Microcirculation blood flow speed measurement method and device, electronic equipment and storage medium

Abstract

The invention discloses a microcirculation blood flow speed measurement method and device, electronic equipment and a storage medium. The method comprises the following steps that a blood flow video of a target blood vessel is obtained, and the blood flow video comprises multiple frames of blood vessel images; selecting a reference blood vessel image from the multiple frames of blood vessel images, and extracting a blood vessel trend reference line of the reference blood vessel image; a reference template image sequence is determined in the reference blood vessel image along the blood vessel trend reference line, the reference template image sequence comprises a plurality of reference template images, and the reference template images are images of a blood vessel area in the reference blood vessel image; determining an image sequence corresponding to the reference template image sequence in the blood vessel image of the adjacent frame of the reference blood vessel image; and calculating the inter-frame blood flow velocity based on the reference template image sequence and the position of the image sequence corresponding to the reference template image sequence. According to the method, no tracer particles need to be introduced, noise interference can be reduced, operation is convenient, and the accuracy of medium-low-speed blood flow measurement is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of medical image analysis, and in particular relates to a method and device for measuring microcirculation blood flow velocity, an electronic device and a storage medium. Background Art

[0002] As a core component of the blood circulation system, microcirculation plays an important role in medical research. Through in-depth exploration, basic medicine can more comprehensively grasp the functions and changing laws of the circulatory system, while clinical medicine can better understand the pathogenesis of the disease, thereby improving the ability to analyze and judge the disease. For this reason, microcirculation has become an important research direction in the field of medicine. In the process of microcirculation research, blood flow rate is regarded as a very critical indicator, which plays an irreplaceable role in evaluating the microcirculation status and monitoring the development of related diseases.

[0003] Modern blood flow velocity measurement technology includes two categories: Doppler frequency shift technology and digital image analysis technology. The Doppler frequency shift technology has a relatively high accuracy for high-speed blood flow measurement, but its accuracy will be affected by background noise when the blood flow is low. Digital image analysis technology requires the introduction of tracer ions into the blood flow, and then uses image processing and computer vision technology to track particle movement. However, the introduction of tracer particles into the blood is generally not allowed, which leads to certain difficulties in measuring the velocity of medium and low-speed blood flow.

[0004] Therefore, in view of the above technical problems, it is necessary to provide a method and device for measuring microcirculation blood flow velocity, an electronic device and a storage medium.

[0005] The information disclosed in this background technology section is only intended to increase the understanding of the overall background of the application and should not be regarded as an admission or any form of suggestion that the information constitutes the prior art already known to a person skilled in the art. Summary of the invention

[0006] The purpose of the present invention is to provide a microcirculation blood flow velocity measurement method, device, electronic device and storage medium, which can solve the above-mentioned problem that it is difficult to measure medium and low speed blood flow velocity because tracer particles are not allowed to be introduced during blood flow velocity detection.

[0007] In order to achieve the above object, a specific embodiment of the present invention provides a method for measuring microcirculatory blood flow velocity, and the technical solution is as follows:

[0008] A method for measuring microcirculatory blood flow velocity comprises the following steps:

[0009] Acquire a blood flow video of a target blood vessel, wherein the blood flow video includes multiple frames of blood vessel images;

[0010] Selecting a reference blood vessel image from the multiple frames of blood vessel images, and extracting a blood vessel direction reference line of the reference blood vessel image;

[0011] Determining a reference template image sequence in the reference blood vessel image along the blood vessel direction reference line, wherein the reference template image sequence includes a plurality of reference template images, and the reference template image is an image of a blood vessel region in the reference blood vessel image;

[0012] Determining, in the blood vessel images of the frames adjacent to the reference blood vessel image, an image sequence corresponding to the reference template image sequence;

[0013] Based on the positions of the reference template image sequence and the image sequence corresponding thereto, the inter-frame blood flow velocity is calculated.

[0014] In one or more embodiments of the present invention, extracting the blood vessel direction reference line of the reference blood vessel image specifically includes:

[0015] Binarizing the reference blood vessel image to obtain foreground pixels, wherein the foreground pixels belong to a blood vessel region image;

[0016] Traversing the foreground pixels based on a preset image refinement rule to determine whether to delete the corresponding foreground pixels, and updating the reference blood vessel image;

[0017] The above image thinning steps are repeated until there are no foreground pixels that can be deleted in the reference blood vessel image, so as to obtain the center line of the reference blood vessel image.

[0018] In one or more embodiments of the present invention, extracting the blood vessel direction reference line of the reference blood vessel image specifically includes:

[0019] A middle line segment of a preset proportion is intercepted from the center line of the reference blood vessel image and determined as the blood vessel direction reference line.

[0020] In one or more embodiments of the present invention, determining a reference template image sequence in the reference blood vessel image along the blood vessel direction reference line specifically includes:

[0021] Determining a plurality of reference points at intervals on the blood vessel running reference line;

[0022] An image of a blood vessel region within a preset range is determined as a reference template image with the multiple reference points as the center.

[0023] In one or more embodiments of the present invention, the method specifically includes:

[0024] Based on the width of the blood vessel in the reference blood vessel image, a preset range of the reference template image is determined.

[0025] In one or more embodiments of the present invention, determining, in a blood vessel image of a frame adjacent to the reference blood vessel image, an image sequence corresponding to the reference template image sequence specifically includes:

[0026] In a blood vessel image of a frame adjacent to the reference blood vessel image, determining a template image search space corresponding to the reference template image, wherein the template image search space does not include background pixels in a non-blood vessel area;

[0027] In the template image search space, determining a template image corresponding to the reference template image;

[0028] and / or,

[0029] In the blood vessel images of the frames adjacent to the reference blood vessel image, determining a plurality of candidate template images corresponding to the reference template image;

[0030] Based on the normalized square difference between the reference template image and a plurality of candidate template images, a template image corresponding to the reference template image is determined from the plurality of candidate template images.

[0031] In one or more embodiments of the present invention, calculating the inter-frame blood flow velocity based on the position of the reference template image sequence and the image sequence corresponding thereto specifically includes:

[0032] The inter-frame blood flow velocity is calculated based on the average offset distance of the corresponding template images in the reference template image sequence and the image sequence corresponding thereto.

[0033] A specific embodiment of the present invention further provides a device for measuring microcirculatory blood flow velocity, and the technical solution is as follows:

[0034] A device for measuring microcirculatory blood flow velocity, comprising:

[0035] An acquisition module, used for acquiring a blood flow video of a target blood vessel, wherein the blood flow video includes multiple frames of blood vessel images;

[0036] An extraction module, used for selecting a reference blood vessel image from the multiple frames of blood vessel images, and extracting a blood vessel direction reference line of the reference blood vessel image;

[0037] A first determination module is used to determine a reference template image sequence in the reference blood vessel image along the blood vessel direction reference line, wherein the reference template image sequence includes a plurality of reference template images, and the reference template image is an image of a blood vessel region in the reference blood vessel image;

[0038] A second determination module is used to determine an image sequence corresponding to the reference template image sequence in the blood vessel images of the frames adjacent to the reference blood vessel image;

[0039] The calculation module is used to calculate the inter-frame blood flow velocity based on the position of the reference template image sequence and the image sequence corresponding thereto.

[0040] A specific embodiment of the present invention further provides an electronic device, and the technical solution is as follows:

[0041] An electronic device, comprising:

[0042] at least one processor; and

[0043] A memory storing instructions, which, when executed by the at least one processor, enables the at least one processor to execute the microcirculation blood flow velocity measurement method as described above.

[0044] A specific embodiment of the present invention further provides a machine-readable storage medium, and the technical solution is as follows:

[0045] A machine-readable storage medium stores executable instructions, which, when executed, enable the machine to perform the microcirculation blood flow velocity measurement method as described above.

[0046] Compared with the prior art, the microcirculation blood flow velocity measurement method of the present invention selects a reference blood vessel image through the blood flow video of the target blood vessel, and determines a reference template image sequence in the reference blood vessel image along the reference line of the blood vessel direction, and then determines an image sequence corresponding to the reference template image sequence in the blood vessel image of the adjacent frame to the reference blood vessel image, and finally calculates and obtains the inter-frame blood flow velocity based on the position of the reference template image sequence and the image sequence corresponding thereto to evaluate the microcirculation status. Among them, the above-mentioned microcirculation blood flow velocity measurement method does not need to introduce tracer particles, thereby improving the convenience of operation. At the same time, calculation based on the template image sequence can reduce noise interference, thereby improving the accuracy of the velocity measurement of medium and low-speed blood flow. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0048] Figure 1 This is a schematic diagram of an application scenario of a method for measuring microcirculation blood flow velocity in an embodiment of the present invention;

[0049] Figure 2 This is a flow chart of a method for measuring microcirculatory blood flow velocity in one embodiment of the present invention;

[0050] Figure 3 A reference blood vessel image in a microcirculation blood flow velocity measurement method in an embodiment of the present invention;

[0051] Figure 4 A reference blood vessel image after binarization processing in a microcirculation blood flow velocity measurement method in an embodiment of the present invention;

[0052] Figure 5 Schematic diagram of the positions of pixels P1-P9 in a method for measuring microcirculation blood flow velocity in one embodiment of the present invention.

[0053] Figure 6 A schematic diagram of a blood vessel direction reference line referring to a blood vessel image in a method for measuring microcirculation blood flow velocity in one embodiment of the present invention;

[0054] Figure 7 A schematic diagram of reference points on a blood vessel direction reference line of a reference blood vessel image in a method for measuring microcirculatory blood flow velocity in one embodiment of the present invention;

[0055] Figure 8 A schematic diagram of the positions of a reference template image sequence and a corresponding image sequence in two adjacent frames in a method for measuring microcirculatory blood flow velocity in one embodiment of the present invention;

[0056] Fig. 9 This is an experimental data diagram between the video image frame number and the blood flow velocity obtained according to the microcirculation blood flow velocity measurement method in one embodiment of the present invention;

[0057] Fig.10 This is a module diagram of a device for measuring microcirculatory blood flow velocity in one embodiment of the present invention;

[0058] Fig.11 FIG. 4 is a hardware structure diagram of an electronic device in one embodiment of the present invention.

[0059] Description of main reference numerals:

[0060] 21. Acquisition module; 22. Extraction module; 23. First determination module; 24. Second determination module; 25. Calculation module; 31. Processor; 32. Storage; 33. Memory; 34. Communication interface; 35. Internal bus. DETAILED DESCRIPTION

[0061] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0062] Blood flow velocity measurement technology has evolved from contact measurement to non-invasive measurement, and its development is driven by the demand for medical diagnosis. Modern blood flow velocity measurement technology provides an important auxiliary tool for the medical field with its fast, reliable and non-invasive characteristics. Modern blood flow velocity measurement technology includes two categories: based on Doppler frequency shift technology and based on digital image analysis technology.

[0063] Doppler frequency shift technology is based on the Doppler effect and quantifies blood flow velocity by analyzing the frequency shift. For example, laser Doppler blood flow measurement technology, ultrasonic Doppler technology, etc. Laser Doppler blood flow measurement technology uses the Doppler frequency shift caused by the scattering of laser light by red blood cells in the blood to measure blood flow velocity. Similarly, ultrasonic Doppler technology also follows a similar principle, evaluating blood flow velocity by detecting the frequency change of ultrasonic signals reflected by moving red blood cells. The above-mentioned velocity measurement method performs well in high-speed blood flow measurement such as the heart and major blood vessels, but its accuracy is average when dealing with low-speed blood flow in microcirculation. In the case of medium and low-speed blood flow, the Doppler spectrum is easily interfered by clutter, resulting in a decrease in the signal-to-noise ratio, making the measurement results inaccurate.

[0064] Blood flow images are mainly obtained through different imaging techniques based on digital image analysis. For example, particle image velocimetry and particle tracking velocimetry require the introduction of tracer particles into the blood flow field, and then use image processing and computer vision technology to track particle movement and infer blood flow velocity. However, it is generally not allowed to introduce tracer particles into the blood, which makes it difficult to measure medium and low blood flow velocities.

[0065] Reference Figure 1 In an implementation environment scenario example, the server and the terminal are connected via a network, and the user can upload the blood flow video to the server via the terminal. The server measures the blood flow in the blood vessels included in the blood flow video by running the microcirculation blood flow velocity measurement method provided in the embodiment of the present application.

[0066] Alternatively, in other implementation scenarios, the microcirculation blood flow velocity measurement method provided in this embodiment can also be run by the server and the terminal together. For example, after receiving the blood flow video of the target blood vessel input by the user, the terminal first selects a reference blood vessel image from the multiple frames of blood vessel images therein, and extracts the corresponding blood vessel direction reference line; the server can further obtain the processing results of the above terminal, and determine the reference image sequence in the blood vessel reference image along the blood vessel direction reference line, and then determine the image sequence corresponding to the reference template image sequence in the blood vessel image of the adjacent frame to the reference blood vessel image, and calculate the inter-frame blood flow velocity based on the position of the reference template image sequence and the image sequence corresponding thereto.

[0067] In the above implementation environment, data communication is performed between the terminal and the server through a communication network. Optionally, the communication network can be a wired network or a wireless network, and the communication network can be at least one of a local area network, a metropolitan area network, and a wide area network. The server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and big data and artificial intelligence platforms. The server and terminal devices can be independent devices or integrated into the same system, which is not limited here.

[0068] Based on the above description of the microcirculation blood flow velocity measurement process, it can be seen that the microcirculation blood flow velocity measurement method proposed in the embodiment of the present application can be executed by any suitable computer device (terminal or server); or, the microcirculation blood flow velocity measurement can be performed by the terminal and the server together. For the convenience of explanation, the following description is taken as an example of a computer device executing the microcirculation blood flow velocity measurement method.

[0069] Reference Figure 2 The microcirculation blood flow velocity measurement method in one embodiment of the present invention can be effectively applied to the measurement of medium and low speed blood flow, and the method comprises the following steps:

[0070] S1. Obtain the blood flow video of the target blood vessel.

[0071] Mate Reference Figure 3 The blood flow video can be obtained by a variety of common blood flow imaging technologies, such as laser Doppler imaging, laser speckle contrast analysis, etc., which are not limited in this application. The blood flow video obtained by the computer device usually includes multiple frames such as Figure 3 In this embodiment, the blood flow video of the target blood vessel can be segmented from the original blood flow video into blood vessel images with a set number of frames as the image basis for calculating the blood flow velocity between frames.

[0072] S2. Select a reference blood vessel image from multiple frames of blood vessel images, and extract a blood vessel direction reference line of the reference blood vessel image.

[0073] The reference blood vessel image may be any frame in the multiple blood vessel images. For example, the first frame in the multiple blood vessel images may be selected as the reference blood vessel image, and then the change in blood flow velocity in the blood vessel starting from the initial frame is calculated. The blood vessel direction reference line is used to characterize the approximate direction of the blood vessel in the reference blood vessel image. For example, the center line of the reference blood vessel image may be obtained as the blood vessel direction reference line, or the blood vessel wall direction line of the reference blood vessel image may be obtained as the blood vessel direction reference line.

[0074] Mate Reference Figure 3 and Figure 4 In this embodiment, taking the center line of the reference blood vessel image of the blood vessel as the reference line of the blood vessel direction as an example, the reference blood vessel image can be firstly binarized to obtain foreground pixels. The foreground pixels belong to the blood vessel region image, and the corresponding background pixels belong to the remaining region images except the blood vessel region in the reference blood vessel image, and the values ​​of the foreground pixels are marked as 1, and the values ​​of the background pixels are marked as 0.

[0075] Specifically, the reference blood vessel image can be binarized using a threshold method to obtain Figure 4 The mask image of the reference blood vessel image is shown, and the mask image is the blood vessel area image.

[0076] Then, the foreground pixels are traversed based on the preset image refinement rule to determine whether to delete the corresponding foreground pixels, and the reference blood vessel image is updated.

[0077] With reference Figure 5 In this embodiment, the preset image thinning rule can select the Zhang-Suen thinning algorithm to perform skeleton thinning processing on the blood vessel region image.

[0078] The Zhang-Suen refinement algorithm is usually an iterative algorithm. The entire iterative process is divided into two steps:

[0079] Step 1: Loop through all foreground pixels and mark foreground pixels that meet the following conditions as deleted (taking the current foreground pixel P1 as an example):

[0080] 1. 2<=N(p1)<=6

[0081] 2. S(P1)=1

[0082] 3. P2*P4*P6=0

[0083] 4. P4*P6*P8=0

[0084] Where N(p1) represents the number of foreground pixels among the 8 pixels adjacent to P1. Figure 5 A schematic diagram showing the positions of pixels P1-P9 is shown.

[0085] S(P1) represents the cumulative number of times 0 to 1 appear in pixels P2 to P9 to P2, where 0 represents a background pixel and 1 represents a foreground pixel.

[0086] Step 2: Conditions 1 and 2 are exactly the same as those in step 1, but conditions 3 and 4 are slightly different. Pixels P1 that meet the following conditions are deleted. The conditions are as follows:

[0087] 1. 2<=N(p1)<=6

[0088] 2. S(P1)=1

[0089] 3. P2*P4*P8=0

[0090] 4. P2*P6*P8=0

[0091] The above two steps constitute a round of image thinning, that is, a certain number of pixels are deleted from the vascular area image. Subsequently, the above image thinning steps are repeated until there are no foreground pixels that can be deleted in the reference vascular image to obtain the center line of the reference vascular image.

[0092] Reference Figure 6 In this embodiment, after obtaining the center line of the reference blood vessel image, a preset proportion of the middle line segment portion can be intercepted from the center line of the reference blood vessel image to determine it as the blood vessel direction reference line. For example, the center line of the reference blood vessel image can be divided into a number of odd-numbered segments, and the middle line segment portion can be intercepted to determine it as the blood vessel direction reference line. For example, the blood vessel center line can be divided into three equal parts, and the middle line segment can be intercepted as the blood vessel direction reference line. Alternatively, a line segment in a certain area in the middle can be directly intercepted to determine it as the blood vessel direction reference line.

[0093] S3. Determine a reference template image sequence in the reference blood vessel image along the blood vessel reference line.

[0094] The reference template image sequence includes a plurality of reference template images, and the reference template image is an image of a blood vessel region in a reference blood vessel image. Figure 7 and Figure 8 In this embodiment, a plurality of reference points at intervals may be determined on the blood vessel direction reference line, and an image of a blood vessel region within a preset range may be determined as a reference template image with the plurality of reference points as the center.

[0095] For example, the parameter I can be set to determine the number of pixel intervals between reference points. Based on all pixel sequences of the blood vessel direction reference line, a reference point is set every I pixel interval, and a reference template is arranged at the reference point. The blood vessel region image corresponding to the reference template is the reference template image. It can be understood that by adjusting the I value, the density of the reference template can be adjusted, thereby balancing the computational efficiency and the precision of data analysis.

[0096] For another example, the number of reference templates to be arranged may be determined first, and then the blood vessel direction reference line may be evenly divided based on the number of reference templates, and then the endpoint of each blood vessel direction reference line may be set as a reference point to arrange the reference template at the reference point.

[0097] In this embodiment, the shape of the reference template can be set as a rectangular reference template, which is not a limitation on the shape of the reference template image in the present invention. In other embodiments, the shape of the reference template can be a circle, a diamond or other suitable shapes. Among them, the preset range of the reference template image is determined by the length and width of the rectangular reference template. It can be understood that the reasonable setting of the size of the preset range can ensure that the reference template image sequence can cover sufficient blood flow information without being too large to cause information redundancy. In addition, for the reference template image sequence, multiple reference template images may or may not overlap, and this application does not impose any limitation on this.

[0098] The size of the preset range can be adjusted based on a variety of factors. For example, the preset range of the reference template image can be determined based on the width of the blood vessels in the reference blood vessel image. Taking the above rectangular reference template as an example, the length and width of the rectangular reference template should be smaller than the width of the blood vessels in the reference blood vessel image, so as to facilitate subsequent tracking and matching of appropriate image information.

[0099] Compared with obtaining the reference template image sequence in the vascular wall area, determining the reference template image sequence along the vascular direction reference line can obtain more vascular area image information and be more representative, and can also reduce the adverse effects of vascular wall uncertainty factors on the accuracy of microcirculation blood flow velocity measurement.

[0100] Furthermore, in this embodiment, multiple frames of blood vessel images may be aligned in advance to obtain Figure 3 The shape of the target blood vessel shown. Since the blood flow in the target blood vessel is in a flowing state, the peripheral wall of the blood vessel may be deformed to a certain extent, so that the shape of the target blood vessel in each frame of the blood vessel image may vary slightly. By aligning multiple frames of blood vessel images, a representative shape of the target blood vessel can be obtained. Therefore, after aligning multiple frames of blood vessel images, the blood vessel direction reference line obtained based on any frame can represent the blood vessel direction reference line in other frames, that is, the reference template image sequence arranged based on the blood vessel direction reference line of any frame can also be used for any other frame, and there is no need to repeat the steps of obtaining the blood vessel direction reference line and determining the reference template image sequence along the blood vessel direction reference line, thereby reducing the subsequent repeated operation steps and improving the calculation efficiency.

[0101] S4. Determine, in the blood vessel images of the frames adjacent to the reference blood vessel image, an image sequence corresponding to the reference template image sequence.

[0102] In this embodiment, the image sequence corresponding to the reference template image sequence can be determined by template matching technology, wherein template matching is a technology for finding the area most similar to the template image in a larger image. Determining the image sequence corresponding to the reference template image sequence by template matching technology is more objective and time-saving.

[0103] Reference Figure 8 Specifically, a plurality of candidate template images corresponding to the reference template image can be first determined in the vascular images of the frames adjacent to the reference vascular image; and a template image corresponding to the reference template image can be determined from the plurality of candidate template images based on the normalized square difference between the reference template image and the plurality of candidate template images.

[0104] Among them, the normalized square difference method determines the best matching position by calculating the normalized square difference D(x, y) between the sub-region R at each possible position in the template image T and the target image I. The normalization process effectively eliminates the influence of different brightness and contrast, and improves the robustness and accuracy of the matching. The underlying principle of the normalized square difference is as follows:

[0105] Assume the size of the template image T is (w T ,h T ), the size of the target image I is (w I ,h I ). For each possible starting point (x, y) in the target image, the size of its corresponding sub-region R(x, y) is also (w T ,h T ).

[0106] The formula for the normalized square difference D(x, y) is as follows:

[0107]

[0108] Among them, T(i, j) represents the pixel value of the template image at the position (i, j); R(x+i, y+j) represents the pixel value of the target image at the position (x+i, y+j).

[0109] The numerator is the sum of the squared differences of the pixel-by-pixel values ​​between the template and the sub-region. The denominator is the normalization of the template and the sub-region to ensure that the calculation result is not affected by the overall brightness and contrast.

[0110] The value range of the normalized squared difference D(x, y) is usually between [0, 1], where 0 indicates a perfect match (i.e., the template and the sub-region are exactly the same), and 1 indicates a complete mismatch. In practical applications, due to numerical precision issues, D(x, y) may slightly exceed this range, but is usually very close.

[0111] In order to further optimize the calculation speed and improve the calculation efficiency, the present embodiment further includes the following steps:

[0112] In a vascular image of a frame adjacent to a reference vascular image, a template image search space corresponding to a reference template image is determined, wherein the template image search space does not include background pixels in a non-vascular area; in the template image search space, a template image corresponding to the reference template image is determined.

[0113] In the above steps, by limiting the search space, background pixels that do not include the blood vessel area can be automatically filtered out during the search process to avoid unnecessary calculations in the background area, thereby speeding up the processing speed. Specifically, the binary blood vessel image can be used to determine the search space. For example, for blood vessel images of adjacent frames, if the image corresponding to a certain position of the reference template includes background pixels (value 0), the reference template at this position can be automatically filtered. Conversely, if the image corresponding to a certain position of the reference template includes only foreground pixels (value 1), it can be considered that the reference template at this position can be used as part of the search space.

[0114] S5. Calculate the inter-frame blood flow velocity based on the positions of the reference template image sequence and the image sequence corresponding thereto.

[0115] In this embodiment, the inter-frame blood flow velocity may be calculated based on the average offset distance of the corresponding template images in the reference template image sequence and the image sequence corresponding thereto.

[0116] The following is an exemplary description of the calculation of blood flow velocity between frames:

[0117] Assume that the image at the current time t is I t , whose reference template image sequence is n represents the number of template images. These reference template images are sequentially compared with the image I of the next frame t+1. t+1 Perform template matching to find each reference template image in I t+1 The best matching position in Represents the corresponding image sequence matched.

[0118] According to the current frame reference template image sequence The position of the next frame image is tracked to the corresponding image sequence Compare and calculate the offset distance sequence In order to obtain a more stable blood flow velocity, the average offset distance of n template images is Represents the average blood flow velocity at the current moment.

[0119] Furthermore, by calculating the blood flow velocity between two adjacent frames in the blood flow video of the target blood vessel with a set number of frames, the following can be obtained: Fig. 9A dynamic change chart of the microcirculation blood flow velocity in the blood flow video of the target blood vessel is shown, so as to facilitate the subsequent analysis of the microcirculation status through the image.

[0120] This embodiment of Fig. 9 It can not only characterize the blood flow velocity between every two reference images, but also provide blood flow information in the x-axis direction. Figure 8 , of this embodiment Fig. 9 In the equation, negative values ​​indicate that the blood flow tends to flow to the left of the x-axis, and positive values ​​indicate that the blood flow tends to flow to the right of the x-axis. It should be noted that the positive and negative values ​​only represent the blood flow information in the x-axis direction, and do not represent the actual flow direction of the blood flow. The actual flow direction of the blood flow in the blood vessel can be accurately described by the vector (x, y).

[0121] from Fig. 9 It can be concluded that the value of blood flow velocity fluctuates between positive and negative values, which indicates that the blood flow direction in the target vessel is usually not a one-way flow, but a back-and-forth flow along the direction of the reference vessel toward the reference line. Therefore, by analyzing the position information of the reference template image sequence and the matching corresponding image sequence, the flow direction information of the blood flow in the target vessel can also be obtained.

[0122] The microcirculation blood flow velocity measurement method of the present invention does not need to introduce tracer particles, thereby improving the convenience of operation. In addition, for dynamic blood flow images, the fluid has unstable conditions such as turbulence. If the blood flow velocity obtained by template matching based on a template is large, there may be a large error. The present invention can reduce noise interference by determining multiple reference template images for each frame and performing averaging processing based on the template image sequence. Compared with the use of Doppler technology, it can improve the accuracy of velocity measurement of medium and low-speed blood flow and the accuracy of blood flow motion tracking.

[0123] Reference Fig.10 In one embodiment of the present invention, a microcirculation blood flow velocity measuring device is also provided. In this embodiment, the microcirculation blood flow velocity measuring device includes an acquisition module 21, an extraction module 22, a first determination module 23, a second determination module 24 and a calculation module 25.

[0124] Reference Fig.10The acquisition module 21 is used to acquire the blood flow video of the target blood vessel, wherein the blood flow video includes multiple frames of blood vessel images; the extraction module 22 is used to select a reference blood vessel image from the multiple frames of blood vessel images, and extract the blood vessel direction reference line of the reference blood vessel image; the first determination module 23 is used to determine a reference template image sequence in the reference blood vessel image along the blood vessel direction reference line, wherein the reference template image sequence includes multiple reference template images, and the reference template image is an image of the blood vessel area in the reference blood vessel image; the second determination module 24 is used to determine an image sequence corresponding to the reference template image sequence in the blood vessel image of the frame adjacent to the reference blood vessel image; the calculation module 25 is used to calculate the inter-frame blood flow velocity based on the position of the reference template image sequence and the image sequence corresponding thereto.

[0125] In one embodiment, the extraction module 22 is specifically used to perform binarization processing on the reference blood vessel image to obtain foreground pixels, wherein the foreground pixels belong to the blood vessel region image; traverse the foreground pixels based on a preset image refinement rule to determine whether to delete the corresponding foreground pixels, and update the reference blood vessel image; repeat the above image refinement steps until there are no foreground pixels that can be deleted in the reference blood vessel image, so as to obtain the center line of the reference blood vessel image.

[0126] In one embodiment, the extraction module 22 is further configured to intercept a preset proportion of an intermediate line segment portion in the center line of the reference blood vessel image and determine it as the blood vessel direction reference line.

[0127] In one embodiment, the first determination module 23 is specifically used to determine a plurality of reference points at intervals on the blood vessel direction reference line; and to determine an image of a blood vessel region within a preset range as a reference template image, with the plurality of reference points as the center.

[0128] In one embodiment, the preset range of the reference template image is determined based on the width of the blood vessel in the reference blood vessel image.

[0129] In one embodiment, the second determination module 24 is specifically used to determine a template image search space corresponding to a reference template image in a vascular image of a frame adjacent to a reference vascular image, wherein the template image search space does not include background pixels in a non-vascular area; and determine a template image corresponding to the reference template image in the template image search space.

[0130] In one embodiment, the second determination module 24 is further configured to determine a plurality of candidate template images corresponding to the reference template image in the blood vessel images of the frames adjacent to the reference blood vessel image;

[0131] Based on the normalized square difference between the reference template image and the plurality of candidate template images, a template image corresponding to the reference template image is determined from the plurality of candidate template images.

[0132] In one embodiment, the calculation module 25 calculates the inter-frame blood flow velocity based on the reference template image sequence and the average offset distance of the corresponding template image in the image sequence corresponding to the reference template image sequence.

[0133] As above Figures 1 to 9 , a method for measuring microcirculation blood flow velocity according to an embodiment of this specification is described. The details mentioned in the above description of the method embodiment are also applicable to the microcirculation blood flow velocity measuring device of the embodiment of this specification. The above microcirculation blood flow velocity measuring device can be implemented by hardware, or by software, or by a combination of hardware and software.

[0134] Reference Fig.11 In one embodiment of the present invention, an electronic device is also provided. The electronic device may include at least one processor 31, a memory 32 (e.g., a non-volatile memory 32), a memory 33, and a communication interface 34, and the at least one processor 31, the memory 32, the memory 33, and the communication interface 34 are connected together via a bus. At least one processor 31 executes at least one computer-readable instruction stored or encoded in the memory 32.

[0135] It should be understood that the computer executable instructions stored in the memory 32, when executed, cause at least one processor 31 to perform the above combined operations in various embodiments of the present specification. Figures 1 to 9 Describes the various operations and functions.

[0136] In the embodiments of the present specification, electronic devices may include, but are not limited to: personal computers, server computers, workstations, desktop computers, laptop computers, notebook computers, mobile electronic devices, smart phones, tablet computers, cellular phones, personal digital assistants (PDAs), handheld devices, messaging devices, wearable electronic devices, consumer electronic devices, and the like.

[0137] In one embodiment of the present invention, a program product such as a machine-readable medium is also provided. The machine-readable medium may have instructions (i.e., the above-mentioned elements implemented in the form of software), which, when executed by a machine, causes the machine to execute the above-mentioned combination of various embodiments of this specification. Figures 1 to 9 Specifically, a system or device equipped with a readable storage medium may be provided, on which a software program code implementing the functions of any of the above-mentioned embodiments is stored, and a computer or processor of the system or device reads and executes the instructions stored in the readable storage medium.

[0138] In this case, the program code itself read from the machine-readable medium can realize the function of any one of the above embodiments, and thus the machine-readable code and the machine-readable storage medium storing the machine-readable code constitute part of this specification.

[0139] Examples of readable storage media include floppy disks, hard disks, magneto-optical disks, optical disks (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD-RW), magnetic tapes, non-volatile memory cards, and ROMs. Alternatively, the program code may be downloaded from a server computer or a cloud via a communication network.

[0140] Those skilled in the art should understand that the various embodiments disclosed above can be modified and altered in various ways without departing from the essence of the invention. Therefore, the protection scope of this specification should be defined by the appended claims.

[0141] It should be noted that not all steps and units in the above-mentioned processes and system structure diagrams are necessary, and some steps or units can be ignored according to actual needs. The execution order of each step is not fixed and can be determined as needed. The device structure described in the above-mentioned embodiments can be a physical structure or a logical structure, that is, some units may be implemented by the same physical client, or some units may be implemented by multiple physical clients, or some components in multiple independent devices may be implemented together.

[0142] In the above embodiments, the hardware unit or module can be realized by mechanical or electrical means. For example, a hardware unit, module or processor can include permanent dedicated circuit or logic (such as special processor, FPGA or ASIC) to complete the corresponding operation. The hardware unit or processor can also include programmable logic or circuit (such as general-purpose processor or other programmable processor), which can be temporarily set by software to complete the corresponding operation. Specific implementation (mechanical method or dedicated permanent circuit or temporary circuit) can be determined based on cost and time consideration.

[0143] The specific embodiments described above in conjunction with the accompanying drawings describe exemplary embodiments, but do not represent all embodiments that can be implemented or fall within the scope of protection of the claims. The term "exemplary" used throughout this specification means "used as an example, instance or illustration" and does not mean "preferred" or "having advantages" over other embodiments. For the purpose of providing an understanding of the described technology, the specific embodiments include specific details. However, these technologies can be implemented without these specific details. In some instances, in order to avoid making the concepts of the described embodiments difficult to understand, well-known structures and devices are shown in block diagram form.

[0144] The above description of the present disclosure is provided to enable any person of ordinary skill in the art to implement or use the present disclosure. Various modifications to the present disclosure will be apparent to those of ordinary skill in the art, and the general principles corresponding to the present disclosure may be applied to other variations without departing from the scope of protection of the present disclosure. Therefore, the present disclosure is not limited to the examples and designs described herein, but is consistent with the widest range of principles and novel features disclosed herein.

Claims

1. A method for measuring microcirculatory blood flow velocity, characterized in that: The following steps are involved: Acquire a blood flow video of a target blood vessel, wherein the blood flow video includes multiple frames of blood vessel images; Selecting a reference blood vessel image from the multiple frames of blood vessel images, and extracting a blood vessel direction reference line of the reference blood vessel image; Determining a reference template image sequence in the reference blood vessel image along the blood vessel direction reference line, wherein the reference template image sequence includes a plurality of reference template images, and the reference template image is an image of a blood vessel region in the reference blood vessel image; Determining, in the blood vessel images of the frames adjacent to the reference blood vessel image, an image sequence corresponding to the reference template image sequence; Based on the positions of the reference template image sequence and the image sequence corresponding thereto, the inter-frame blood flow velocity is calculated.

2. The microcirculation blood flow velocity measurement method according to claim 1, characterized in that: Extracting the blood vessel direction reference line of the reference blood vessel image specifically includes: Binarizing the reference blood vessel image to obtain foreground pixels, wherein the foreground pixels belong to a blood vessel region image; Traversing the foreground pixels based on a preset image refinement rule to determine whether to delete the corresponding foreground pixels, and updating the reference blood vessel image; The above image thinning steps are repeated until there are no foreground pixels that can be deleted in the reference blood vessel image, so as to obtain the center line of the reference blood vessel image.

3. The microcirculation blood flow velocity measurement method according to claim 2, characterized in that: Extracting the blood vessel direction reference line of the reference blood vessel image specifically includes: A middle line segment of a preset proportion is intercepted from the center line of the reference blood vessel image and determined as the blood vessel direction reference line.

4. The microcirculation blood flow velocity measurement method according to claim 1, characterized in that: Determining a reference template image sequence in the reference blood vessel image along the blood vessel direction reference line specifically includes: Determining a plurality of reference points at intervals on the blood vessel running reference line; An image of a blood vessel region within a preset range is determined as a reference template image with the multiple reference points as the center.

5. The microcirculation blood flow velocity measurement method according to claim 4, characterized in that: The method specifically comprises: Based on the width of the blood vessel in the reference blood vessel image, a preset range of the reference template image is determined.

6. The microcirculation blood flow velocity measurement method according to claim 1, characterized in that: Determining, in a blood vessel image of a frame adjacent to the reference blood vessel image, an image sequence corresponding to the reference template image sequence, specifically includes: In a blood vessel image of a frame adjacent to the reference blood vessel image, determining a template image search space corresponding to the reference template image, wherein the template image search space does not include background pixels in a non-blood vessel area; In the template image search space, determining a template image corresponding to the reference template image; and / or, In the blood vessel images of the frames adjacent to the reference blood vessel image, determining a plurality of candidate template images corresponding to the reference template image; Based on the normalized square difference between the reference template image and a plurality of candidate template images, a template image corresponding to the reference template image is determined from the plurality of candidate template images.

7. The microcirculation blood flow velocity measurement method according to claim 1, characterized in that: Calculating the inter-frame blood flow velocity based on the reference template image sequence and the position of the image sequence corresponding thereto, specifically comprising: The inter-frame blood flow velocity is calculated based on the average offset distance of the corresponding template images in the reference template image sequence and the image sequence corresponding thereto.

8. A device for measuring microcirculatory blood flow velocity, characterized in that: include: An acquisition module, used for acquiring a blood flow video of a target blood vessel, wherein the blood flow video includes multiple frames of blood vessel images; An extraction module, used for selecting a reference blood vessel image from the multiple frames of blood vessel images, and extracting a blood vessel direction reference line of the reference blood vessel image; A first determination module is used to determine a reference template image sequence in the reference blood vessel image along the blood vessel direction reference line, wherein the reference template image sequence includes a plurality of reference template images, and the reference template image is an image of a blood vessel region in the reference blood vessel image; A second determination module is used to determine an image sequence corresponding to the reference template image sequence in the blood vessel images of the frames adjacent to the reference blood vessel image; The calculation module is used to calculate the inter-frame blood flow velocity based on the position of the reference template image sequence and the image sequence corresponding thereto.

9. An electronic device, characterized in that: include: at least one processor; as well as A memory storing instructions, wherein when the instructions are executed by the at least one processor, the at least one processor executes the microcirculation blood flow velocity measurement method according to any one of claims 1 to 7.

10. A machine-readable storage medium, characterized in that: It stores executable instructions, which, when executed, enable the machine to perform the microcirculation blood flow velocity measurement method as described in any one of claims 1 to 7.

Images