A method and apparatus for catheter positioning using angiographic nonfill frames

Abstract

The application provides a catheter positioning method and a catheter positioning device for an angiographic non-filling frame, the method comprising: determining a dynamic gray scale marker by using gray scale values corresponding to a plurality of edge pixel points in each angiographic image in an angiographic video, and determining a starting point of a catheter in each angiographic image by using the dynamic gray scale marker; for each angiographic image, calculating a catheter area of a catheter region corresponding to the catheter in the angiographic image; skeletonizing the catheter region in the terminal angiographic image to obtain a catheter center line, and determining a terminal point of the catheter in the terminal angiographic image based on the catheter center line. According to the catheter positioning method and the catheter positioning device, the starting point of the catheter can be accurately positioned, so that the catheter position in the non-filling terminal angiographic image is determined, and an important basis is provided for subsequent filling frame catheter positioning.

Description

Technical Field

[0001] This application relates to the field of medical image processing technology, and more specifically, to a catheter positioning method and catheter positioning device for non-filling frames in angiography. Background Technology

[0002] In angiographic images, catheter localization is a crucial prerequisite for vessel origin localization, and automated catheter localization is an essential prerequisite for automated vessel analysis. Automated catheter localization in non-filling frames also provides important reference for subsequent automated catheter localization in filling frames.

[0003] Currently, the most common method for catheter localization in angiography is based on deep learning. This involves manually annotating a large amount of catheter data, then spending considerable time training a model, which is then directly applied to new data. The limitations of this method lie in the need for a large amount of data, accurate manual annotation, and significant subsequent model training time. Furthermore, deep learning methods are limited by data availability; the catheter position can be at any edge of the image, and the model's adaptability to such arbitrary orientations is poor. Another approach is a semi-automatic method, such as manually determining a seed point and then growing the model based on that point. This method has a low degree of automation and requires selecting a point for each frame, making it tedious and complex. Summary of the Invention

[0004] In view of this, the purpose of this application is to provide a catheter positioning method and catheter positioning device for non-filling frames of angiography, which can automatically and quickly acquire the catheter position of angiography, accurately locate the starting point of the catheter, thereby determining the catheter position in the non-filling termination frame angiography image, and providing an important basis for subsequent catheter positioning in the filling frame.

[0005] In a first aspect, embodiments of this application provide a catheter positioning method for non-filling frames in angiography, the catheter positioning method comprising:

[0006] Acquire angiography video and identify multiple edge pixels in the angiography video;

[0007] A dynamic grayscale marker map is determined using the grayscale values ​​corresponding to the multiple edge pixels in each frame of the angiography video, and the starting point of the catheter in each frame of the angiography video is determined using the dynamic grayscale marker map.

[0008] For each frame of angiography image, the catheter area of ​​the catheter region corresponding to the catheter in the angiography image is calculated using the starting point of the catheter in the angiography image;

[0009] The catheter area of ​​the catheter region in any two adjacent frames of the angiography video is compared sequentially. If the difference between the catheter area of ​​the catheter region in the later frame of the two adjacent frames and the catheter area of ​​the catheter region in the earlier frame of the two adjacent frames is greater than or equal to the area difference threshold, then the earlier frame of the angiography video is taken as the termination frame of the angiography video in the non-filled state.

[0010] The catheter region in the termination frame angiography image is skeletonized to obtain the catheter centerline, and the termination point of the catheter in the termination frame angiography image is determined based on the catheter centerline.

[0011] Furthermore, the step of determining a dynamic grayscale marker map using the grayscale values ​​corresponding to multiple edge pixel coordinates in each frame of the angiography image, and determining the starting point of the catheter in each frame of the angiography image using the dynamic grayscale marker map, includes:

[0012] Using the pixel coordinates of the multiple edge pixels in any frame of the angiography image as the horizontal axis and the frame number corresponding to the angiography video as the vertical axis, a blank grayscale marker image is generated.

[0013] For each edge pixel in each frame of the contrast image, determine whether the gray value of the edge pixel in the contrast image is less than or equal to the gray value threshold;

[0014] If so, then according to the pixel coordinates of the edge pixel in the angiography image and the frame number of the angiography image in the angiography video, the pixel block corresponding to the edge pixel is drawn in the blank grayscale marker image to generate the dynamic grayscale marker image.

[0015] The starting point of the catheter in each frame of the angiography image is determined by using multiple pixel blocks in the dynamic grayscale marker image; wherein, the pixel block is composed of multiple adjacent pixel blocks.

[0016] Furthermore, determining the starting point of the catheter in each frame of the angiography image by dividing the image into multiple pixel blocks in the dynamic grayscale marker image includes:

[0017] The target pixel block is determined by filtering multiple pixel blocks in the dynamic grayscale marker image.

[0018] For each row of pixel blocks in the target pixel block, the centroid is calculated using the pixel coordinates corresponding to each pixel block in that row, and the centroid coordinates are obtained.

[0019] The target frame number corresponding to the row of pixels is determined in the dynamic grayscale marker image, and the starting point of the catheter in the angiography image corresponding to the target frame number in the angiography video is determined according to the centroid coordinates.

[0020] Furthermore, the step of filtering multiple pixel blocks in the dynamic grayscale marker image to determine the target pixel block includes:

[0021] For each pixel block, determine whether the pixel width of the pixel block is within the preset pixel width range;

[0022] If the pixel width of the pixel block is within the pixel width range, then continue to determine whether the pixel height of the pixel block is greater than or equal to the preset pixel height threshold;

[0023] If the pixel height of the pixel block is greater than or equal to the pixel height threshold, then the pixel block is determined as the target pixel block.

[0024] Furthermore, the step of calculating the catheter area corresponding to the catheter in the contrast image using the starting point of the catheter in the contrast image includes:

[0025] The starting point is used as the catheter pixel point, and the pixel value of the catheter pixel point in the contrast image is obtained;

[0026] For each adjacent pixel in the contrast image that is adjacent to the duct pixel, the pixel value of the adjacent pixel is obtained, and it is determined whether the difference between the pixel value of the adjacent pixel and the pixel value of the duct pixel is within a preset range;

[0027] If so, then the adjacent pixel is identified as the conduit pixel;

[0028] Return to the step of obtaining the pixel value of each adjacent pixel in the contrast image that is adjacent to the duct pixel, until there are no adjacent pixels in the contrast image that are adjacent to the duct pixel, and obtain all duct pixels in the contrast image;

[0029] The catheter region is determined based on all the catheter pixels in the imaging image, and the catheter area corresponding to the catheter region is calculated based on the number of all the catheter pixels.

[0030] Secondly, embodiments of this application also provide a catheter positioning device for non-filling frames in angiography, the catheter positioning device comprising:

[0031] An edge pixel determination module is used to acquire angiography video and determine multiple edge pixels in the angiography video.

[0032] The catheter starting point determination module is used to determine a dynamic grayscale marker map by using the grayscale values ​​corresponding to the multiple edge pixels in each frame of the angiography video, and to determine the starting point of the catheter in each frame of the angiography video by using the dynamic grayscale marker map.

[0033] The catheter area determination module is used to calculate the catheter area of ​​the catheter region corresponding to the catheter in each frame of the angiography image using the starting point of the catheter in the angiography image.

[0034] The termination frame angiography image determination module is used to sequentially compare the catheter area of ​​the catheter region in any two adjacent frames of the angiography video. When the difference between the catheter area of ​​the catheter region in the later frame of the two adjacent frames and the catheter area of ​​the catheter region in the previous frame of the two adjacent frames is greater than or equal to the area difference threshold, the previous frame angiography image is taken as the termination frame angiography image in the non-filling state.

[0035] The catheter termination point determination module is used to skeletonize the catheter region in the termination frame angiography image to obtain the catheter centerline, and determine the termination point of the catheter in the termination frame angiography image based on the catheter centerline.

[0036] Furthermore, when the catheter start point determination module determines a dynamic grayscale marker map using the grayscale values ​​corresponding to multiple edge pixel coordinates in each frame of the angiography image, and determines the start point of the catheter in each frame of the angiography image using the dynamic grayscale marker map, the catheter start point determination module is also used for:

[0037] Using the pixel coordinates of the multiple edge pixels in any frame of the angiography image as the horizontal axis and the frame number corresponding to the angiography video as the vertical axis, a blank grayscale marker image is generated.

[0038] For each edge pixel in each frame of the contrast image, determine whether the gray value of the edge pixel in the contrast image is less than or equal to the gray value threshold;

[0039] If so, then according to the pixel coordinates of the edge pixel in the angiography image and the frame number of the angiography image in the angiography video, the pixel block corresponding to the edge pixel is drawn in the blank grayscale marker image to generate the dynamic grayscale marker image.

[0040] The starting point of the catheter in each frame of the angiography image is determined by using multiple pixel blocks in the dynamic grayscale marker image; wherein, the pixel block is composed of multiple adjacent pixel blocks.

[0041] Furthermore, when determining the starting point of the catheter in each frame of the angiography image using multiple pixel blocks in the dynamic grayscale marker image, the catheter starting point determination module is also used to:

[0042] The target pixel block is determined by filtering multiple pixel blocks in the dynamic grayscale marker image.

[0043] For each row of pixel blocks in the target pixel block, the centroid is calculated using the pixel coordinates corresponding to each pixel block in that row, and the centroid coordinates are obtained.

[0044] The target frame number corresponding to the row of pixels is determined in the dynamic grayscale marker image, and the starting point of the catheter in the angiography image corresponding to the target frame number in the angiography video is determined according to the centroid coordinates.

[0045] Thirdly, embodiments of this application also provide an electronic device, including: a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus. When the machine-readable instructions are executed by the processor, the steps of the catheter positioning method for non-filling frames of angiography as described above are performed.

[0046] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a computer program that, when executed by a processor, performs the steps of the catheter positioning method for non-filling frames of angiography as described above.

[0047] The catheter localization method for non-filled frames of angiography provided in this application first acquires an angiography video and identifies multiple edge pixels in the video. Then, a dynamic grayscale marker map is determined using the grayscale values ​​corresponding to these edge pixels in each frame of the angiography video, and the starting point of the catheter in each frame is determined using the dynamic grayscale marker map. For each frame, the catheter area corresponding to the catheter in that frame is calculated using the starting point of the catheter in that frame. The angiography images are then compared sequentially. In any two adjacent frames of contrast imaging in the video, if the difference between the catheter area in the later frame of the two adjacent frames and the catheter area in the earlier frame of the two adjacent frames is greater than or equal to an area difference threshold, then the earlier frame of contrast imaging is taken as the termination frame of contrast imaging in a non-filled state. Finally, the catheter region in the termination frame of contrast imaging is skeletonized to obtain the catheter centerline, and the termination point of the catheter in the termination frame of contrast imaging is determined based on the catheter centerline.

[0048] This application obtains the catheter start point in each frame of angiography by dynamically analyzing the grayscale of surrounding pixels in dynamic angiography images. Then, region growing is used to obtain the catheter termination position. The catheter localization method for non-filled frames of angiography provided by this application can automatically and quickly acquire the catheter position of angiography, accurately locate the catheter start point, and thus determine the catheter position in the non-filled termination frame angiography image, providing an important foundation for the subsequent catheter localization in filled frames.

[0049] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0050] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0051] Figure 1 A flowchart illustrating a catheter positioning method for non-filling frames in angiography, provided as an embodiment of this application;

[0052] Figure 2 A schematic diagram of a dynamic grayscale marker image provided in an embodiment of this application;

[0053] Figure 3 A schematic diagram of the structure of a catheter positioning device for non-filled frames in angiography provided in an embodiment of this application;

[0054] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0055] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. Based on the embodiments of this application, every other embodiment obtained by those skilled in the art without inventive effort falls within the scope of protection of this application.

[0056] First, the applicable scenarios for this application will be introduced. This application can be applied to the field of medical image processing technology.

[0057] In angiographic images, catheter localization is a crucial prerequisite for vessel origin localization, and automated catheter localization is an essential prerequisite for automated vessel analysis. Automated catheter localization in non-filling frames also provides important reference for subsequent automated catheter localization in filling frames.

[0058] Research has found that the most common method for catheter localization in angiography is based on deep learning. This involves manually annotating a large amount of catheter data, then spending considerable time training a model, which is then directly applied to new data. The limitations of this method lie in the need for large amounts of data, accurate manual annotation, and significant subsequent model training time. Furthermore, deep learning methods are limited by data availability; the catheter position can be at any edge of the image, and the model's adaptability to such arbitrary orientations is poor. Another approach is a semi-automatic method, such as manually determining a seed point and then growing the model based on that point. This method has a low degree of automation and requires selecting a point for each frame, making it tedious and complex.

[0059] Based on this, embodiments of this application provide a catheter positioning method for non-filling frames in angiography, so as to automatically and quickly determine the catheter position in the non-filling termination frame angiography image.

[0060] Please see Figure 1 , Figure 1This is a flowchart illustrating a catheter positioning method for non-filling frames in angiography, provided as an embodiment of this application. Figure 1 As shown in the embodiments of this application, the catheter positioning method includes:

[0061] S101, acquire the angiography video and determine multiple edge pixels in the angiography video.

[0062] It should be noted that edge pixels refer to the pixels at the edges in each frame of the angiography video.

[0063] Since the catheter may enter the angiography image from different directions, it is necessary to identify multiple edge pixels to locate the catheter's starting point. In specific implementation of step S101, an angiography video is acquired, and multiple edge pixels in the video are identified. When identifying edge pixels, any frame of the angiography video can be selected, and all boundary pixels in that image are chosen as edge pixels. The position of each edge pixel is recorded. For example, if the angiography image size is 455 pixels * 455 pixels, the pixel coordinates of each edge pixel in the image include (0,0), (455,0), (0,455), (455,455), etc. The horizontal and vertical coordinates must satisfy at least one being 0 or at least being the maximum value of the pixel size of the angiography image.

[0064] S102, a dynamic grayscale marker map is determined using the grayscale values ​​corresponding to the multiple edge pixels in each frame of the angiography video, and the starting point of the catheter in each frame of the angiography video is determined using the dynamic grayscale marker map.

[0065] It should be noted that the dynamic grayscale marker is used to record whether the grayscale value of each edge pixel in each frame of the imaging image meets the preset grayscale value conditions.

[0066] Regarding step S102 above, in specific implementation, a dynamic grayscale marker map is determined by using the grayscale values ​​corresponding to multiple edge pixels in each frame of the angiography video, and the starting point of the catheter in each frame of the angiography image is determined by using the dynamic grayscale marker map.

[0067] Specifically, regarding step S102 above, the step of determining a dynamic grayscale marker map using the grayscale values ​​corresponding to the coordinates of multiple edge pixels in each frame of the angiography image, and determining the starting point of the catheter in each frame of the angiography image using the dynamic grayscale marker map, includes:

[0068] Step 1021: Using the pixel coordinates of the multiple edge pixels in any frame of the angiography image as the horizontal axis and the frame number corresponding to the angiography video as the vertical axis, a blank grayscale marker image is generated.

[0069] It should be noted that the blank grayscale marker image refers to a blank marker image generated based on the pixel coordinates of multiple edge pixels and the frame number of the angiography image in the angiography video. Specifically, the pixel coordinates of multiple edge pixels in the angiography image are sorted in a preset order and used as the horizontal axis of the blank grayscale marker image. Assuming there are N frames in the angiography video, the frames are sorted from 0 to N and used as the vertical axis of the blank grayscale marker image.

[0070] Regarding step 1021 above, in specific implementation, the pixel coordinates of multiple edge pixels in any frame of the angiography image are used as the horizontal axis, and the frame number of the corresponding angiography video is used as the vertical axis to generate a blank grayscale marker image. Here, the horizontal axis of the blank grayscale marker image represents the pixel coordinates of each edge pixel in the angiography image, and the vertical axis represents the frame number of the angiography image in the angiography video. As an example, when the number of frames of the angiography image in the angiography video is N, the vertical axis of the blank grayscale marker image is sorted in ascending order from 0 to N. Each horizontal cell corresponds to the pixel coordinates of an edge pixel, and each vertical cell corresponds to the frame number of an angiography image in the angiography video.

[0071] Step 1022: For each edge pixel in each frame of the contrast image, determine whether the gray value of the edge pixel in the contrast image is less than or equal to the gray value threshold.

[0072] Step 1023, if yes, then according to the pixel coordinates of the edge pixel in the angiography image and the frame number of the angiography image in the angiography video, draw the pixel block corresponding to the edge pixel in the blank grayscale marker map to generate the dynamic grayscale marker map.

[0073] It should be noted that the grayscale threshold refers to a pre-set grayscale value threshold used to determine whether edge pixels can be marked. For example, the grayscale threshold can be pre-set to 100, and this application does not make specific limitations on this.

[0074] Regarding steps 1022-1023 above, in specific implementation, due to the contrast agent, the location of the catheter in the angiography image appears darker. Therefore, it is necessary to filter out edge pixels with grayscale values ​​less than or equal to a grayscale threshold. For each edge pixel in each frame of the angiography image, it is determined whether the grayscale value of the edge pixel in the angiography image is less than or equal to the grayscale threshold. If so, based on the pixel coordinates of the edge pixel in the angiography image and the corresponding frame number of the angiography image in the angiography video, the pixel block corresponding to the edge pixel is drawn in the blank grayscale marker map to generate a dynamic grayscale marker map.

[0075] Please see Figure 2 , Figure 2 This is a schematic diagram of a dynamic grayscale marker image provided in an embodiment of this application. Figure 2 As shown, Figure 2 Each black pixel block in the image represents an edge pixel that meets the condition.

[0076] Step 1024: Determine the starting point of the catheter in each frame of the angiography image by using multiple pixel blocks in the dynamic grayscale marker image.

[0077] Here, the pixel block is composed of multiple adjacent pixel blocks.

[0078] Regarding step 1024 above, in specific implementation, after the dynamic grayscale marker image is drawn, multiple pixel blocks in the dynamic grayscale marker image are determined. Here, a pixel block is composed of multiple adjacent pixel blocks. Then, the starting point of the catheter in each frame of the angiography image is determined using the multiple pixel blocks in the dynamic grayscale marker image. Here, as an example, such as... Figure 2 As shown, Figure 2 It includes four pixel blocks: pixel block A, pixel block B, pixel block C, and pixel block D.

[0079] Specifically, regarding step 1024 above, determining the starting point of the catheter in each frame of the angiography image by dividing the image into multiple pixel blocks using the dynamic grayscale marker image includes:

[0080] Step 10241: Filter the multiple pixel blocks in the dynamic grayscale marker image to determine the target pixel block.

[0081] Regarding step 10241 above, in specific implementation, multiple pixel blocks in the dynamic grayscale marker image are filtered to determine the target pixel block.

[0082] Specifically, regarding step 10241 above, the step of filtering multiple pixel blocks in the dynamic grayscale marker image to determine the target pixel block includes:

[0083] A: For each pixel block, determine whether the pixel width of the pixel block is within the preset pixel width range.

[0084] It should be noted that the pixel width range refers to a pre-defined width range used to determine whether a pixel block meets the filtering criteria. For example, the pre-defined pixel width range is greater than 4 pixels and less than 10 pixels.

[0085] Here, the size of the conduit is generally 5F or 6F, which is represented by about 6 pixels on the image. Therefore, it is necessary to exclude pixel blocks whose pixel width is not within the pixel width range. Regarding step A above, in specific implementation, for each pixel block, it is determined whether the pixel width of the pixel block is within the preset pixel width range. If not, the pixel block is filtered out; if so, proceed to step B below.

[0086] B: If the pixel width of the pixel block is within the pixel width range, then continue to determine whether the pixel height of the pixel block is greater than or equal to the preset pixel height threshold.

[0087] C: If the pixel height of the pixel block is greater than or equal to the pixel height threshold, then the pixel block is determined as the target pixel block.

[0088] It should be noted that the pixel height threshold refers to a pre-set height threshold used to determine whether a pixel block meets the filtering criteria. For example, the pixel height threshold can be set to 0.9 times the number of frames in the imaging image.

[0089] Regarding step B above, in specific implementation, since the catheter is always present on the imaging image, it is necessary to determine whether the pixel height of the pixel block is greater than or equal to the preset pixel height threshold. If not, the pixel block is filtered out; if so, step C above is continued to determine the pixel block as the target pixel block.

[0090] As an optional implementation, since the conduit is dynamically changing, and some pixel blocks in the dynamic grayscale marker image represent static elements, they also need to be filtered out. After filtering based on the above three conditions, if there are still more than one pixel block, the pixel block with the highest pixel height (longest existence time) is selected as the target pixel block. Here, as an example, such as... Figure 2 As shown, Figure 2 Pixel block A in the image is the final target pixel block that meets the filtering criteria.

[0091] Step 10242: For each row of pixel blocks in the target pixel block, the centroid is calculated using the pixel coordinate values ​​corresponding to each pixel block in that row to obtain the centroid coordinates.

[0092] Regarding step 10242 above, in specific implementation, after the target pixel blocks are determined, for each row of pixel blocks in the target pixel blocks, the centroid is calculated using the pixel coordinate values ​​corresponding to each pixel block in that row to obtain the centroid coordinates. Specifically, the centroid calculation method is as follows:

[0093]

[0094] Where i represents the i-th frame, c(i) = c(x, y) represents the centroid coordinates of the i-th frame, and M represents the number of pixel blocks in the i-th frame, for example, as... Figure 2 In pixel block A, row 0 has two pixel blocks, so M = 2, and (x j y j ) represents the pixel coordinate value corresponding to the pixel block on the horizontal axis.

[0095] Step 10243: Determine the target frame number corresponding to the row of pixels in the dynamic grayscale marker image, and determine the starting point of the catheter in the angiography image corresponding to the target frame number in the angiography video based on the centroid coordinates.

[0096] Regarding step 10243 above, in specific implementation, after determining the centroid coordinates corresponding to the row of pixels, the target frame number corresponding to that row of pixels is determined in the dynamic grayscale marker image. Based on the centroid coordinates, the starting point of the catheter in the angiography image corresponding to the target frame number in the angiography video is determined. Here, since the vertical axis of the dynamic grayscale marker image represents the frame number, the target frame number corresponding to that row of pixels is determined, and the angiography image corresponding to that target frame number is determined in the angiography video. The point corresponding to the centroid coordinates in this angiography image is the starting point of the catheter in that angiography image.

[0097] S103, for each frame of contrast image, calculate the catheter area of ​​the catheter region corresponding to the catheter in the contrast image using the starting point of the catheter in the contrast image.

[0098] Regarding step S103 above, in specific implementation, for each frame of contrast image, the catheter area of ​​the catheter region corresponding to the catheter in the contrast image is calculated using the starting point of the catheter in the contrast image.

[0099] Specifically, regarding step S103 above, the step of calculating the catheter area corresponding to the catheter in the contrast image using the starting point of the catheter in the contrast image includes:

[0100] Step 1031: Take the starting point as the catheter pixel point and obtain the pixel value of the catheter pixel point in the imaging image.

[0101] Step 1032: For each adjacent pixel in the contrast image that is adjacent to the duct pixel, obtain the pixel value of the adjacent pixel, and determine whether the difference between the pixel value of the adjacent pixel and the pixel value of the duct pixel is within a preset range.

[0102] Step 1033: If yes, then the adjacent pixel is determined as the conduit pixel.

[0103] Step 1034: Return to the step of obtaining the pixel value of each adjacent pixel in the contrast image that is adjacent to the duct pixel, until there are no adjacent pixels in the contrast image that are adjacent to the duct pixel, and obtain all duct pixels in the contrast image.

[0104] Here, to determine the duct region in each frame of the contrast image, region generation needs to start from the starting point of the duct. Regarding steps 1031-1034 above, in specific implementation, the starting point is taken as the duct pixel, and the pixel value of the duct pixel in the contrast image is obtained. For each adjacent pixel in the contrast image that is adjacent to the duct pixel, the pixel value of the adjacent pixel is obtained, and it is determined whether the difference between the pixel value of the adjacent pixel and the pixel value of the duct pixel is within a preset range. If so, the adjacent pixel is determined as the duct pixel. Then, following the above conditions, the process continues forward, returning to the step described in step 1032 above, where the pixel value of each adjacent pixel in the contrast image that is adjacent to the duct pixel is obtained, until there are no adjacent pixels in the contrast image that are adjacent to the duct pixel. At this point, it is considered that all pixels cannot grow outwards, and all duct pixels in the contrast image are obtained.

[0105] Step 1035: Determine the catheter region based on all catheter pixels in the imaging image, and calculate the catheter area corresponding to the catheter region based on the number of all catheter pixels.

[0106] Regarding step 1035 above, in specific implementation, after all catheter pixels in the contrast image are determined, all catheter pixels are defined as the catheter region, and then the catheter area corresponding to the catheter region is calculated based on the number of all catheter pixels. Here, the catheter area is calculated using the following formula:

[0107]

[0108] Where S i S represents the area of ​​the duct corresponding to the duct region in the i-th frame, M is the total number of duct pixels after growth in the i-th frame, and we can assume that the area of ​​each duct pixel is 1. iThat is, the number of pixels in the conduit multiplied by 1.

[0109] S104, sequentially compare the catheter area of ​​the catheter region in any two adjacent frames of the angiography video. If the difference between the catheter area of ​​the catheter region in the later frame of the two adjacent frames and the catheter area of ​​the catheter region in the previous frame of the two adjacent frames is greater than or equal to the area difference threshold, then the previous frame of the angiography is taken as the termination frame of the angiography in the non-filled state.

[0110] It should be noted that two adjacent angiographic images refer to any two consecutive frames in an angiographic video. For example, frame 0 and frame 1 are considered two adjacent angiographic images. In this case, frame 0 is the preceding frame in the two adjacent frames, and frame 1 is the following frame. The area difference threshold can be 30% of the catheter area in the preceding frame; however, this application does not impose a specific limitation on this.

[0111] Regarding step S104 above, in specific implementation, the catheter area of ​​the catheter region in any two adjacent frames of angiography video is compared sequentially. When the ratio between the catheter area of ​​the catheter region in the later frame of two adjacent frames and the catheter area of ​​the catheter region in the earlier frame of two adjacent frames is greater than or equal to the area difference threshold, the earlier frame is taken as the termination frame of the non-filling state. Here, starting from frame 0, when the catheter area in the later frame increases dramatically compared to the catheter area in the earlier frame, for example, if the catheter area in the later frame exceeds 30% of the catheter area in the earlier frame, it is considered that the contrast agent has begun to fill, and the later frame is the first frame in the filling state, and the earlier frame is the last frame in the non-filling state.

[0112] S105, the catheter region in the termination frame angiography image is skeletonized to obtain the catheter centerline, and the termination point of the catheter in the termination frame angiography image is determined based on the catheter centerline.

[0113] Regarding step S105 above, in specific implementation, after the duct region in the final frame angiography image is determined, skeletonization is performed on this duct region to obtain the duct centerline. Here, digital image skeletonization is the process of transforming the foreground region in a binarized image into its "skeleton". Generally, the steps of digital image skeletonization can be summarized as follows: 1. Image preprocessing: Usually, some preprocessing operations are needed on the image, such as noise removal and smoothing, in order to better extract the image skeleton. 2. Edge extraction: Some edge detection algorithms, such as the Canny algorithm, can be used to extract the edges in the image. 3. Central axis extraction: The edge lines are shrunk inward until the central axis is extracted. Commonly used algorithms include distance transformation and thinning algorithms. 4. Skeleton refinement: Some post-processing operations are performed on the extracted skeleton to make the skeleton more refined and continuous. For example, operations such as connecting breakpoints and removing isolated points can be performed. The other endpoint after skeletonization is the duct endpoint. Once the catheter centerline is obtained, the other endpoint of the catheter centerline, excluding the starting point of the catheter, can be determined as the termination point of the catheter in the final frame angiographic image.

[0114] The catheter localization method for non-filled frames of angiography provided in this application first acquires an angiography video and identifies multiple edge pixels in the video. Then, a dynamic grayscale marker map is determined using the grayscale values ​​corresponding to these edge pixels in each frame of the angiography video, and the starting point of the catheter in each frame is determined using the dynamic grayscale marker map. For each frame, the catheter area corresponding to the catheter in that frame is calculated using the starting point of the catheter in that frame. The angiography images are then compared sequentially. In any two adjacent frames of contrast imaging in the video, if the difference between the catheter area in the later frame of the two adjacent frames and the catheter area in the earlier frame of the two adjacent frames is greater than or equal to an area difference threshold, then the earlier frame of contrast imaging is taken as the termination frame of contrast imaging in a non-filled state. Finally, the catheter region in the termination frame of contrast imaging is skeletonized to obtain the catheter centerline, and the termination point of the catheter in the termination frame of contrast imaging is determined based on the catheter centerline.

[0115] This application obtains the catheter start point in each frame of angiography by dynamically analyzing the grayscale of surrounding pixels in dynamic angiography images. Then, region growing is used to obtain the catheter termination position. The catheter localization method for non-filled frames of angiography provided by this application can automatically and quickly acquire the catheter position of angiography, accurately locate the catheter start point, and thus determine the catheter position in the non-filled termination frame angiography image, providing an important foundation for the subsequent catheter localization in filled frames.

[0116] Please see Figure 3 , Figure 3 This is a schematic diagram of a catheter positioning device for non-filling frames in angiography, provided as an embodiment of this application. Figure 3 As shown, the catheter positioning device 300 includes:

[0117] Edge pixel point determination module 301 is used to acquire angiography video and determine multiple edge pixels in the angiography video;

[0118] The catheter starting point determination module 302 is used to determine a dynamic grayscale marker map by using the grayscale values ​​corresponding to the multiple edge pixels in each frame of the angiography video, and to determine the starting point of the catheter in each frame of the angiography video by using the dynamic grayscale marker map.

[0119] The catheter area determination module 303 is used to calculate the catheter area of ​​the catheter region corresponding to the catheter in the contrast image for each frame of contrast image using the starting point of the catheter in the contrast image;

[0120] The termination frame angiography image determination module 304 is used to sequentially compare the catheter area of ​​the catheter region in any two adjacent frames of the angiography video. When the difference between the catheter area of ​​the catheter region in the later frame of the two adjacent frames of the angiography video and the catheter area of ​​the catheter region in the previous frame of the two adjacent frames of the angiography video is greater than or equal to the area difference threshold, the previous frame of the angiography video is used as the termination frame angiography image in the non-filling state.

[0121] The catheter termination point determination module 305 is used to skeletonize the catheter region in the termination frame angiography image to obtain the catheter centerline, and determine the termination point of the catheter in the termination frame angiography image based on the catheter centerline.

[0122] Furthermore, when the catheter start point determination module 302 determines a dynamic grayscale marker map using the grayscale values ​​corresponding to multiple edge pixel coordinates in each frame of the angiography image, and determines the start point of the catheter in each frame of the angiography image using the dynamic grayscale marker map, the catheter start point determination module 302 is also used for:

[0123] Using the pixel coordinates of the multiple edge pixels in any frame of the angiography image as the horizontal axis and the frame number corresponding to the angiography video as the vertical axis, a blank grayscale marker image is generated.

[0124] For each edge pixel in each frame of the contrast image, determine whether the gray value of the edge pixel in the contrast image is less than or equal to the gray value threshold;

[0125] If so, then according to the pixel coordinates of the edge pixel in the angiography image and the frame number of the angiography image in the angiography video, the pixel block corresponding to the edge pixel is drawn in the blank grayscale marker image to generate the dynamic grayscale marker image.

[0126] The starting point of the catheter in each frame of the angiography image is determined by using multiple pixel blocks in the dynamic grayscale marker image; wherein, the pixel block is composed of multiple adjacent pixel blocks.

[0127] Furthermore, when determining the starting point of the catheter in each frame of the angiography image using multiple pixel blocks in the dynamic grayscale marker image, the catheter starting point determination module 302 is also used to:

[0128] The target pixel block is determined by filtering multiple pixel blocks in the dynamic grayscale marker image.

[0129] For each row of pixel blocks in the target pixel block, the centroid is calculated using the pixel coordinates corresponding to each pixel block in that row, and the centroid coordinates are obtained.

[0130] The target frame number corresponding to the row of pixels is determined in the dynamic grayscale marker image, and the starting point of the catheter in the angiography image corresponding to the target frame number in the angiography video is determined according to the centroid coordinates.

[0131] Furthermore, when the catheter starting point determination module 302 is used to filter multiple pixel blocks in the dynamic grayscale marker image and determine the target pixel block, the catheter starting point determination module 302 is also used to:

[0132] For each pixel block, determine whether the pixel width of the pixel block is within the preset pixel width range;

[0133] If the pixel width of the pixel block is within the pixel width range, then continue to determine whether the pixel height of the pixel block is greater than or equal to the preset pixel height threshold;

[0134] If the pixel height of the pixel block is greater than or equal to the pixel height threshold, then the pixel block is determined as the target pixel block.

[0135] Furthermore, when the catheter area determination module 303 calculates the catheter area of ​​the catheter region corresponding to the catheter in the contrast image using the starting point of the catheter in the contrast image, the catheter area determination module 303 is also used for:

[0136] The starting point is used as the catheter pixel point, and the pixel value of the catheter pixel point in the contrast image is obtained;

[0137] For each adjacent pixel in the contrast image that is adjacent to the duct pixel, the pixel value of the adjacent pixel is obtained, and it is determined whether the difference between the pixel value of the adjacent pixel and the pixel value of the duct pixel is within a preset range;

[0138] If so, then the adjacent pixel is identified as the conduit pixel;

[0139] Return to the step of obtaining the pixel value of each adjacent pixel in the contrast image that is adjacent to the duct pixel, until there are no adjacent pixels in the contrast image that are adjacent to the duct pixel, and obtain all duct pixels in the contrast image;

[0140] The catheter region is determined based on all the catheter pixels in the imaging image, and the catheter area corresponding to the catheter region is calculated based on the number of all the catheter pixels.

[0141] Please see Figure 4 , Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 4 As shown, the electronic device 400 includes a processor 410, a memory 420, and a bus 430.

[0142] The memory 420 stores machine-readable instructions executable by the processor 410. When the electronic device 400 is running, the processor 410 communicates with the memory 420 via the bus 430. When the machine-readable instructions are executed by the processor 410, they can perform the operations described above. Figure 1 The steps of the catheter positioning method for non-filling frames in angiography in the method embodiment shown are described in detail in the method embodiment, and will not be repeated here.

[0143] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, can perform the above-described actions. Figure 1The steps of the catheter positioning method for non-filling frames in angiography in the method embodiment shown are described in detail in the method embodiment, and will not be repeated here.

[0144] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0145] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the shown or discussed mutual couplings, direct couplings, or communication connections may be through some communication interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0146] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0147] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0148] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0149] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0150] Finally, it should be noted that the above-described embodiments are merely specific implementations of this application, used to illustrate the technical solutions of this application, and not to limit them. The scope of protection of this application is not limited thereto. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the scope of the technology disclosed in this application. Such modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method of positioning a catheter for an angiographic non- opacified frame, characterized in that, The catheter positioning method comprises: An angiography video is acquired, and a plurality of edge pixel points in the angiography video are determined; wherein the edge pixel points refer to pixel points of a boundary in each frame of the angiography video, and the horizontal coordinate and the vertical coordinate in the pixel coordinate of the edge pixel points satisfy at least one being 0 or at least one being the maximum value of the pixel size of the angiography image; A dynamic gray scale marker map is determined by using the gray scale values corresponding to the plurality of edge pixel points in each frame of the angiography video, and a starting point of the catheter in each frame of the angiography video is determined by using the dynamic gray scale marker map; For each frame of the angiography image, the catheter area corresponding to the catheter in the angiography image is calculated by using the starting point of the catheter in the angiography image; The catheter areas of the catheter regions in any two adjacent frames of the angiography video are compared in sequence, and when the difference between the catheter area of the catheter region in the latter frame of the two adjacent frames of the angiography video and the catheter area of the catheter region in the former frame of the two adjacent frames of the angiography video is greater than or equal to an area difference threshold value, the former frame of the angiography image is taken as a terminal frame of angiography in a non-filling state; The catheter region in the terminal frame of the angiography image is skeletonized to obtain a catheter center line, and a terminal point of the catheter in the terminal frame of the angiography image is determined based on the catheter center line; wherein the other end point of the catheter center line except the starting point of the catheter is determined as the terminal point of the catheter in the terminal frame of the angiography image; The dynamic gray scale marker map is determined by using the gray scale values corresponding to the plurality of edge pixel coordinates in each frame of the angiography image, and the starting point of the catheter in each frame of the angiography image is determined by using the dynamic gray scale marker map, comprising: The pixel coordinate values of the plurality of edge pixel points in any one frame of the angiography image are taken as the horizontal axis, and the frame number corresponding to the angiography video is taken as the vertical axis to generate a blank gray scale marker map; For each edge pixel point in each frame of the angiography image, it is judged whether the gray scale value of the edge pixel point in the angiography image is less than or equal to a gray scale threshold value; If yes, a pixel block corresponding to the edge pixel point is drawn in the blank gray scale marker map according to the pixel coordinate value of the edge pixel point in the angiography image and the frame number corresponding to the angiography image in the angiography video, so as to generate the dynamic gray scale marker map; wherein the dynamic gray scale marker map is used to record whether the gray scale value of each edge pixel point in each frame of the angiography image satisfies a preset gray scale value condition; The starting point of the catheter in each frame of the angiography image is determined by using a plurality of pixel blocks in the dynamic gray scale marker map; wherein the pixel block is composed of a plurality of adjacent pixel blocks; The starting point of the catheter in each frame of the angiography image is determined by using a plurality of pixel blocks in the dynamic gray scale marker map, comprising: The plurality of pixel blocks in the dynamic gray scale marker map are screened to determine a target pixel block; For each row of pixel blocks in the target pixel block, a centroid coordinate is calculated using the pixel coordinate value corresponding to each pixel block in the row; A target frame number corresponding to the row of pixel blocks is determined in the dynamic gray scale mark graph, and the starting point of the catheter in the angiography image corresponding to the target frame number in the angiography video is determined according to the centroid coordinate.

2. The catheter positioning method of claim 1, wherein, The screening of the plurality of pixel blocks in the dynamic gray scale mark graph to determine a target pixel block comprises: For each pixel block, it is determined whether the pixel width of the pixel block is within a preset pixel width range; If the pixel width of the pixel block is within the pixel width range, it is further determined whether the pixel height of the pixel block is greater than or equal to a preset pixel height threshold; If the pixel height of the pixel block is greater than or equal to the pixel height threshold, the pixel block is determined as the target pixel block.

3. The catheter positioning method of claim 1, wherein, The calculation of the catheter area of the catheter region corresponding to the catheter in the angiography image using the starting point of the catheter in the angiography image comprises: The starting point is taken as a catheter pixel point, and a pixel value of the catheter pixel point in the angiography image is obtained; For each adjacent pixel point adjacent to the catheter pixel point in the angiography image, a pixel value of the adjacent pixel point is obtained, and it is determined whether the difference between the pixel value of the adjacent pixel point and the pixel value of the catheter pixel point is within a preset range; If yes, the adjacent pixel point is determined as the catheter pixel point; The step of obtaining the pixel value of each adjacent pixel point adjacent to the catheter pixel point in the angiography image is returned to be executed until there is no adjacent pixel point adjacent to the catheter pixel point in the angiography image, and all catheter pixel points in the angiography image are obtained; The catheter region is determined according to the all catheter pixel points in the angiography image, and the catheter area corresponding to the catheter region is calculated according to the number of all catheter pixel points.

4. A catheter positioning device for angiographic non- opacified frames, characterized in that, The catheter positioning device comprises: An edge pixel point determination module is configured to obtain a digital subtraction angiography video and determine a plurality of edge pixel points in the digital subtraction angiography video; wherein the edge pixel point refers to a pixel point of a boundary in each frame of the digital subtraction angiography video, and the horizontal coordinate and the vertical coordinate in the pixel coordinate of the edge pixel point satisfy at least one of 0 or at least one of the maximum value of the pixel size of the frame of the digital subtraction angiography video; A catheter starting point determination module is configured to determine a dynamic gray scale mark graph using the gray scale values corresponding to the plurality of edge pixel points in each frame of the digital subtraction angiography video, and determine a starting point of a catheter in each frame of the digital subtraction angiography video using the dynamic gray scale mark graph; A catheter area determination module is configured to calculate, for each frame of the digital subtraction angiography video, a catheter area of a catheter region corresponding to the catheter in the frame of the digital subtraction angiography video using the starting point of the catheter in the frame of the digital subtraction angiography video. a termination frame angiogram determining module, configured to compare the catheter area of the catheter region in any two adjacent angiogram images in the angiography video in sequence, and when the difference between the catheter area of the catheter region in a later angiogram image and the catheter area of the catheter region in an earlier angiogram image in the two adjacent angiogram images is greater than or equal to an area difference threshold value, the earlier angiogram image is determined as a termination frame angiogram in a non-filling state; a catheter termination point determining module, configured to skeletonize the catheter region in the termination frame angiogram to obtain a catheter center line, and determine a termination point of the catheter in the termination frame angiogram based on the catheter center line; wherein another end point of the catheter center line except a starting point of the catheter is determined as the termination point of the catheter in the termination frame angiogram; the catheter starting point determining module is further configured to: generate a blank gray scale mark graph by taking the pixel coordinate value of the plurality of edge pixels in any angiogram image as the horizontal axis and taking the frame number corresponding to the angiography video as the vertical axis; determine, for each edge pixel in each angiogram image, whether the gray scale value of the edge pixel in the angiogram image is less than or equal to a gray scale threshold value; if yes, draw a pixel block corresponding to the edge pixel in the blank gray scale mark graph according to the pixel coordinate value of the edge pixel in the angiogram image and the frame number corresponding to the angiogram image in the angiography video, to generate the dynamic gray scale mark graph; wherein the dynamic gray scale mark graph is used to record whether the gray scale value of each edge pixel in each angiogram image meets a preset gray scale value condition; determine the starting point of the catheter in each angiogram image by using a plurality of pixel blocks in the dynamic gray scale mark graph; wherein the pixel block is composed of a plurality of adjacent pixel blocks; the catheter starting point determining module is further configured to: screen the plurality of pixel blocks in the dynamic gray scale mark graph to determine a target pixel block; for each row of pixel blocks in the target pixel block, perform centroid calculation by using the pixel coordinate value corresponding to each pixel block in the row to obtain a centroid coordinate; determine a target frame number corresponding to the row of pixel blocks in the dynamic gray scale mark graph, and determine the starting point of the catheter in the angiogram image corresponding to the target frame number in the angiography video according to the centroid coordinate.

5. An electronic device, comprising: including: A processor, a memory, and a bus, the memory storing machine readable instructions executable by the processor, when the electronic device is running, the processor and the memory communicating through the bus, the machine readable instructions being executed by the processor to perform the steps of the method for positioning a catheter for a non-filled frame of an angiogram according to any one of claims 1 to 3.

6. A computer-readable storage medium, characterized in that, A computer readable storage medium storing a computer program, the computer program being executed by a processor to perform the steps of the method for positioning a catheter for a non-filled frame of an angiogram according to any one of claims 1 to 3.

Images