blood vessel segmentation image by the pixel values of the corresponding pixel points in the blood vessel image to be segmented (preferably the preprocessed blood vessel image to be segmented)), the pixel values of each pixel point in the blood vessel region in the second blood vessel segmentation image can be replaced with the pixel values of the corresponding pixel points in the blood vessel image to be segmented (preferably the preprocessed blood vessel image to be segmented). By using the adaptive region growing method to repair the region between every two adjacent key points in the fifth image respectively to optimize the second blood vessel segmentation image, a third blood vessel segmentation image with a more refined and complete blood vessel region can be obtained. For example, when the positions of the multiple key points are as Figure 2 shown, use the adaptive region growing method to repair the regions between key point A and key point B, between key point B and key point C, between key point B and key point D, between key point C and key point E, and between key point D and key point F in the fifth image respectively.

[0127] The step of using the adaptive region growing method to repair the region between every two adjacent key points in the second blood vessel segmentation image respectively includes:

[0128] Determine a second upper limit value and a second lower limit value according to the pixel values of the multiple key points;

[0129] According to the second upper limit value and the second lower limit value, use the region growing method to repair the region between every two adjacent key points in the fifth image respectively.

[0130] Thus, by calculating the second upper limit value and the second lower limit value according to the pixel values of the multiple key points, and then using the region growing method to repair the region between every two adjacent key points in the fifth image respectively based on the second upper limit value and the second lower limit value (that is, merging the pixel points with pixel values between the second upper limit value and the second lower limit value together, and setting the pixel points with pixel values less than the second lower limit value or greater than the second upper limit value to black), it is possible to more simply and efficiently repair the region between every two adjacent key points in the fifth image by using the region growing method.

[0131] Determining the second upper limit value and the second lower limit value according to the pixel values of the multiple key points includes:

[0132] Statistically analyzing the pixel values of the multiple key points to determine the maximum pixel value and the minimum pixel value;

[0133] Determining the second upper limit value and the second lower limit value according to the maximum pixel value and the minimum pixel value;

[0134] Among them, the calculation formulas for the second upper limit value and the second lower limit value are as follows:

[0135] T max2 =P max *(1 + β)

[0136] T min2 =P min *(1 - β)

[0137] In the formula, T max2 is the second upper limit value, P max is the maximum pixel value, T min2 is the second lower limit value, P min is the minimum pixel value, β is the second adjustment factor, and the value range of β is 0 to 1.

[0138] It should be noted that, as can be understood by those skilled in the art, the value of β can be set according to specific situations. For example, when the to-be-segmented blood vessel image is a CTA image, the value of β is 0.2. In addition, it should be noted that the pixel values of the key points in the above calculation formulas for the second upper limit value and the second lower limit value refer to the pixel values of the key points in the to-be-segmented blood vessel image (preferably the preprocessed to-be-segmented blood vessel image). For example, when the to-be-segmented blood vessel image is a CTA image, the pixel values of the key points refer to the CT values in the CTA image, that is, HU values.

[0139] Step S500: Perform a second process on the third blood vessel segmentation image to remove the non-blood vessel regions in the third blood vessel segmentation image and obtain a blood vessel mask image.

[0140] Specifically, the second processing of the third vascular segmentation image to remove non-vascular regions in the third vascular segmentation image includes:

[0141] Performing hole filling on the third vascular segmentation image;

[0142] Performing morphological opening operation on the third vascular segmentation image after hole filling;

[0143] Performing connected component analysis on the third vascular segmentation image after morphological opening operation to remove non-vascular regions.

[0144] Since there may be some abnormal regions with hole regions inside blood vessels, these holes not connected to the boundary can be filled by the hole filling algorithm. By performing morphological opening operation on the third vascular segmentation image after hole filling, some boundary interferences can be effectively removed. Among them, the specific parameters of the morphological opening operation can be set according to specific situations, such as set to 1. By performing connected component analysis on the third vascular segmentation image after morphological opening operation, small interference regions (non-vascular regions) can be effectively removed, such as removing the bone regions close to the common iliac artery blood vessels, so as to obtain a more pure vascular mask image, further laying a foundation for obtaining high-quality vascular images.

[0145] Step S600: Performing a logical AND operation on the vascular mask image and the blood vessel image to be segmented to obtain the final blood vessel image.

[0146] Specifically, by multiplying the pixel values of each pixel point in the vascular mask image by the pixel values of the corresponding pixel points in the blood vessel image to be segmented (preferably the preprocessed blood vessel image to be segmented), the pixel values of each pixel point in the vascular region of the vascular mask image can be replaced by the pixel values of the corresponding pixel points in the blood vessel image to be segmented (preferably the preprocessed blood vessel image to be segmented), so as to obtain a clear and complete blood vessel image. Please refer to Figure 4 , which schematically shows a display schematic diagram of the final blood vessel image in a specific example of the present invention (displaying the blood vessel image from different levels), as Figure 4 shown, by adopting the blood vessel image segmentation method provided by the present invention, a blood vessel image with clear details and complete contours can be obtained, thus being able to better assist doctors and improve the accuracy of doctor diagnosis.

[0147] Based on the same inventive concept, the present invention also provides an electronic device. Please refer to Figure 5 , which schematically shows a block structure schematic diagram of the electronic device provided by an embodiment of the present invention. As Figure 5As shown, the electronic device includes a processor 101 and a memory 103. A computer program is stored on the memory 103. When the computer program is executed by the processor 101, the vascular image segmentation method described above is implemented.

[0148] As Figure 5 shown, the electronic device further includes a communication interface 102 and a communication bus 104. Among them, the processor 101, the communication interface 102, and the memory 103 complete mutual communication through the communication bus 104. The communication bus 104 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus 104 can be divided into an address bus, a data bus, a control bus, etc. For the sake of simplicity, only a thick line is used in the figure to represent it, but it does not mean that there is only one bus or one type of bus. The communication interface 102 is used for communication between the above-mentioned electronic device and other devices.

[0149] The processor 101 mentioned in the present invention may be a Central Processing Unit (CPU), or it may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The processor 101 is the control center of the electronic device, and connects various parts of the entire electronic device through various interfaces and lines.

[0150] The memory 103 can be used to store the computer program. The processor 101 realizes various functions of the electronic device by running or executing the computer program stored in the memory 103 and calling the data stored in the memory 103.

[0151] The memory 103 may include non-volatile and / or volatile memory. The non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. The volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct Rambus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0152] The present invention also provides a readable storage medium storing a computer program therein, and when the computer program is executed by a processor, the above-described blood vessel image segmentation method can be implemented.

[0153] The readable storage medium according to the embodiment of the present invention may adopt any combination of one or more computer-readable media. The readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may, for example, but not be limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (non-exhaustive list) of the computer-readable storage medium include: an electrical connection having one or more wires, a portable computer hard disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, the computer-readable storage medium may be any tangible medium that contains or stores a program, and the program can be used by or in combination with an instruction execution system, apparatus, or device.

[0154] The computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries the computer-readable program code. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium may also be any computer-readable medium other than the computer-readable storage medium, and the computer-readable medium can send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device.

[0155] Computer program code for performing the operations of the present invention may be written in one or more programming languages or combinations thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and also including conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0156] In summary, compared with the prior art, the vascular image segmentation method, electronic device, and storage medium provided by the present invention have the following advantages: The present invention obtains a vascular image to be segmented; then uses an adaptive threshold segmentation method to segment the vascular image to be segmented to obtain a first vascular segmentation image; then performs a first process on the first vascular segmentation image to remove non-vascular regions in the first vascular segmentation image to obtain a second vascular segmentation image; then uses an adaptive region growing method to repair the second vascular segmentation image to obtain a third vascular segmentation image; then performs a second process on the third vascular segmentation image to remove non-vascular regions in the third vascular segmentation image to obtain a vascular mask image; and finally performs a logical AND operation on the vascular mask image and the vascular image to be segmented to obtain a final vascular image. Thus, it can be seen that the present invention can effectively segment the vascular region through the adaptive threshold segmentation method, the first process, the adaptive region growing method, and the second process, not only reducing the cumbersome operations of human-computer interaction, but also effectively improving the image segmentation efficiency. In addition, the image segmentation algorithm of the present invention has strong versatility and realizes an end-to-end algorithm process, which can better assist doctors to improve the accuracy of diagnosis.

[0157] It should be noted that the devices and methods disclosed in the embodiments of this article can also be implemented in other ways. The device embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions, and operations of devices, methods, and computer program products according to multiple embodiments of this article. In this regard, each block in the flowchart or block diagram can represent a module, program, or part of code that contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, as well as the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0158] In addition, each functional module in the various embodiments of this article can be integrated together to form an independent part, or each module can exist separately, or two or more modules can be integrated to form an independent part.

[0159] The above description is only a description of the preferred embodiments of the present invention and does not limit the scope of the present invention in any way. Any changes and modifications made by those of ordinary skill in the art of the present invention based on the above disclosure belong to the protection scope of the present invention. Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations fall within the scope of the present invention and its equivalent technologies, the present invention also intends to include these modifications and variations.

Claims

1. A method for vascular image segmentation, characterized in that, Including: Obtain the blood vessel image to be segmented; Segment the blood vessel image to be segmented by using an adaptive threshold segmentation method to obtain a first blood vessel segmentation image; Perform a first processing on the first blood vessel segmentation image to remove non-blood vessel regions in the first blood vessel segmentation image and obtain a second blood vessel segmentation image; Repair the second blood vessel segmentation image by using an adaptive region growing method to obtain a third blood vessel segmentation image; Perform a second processing on the third blood vessel segmentation image to remove non-blood vessel regions in the third blood vessel segmentation image and obtain a blood vessel mask image; Perform a logical AND operation on the blood vessel mask image and the blood vessel image to be segmented to obtain a final blood vessel image; Before segmenting the blood vessel image to be segmented by using an adaptive threshold segmentation method, the blood vessel image segmentation method includes: selecting a plurality of key points on the blood vessel image to be segmented; The performing a first processing on the first blood vessel segmentation image to remove non-blood vessel regions in the first blood vessel segmentation image and obtain a second blood vessel segmentation image includes: Calculate the gradient of the blood vessel image to be segmented to obtain a gradient image; Perform regression processing on strong edge pixel points and weak edge pixel points in the gradient image to obtain a first image; Perform a logical AND operation on the first image and the first blood vessel segmentation image to obtain a second image; Use the key points as seed points and perform connected component analysis on the second image to obtain a third image including the blood vessel region, where the connected component corresponding to the key point is used as the blood vessel region; Perform a morphological dilation operation on the blood vessel region in the third image to obtain a fourth image; Perform a logical AND operation on the fourth image and the first blood vessel segmentation image to obtain a second blood vessel segmentation image.

2. The vascular image segmentation method according to claim 1, wherein The segmenting the blood vessel image to be segmented by using an adaptive threshold segmentation method includes: Determine a first upper limit value and a first lower limit value according to the pixel values of the plurality of key points; Segment the blood vessel image to be segmented according to the first upper limit value and the first lower limit value.

3. The vascular image segmentation method according to claim 2, wherein The determining a first upper limit value and a first lower limit value according to the pixel values of the plurality of key points includes: Statistically analyze the pixel values of the plurality of key points to determine the maximum pixel value and the minimum pixel value; Determine a first upper limit value and a first lower limit value according to the maximum pixel value and the minimum pixel value; Wherein, the calculation formulas of the first upper limit value and the first lower limit value are as follows: T max1 = P max *(1 + α) T min1 = P min *(1 - α) where T max1 is the first upper limit value, P max is the maximum pixel value, T min1 is the first lower limit value, P min is the minimum pixel value, α is the first adjustment factor, and the value range of α is 0 to 1.

4. The vascular image segmentation method according to claim 2, characterized in that The performing a first processing on the first blood vessel segmentation image to remove non-blood vessel regions in the first blood vessel segmentation image and obtain a second blood vessel segmentation image includes: Perform a morphological erosion operation on the first blood vessel segmentation image to separate the blood vessel region from the non-blood vessel region; Use the key points as seed points and perform connected component analysis on the first blood vessel segmentation image after the morphological erosion operation, and use the connected component corresponding to the key point as the blood vessel region; Perform a morphological dilation operation on the blood vessel region to obtain a second blood vessel segmentation image.

5. The vascular image segmentation method according to claim 1, characterized in that, The vascular image to be segmented is a CTA image. The gradient calculation of the vascular image to be segmented to obtain a gradient image includes: Performing truncation processing on the vascular image to be segmented to adjust the pixel values of each pixel point in the vascular image to be segmented within a preset range; Performing linear scaling on the pixel values of the truncated vascular image to be segmented to scale the pixel values of the vascular image to be segmented within the range of 0-255; Performing gradient calculation on the vascular image to be segmented with pixel values scaled to the range of 0-255 to obtain a gradient image.

6. The vascular image segmentation method according to claim 1, wherein Using the adaptive region growing method to repair the second vascular segmentation image to obtain a third vascular segmentation image, including: Performing a logical AND operation on the second vascular segmentation image and the vascular image to be segmented to obtain a fifth image; Respectively using the adaptive region growing method to repair the regions between every two adjacent key points in the fifth image; Adding the region growing results of each region to obtain a third vascular segmentation image.

7. The vascular image segmentation method according to claim 6, wherein The respective use of the adaptive region growing method to repair the regions between every two adjacent key points in the second vascular segmentation image includes: Determining a second upper limit value and a second lower limit value according to the pixel values of the multiple key points; Respectively using the region growing method to repair the regions between every two adjacent key points in the fifth image according to the second upper limit value and the second lower limit value.

8. The vascular image segmentation method according to claim 1, wherein Performing a second process on the third vascular segmentation image to remove non-vascular regions from the third vascular segmentation image, including: Performing hole filling on the third vascular segmentation image; Performing a morphological opening operation on the third vascular segmentation image after hole filling; Performing connected component analysis on the third vascular segmentation image after the morphological opening operation to remove non-vascular regions.

9. An electronic device, characterized in that, It includes a processor and a memory. A computer program is stored on the memory. When the computer program is executed by the processor, the method described in any one of claims 1 to 8 is implemented.

10. A readable storage medium, characterized in that, A computer program is stored in the readable storage medium. When the computer program is executed by the processor, the method described in any one of claims 1 to 8 is implemented.

Images