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 comprises the following steps: determining the blood vessel order of each blood vessel branch in a blood vessel medical image; the blood vessel order and a tube diameter parameter of the blood vessel branch are in a first correlation relationship; based on the blood vessel order of the blood vessel branch, a scaling coefficient of each blood vessel branch is determined; the scaling coefficients of different blood vessel branches and the blood vessel order are in a second correlation relationship; based on the scaling coefficient of the blood vessel branch, the tube diameter parameter of the blood vessel branch is adjusted to obtain a processed blood vessel medical image; wherein the first correlation relationship and the second correlation relationship are both positive correlation relationships, or the first correlation relationship and the second correlation relationship are both negative correlation relationships. The processed blood vessel medical image retains the tube diameter characteristics of thick blood vessel branches and the length characteristics of thin blood vessels, improves the white space in the finally presented image, and improves the display effect.

Description

Technical Field

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

[0002] In the visualization of the vascular system, the visualization of vascular branches is particularly important. However, traditional vascular visualization methods generally produce visually coarse vascular branches, resulting in unsatisfactory presentation. Summary of the Invention

[0003] Therefore, it is necessary to provide a vascular image processing method and apparatus, medical image processing equipment, computer storage medium, and computer program product that improves image presentation by optimizing the diameter of blood vessels, 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] Determine the vascular grade of each vascular branch in vascular medical images; the vascular grade is directly correlated with the diameter parameters of the vascular branches.

[0006] Based on the vascular grade of the vascular branches, the scaling factor of the vascular branches is determined; the scaling factor of the vascular branches has a second correlation with the vascular grade.

[0007] Based on the scaling factor of the vascular branches, the diameter parameters of the vascular branches are adjusted to obtain the processed vascular medical image.

[0008] Among them, both the first and second correlations are positive correlations, or both the first and second correlations are negative correlations.

[0009] In one embodiment, the scaling factor of the vascular branch is determined based on the vascular order of the vascular branch, including:

[0010] Based on the vascular order and nonlinear model of vascular branches, the scaling factor of vascular branches is determined; wherein, the nonlinear model is used to characterize the second correlation between the vascular order and the scaling factor of vascular branches.

[0011] In one embodiment, the scaling factor of the vascular branch is determined based on the vascular order of the vascular branch, including:

[0012] Based on the vascular grade of the vascular branches, the scaling factor of the marker points of the vascular branches is determined; wherein, the scaling factor of the marker points is positively correlated with the diameter parameter of the marker points;

[0013] Based on the scaling factor of the vascular branches, the diameter parameters of the vascular branches are adjusted to obtain the processed vascular medical image, including:

[0014] Based on the scaling factor of the marker points, the tube diameter parameters of the marker points are adjusted to obtain the processed vascular medical image.

[0015] In one embodiment, the scaling factor of the marker points of the vascular branches is determined based on the vascular level of the vascular branches, including:

[0016] Based on the number of blood vessels in a blood vessel branch, a first scaling factor and a second scaling factor are determined for the blood vessel branch. The first scaling factor is the scaling factor of the first endpoint of the blood vessel branch, and the second scaling factor is the scaling factor of the second endpoint of the blood vessel branch. The first scaling factor is greater than the second scaling factor, and the diameter parameter of the first endpoint is greater than the diameter parameter of the second endpoint.

[0017] Based on the first scaling factor and the second scaling factor, the scaling factor of the marker point of the vascular branch is determined; wherein the scaling factor of the marker point is less than or equal to the first scaling factor and greater than or equal to the second scaling factor.

[0018] In one embodiment, determining the vascular grade of each vascular branch in a vascular medical image includes:

[0019] Obtain the diameter parameters of each marked point of the blood vessel branch;

[0020] Based on the diameter parameters of each marker point of the vascular branch, the diameter parameters of the vascular branch are obtained.

[0021] Based on the diameter parameters of the vascular branches, the vascular class of the vascular branches is determined.

[0022] In one embodiment, the step of determining the marker point includes:

[0023] Extracting the centerline of blood vessels from vascular medical images;

[0024] The point on the center line of a blood vessel is used as a marker for its branches.

[0025] In one embodiment, determining the vascular grade of each vascular branch in a vascular medical image includes:

[0026] The topology of vascular branches is determined based on the points along the vascular centerline.

[0027] Based on the topology, the vascular order of vascular branches is determined.

[0028] Secondly, a vascular medical image processing device is provided, the device comprising:

[0029] The vessel grade determination module is used to determine the vessel grade of each vessel branch in vascular medical images; the vessel grade is directly correlated with the diameter parameters of the vessel branches.

[0030] The scaling factor determination module is used to determine the scaling factor of a vascular branch based on the vascular level of the vascular branch; the scaling factor of the vascular branch has a second correlation with the vascular level.

[0031] The tube diameter optimization module is used to adjust the tube diameter parameters of blood vessel branches based on the scaling factor of the blood vessel branches to obtain the processed vascular medical image.

[0032] Among them, both the first and second correlations are positive correlations, or both the first and second correlations are negative correlations.

[0033] Thirdly, a medical image processing device is provided, 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 method.

[0034] Fourthly, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the steps of the above-described method.

[0035] The aforementioned vascular medical image processing methods and devices, medical image processing equipment, computer storage media, and computer program products have at least the following beneficial effects:

[0036] This method determines the vessel level of the vascular branches of interest in a vascular medical image. For example, the vessel level can be determined using methods such as Strahler grading (river grading) or clustering. Taking the first and second correlations, both negatively correlated, as an example, a larger vessel diameter corresponds to a smaller vessel level, and vice versa. Further, based on the vessel level, a scaling factor is determined for each vascular branch. A single vascular branch can correspond to one scaling factor or multiple scaling factors. Overall, a smaller vessel level for a vascular branch corresponds to a larger scaling factor, also showing a negative correlation. In other words, the scaling factor for different vascular branches increases with increasing vessel diameter and decreases with decreasing vessel diameter. Optimizing the vascular branches based on the scaling factor yields a processed vascular medical image. This processed image retains the diameter characteristics of large vessels and the length characteristics of small vessels, while also increasing the white space in the final image, thus improving the display effect.

[0037] Understandably, when both the first and second correlations are positive, the positive correlation between the diameter parameters of different vascular branches and the scaling factor is still maintained. The optimized vascular medical image highlights the diameter characteristics of large vascular branches and also preserves the length characteristics of small vascular branches, increasing the white space in the image and improving the display effect. Attached Figure Description

[0038] Figure 1 This is an application environment diagram of a vascular medical image processing method in one embodiment;

[0039] Figure 2 This is a flowchart illustrating a vascular medical image processing method in one embodiment;

[0040] Figure 3 This is a flowchart illustrating a vascular medical image processing method in one embodiment;

[0041] Figure 4 This is a flowchart illustrating a vascular medical image processing method in one embodiment;

[0042] Figure 5 This is a flowchart illustrating a vascular medical image processing method in one embodiment;

[0043] Figure 6 This is a flowchart illustrating a vascular medical image processing method in one embodiment;

[0044] Figure 7 This is a schematic diagram illustrating the relationship between the blood vessel order and the scaling factor under three nonlinear models in one embodiment.

[0045] Figure 8 This is a schematic diagram of a vascular medical image before diameter optimization in one embodiment;

[0046] Figure 9a In one embodiment, based on a nonlinear model A scaling factor is determined, and the pipe diameter parameters are adjusted based on this scaling factor. Figure 8 A schematic diagram of a medical image after adjusting the tube diameter parameters;

[0047] Figure 9b In one embodiment, based on a nonlinear model A scaling factor is determined, and the pipe diameter parameters are adjusted based on this scaling factor. Figure 8 A schematic diagram of a medical image after adjusting the tube diameter parameters;

[0048] Figure 9c In one embodiment, the model is based on a nonlinear model f(x) = 0.9. x A scaling factor is determined, and the pipe diameter parameters are adjusted based on this scaling factor. Figure 8A schematic diagram of a medical image after adjusting the tube diameter parameters;

[0049] Figure 10 This is a structural block diagram of a vascular medical image processing device in one embodiment;

[0050] Figure 11 This is an internal structural diagram of a medical image processing device in one embodiment. Detailed Implementation

[0051] 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.

[0052] The vascular medical image processing method provided in this application embodiment can be applied to, for example... Figure 1 In 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 medical images from the medical scanning device 106 based on the server 104, and process the input 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 scanned medical image and the processed medical image can be generated by the medical image processing device 102.

[0053] 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.

[0054] 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.

[0055] To address the above problems, in one embodiment, such as Figure 2 As shown, this application provides a vascular medical image processing method, which can be applied to... Figure 1 The following steps are used as an example of the medical image processing device 102:

[0056] S202, determine the vascular grade of each vascular branch in the vascular medical image; the vascular grade is primarily correlated with the diameter parameter of the vascular branch. The determination of vascular branches can be achieved based on methods such as centerline extraction, or other image processing methods. The vascular grade reflects the thickness of the blood vessel. When the primary correlation is negative, the vascular grade is negatively correlated with the diameter of the vascular branch; the thicker the blood vessel, the smaller its corresponding vascular grade, and vice versa. When the primary correlation is positive, the thicker the blood vessel, the larger its corresponding vascular grade, and vice versa. Both methods can be used to determine the vascular grade, as long as the primary correlation and the subsequent secondary correlation are both positively correlated or both negatively correlated. That is, ensure that the final determined scaling factor maintains a positive correlation with the blood vessel diameter. However, the process of determining the vessel grade can be independent of obtaining the vessel diameter parameter. For example, when using the Strahler classification method, the vessel grade can be achieved without obtaining the vessel diameter parameter.

[0057] S204. Based on the vascular grade of the vascular branch, determine the scaling factor of the vascular branch. The scaling factor of the vascular branch has a second correlation with the vascular grade. Each vascular branch corresponds to at least one scaling factor. When the scaling factor corresponding to a vascular branch is not unique, the second correlation between the scaling factor of the vascular branch and the vascular grade should be understood as a second correlation between the scaling factors of different vascular branches and the vascular technology of the vascular branch. Taking a negative correlation between the second and first correlations as an example, in this case, the larger the vessel diameter parameter, the smaller its vascular grade, and therefore the larger its scaling factor; conversely, the smaller the vessel diameter parameter, the larger its vascular grade, and therefore the smaller its scaling factor. Overall, based on the determination of the vascular grade, a scaling factor proportional to the vessel diameter parameter can be obtained. Similarly, the process of determining the scaling factor when both the second and first correlations are positively correlated can be understood in a similar way, and will not be elaborated here. The scaling factor corresponding to each vascular branch can be the same. In this case, the entire vascular branch is scaled and adjusted according to the same scaling factor. Each vascular branch can have at least two scaling factors. For example, multiple marker points can be set on a single vascular branch. The scaling factor for each point can be determined on a point-by-point basis so that subsequent scaling adjustments can be made on a point-by-point basis. The scaling factor determined on a point-by-point basis can fully take into account the differences in tube diameter at different points on a single vascular branch. The scaling factor for each point can be determined based on the principle that the scaling factor of different points on a single vascular branch is positively correlated with the tube diameter parameter, thus guiding the subsequent adjustment of the tube diameter parameter.

[0058] S206, Based on the scaling factor of the vascular branches, adjust the diameter parameters of the vascular branches to obtain the processed vascular medical image; wherein, both the first and second correlations are positively correlated, or both are negatively correlated. This scaling refers to scaling the diameter of the vessels presented in the vascular medical image. The process of adjusting based on the scaling factor can be understood as multiplying the diameter parameters of the vascular branches in the vascular medical image by the scaling factor to obtain the adjusted vascular diameter parameters for display. The vascular medical image here can be data generated in the background or data used for display.

[0059] Specifically, when both the first and second correlations are negatively correlated, for at least a portion of the vascular branches in a vascular medical image (which may be vascular branches in a region of interest to the user, such as vascular branches in the heart region of a thoracic vascular medical image), the vascular level of each vascular branch is determined. Based on the vascular level of each vascular branch, at least one scaling factor that is negatively correlated with the vascular level is determined. The scaling factor obtained based on this relationship has the following characteristics: the smaller the diameter parameter, the smaller the scaling factor; the larger the diameter parameter, the larger the scaling factor. The diameter parameter of the corresponding vascular branch is adjusted according to this scaling factor, so that the difference in diameter between thick and thin blood vessels in the scaled medical image is greater than that before processing, realizing the differentiated display between blood vessels of different diameters, increasing the white space, improving the occlusion between vascular branches, and improving the display effect.

[0060] Similarly, when both the first and second correlations are positive, referring to the description and reasoning process of the negative correlation example above, it can be seen that the thicker the blood vessel, the larger the blood vessel level, and the larger the scaling factor; the thinner the blood vessel, the smaller the blood vessel level, and the smaller the scaling factor; the positive correlation between the diameter parameter and the scaling factor can still be maintained. The scaling factor determined based on this relationship is used to guide the adjustment process of the diameter parameters of the blood vessel branches. The adjusted vascular medical image also realizes the differentiated display between blood vessels of different diameters, improves the occlusion between blood vessel branches, and improves the display effect.

[0061] In one embodiment, such as Figure 3 As shown, the scaling factor for vascular branches is determined based on the vascular order of the vascular branches, including:

[0062] S302, based on the vessel level and nonlinear model of vessel branches, the scaling factor of the vessel branches is determined; wherein, the nonlinear model is used to characterize the second correlation between the vessel level and the scaling factor of the vessel branches. The second correlation can be a negative correlation or a positive correlation. Using a nonlinear model to determine the scaling factor, compared with the method based on a linear model, can amplify the difference between the scaling factors of large and small vessels to a greater extent. After adjusting the vessels, the scaling factor obtained in this way will greatly amplify the difference in diameter between large and small vessels in the medical image. This allows the diameter features of large vessels in the displayed area to be magnified, while the diameter of small vessels is reduced to reduce the problem of occlusion between vessels, while the length parameters of small vessels are still retained for user viewing. Optionally, a scaling factor corresponding to each vessel level can be obtained based on the nonlinear model, and vessel branches of the same vessel level share a common scaling factor to guide the adjustment of the diameter parameters. Optionally, when each vascular level corresponds to more than two scaling factors, it can be understood that the scaling factors of vascular branches of different vascular levels as a whole have the mapping relationship with the vascular level as represented by the nonlinear model, while the scaling factor of a single vascular branch can be positively correlated with the diameter parameter.

[0063] Considering that the diameter of a single vascular branch can vary within a certain range, to further improve accuracy when determining the scaling factor, in one embodiment, the scaling factor of the vascular branch is determined based on the vascular level of the branch, such as... Figure 4 As shown, it includes:

[0064] S402, based on the vascular level of the vascular branches, determines the scaling factor of the marker points of the vascular branches; the scaling factor of each marker point is positively correlated with the diameter parameter of the marker point. It is understandable that when the marker points of a vascular branch are not unique, the scaling factor of different marker points on a single vascular branch is positively correlated with the diameter parameter of the marker point. Furthermore, the scaling factor of marker points on different vascular branches is also positively correlated with the overall diameter parameter of the marker points. The marker points of vascular branches can be points on the centerline of the vascular medical image; that is, the determination of the above marker points can be achieved based on methods such as centerline extraction, or based on other image processing methods.

[0065] For each blood vessel in a vascular medical image, multiple marker points for vascular branches are determined based on centerline extraction or other marking rules, providing a basis for subsequent determination of vessel order and adjustment of diameter parameters. For example, multiple marker points can be determined at equal intervals along the extension direction of the vessel centerline in the vascular medical image; alternatively, marker points can be determined at different locations on the vessel branches according to other rules. When using marker points on the vessel centerline as marker points for vessel branch adjustment, the distances from points on the centerline to points on the edge of the vessel cross-section at that point 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 that the cross-sections of the vessel are not necessarily circular but may be irregular in shape. Diameter parameters refer to parameters that reflect the thickness of the vessel, such as vessel radius and vessel diameter.

[0066] Marker points are points on which the vessel diameter parameters will be adjusted. Their selection is based on the principle that adjusting the diameter parameters at these marker points will result in clearer vascular networks and better visual effects in the vascular medical images. Marker points can be selected from some or all of the points along the vessel branches.

[0067] 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 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 used as the center point. Fitting the center points on each interface yields the vessel centerline. The center point can be directly used as a marker point for vessel branches. 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 for vessel branches. Of course, based on the obtained vascular centerline, the marker points of the vascular branches can be remarked to obtain the marker points of the vascular branches. For example, when extracting the centerline from medical images of dark blood 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.

[0068] 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.

[0069] When the marker point of the vascular branch is a marker point on the vascular centerline, the above marker point can be determined based on the extraction of the centerline, determining one endpoint on the centerline as a marker point, and determining each marker point on the centerline based on the extension direction of the centerline along the endpoint, with a first preset distance as the interval between two adjacent marker points.

[0070] If the interval between the marker points of the vascular branches is large, the result of adjusting the vascular diameter parameters based on the marker points will be that a long section of the vascular segment will not be adjusted, which will lead to an abnormal difference in the vascular diameter parameters between the segment and the adjacent marker points.

[0071] Step S206, which adjusts the vessel diameter parameters corresponding to the vessel branches based on the scaling factor corresponding to the vessel branches to obtain the processed vascular medical image, includes:

[0072] S404 adjusts the tube diameter parameters of the marker points based on the scaling factor of the marker points to obtain the processed vascular medical image.

[0073] Specifically, the scaling factor for at least one marker point can be determined first based on the vessel level of the vessel branch. Then, following the principle that the scaling factor of each marker point on a single vessel branch is positively correlated with its corresponding vessel diameter parameter, the scaling factors for other marker points can be determined. Alternatively, this process can begin by determining the scaling factor for at least one marker point based on the vessel level, and then, based on the obtained vessel diameter parameters for each marker point and the constraint of the positive correlation, determine the scaling factors for the remaining marker points. Of course, this process can also be independent of obtaining the vessel diameter parameter. For example, when determining vessel level using the Strahler grading method, during the process of determining the vessel topology, the thicker and thinner ends of the vessel branch can be identified. In this case, the scaling factors for the thicker first endpoint and / or the thinner second endpoint can be determined based on the vessel level. Then, based on the scaling factors of the endpoints and the principle of positive correlation, the scaling factors for other marker points can be determined. Of course, endpoints can also be designated as marker points.

[0074] When adjusting the diameter of selected vascular branch markers, these markers, as a whole, still follow the positive correlation between the diameter parameter and the scaling factor. That is, in the same vascular medical image, the larger the vascular diameter parameter corresponding to the marker point, the larger the scaling factor; the smaller the vascular diameter parameter, the smaller the scaling factor. Based on the scaling factor adjustment, the difference between thick and thin blood vessels in the original image is increased, thus optimizing the visual display effect.

[0075] In one embodiment, the process of adjusting the tube diameter parameter corresponding to the marker point based on the scaling factor can be achieved by traversing the marker points on the center line of the blood vessel.

[0076] In one embodiment, such as Figure 5 As shown, based on the vascular level of the vascular branches, the scaling factor corresponding to the marker point of each vascular branch is determined, including:

[0077] S502, based on the vascular level of the vascular branch, determine the first scaling factor and the second scaling factor of the vascular branch; wherein, the first scaling factor is the scaling factor of the first endpoint of the vascular branch, the second scaling factor is the scaling factor of the second endpoint of the vascular branch, and the first scaling factor is greater than the second scaling factor, and the diameter parameter of the first endpoint is greater than the diameter parameter of the second endpoint. Considering that as blood vessels extend, they mostly exhibit the characteristic of being thicker at one end and thinner at the other, and the change in diameter in the middle is basically linear, based on this characteristic, for each vascular branch, the first scaling factor of its thicker endpoint and the second scaling factor of its thinner endpoint can be determined based on its vascular level. By comparing the diameter parameters of the two endpoints, the endpoint with the larger diameter parameter can be determined as the first endpoint, and then the scaling factor of the first endpoint can be determined as the first scaling factor, and the scaling factor of the second endpoint can be determined as the second scaling factor. In addition to determining the correspondence between the endpoints and the first and second scaling factors based on the diameter parameters, other methods can also be used to achieve this. For example, when determining the vascular grading based on the Strahler grading method, the blood supply end can be identified as the root node. During the traversal, the endpoint on the vascular branch that is closer to the root node is identified as the first endpoint, and the scaling factor of this endpoint is identified as the first scaling factor. This process does not require the acquisition of the tube diameter parameter.

[0078] S504, based on the first and second scaling factors, determine the scaling factors of the marker points on the vascular branches; the scaling factor of the marker points is less than or equal to the first scaling factor and greater than or equal to the second scaling factor. After determining the first and second scaling factors, within the range determined by both, the scaling factor of each marker point on the vascular branch can be determined according to certain rules. Based on the requirements of calculation speed and accuracy, some points on the vascular branch can be selected as marker points to determine the scaling factor of the diameter of each marker point. For example, within the interval [min, max] (where max is the first scaling factor and min is the second scaling factor), the scaling factor of each marker point can be determined according to nonlinear rules or linear change rules. Alternatively, the scaling factor of each marker point can be determined according to an arithmetic progression rule, uniformly scaling the diameter of each marker point on the vascular branch. Using the marker points as the adjustment unit, the diameter parameters are adjusted. In the optimized vascular medical image, the vascular branches have a gradient effect; the closer to the root node of the vascular branch topology, the thicker the vascular diameter, and the farther away from the root node, the thinner the vascular diameter. Based on this method, there is also a gradient effect for blood vessel branches with the same diameter parameters on the same branch, which can show the hierarchical relationship of blood vessels.

[0079] It should be noted that the above-mentioned marker points may include the two endpoints of the vascular branch, and the marker points may also include these two endpoints. The adjustment of the diameter parameters of these two endpoints is based on the above-mentioned first scaling factor and second scaling factor, respectively.

[0080] In one embodiment, determining the scaling factor of the marker points for the vascular branches based on the first scaling factor and the second scaling factor includes:

[0081] Based on the first scaling factor, the second scaling factor, and the following expression, the scaling factor of the marker points for the vascular branches is determined:

[0082]

[0083] Where f(n) is the scaling factor of the nth marker on the vascular branch, with the first endpoint as the first marker and arranged in ascending order towards the second endpoint; max is the first scaling factor; min is the second scaling factor; and m is the number of markers on the vascular branch. The first endpoint is the first marker, and its scaling factor is the first scaling factor max. The second endpoint is the mth marker, and its scaling factor is the second scaling factor min. The scaling factors of the markers between the first and second endpoints are evenly distributed, decreasing sequentially from the first marker to the mth marker. Vascular medical images processed in this way can more vividly display the diameter changes of a single vascular branch. Different scaling factors are assigned to the positions of different diameter parameters on a single vascular branch. After adjustment, the differences in diameter parameters at various points on a single vascular branch are also greater than before adjustment, further improving the display effect.

[0084] In one embodiment, the tube diameter parameters of the marker points are adjusted based on the scaling factor of the marker points to obtain a processed vascular medical image, including:

[0085] The sub-segments corresponding to the marker points of the vascular branches are determined; a sub-segment refers to a segment of the vascular body determined based on the marker points and segmentation rules. The segmentation rules may include, but are not limited to, the rules exemplified in the embodiments of this application.

[0086] Based on the scaling factor of the marker points, the diameter parameters of the sub-segments corresponding to the marker points are adjusted to obtain the processed vascular medical image; for example, a sub-segment can be the part between two adjacent marker points on the center line of the blood vessel, which can be a straight line segment or a curve.

[0087] In this system, 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 blood vessel portion between two adjacent marker points. Alternatively, depending on the required precision of the tube diameter adjustment, a second preset distance that is infinitely small but not zero can be set.

[0088] When the distance between adjacent marker points is greater than a third preset distance, the sub-segment corresponding to this type of marker point is determined. The sub-segmentation rule can be based on the current marker point as the starting point, extending along the vessel's extension direction, with the next marker point as the ending point, defining the segment containing the vessel between the two marker points as the sub-segment corresponding to the current marker point. Alternatively, it can be based on the current marker point A as the center, using the distance D1 between A and its left-adjacent marker point B, and the distance D2 between A and its right-adjacent marker point 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 marker point A as the center, using a preset radius along the vessel's extension direction to define the vessel segment within that radius as the sub-segment corresponding to A. In summary, there can be various rules for sub-segmentation, but the general principle is that the interval between two adjacent sub-segments cannot exceed the second preset distance, to ensure that nearby vessels still exhibit smooth changes after adjusting the vessel diameter parameters.

[0089] In one embodiment, the vascular grade of each vascular branch in the vascular medical image is determined, such as... Figure 6 As shown, it includes:

[0090] S602, obtain the diameter parameters of each marker point of the blood vessel branch. Diameter parameters refer to parameters that reflect the thickness of the blood vessel, such as the vessel radius and vessel diameter.

[0091] S604. Based on the diameter parameters of each marker point of the vascular branch, the diameter parameters of the vascular branch are obtained. The diameter parameters of a vascular branch refer to parameters that reflect the thickness of the vascular branch's diameter. For example, it can refer to the set of diameter parameters of each marker point of the vascular branch, or it can refer to the average diameter parameter of the vascular branch. The diameter parameters of the marker points can be determined based on the extraction of the centerline. For example, the distance from the marker point on the centerline to the vessel wall can be calculated as the vessel radius. Alternatively, a straight line passing through the marker point on the vascular cross-section can be determined, and the vessel diameter at that marker point can be determined based on the length of the line segment between the two intersection points of this line and the vessel wall. Of course, the determination method is not limited to the examples given here; the diameter parameters can also be obtained based on other image processing algorithms, which will not be exhaustively listed here. Based on the diameter parameters of each marker point, the diameter parameters of each vascular branch can be calculated. For example, the average diameter parameter of a blood vessel branch can also characterize the thickness of the blood vessel. Considering that the diameter parameter of a single blood vessel branch will not change too much, the average diameter parameter can be used to directly determine the blood vessel grade. This is fast and can ensure calculation accuracy, achieving a balance between the two.

[0092] S606, Determine the vessel class of the vessel branch based on its diameter parameters. Here, it is still based on the first correlation relationship, determining the matching vessel class according to the diameter parameters of the vessel branch.

[0093] Determining the vessel class by analyzing the diameter parameters of vessel branches can be achieved using clustering. Various clustering algorithms can be employed, such as K-MEANS, K-MEDOIDS, and CLARANS algorithms, as well as hierarchical clustering methods like BIRCH, CURE, and CHAMELEON. These will not be exhaustively listed here. The difference in diameter parameters between vessel branches within the same cluster should not exceed a preset threshold, and the diameter parameters of vessel branches should differ across different clusters. The same vascular level is assigned to each vascular branch in each cluster set, and different vascular levels are assigned to vascular branches in different cluster sets. The vascular levels corresponding to different cluster sets also follow the first correlation mentioned above. For example, if the average diameter parameter in cluster set M is between [c, d], and the average diameter parameter of the vascular branches in cluster set N is between [e, f], where e > d, then when the first correlation is negative, the vascular level h corresponding to each vascular branch in cluster set M is greater than the vascular level j corresponding to each vascular branch in cluster set N.

[0094] In one embodiment, determining the marker point may include the following steps:

[0095] 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.

[0096] Points on the center line of a blood vessel are designated as markers for its branches.

[0097] In one embodiment, determining the vascular grade of each vascular branch in a vascular medical image includes the following steps:

[0098] The topological structure of vascular branches is determined based on points on the vascular centerline.

[0099] Based on the topology, the vascular order of vascular branches is determined.

[0100] The topological structure of vascular branches can be determined by the degree of points on the vascular centerline. Specifically, the degree of points on the vascular centerline can be determined based on the extraction of the centerline. For each point in the vascular medical image, points on the centerline are assigned a value of 1, and points not on the centerline are assigned a value of 0. The degree of a point is determined by whether it has adjacent points and the number of adjacent points. The number of adjacent points of the current point is the degree of the current point. Based on the degree, points on the centerline can be classified into endpoints (points 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 points).

[0101] Based on the degree of points on the centerline, the branches of blood vessels in a vascular medical image can be determined. For example, this can be done by traversing the points on the centerline and determining the branches of blood vessels in the medical image based on the degree of the points. Endpoints with a degree greater than or equal to 3 indicate that the end of that point is connected to other blood vessel branches; points with a degree of 1 indicate that the end of that blood vessel branch is not connected to other blood vessel branches, and are either the start or end point of the blood vessel; while points with a degree of 2 are points in the middle of the endpoints. Based on this, the blood vessel branches can be determined. For example, a point on the centerline can be used as a seed point to traverse the marked points. During the traversal, each blood vessel branch (the part between two endpoints) can be determined, and the start and end points of the blood vessels can be identified.

[0102] The starting point here refers to the point with the largest pipe diameter parameter among the points with a degree of 1. The ending point refers to the other points with a degree of 1.

[0103] 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, which can then be used as the seed node. Following the direction from the seed node to the next point, the degree of the next point is determined to identify its type (endpoint, point between two endpoints on the centerline). This next point is then updated as the seed node. This process of "following the direction from the seed node to the next point, determining the degree of the next point, and then determining its type" is repeated until all points on the centerline 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.

[0104] In one embodiment, the vascular grade of each vascular branch can be determined by traversing the points on the centerline, based on the average diameter parameter and grading threshold of the current vascular branch during the traversal process.

[0105] First, the vessel level of the branch containing the root node can be determined; the root node can be the marker point with the largest diameter parameter. By searching through the root node, the vessel branch containing the root node is identified, and a vessel level is assigned to this branch, providing a reference for determining the vessel levels of other branches. If the absolute difference between the average diameter parameter of the current vessel branch and the average diameter parameter of the previous vessel branch is greater than the grading threshold, then the current vessel branch and the previous vessel branch belong to different cluster sets, and the current vessel branch is assigned a different vessel level than the previous vessel branch. If the absolute difference between the average diameter parameter of the current vessel branch and the average diameter parameter of the previous vessel branch is less than or equal to the grading threshold, then the current vessel branch and the previous vessel branch belong to the same cluster set, and the current vessel branch is assigned the same vessel level as the previous vessel branch.

[0106] Specifically, the determination and traversal of marker points, as well as the search for root nodes, can be achieved by extracting the centerline of the vascular branches. Taking a negative correlation as an example, based on the hierarchical clustering method, the vascular branches are traversed starting from the determined root node (the traversal of vascular branches can be achieved by traversing the centerline). The vascular branch where the root node is located is divided into the first cluster set (the determination of vascular branches can be found in the above embodiment). If the absolute difference between the average diameter parameter of the next vascular branch and the average diameter parameter of the vascular branch where the root node is located is greater than the grading threshold, the next vascular branch is divided into the second cluster set; otherwise, the next vascular branch is divided into the first cluster set. This process continues. If the change in the average diameter parameter of the next vascular branch compared to the average diameter parameter of the current vascular branch exceeds the grading threshold, the next vascular branch is identified as a vascular branch in another cluster set, and the vascular level corresponding to the next vascular branch is determined to be y+1, where y is the vascular level corresponding to the current vascular branch. Through iteration, vascular branches with adjacent average diameter parameters are grouped into a set. The grading threshold can be pre-set based on experiments and user feedback.

[0107] Besides using clustering to determine the number of blood vessels, the topology can also be determined based on centerline extraction, as described in the above embodiments, to determine the number of blood vessels. First, the topology of each blood vessel branch is determined. This process can be based on centerline extraction, traversing all blood vessel branches to find the branch containing the root node. Referring to the description in the above embodiments, during the traversal of each marked point on the centerline, it is possible to determine which are branch points (endpoints with a degree greater than or equal to 3), start points, and end points, thereby determining the topology.

[0108] Specifically, the Strahler grading method can be used to determine the vascular topology based on centerline extraction, and then determine the vascular level based on the topology to achieve vascular grading. On this basis, a nonlinear / linear transformation model is used for the vascular level, where each level uses a different scaling factor to obtain the scaling factors for each vascular branch. Then, based on these scaling factors, the diameter parameters of the vascular branches are optimized. The diameter parameter can be either diameter or radius.

[0109] When the primary correlation is negative, the scaling factor determined based on the topological structure can be determined by traversing all vascular branches along the entire centerline to determine the maximum number of vascular layers. Then, traversing all vascular branches and calculating the corresponding scaling factor for each branch, and finally traversing all marker points on the current vascular branch and adjusting the vascular diameter parameters at each marker point to obtain a vascular medical image.

[0110] After adjusting the diameter parameters, the blood vessels in the 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 can be colored with different colors or different gray levels to improve the display effect of the processed vascular medical image.

[0111] Of course, it should be noted that, in addition to the examples mentioned above, nonlinear models can also employ other polynomial models such as exponential transformation, logarithmic transformation, and polynomial transformation.

[0112] In one embodiment, when the first correlation is negative, determining a scaling factor matching the vascular level based on the vascular branching order and nonlinear model may include:

[0113] When the first correlation is negative, an exponential operation on the number of blood vessels is performed based on the first constant to determine the scaling factor that matches the blood vessel branches; the first constant is less than 1.

[0114] For example, the first constant can be 0.9, and the scaling factor can be determined using the following expression:

[0115] f(x) = 0.9 x x∈[0, A-1];

[0116] Where f(x) represents the scaling factor corresponding to the blood vessel branch with blood vessel level x, and x represents the blood vessel level of the blood vessel branch.

[0117] The vessel level of the branch containing the root node is 0, and the scaling factor decreases as the vessel level increases. A represents the highest vessel level among the vessel branches. When the first correlation is negative, the branch with the highest vessel level is usually the branch containing the leaf nodes. For the vessel branch containing the root node, the scaling factor is 1, and its diameter parameters are not adjusted. This keeps the diameter parameters of thicker vessels unchanged, while thinner vessels can be optimized into even thinner vessels, thereby improving the presentation of vascular medical images.

[0118] In one embodiment, when the first correlation is negative, determining a scaling factor matching the vascular level based on the vascular branching order and nonlinear model may include:

[0119] Determine the maximum vascular grade;

[0120] Based on the vascular order of vascular branches, a power operation result that increases with the increase of the vascular order is determined;

[0121] Based on the difference between the result of 1 and the exponentiation, the scaling factor that matches the vascular branch is determined.

[0122] Among them, exponentiation can be performed using or The expression is used to determine the vascular level, where A represents the highest vascular level among the vascular branches, and x represents the vascular level of the vascular branch.

[0123] In some embodiments, the process of determining the scaling factor matching the vascular branch based on the difference between 1 and the result of the exponentiation can be implemented based on the following expression:

[0124]

[0125] f(x) represents the scaling factor corresponding to the blood vessel branch with blood vessel level x, where x represents the blood vessel level of the blood vessel branch, and A represents the maximum blood vessel level in the blood vessel tree. When the first correlation is negative, the root node level is 0, and the blood vessel branch with the maximum blood vessel level is usually the blood vessel branch containing the leaf node. Based on experiments, the effect of blood vessel diameter optimization under this expression is more in line with clinical expectations. The scaling degree of the first few levels of thicker blood vessel branches is much smaller and can be relatively ignored, which well preserves the information of the diameter dimension of the first few levels of blood vessels. It also optimizes the visual presentation effect by optimizing the diameter parameters of thinner blood vessels.

[0126] In some embodiments, when the first correlation is negative, the process of determining the scaling factor matching the vascular branch based on the difference between 1 and the result of the exponentiation can be implemented based on the following expression:

[0127]

[0128] f(x) represents the scaling factor corresponding to the blood vessel branch with blood vessel level x, where x represents the blood vessel level of the blood vessel branch. The blood vessel level of the blood vessel branch where the root node is located is 0. A represents the maximum blood vessel level in the blood vessel tree. The branch with the maximum blood vessel level is usually the blood vessel branch where the leaf node is located.

[0129] like Figure 7 This is a schematic diagram showing the relationship between the number of blood vessels and the scaling factor under the three nonlinear models mentioned above.

[0130] To better illustrate the beneficial effects achieved by the method provided in the embodiments of this application, a vascular medical image of a vein in the liver is used as an example for explanation. Figure 8 It displays original medical images of blood vessels. Figures 9a-9c The processed vascular medical images are shown. 9a represents a nonlinear model. The adjusted vascular medical image corresponding to the determined scaling factor, 9b is a nonlinear model. The adjusted vascular medical image corresponding to the determined scaling factor, 9c is a nonlinear model f(x) = 0.9x The adjusted vascular medical image corresponding to the determined scaling factor. In the three sets of results, The nonlinear model-based optimization of vessel diameter best matches clinical expectations, satisfying two characteristics: vessels with smaller vessel orders have a large scaling factor, close to 1, which can be ignored; and... Figure 7 As shown, for vascular branches with smaller vessel levels, the difference in vessel scaling factors between adjacent vessel levels is not significant, meaning that the scaling adjustment for larger vessels is relatively gradual, better preserving the characteristics of their diameter dimension. However, as... Figure 7 As shown, for larger vessel levels, the difference between the scaling factors of adjacent vessel levels increases, and as the vessel level increases, the slope of the scaling factor of the corresponding point is greater. Based on this characteristic, in the processed vascular medical image, thicker vessels can better retain their diameter features, while thinner vessels can have their diameter reduced to a large extent to reduce the occlusion of branches of thicker vessels and increase the blank space.

[0131] 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.

[0132] 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.

[0133] In one embodiment, such as Figure 10 As shown, a vascular medical image processing device is provided, the device comprising:

[0134] The vessel grade determination module 1002 is used to determine the vessel grade of each vessel branch in a vascular medical image; the vessel grade is in a primary correlation with the diameter parameter of the vessel branch;

[0135] The scaling factor determination module 1004 is used to determine the scaling factor of the vascular branch based on the vascular level of the vascular branch; the scaling factor of the vascular branch has a second correlation with the vascular level.

[0136] The diameter optimization module 1006 is used to adjust the diameter parameters of the vascular branches based on the scaling factor of the vascular branches to obtain the processed vascular medical image.

[0137] Among them, both the first and second correlations are positive correlations, or both the first and second correlations are negative correlations.

[0138] The definitions of all terms are provided in the descriptions in the above embodiments and will not be repeated here. Specifically, the vessel level determination module 1002 determines the vessel level of each vessel branch in the vascular medical image. The scaling factor determination module 1004 determines the scaling factor of the vessel branch based on the vessel level. The diameter optimization module 1006 adjusts the diameter parameters of the vessel branch based on the scaling factor to obtain the processed vascular medical image.

[0139] In one embodiment, the scaling factor determination module 1004 includes:

[0140] The first scaling factor determination unit is used to determine the scaling factor of the vascular branch based on the vascular order and nonlinear model; wherein, the nonlinear model is used to characterize the second correlation between the vascular order and the scaling factor of the vascular branch.

[0141] In one embodiment, the scaling factor determination module 1004 includes:

[0142] The second scaling factor determination unit is used to determine the scaling factor of the marker point of the blood vessel branch based on the blood vessel level of the blood vessel branch; wherein, the scaling factor of the marker point is positively correlated with the diameter parameter of the marker point;

[0143] Pipe diameter optimization module 1006 includes:

[0144] The first optimization unit is used to adjust the tube diameter parameters of the marker points based on the scaling factor of the marker points to obtain the processed vascular medical image.

[0145] In one embodiment, the second scaling factor determining unit includes:

[0146] The third scaling factor determination unit is used to determine the first scaling factor and the second scaling factor of the vascular branch based on the vascular level of the vascular branch; wherein the first scaling factor is the scaling factor of the first end of the vascular branch, the second scaling factor is the scaling factor of the second end of the vascular branch, and the first scaling factor is greater than the second scaling factor, and the diameter parameter of the first end is greater than the diameter parameter of the second end.

[0147] The fourth scaling factor determination unit is used to determine the scaling factor of the marker point of the vascular branch based on the first scaling factor and the second scaling factor; wherein the scaling factor of the marker point is less than or equal to the first scaling factor and greater than or equal to the second scaling factor.

[0148] In one embodiment, the fourth scaling factor determination unit includes:

[0149] The scaling factor calculation unit is used to determine the scaling factor of the marker points of the blood vessel branches based on the first scaling factor, the second scaling factor, and the following expression:

[0150]

[0151] Where f(n) is the scaling factor of the nth marker on the blood vessel branch with the first endpoint as the first marker and arranged in ascending order towards the second endpoint, max is the first scaling factor, min is the second scaling factor, and m is the number of markers on the blood vessel branch.

[0152] In one embodiment, the blood vessel grade determination module 1002 includes:

[0153] The marker point parameter acquisition unit is used to acquire the diameter parameters of each marker point of the blood vessel branch;

[0154] The diameter acquisition unit is used to obtain the diameter parameters of the blood vessel branches based on the diameter parameters of each marker point of the blood vessel branch;

[0155] The first vessel class determination unit is used to determine the vessel class of a vessel branch based on the diameter parameters of the vessel branch.

[0156] In one embodiment, the device further includes:

[0157] The centerline information acquisition unit is used to extract the centerline of blood vessels in vascular medical images;

[0158] Topology determination unit, used to identify points on the centerline of a blood vessel as markers for blood vessel branches.

[0159] In one embodiment, the blood vessel grade determination module 1002 includes:

[0160] The topological structure of vascular branches is determined based on points on the vascular centerline.

[0161] Based on the aforementioned topology, the vascular order of the vascular branches is determined.

[0162] 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.

[0163] In one embodiment, a medical image processing device is provided. This medical image processing device may be a terminal, and its internal structure diagram may be as follows: Figure 11 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.

[0164] Those skilled in the art will understand that Figure 11 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.

[0165] In one embodiment, a medical image processing device is provided, including a memory and a processor, the memory storing a computer program, the processor executing the computer program to perform the following steps:

[0166] Determine the vascular grade of each vascular branch in vascular medical images; the vascular grade is directly correlated with the diameter parameters of the vascular branches.

[0167] Based on the vascular grade of the vascular branches, the scaling factor of the vascular branches is determined; the scaling factor of the vascular branches has a second correlation with the vascular grade.

[0168] Based on the scaling factor of the vascular branches, the diameter parameters of the vascular branches are adjusted to obtain the processed vascular medical image.

[0169] Among them, both the first and second correlations are positive correlations, or both the first and second correlations are negative correlations.

[0170] In one embodiment, the processor further performs the following steps when executing the computer program:

[0171] Based on the vascular order and nonlinear model of vascular branches, the scaling factor of vascular branches is determined; wherein, the nonlinear model is used to characterize the second correlation between the vascular order and the scaling factor of vascular branches.

[0172] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0173] Based on the vascular grade of the vascular branches, the scaling factor of the marker points of the vascular branches is determined; wherein, the scaling factor of the marker points is positively correlated with the diameter parameter of the marker points;

[0174] Based on the scaling factor of the marker points, the tube diameter parameters of the marker points are adjusted to obtain the processed vascular medical image.

[0175] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0176] Based on the number of blood vessels in a blood vessel branch, a first scaling factor and a second scaling factor are determined for the blood vessel branch. The first scaling factor is the scaling factor of the first endpoint of the blood vessel branch, and the second scaling factor is the scaling factor of the second endpoint of the blood vessel branch. The first scaling factor is greater than the second scaling factor, and the diameter parameter of the first endpoint is greater than the diameter parameter of the second endpoint.

[0177] Based on the first scaling factor and the second scaling factor, the scaling factor of the marker point of the vascular branch is determined; wherein the scaling factor of the marker point is less than or equal to the first scaling factor and greater than or equal to the second scaling factor.

[0178] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0179] Based on the first scaling factor, the second scaling factor, and the following expression, the scaling factor of the marker points for the vascular branches is determined:

[0180]

[0181] Where f(n) is the scaling factor of the nth marker on the blood vessel branch, which is arranged in ascending order from the first endpoint to the second endpoint, max is the first scaling factor, min is the second scaling factor, and m is the number of markers on the blood vessel branch.

[0182] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0183] Obtain the diameter parameters of each marked point of the blood vessel branch;

[0184] Based on the diameter parameters of each marker point of the vascular branch, the diameter parameters of the vascular branch are obtained.

[0185] Based on the diameter parameters of the vascular branches, the vascular class of the vascular branches is determined.

[0186] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0187] Extracting the centerline of blood vessels from vascular medical images;

[0188] Points on the center line of a blood vessel are designated as markers for its branches.

[0189] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0190] The topological structure of vascular branches is determined based on points on the vascular centerline.

[0191] Based on the topology, the vascular order of vascular branches is determined.

[0192] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, it implements other steps of the above-described vascular medical image processing method and achieves corresponding beneficial effects, which will not be elaborated here.

[0193] In one embodiment, a computer program product is provided, comprising a computer program that, when executed by a processor, implements other steps of the above-described vascular medical image processing method and achieves corresponding beneficial effects, which will not be elaborated here.

[0194] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0195] 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.

[0196] 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.

[0197] 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: Determine the vascular grade of each vascular branch in a vascular medical image; the vascular grade is in a first correlation with the diameter parameter of the vascular branch; Based on the vascular grade of the vascular branch, the scaling factor of the vascular branch is determined; the scaling factor of the vascular branch has a second correlation with the vascular grade. Based on the scaling factor of the vascular branch, the diameter parameters of the vascular branch are adjusted to obtain the processed vascular medical image. Both the first correlation and the second correlation are negative correlations. Determining the scaling factor of the vascular branch based on the vascular order of the vascular branch includes: Based on the vascular grade of the vascular branch, the scaling factor of the marker point of the vascular branch is determined; wherein, the scaling factor of the marker point is positively correlated with the diameter parameter of the marker point; The process of adjusting the diameter parameters of the blood vessel branches based on their scaling factors to obtain the processed vascular medical image includes: Based on the scaling factor of the marker points, the tube diameter parameters of the marker points are adjusted to obtain the processed vascular medical image; The steps for determining the marker points include: Extract the centerline of the blood vessels from the vascular medical image; The points on the center line of the blood vessel are designated as the marking points of the blood vessel branches; The step of determining the scaling factor of the vascular branch based on the vascular order of the vascular branch further includes: Determine the maximum vascular grade; Based on the vessel order of the vessel branch, the maximum vessel order, and a nonlinear model, the scaling factor of the vessel branch is determined; wherein, the nonlinear model is used to characterize the second correlation between the vessel order and the scaling factor of the vessel branch; the nonlinear model is: f(x) represents the scaling factor corresponding to the blood vessel branch with blood vessel level x, where x represents the blood vessel level of the blood vessel branch, and A represents the maximum blood vessel level in the blood vessel tree.

2. The method according to claim 1, characterized in that, The process of determining the scaling factor of the marker points of the vascular branches based on the vascular order of the vascular branches includes: Based on the vascular grade of the vascular branch, a first scaling factor and a second scaling factor of the vascular branch are determined; wherein, the first scaling factor is the scaling factor of the first endpoint of the vascular branch, the second scaling factor is the scaling factor of the second endpoint of the vascular branch, and the first scaling factor is greater than the second scaling factor, and the diameter parameter of the first endpoint is greater than the diameter parameter of the second endpoint. Based on the first scaling factor and the second scaling factor, the scaling factor of the marker point of the blood vessel branch is determined; wherein the scaling factor of the marker point is less than or equal to the first scaling factor and greater than or equal to the second scaling factor.

3. The method according to claim 1, characterized in that, The determination of the vascular grade of each vascular branch in a vascular medical image includes: Obtain the diameter parameters of each marked point of the blood vessel branch; Based on the diameter parameters of each marker point of the blood vessel branch, the diameter parameters of the blood vessel branch are obtained. Based on the diameter parameters of the blood vessel branch, the vascular grade of the blood vessel branch is determined.

4. The method according to claim 3, characterized in that, The determination of the vascular grade of each vascular branch in a vascular medical image includes: The topology of the blood vessel branches is determined based on the points on the center line of the blood vessel. Based on the topology, the vascular order of the vascular branch is determined.

5. A vascular medical image processing device, characterized in that, The device includes: A vessel grade determination module is used to determine the vessel grade of each vessel branch in a vascular medical image; the vessel grade is in a first correlation with the diameter parameter of the vessel branch; The scaling factor determination module is used to determine the scaling factor of the blood vessel branch based on the blood vessel level of the blood vessel branch; the scaling factor of the blood vessel branch has a second correlation with the blood vessel level; The diameter optimization module is used to adjust the diameter parameters of the blood vessel branch based on the scaling factor of the blood vessel branch to obtain the processed vascular medical image. Both the first correlation and the second correlation are negative correlations. The scaling factor determination module includes: The second scaling factor determination unit is used to determine the scaling factor of the marker point of the blood vessel branch based on the blood vessel level of the blood vessel branch; wherein the scaling factor of the marker point is positively correlated with the diameter parameter of the marker point; The pipe diameter optimization module includes: The first optimization unit is used to adjust the tube diameter parameter of the marker point based on the scaling factor of the marker point to obtain the processed vascular medical image; The vascular medical image processing device further includes: A centerline information acquisition unit is used to extract the centerline of blood vessels in the vascular medical image. A topology determination unit is used to determine points on the center line of the blood vessel as marker points for the blood vessel branches; The scaling factor determination module is also used for: Determine the maximum vascular grade; Based on the vessel order of the vessel branch, the maximum vessel order, and a nonlinear model, the scaling factor of the vessel branch is determined; wherein, the nonlinear model is used to characterize the second correlation between the vessel order and the scaling factor of the vessel branch; the nonlinear model is: f(x) represents the scaling factor corresponding to the blood vessel branch with blood vessel level x, where x represents the blood vessel level of the blood vessel branch, and A represents the maximum blood vessel level in the blood vessel tree.

6. 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 4.

7. 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 4.

Images