Enhancement Method, Device, Equipment and Storage Medium for Vascular Images

Abstract

The present application relates to a method, device, equipment and storage medium for enhancing blood vessel images. The method includes: obtaining a blood vessel segmentation image corresponding to an original blood vessel image and a blood vessel segmentation probability map corresponding to the original blood vessel image; determining target blood vessel points to be enhanced in the original blood vessel image according to the eigenvalue of each blood vessel point in the blood vessel segmentation image and a preset threshold; enhancing the eigenvalue of the target blood vessel points according to the eigenvalue of the target blood vessel points and the blood vessel segmentation probability map to obtain an enhanced blood vessel image. By using this method, small blood vessels and the ends of blood vessels can be clearly displayed.

Description

Technical Field

[0001] The present application relates to the field of medical imaging technology, and in particular, to a method, apparatus, device, and storage medium for enhancing vascular images. Background Art

[0002] Currently, cardiovascular and cerebrovascular diseases still pose a great threat to human life. The diagnosis of cardiovascular and cerebrovascular diseases mainly relies on angiography images. Doctors can directly understand the shape and structure of blood vessels by observing angiography images. However, in the actual medical imaging process, due to the relatively low gray values of some small blood vessels and the ends of blood vessels, their contrast is relatively low, and the blood vessels are not clearly displayed, which is not conducive to doctors observing the morphology of blood vessels. Therefore, clearer vascular images are of great significance for doctors' clinical diagnosis. In traditional technologies, the method based on the Hessian matrix is mainly used to enhance vascular images. However, this enhancement method does not clearly display small blood vessels and the ends of blood vessels. Summary of the Invention

[0003] Based on this, in view of the above technical problems, it is necessary to provide a method, apparatus, device, and storage medium for enhancing vascular images that can clearly display small blood vessels and the ends of blood vessels.

[0004] In a first aspect, the present application provides a method for enhancing a vascular image, the method comprising:

[0005] Obtaining a vascular segmentation image corresponding to the original vascular image and a vascular segmentation probability map corresponding to the original vascular image;

[0006] Determining target vascular points to be enhanced in the original vascular image according to the feature values of each vascular point in the vascular segmentation image and a preset threshold;

[0007] Enhancing the feature values of the target vascular points according to the feature values of the target vascular points and the vascular segmentation probability map to obtain an enhanced vascular image.

[0008] In one embodiment, the enhancing the feature values of the target vascular points according to the feature values of the target vascular points and the vascular segmentation probability map to obtain an enhanced vascular image includes:

[0009] Determining a probability value corresponding to the target vascular point according to the vascular segmentation probability map; the probability value is used to represent the probability that the target vascular point belongs to a blood vessel;

[0010] Obtaining an enhanced value of the target vascular point according to the feature value of the target vascular point, the probability value corresponding to the target vascular point, and a preset enhancement function;

[0011] Enhance the eigenvalue of the target blood vessel point according to the eigenvalue and the enhancement value of the target blood vessel point to obtain the enhanced blood vessel image.

[0012] In one embodiment, obtaining the enhancement value of the target blood vessel point according to the eigenvalue of the target blood vessel point, the probability value corresponding to the target blood vessel point, and a preset enhancement function includes:

[0013] Obtain a first enhancement coefficient according to a preset increment value and the eigenvalue of the target blood vessel point;

[0014] Obtain a second enhancement coefficient according to the probability value corresponding to the target blood vessel point and the enhancement function;

[0015] Obtain the enhancement value of the target blood vessel point according to the first enhancement coefficient and the second enhancement coefficient.

[0016] In one embodiment, before enhancing the eigenvalue of the target blood vessel point according to the eigenvalue of the target blood vessel point and the blood vessel segmentation probability map to obtain the enhanced blood vessel image, the method further includes:

[0017] Process the blood vessel segmentation probability map according to the blood vessel segmentation image to obtain a processed blood vessel segmentation probability map;

[0018] Enhancing the eigenvalue of the target blood vessel point according to the eigenvalue of the target blood vessel point and the blood vessel segmentation probability map to obtain the enhanced blood vessel image includes:

[0019] Enhance the eigenvalue of the target blood vessel point according to the eigenvalue of the target blood vessel point and the processed blood vessel segmentation probability map to obtain the enhanced blood vessel image.

[0020] In one embodiment, processing the blood vessel segmentation probability map according to the blood vessel segmentation image to obtain a processed blood vessel segmentation probability map includes:

[0021] Determine whether the initial probability value of the target blood vessel point in the blood vessel segmentation probability map is greater than or equal to a preset probability threshold according to the blood vessel segmentation image;

[0022] If so, determine the initial probability value of the target blood vessel point as the target probability value of the target blood vessel point; if not, determine the probability threshold as the target probability value of the target blood vessel point to obtain the processed blood vessel segmentation probability map.

[0023] In one embodiment, determining the target blood vessel point to be enhanced in the original blood vessel image according to the eigenvalue of each blood vessel point in the blood vessel segmentation image and a preset threshold includes:

[0024] Compare the eigenvalue of each of the vascular points with the preset threshold, and determine the vascular points with eigenvalues less than the preset threshold as the target vascular points.

[0025] In one embodiment, the method further includes:

[0026] Perform smoothing processing on the enhanced vascular image to obtain a smoothed vascular image.

[0027] In a second aspect, the present application further provides an enhancement device for vascular images, and the device includes:

[0028] An acquisition module, configured to acquire a vascular segmentation image corresponding to the original vascular image and a vascular segmentation probability map corresponding to the original vascular image;

[0029] A determination module, configured to determine the target vascular points to be enhanced in the original vascular image according to the eigenvalues of the vascular points in the vascular segmentation image and a preset threshold;

[0030] An enhancement module, configured to enhance the eigenvalue of the target vascular point according to the eigenvalue of the target vascular point and the vascular segmentation probability map to obtain an enhanced vascular image.

[0031] In a third aspect, the present application further provides a computer device, and the computer device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0032] Acquire a vascular segmentation image corresponding to the original vascular image and a vascular segmentation probability map corresponding to the original vascular image;

[0033] Determine the target vascular points to be enhanced in the original vascular image according to the eigenvalues of the vascular points in the vascular segmentation image and a preset threshold;

[0034] Enhance the eigenvalue of the target vascular point according to the eigenvalue of the target vascular point and the vascular segmentation probability map to obtain an enhanced vascular image.

[0035] In a fourth aspect, the present application further provides a computer-readable storage medium, and the computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the following steps are implemented:

[0036] Acquire a vascular segmentation image corresponding to the original vascular image and a vascular segmentation probability map corresponding to the original vascular image;

[0037] Determine the target blood vessel points to be enhanced in the original blood vessel image according to the eigenvalue of each blood vessel point in the blood vessel segmentation image and a preset threshold value;

[0038] Enhance the eigenvalue of the target blood vessel point according to the eigenvalue of the target blood vessel point and the blood vessel segmentation probability map to obtain an enhanced blood vessel image.

[0039] In a fifth aspect, the present application further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the following steps are implemented:

[0040] Obtain the blood vessel segmentation image corresponding to the original blood vessel image and the blood vessel segmentation probability map corresponding to the original blood vessel image;

[0041] Determine the target blood vessel points to be enhanced in the original blood vessel image according to the eigenvalue of each blood vessel point in the blood vessel segmentation image and a preset threshold value;

[0042] Enhance the eigenvalue of the target blood vessel point according to the eigenvalue of the target blood vessel point and the blood vessel segmentation probability map to obtain an enhanced blood vessel image.

[0043] For the above blood vessel image enhancement method, device, equipment, storage medium and program product, since the target blood vessel points to be enhanced are determined according to the eigenvalue of each blood vessel point and a preset threshold value, the selected target blood vessel points are the blood vessel points that need to be enhanced. In this way, when enhancing the eigenvalue of the target blood vessel point according to the eigenvalue of the target blood vessel point and the blood vessel segmentation probability map, only the blood vessel points that need to be enhanced are processed, which is targeted. And the target blood vessel points are all blood vessel points that need to be enhanced, including small blood vessels and the ends of blood vessels. Therefore, when enhancing the eigenvalue of the target blood vessel point, the eigenvalue of small blood vessels and the ends of blood vessels can be enhanced, so that the obtained enhanced blood vessel image can clearly display small blood vessels and the ends of blood vessels; in addition, since the target blood vessel points are the blood vessel points that need to be enhanced, only the blood vessel points that need to be enhanced are processed, which improves the processing speed of enhancing the blood vessel image. Description of the Drawings

[0044] Figure 1 It is an application environment diagram of the blood vessel image enhancement method in an embodiment;

[0045] Figure 2 It is a flowchart of the blood vessel image enhancement method in an embodiment;

[0046] Figure 3 It is a flowchart of the blood vessel image enhancement method in another embodiment;

[0047] Figure 4Schematic flowchart of the method for enhancing a blood vessel image in another embodiment;

[0048] Figure 5 Schematic diagram of the original coronary blood vessel image in one embodiment;

[0049] Figure 6 Schematic diagram of the blood vessel image after enhancement and smoothing processing in one embodiment;

[0050] Figure 7 Schematic flowchart of the method for enhancing a blood vessel image in another embodiment;

[0051] Figure 8 Block diagram of the structure of the device for enhancing a blood vessel image in one embodiment. Detailed implementation manners

[0052] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to 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.

[0053] At present, cardiovascular and cerebrovascular diseases still pose a great threat to human life. The diagnosis of cardiovascular and cerebrovascular diseases mainly relies on angiography images. Doctors can directly understand the shape and structure of blood vessels by observing angiography images. However, in the actual medical imaging process, due to the relatively low gray values of some small blood vessels and the ends of blood vessels, the contrast is relatively low, the blood vessels are not clearly displayed, which is not conducive to doctors observing the morphology of blood vessels. Taking the angiography image of coronary arteries as an example, when the heart is used as the background, the contrast between the ends of blood vessels and the heart is not obvious, which is not conducive to doctors observing the morphology of blood vessels. Therefore, how to improve the display effect of small blood vessels and the ends of blood vessels in blood vessel images and obtain relatively clear blood vessel images is of great significance for doctors' clinical diagnosis. In traditional technologies, the method based on the Hessian matrix is mainly used to enhance blood vessel images. Its main idea is to construct a multi-scale blood vessel enhancement filter based on the Hessian matrix, and use the Hessian filter to enhance the blood vessel image by filtering. However, the traditional blood vessel enhancement method will suppress the non-blood vessel parts in the image and highlight the blood vessel structure in the image. However, this is not suitable for observing blood vessels and some other non-blood vessel parts that need attention at the same time, and the display of small blood vessels and the ends of blood vessels is not clear enough; in addition, the above calculation process is relatively complex and the calculation method is not simple. Therefore, this application proposes a blood vessel enhancement method based on a blood vessel segmentation probability map. Through this blood vessel enhancement algorithm, the areas with relatively low gray values of small blood vessels and the ends of blood vessels can be enhanced. Only the blood vessel points that need to be enhanced are processed during the above enhancement process, the calculation process is relatively simple, the processing speed of the blood vessel points to be enhanced is improved, the efficiency of the obtained enhanced blood vessel image is improved while obtaining relatively clear blood vessel images, and the real-time performance of the obtained enhanced blood vessel image is ensured.

[0054] The blood vessel image enhancement method provided by the embodiments of this application can be applicable to, for example Figure 1The computer device shown. The computer device includes a processor and a memory connected by a system bus. A computer program is stored in the memory. When the processor executes the computer program, it can execute the steps of the following method embodiments. Optionally, the computer device may further include a network interface, a display screen, and an input device. 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 network interface of the computer device is used to communicate with an external terminal through a network connection. Optionally, the computer device may be a server, a personal computer, a personal digital assistant, or other terminal devices, such as a tablet computer, a mobile phone, etc., or may also be a cloud or a remote server. The specific form of the computer device in the embodiments of the present application is not limited.

[0055] In one embodiment, as Figure 2 shown, a method for enhancing a vascular image is provided. Taking the method applied to the Figure 1 computer device in

[0056] as an example, the method includes the following steps:

[0057] S201, obtain a vascular segmentation image corresponding to the original vascular image and a vascular segmentation probability map corresponding to the original vascular image.

[0058] Among them, the original vascular image may be a CT angiography (CTA) image corresponding to the region of interest, or may also be other medical images. Optionally, the region of interest may be a coronary region, a brain region, etc. The vascular segmentation image corresponding to the original vascular image may be an image obtained by segmenting and segmenting each blood vessel in the vascular image. The probability value of each point in the vascular segmentation probability map corresponding to the original vascular image is a number between 0 and 1, and the probability value of each point can be used to represent the probability that the point belongs to a blood vessel. Optionally, the computer device may input the original vascular image into a pre-trained neural network model, first obtain a vascular segmentation probability map corresponding to the original vascular segmentation image through the neural network model, and then use a preset probability threshold to divide the vascular segmentation probability map to obtain a vascular segmentation image. It can be understood that the above pre-trained neural network model may be trained with a sample vascular image as the input of the initial neural network model and the sample vascular segmentation image corresponding to the sample vascular image as the golden standard.

[0058] S202, determine the target vascular points to be enhanced in the original vascular image according to the feature values of each vascular point in the vascular segmentation image and a preset threshold.

[0059] Among them, the blood vessel data is shown as blood vessel points in the image; the characteristic values of each blood vessel point in the above-mentioned blood vessel segmentation image can be the gray values of each blood vessel point, can also be the pixel values of each blood vessel point, or can be the voxel values of each blood vessel point. Optionally, the above-mentioned preset threshold can be determined by the computer device according to the average value of the characteristic values of the blood vessel segmentation region in the above-mentioned blood vessel segmentation image and the threshold coefficient. Taking the characteristic value of each blood vessel point in the blood vessel segmentation image as the gray value as an example, the above-mentioned preset threshold can be obtained according to the formula: T = k × b, where T represents the above-mentioned preset threshold, k represents the threshold coefficient, and b represents the average gray value of the blood vessel segmentation region in the blood vessel segmentation image. Optionally, the computer device can judge each blood vessel point in the blood vessel segmentation image point by point according to the preset threshold, determine the points with lower characteristic values in the original blood vessel image, and determine the points with lower characteristic values in the original blood vessel image as the target blood vessel points to be enhanced in the original blood vessel image. Optionally, the computer device can determine the blood vessel points with characteristic values less than the preset threshold as the target blood vessel points to be enhanced. Optionally, the target blood vessel points determined by the computer device can be scattered blood vessel points or relatively dense scattered blood vessel points.

[0060] S203. According to the characteristic value of the target blood vessel point and the blood vessel segmentation probability map, enhance the characteristic value of the target blood vessel point to obtain an enhanced blood vessel image.

[0061] Optionally, the computer device can obtain the probability value that the target blood vessel point belongs to a blood vessel according to the above-mentioned blood vessel segmentation probability map, and enhance the characteristic value of the target blood vessel according to the characteristic value of the target blood vessel point and the probability value that the target blood vessel point belongs to a blood vessel to obtain an enhanced blood vessel image. Further, as an implementable implementation manner, the computer device can obtain the enhancement value of the target blood vessel point according to the characteristic value of the target blood vessel point and the probability value that the target blood vessel point belongs to a blood vessel, and use the obtained enhancement value of the target blood vessel point to enhance the characteristic value of the target blood vessel point to obtain an enhanced blood vessel image. Taking the characteristic value of the target blood vessel point as the gray value of the target blood vessel point as an example, when the computer device enhances the characteristic value of the target blood vessel point, it can be to enhance the gray value of the target blood vessel point. Another example is that if the characteristic value of the target blood vessel point is the voxel value of the target blood vessel point, then when the computer device enhances the characteristic value of the target blood vessel point, it can be to enhance the voxel value of the target blood vessel point.

[0062] In the above method for enhancing a vascular image, since the computer device determines the target vascular points to be enhanced based on the eigenvalue of each vascular point and a preset threshold, the selected target vascular points are the vascular points that need to be enhanced. Thus, when enhancing the eigenvalue of the target vascular points according to the eigenvalue of the target vascular points and the vascular segmentation probability map, only the vascular points that need to be enhanced are processed, which is targeted and can ensure that all the determined target vascular points are enhanced specifically. And all the target vascular points that need to be enhanced include small blood vessels and the ends of blood vessels. Therefore, when enhancing the eigenvalue of the target vascular points, the eigenvalue of small blood vessels and the ends of blood vessels can be enhanced, so that the obtained enhanced vascular image can clearly display small blood vessels and the ends of blood vessels. In addition, since the target vascular points are the vascular points that need to be enhanced, only the vascular points that need to be enhanced are processed, which improves the processing speed of enhancing the vascular image.

[0063] In the scenario where the computer device enhances the eigenvalue of the target vascular points according to the eigenvalue of the target vascular points and the vascular segmentation probability map, the computer device can first determine the enhancement value of the target vascular points and use the enhancement value of the target vascular points to enhance the target vascular points. In one embodiment, as Figure 3 shown, the above S203 includes:

[0064] S301, determine the probability value corresponding to the target vascular points according to the vascular segmentation probability map; the probability value is used to represent the probability that the target vascular points belong to blood vessels.

[0065] It can be understood that the vascular segmentation probability map corresponds to the probability values of each voxel point in the original vascular image belonging to blood vessels. The computer device can determine the probability value corresponding to the above target vascular points according to this vascular segmentation probability map. Among them, the probability value corresponding to the target vascular points is a number between 0 and 1. The larger the probability value corresponding to the target vascular points, the greater the probability that the target vascular points belong to blood vessels, and the smaller the probability value corresponding to the target vascular points, the smaller the probability that the target vascular points belong to blood vessels.

[0066] S302, obtain the enhancement value of the target vascular points according to the eigenvalue of the target vascular points, the probability value corresponding to the target vascular points, and a preset enhancement function.

[0067] Optionally, the computer device can obtain the enhancement coefficient of the target vascular points according to the probability value corresponding to the target vascular points and a preset enhancement function, and obtain the enhancement value of the target vascular points according to the enhancement coefficient of the target vascular points and the eigenvalue of the target blood vessels.

[0068] Optionally, as an implementable embodiment, as Figure 4 shown, the computer device can obtain the enhancement value of the target vascular points through the following steps:

[0069] S401. Obtain a first enhancement coefficient according to a preset increment value and the eigenvalue of the target blood vessel point;

[0070] S402. Obtain a second enhancement coefficient according to the probability value corresponding to the target blood vessel point and an enhancement function;

[0071] S403. Obtain the enhancement value of the target blood vessel point according to the first enhancement coefficient and the second enhancement coefficient.

[0072] Among them, the preset increment value in the above S401 can be determined by the computer device according to empirical values. Optionally, the computer device can determine the difference between the preset increment value and the eigenvalue of the target blood vessel point as the above first enhancement coefficient. Optionally, in the above S403, the computer device can determine the product value of the first enhancement coefficient and the second enhancement coefficient as the enhancement value of the target blood vessel point. That is to say, the process by which the computer device obtains the enhancement value of the target blood vessel point can be represented by the following formula: H = (B - X ijk ) × f(P ijk ), where H represents the enhancement value of the target blood vessel point, X ijk represents the eigenvalue of the target blood vessel point, ijk represents the coordinate value of the target blood vessel point, B represents the preset increment value, P ijk represents the probability value corresponding to the target blood vessel point, f(x) represents the enhancement function, x represents the independent variable, B - X ijk represents the first enhancement coefficient, f(P ijk ) represents the second enhancement function, where f(x) can be obtained by the formula f(x) = x n , where n is the power exponent, and theoretically n ∈ (0, +∞), or f(x) can be obtained by the formula f(x) = x / m, where m ∈ [1, +∞).

[0073] S303. Enhance the eigenvalue of the target blood vessel point according to the eigenvalue and the enhancement value of the target blood vessel point to obtain an enhanced blood vessel image.

[0074] Optionally, the computer device can determine the sum of the eigenvalue of the target blood vessel point and the above enhancement value as the enhanced eigenvalue of the target blood vessel point, and use the enhanced eigenvalue to replace the eigenvalue of the target blood vessel point in the blood vessel image to obtain an enhanced blood vessel image. Or, the computer device can determine the weighted sum of the eigenvalue of the target blood vessel point and the above enhancement value as the enhanced eigenvalue of the target blood vessel point, and use the enhanced eigenvalue to replace the eigenvalue of the target blood vessel point in the blood vessel image to obtain an enhanced blood vessel image.

[0075] In this embodiment, since the computer device can accurately determine the probability value corresponding to the target blood vessel point according to the blood vessel segmentation probability map, the enhancement value of the target blood vessel point can be obtained according to the eigenvalue of the target blood vessel point, the probability value corresponding to the target blood vessel point, and the preset enhancement function. Furthermore, the eigenvalue of the target blood vessel point can be enhanced according to the eigenvalue of the target blood vessel point and the obtained enhancement value, ensuring that small blood vessels and the blood vessels at the ends are not missed. As a result, the enhanced blood vessel image obtained can clearly display small blood vessels and the ends of blood vessels. Additionally, since the determined target blood vessel points are the blood vessel points to be enhanced, when enhancing the eigenvalue of the target blood vessel point, the eigenvalue of non-blood vessel points is not enhanced, reducing the amount of computation. The amount of calculation is small, thereby improving the real-time performance of enhancing the target blood vessel point, that is, improving the real-time performance of the obtained enhanced blood vessel image.

[0076] In the scenario where the computer device enhances the eigenvalue of the target blood vessel point according to the eigenvalue of the target blood vessel point and the blood vessel segmentation probability map, since the segmentation result in the blood vessel segmentation image corresponding to the original blood vessel image may be post-processed, resulting in a small probability value for some blood vessel parts, but theoretically the probability value of these points should be greater than or equal to the preset probability threshold. Therefore, the computer device can also process the blood vessel segmentation probability map. On the basis of the above embodiment, in one embodiment, the above method further includes: processing the blood vessel segmentation probability map according to the blood vessel segmentation image to obtain a processed blood vessel segmentation probability map; the above S203 includes: enhancing the eigenvalue of the target blood vessel point according to the eigenvalue of the target blood vessel point and the processed blood vessel segmentation probability map to obtain an enhanced blood vessel image.

[0077] Specifically, the computer device locates the corresponding blood vessels in the blood vessel segmentation probability map according to the positions of the blood vessels in the above-mentioned blood vessel segmentation image, and then processes the probability values of each blood vessel point in the blood vessel to obtain a processed blood vessel segmentation probability map. Further, the computer device enhances the eigenvalue of the target blood vessel point according to the eigenvalue of the target blood vessel point and the processed blood vessel segmentation probability map to obtain an enhanced blood vessel image. Optionally, the computer device may determine whether the initial probability value of the target blood vessel point in the above-mentioned blood vessel segmentation probability map is greater than or equal to a preset probability threshold according to the above-mentioned blood vessel segmentation image. If the computer device determines that the initial probability value of the target blood vessel point in the blood vessel segmentation probability map is greater than or equal to the preset probability threshold, the computer device determines the initial probability value of the target blood vessel point as the target probability value of the target blood vessel point. If the computer device determines that the initial probability value of the target blood vessel point in the blood vessel segmentation probability map is less than the preset probability threshold, the computer device determines the above-mentioned probability threshold as the target probability value of the target blood vessel point to obtain a processed blood vessel segmentation probability map. Preferably, in the embodiments of the present application, the preset probability threshold may be 0.5. That is to say, the computer device may process the blood vessel segmentation probability map according to the following formula: P' ijk = max(0.5, P ijk ), where P ijk represents the initial probability value of the target blood vessel point in the blood vessel segmentation probability map, and P' ijk represents the target probability value of the target blood vessel point in the blood vessel segmentation probability map.

[0078] Further, as an optional implementation manner, when the computer device enhances the eigenvalue of the target blood vessel point according to the eigenvalue of the target blood vessel point and the processed blood vessel segmentation probability map, the eigenvalue of the target blood vessel point may be enhanced by using the following formula: X' ijk = X ijk + (B - X ijk ) × f(P' ijk ), where X ijk represents the eigenvalue of the target blood vessel point, B represents a preset increment value, P' ijk represents the processed probability value corresponding to the target blood vessel, f(x) represents an enhancement function, x represents an independent variable, where f(x) may be obtained by the formula f(x) = x n , where n is an exponent, and the value of n is theoretically n ∈ (0, +∞), or f(x) may be obtained by the formula f(x) = x / m, where m ∈ [1, +∞).

[0079] ​In this embodiment, since the enhanced blood vessel image obtained by the computer device enhances the eigenvalue of the target blood vessel point based on the eigenvalue of the target blood vessel point and the processed blood vessel segmentation probability map, and since the blood vessel segmentation probability map has been processed, the computer device can more accurately enhance the characteristics of the target blood vessel point, so that the enhancement effect of the obtained enhanced blood vessel image is better. In addition, if the probability value corresponding to the blood vessel area to be enhanced is large, more eigenvalues will be compensated; at the same time, when the blood vessel eigenvalue is smaller, more eigenvalues will also be compensated, which can effectively increase the clarity shown in the blood vessel image, thereby obtaining a relatively clear blood vessel image.

[0080] In the scenario where the computer device determines the target blood vessel points to be enhanced in the original image according to the eigenvalues of each blood vessel point in the blood vessel segmentation image and a preset threshold, the computer device can determine the blood vessel points with eigenvalues less than the preset threshold as the target blood vessel points. In one embodiment, the above S202 includes: comparing the eigenvalues of each blood vessel point with the preset threshold, and determining the blood vessel points with eigenvalues less than the preset threshold as the target blood vessel points.

[0081] Optionally, the computer device can determine the above target blood vessel points by obtaining the difference between the eigenvalue of each blood vessel point and the preset threshold; or, the computer device can determine the above target blood vessel points by obtaining the ratio of the eigenvalue of each blood vessel point to the preset threshold. It can be understood that if the difference between the eigenvalue of the blood vessel point and the preset threshold is less than 0, it means that the eigenvalue of the blood vessel point is less than the preset threshold; if the ratio of the eigenvalue of the blood vessel point to the preset threshold is less than 1, it means that the eigenvalue of the blood vessel point is less than the preset threshold. It should be noted that for the blood vessel points with eigenvalues greater than the preset threshold, the computer device does not need to perform enhancement processing on these blood vessel points. The blood vessel points on which the computer device performs enhancement processing only include the blood vessel points with eigenvalues less than the preset threshold in the comparison result.

[0082] In this embodiment, since the process of the computer device comparing the eigenvalues of each blood vessel point with the preset threshold is relatively simple, the computer device can quickly obtain the comparison result of the eigenvalues of each blood vessel point and the preset threshold. Thus, the computer device can quickly determine the blood vessel points with eigenvalues less than the preset threshold in the comparison result as the target blood vessel points, improving the real-time performance of determining the target blood vessel points. Further, when enhancing the eigenvalues of the blood vessel points, the eigenvalues of the target blood vessel points are enhanced, and non-blood vessel points are not enhanced, reducing the amount of computation and the calculation amount is small, thereby improving the real-time performance of enhancing the target blood vessel points, that is, improving the real-time performance of the obtained enhanced blood vessel image.

[0083] In some scenarios, if a computer device directly displays the enhanced blood vessel image, it may cause some noise at the blood vessel edges. Therefore, the computer device can also perform smoothing processing on the enhanced blood vessel image to make the display of the enhanced blood vessel image more beautiful. On the basis of the above embodiments, in one embodiment, the above method further includes: performing smoothing processing on the enhanced blood vessel image to obtain a smoothed blood vessel image.

[0084] Among them, smoothing can also be called filtering, or together called smoothing filtering. Smoothing filtering is a spatial domain filtering technology for low-frequency enhancement. Optionally, the above smoothing processing may include at least one of mean filtering, median filtering, Gaussian filtering, and bilateral filtering. Exemplarily, taking a coronary angiography image as an example, Figure 5 is the original coronary angiography image, Figure 6 is the smoothed blood vessel image obtained by performing smoothing processing on the enhanced blood vessel image again. By comparing Figure 5 and Figure 6 it can be seen that Figure 6 the small blood vessels extending from the left blood vessel, the small blood vessels extending from the right blood vessel, and the blood vessel ends are shown more clearly and intuitively in

[0085] In this embodiment, the computer device performs smoothing processing on the enhanced blood vessel image again, which can avoid the noise generated at the blood vessel edges and make the display of small blood vessels and blood vessel ends in the smoothed blood vessel image more clear and intuitive.

[0086] For the convenience of those skilled in the art to understand, the following provides a detailed introduction to the method for enhancing the blood vessel image provided in this application. Please refer to Figure 7 This method may include:

[0087] S1, obtaining a blood vessel segmentation image corresponding to the original blood vessel image and a blood vessel segmentation probability map corresponding to the original blood vessel image.

[0088] S2, comparing the feature values of each blood vessel point with a preset threshold, and determining the blood vessel points with feature values less than the preset threshold as target blood vessel points.

[0089] S3, according to the blood vessel segmentation image, determining whether the initial probability value of the target blood vessel point in the blood vessel segmentation probability map is greater than or equal to a preset probability threshold;

[0090] S4, if so, determining the initial probability value of the target blood vessel point as the target probability value of the target blood vessel point, if not, determining the probability threshold as the target probability value of the target blood vessel point to obtain a processed blood vessel segmentation probability map.

[0091] S5. Determine the target probability value corresponding to the target blood vessel point according to the processed blood vessel segmentation probability map; the target probability value represents the probability that the target blood vessel point belongs to a blood vessel.

[0092] S6. Obtain a first enhancement coefficient according to a preset increment value and the eigenvalue of the target blood vessel point.

[0093] S7. Obtain a second enhancement coefficient according to the probability value corresponding to the target blood vessel point and an enhancement function.

[0094] S8. Obtain the enhancement value of the target blood vessel point according to the first enhancement coefficient and the second enhancement coefficient.

[0095] S9. Enhance the eigenvalue of the target blood vessel point according to the eigenvalue and the enhancement value of the target blood vessel point to obtain an enhanced blood vessel image.

[0096] S10. Perform smoothing processing on the enhanced blood vessel image to obtain a smoothed blood vessel image.

[0097] It should be noted that for the descriptions in the above S1 - S10, reference can be made to the relevant descriptions in the above embodiments, and their effects are similar, so they will not be elaborated in this embodiment.

[0098] It should be understood that although the steps in the flowcharts involved in the above embodiments are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise clearly stated in this article, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0099] Based on the same inventive concept, an embodiment of the present application also provides an enhancement device for a blood vessel image for implementing the above - mentioned enhancement method of a blood vessel image. The solution provided by this device for solving problems is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the following enhancement device for a blood vessel image can refer to the limitations on the enhancement method of a blood vessel image in the above text, and will not be elaborated here.

[0100] In one embodiment, as Figure 8 shown, an enhancement device for a blood vessel image is provided, including: an acquisition module, a determination module, and an enhancement module, where:

[0101] An acquisition module, configured to acquire a blood vessel segmentation image corresponding to an original blood vessel image and a blood vessel segmentation probability map corresponding to the original blood vessel image;

[0102] A determination module, configured to determine target blood vessel points to be enhanced in the original blood vessel image according to the eigenvalue of each blood vessel point in the blood vessel segmentation image and a preset threshold;

[0103] An enhancement module, configured to enhance the eigenvalue of the target blood vessel point according to the eigenvalue of the target blood vessel point and the blood vessel segmentation probability map, so as to obtain an enhanced blood vessel image.

[0104] The blood vessel image enhancement device provided in this embodiment may execute the above method embodiment, and its implementation principle and technical effect are similar, which will not be elaborated here.

[0105] Based on the above embodiment, optionally, the above enhancement module includes: a first determination unit, a second determination unit, and an enhancement unit, where:

[0106] The first determination unit is configured to determine a probability value corresponding to the target blood vessel point according to the blood vessel segmentation probability map; the probability value represents the probability that the target blood vessel point belongs to a blood vessel.

[0107] The second determination unit is configured to obtain an enhancement value of the target blood vessel point according to the eigenvalue of the target blood vessel point, the probability value corresponding to the target blood vessel point, and a preset enhancement function.

[0108] The enhancement unit is configured to enhance the eigenvalue of the target blood vessel point according to the eigenvalue of the target blood vessel point and the enhancement value, so as to obtain an enhanced blood vessel image.

[0109] The blood vessel image enhancement device provided in this embodiment may execute the above method embodiment, and its implementation principle and technical effect are similar, which will not be elaborated here.

[0110] Based on the above embodiment, optionally, the above second determination unit is configured to obtain a first enhancement coefficient according to a preset increment value and the eigenvalue of the target blood vessel point; obtain a second enhancement coefficient according to the probability value corresponding to the target blood vessel point and the enhancement function; and obtain the enhancement value of the target blood vessel point according to the first enhancement coefficient and the second enhancement coefficient.

[0111] The blood vessel image enhancement device provided in this embodiment may execute the above method embodiment, and its implementation principle and technical effect are similar, which will not be elaborated here.

[0112] Based on the above embodiment, optionally, the above device further includes: a first processing module, where:

[0113] The first processing module is configured to process the blood vessel segmentation probability map according to the blood vessel segmentation image to obtain a processed blood vessel segmentation probability map;

[0114] The above enhancement module is used to enhance the eigenvalue of the target blood vessel point according to the eigenvalue of the target blood vessel point and the processed blood vessel segmentation probability map, so as to obtain an enhanced blood vessel image.

[0115] The blood vessel image enhancement device provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effect are similar, which will not be elaborated here.

[0116] Based on the above embodiment, optionally, the above first processing module includes: a third determination unit and a fourth determination unit, where:

[0117] The third determination unit is used to determine whether the initial probability value of the target blood vessel point in the blood vessel segmentation probability map is greater than or equal to a preset probability threshold according to the blood vessel segmentation image.

[0118] The fourth determination unit is used to, if the initial probability value of the target blood vessel point in the blood vessel segmentation probability map is greater than or equal to the preset probability threshold, determine the initial probability value of the target blood vessel point as the target probability value of the target blood vessel point; if the initial probability value of the target blood vessel point in the blood vessel segmentation probability map is less than the preset probability threshold, determine the probability threshold as the target probability value of the target blood vessel point, so as to obtain a processed blood vessel segmentation probability map.

[0119] The blood vessel image enhancement device provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effect are similar, which will not be elaborated here.

[0120] Based on the above embodiment, optionally, the above determination module includes: a comparison unit, where:

[0121] The comparison unit is used to compare the eigenvalue of each blood vessel point with a preset threshold, and determine the blood vessel point with the eigenvalue of the blood vessel point less than the preset threshold as the target blood vessel point.

[0122] The blood vessel image enhancement device provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effect are similar, which will not be elaborated here.

[0123] Based on the above embodiment, optionally, the above device further includes: a second processing module, where:

[0124] The second processing module is used to perform smoothing processing on the enhanced blood vessel image to obtain a smoothed blood vessel image.

[0125] The blood vessel image enhancement device provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effect are similar, which will not be elaborated here.

[0126] Each module in the above-mentioned vascular image enhancement device can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above modules can be embedded in the processor of a computer device in hardware form or be independent of it, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each of the above modules.

[0127] In one embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, the following steps are implemented:

[0128] Obtain the vascular segmentation image corresponding to the original vascular image and the vascular segmentation probability map corresponding to the original vascular image;

[0129] Determine the target vascular points to be enhanced in the original vascular image according to the feature values of each vascular point in the vascular segmentation image and a preset threshold;

[0130] Enhance the feature values of the target vascular points according to the feature values of the target vascular points and the vascular segmentation probability map to obtain an enhanced vascular image.

[0131] For the computer device provided in the above embodiment, its implementation principle and technical effects are similar to those of the above method embodiment, and will not be elaborated here.

[0132] 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 following steps are implemented:

[0133] Obtain the vascular segmentation image corresponding to the original vascular image and the vascular segmentation probability map corresponding to the original vascular image;

[0134] Determine the target vascular points to be enhanced in the original vascular image according to the feature values of each vascular point in the vascular segmentation image and a preset threshold;

[0135] Enhance the feature values of the target vascular points according to the feature values of the target vascular points and the vascular segmentation probability map to obtain an enhanced vascular image.

[0136] For the computer-readable storage medium provided in the above embodiment, its implementation principle and technical effects are similar to those of the above method embodiment, and will not be elaborated here.

[0137] In one embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the following steps are implemented:

[0138] Obtain the vascular segmentation image corresponding to the original vascular image and the vascular segmentation probability map corresponding to the original vascular image;

[0139] Determine the target blood vessel points to be enhanced in the original blood vessel image according to the eigenvalue of each blood vessel point in the blood vessel segmentation image and a preset threshold value;

[0140] Enhance the eigenvalue of the target blood vessel point according to the eigenvalue of the target blood vessel point and the blood vessel segmentation probability map to obtain an enhanced blood vessel image.

[0141] The computer program product provided by the above embodiment has the same implementation principle and technical effect as the above method embodiment, which will not be elaborated here.

[0142] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0143] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. 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 methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. 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. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0144] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, 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, it should be considered as the scope recorded in this specification.

[0145] The above-described embodiments only represent several implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. An enhancement method for vascular images, characterized in that, The method includes: Obtaining a vascular segmentation image corresponding to the original vascular image and a vascular segmentation probability map corresponding to the original vascular image; Determining target vascular points to be enhanced in the original vascular image according to the eigenvalue of each vascular point in the vascular segmentation image and a preset threshold; Enhancing the eigenvalue of the target vascular point according to the eigenvalue of the target vascular point and the vascular segmentation probability map to obtain an enhanced vascular image; Wherein, the enhancing the eigenvalue of the target vascular point according to the eigenvalue of the target vascular point and the vascular segmentation probability map to obtain an enhanced vascular image includes: Determining a probability value corresponding to the target vascular point according to the vascular segmentation probability map; the probability value is used to represent the probability that the target vascular point belongs to a blood vessel; Obtaining an enhanced value of the target vascular point according to the eigenvalue of the target vascular point, the probability value corresponding to the target vascular point, and a preset enhancement function; the preset enhancement function is an exponential function or a linear function; Obtaining the enhanced vascular image according to the eigenvalue of the target vascular point and the enhanced value.

2. The method according to claim 1, wherein The obtaining the enhanced value of the target vascular point according to the eigenvalue of the target vascular point, the probability value corresponding to the target vascular point, and a preset enhancement function includes: Obtaining a first enhancement coefficient according to a preset increment value and the eigenvalue of the target vascular point; Obtaining a second enhancement coefficient according to the probability value corresponding to the target vascular point and the enhancement function; Obtaining the enhanced value of the target vascular point according to the product value of the first enhancement coefficient and the second enhancement coefficient.

3. The method according to claim 2, wherein The obtaining the first enhancement coefficient according to a preset increment value and the eigenvalue of the target vascular point includes: Determining the difference between the preset increment value and the eigenvalue of the target vascular point as the first enhancement coefficient.

4. The method according to claim 1, characterized in that, Before the enhancing the eigenvalue of the target vascular point according to the eigenvalue of the target vascular point and the vascular segmentation probability map to obtain an enhanced vascular image, the method further includes: Processing the vascular segmentation probability map according to the vascular segmentation image to obtain a processed vascular segmentation probability map; The enhancing the eigenvalue of the target vascular point according to the eigenvalue of the target vascular point and the vascular segmentation probability map to obtain an enhanced vascular image includes: Enhancing the eigenvalue of the target vascular point according to the eigenvalue of the target vascular point and the processed vascular segmentation probability map to obtain an enhanced vascular image.

5. The method according to claim 4, wherein The processing the vascular segmentation probability map according to the vascular segmentation image to obtain a processed vascular segmentation probability map includes: Determining whether the initial probability value of the target vascular point in the vascular segmentation probability map is greater than or equal to a preset probability threshold according to the vascular segmentation image; If so, determining the initial probability value of the target vascular point as the target probability value of the target vascular point, and if not, determining the probability threshold as the target probability value of the target vascular point to obtain the processed vascular segmentation probability map.

6. The method according to claim 1, characterized in that Determining the target blood vessel points to be enhanced in the original blood vessel image according to the eigenvalue of each blood vessel point in the blood vessel segmentation image and a preset threshold includes: Comparing the eigenvalue of each blood vessel point with the preset threshold, and determining the blood vessel points with the eigenvalue less than the preset threshold as the target blood vessel points.

7. The method according to any one of claims 1 to 6, characterized in that The method further includes: Performing smoothing processing on the enhanced blood vessel image to obtain a smoothed blood vessel image.

8. An enhancement device for vascular images, characterized in that, The device includes: An acquisition module, configured to acquire a blood vessel segmentation image corresponding to the original blood vessel image and a blood vessel segmentation probability map corresponding to the original blood vessel image; A determination module, configured to determine the target blood vessel points to be enhanced in the original blood vessel image according to the eigenvalue of each blood vessel point in the blood vessel segmentation image and a preset threshold; An enhancement module, configured to enhance the eigenvalue of the target blood vessel points according to the eigenvalue of the target blood vessel points and the blood vessel segmentation probability map to obtain an enhanced blood vessel image; The enhancement module includes: A first determination unit, configured to determine a probability value corresponding to the target blood vessel points according to the blood vessel segmentation probability map; the probability value is used to represent the probability that the target blood vessel points belong to blood vessels; A second determination unit, configured to obtain an enhancement value of the target blood vessel points according to the eigenvalue of the target blood vessel points, the probability value corresponding to the target blood vessel points, and a preset enhancement function; the preset enhancement function is an exponential function or a linear function; An enhancement unit, configured to obtain the enhanced blood vessel image according to the eigenvalue of the target blood vessel points and the enhancement value.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images