Image processing method and device, computer device and storage medium

Abstract

The application relates to an image processing method and device, computer equipment and a storage medium. The method comprises the following steps: obtaining a matching result of a control point in a mask image and a matching point in a plurality of frame overexposed images; the mask image and the plurality of frame overexposed images are images of the same part; performing modulation processing on the position of the matching point in the plurality of frame overexposed images according to the matching result of the plurality of frame overexposed images; performing conversion on the mask image based on the conversion relationship between the plurality of frame overexposed images after modulation and the mask image; and subtracting the converted mask image from the plurality of frame overexposed images to obtain a plurality of frame blood vessel images. The method can reduce the inconsistency of the false shape of the plurality of frame blood vessel images.

Description

TECHNICAL FIELD

[0001] The present application relates to the image technical field, and in particular to an image processing method and device, computer equipment and storage medium. BACKGROUND

[0002] Digital subtraction angiography (DSA) is a process of subtraction, enhancement and re-imaging, which subtracts a pre-contrast image from a post-contrast image to obtain a plurality of blood vessel images in time sequence.

[0003] In the related art, when the post-contrast image is obtained, due to various movements of the target object, for example, the movements of the target object include breathing, muscle movement, heart movement, etc., the obtained blood vessel image has artifacts. In order to weaken the artifacts in the blood vessel image, when the blood vessel image is obtained, the pre-contrast image and the post-contrast image are usually transformed to obtain a plurality of blood vessel images with weakened artifacts.

[0004] However, the method of the related art has the problem that the artifact forms of the plurality of blood vessel images are inconsistent. SUMMARY

[0005] Therefore, it is necessary to provide an image processing method, device, computer equipment and storage medium to solve the problem of inconsistency of the artifact forms of the plurality of blood vessel images.

[0006] In a first aspect, the present application provides an image processing method, which comprises:

[0007] obtaining a matching result of a control point in a pre-contrast image and a matching point in a plurality of post-contrast images; the pre-contrast image and the plurality of post-contrast images are images of the same part;

[0008] modulating the positions of the matching points in the plurality of post-contrast images according to the matching result of the plurality of post-contrast images;

[0009] transforming the pre-contrast image based on a conversion relationship between the plurality of post-contrast images after modulation and the pre-contrast image;

[0010] subtracting the transformed pre-contrast image from the plurality of post-contrast images after modulation to obtain blood vessel images corresponding to the plurality of post-contrast images.

[0011] In one of the embodiments, the obtaining of the matching result of the control point in the pre-contrast image and the matching point in the plurality of post-contrast images comprises:

[0012] dividing the control points in the mask image to obtain a plurality of control point sets, and dividing the matching points in the plurality of frame excess images to obtain a plurality of matching point sets of each frame excess image; wherein the control points in the mask image and the corresponding matching points in each frame excess image correspond to a same structure position;

[0013] matching each control point set with the corresponding matching point set in the plurality of frame excess images to obtain a matching result.

[0014] In one embodiment, the control points in the mask image are divided to obtain a plurality of control point sets, and the matching points in the plurality of frame excess images are divided to obtain a plurality of matching point sets of each frame excess image, including:

[0015] triangulating the control points to obtain a plurality of control point triangles, and triangulating the matching points in the plurality of frame excess images to obtain a plurality of matching point triangles;

[0016] wherein the three corner points in each control point triangle and the three corner points in each matching point triangle have a spatial order, and each control point triangle corresponds to a control point set, and each matching point triangle corresponds to a matching point set.

[0017] In one embodiment, the plurality of control point sets in the mask image are matched with the plurality of matching point sets in each frame excess image to obtain a matching result, including:

[0018] For any target frame excess image, the spatial order of the control point set in the mask image and the spatial order of the matching point set in the target frame excess image are obtained;

[0019] the spatial order of the control point set is matched with the spatial order of the matching point set;

[0020] If the spatial order of the control point set is the same as the spatial order of the matching point set, it is determined that the matching result is a matching success; if the spatial order of the control point set is not the same as the spatial order of the matching point set, it is determined that the matching result is a matching failure.

[0021] In one embodiment, according to the matching result of the plurality of frame excess images, the matching point positions in the plurality of frame excess images are modulated, including:

[0022] For any target frame excess image, if the target frame excess image is a first frame excess image, the first frame excess image is modulated according to the matching result of the target frame excess image and the position of the control point in the mask image;

[0023] If the target frame overexposed image is not the first frame overexposed image, the matching point position in the target frame overexposed image is modulated according to the matching result of the target frame overexposed image and the matching point position in the last frame overexposed image of the target frame overexposed image.

[0024] In one embodiment, the matching point position in the target frame overexposed image is modulated according to the matching result of the target frame overexposed image and the matching point position in the last frame overexposed image of the target frame overexposed image, including:

[0025] If the matching result is a matching success, the inter-frame displacement of the target frame overexposed image is obtained; the inter-frame displacement represents the displacement between the matching point position in the target frame overexposed image and the matching point position in the last frame overexposed image.

[0026] The matching point position in the target frame overexposed image is modulated according to the inter-frame displacement.

[0027] In one embodiment, the matching point position in the target frame overexposed image is modulated according to the inter-frame displacement, including:

[0028] If the inter-frame displacement is greater than a preset displacement, the matching point position in the target frame overexposed image is modulated; the displacement between the modulated matching point position and the matching point position in the last frame overexposed image is the preset displacement.

[0029] In one embodiment, the method further includes:

[0030] If the matching result is a matching failure, the matching point position in the last frame overexposed image is determined as the matching point position in the target frame overexposed image.

[0031] In a second aspect, the present application further provides an image processing device, which includes:

[0032] A first obtaining module is configured to obtain the matching result of the control point in the mask image and the matching point in the plurality of frame overexposed images; the mask image and the plurality of frame overexposed images are images of the same part;

[0033] A modulation module is configured to modulate the matching point position in the plurality of frame overexposed images according to the matching result of the plurality of frame overexposed images.

[0034] A second obtaining module is configured to transform the mask image based on the conversion relationship between the modulated plurality of frame overexposed images and the mask image.

[0035] A processing module is configured to subtract the transformed mask image from the modulated plurality of frame overexposed images to obtain the blood vessel image corresponding to the plurality of frame overexposed images.

[0036] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the content of any of the image processing methods described in the first aspect above.

[0037] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the content of any one of the image processing methods described in the first aspect above.

[0038] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the content of any of the image processing methods described in the first aspect above.

[0039] The aforementioned image processing method, apparatus, computer equipment, and storage medium acquire the matching results of control points in a mask image and matching points in a multi-frame film image; the mask image and the multi-frame film image are images of the same location; based on the matching results of the multi-frame film image, the positions of the matching points in the multi-frame film image are modulated; based on the conversion relationship between the modulated multi-frame film image and the mask image, the mask image is transformed; the transformed mask image is subtracted from the modulated multi-frame film image to obtain the blood vessel image corresponding to the multi-frame film image. This method can accurately modulate the position of the matching points in the multi-frame vascular images by matching the control points in the mask image with the matching points in the multi-frame vascular images, thereby reducing the positional error of the matching points between the multi-frame vascular images. Through the conversion relationship between the multi-frame vascular images and the mask image, the mask image can be converted into an image that is closer to the structure of the multi-frame vascular images. By subtracting the converted mask image from the multi-frame vascular images, a more accurate multi-frame vascular image can be obtained, thus solving the problem of inconsistent artifact morphology between the vascular images corresponding to the multi-frame vascular images. Attached Figure Description

[0040] Figure 1 This is an application environment diagram of an image processing method in one embodiment;

[0041] Figure 2 This is a flowchart illustrating an image processing method in one embodiment;

[0042] Figure 3 This is a schematic diagram of a mask image in one embodiment;

[0043] Figure 4 This is a schematic diagram of the control points of a mask image in one embodiment;

[0044] Figure 5 This is a flowchart illustrating an image processing method in one embodiment;

[0045] Figure 6 a control point triangle in an embodiment based on triangulation;

[0046] Figure 7 a schematic diagram of a control point triangle in an embodiment;

[0047] Figure 8 a schematic diagram of a matching point triangle in an embodiment;

[0048] Figure 9 a schematic diagram of a flow of an image processing method in an embodiment;

[0049] Figure 10 a schematic diagram of a successful matching between a control point set and a matching point set in an embodiment;

[0050] Figure 11 a schematic diagram of a failed matching between a control point set and a matching point set in an embodiment;

[0051] Figure 12 a schematic diagram of a flow of an image processing method in an embodiment;

[0052] Figure 13 a schematic diagram of a flow of an image processing method in an embodiment;

[0053] Figure 14 a schematic diagram of a flow of an image processing method in an embodiment;

[0054] Figure 15 a structural block diagram of an image processing apparatus in an embodiment. DETAILED DESCRIPTION

[0055] In order to make the purposes, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and should not be used to limit the present application.

[0056] The image processing method provided by the embodiments of the present application can be applied in an application environment as shown in Figure 1 The internal structure diagram of the computer device can be as shown in Figure 1As shown in the figure. The computer device can be a server, which includes a processor, a memory and a network interface connected by a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium, an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data in the image processing process. The network interface of the computer device is used to communicate with the external terminal through the network connection, and the computer program is executed by the processor to realize an image processing method. Among them, the computer device can be realized by an independent computer device or a computer device cluster composed of multiple computer devices.

[0057] In one embodiment, as shown in the figure, an image processing method is provided. Taking the server in the figure as an example, the method comprises the following steps: Figure 2 Figure 1 In one embodiment, as shown in the figure, an image processing method is provided. Taking the server in the figure as an example, the method comprises the following steps:

[0058] S201, obtaining the matching result of the control points in the mask image and the matching points in the multiple frames of excess slice images; the mask image and the multiple frames of excess slice images are images of the same part.

[0059] Among them, in the digital subtraction angiography (Digital subtraction Angiography, DSA) technology, when the blood vessel image of the target part needs to be obtained, the image of the target part before the contrast agent is injected is first collected, and the image of the target part is determined as the mask image; then, while the contrast agent is injected into the target part, the multiple frames of target part images after the contrast agent is injected are collected through the same collection condition, and the obtained multiple frames of target part images are determined as the excess slice images. That is, the mask image and the multiple frames of excess slice images are images of the target part.

[0060] Further, the server can analyze the mask image, select a point with a larger local gradient from the mask image, and determine the point with a larger local gradient in the mask image as the control point in the mask image. Among them, the point with a larger local gradient refers to the pixel point whose gray value difference with the adjacent pixel point is greater than the preset gray difference value, and the local gradient of the point with a larger local gradient can be calculated according to the following formula:

[0061]

[0062] Among them, f(x,y) represents the gray value of the current pixel point; f(x-1,y) and f(x,y-1) represent the gray value of the adjacent pixel point of the current pixel point.

[0063] ​​For example, when the preset grayscale difference is 0.01, pixels with a local gradient greater than 0.01 are considered to have a large local gradient.

[0064] Using control points on the mask image as centers, image blocks of a preset area are delineated. From each frame of the filled image, image blocks with high similarity to those on the mask image are obtained. The center point of each image block in the filled image is determined as the matching point of the filled image. For example, if the center point of the mask image is (100, 100), and assuming the preset area size, the width and height of the mask image block are 20, then for any frame of the filled image, the point with coordinates (100, 100) is determined as the center of the filled image. Starting from the center position of the filled image, a range of ±10 is defined in both the x-direction and y-direction. The resulting defined area has a numerical range of 90-110 in both the x-direction and y-direction. Using the position of any pixel within this defined area as the center point of a rectangular image block, multiple filled image blocks with a width and height of 20 are obtained. Then calculate the similarity between each piece of the image and the masking rectangle, and take the center point of the piece of the image with the highest similarity as the matching point of the piece of the image.

[0065] Optionally, for any sheet image, the server can match the coordinates of control points in the mask image with the coordinates of matching points in the sheet image. If the error between the coordinates of the control points in the mask image and the coordinates of the matching points in the sheet image is less than a preset error, the match is considered successful; if the error is greater than or equal to the preset error, the match is considered unsuccessful. Optionally, the server can perform edge-connecting operations on multiple control points in the mask image to obtain multiple closed shapes. Simultaneously, it can also perform edge-connecting operations on the matching points corresponding to multiple control points in multiple sheet images to obtain multiple closed shapes. For any sheet image, the server can compare the closed shapes in the mask image with the multiple closed shapes in the sheet image. If the error between the closed shapes in the mask image and the closed shapes in the sheet image is less than a preset error, the match is considered successful; if the error is greater than or equal to the preset error, the match is considered unsuccessful. This embodiment does not limit the method for obtaining the matching results of control points in the mask image and matching points in multiple sheet images.

[0066] If the part in the captured mask image is the head of the simulated object. Figure 3 This is a schematic diagram of the masked image. Since the masked image and the multi-frame film images are images of the same area, the schematic diagram of each frame film image can also be obtained through... Figure 3 To illustrate. Figure 4This is a schematic diagram of the control points of the mask image. The mask image includes multiple control points. A schematic diagram of the matching points of the mask image can be obtained by... Figure 4 As shown, the number of matching points and control points is the same. The difference lies in the fact that the positions of the control points in the mask image and the matching points in the overlay image may differ due to the movement of the target object.

[0067] S202, based on the matching results of the multi-frame wafer images, modulate the positions of the matching points in the multi-frame wafer images.

[0068] In this embodiment, for any frame of the wafer image, if the matching point of the wafer image and the control point of the mask image fail to match, it indicates that the error between the matching point position of the wafer image and the control point position of the mask image is too large. In this case, the matching point position of the previous frame of the wafer image is directly used as the matching point position of the current frame of the wafer image. If the matching point of the wafer image and the control point of the mask image succeed, it indicates that the error between the matching point position of the wafer image and the control point position of the mask image is small. The error between the matching point position of the current frame of the wafer image and the matching point position of the previous frame of the wafer image is obtained. If the error is greater than a preset threshold, the matching point position in the current frame of the wafer image is modulated. The error between the matching point position in the modulated wafer image and the matching point position in the previous frame of the wafer image is less than or equal to the preset threshold. The modulation process will now be described using an example. Assume the displacement of a control point in the previous frame of the wafer image is 2, and the displacement of that control point in the current frame of the wafer image is 8. The difference between the displacement of that control point in the current frame and the displacement of that control point in the previous frame is 6. If the preset threshold is 2, the displacement in the current frame becomes 4. This ensures that the difference between the displacement of that control point in the current frame and the displacement of that control point in the previous frame is less than or equal to 2.

[0069] S203, transform the mask image based on the transformation relationship between the modulated multi-frame filled image and the mask image.

[0070] In this embodiment, for any modulated wafer image, the server can obtain the coordinates of the matching points in the modulated wafer image and the coordinates of the control points in the mask image. Using the coordinates of the matching points in the wafer image and the coordinates of the control points in the mask image, the transformation relationship between the mask image and the wafer image is analyzed. For any wafer image, the server can convert the mask image into an image that more closely corresponds to the structure of the wafer image based on the transformation relationship between the mask image and the wafer image, resulting in a multi-frame mask image. For example, the aforementioned transformation relationship refers to the simulated transformation matrix between the mask image and the wafer image, which represents the difference between the coordinates of the control points and the coordinates of the corresponding matching points.

[0071] S204, subtract the converted masked image from the modulated multi-frame film image to obtain the blood vessel image corresponding to the multi-frame film image.

[0072] In this embodiment, there is a one-to-one correspondence between the converted multi-frame masked images and the multi-frame filled images. For any converted masked image, the server can subtract the filled image from the corresponding masked image to remove tissues other than blood vessels, thereby obtaining the blood vessel image corresponding to the multi-frame filled images.

[0073] In the aforementioned image processing method, the matching results of control points in the mask image and matching points in the multi-frame vascular images are obtained; the mask image and the multi-frame vascular images are images of the same location; based on the matching results of the multi-frame vascular images, the positions of the matching points in the multi-frame vascular images are modulated; based on the transformation relationship between the modulated multi-frame vascular images and the mask image, the mask image is transformed; the transformed mask image is subtracted from the modulated multi-frame vascular images to obtain the vascular image corresponding to the multi-frame vascular images. This method, by matching the control points in the mask image with the matching points in the multi-frame vascular images, can accurately modulate the positions of the matching points in the multi-frame vascular images, thus reducing the positional error of the matching points between the multi-frame vascular images. Through the transformation relationship between the multi-frame vascular images and the mask image, the mask image can be converted into an image more similar to the structure of the multi-frame vascular images. Subtracting the transformed mask image from the multi-frame vascular images yields a more accurate multi-frame vascular image, thereby solving the problem of inconsistent artifact morphology between the vascular images corresponding to the multi-frame vascular images.

[0074] Based on the above embodiments, this embodiment is... Figure 2 The following section describes and explains the relevant content of step S201, "Obtaining the matching results of control points in the mask image and matching points in multiple frame film images." Figure 5 As shown, step S201 above may include the following:

[0075] S301, the control points in the mask image are divided to obtain multiple control point sets; and the matching points in the multi-frame film images are divided to obtain multiple matching point sets for each frame film image; wherein, the control points in the mask image and the corresponding matching points in each frame film image correspond to the same structural position.

[0076] In this embodiment, the mask image includes multiple control points, and each frame of the fill image also includes multiple matching points. To quickly match the control points in the mask image with the matching points in the fill image, the server can divide the multiple control points in the mask image into multiple control point sets, and divide the multiple control points in the fill image into multiple matching point sets for each frame of the fill image. Matching the control point sets with the matching point sets can improve the matching efficiency. Each control point set may include at least two control points, and each matching point set may include at least two matching points. The number of control points in the control point set is the same as the number of matching points in the matching point set, and the positions of the control points and the matching points correspond one-to-one.

[0077] S302, each set of control points is matched with the corresponding set of matching points in the multi-frame film image to obtain the matching result.

[0078] For any frame of the transparency image, optionally, the server can obtain the similarity between the set of control points in the mask image and the set of matching points in the transparency image. If the number of similarities satisfying preset conditions is greater than or equal to a preset number, it is determined that the control points in the mask image and the matching points in the transparency image are successfully matched; if the number of similarities satisfying preset conditions is less than or equal to a preset number, it is determined that the control points in the mask image and the matching points in the transparency image are not matched. Optionally, the server can input the set of control points in the mask image and the set of matching points in the transparency image into a preset matching model, and perform matching on the set of control points in the mask image and the set of matching points in the transparency image using the preset matching model. If the output result of the matching model is yes, it is determined that the control points in the mask image and the matching points in the transparency image are successfully matched; if the output result of the matching model is no, it is determined that the control points in the mask image and the matching points in the transparency image are not matched.

[0079] In the aforementioned image processing method, control points in the mask image are divided into multiple control point sets; and matching points in multiple frames of the film image are divided into multiple matching point sets for each frame of the film image. Each control point set is then matched with its corresponding matching point set in the multiple frames of the film image to obtain a matching result. The control points in the mask image and their corresponding matching points in each frame of the film image correspond to the same structural position. This method, by dividing both the control points in the mask image and the film image separately, and then matching the resulting control point sets and matching point sets, improves the efficiency of the matching process, thus enabling the rapid acquisition of the matching results between the control points in the mask image and the matching points in the film image.

[0080] Based on the above embodiments, this embodiment is... Figure 5 The relevant content of step S301, "dividing the control points in the mask image to obtain multiple control point sets; and dividing the matching points in multiple frames of the mask image to obtain multiple matching point sets for each frame of the mask image," will be introduced and explained.

[0081] Step S301 above may include the following:

[0082] Triangulation is performed on each control point to obtain multiple control point triangles; and triangulation is performed on the matching points in multiple frames of the image to obtain multiple matching point triangles; wherein the three corner points of each control point triangle and the three corner points of each matching point triangle have a spatial order, and each control point triangle corresponds to a set of control points, and each matching point triangle corresponds to a set of matching points.

[0083] In this embodiment, the server can divide multiple control points into multiple control point sets, with each set containing three control points. Edge connections are then performed between the three control points in each set, and connections are also made between different control point sets, resulting in multiple control point triangles. Each control point is then labeled sequentially, using either numbers or letters. Following this method, the matching points in each frame of the image are further triangulated to obtain multiple matching point triangles.

[0084] Figure 6 This represents the control point triangle based on triangulation. Figure 6 Each control point in the system forms a control point triangle with the other two control points. Figure 7 This diagram illustrates a control point triangle. The three corner points of the triangle correspond to three control points, each represented by the letter ABC. The spatial order of the three control points is ABC. Figure 8This diagram illustrates a matching point triangle. The three corner points of the triangle correspond to three matching points, each represented by the letters abc. The spatial order of the three matching points is abc.

[0085] In the aforementioned image processing method, triangulation is performed on each control point to obtain multiple control point triangles; and triangulation is performed on the matching points in multiple frames of the masked image to obtain multiple matching point triangles. The three corner points of each control point triangle and the three corner points of each matching point triangle have a spatial order, and each control point triangle corresponds to a set of control points, and each matching point triangle corresponds to a set of matching points. This method reduces the matching time and improves the matching efficiency between control points in the masked image and matching points in the masked image by triangulating each control point and each matching point into multiple control point triangles and vice versa.

[0086] Based on the above embodiments, this embodiment is... Figure 5 The following section describes and explains step S302, "Matching the multiple control point sets in the masked image with the multiple matching point sets in each frame of the film image to obtain the matching results." Figure 9 As shown, step S302 above may include the following:

[0087] S401, for any target frame filled image, obtain the spatial order of the control point set in the mask image and the spatial order of the matching point set in the target frame filled image.

[0088] In this embodiment, the server can obtain the identification information of each control point set in the masked image, and determine the spatial order of each control point set based on the identification information. For example, when the identification information of the three control points in a control point set is ABC, the spatial order of the control point set is ABC; when the identification information of the three control points in a control point set is 135, the spatial order of the control point set is 1-3-5. Furthermore, the server can obtain the identification information of each matching point set in the target frame filled image, and determine the spatial order of each matching point set based on the identification information. For example, when the identification information of the three matching points in a matching point set is abc, the spatial order of the matching point set is abc; when the identification information of the three matching points in a matching point set is 246, the spatial order of the matching point set is 2-4-6.

[0089] S402, Match the spatial order of the control point set with the spatial order of the matching point set.

[0090] In this embodiment, the three control points in the control point set correspond one-to-one with the three matching points in the matching point set. The server can compare the spatial order of the control point set with the spatial order of the matching point set, and determine whether a match is successful based on the comparison result.

[0091] S403, if the spatial order of the control point set is the same as the spatial order of the matching point set, the matching result is determined to be a successful match; if the spatial order of the control point set is different from the spatial order of the matching point set, the matching result is determined to be a failed match.

[0092] In this embodiment, when the spatial order of the control point set is the same as the spatial order of the matching point set, it means that the error between the position of the matching point and the position of the control point is small, and the control point set and the matching point set are successfully matched; when the spatial order of the control point set is different from the spatial order of the matching point set, it means that the error between the position of the matching point and the position of the control point is large, and the control point set and the matching point set are not matched. Figure 10 This diagram illustrates a successful match between the control point set and the matching point set. The spatial order of the control point set is ABC, and the spatial order of the matching point set is abc. The spatial order of the two sets is the same. Figure 11 This diagram illustrates a failure to match between the control point set and the matching point set. The spatial order of the control point set is ABC, and the spatial order of the matching point set is acb. The spatial orders of the two sets are different.

[0093] In the image processing method described above, for any target frame image, the spatial order of the control point set in the mask image and the spatial order of the matching point set in the target frame image are obtained. The spatial order of the control point set is then matched with the spatial order of the matching point set. If the spatial order of the control point set and the spatial order of the matching point set are the same, the matching result is considered successful; otherwise, the matching result is considered unsuccessful. This method, by matching the spatial order of the control point set and the matching point set, reduces the number of matching operations and significantly reduces the matching time, thus making the matching process more efficient.

[0094] Based on the above embodiments, this embodiment is... Figure 2 The following section describes and explains step S202, "Modulating the positions of matching points in the multi-frame wafer images based on the matching results of the multi-frame wafer images." Figure 12 As shown, step S202 above may include the following:

[0095] S501, for any target frame filled image, if the target frame filled image is the first frame filled image, then the first frame filled image is modulated according to the matching result of the target frame filled image and the position of the control point in the mask image.

[0096] In this embodiment, when the target frame filled image is the first frame filled image, and the matching result between the first frame filled image and the mask image is successful, the error between the matching point position in the filled image and the matching point position in the first frame filled image is obtained. If this error is greater than a preset error, the position of the matching point in the first frame mask image needs to be modulated according to the position of the control point in the mask image, so that the error between the position of the matching point in the first frame mask image and the position of the control point in the mask image is less than or equal to the preset error. For example, if the matching point position in the first frame filled image is (0, 12), the position of the control point in the mask image is (0, 8), and the preset error is 2, then the matching point position in the first frame filled image needs to be modulated to (0, 10). If the matching result between the first frame filled image and the mask image is a failure, then the matching point position in the filled image is adjusted to the control point position in the mask image.

[0097] S502, if the target frame image is not the first frame image, then the position of the matching point in the target frame image is modulated according to the matching result of the target frame image and the position of the matching point in the previous frame image of the target frame image.

[0098] In this embodiment, when the target frame fill image is not the first frame fill image, and the matching result of the target frame fill image is a successful match, the error between the matching point position of the target frame fill image and the matching point position in the previous frame fill image is obtained. If this error is greater than a preset error, the matching point position of the target frame fill image needs to be modulated according to the matching point position in the previous frame fill image, so that the error between the matching point position of the target frame fill image and the matching point position in the previous frame fill image is less than or equal to the preset error. If the matching result between the target frame fill image and the previous frame fill image is a failed match, the matching point position of the previous frame fill image is adjusted to the control point position of the target frame image.

[0099] Furthermore, it is understandable that if the matching result of the target frame is correct, but the matching point position of the previous frame's wafer image has been modulated, and if the error between the matching point position of the target frame's wafer image and the matching point position of the previous frame's wafer image is large, then it is still necessary to modulate the matching point position of the target frame's wafer image.

[0100] In the above image processing method, for any target frame vascular image, if the target frame vascular image is the first vascular image, the first vascular image is modulated based on the matching result of the target frame vascular image and the position of the control points in the mask image. If the target frame vascular image is not the first vascular image, the position of the matching point in the target frame vascular image is modulated based on the matching result of the target frame vascular image and the position of the matching point in the previous vascular image. This method distinguishes whether the target frame vascular image is the first vascular image. When it is the first frame, the first vascular image is adjusted based on the control points in the mask image to ensure that the error between the first vascular image and the mask image is smaller. At the same time, when the target frame is not the first frame, the target frame is processed based on the position of the matching point in the previous vascular image, which can ensure that the error between the positions of the matching points in adjacent vascular images is small, thereby solving the problem of inconsistent artifact morphology between vascular images corresponding to multiple vascular images.

[0101] Based on the above embodiments, this embodiment is... Figure 12 The following section describes and explains step S502, "Modulating the position of the matching point in the target frame image based on the matching result of the target frame image and the position of the matching point in the previous frame image of the target frame image." Figure 13 As shown, step S502 above may include the following:

[0102] S601, if the matching result is successful, then obtain the inter-frame displacement of the target frame image; the inter-frame displacement represents the displacement between the matching point position in the target frame image and the matching point position in the previous frame image.

[0103] In this embodiment, when the matching point position of the target frame fill image and the control point position of the mask image are successfully matched, the error between the matching point position and the control point position is small. At this time, to address the issue of inconsistent artifact morphology between adjacent fill images, it is necessary to determine whether the error between the matching point positions of adjacent fill images is less than a preset error. The server can calculate the difference between the matching point position in the target frame fill image and the matching point position in the previous frame fill image, and use this difference as the inter-frame displacement of the target frame fill image.

[0104] S602, modulates the position of the matching point in the target frame slice image according to the inter-frame displacement.

[0105] In this embodiment, if the inter-frame displacement is greater than a preset displacement, the server can adjust the matching point position in the target frame image based on the difference between the matching point position in the target frame image and the matching point position in the previous frame image, so that the difference between the matching point position in the target frame image and the matching point position in the previous frame image is less than or equal to a preset difference. If the inter-frame displacement is less than or equal to the preset displacement, then there is no need to modulate the matching point position in the target frame image.

[0106] S603, if the matching result is a failure, then the matching point position in the previous frame of the film image is determined as the matching point position in the target frame of the film image.

[0107] In this embodiment, when the matching point position of the target frame film image and the control point position of the mask image are successfully matched, it indicates that the matching point position of the target frame film image has changed significantly. Therefore, the matching point position in the previous frame film image is directly determined as the matching point position in the target frame film image.

[0108] In the above image processing method, if the matching result is successful, the inter-frame displacement of the target frame image is obtained; the inter-frame displacement represents the displacement between the matching point position in the target frame image and the matching point position in the previous frame image; based on the inter-frame displacement, the matching point position in the target frame image is modulated; if the matching result is unsuccessful, the matching point position in the previous frame image is determined as the matching point position in the target frame image. This method, based on successful matching, modulates the matching point position in the target frame image according to the displacement between the matching point position in the target frame image and the matching point position in the previous frame image, so that the inter-frame displacement between the matching point positions of adjacent frame images is less than a preset displacement, reducing the matching point position error between multiple frame images, thereby solving the problem of inconsistent artifact morphology between the corresponding vascular images of multiple frame images.

[0109] Based on the above embodiments, this embodiment is... Figure 13 The relevant content of step S602, "modulating the position of the matching point in the target frame slice image according to the inter-frame displacement," is introduced and explained.

[0110] Step S602 above may include the following:

[0111] If the inter-frame displacement is greater than the preset displacement, the position of the matching point in the target frame's wafer image is modulated; the displacement between the modulated matching point position and the matching point position in the previous frame's wafer image is the preset displacement.

[0112] In this embodiment, when the inter-frame displacement between the matching point position in the target frame image and the matching point position in the previous frame image is greater than a preset displacement, it is determined that the error between the matching point position in the target frame image and the matching point position in the previous frame image is large. Then, the matching point position in the target frame image is modulated so that the inter-frame displacement between the matching point position in the target frame image and the matching point position in the previous frame image is equal to the preset displacement.

[0113] In the above image processing method, if the inter-frame displacement is greater than a preset displacement, the position of the matching point in the target frame transillumination image is modulated; the displacement between the modulated matching point position and the matching point position in the previous frame transillumination image is the preset displacement. This method modulates the displacement of the matching point in the target frame transillumination image when the inter-frame displacement is greater than the preset displacement, ensuring that the inter-frame displacement between adjacent frames is less than or equal to the preset displacement. This reduces the error between the matching point positions of multiple transillumination images, thereby solving the problem of inconsistent artifact morphology between the corresponding vascular images of multiple transillumination images.

[0114] In one embodiment, the image processing method is described in detail below, such as... Figure 14 As shown, the method may include:

[0115] S701, perform triangulation on each control point to obtain multiple control point triangles; and perform triangulation on the matching points in multiple frames of filled images to obtain multiple matching point triangles;

[0116] S702, for any target frame filled image, obtain the spatial order of the control point set in the mask image and the spatial order of the matching point set in the target frame filled image;

[0117] S703, Match the spatial order of the control point set with the spatial order of the matching point set;

[0118] S704, if the spatial order of the control point set is the same as the spatial order of the matching point set, the matching result is determined to be a successful match; if the spatial order of the control point set is different from the spatial order of the matching point set, the matching result is determined to be a failed match.

[0119] S705, for any target frame filled image, if the target frame filled image is the first frame filled image, then the first frame filled image is modulated according to the matching result of the target frame filled image and the position of the control point in the mask image.

[0120] S706, If the matching result is successful, then obtain the inter-frame displacement of the target frame image; the inter-frame displacement represents the displacement between the matching point position in the target frame image and the matching point position in the previous frame image.

[0121] S707, if the inter-frame displacement is greater than the preset displacement, the matching point position in the target frame's filled image is modulated; the displacement between the modulated matching point position and the matching point position in the previous frame's filled image is the preset displacement.

[0122] S708, if the matching result is a failure, then the matching point position in the previous frame of the film image is determined as the matching point position in the target frame of the film image.

[0123] S709, Obtain the conversion relationship between the modulated multi-frame filled image and the masked image;

[0124] S710, the mask image is converted according to the conversion relationship to obtain the converted mask image;

[0125] S711, subtract the converted mask image from the modulated multi-frame film image to obtain the blood vessel image corresponding to the multi-frame film image.

[0126] It should be understood that although the steps in the flowcharts of the above embodiments 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 above embodiments 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.

[0127] Based on the same inventive concept, this application also provides an image processing apparatus for implementing the image processing method described above. The solution provided by this apparatus is similar to the implementation scheme described in the above method; therefore, the specific limitations in one or more image processing apparatus embodiments provided below can be found in the limitations of the image processing method described above, and will not be repeated here.

[0128] In one embodiment, such as Figure 15 As shown, an image processing apparatus is provided, comprising: a first acquisition module 11, a modulation module 12, and a second acquisition module 13, wherein:

[0129] The first acquisition module 11 is used to acquire the matching results of control points in the mask image and matching points in the multi-frame film image; the mask image and the multi-frame film image are images of the same part;

[0130] The modulation module 12 is used to modulate the position of the matching point in the multi-frame film image according to the matching result of the multi-frame film image;

[0131] The second acquisition module 13 is used to transform the mask image based on the conversion relationship between the modulated multi-frame filled image and the mask image.

[0132] Processing module 14 is used to subtract the converted mask image from the modulated multi-frame film image to obtain the blood vessel image corresponding to the multi-frame film image.

[0133] In one embodiment, the first acquisition module 11 includes: a partitioning unit and a matching unit, wherein:

[0134] The segmentation unit is used to segment the control points in the mask image to obtain multiple control point sets; and to segment the matching points in multiple frames of the film image to obtain multiple matching point sets for each frame of the film image; wherein the control points in the mask image and the corresponding matching points in each frame of the film image correspond to the same structural position.

[0135] The matching unit is used to match each set of control points with the corresponding set of matching points in the multi-frame film image to obtain the matching result.

[0136] In one embodiment, the above-mentioned partitioning unit is further used to triangulate each control point to obtain multiple control point triangles; and to triangulate the matching points in the multi-frame image to obtain multiple matching point triangles; wherein the three corner points in each control point triangle and the three corner points in each matching point triangle have a spatial order, and each control point triangle corresponds to a control point set, and each matching point triangle corresponds to a matching point set.

[0137] In one embodiment, the matching unit is further configured to, for any target frame overlay image, obtain the spatial order of the control point set in the mask image and the spatial order of the matching point set in the target frame overlay image; match the spatial order of the control point set with the spatial order of the matching point set; if the spatial order of the control point set is the same as the spatial order of the matching point set, the matching result is determined to be a successful match; if the spatial order of the control point set is different from the spatial order of the matching point set, the matching result is determined to be a failed match.

[0138] In one embodiment, the modulation module includes: a first modulation unit and a second modulation unit, wherein:

[0139] The first modulation unit is used to perform modulation processing on the first frame image based on the matching result of the target frame image and the position of the control point in the mask image for any target frame image.

[0140] The second modulation unit is used to modulate the position of the matching point in the target frame image based on the matching result of the target frame image and the position of the matching point in the previous frame image when the target frame image is not the first frame image.

[0141] In one embodiment, the second modulation unit is further configured to, when the matching result is a successful match, obtain the inter-frame displacement of the target frame image; the inter-frame displacement represents the displacement between the matching point position in the target frame image and the matching point position in the previous frame image; and modulate the matching point position in the target frame image according to the inter-frame displacement.

[0142] In one embodiment, the second modulation unit is further configured to modulate the matching point position in the target frame image when the inter-frame displacement is greater than a preset displacement; the displacement between the modulated matching point position and the matching point position in the previous frame image is the preset displacement.

[0143] In one embodiment, the second modulation unit is further configured to determine the matching point position in the previous frame of the film image as the matching point position in the target frame of the film image if the matching result is a matching failure.

[0144] Each module in the aforementioned image processing device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0145] In one embodiment, a computer 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 content of any of the above-described image processing methods.

[0146] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the content of any of the above-described image processing methods.

[0147] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the content of any of the above-described image processing methods.

[0148] 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.

[0149] 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. When executed, the computer program 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.

[0150] 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.

[0151] The above embodiments are merely illustrative of several implementation methods of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of this 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. An image processing method, characterized in that, The method includes: Obtain the matching results between control points in the masked image and matching points in the multi-frame filled image; the masked image and the multi-frame filled image are images of the same part; For any target frame filled image, if the target frame filled image is the first frame filled image, then the first frame filled image is modulated according to the matching result of the target frame filled image and the position of the control point in the mask image; If the target frame fill image is not the first frame fill image, then the position of the matching point in the target frame fill image is modulated according to the matching result of the target frame fill image and the position of the matching point in the previous frame fill image of the target frame fill image. Based on the conversion relationship between the modulated multi-frame filled image and the mask image, the mask image is transformed; The converted masked image is subtracted from the modulated multi-frame film image to obtain the blood vessel image corresponding to the multi-frame film image.

2. The method according to claim 1, characterized in that, The process of obtaining the matching results between control points in the masked image and matching points in multiple frames of the film image includes: The control points in the mask image are divided to obtain multiple control point sets; and the matching points in the multi-frame filled image are divided to obtain multiple matching point sets for each frame filled image; wherein the control points in the mask image and the corresponding matching points in each frame filled image correspond to the same structural position. Each set of control points is matched with the corresponding set of matching points in the multi-frame filled image to obtain the matching result.

3. The method according to claim 2, characterized in that, The process of dividing the control points in the masked image to obtain multiple control point sets, and dividing the matching points in the multi-frame filled image to obtain multiple matching point sets for each frame filled image, includes: Triangulation is performed on each of the control points to obtain multiple control point triangles; and triangulation is performed on the matching points in the multi-frame filled image to obtain multiple matching point triangles. The three corner points of each control point triangle and the three corner points of each matching point triangle have a spatial order, and each control point triangle corresponds to a set of control points and each matching point triangle corresponds to a set of matching points.

4. The method according to claim 2, characterized in that, The step of matching each set of control points with the corresponding set of matching points in the multi-frame filled image to obtain a matching result includes: For any target frame overlay image, obtain the spatial order of the control point set in the mask image and the spatial order of the matching point set in the target frame overlay image; Match the spatial order of the control point set with the spatial order of the matching point set; If the spatial order of the control point set is the same as the spatial order of the matching point set, the matching result is determined to be a successful match; if the spatial order of the control point set is different from the spatial order of the matching point set, the matching result is determined to be a failed match.

5. The method according to any one of claims 1-4, characterized in that, The mask image is an image of the target area before the contrast agent is injected.

6. The method according to any one of claims 1-4, characterized in that, The step of modulating the position of the matching point in the target frame fill image based on the matching result of the target frame fill image and the position of the matching point in the previous frame fill image of the target frame fill image includes: If the matching result is successful, the inter-frame displacement of the target frame image is obtained; the inter-frame displacement represents the displacement between the matching point position in the target frame image and the matching point position in the previous frame image. Based on the inter-frame displacement, the position of the matching point in the target frame slice image is modulated.

7. The method according to claim 6, characterized in that, The step of modulating the matching point position in the target frame slice image according to the inter-frame displacement includes: If the inter-frame displacement is greater than a preset displacement, the matching point position in the target frame image is modulated; the displacement between the modulated matching point position and the matching point position in the previous frame image is the preset displacement.

8. An image processing apparatus, characterized in that, The device includes: The first acquisition module is used to acquire the matching results of control points in the mask image and matching points in the multi-frame film image; the mask image and the multi-frame film image are images of the same part; The modulation module is configured to, for any target frame filled image, if the target frame filled image is the first frame filled image, modulate the first frame filled image according to the matching result of the target frame filled image and the position of the control point in the mask image; if the target frame filled image is not the first frame filled image, modulate the position of the matching point in the target frame filled image according to the matching result of the target frame filled image and the position of the matching point in the previous frame filled image of the target frame filled image. The second acquisition module is used to transform the mask image based on the conversion relationship between the modulated multi-frame filled image and the mask image; The processing module is used to subtract the converted masked image from the modulated multi-frame film image to obtain the blood vessel image corresponding to the multi-frame film image.

9. A computer 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 7.

10. 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 7.

Images