Vascular medical image processing method and apparatus therefor, medical image processing device

Abstract

The application relates to a blood vessel medical image processing method and device and a medical image processing equipment. The method takes at least part of marking points on a blood vessel in a blood vessel medical image as target marking points, determines a target scaling coefficient corresponding to each target marking point based on a target parameter corresponding to the target marking point, the target parameter includes a pipe diameter parameter and a gray value, the pipe diameter parameter and the gray value are positively correlated with the target scaling coefficient, adjusts the pipe diameter parameter corresponding to the target marking point based on the target scaling coefficient, and obtains a processed blood vessel medical image. The pipe diameter difference of thick and thin blood vessels in the processed blood vessel medical image is larger than that before processing, and for blood vessel branches with little difference in the pipe diameter parameter before processing, the pipe diameter difference of each marking point on the blood vessel branches can also be well differentiated, the shielding condition between the blood vessel branches is effectively improved, and the display effect is improved.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and in particular to a method and apparatus for vascular medical image processing, a medical image processing device, and a computer storage medium. Background Technology

[0002] Blood vessels are characterized by their numerous and complex branches. Traditional methods of visualizing blood vessels often result in visually thicker branches in medical images, leading to poor display quality. Summary of the Invention

[0003] Therefore, it is necessary to provide a vascular medical image processing method and apparatus, medical image processing equipment, and computer storage medium that improve image display effect by optimizing pipe diameter parameters in order to address the above-mentioned technical problems.

[0004] In a first aspect, this application provides a method for processing vascular medical images, the method comprising:

[0005] Based on the target parameters corresponding to the target markers on the blood vessels in vascular medical images, the target scaling factor corresponding to the target markers is determined; the target parameters include the tube diameter parameter and the gray value, wherein both the tube diameter parameter and the gray value are positively correlated with the target scaling factor;

[0006] Based on the target scaling factor, the tube diameter parameters corresponding to the target marker points are adjusted to obtain the processed vascular medical image.

[0007] In one embodiment, determining the target scaling factor corresponding to the target marker point based on the target parameters includes:

[0008] Based on the pipe diameter parameters corresponding to the target marker points, a first scaling factor is determined for each target marker point; the first scaling factor is positively correlated with the pipe diameter parameters.

[0009] Based on the grayscale value corresponding to the target marker point, a second scaling factor is determined for the target marker point; the second scaling factor is positively correlated with the grayscale value.

[0010] Based on the first scaling factor, the second scaling factor, and the first nonlinear model corresponding to the target marker point, the target scaling factor corresponding to the target marker point is determined.

[0011] In one embodiment, determining the target scaling factor corresponding to the target marker point based on the first scaling factor, the second scaling factor, and the first nonlinear model corresponding to the target marker point includes:

[0012] Based on the first scaling factor, the second scaling factor, and the following first nonlinear model, the target scaling factor corresponding to the target marker point is determined:

[0013] f(x1,x2)=a*g(x1)+b*h(x2), a+b=1, a∈(0,1), b∈(0,1);

[0014] Where f(x1,x2) represents the target scaling factor corresponding to the target marker point, x1 represents the pipe diameter parameter corresponding to the target marker point, g(x1) represents the first scaling factor based on the pipe diameter parameter corresponding to the target marker point, x2 represents the gray value of the target marker point, h(x2) represents the second scaling factor based on the gray value corresponding to the target marker point, a represents the weight of g(x1), and b represents the weight of h(x2).

[0015] In one embodiment, the target scaling factor includes a first scaling factor and a second scaling factor. The target scaling factor corresponding to the target marker point is determined based on the target parameters corresponding to the target marker point. Based on the target scaling factor, the tube diameter parameters corresponding to the target marker point are adjusted to obtain the processed vascular medical image, including:

[0016] Based on the pipe diameter parameters corresponding to the target marker point, determine the first scaling factor corresponding to the target marker point;

[0017] Based on the first scaling factor, the pipe diameter parameters corresponding to the target marker points are adjusted to obtain an intermediate optimized image;

[0018] For blood vessel branches with consistent diameter parameters in the intermediate optimized image, the second scaling factor corresponding to the target marker point is determined based on the gray value corresponding to the target marker point.

[0019] For blood vessel branches with consistent diameter parameters in the intermediate optimized image, the diameter parameters corresponding to the target marker points in the intermediate optimized image are adjusted based on the second scaling factor to obtain the processed vascular medical image.

[0020] In one embodiment, identifying vascular branches with consistent diameter parameters includes:

[0021] Based on the diameter parameters corresponding to the target marker points on each blood vessel branch in the intermediate optimized image, the variance of the diameter parameters of the blood vessel branch is calculated.

[0022] If the variance is less than the preset variance, then the vascular branch is determined to be a vascular branch with the same diameter parameters.

[0023] In one embodiment, determining a first scaling factor corresponding to the target marker point based on the pipe diameter parameter corresponding to the target marker point includes:

[0024] Obtain the diameter parameters corresponding to each marker point on the blood vessel in a vascular medical image;

[0025] Select the marker points whose pipe diameter parameter is less than or equal to the first target threshold as target marker points;

[0026] Based on the pipe diameter parameters corresponding to the target marker point, determine the first scaling factor corresponding to the target marker point. The first scaling factor is less than or equal to 1.

[0027] In one embodiment, the step of determining the first target threshold includes:

[0028] Based on the diameter parameters corresponding to each marker point on all blood vessels in vascular medical images, the minimum and maximum diameter parameters are determined.

[0029] A first threshold is determined based on the minimum pipe diameter parameter and the maximum pipe diameter parameter; wherein the first threshold is greater than the minimum pipe diameter parameter and less than the maximum pipe diameter parameter;

[0030] The first threshold is used as the first target threshold, or the minimum value between the first threshold and the preset second threshold is used as the first target threshold.

[0031] In one embodiment, determining a first scaling factor corresponding to the target marker point based on the pipe diameter parameter corresponding to the target marker point includes:

[0032] Based on the pipe diameter parameters corresponding to the target marker point and the second nonlinear model, a first scaling factor corresponding to the target marker point is determined; wherein, the second nonlinear model is used to characterize the positive correlation mapping relationship between the pipe diameter parameters and the first scaling factor.

[0033] In one embodiment, determining a second scaling factor corresponding to the target marker point based on the grayscale value of the target marker point includes:

[0034] Obtain the grayscale values ​​corresponding to each marker point on a blood vessel in a vascular medical image;

[0035] Select marker points whose grayscale values ​​are less than or equal to the second target threshold as target marker points;

[0036] Based on the grayscale value corresponding to the target marker point, a second scaling factor is determined, which is less than or equal to 1.

[0037] In one embodiment, the step of determining the second target threshold includes:

[0038] Based on the gray values ​​corresponding to each marker point on all blood vessels in vascular medical images, determine the minimum and maximum gray values;

[0039] A third threshold is determined based on the minimum and maximum gray values; wherein the third threshold is greater than the minimum gray value and less than the maximum gray value.

[0040] The third threshold is used as the second target threshold, or the minimum value between the third threshold and the preset fourth threshold is determined to be the second target threshold.

[0041] In one embodiment, determining a second scaling factor corresponding to the target marker point based on the grayscale value of the target marker point includes:

[0042] Based on the gray value corresponding to the target marker point and the third nonlinear model, the second scaling factor corresponding to the target marker point is determined; wherein, the third nonlinear model is used to characterize the positive correlation mapping relationship between the gray value and the second scaling factor.

[0043] In one embodiment, the above-described vascular medical image processing method further includes:

[0044] Extracting the centerline of blood vessels from vascular medical images;

[0045] The markers on the center line of the blood vessel are identified as the markers on the blood vessel.

[0046] The target markers are at least some of the markers on the blood vessels.

[0047] In one embodiment, the distance between any two adjacent markers on the blood vessel is less than or equal to a first preset distance value; wherein, the target markers are at least a portion of the markers on the blood vessel.

[0048] In one embodiment, based on the target scaling factor, the tube diameter parameters corresponding to the target marker points are adjusted to obtain the processed vascular medical image, including:

[0049] Determine the sub-segments corresponding to the target markers on the blood vessels;

[0050] Based on the target scaling factor, the diameter parameters of the sub-segments corresponding to the target marker points are adjusted to obtain the processed vascular medical image;

[0051] Among them, the distance between two endpoints that are close to each other in two adjacent sub-segments is less than or equal to the second preset distance.

[0052] Secondly, a vascular medical image processing device is provided, the device comprising:

[0053] The scaling factor determination module is used to determine the target scaling factor corresponding to the target marker point based on the target parameters corresponding to the target marker point on the blood vessel in the vascular medical image; the target parameters include the pipe diameter parameter and the gray value, wherein the pipe diameter parameter and the gray value are both positively correlated with the target scaling factor;

[0054] The pipe diameter optimization module is used to adjust the pipe diameter parameters corresponding to the target marker points based on the target scaling factor to obtain the processed vascular medical image.

[0055] Thirdly, this application also provides a medical image processing device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the above-described vascular medical image processing method.

[0056] Fourthly, a computer-readable storage medium is also provided, on which a computer program is stored, which, when executed by a processor, implements the steps of the above-described vascular medical image processing method.

[0057] The above-mentioned vascular medical image processing method and apparatus, medical image processing equipment, and computer storage medium have at least the following beneficial effects:

[0058] This vascular medical image processing method uses at least some of the marker points on the blood vessels in the vascular medical image as target marker points. For each target marker point, a target scaling factor is determined that is positively correlated with both the diameter parameter and the gray value at that target marker point. The smaller the diameter parameter, the smaller the target scaling factor; conversely, the larger the diameter parameter, the larger the target scaling factor. This makes the difference in the diameter of thick and thin blood vessels in the vascular medical image after the diameter parameter scaling process greater than the difference before the processing. Furthermore, considering that when the diameter is optimized based solely on the scaling factor determined by the diameter parameter, for blood vessel branches with small diameter differences, the difference in the diameter of each target marker point on the blood vessel branch is still not very obvious after the diameter parameter is adjusted. Considering the partial volume effect, the grayscale values ​​corresponding to each marked point on blood vessel branches with similar diameter parameters can vary significantly. Therefore, when determining the target scaling factor, grayscale values ​​are considered in addition to diameter parameters. Based on the characteristics of blood vessel diameter, the target scaling factor is determined by comprehensively considering both diameter parameters and grayscale values. The diameter parameters in the vascular medical image are then adjusted based on this target scaling factor to improve the differentiation of blood vessels of different diameters after diameter optimization. Furthermore, for blood vessel branches with basically consistent diameter parameters, the degree of difference in diameter parameters on individual blood vessel branches can also be improved, effectively reducing occlusion between blood vessels and improving the display effect.

[0059] In addition, by selecting appropriate target markers, both the diameter characteristics of large blood vessel branches and the length characteristics of small blood vessels can be preserved, matching the user's image viewing needs. Attached Figure Description

[0060] Figure 1 This is an application environment diagram of a vascular medical image processing method in one embodiment;

[0061] Figure 2 This is a flowchart illustrating a vascular medical image processing method in one embodiment;

[0062] Figure 3This is a flowchart illustrating a vascular medical image processing method in one embodiment;

[0063] Figure 4 This is a flowchart illustrating a vascular medical image processing method in one embodiment;

[0064] Figure 5 This is a schematic diagram illustrating the positive correlation between the vessel radius and the first scaling factor when the vessel diameter parameter is the vessel radius in one embodiment, under two cases where the parameter d in the second nonlinear model is 12 and 16.

[0065] Figure 6a This is a schematic diagram of a vascular medical image before processing in one embodiment;

[0066] Figure 6b This is a schematic diagram of a vascular medical image after the diameter parameter has been adjusted based on a first scaling factor determined when the parameter d is 12 in one embodiment.

[0067] Figure 6c This is a schematic diagram of a vascular medical image after the diameter parameter has been adjusted based on a first scaling factor determined when parameter d is 16 in one embodiment.

[0068] Figure 7 This is a schematic diagram illustrating the positive correlation between vascular grayscale values ​​and the second scaling factor in a vascular medical image with a maximum grayscale value of 300 and a minimum grayscale value of 50, as shown in one embodiment.

[0069] Figure 8 This is a structural block diagram of a vascular medical image processing device in one embodiment;

[0070] Figure 9 This is an internal structural diagram of a medical image processing device in one embodiment. Detailed Implementation

[0071] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0072] The vascular medical image processing method provided in this application embodiment can be applied to, for example... Figure 1In the application environment shown, the medical image processing device 102 communicates with the server 104 via a network. A data storage system can store the data that the server 104 needs to process. The data storage system can be integrated onto the server 104 or placed on a cloud or other network server. The medical image processing device 102 can acquire vascular medical images from the medical scanning device 106 based on the server 104, and process the input vascular medical images by executing the steps of the following vascular medical image processing method to obtain optimized vascular medical images. The medical image processing device 102 can be, but is not limited to, various medical devices with image processing functions, such as vascular visualization system devices. The server 104 can be implemented using a standalone server or a server cluster composed of multiple servers. It should be noted that if the medical image processing device 102 itself integrates scanning and image processing, both the initial vascular medical image and the processed vascular medical image can be generated by the medical image processing device 102.

[0073] In practical applications, it has been found that abundant vascular branches can make it less intuitive for doctors to view the overall vascular structure, and too many vascular branches can affect the interpretation of images.

[0074] In one exemplary technique, there are two main methods for visualizing the vascular system. The first is to directly render the vascular structure obtained after image segmentation to obtain a visualized vascular image. The second is to skeletonize the segmented vascular system after image segmentation, extract the centerline, calculate the vessel diameter parameters, and then render the image based on the centerline and vessel diameter parameters to obtain a visualized vascular image. However, the vessels rendered by these two methods appear visually coarse, especially the thinner vessels near the ends, which does not match actual clinical needs. Furthermore, the coarse and dense representation of vascular branches leads to low image reading quality and efficiency.

[0075] To address the aforementioned technical problems, in one embodiment of this application, as follows: Figure 2 As shown, a first aspect is provided: this application provides a method for processing vascular medical images, the method comprising:

[0076] S200: Based on the target parameters corresponding to the target markers on the blood vessels in the vascular medical image, determine the target scaling factor corresponding to the target markers. The target parameters include the vessel diameter parameter and the grayscale value, where both the vessel diameter parameter and the grayscale value are positively correlated with the target scaling factor. The target markers are at least some of the markers on the blood vessels, and the target scaling factor can be determined by obtaining the vessel diameter parameter and grayscale value corresponding to each marker on the blood vessels in the vascular medical image. The target markers on the blood vessels are at least some of the markers on the blood vessels, and the markers on the blood vessels can be points on the centerline of the blood vessels in the vascular medical image. That is, the determination of the target markers can be achieved based on methods such as centerline extraction, or based on other image processing methods.

[0077] For each blood vessel in a vascular medical image, multiple marker points can be determined based on centerline extraction or other marking rules, providing a basis for subsequent acquisition and adjustment of vessel diameter parameters. For example, multiple marker points can be determined at equal intervals along the extension direction of the vessel's centerline in the vascular medical image; alternatively, marker points can be determined at different locations on the vessel according to other rules. When using marker points on the vessel's centerline as marker points for adjusting vessel diameter parameters, the distances from points on the centerline to points on the edge of the vessel's cross-section tend to be consistent. Therefore, the diameter parameters determined based on this approach more accurately reflect the true thickness of the vessel, resulting in higher precision. In other words, the scheme of determining the scaling factor based on the diameter parameters corresponding to the marker points on the centerline fully considers the possibility that the cross-sections of the vessel are not necessarily circular but may be irregular in shape.

[0078] Vascular diameter parameters refer to parameters that reflect the thickness of blood vessels as presented in vascular medical images, such as vessel radius and vessel diameter. Grayscale value refers to the grayscale value of each marker point in a vascular medical image, which characterizes the actual thickness of blood vessels. Grayscale value is positively correlated with the scaling factor, and the vascular diameter parameter is also positively correlated with the scaling factor. For example, for vascular medical images obtained from CT (Computed Tomography) scans, due to the partial volume effect, the value of each voxel in the vascular medical image represents the average CT value of the corresponding unit tissue (a unit of measurement for the density of a local tissue or organ in the human body, also known as Henle units). In voxels of thicker parts of blood vessels, the proportion of blood is higher, and the contrast agent concentration is higher, resulting in a higher intensity value in the vascular medical image. The higher the intensity value, the larger the grayscale value displayed in the vascular medical image. Conversely, in voxels of thinner parts, the proportion of blood is lower, and the contrast agent concentration is lower, resulting in a lower intensity value and a lower grayscale value in the vascular medical image. Therefore, the grayscale value of a blood vessel changes from thickest to thinnest, and this grayscale value is positively correlated with the vessel diameter parameter. Furthermore, for two marker points on a blood vessel with similar diameters, the corresponding grayscale values ​​differ significantly. This means that using a scaling factor based on grayscale values ​​yields higher accuracy. Additionally, grayscale values ​​accurately reflect the actual thickness of blood vessels, and their reliability is unaffected by the imaging algorithms used in the vascular medical image process. However, when extracting vessel diameter parameters from vascular medical images and determining the scaling factor based on these parameters, the imaging algorithm can lead to situations where blood vessels with small diameter differences in reality appear with equal diameter parameters in the vascular medical image. If this occurs within the same blood vessel, it will result in the branches appearing to have uniform thickness, differing from the actual branching pattern and further impacting the accuracy of the diameter parameter adjustment.

[0079] There are many ways to determine grayscale values. For example, some devices can directly obtain grayscale images of blood vessels after scanning, such as the vascular medical images obtained from CT scans mentioned above. For this image, to obtain the grayscale values ​​at the marked points, the vascular medical image can be segmented, the vessel centerline extracted, and the marked points on the centerline determined. Further, the grayscale value of the marked points on the centerline is determined to be the grayscale value of the corresponding pixel in the original vascular medical image before image segmentation. This ensures that the grayscale value is the same as the original image before processing, improving the accuracy and reliability of adjusting pipe diameter parameters based on this grayscale value.

[0080] Target markers refer to the markers on which the tube diameter will be adjusted. The principle for their selection is to ensure that after adjusting the tube diameter of these target markers, the vascular network in the vascular medical image will be clearer and the visual effect will be better.

[0081] S400: Based on the target scaling factor, adjust the pipe diameter parameters corresponding to the target marker points to obtain the processed vascular medical image. Based on the selected target marker points, using the target marker points as the adjustment unit, scale the pipe diameter parameters at each target marker point. This scaling refers to scaling the pipe diameter presented in the vascular medical image. The process of adjusting based on the target scaling factor can be understood as multiplying the pipe diameter parameters in the vascular medical image by the target scaling factor to obtain the adjusted pipe diameter parameters, which are then displayed.

[0082] Specifically, the vascular medical image processing method provided in this application optimizes the vessel diameter for target marker points on blood vessels in vascular medical images. Firstly, the marker points can be blood vessels in regions of interest to the user in the vascular medical image, such as branches of blood vessels in the heart region of a thoracic vascular medical image. This means that the steps of the vascular medical image processing method provided in this application can be performed only on a portion of the vascular medical image. In this case, the selection range of target marker points can be constrained by marking only the blood vessels in the region of interest. Alternatively, the steps of the vascular medical image processing method in this application can be performed on the entire vascular medical image to adjust the vessel diameter parameters. Each marker point among at least some marker points on the blood vessel is taken as a target marker point, and the corresponding vessel diameter parameters and grayscale values ​​are obtained. Then, based on the vessel diameter parameters and grayscale values ​​corresponding to the target marker points, a target scaling factor that is positively correlated with both the vessel diameter parameters and the grayscale values ​​is determined. Based on the target scaling factor, the diameter parameters corresponding to the target marker points are adjusted, making the difference in diameter between thick and thin blood vessels in the scaled vascular medical image greater than before processing. This enables differentiated display of blood vessels with different diameters, improves the occlusion between blood vessels, and enhances the display effect. Furthermore, for individual blood vessel branches with small diameter differences, the difference in diameter between different target marker points on that branch can also be increased, improving the optimization effect.

[0083] When selecting specific marker points for diameter adjustment, these target marker points, as a whole, still follow the positive correlation between the target parameters and the target scaling factor. That is, the thicker the blood vessel in the same vascular medical image, the larger its target scaling factor; the thinner the blood vessel, the smaller its target scaling factor. Based on the target scaling factor adjustment, the difference in blood vessel thickness within the vascular medical image is increased, and even for blood vessel branches with consistent diameter parameters, the degree of diameter differentiation is improved, optimizing the visual display effect.

[0084] In one embodiment, the process of adjusting the tube diameter parameters corresponding to the target marker points based on the target scaling factor can be achieved by traversing the marker points along the vessel centerline. If the branches of the blood vessels in the vascular medical image are already known, the tube diameter parameters at each target marker point can also be adjusted by traversing the vessel branches. The determination of the vessel branches can be based on the extraction of the vessel centerline, and the number of marker points on the vessel branches can be the same as the number of marker points on the centerline, which will not be elaborated here.

[0085] In one embodiment, the determination of vascular branches may include the following steps:

[0086] Extract the centerline of blood vessels from vascular medical images; the extraction of the centerline can be implemented based on the description in the above embodiments, and will not be repeated here.

[0087] The degree of each marker point on the vascular centerline is determined; the selection of marker points can also be based on the description in other embodiments. The marking process can involve assigning a value of 1 to points on the centerline and a value of 0 to points outside the centerline for each point in the vascular medical image. The degree of a marker point can be determined based on whether it has adjacent marker points and the number of adjacent marker points. The number of adjacent marker points of the current marker point is the degree of the current marker point. Based on the degree of the marker points, they can be classified into endpoints (markers with a degree of 1 or greater than or equal to 3) and points between the two endpoints on the centerline (points with a degree of 2, i.e., only two adjacent marker points).

[0088] The branches of blood vessels in a vascular medical image are determined based on the degree of each marker point. For example, this can be achieved by traversing the marker points and determining the branches of blood vessels in the medical image based on the degree of each marker point. An endpoint is always the endpoint of a blood vessel branch; a marker point with a degree greater than or equal to 3 indicates that the end of the blood vessel branch containing that marker point is connected to other blood vessel branches; a marker point with a degree of 1 indicates that the end of the blood vessel branch containing that marker point is not connected to other blood vessel branches, and is either the start or end point of the blood vessel. For example, a marker point can be used as a seed node to traverse the marker points. During the traversal, each blood vessel branch (the portion between two endpoints) can be determined, and the start and end points of the blood vessels can be identified.

[0089] The starting point here refers to the marker with the largest pipe diameter parameter among the markers with a degree of 1. The ending point refers to the other markers with a degree of 1.

[0090] The start and end points can also be determined based on the root node. This can be based on preset rules; for example, the point with the largest diameter parameter can be used as the root node, and the root node can be used as the seed node. Following the direction from the seed node to the next marker point, the degree of the next marker point is determined to determine its type (endpoint, point between two endpoints on the centerline). The next marker point is then updated as the seed node. This process of "following the direction from the seed node to the next marker point, determining the degree of the next marker point, and determining the type of the next marker point" is repeated until all marker points have been traversed. During this process, various parameters of the blood vessel can be obtained, including diameter parameters such as radius, average radius, and overall diameter.

[0091] In one embodiment, the target scaling factor corresponding to the target marker point is determined based on the target parameters corresponding to the target marker point, such as... Figure 3 As shown, it includes:

[0092] S220, Based on the pipe diameter parameter corresponding to the target marker point, determine the first scaling factor corresponding to the target marker point; the first scaling factor is positively correlated with the pipe diameter parameter, the larger the pipe diameter parameter, the larger the first scaling factor, and vice versa.

[0093] S240, based on the grayscale value corresponding to the target marker point, determine the second scaling factor corresponding to the target marker point; the second scaling factor is positively correlated with the grayscale value, the larger the grayscale value, the larger the second scaling factor, and vice versa. The grayscale value can reflect the actual diameter of the blood vessel. For two marker points on a blood vessel branch with a small difference in diameter, the difference in grayscale value is more obvious than the difference in diameter parameter.

[0094] S260, based on the first scaling factor, the second scaling factor, and the first nonlinear model corresponding to the target marker point, determine the target scaling factor. The first nonlinear model refers to a model that can characterize the mapping relationship between the first scaling factor, the second scaling factor, and the target scaling factor.

[0095] Of course, the determination of the target scaling factor corresponding to the target marker point based on the first scaling factor and the second scaling factor corresponding to the target marker point can be achieved not only by adopting the first nonlinear model given in the embodiments of this application, but also by adopting linear transformation and other nonlinear transformations of various types not listed in the embodiments of this application, such as exponential transformation, logarithmic transformation, polynomial transformation and other forms.

[0096] In one embodiment, determining the target scaling factor corresponding to the target marker point based on the first scaling factor, the second scaling factor, and the first nonlinear model corresponding to the target marker point includes:

[0097] Based on the first scaling factor, the second scaling factor, and the following first nonlinear model, the target scaling factor corresponding to the target marker point is determined:

[0098] f(x1,x2)=a*g(x1)+b*h(x2), a+b=1, a∈(0,1), b∈(0,1);

[0099] Where f(x1,x2) represents the target scaling factor corresponding to the target marker point, x1 represents the pipe diameter parameter corresponding to the target marker point, g(x1) represents the first scaling factor based on the pipe diameter parameter corresponding to the target marker point, x2 represents the gray value of the target marker point, h(x2) represents the second scaling factor based on the gray value corresponding to the target marker point, a represents the weight of g(x1), and b represents the weight of h(x2).

[0100] The weights of a and b can be determined based on experimental test results, or by adjusting a and b based on user evaluations of the processed vascular medical images until the user evaluations meet expectations. The weights are optimized through continuous machine learning. This machine learning process can be performed on the current medical image processing equipment based on usage data (vascular medical images and user evaluations) on the current equipment, or it can be based on all usage data of similar vascular medical image equipment on the server. When using a weighted approach to determine the target scaling factor for adjusting the pipe diameter parameters, the target markers that ultimately need to be adjusted can be either the intersection or union of first-type target markers determined based on a first target threshold and second-type target markers determined based on a second target threshold, or they can be directly based on either the first or second target threshold.

[0101] In addition to using a weighted method to determine the target scaling factor for adjusting the diameter parameters of vascular medical images, a hierarchical adjustment method can also be used. First, a first scaling factor is determined based on the diameter parameters to adjust the diameter parameters. Then, for the adjusted vascular medical image, a second scaling factor is determined based on the grayscale values ​​to perform a second adjustment of the diameter parameters.

[0102] In one embodiment, the target scaling factor includes a first scaling factor and a second scaling factor. Based on the target parameters corresponding to the target marker points, the target scaling factor corresponding to the target marker points is determined. Based on the target scaling factor, the tube diameter parameters corresponding to the target marker points are adjusted to obtain the processed vascular medical image, such as... Figure 4 As shown, it includes:

[0103] S220, based on the pipe diameter parameter corresponding to the target marker point, determine the first scaling factor corresponding to the target marker point; the first scaling factor can be referred to the description in the above embodiment.

[0104] S420: Based on the first scaling factor, adjust the pipe diameter parameters corresponding to the target marker points to obtain an intermediate optimized image. Alternatively, adjust the pipe diameter parameters of all target marker points based on their corresponding first scaling factor to obtain an intermediate optimized image. In this image, for blood vessel branches with consistent pipe diameter parameters, the differences in pipe diameter parameters in the optimized image are still small, which to some extent affects the user's viewing experience. When optimizing pipe diameter based on the first scaling factor, the target marker points can be those determined based on a first target threshold.

[0105] S280, for blood vessel branches with consistent diameter parameters in the intermediate optimized image, a second scaling factor corresponding to the target marker point is determined based on the grayscale value corresponding to the target marker point. The second scaling factor can be referred to the description in the above embodiments. The determination of the second scaling factor can be performed only on blood vessel branches with consistent diameter parameters to reduce the amount of data to be processed and improve processing speed. To avoid significant differences between the results of diameter adjustment using different scaling strategies on the same blood vessel branch and the actual changes in blood vessel thickness, in the process of determining whether to further adjust the intermediate optimized image using the second scaling factor, the consistency of the diameter parameters on a complete blood vessel branch is judged. A blood vessel branch can be understood as a segment of blood vessel between two adjacent endpoints in the above embodiments. Its determination method is also described in the above embodiments and will not be repeated here.

[0106] S440, for blood vessel branches with consistent diameter parameters in the intermediate optimized image, the diameter parameters corresponding to the target markers in the intermediate optimized image are adjusted based on the second scaling factor to obtain the processed vascular medical image. For blood vessel branches with consistent diameter parameters, based on the second scaling factor corresponding to each target marker, further diameter parameter adjustments are made to these branches based on the intermediate optimized image to obtain the processed vascular medical image. Since the grayscale values ​​corresponding to diameters with small differences in diameter parameters are significantly different, the processed vascular medical image can better enhance the differentiation of thick and thin blood vessels in the previous vascular medical image, increase the white space in the image, and reduce occlusion between blood vessel branches. It also more vividly displays the changes in blood vessel thickness. When optimizing target markers based on the second scaling factor, the target markers here can refer to the target markers determined based on the second target threshold.

[0107] In one embodiment, identifying vascular branches with consistent diameter parameters includes:

[0108] Based on the diameter parameters corresponding to the target marker points on each blood vessel branch in the intermediate optimized image, the variance of the diameter parameters of the blood vessel branch is calculated.

[0109] If the variance is less than the preset variance, then the vascular branch is determined to be a vascular branch with the same diameter parameters.

[0110] By calculating the variance, vascular branches with variances not exceeding a preset variance are identified as vascular branches with consistent diameter parameters. The preset variance can be set based on the required display accuracy.

[0111] In one embodiment, if the variance of the diameter parameter of each blood vessel branch in the intermediate optimized image is greater than or equal to the preset variance, it indicates that the display effect of blood vessel thickness difference in the intermediate optimized image is better, and it is not necessary to execute steps S280 and S440. At this time, the intermediate optimized image is determined to be the vascular medical image processed as described above.

[0112] In one embodiment, determining the first scaling factor corresponding to the target marker point based on the pipe diameter parameter corresponding to the target marker point includes:

[0113] Obtain the diameter parameters corresponding to each marker point on the blood vessel in vascular medical images;

[0114] Select the marker points whose pipe diameter parameter is less than or equal to the first target threshold as target marker points;

[0115] Based on the pipe diameter parameters corresponding to the target marker point, determine the first scaling factor corresponding to the target marker point. The first scaling factor is less than or equal to 1.

[0116] The selection of the first target threshold can be based on user-configurable settings. For example, for vascular medical images of the heart, the target markers can be determined based on the average vessel radius as the first target threshold. For markers with a vessel diameter parameter less than or equal to the first target threshold, a first scaling factor that is positively correlated with the vessel diameter parameter at that location and less than or equal to 1 is determined. For example, if the scaling factor for markers with a vessel diameter parameter equal to the first target threshold is determined to be 1, then following the positive correlation between the vessel diameter parameter and the first scaling factor, the larger the absolute value of the difference between the vessel diameter parameter and the target threshold at other target markers, the smaller the corresponding first scaling factor.

[0117] In one embodiment, for markers with a diameter parameter greater than or equal to a first target threshold, their diameter parameter can be kept unchanged, i.e., the scaling factor is equal to 1. Based on this, combined with the previous embodiment, a first scaling factor less than or equal to 1 is determined for markers with a diameter parameter less than or equal to the first target threshold to guide the adjustment of the diameter parameter corresponding to the target marker in the vascular medical image. In the processed vascular medical image, the diameter parameter of markers with a diameter parameter greater than or equal to the first target threshold is not adjusted. For markers with a diameter parameter less than or equal to the first target threshold, based on the positive correlation between the first scaling factor and the target scaling factor, the larger the absolute value of the difference between the diameter and the target threshold, the greater the reduction in the diameter parameter at the processed target marker, thereby well preserving the diameter characteristics of thicker blood vessels and also well preserving the length characteristics of thinner blood vessels.

[0118] The method of optimizing the visual display effect by increasing the difference in blood vessel diameter can be achieved, in addition to the examples mentioned above. The diameter parameters of marked points where the diameter parameter is greater than a first target threshold can also be adjusted. This can be done by increasing the diameter parameter at these marked points to increase the difference between blood vessels of different sizes. Therefore, in one embodiment, determining the first scaling factor corresponding to the target marked point based on the diameter parameter includes:

[0119] Select the marker points whose pipe diameter parameter is greater than or equal to the first target threshold as target marker points;

[0120] Based on the pipe diameter parameters corresponding to the target marker point, determine the first scaling factor corresponding to the target marker point. The first scaling factor is greater than or equal to 1.

[0121] For markers with diameter parameters greater than a first target threshold, the diameter parameters are adjusted. Following the positive correlation between the diameter parameter and the first scaling factor, a first scaling factor is determined for each target marker. This first scaling factor is greater than or equal to 1. For example, the first scaling factor for a marker with a diameter parameter equal to the first target threshold is 1, and the first scaling factor for other markers with diameter parameters greater than the first target threshold is also greater than or equal to 1. Furthermore, the scaling factor generally increases gradually as the diameter parameter increases. Based on this first scaling factor, vascular medical image processing can increase the diameter parameters of markers with diameter parameters greater than or equal to the first target threshold in the vascular medical image. Due to the positive correlation between the first scaling factor and the target scaling factor, the larger the diameter parameter of the target marker before adjustment, the greater the increase in diameter after adjustment, thereby increasing the difference in diameter between large and small blood vessels and effectively presenting the diameter dimension of large blood vessels as well as the length of small blood vessels.

[0122] Of course, it should be noted that the embodiments of this application can adjust the pipe diameter parameters not only at the marker points where the pipe diameter parameter is less than or equal to the first target threshold, or only at the marker points where the pipe diameter parameter is greater than or equal to the first target threshold, but also at all the marker points on the blood vessels in the vascular medical image. The selection principle is as described above; any scheme that can increase the visual difference in the diameter of thick and thin blood vessels falls under the above-mentioned target marker point selection implementation scheme.

[0123] The determination of target marker points is inseparable from the first target threshold. If the first target threshold is too small or too large, there will be too few marker points to adjust, resulting in a small difference in the diameter of blood vessels in the adjusted vascular medical image. Based on this, in one embodiment, the step of determining the first target threshold includes:

[0124] Based on the diameter parameters corresponding to each marker point on all blood vessels in vascular medical images, the minimum and maximum diameter parameters are determined.

[0125] A first threshold is determined based on the minimum pipe diameter parameter and the maximum pipe diameter parameter; wherein the first threshold is greater than the minimum pipe diameter parameter and less than the maximum pipe diameter parameter;

[0126] Use the first threshold as the first target threshold.

[0127] Considering the different blood vessel diameters in different locations, for each vascular medical image, the first target threshold can be selected based on the distribution of blood vessel diameter. Therefore, as mentioned above, the maximum and minimum blood vessel diameter parameters can be determined based on the diameter parameters at all marked points on the blood vessel (it should be noted that if only the diameter parameters of the region of interest in the vascular medical image need to be adjusted, this can be achieved by marking points only on the blood vessels in the region of interest), and the first threshold can be determined based on these two parameter values. This first threshold is then used as the first target threshold to determine the target marked points.

[0128] In one embodiment, the determination of the maximum and minimum pipe diameter parameters can be achieved by traversing the marker points. By traversing the marker points on the blood vessel, the maximum and minimum pipe diameter parameters are updated based on their relationship with the existing maximum and minimum pipe diameter parameters during the traversal. Initially, this comparison and update process can begin by initializing the maximum and minimum pipe diameter parameters. The traversal of marker points can be achieved by directly traversing the marker points on the centerline based on centerline extraction, or it can be based on... Figure 5As shown, the traversal of each marker point is based on whether the blood vessel branches have been traversed. In one implementation, the scaling factor can also be determined by traversing the blood vessel branches, which will not be elaborated here.

[0129] In one embodiment, determining a first threshold based on the minimum pipe diameter parameter and the maximum pipe diameter parameter includes:

[0130] The first threshold is obtained by weighted summation of the minimum and maximum pipe diameter parameters.

[0131] A first threshold is determined by weighted summation, taking into full account the minimum and maximum diameter parameters of the blood vessels. The target marker points can be adaptively determined based on the maximum difference in blood vessel diameter. Using this method to determine the first threshold, and then using it as the first target threshold for selecting target marker points, ensures that the marker points with adjusted vessel diameters in the final processed vascular medical image match the user's needs, improving the visual effect of blood vessel display.

[0132] In one embodiment, the process of weighted summation based on the minimum pipe diameter parameter and the maximum pipe diameter parameter can be implemented based on the following expression:

[0133] threshold=a*radiusMin+(1-c)*radiusMax,c∈[0,1]

[0134] Where threshold is the first threshold, radiusMin is the minimum tube diameter parameter, radiusMax is the maximum half-tube diameter parameter, and c is a linearly weighted scaling factor. c can be configured based on the user's viewing needs for blood vessel diameter.

[0135] In one embodiment, determining a first scaling factor corresponding to the target marker point based on the pipe diameter parameter at the target marker point includes:

[0136] Based on the pipe diameter parameters at the target marker point and the second nonlinear model, the first scaling factor corresponding to the target marker point is determined; wherein, the second nonlinear model is used to characterize the positive correlation mapping relationship between the pipe diameter parameters and the first scaling factor.

[0137] Compared to the linear model, the nonlinear model uses the pipe diameter parameter as input. Based on the first scaling factor determined by the second nonlinear model, the scaling factor increases more as the pipe diameter parameter increases. The larger the first scaling factor, the larger the target scaling factor. Based on the target scaling factor, the pipe diameter parameter at the target marker point is adjusted. The difference between thick and thin blood vessels in the resulting vascular medical image is also greater, which can more significantly improve the blood vessel presentation effect in the processed vascular medical image.

[0138] In one embodiment, the second nonlinear model can be as follows:

[0139]

[0140] Where g(x1) represents the first scaling factor corresponding to the target marker point with a tube diameter parameter of x1, x1 represents the tube diameter parameter (e.g., the radius or diameter of the blood vessel) of a target marker point on the blood vessel in the vascular medical image, and the minimum value of x1 is related to the physical spatial distance (spacing) between adjacent pixels in the vascular medical image; d represents a parameter that can be pre-configured.

[0141] When the vessel diameter parameter is the vessel radius, the correspondence between the vessel radius and the first scaling factor under this second nonlinear model is as follows: Figure 5 As shown.

[0142] Based on testing, when d takes the empirical value of 12, in one test case, only for... Figure 6a The original vascular medical image shown is subjected to tube diameter parameter adjustment based on the first scaling parameter, resulting in an intermediate optimized image as follows. Figure 6b As shown; when d takes the empirical value of 16, in this test case, for example... Figure 6a The original vascular medical image shown is followed by an intermediate optimized image after diameter optimization, as shown below. Figure 6c As shown in the diagram. Through comparison, it can be seen that when d is 12, the overall optimization effect on blood vessels is better, and it better meets the user's viewing needs. Then you can... Figure 6b Based on this, the tube diameter parameters are further adjusted using a second scaling factor determined by the grayscale values. In the processed vascular medical images, for Figure 6b The original image showed uniformly thick blood vessel branches, but the diameter differences at various points on the branches have been increased, making it closer to the actual variation in the thickness of blood vessels.

[0143] In one implementation, target markers are defined as those with a diameter parameter less than or equal to a first target threshold. Larger blood vessels with a diameter parameter greater than this target marker are not scaled; optimization is only performed on the diameter parameters of markers with diameter parameters less than or equal to the first target threshold. Furthermore, based on the aforementioned second nonlinear model, see [link to relevant documentation]. Figure 5 In the target marker points, the first scaling factor corresponding to the larger vessel radii in the first few levels is not significantly different, and the vessel diameter parameters at these target marker points, adjusted based on this first scaling factor, are still not significantly different. (See also...) Figure 5For the smaller vessel radii in later stages, the first scaling factor varies significantly depending on the vessel radius. Based on this characteristic, the finer the vessel, the greater the degree of shrinkage in the later stage compared to the earlier stage. Here, the later and earlier stages of vessel size can be understood as... Figure 5 The image shows blood vessels at two different radii on the horizontal axis. Specifically, for marker points where the vessel diameter parameter is less than or equal to the target threshold, the larger the absolute value of the difference between the marker point's diameter parameter and the target threshold, the smaller the corresponding scaling factor. Based on this second nonlinear model, the processed vascular medical image retains the diameter characteristics of thicker vessels to a greater extent, while thinner vessels are significantly reduced in size while retaining their length characteristics, thus improving the visual effect of the vascular medical image. Furthermore, by combining this with the second scaling factor to determine the aforementioned target scaling factor, the processed vascular medical image can be obtained, significantly improving the display effect.

[0144] After adjusting the vessel diameter parameters, the blood vessels in the vascular medical image can be colored to distinguish different types of vessels. For example, the hepatic vein, inferior vena cava, portal vein, hepatic artery, and bile duct are colored with different colors, improving the display effect of the processed vascular medical image. Coloring can be done on a unit basis, focusing on a single complete blood vessel branch. When adjusting the vessel diameter parameters, on the same blood vessel branch, only the diameter parameters at target markers where the diameter parameter is less than or equal to the target threshold can be adjusted. In other words, the diameter parameter adjustment can be applied only to a portion of the blood vessel branch.

[0145] Of course, it should be noted that, in addition to the examples mentioned above, other polynomial models such as exponential transformation, logarithmic transformation, and polynomial transformation can also be used for the second nonlinear model.

[0146] For schemes that reduce the diameter parameter to less than or equal to the first target threshold, to avoid the first target threshold determined based on the maximum and minimum diameter parameters being too large due to the maximum diameter parameter of the blood vessels in the vascular medical image being too large, the blood vessel diameter that is not intended to be reduced is reduced. Therefore, in one embodiment, the step of determining the first target threshold includes:

[0147] Based on the diameter parameters corresponding to each marker point on all blood vessels in vascular medical images, the minimum and maximum diameter parameters are determined.

[0148] A first threshold is determined based on the minimum and maximum pipe diameter parameters; the first threshold is greater than the minimum pipe diameter parameter and less than the maximum pipe diameter parameter. The first threshold can be the result of a weighted sum of the minimum and maximum pipe diameter parameters as described in the above embodiments.

[0149] The minimum value between a first threshold and a preset second threshold is determined as the first target threshold. The second threshold can be configured based on the user's viewing needs for the vascular visual image. Different colors or grayscale values ​​can be used to represent different vascular branches, further improving the visual presentation of blood vessels in the processed vascular medical image.

[0150] In one embodiment, determining a second scaling factor corresponding to the target marker point based on the grayscale value of the target marker point includes:

[0151] Obtain the grayscale values ​​corresponding to each marker point on a blood vessel in a vascular medical image;

[0152] Select marker points whose grayscale values ​​are less than or equal to the second target threshold as target marker points;

[0153] Based on the grayscale value corresponding to the target marker point, a second scaling factor is determined, which is less than or equal to 1.

[0154] The selection of the second target threshold can be based on user-configurable settings. For example, for vascular medical images of the heart, the target markers can be determined based on the average vessel radius as the second target threshold. For markers with grayscale values ​​less than or equal to the second target threshold, a scaling factor that is positively correlated with the grayscale value and less than or equal to 1 is determined. For example, if the scaling factor for markers with grayscale values ​​equal to the second target threshold is determined to be 1, then following the positive correlation between grayscale values ​​and the second scaling factor, the larger the absolute value of the difference between the grayscale value and the second target threshold at other markers, the smaller the corresponding second scaling factor. Based on this, the second scaling factor at each target marker is determined to guide the adjustment of vessel diameter parameters in the vascular medical image, resulting in the processed vascular medical image.

[0155] In one embodiment, for markers with grayscale values ​​greater than or equal to a second target threshold, their diameter parameters can be kept unchanged, i.e., the scaling factor is equal to 1. Based on this, combined with the previous embodiment, a second scaling factor less than or equal to 1 is determined for markers with grayscale values ​​less than or equal to the second target threshold to guide the adjustment of the diameter parameters corresponding to the target markers in the medical image. In the processed vascular medical image, the diameter parameters of markers with grayscale values ​​greater than the second target threshold are not adjusted. For markers with grayscale values ​​less than or equal to the second target threshold, the larger the absolute value of the difference between the grayscale value and the target threshold, the greater the reduction in the diameter parameters of the processed target markers, thus well preserving the diameter characteristics of thicker blood vessels and also well preserving the length characteristics of thinner blood vessels.

[0156] Of course, besides the examples mentioned above, in order to optimize the visual display effect by increasing the difference in blood vessel diameter, the diameter parameters of the marked points with gray values ​​greater than the second target threshold can also be adjusted. This can be achieved by increasing the diameter parameters at these marked points to amplify the difference between blood vessels of different sizes. Therefore, in one embodiment, determining the second scaling factor corresponding to the target marked point based on its gray value includes:

[0157] Select marker points with gray values ​​greater than or equal to the second target threshold as target marker points;

[0158] Based on the grayscale value corresponding to the target marker point, a second scaling factor is determined for the target marker point, and the scaling factor is greater than or equal to 1.

[0159] For markers with gray values ​​greater than the second target threshold, the tube diameter parameters are adjusted. Following the positive correlation between gray values ​​and scaling factors, a second scaling factor is determined for each target marker. This second scaling factor is greater than or equal to 1. Based on the vascular medical image processing guided by this second scaling factor, the tube diameter parameters at markers with gray values ​​greater than or equal to the second target threshold in the vascular medical image can be increased. The larger the absolute value of the difference between the gray value of the target marker and the target threshold before adjustment, the greater the thickening of the tube diameter after adjustment, thereby increasing the difference in tube diameter between large and small blood vessels and presenting the tube diameter dimension of large blood vessels well, as well as the length of small blood vessels well.

[0160] Of course, it should be noted that the embodiments of this application can adjust the tube diameter parameters not only for marker points with gray values ​​less than or equal to the second target threshold, or only for marker points with gray values ​​greater than or equal to the second target threshold, but also for all marker points. The selection principle is as described above; any scheme that can increase the visual difference in the diameter of blood vessels falls under the above-mentioned target marker point selection implementation scheme.

[0161] The determination of target marker points is inseparable from the second target threshold. If the second target threshold is too small or too large, there will be too few marker points to adjust, resulting in a small difference in the diameter of blood vessels in the adjusted vascular medical image. Based on this, in one embodiment, the step of determining the second target threshold includes:

[0162] Based on the gray values ​​corresponding to each marker point on all blood vessels in vascular medical images, determine the minimum and maximum gray values;

[0163] A third threshold is determined based on the minimum and maximum gray values; wherein the third threshold is greater than the minimum gray value and less than the maximum gray value.

[0164] Use the third threshold as the second target threshold.

[0165] Considering the different thicknesses of blood vessels in different locations, a second target threshold can be selected for each vascular medical image based on its own distribution of blood vessel thickness. Therefore, as mentioned above, the maximum and minimum gray values ​​can be determined based on the gray values ​​of all marked points on the blood vessels (it should be noted that if only the diameter parameters of the region of interest in the vascular medical image need to be adjusted, this can be achieved by marking points only on the blood vessels in the region of interest), and the second target threshold can be determined based on these two values ​​to determine the target marked points.

[0166] In one embodiment, the determination of the maximum and minimum grayscale values ​​can be achieved by traversing the marker points. By traversing the marker points on the blood vessel, the maximum and minimum grayscale values ​​are updated based on their relationship with the existing maximum and minimum grayscale values ​​during the traversal. Initially, this comparison and update process can begin by initializing the maximum and minimum grayscale values. Traversing the marker points can be achieved by directly traversing the marker points on the centerline based on centerline extraction, or by traversing each marker point based on whether all blood vessel branches have been traversed. In one embodiment, the scaling factor can also be determined by traversing the blood vessel branches, which will not be elaborated upon here.

[0167] In one embodiment, determining a third threshold based on the minimum and maximum grayscale values ​​includes:

[0168] The third threshold is obtained by weighted summation of the minimum and maximum gray values.

[0169] A third threshold is determined by weighted summation, which further yields a second target threshold. This fully considers both minimum and maximum grayscale values, and the target markers are adaptively determined based on the maximum difference in vessel size. This method of determining the second target threshold and selecting target markers ensures that the vessel diameter parameters in the final processed vascular medical image match the user's needs, improving the visual effect of vessel branches.

[0170] In one embodiment, the process of weighted summation based on the minimum and maximum grayscale values ​​can be implemented using the following expression:

[0171] threshold=a*GrayValue_Min+(1-e)*GrayValue_Max, e∈[0,1]

[0172] Where `threshold` is the third threshold, `GrayValue_Min` is the minimum grayscale value, `rGrayValue_Max` is the maximum grayscale value, and `e` is a linearly weighted scaling factor. `e` can be configured based on the user's viewing needs for vessel diameter, combined with the relationship between vessel diameter and grayscale values. For example, by properly configuring `e`, the third threshold can be determined as a grayscale value ranking in the 40th percentile when sorted from largest to smallest. This grayscale value is used as the third threshold, and markers with grayscale values ​​less than or equal to this third threshold (when used as the second target threshold) are designated as target markers, and a second scaling factor is determined for these target markers.

[0173] In one embodiment, determining the second scaling factor corresponding to the target marker point based on the grayscale value at the target marker point includes:

[0174] Based on the gray value at the target marker point and the third nonlinear model, the second scaling factor corresponding to the target marker point is determined; wherein, the third nonlinear model is used to characterize the positive correlation mapping relationship between the gray value and the second scaling factor.

[0175] Compared to the linear model, the third nonlinear model uses grayscale values ​​as input. Based on the second scaling factor determined by the third nonlinear model, the scaling factor increases more as the grayscale value increases. The second scaling factor determined by this model guides the adjustment of the grayscale value at the target marker point, resulting in a greater difference in the thickness of blood vessels in the adjusted medical image. This can more significantly improve the blood vessel rendering effect in the adjusted vascular medical image.

[0176] In one embodiment, the third nonlinear model can be as follows:

[0177]

[0178] Where f(x2) represents the second scaling factor corresponding to the target marker point with a tube diameter parameter of x2, x2 represents the gray value of a target marker point on a blood vessel in a vascular medical image; f represents the maximum gray value among all gray values ​​of all marker points on all blood vessels; g represents the minimum gray value among all gray values ​​of marker points. f and g can be obtained based on the gray values ​​of each marker point on a blood vessel in a vascular medical image.

[0179] The correspondence between the blood vessel grayscale values ​​and the second scaling factor under this third nonlinear model is as follows: Figure 7 As shown.

[0180] Based on testing, in a vascular medical image, statistical analysis showed that when f = 300 and g = 50, in a test case, for example... Figure 6bThe original vascular medical image, after processing, now shows a larger difference in the diameter of blood vessel branches that were originally similar in diameter. This better reflects the actual diameter variations of blood vessels and meets the user's viewing needs. This process can be optimized only for blood vessel branches with consistent diameter parameters; branches with inconsistent diameter parameters in the intermediate optimized images are not further processed.

[0181] For blood vessel branches with consistent diameter parameters, due to the setting of the second target threshold, thicker blood vessels with gray values ​​greater than or equal to the second target threshold will not be reduced in size. For other markers with gray values ​​less than the second target threshold, the scaling of the diameter parameters at the first few thicker markers is smaller, while thinner blood vessels will be reduced to varying degrees. The thinner the blood vessel, the greater the reduction in diameter parameters at the target marker. Furthermore, as the gray value of the blood vessel decreases, i.e., the blood vessel diameter parameter decreases, the reduction in diameter parameters at the target marker will become increasingly larger.

[0182] After adjusting the hierarchical tube diameter parameters, the blood vessels in the final vascular medical image can be colored to distinguish different types of blood vessels. For example, the hepatic vein, inferior vena cava, portal vein, hepatic artery, and bile duct are colored with different colors to improve the display effect of the processed vascular medical image.

[0183] Of course, it should be noted that, in addition to the examples mentioned above, other nonlinear models such as exponential transformation, logarithmic transformation, and polynomial transformation can also be used for the third nonlinear model.

[0184] For schemes that reduce blood vessel diameter parameters with grayscale values ​​less than or equal to a second target threshold, to avoid the second target threshold determined based on the maximum and minimum grayscale values ​​being too large due to the maximum grayscale value of blood vessels in vascular medical images being too large, the blood vessel diameter, which is not intended to be reduced, is reduced. Therefore, in one embodiment, the step of determining the second target threshold includes:

[0185] Based on the gray values ​​corresponding to each marker point on all blood vessels in vascular medical images, determine the minimum and maximum gray values;

[0186] A third threshold is determined based on the minimum and maximum gray values; the third threshold can be the result of a weighted sum of the minimum and maximum gray values ​​as described in the above embodiments.

[0187] The minimum value between the third threshold and the preset fourth threshold is determined as the second target threshold. The fourth threshold can be configured based on the user's viewing needs for the visual representation of blood vessels.

[0188] In one embodiment, the above-described vascular medical image processing method further includes:

[0189] Extracting the centerline of blood vessels from vascular medical images;

[0190] The markers on the center line of the blood vessel are identified as markers on the blood vessel; wherein, the target markers are at least a portion of the markers on the blood vessel.

[0191] In one embodiment, the distance between any two adjacent markers on the blood vessel is less than or equal to a first preset distance value; wherein, the target markers are at least a portion of the markers on the blood vessel.

[0192] There are several ways to extract the centerline. For example, one method is to acquire medical images of black and bright blood vessels; perform vessel identification processing on both images to obtain black and bright blood vessel identification images; register and fuse these images to obtain a fused vessel identification image; and extract the segmental centerline of each vessel segment in the fused vessel identification image, then determine the centerline of the vessel in the medical image (which can be either a black or bright blood image) based on the segmental centerline of each vessel segment. Alternatively, based on the medical image, the distance from any point on a cross-section to points on the edge of the cross-section can be calculated, and the point with the smallest difference between the distances from the cross-section to the edge can be taken as the center point. Fitting the center points on each interface can yield the vessel centerline. The aforementioned center point can be directly used as a marker point on the vessel. For example, when the parallel distance between two adjacent cross-sections is less than or equal to the first preset distance in this embodiment, the center point can be directly used as a marker point on the vessel. Of course, based on the obtained vessel centerline, the points can be remarked to obtain the marker points on the vessel. For example, when extracting the centerline from medical images of dark and bright blood vessels, the marker points can be selected on the centerline according to preset rules. For example, the marker points can be selected at equal intervals.

[0193] To avoid excessively large intervals between marker points on the blood vessel, which could lead to unadjusted blood vessels between adjacent marker points during diameter parameter adjustment and affect the adjustment effect, in one embodiment, the distance between any two adjacent marker points on the blood vessel is less than or equal to a first preset distance value. This first preset distance value can be set based on the required adjustment precision; for example, it can be a value approaching infinity. Alternatively, it can be based on the pixels displayed in the image; for example, the first preset distance is equal to the physical spatial size of a single pixel.

[0194] When the marker on the blood vessel is a marker on the center line of the blood vessel, the marker can be determined based on the extraction of the center line, determining one endpoint on the center line as a marker, and determining each marker on the center line based on the extension direction of the center line along the endpoint, with a first preset distance as the interval between two adjacent markers.

[0195] If the selected markers on the blood vessels are spaced far apart, the result of adjusting the blood vessel diameter parameters based on the markers will be that a long section of blood vessel between the markers will not be adjusted, which will lead to an abnormal difference in the diameter parameters of the blood vessel segment and the adjacent target markers.

[0196] To address this situation, in one embodiment, the diameter parameters corresponding to the target marker points are adjusted based on a scaling factor to obtain a processed vascular medical image, including:

[0197] The sub-segments corresponding to the target markers on the blood vessel are determined; a sub-segment refers to a section of the blood vessel determined based on the target markers and segmentation rules. Segmentation rules may include, but are not limited to, the rules exemplified in the embodiments of this application.

[0198] Based on the scaling factor, the diameter parameters of the sub-segments corresponding to the target markers are adjusted to obtain the processed vascular medical image; for example, a sub-segment can be the part between two adjacent target markers on the center line of the blood vessel, which can be a straight line segment or a curve.

[0199] In this configuration, the distance between the two closest endpoints of two adjacent sub-segments is less than or equal to a second preset distance. This second preset distance can be zero, thus enabling full adjustment of the vascular portion between two adjacent target markers. Alternatively, depending on the required precision of the tube diameter adjustment, a second preset distance that approaches infinity but is not zero can be set.

[0200] When the distance between adjacent target markers is greater than a third preset distance, a sub-segment corresponding to such target markers is determined. The sub-segmentation rule can be based on the current target marker as the starting point, extending along the vessel's extension direction, with the next target marker as the ending point, defining the segment containing the vessel between the two target markers as the sub-segment corresponding to the current target marker. Alternatively, it can be based on the current target marker A as the center, using the distance D1 between A and its left-adjacent target marker B, and the distance D2 between A and its right-adjacent target marker C, defining the vessel segment within the range from D1 / 2 to D2 / 2 to the right of A as the aforementioned sub-segment. Of course, it can also be based on the current target marker A as the center, using a preset radius along the vessel's extension direction, defining the vessel segment within that radius as the sub-segment corresponding to A. In summary, there can be various sub-segmentation rules, but the general principle is that the interval between two adjacent sub-segments cannot exceed a second preset distance, to ensure that nearby vessels still exhibit smooth changes after adjusting the vessel diameter parameters.

[0201] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed 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 performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0202] Based on the same inventive concept, this application also provides a vascular medical image processing apparatus for implementing the aforementioned vascular medical image processing method. The solution provided by this apparatus is similar to the implementation described in the above method; therefore, the specific limitations in one or more embodiments of the vascular medical image processing apparatus provided below can be found in the limitations of the vascular medical image processing method described above, and will not be repeated here.

[0203] In one embodiment, such as Figure 8 As shown, a vascular medical image processing device is provided, the device comprising:

[0204] The target scaling factor determination module 200 is used to determine the target scaling factor corresponding to the target marker point based on the target parameters corresponding to the target marker point on the blood vessel in the vascular medical image; the target parameters include the pipe diameter parameter and the gray value, wherein the pipe diameter parameter and the gray value are both positively correlated with the target scaling factor;

[0205] The pipe diameter optimization module 400 is used to adjust the pipe diameter parameters corresponding to the target marker points based on the target scaling factor to obtain the processed vascular medical image.

[0206] The definitions of terms can be found in the above method embodiments and will not be repeated here. Specifically, the target scaling factor determination module 200 determines the target scaling factor corresponding to the target marker point on the blood vessel in the vascular medical image based on the target parameters, and sends the target scaling factor to the pipe diameter optimization module 400. Finally, the pipe diameter optimization module 400 adjusts the pipe diameter parameters corresponding to the target marker point in the vascular medical image based on the target scaling factor to obtain the processed vascular medical image. The pipe diameter parameters and grayscale values ​​are both positively correlated with the target scaling factor.

[0207] Each module in the aforementioned vascular medical image processing device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of the medical image processing device in hardware form or independent of it, or stored in the memory of the medical image processing device in software form, so that the processor can call and execute the corresponding operations of each module.

[0208] It should be noted that the vascular medical image processing device provided in this application embodiment also includes other modules and units to implement the functions of any method steps in the above method embodiments, which will not be elaborated here.

[0209] In one embodiment, a medical image processing device is provided. This medical image processing device can be a terminal, and its internal structure diagram can be as follows: Figure 9 As shown, the medical image processing device includes a processor, memory, communication interface, display screen, and input device connected via a system bus. The processor provides computational and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage medium. The communication interface allows for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a vascular medical image processing method. The display screen can be an LCD screen or an e-ink screen. The input device can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the device's casing, or an external keyboard, touchpad, or mouse.

[0210] Those skilled in the art will understand that Figure 9 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the medical image processing device to which the present application is applied. A specific medical image processing device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0211] This application also provides a medical image processing device, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement, for example... Figure 2 The following steps are shown:

[0212] S200, based on the target parameters corresponding to the target markers on the blood vessels in the vascular medical image, determines the target scaling factor corresponding to the target markers; the target parameters include the tube diameter parameter and the gray value, wherein the tube diameter parameter and the gray value are both positively correlated with the target scaling factor;

[0213] S400 adjusts the tube diameter parameters corresponding to the target marker points based on the target scaling factor to obtain the processed vascular medical image.

[0214] In one embodiment, when the processor executes the computer program, it also implements other steps of the above-described vascular medical image processing method and achieves corresponding beneficial effects, which will not be elaborated here.

[0215] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0216] S200, based on the target parameters corresponding to the target markers on the blood vessels in the vascular medical image, determine the target scaling factor corresponding to the target markers; the target parameters include the tube diameter parameter and the gray value, wherein the tube diameter parameter and the gray value are positively correlated with the target scaling factor;

[0217] S400 adjusts the tube diameter parameters corresponding to the target marker points based on the target scaling factor to obtain the processed vascular medical image.

[0218] In one embodiment, when the computer program is executed by the processor, it also implements other steps of the above-described vascular medical image processing method and achieves corresponding beneficial effects, which will not be elaborated here.

[0219] In one embodiment, a computer program product is provided, comprising a computer program that, when executed by a processor, implements some or all of the method steps of the above-described vascular medical image processing method and achieves the corresponding beneficial effects.

[0220] It should be noted that the data involved in this application (including but not limited to user data used for analysis, stored data, and displayed data) are all information and data authorized by the user or fully authorized by all parties (such as vascular medical images of the user).

[0221] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic 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 take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0222] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0223] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for processing vascular medical images, characterized in that, The method includes: Based on the target parameters corresponding to target markers on blood vessels in vascular medical images, a target scaling factor corresponding to the target markers is determined. The target parameters include a vessel diameter parameter and a grayscale value, wherein both the vessel diameter parameter and the grayscale value are positively correlated with the target scaling factor. The target markers include markers whose vessel diameter parameter or grayscale value is less than or equal to a corresponding target threshold, and the target scaling factor for the target markers whose vessel diameter parameter or grayscale value is less than or equal to the corresponding target threshold decreases as the absolute value of the difference between the vessel diameter parameter or grayscale value and the corresponding target threshold increases. Based on the target scaling factor, the diameter parameters corresponding to the target marker points are adjusted to obtain the processed vascular medical image, which increases the difference in diameter between thick and thin blood vessels in the processed vascular medical image compared to the unprocessed image.

2. The method according to claim 1, characterized in that, The step of determining the target scaling factor corresponding to the target marker point based on the target parameters corresponding to the target marker point includes: Based on the pipe diameter parameter corresponding to the target marker point, a first scaling factor is determined for the target marker point; the first scaling factor is positively correlated with the pipe diameter parameter. Based on the grayscale value corresponding to the target marker point, a second scaling factor is determined for the target marker point; the second scaling factor is positively correlated with the grayscale value. Based on the first scaling factor, the second scaling factor, and the first nonlinear model corresponding to the target marker point, the target scaling factor corresponding to the target marker point is determined.

3. The method according to claim 2, characterized in that, The step of determining the target scaling factor corresponding to the target marker point based on the first scaling factor, the second scaling factor, and the first nonlinear model corresponding to the target marker point includes: Based on the first scaling factor, the second scaling factor, and the following first nonlinear model corresponding to the target marker point, the target scaling factor corresponding to the target marker point is determined: , in, This represents the target scaling factor corresponding to the target marker point. This indicates the pipe diameter parameter corresponding to the target marker point. This represents the first scaling factor based on the pipe diameter parameter corresponding to the target marker point. This represents the grayscale value of the target marker point. This represents the second scaling factor based on the grayscale value corresponding to the target marker point, where 'a' represents... The weight, b represents The weight.

4. The method according to claim 1, characterized in that, The target scaling factor includes a first scaling factor and a second scaling factor. The steps of determining the target scaling factor corresponding to the target marker point based on the target parameters corresponding to the target marker point, and adjusting the tube diameter parameter corresponding to the target marker point based on the target scaling factor to obtain the processed vascular medical image, include: Based on the pipe diameter parameters corresponding to the target marker point, determine the first scaling factor corresponding to the target marker point; Based on the first scaling factor, the pipe diameter parameters corresponding to the target marker points are adjusted to obtain an intermediate optimized image; For blood vessel branches with consistent diameter parameters in the intermediate optimized image, a second scaling factor corresponding to the target marker point is determined based on the gray value corresponding to the target marker point. For the blood vessel branches with consistent diameter parameters in the intermediate optimized image, the diameter parameters corresponding to the target marker points in the intermediate optimized image are adjusted based on the second scaling factor to obtain the processed vascular medical image.

5. The method according to claim 4, characterized in that, Identify blood vessel branches with consistent diameter parameters, including: Based on the diameter parameters corresponding to the target marker points on each blood vessel branch in the intermediate optimized image, the variance of the diameter parameters of the blood vessel branch is calculated. If the variance is less than the preset variance, then the vascular branch is determined to be a vascular branch with the same diameter parameters.

6. The method according to claim 4 or 5, characterized in that, The step of determining the first scaling factor corresponding to the target marker point based on the pipe diameter parameter corresponding to the target marker point includes: Obtain the diameter parameters corresponding to each marker point on the blood vessel in the vascular medical image; The marker point whose pipe diameter parameter is less than or equal to the first target threshold is selected as the target marker point; Based on the pipe diameter parameters corresponding to the target marker point, a first scaling factor corresponding to the target marker point is determined, wherein the first scaling factor is less than or equal to 1.

7. The method according to claim 6, characterized in that, The steps for determining the first target threshold include: Based on the diameter parameters corresponding to each marker point on all blood vessels in the vascular medical image, the minimum diameter parameter and the maximum diameter parameter are determined; A first threshold is determined based on the minimum pipe diameter parameter and the maximum pipe diameter parameter; wherein the first threshold is greater than the minimum pipe diameter parameter and less than the maximum pipe diameter parameter; The first threshold is used as the first target threshold, or the minimum value between the first threshold and a preset second threshold is used as the first target threshold.

8. The method according to claim 2, 3, 4, 5, or 7, characterized in that, The step of determining the first scaling factor corresponding to the target marker point based on the pipe diameter parameter corresponding to the target marker point includes: Based on the pipe diameter parameters corresponding to the target marker point and the second nonlinear model, a first scaling factor corresponding to the target marker point is determined; wherein, the second nonlinear model is used to characterize the positive correlation mapping relationship between the pipe diameter parameters and the first scaling factor.

9. The method according to claim 4, 5, or 7, characterized in that, The step of determining the second scaling factor corresponding to the target marker point based on the grayscale value of the target marker point includes: Obtain the grayscale value corresponding to each marker point on the blood vessel in the vascular medical image; Select marker points whose grayscale values ​​are less than or equal to the second target threshold as the target marker points; Based on the grayscale value corresponding to the target marker point, a second scaling factor corresponding to the target marker point is determined, wherein the second scaling factor is less than or equal to 1.

10. The method according to claim 9, characterized in that, The steps for determining the second target threshold include: Based on the gray values ​​corresponding to each marker point on all blood vessels in the vascular medical image, the minimum gray value and the maximum gray value are determined; A third threshold is determined based on the minimum grayscale value and the maximum grayscale value; wherein the third threshold is greater than the minimum grayscale value and less than the maximum grayscale value; The third threshold is used as the second target threshold, or the minimum value between the third threshold and the preset fourth threshold is determined to be the second target threshold.

11. The method according to claim 2, 3, 4, 5, 7, or 10, characterized in that, Based on the grayscale value corresponding to the target marker point, a second scaling factor corresponding to the target marker point is determined, including: Based on the gray value corresponding to the target marker point and the third nonlinear model, a second scaling factor corresponding to the target marker point is determined; wherein, the third nonlinear model is used to characterize the positive correlation mapping relationship between the gray value and the second scaling factor.

12. The method according to claim 1, characterized in that, The method further includes: Extract the centerline of the blood vessels from the vascular medical image; The marker point on the center line of the blood vessel is determined as the marker point on the blood vessel; The target markers are at least some of the markers on the blood vessel.

13. The method according to claim 1, 2, 3, 4, 5, 7, 10, or 12, characterized in that, The distance between any two adjacent markers on the blood vessel is less than or equal to a first preset distance value; wherein, the target marker is at least a portion of the markers on the blood vessel.

14. The method according to claim 1, 2, 3, 4, 5, 7, 10, or 12, characterized in that, The step of adjusting the tube diameter parameters corresponding to the target marker points based on the target scaling factor to obtain the processed vascular medical image includes: Determine the sub-segment corresponding to the target marker point on the blood vessel; Based on the target scaling factor, the diameter parameters of the sub-segments corresponding to the target marker points are adjusted to obtain the processed vascular medical image; Wherein, the distance between two endpoints that are close to each other in two adjacent sub-segments is less than or equal to a second preset distance.

15. A vascular medical image processing device, characterized in that, The device includes: A scaling factor determination module is used to determine a target scaling factor corresponding to a target marker point on a blood vessel in a vascular medical image based on target parameters corresponding to the target marker points. The target parameters include a pipe diameter parameter and a grayscale value, wherein both the pipe diameter parameter and the grayscale value are positively correlated with the target scaling factor. The target marker points include marker points whose pipe diameter parameter or grayscale value is less than or equal to a corresponding target threshold, and the target scaling factor for the target marker points whose pipe diameter parameter or grayscale value is less than or equal to the corresponding target threshold decreases as the absolute value of the difference between the pipe diameter parameter or grayscale value and the corresponding target threshold increases. The pipe diameter optimization module is used to adjust the pipe diameter parameters corresponding to the target marker points based on the target scaling factor to obtain the processed vascular medical image, so that the difference in pipe diameter between thick and thin blood vessels in the processed vascular medical image increases compared with the difference before processing.

16. A medical image processing device, comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 14.

17. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 14.

Images