Method and device for extracting lumen profile of blood vessel, electronic equipment and storage medium

Abstract

The application provides a blood vessel lumen profile extraction method and device, electronic equipment and storage medium. The extraction method comprises the following steps: taking the first video frame in the acquired blood vessel lumen video sequence as a current video frame to obtain a current lumen profile of the current video frame; denoising the current lumen profile of the current video frame to obtain an initial lumen profile of the current video frame; optimizing the initial lumen profile of the current video frame to determine a target lumen profile of the current video frame; taking the target lumen profile of the current video frame as the initial lumen profile of the next video frame of the current video frame, and updating the next video frame of the current video frame as the current video frame to continue optimization until the last video frame in the lumen video sequence. The technical scheme provided by the application can improve the efficiency and accuracy of blood vessel lumen profile extraction.

Description

Technical Field

[0001] This application relates to the field of medical imaging technology, and in particular to a method, apparatus, electronic device, and storage medium for extracting the luminal contour of a blood vessel. Background Technology

[0002] Vascular imaging is mainly divided into intravascular ultrasound (IVUS) and optical coherence tomography (OCT). Intravascular imaging (IVUS / OCT) offers extremely high resolution, clearly showing the lumen and plaque conditions of blood vessels. Obtaining the luminal contour is a crucial prerequisite for calculating the luminal diameter / area, analyzing the degree of stenosis, and subsequent vascular reconstruction. In intravascular imaging, rapidly and automatically acquiring smooth and accurate luminal contours can significantly shorten surgical time, facilitate observation of pre- and post-operative vascular lumen conditions, and reduce the burden on both doctors and patients.

[0003] Currently, there are two main types of methods for extracting (segmenting) the luminal contour of intravascular images. One type is based on deep learning, which involves manually annotating a large amount of luminal data, spending considerable time training a final model, and then directly applying it to new data. The other type uses polar coordinate transformation, then uses gradients to obtain the vessel boundaries, and finally connects them to form the contour. The former is limited by the need for a large amount of data, accurate manual annotation, and significant subsequent model training time. The latter requires polar coordinate transformation, and the contour obtained by simply using gradients contains some noise, requiring reasonable noise removal methods to obtain an accurate and smooth contour. Therefore, how to extract the luminal contour of blood vessels has become an urgent problem to be solved. Summary of the Invention

[0004] In view of this, the purpose of this application is to provide a method, apparatus, electronic device, and storage medium for extracting the lumen contour of a blood vessel. This method can extract the lumen contour of a blood vessel without labeling the lumen or performing polar coordinate transformation. It obtains an initial lumen contour by denoising the current lumen contour of the first extracted video frame, optimizes the initial lumen contour to obtain a target lumen contour, and uses the target lumen contour as the initial lumen contour of the next video frame for further optimization. This process improves the efficiency and accuracy of extracting the lumen contour of a blood vessel.

[0005] This application mainly includes the following aspects:

[0006] In a first aspect, embodiments of this application provide a method for extracting the luminal contour of a blood vessel, the extraction method comprising:

[0007] Acquire a video sequence of the lumen of a blood vessel; wherein the video sequence is a sequence of multiple video frames taken at intervals along the course of the blood vessel;

[0008] The first video frame in the lumen video sequence is taken as the current video frame to obtain the current lumen profile of the current video frame;

[0009] Based on the current lumen contour of the current video frame, the current lumen contour of the current video frame is denoised, and the denoised current lumen contour is determined as the initial lumen contour of the current video frame.

[0010] The initial lumen profile of the current video frame is optimized to determine the target lumen profile of the current video frame;

[0011] Determine whether the current video frame is the last video frame in the lumen video sequence. If not, use the target lumen contour of the current video frame as the initial lumen contour of the next video frame, and update the next video frame to the current video frame to continue optimization until the last video frame in the lumen video sequence. Then, determine the target lumen contour of each video frame in the lumen video sequence as the lumen contour of the blood vessel.

[0012] Furthermore, the step of taking the first video frame in the lumen video sequence as the current video frame and obtaining the current lumen contour of the current video frame includes:

[0013] The first video frame in the lumen video sequence is taken as the current video frame. A ray is emitted at preset degrees from the center point of the current video frame to obtain multiple rays.

[0014] For each ray, determine the pixels that the ray passes through and the grayscale difference of each pixel in the current video frame;

[0015] The pixel corresponding to the largest grayscale difference is determined as the lumen contour point of the ray;

[0016] The lumen contour points of each ray are connected sequentially to obtain the current lumen contour of the current video frame.

[0017] Furthermore, the step of determining, for each ray, the pixels traversed by the ray and the grayscale difference of each traversed pixel in the current video frame includes:

[0018] For each ray, a sampling point on that ray is obtained, and the distance between the sampling point and the four surrounding pixels is determined by Euclidean distance.

[0019] The pixel corresponding to the smallest distance is determined as the pixel that the ray passes through;

[0020] The pixels along the path of the ray are arranged sequentially according to the direction of the ray to obtain a pixel sequence;

[0021] The pixel sequence is processed by sliding convolution to obtain the grayscale difference of each pixel in the pixel sequence.

[0022] Furthermore, the step of denoising the current lumen contour of the current video frame based on the current lumen contour of the current video frame, and determining the denoised current lumen contour as the initial lumen contour of the current video frame, includes:

[0023] Based on the current lumen profile of the current video frame, a fan-shaped region of a preset angle is determined in the current lumen profile of the current video frame at each preset interval angle.

[0024] Based on each lumen contour point in the current lumen contour of the current video frame, for each sector region, determine the distance from each lumen contour point in the sector region to the center point of the current video frame;

[0025] The variance of the sector region is determined based on the distance from each lumen profile point in the sector region to the center point of the current video frame.

[0026] In the variance of each sector region, the consecutive sector regions containing the largest variance are determined as the target sector region;

[0027] For each lumen contour point in the target sector region, determine the updated position of each lumen contour point in the target sector region;

[0028] Based on the updated position of each lumen contour point in the target sector region, the current lumen contour is updated, and the updated current lumen contour is determined as the initial lumen contour of the current video frame.

[0029] Furthermore, the step of determining the updated position of each lumen contour point in the target sector region includes:

[0030] For each lumen contour point in the target sector region, the updated distance from the lumen contour point to the center point of the current video frame is determined based on the angle corresponding to the lumen contour point, the minimum angle of the target sector region, the distance from the lumen contour point corresponding to the minimum angle to the center point of the current video frame, the maximum angle of the target sector region, and the distance from the lumen contour point corresponding to the maximum angle to the center point of the current video frame.

[0031] The updated position of each lumen profile point in the target sector region is determined based on the updated distance of each lumen profile point in the target sector region and the angle of each lumen profile point in the target sector region.

[0032] Furthermore, the initial lumen profile of the current video frame is optimized through the following steps to determine the target lumen profile of the current video frame:

[0033] Based on the position of each lumen contour point in the initial lumen contour of the current video frame, determine the current energy of each lumen contour point;

[0034] For each lumen contour point, the lumen contour point is moved according to a preset movement method to obtain the position of the lumen contour point after the movement, and the energy of the lumen contour point is re-determined based on the position of the lumen contour point after the movement.

[0035] If the energy of the redefined lumen profile point is less than the current energy of the lumen profile point, then the energy of the redefined lumen profile point is updated to the current energy of the lumen profile point, and the lumen profile point is moved again until it is determined that the energy of the moved lumen profile point is not less than the current energy of the lumen profile point, and the target position of the lumen profile point is obtained.

[0036] Based on the target position of each lumen contour point, the initial lumen contour of the current video frame is updated, and the updated initial lumen contour of the current video frame is determined as the target lumen contour of the current video frame.

[0037] Secondly, embodiments of this application also provide an extraction device for the lumen contour of a blood vessel, the extraction device comprising:

[0038] An acquisition module is used to acquire a video sequence of the lumen of a blood vessel; wherein the video sequence of the lumen is a sequence of multiple video frames taken at intervals along the course of the blood vessel;

[0039] The first extraction module is used to take the first video frame in the lumen video sequence as the current video frame and obtain the current lumen contour of the current video frame;

[0040] The second extraction module is used to denoise the current cavity contour of the current video frame based on the current cavity contour of the current video frame, and determine the denoised current cavity contour as the initial cavity contour of the current video frame.

[0041] The third extraction module is used to optimize the initial lumen profile of the current video frame and determine the target lumen profile of the current video frame.

[0042] The determination module is used to determine whether the current video frame is the last video frame in the lumen video sequence. If not, the target lumen contour of the current video frame is used as the initial lumen contour of the next video frame, and the next video frame is updated to the current video frame to continue optimization until the last video frame in the lumen video sequence. The target lumen contour of each video frame in the lumen video sequence is determined as the lumen contour of the blood vessel.

[0043] Furthermore, the first extraction module is specifically used for:

[0044] The first video frame in the lumen video sequence is taken as the current video frame. A ray is emitted at preset degrees from the center point of the current video frame to obtain multiple rays.

[0045] For each ray, determine the pixels that the ray passes through and the grayscale difference of each pixel in the current video frame;

[0046] The pixel corresponding to the largest grayscale difference is determined as the lumen contour point of the ray;

[0047] The lumen contour points of each ray are connected sequentially to obtain the current lumen contour of the current video frame.

[0048] 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 method for extracting the lumen contour of blood vessels as described above are performed.

[0049] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the method for extracting the lumen contour of a blood vessel as described above.

[0050] This application provides a method, apparatus, electronic device, and storage medium for extracting the lumen contour of a blood vessel. The extraction method includes: acquiring a video sequence of the blood vessel lumen; wherein the lumen video sequence is a sequence composed of multiple video frames taken at intervals along the direction of the blood vessel; taking the first video frame in the lumen video sequence as the current video frame to obtain the current lumen contour of the current video frame; based on the current lumen contour of the current video frame, denoising the current lumen contour of the current video frame, and determining the denoised current lumen contour as the initial lumen contour of the current video frame; optimizing the initial lumen contour of the current video frame to determine the target lumen contour of the current video frame; determining whether the current video frame is the last video frame in the lumen video sequence; if not, taking the target lumen contour of the current video frame as the initial lumen contour of the next video frame, and updating the next video frame to the current video frame to continue optimization until the last video frame in the lumen video sequence, and determining the target lumen contour of each video frame in the lumen video sequence as the lumen contour of the blood vessel.

[0051] Thus, the technical solution provided in this application eliminates the need for lumen labeling and polar coordinate transformation. By denoising the current lumen contour of the extracted first video frame, an initial lumen contour is obtained. The initial lumen contour is then optimized to obtain the target lumen contour. The target lumen contour is used as the initial lumen contour for the next video frame for further optimization, thereby extracting the lumen contour of the blood vessel and obtaining an accurate and smooth lumen contour, thus improving the efficiency and accuracy of blood vessel lumen contour extraction.

[0052] 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

[0053] 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.

[0054] Figure 1 A flowchart of a method for extracting the lumen contour of a blood vessel provided in an embodiment of this application is shown;

[0055] Figure 2 A flowchart is shown for another method for extracting the lumen contour of a blood vessel provided in an embodiment of this application;

[0056] Figure 3 A schematic diagram of a sliding convolution calculation provided by an embodiment of this application is shown;

[0057] Figure 4 A schematic diagram of a noise removal method provided in an embodiment of this application is shown;

[0058] Figure 5 This diagram illustrates the structure of a device for extracting the lumen contour of a blood vessel according to an embodiment of this application.

[0059] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of this application is shown. Detailed Implementation

[0060] 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. It should be understood that the drawings in this application are for illustrative and descriptive purposes only and are not intended to limit the scope of protection of this application. Furthermore, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of this application. It should be understood that the operations in the flowcharts may not be implemented in sequence, and steps without logical contextual relationships may be reversed or implemented simultaneously. In addition, those skilled in the art, guided by the content of this application, may add one or more other operations to the flowcharts, or remove one or more operations from the flowcharts.

[0061] Furthermore, the described embodiments are merely some, not all, of the embodiments of this application. The components of the embodiments of this application described and illustrated herein can typically 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 to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0062] To enable those skilled in the art to use the content of this application, and in conjunction with the specific application scenario of "extraction of the lumen contour of blood vessels", the following implementation methods are provided. For those skilled in the art, the general principles defined herein can be applied to other embodiments and application scenarios without departing from the spirit and scope of this application.

[0063] The methods, apparatus, electronic devices, or computer-readable storage media described in this application can be applied to any scenario where the lumen contour of a blood vessel needs to be extracted. This application does not limit the specific application scenario. Any scheme that uses the method, apparatus, electronic device, and storage medium for extracting the lumen contour of a blood vessel provided in this application is within the protection scope of this application.

[0064] It is worth noting that intravascular imaging of the coronary arteries is mainly divided into intravascular ultrasound (IVUS) and optical coherence tomography (OCT). IVUS uses catheter technology to insert a miniature ultrasound probe into the blood vessel lumen, performing a 360-degree scan. The results are clearly displayed on a screen showing the structure of the heart's blood vessels and lesions. Unlike coronary angiography, which visualizes the outline of the lumen filled with contrast agent, IVUS displays cross-sectional images of the blood vessel, providing in vivo intravascular imaging. IVUS can accurately measure the lumen, vessel diameter, and assess the severity and nature of lesions, playing a crucial role in improving the understanding of coronary artery lesions and guiding interventional treatment. OCT works by inserting an imaging catheter into the blood vessel and analyzing the time delay of the light source reflecting off the vessel wall, converting internal structural information into high-resolution images displayed on a monitor. Intravascular imaging (IVUS / OCT) has extremely high resolution, clearly showing the lumen and plaque conditions of the blood vessel. Obtaining the luminal contour is a crucial prerequisite for calculating the vessel's diameter / area, analyzing the degree of stenosis, and subsequent vessel reconstruction. In endovascular imaging, rapidly and automatically acquiring smooth and accurate luminal contours can significantly shorten surgical time, facilitate observation of pre- and post-operative vessel conditions, and reduce the burden on both doctors and patients.

[0065] Currently, there are two main types of methods for extracting (segmenting) the contours of intravascular images. One type is based on deep learning, which involves manually annotating a large amount of lumen data, then spending a significant amount of time training a model, which is then directly applied to new data. The other type uses polar coordinate transformation, then uses gradients to obtain the vessel boundaries, and finally connects them to form the contour. The former is limited by the need for a large amount of data, accurate manual annotation, and significant time for subsequent model training. The latter requires polar coordinate transformation, and the contours obtained solely using gradients contain some noise, requiring appropriate noise removal methods to obtain accurate and smooth contours. Therefore, how to extract the contours of the vessel lumen has become an urgent problem to be solved.

[0066] Based on this, this application proposes a method, apparatus, electronic device, and storage medium for extracting the lumen contour of a blood vessel. The extraction method includes: acquiring a video sequence of the blood vessel lumen; wherein the lumen video sequence is a sequence composed of multiple video frames taken at intervals along the direction of the blood vessel; taking the first video frame in the lumen video sequence as the current video frame to obtain the current lumen contour of the current video frame; based on the current lumen contour of the current video frame, denoising the current lumen contour of the current video frame, and determining the denoised current lumen contour as the initial lumen contour of the current video frame; optimizing the initial lumen contour of the current video frame to determine the target lumen contour of the current video frame; determining whether the current video frame is the last video frame in the lumen video sequence; if not, taking the target lumen contour of the current video frame as the initial lumen contour of the next video frame, and updating the next video frame of the current video frame to the current video frame to continue optimization until the last video frame in the lumen video sequence, and determining the target lumen contour of each video frame in the lumen video sequence as the lumen contour of the blood vessel.

[0067] Thus, the technical solution provided in this application eliminates the need for lumen labeling and polar coordinate transformation. By denoising the current lumen contour of the extracted first video frame, an initial lumen contour is obtained. The initial lumen contour is then optimized to obtain the target lumen contour. The target lumen contour is used as the initial lumen contour for the next video frame for further optimization, thereby extracting the lumen contour of the blood vessel and obtaining an accurate and smooth lumen contour, thus improving the efficiency and accuracy of blood vessel lumen contour extraction.

[0068] To facilitate understanding of this application, the technical solutions provided in this application will be described in detail below with reference to specific embodiments.

[0069] Please see Figure 1 , Figure 1 A flowchart illustrating a method for extracting the lumen contour of a blood vessel provided in an embodiment of this application is shown below. Figure 1 As shown, the extraction method includes:

[0070] S101. Obtain the video sequence of the blood vessel lumen;

[0071] In this step, the lumen video sequence is a sequence of multiple video frames taken at intervals along the course of the blood vessel. Here, the images inside the blood vessel are captured continuously at intervals along the course of the blood vessel, for example, one frame is captured every 0.2 mm, displaying a cross-section of the blood vessel. These cross-sections are stacked together to form a lumen video sequence with a size of N×W×H, where N is the number of video frames in the lumen video sequence, and W and H are the width and height of each video frame image.

[0072] S102. Take the first video frame in the lumen video sequence as the current video frame to obtain the current lumen contour of the current video frame;

[0073] In this step, when extracting the lumen profile, the first video frame in the lumen video sequence is selected first to determine the current lumen profile of the first video frame.

[0074] It should be noted that you should refer to [link / reference]. Figure 2 , Figure 2 A flowchart illustrating another method for extracting the lumen contour of a blood vessel provided in this application embodiment is shown below. Figure 2 As shown, the step of taking the first video frame in the lumen video sequence as the current video frame and obtaining the current lumen contour of the current video frame includes:

[0075] S201. Take the first video frame in the lumen video sequence as the current video frame, and emit a ray at preset degrees with the center point of the current video frame as the center to obtain multiple rays;

[0076] In this step, starting from the center of the first video frame, a ray is emitted around the center at preset degrees. The preset degrees can be set in advance based on historical experience or experimental data; for example, a ray is emitted every 1°, and after traversing one circle, a total of 360 rays can be obtained.

[0077] S202. For each ray, determine the pixels that the ray passes through and the grayscale difference of each pixel in the current video frame.

[0078] In this step, a sliding convolution calculation is performed based on the image pixels traversed by each ray in the first video frame to determine the pixel with the largest grayscale difference, which is then used as one of the current lumen contour points in the first video frame.

[0079] It should be noted that, for each ray, the steps of determining the pixels traversed by the ray and the grayscale difference of each traversed pixel in the current video frame include:

[0080] S2021. For each ray, obtain the sampling point on the ray, and determine the distance between the sampling point and the four surrounding pixels using Euclidean distance;

[0081] In this step, each ray consists of multiple sampling points. The sampling points on each ray can be obtained, and the nearest neighbor set of each sampling point can be determined using Euclidean distance.

[0082] Specifically, the Euclidean distance is as follows:

[0083]

[0084] Where, p i Let x represent the nearest neighbor point to be found. i y i (x) represents the position coordinates of the sampling point on the ray. j y j (j = 1, ..., 4) are the position coordinates of four pixels around the sampling point. The pixel closest to the sampling point among the four pixels around the sampling point is taken as the nearest neighbor of the sampling point.

[0085] S2022. Determine the pixel point corresponding to the distance with the smallest value as the pixel point through which the ray passes;

[0086] In this step, the nearest point of the sampling point obtained by Euclidean distance is determined as the pixel point through which the ray passes.

[0087] S2023. Arrange the pixels that the ray passes through in sequence according to the direction of the ray to obtain a pixel sequence;

[0088] In this step, based on the nearest neighbor of each sampling point on the ray, multiple pixels traversed by the ray can be obtained. These multiple pixels traversed by the ray are arranged sequentially according to the ray direction to obtain a pixel sequence. For example, assuming that K nearest neighbor points are calculated along the ray, these K nearest neighbor points are connected in a row, and then in step S2024, sliding convolution is used to calculate the grayscale difference of each pixel on the K nearest neighbor points.

[0089] S2024. The pixel sequence is processed by sliding convolution to obtain the grayscale difference of each pixel in the pixel sequence.

[0090] For example, please refer to Figure 3 , Figure 3 This is a schematic diagram of a sliding convolution calculation provided in an embodiment of this application, as shown below. Figure 3 As shown, the pixels traversed by the ray are arranged sequentially along the ray direction, resulting in a pixel sequence of K=9 nearest neighbors: [45, 53, 50, 55, 44, 149, 154, 144, 134]. The convolution kernel in the sliding convolution process can be k1=[-1, 0, 1] along the ray direction, and k2=[-1, 1] at the edge. The specific formula for the sliding convolution process is as follows:

[0091]

[0092]

[0093] Where f(x) is the gray value of the x-th pixel in the pixel sequence, x = i-1 + j, i is the ith pixel in the pixel sequence, j is the j-th value on the convolution kernel, k1 is the first convolution kernel, K is the number of pixels in the pixel sequence, k2 is the second convolution kernel, and g(i) is the gray difference of the ith pixel in the pixel sequence. Substituting the gray values ​​of each pixel in the pixel sequence into the specific formula of the sliding convolution process above, we can obtain the convolution result [8, 5, 2, -6, 94, 110, -5, -20, -10], which is the gray difference of each pixel in the pixel sequence.

[0094] S203. The pixel point corresponding to the largest grayscale difference is determined as the cavity contour point of the ray.

[0095] In this step, the maximum point is found in the convolution result using the following formula, that is, the gray-level difference with the largest value is determined in the gray-level difference:

[0096]

[0097] Where g(n) is the gray-level difference corresponding to the nth pixel (i.e., the gray-level difference with the largest value in the convolution result; for example, g(n) could be... Figure 3 The grayscale difference corresponding to the 6th pixel (110), such as Figure 3 As shown, the 6th pixel in the pixel sequence can be identified as the lumen contour point of the ray.

[0098] S204. Connect the lumen contour points of each ray sequentially to obtain the current lumen contour of the current video frame.

[0099] For example, the above calculation is performed on all 360 rays to obtain the lumen contour points of each ray. Connecting the 360 ​​lumen contour points in sequence can obtain the current lumen contour of the first video frame.

[0100] S103. Based on the current lumen contour of the current video frame, denoise the current lumen contour of the current video frame, and determine the denoised current lumen contour as the initial lumen contour of the current video frame.

[0101] In this step, due to the artifacts of the guidewire, the lumen of the blood vessel is blocked when the sampling ray passes through the location of the guidewire. The grayscale change at the guidewire is relatively gradual, making it impossible to correctly obtain the lumen contour points. Therefore, it is necessary to identify these points, remove noise, and optimize them to obtain the initial lumen contour.

[0102] Specifically, the distance from all lumen contour points in the current lumen contour to the center point of the first video frame image can be calculated first. Then, the local distance variance is calculated by means of fan-shaped sliding convolution or curve smoothing fitting to obtain the range with large variance as the noise region. Finally, local contour point optimization is performed for each noise region.

[0103] It should be noted that the step of denoising the current lumen contour of the current video frame and determining the denoised current lumen contour as the initial lumen contour of the current video frame includes:

[0104] S1031. Based on the current cavity contour of the current video frame, at each preset interval angle, a fan-shaped region of a preset angle is determined in the current cavity contour of the current video frame.

[0105] In this step, the preset interval angle and the preset angle can be preset based on historical experience or experimental data; for example, the preset interval angle can be set to 1°, the preset angle can be set to 10°, the range of the first sector is [0°, 10°], the range of the second sector is [1°, 11°], and so on, to obtain multiple sector regions.

[0106] S1032. Based on each lumen contour point in the current lumen contour of the current video frame, for each sector region, determine the distance from each lumen contour point in the sector region to the center point of the current video frame;

[0107] For example, there are 360 ​​lumen contour points in the current lumen contour. Based on the position coordinates of each lumen contour point in the current lumen contour, the distance from these 360 ​​lumen contour points to the center point of the first video frame image can be calculated, resulting in 360 distances.

[0108] S1033. Determine the variance of the sector region based on the distance from each lumen contour point in the sector region to the center point of the current video frame;

[0109] It should be noted that the variance of this sector is determined in the following way:

[0110]

[0111]

[0112] Among them, s i Let x be the variance of the sector region containing the i-th lumen profile point. j The distance from the j-th lumen contour point in the sector region to the center point of the current video frame is [the distance]. This is the average distance from all lumen contour points in the sector region to the center point of the current video frame.

[0113] S1034. In the variance of each sector region, the continuous sector region containing the largest variance is determined as the target sector region.

[0114] For example, the set S = {s1, s2, ..., s...} of the variances of each sector region. 360} represents the variance of the sector containing each point, and the continuous region [r] with the largest variance is found. i r j For example, [10°, 36°], this area is defined as the target sector area.

[0115] S1035. For each lumen contour point in the target sector region, determine the updated position of each lumen contour point in the target sector region;

[0116] It should be noted that the step of determining the updated position of each lumen contour point in the target sector region includes:

[0117] 1) For each lumen contour point in the target sector region, based on the angle corresponding to the lumen contour point, the minimum angle of the target sector region, the distance from the lumen contour point corresponding to the minimum angle to the center point of the current video frame, the maximum angle of the target sector region, and the distance from the lumen contour point corresponding to the maximum angle to the center point of the current video frame, determine the update distance from the lumen contour point to the center point of the current video frame.

[0118] It should be noted that the update distance from the lumen contour point to the center point of the current video frame is determined in the following way:

[0119]

[0120] Among them, l k For r i to r j The update distance r from the k-th lumen contour point within the angular range to the center point of the current video frame k For r i to r j The angle r corresponding to the k-th lumen profile point within the angle range i l is the minimum angle of the target sector region. i The minimum angle r of the target sector region i The distance r from the corresponding lumen contour point to the center point of the current video frame j l represents the maximum angle of the target sector region. jThe maximum angle r of the target sector region j The distance from the corresponding lumen contour point to the center point of the current video frame.

[0121] For example, please refer to Figure 4 , Figure 4 This is a schematic diagram of noise removal provided in an embodiment of this application, as shown below. Figure 4 As shown, the circular boundary line represents the current lumen contour, the black dots within the current lumen contour represent the center points of the current video frame, and the area containing angle α within the current lumen contour is the target sector region. This target sector region contains five lumen contour points A, B, C, D, and E; the range of α is [r...]. i r j ], angle r i The distance from the corresponding lumen contour point A to the center point of the current video frame is l i , angle r j The distance from the corresponding lumen contour point E to the center point of the current video frame is l j It can be based on r i r j l i l j The angles of the lumen contour points B, C, and D are used to determine the update distances from B, C, and D to the center point of the current video frame. After this calculation, the change in the length of the lumen contour points is smoother and its variance is smaller.

[0122] 2) Based on the update distance of each lumen contour point in the target sector region and the angle of each lumen contour point in the target sector region, determine the update position of each lumen contour point in the target sector region.

[0123] In this step, the updated position of each lumen contour point within the target sector area is calculated using the angle and the update distance determined in step 1) above. The specific formula is as follows:

[0124] p k =(l k cos(r k ), l k sin(r k ));

[0125] Where, p k This is the update position of the k-th lumen profile point within the target sector region.

[0126] S1036. Based on the updated position of each lumen contour point in the target sector region, update the current lumen contour, and determine the updated current lumen contour as the initial lumen contour of the current video frame.

[0127] S104. Optimize the initial lumen profile of the current video frame to determine the target lumen profile of the current video frame;

[0128] In this step, the initial lumen profile of the current video frame can be optimized using energy equations or gradient methods.

[0129] Here, simply removing grayscale differences and noise is insufficient to obtain a completely accurate contour. Therefore, an active contour model is needed to further optimize the initial lumen contour to obtain a contour that better fits the vessel edge. For example, the active contour model requires establishing an energy equation, consisting of internal energy (internal force) and external energy (external force). When the energy is minimized, it represents the optimal solution for the contour, yielding the target lumen contour.

[0130] It should be noted that the initial lumen profile of the current video frame is optimized through the following steps to determine the target lumen profile of the current video frame:

[0131] S1041. Based on the position of each lumen contour point in the initial lumen contour of the current video frame, determine the current energy of each lumen contour point;

[0132] In this step, the energy equation is as follows:

[0133]

[0134]

[0135]

[0136]

[0137]

[0138]

[0139] Where I represents the current video frame, and E(i,j) represents the energy of the lumen profile point with coordinates (i,j).

[0140] S1042. For each lumen contour point, move the lumen contour point according to a preset movement method to obtain the position of the lumen contour point after movement, and redetermine the energy of the lumen contour point based on the position of the lumen contour point after movement.

[0141] S1043. If the energy of the re-determined lumen contour point is less than the current energy of the lumen contour point, then update the energy of the re-determined lumen contour point to the current energy of the lumen contour point, and continue to move the lumen contour point until it is determined that the energy of the moved lumen contour point is not less than the current energy of the lumen contour point, and obtain the target position of the lumen contour point.

[0142] In steps S1042-S1043, after each calculation of the energy of a lumen contour point, the lumen contour point is offset in multiple directions, such as moving it up by one point, and the position of the lumen contour point is updated. Based on the updated position, the energy of the lumen contour point is calculated again. If the calculated energy is lower, the lumen contour point is moved up again until the energy of the lumen contour point no longer decreases. Then, the last updated position of the lumen contour point is determined as the target position of the lumen contour point.

[0143] S1044. Based on the target position of each lumen contour point, update the initial lumen contour of the current video frame, and determine the updated initial lumen contour of the current video frame as the target lumen contour of the current video frame.

[0144] In this step, the lumen contour points in the initial lumen contour that need to be updated to the target position are obtained through step S1043. The positions of these lumen contour points are updated to the target position, that is, the initial lumen contour of the current video frame is updated to the target lumen contour of the current video frame.

[0145] S105. Determine whether the current video frame is the last video frame in the lumen video sequence. If not, use the target lumen contour of the current video frame as the initial lumen contour of the next video frame of the current video frame, and update the next video frame of the current video frame to the current video frame to continue optimization until the last video frame in the lumen video sequence. Determine the target lumen contour of each video frame in the lumen video sequence as the lumen contour of the blood vessel.

[0146] In this step, up to step S104, the target lumen contour of the first video frame in the intraluminal image has been obtained. Considering the similarity between the lumen contours of blood vessels in two consecutive frames, the target lumen contour of the first video frame is mapped onto the second video frame as the initial lumen contour of the second video frame. This is then optimized using an active contour model. After optimization, the target lumen contour of the second video frame is mapped onto the third video frame as the initial lumen contour, and optimized again using the active contour model. This chain-like continuous processing continues until the last video frame is processed. The target lumen contour of each video frame obtained is the extracted lumen contour of the blood vessel. This embodiment can automatically, quickly, and continuously acquire the lumen contour of blood vessels, locate and eliminate noise, optimize the contour at guidewire obstruction points to obtain an accurate and smooth initial lumen contour, and optimize the initial lumen contour using an active contour model, followed by a chain-like automatic continuous acquisition of the lumen contour, thus improving the efficiency and accuracy of extracting the lumen contour of blood vessels.

[0147] This application provides a method for extracting the lumen contour of a blood vessel. The extraction method includes: acquiring a video sequence of the blood vessel lumen; wherein the video sequence is a sequence composed of multiple video frames taken at intervals along the direction of the blood vessel; taking the first video frame in the video sequence as the current video frame to obtain the current lumen contour of the current video frame; based on the current lumen contour of the current video frame, denoising the current lumen contour of the current video frame, and determining the denoised current lumen contour as the initial lumen contour of the current video frame; optimizing the initial lumen contour of the current video frame to determine the target lumen contour of the current video frame; determining whether the current video frame is the last video frame in the lumen video sequence; if not, taking the target lumen contour of the current video frame as the initial lumen contour of the next video frame, and updating the next video frame of the current video frame to the current video frame to continue optimization until the last video frame in the lumen video sequence, and determining the target lumen contour of each video frame in the lumen video sequence as the lumen contour of the blood vessel.

[0148] Thus, the technical solution provided in this application eliminates the need for lumen labeling and polar coordinate transformation. By denoising the current lumen contour of the extracted first video frame, an initial lumen contour is obtained. The initial lumen contour is then optimized to obtain the target lumen contour. The target lumen contour is used as the initial lumen contour for the next video frame for further optimization, thereby extracting the lumen contour of the blood vessel and obtaining an accurate and smooth lumen contour, thus improving the efficiency and accuracy of blood vessel lumen contour extraction.

[0149] Based on the same application concept, this application also provides a device for extracting the lumen contour of a blood vessel, corresponding to the method for extracting the lumen contour of a blood vessel provided in the above embodiment. Since the principle of the device in this application is similar to the method for extracting the lumen contour of a blood vessel in the above embodiment, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be described again.

[0150] Please see Figure 5 , Figure 5 This is a structural diagram of a device for extracting the lumen contour of a blood vessel, provided in an embodiment of this application. Figure 5 As shown, the extraction device 510 includes:

[0151] The acquisition module 511 is used to acquire a video sequence of the lumen of a blood vessel; wherein the video sequence of the lumen is a sequence composed of multiple video frames taken at intervals along the course of the blood vessel;

[0152] The first extraction module 512 is used to take the first video frame in the lumen video sequence as the current video frame and obtain the current lumen contour of the current video frame.

[0153] The second extraction module 513 is used to denoise the current cavity contour of the current video frame based on the current cavity contour of the current video frame, and determine the denoised current cavity contour as the initial cavity contour of the current video frame.

[0154] The third extraction module 514 is used to optimize the initial lumen profile of the current video frame and determine the target lumen profile of the current video frame.

[0155] The determining module 515 is used to determine whether the current video frame is the last video frame in the lumen video sequence. If not, the target lumen contour of the current video frame is used as the initial lumen contour of the next video frame of the current video frame, and the next video frame of the current video frame is updated to the current video frame to continue optimization until the last video frame in the lumen video sequence. The target lumen contour of each video frame in the lumen video sequence is determined as the lumen contour of the blood vessel.

[0156] Optionally, the first extraction module 512 is specifically used for:

[0157] The first video frame in the lumen video sequence is taken as the current video frame. A ray is emitted at preset degrees from the center point of the current video frame to obtain multiple rays.

[0158] For each ray, determine the pixels that the ray passes through and the grayscale difference of each pixel in the current video frame;

[0159] The pixel corresponding to the largest grayscale difference is determined as the lumen contour point of the ray;

[0160] The lumen contour points of each ray are connected sequentially to obtain the current lumen contour of the current video frame.

[0161] Optionally, when the first extraction module 512 determines, for each ray, the pixels traversed by the ray and the grayscale difference of each traversed pixel in the current video frame, the first extraction module 512 is specifically used for:

[0162] For each ray, a sampling point on that ray is obtained, and the distance between the sampling point and the four surrounding pixels is determined by Euclidean distance.

[0163] The pixel corresponding to the smallest distance is determined as the pixel that the ray passes through;

[0164] The pixels along the path of the ray are arranged sequentially according to the direction of the ray to obtain a pixel sequence;

[0165] The pixel sequence is processed by sliding convolution to obtain the grayscale difference of each pixel in the pixel sequence.

[0166] Optionally, when the second extraction module 513 is used to denoise the current lumen contour of the current video frame based on the current lumen contour of the current video frame, and determine the denoised current lumen contour as the initial lumen contour of the current video frame, the second extraction module 513 is specifically used for:

[0167] Based on the current lumen profile of the current video frame, a fan-shaped region of a preset angle is determined in the current lumen profile of the current video frame at each preset interval angle.

[0168] Based on each lumen contour point in the current lumen contour of the current video frame, for each sector region, determine the distance from each lumen contour point in the sector region to the center point of the current video frame;

[0169] The variance of the sector region is determined based on the distance from each lumen profile point in the sector region to the center point of the current video frame.

[0170] In the variance of each sector region, the consecutive sector regions containing the largest variance are determined as the target sector region;

[0171] For each lumen contour point in the target sector region, determine the updated position of each lumen contour point in the target sector region;

[0172] Based on the updated position of each lumen contour point in the target sector region, the current lumen contour is updated, and the updated current lumen contour is determined as the initial lumen contour of the current video frame.

[0173] Optionally, when determining the updated position of each lumen contour point in the target sector region for each lumen contour point in the target sector region, the second extraction module 513 is specifically used for:

[0174] For each lumen contour point in the target sector region, the updated distance from the lumen contour point to the center point of the current video frame is determined based on the angle corresponding to the lumen contour point, the minimum angle of the target sector region, the distance from the lumen contour point corresponding to the minimum angle to the center point of the current video frame, the maximum angle of the target sector region, and the distance from the lumen contour point corresponding to the maximum angle to the center point of the current video frame.

[0175] The updated position of each lumen profile point in the target sector region is determined based on the updated distance of each lumen profile point in the target sector region and the angle of each lumen profile point in the target sector region.

[0176] Optionally, when the third extraction module 514 optimizes the initial lumen contour of the current video frame and determines the target lumen contour of the current video frame, the third extraction module 514 is specifically used for:

[0177] Based on the position of each lumen contour point in the initial lumen contour of the current video frame, determine the current energy of each lumen contour point;

[0178] For each lumen contour point, the lumen contour point is moved according to a preset movement method to obtain the position of the lumen contour point after the movement, and the energy of the lumen contour point is re-determined based on the position of the lumen contour point after the movement.

[0179] If the energy of the redefined lumen profile point is less than the current energy of the lumen profile point, then the energy of the redefined lumen profile point is updated to the current energy of the lumen profile point, and the lumen profile point is moved again until it is determined that the energy of the moved lumen profile point is not less than the current energy of the lumen profile point, and the target position of the lumen profile point is obtained.

[0180] Based on the target position of each lumen contour point, the initial lumen contour of the current video frame is updated, and the updated initial lumen contour of the current video frame is determined as the target lumen contour of the current video frame.

[0181] This application provides a device for extracting the lumen contour of a blood vessel. The device includes: an acquisition module for acquiring a video sequence of the blood vessel lumen; wherein the video sequence is a sequence composed of multiple video frames taken at intervals along the direction of the blood vessel; a first extraction module for taking the first video frame in the video sequence as the current video frame and obtaining the current lumen contour of the current video frame; and a second extraction module for denoising the current lumen contour of the current video frame based on the current lumen contour of the current video frame, and determining the denoised current lumen contour as the initial lumen outline of the current video frame. The system comprises: a third extraction module for optimizing the initial lumen profile of the current video frame and determining the target lumen profile of the current video frame; and a determination module for determining whether the current video frame is the last video frame in the lumen video sequence. If not, the target lumen profile of the current video frame is used as the initial lumen profile of the next video frame, and the next video frame is updated to the current video frame to continue optimization until the last video frame in the lumen video sequence. The target lumen profile of each video frame in the lumen video sequence is then determined as the lumen profile of the blood vessel.

[0182] Thus, the technical solution provided in this application eliminates the need for lumen labeling and polar coordinate transformation. By denoising the current lumen contour of the extracted first video frame, an initial lumen contour is obtained. The initial lumen contour is then optimized to obtain the target lumen contour. The target lumen contour is used as the initial lumen contour for the next video frame for further optimization, thereby extracting the lumen contour of the blood vessel and obtaining an accurate and smooth lumen contour, thus improving the efficiency and accuracy of blood vessel lumen contour extraction.

[0183] Please see Figure 6 , Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 6 As shown, the electronic device 600 includes a processor 610, a memory 620, and a bus 630.

[0184] The memory 620 stores machine-readable instructions executable by the processor 610. When the electronic device 600 is running, the processor 610 and the memory 620 communicate via the bus 630. When the machine-readable instructions are executed by the processor 610, they can perform the operations described above. Figure 1 as well as Figure 2 The steps of the method for extracting the lumen contour of blood vessels in the illustrated embodiment can be found in the method embodiment for specific implementation, and will not be repeated here.

[0185] 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 1 as well as Figure 2 The steps of the method for extracting the lumen contour of blood vessels in the illustrated embodiment can be found in the method embodiment for specific implementation, and will not be repeated here.

[0186] Those skilled in the art will 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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 for extracting the luminal contour of a blood vessel, characterized in that, The extraction method includes: Acquire a video sequence of the lumen of a blood vessel; wherein the video sequence is a sequence of multiple video frames taken at intervals along the course of the blood vessel; The first video frame in the lumen video sequence is taken as the current video frame to obtain the current lumen profile of the current video frame; Based on the current lumen contour of the current video frame, the current lumen contour of the current video frame is denoised, and the denoised current lumen contour is determined as the initial lumen contour of the current video frame. The initial lumen profile of the current video frame is optimized to determine the target lumen profile of the current video frame; Determine whether the current video frame is the last video frame in the lumen video sequence. If not, use the target lumen contour of the current video frame as the initial lumen contour of the next video frame, and update the next video frame to the current video frame to continue optimization until the last video frame in the lumen video sequence. Then, determine the target lumen contour of each video frame in the lumen video sequence as the lumen contour of the blood vessel. The step of denoising the current lumen contour of the current video frame based on the current lumen contour of the current video frame, and determining the denoised current lumen contour as the initial lumen contour of the current video frame, includes: Based on the current lumen profile of the current video frame, a fan-shaped region of a preset angle is determined in the current lumen profile of the current video frame at each preset interval angle. Based on each lumen contour point in the current lumen contour of the current video frame, for each sector region, determine the distance from each lumen contour point in the sector region to the center point of the current video frame; The variance of the sector region is determined based on the distance from each lumen profile point in the sector region to the center point of the current video frame. In the variance of each sector region, the consecutive sector regions containing the largest variance are determined as the target sector region; For each lumen contour point in the target sector region, determine the updated position of each lumen contour point in the target sector region; Based on the updated position of each lumen contour point in the target sector region, the current lumen contour is updated, and the updated current lumen contour is determined as the initial lumen contour of the current video frame. The step of determining the updated position of each lumen contour point in the target sector region includes: For each lumen contour point in the target sector region, determine the update distance from that lumen contour point to the center point of the current video frame; wherein, the update distance from that lumen contour point to the center point of the current video frame is determined in the following manner: in, for arrive Within the angle range, the first The updated distance from each lumen contour point to the center point of the current video frame. for arrive Within the angle range, the first The angle corresponding to each point on the lumen profile. The minimum angle for the target sector area. Minimum angle of the target sector region The distance from the corresponding lumen contour point to the center point of the current video frame. The maximum angle of the target sector area. The maximum angle of the target sector area The distance from the corresponding lumen contour point to the center point of the current video frame; The updated position of each lumen profile point in the target sector region is determined based on the updated distance of each lumen profile point in the target sector region and the angle of each lumen profile point in the target sector region.

2. The extraction method according to claim 1, characterized in that, The step of taking the first video frame in the lumen video sequence as the current video frame and obtaining the current lumen contour of the current video frame includes: The first video frame in the lumen video sequence is taken as the current video frame. A ray is emitted at preset degrees from the center point of the current video frame to obtain multiple rays. For each ray, determine the pixels that the ray passes through and the grayscale difference of each pixel in the current video frame; The pixel corresponding to the largest grayscale difference is determined as the lumen contour point of the ray; The lumen contour points of each ray are connected sequentially to obtain the current lumen contour of the current video frame.

3. The extraction method according to claim 2, characterized in that, The step of determining, for each ray, the pixels traversed by that ray and the grayscale difference of each traversed pixel in the current video frame includes: For each ray, a sampling point on that ray is obtained, and the distance between the sampling point and the four surrounding pixels is determined by Euclidean distance. The pixel corresponding to the smallest distance is determined as the pixel that the ray passes through; The pixels along the path of the ray are arranged sequentially according to the direction of the ray to obtain a pixel sequence; The pixel sequence is processed by sliding convolution to obtain the grayscale difference of each pixel in the pixel sequence.

4. The extraction method according to claim 1, characterized in that, The initial lumen profile of the current video frame is optimized through the following steps to determine the target lumen profile of the current video frame: Based on the position of each lumen contour point in the initial lumen contour of the current video frame, determine the current energy of each lumen contour point; For each lumen contour point, the lumen contour point is moved according to a preset movement method to obtain the position of the lumen contour point after the movement, and the energy of the lumen contour point is re-determined based on the position of the lumen contour point after the movement. If the energy of the redefined lumen profile point is less than the current energy of the lumen profile point, then the energy of the redefined lumen profile point is updated to the current energy of the lumen profile point, and the lumen profile point is moved again until it is determined that the energy of the moved lumen profile point is not less than the current energy of the lumen profile point, and the target position of the lumen profile point is obtained. Based on the target position of each lumen contour point, the initial lumen contour of the current video frame is updated, and the updated initial lumen contour of the current video frame is determined as the target lumen contour of the current video frame.

5. A device for extracting the luminal contour of a blood vessel, said extraction device being used in the extraction method of claim 1, characterized in that, The extraction device includes: An acquisition module is used to acquire a video sequence of the lumen of a blood vessel; wherein the video sequence of the lumen is a sequence composed of multiple video frames taken at intervals along the course of the blood vessel; The first extraction module is used to take the first video frame in the lumen video sequence as the current video frame and obtain the current lumen contour of the current video frame. The second extraction module is used to denoise the current cavity contour of the current video frame based on the current cavity contour of the current video frame, and determine the denoised current cavity contour as the initial cavity contour of the current video frame. The third extraction module is used to optimize the initial lumen profile of the current video frame and determine the target lumen profile of the current video frame. The determination module is used to determine whether the current video frame is the last video frame in the lumen video sequence. If not, the target lumen contour of the current video frame is used as the initial lumen contour of the next video frame, and the next video frame is updated to the current video frame to continue optimization until the last video frame in the lumen video sequence. The target lumen contour of each video frame in the lumen video sequence is determined as the lumen contour of the blood vessel.

6. The extraction device according to claim 5, characterized in that, The first extraction module is specifically used for: The first video frame in the lumen video sequence is taken as the current video frame. A ray is emitted at preset degrees from the center point of the current video frame to obtain multiple rays. For each ray, determine the pixels that the ray passes through and the grayscale difference of each pixel in the current video frame; The pixel corresponding to the largest grayscale difference is determined as the lumen contour point of the ray; The lumen contour points of each ray are connected sequentially to obtain the current lumen contour of the current video frame.

7. An electronic device, characterized in that, include: The device includes 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. The machine-readable instructions are executed by the processor to perform the steps of the method for extracting the luminal contour of a blood vessel as described in any one of claims 1 to 4.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the steps of the method for extracting the luminal contour of a blood vessel as described in any one of claims 1 to 4.

Images