Method, device and equipment for monitoring blood flow velocity of animal microcirculation

Abstract

The invention relates to the technical field of biomedical monitoring, in particular to a blood flow velocity monitoring method, device and equipment for animal microcirculation, and the method comprises the following steps: acquiring a video of an animal microcirculation area; preprocessing the video to obtain a preprocessed video; determining a tracking point based on the preprocessed video; a microcirculation tracker is adopted to track the tracking points, the motion trails of the tracking points are determined, and the microcirculation tracker is obtained through training; calculating the blood flow velocity based on the motion trail; displaying the blood flow velocity; by means of the deep learning video pixel tracking technology, the accuracy and reliability of blood flow velocity monitoring are remarkably improved, and powerful technical support is provided for biomedical research.

Description

Technical Field

[0001] The present invention relates to the field of biomedical monitoring technology, and in particular to a method, device and equipment for monitoring blood flow velocity of animal microcirculation. Background Art

[0002] In modern medical research, the study of blood flow in microcirculation is crucial to understanding physiological and pathological processes. Microcirculation refers to the blood circulation in the smallest vascular network between tissue cells, which is directly involved in the exchange of nutrients, oxygen and metabolic waste. Therefore, accurately measuring the blood flow velocity in microcirculation is not only helpful for diagnosing various diseases (such as cardiovascular disease, diabetes, etc.), but also has important significance for developing new treatment methods.

[0003] A traditional method for measuring blood flow velocity is to use a Doppler analyzer, which is very expensive and difficult to operate.

[0004] Another method is visual analysis, which mainly includes spatial correlation method, optical flow method and method based on spatiotemporal graph.

[0005] The spatial correlation method calculates the displacement distance of the regional window in the video sequence based on the maximum correlation coefficient, and then divides it by the interval time of the video sequence to obtain the result. This method is greatly affected by noise, and the size and shape of the regional window are difficult to determine.

[0006] The optical flow method analyzes the movement of blood cell pixels in the time domain and the correlation between adjacent frames to find the correspondence between the previous frame and the current frame, and then estimates their speed. However, it has high requirements on image quality, high computational complexity and difficulty in handling complex flow fields.

[0007] The blood flow velocity measurement method based on space-time (ST) map maps the movement trajectory of cells into a two-dimensional space-time map, and converts the video-based velocity measurement into the direction measurement of the trajectory in the ST map. However, this method has a large amount of calculation, and in areas with branched or curved blood vessels or uneven blood flow, the stripes on the ST map will become complex and difficult to accurately identify and analyze, resulting in increased velocity measurement errors.

[0008] Existing solutions usually lack sufficient accuracy or cannot adapt well to the needs of specific application scenarios, especially in processing high-resolution video data and achieving fast and reliable blood flow velocity estimation. Summary of the invention

[0009] In view of the above problems, the present invention provides a method, device and equipment for monitoring blood flow velocity of animal microcirculation that overcomes the above problems or at least partially solves the above problems.

[0010] In a first aspect, the present invention provides a method for monitoring blood flow velocity in animal microcirculation, comprising:

[0011] Obtain videos of the animal's microcirculatory regions;

[0012] Preprocessing the video to obtain a preprocessed video;

[0013] Based on the preprocessed video, determining a tracking point;

[0014] Using a microcirculation tracker to track the tracking point and determine the motion trajectory of the tracking point, the microcirculation tracker is obtained through training;

[0015] Based on the motion trajectory, calculating the blood flow velocity;

[0016] The blood flow velocity is displayed.

[0017] Preferably, preprocessing the video to obtain a preprocessed video includes:

[0018] Cropping the video to obtain a cropped video, wherein the cropped video is an unmoved segment;

[0019] Performing shake correction processing on the cropped video to obtain a shake-corrected video;

[0020] Performing noise reduction processing on the shake-corrected video to obtain a noise-reduced video;

[0021] Performing illumination correction processing on the noise reduction video to obtain an illumination corrected video;

[0022] Generating a segmentation mask process on the illumination correction video to obtain a binary image video;

[0023] The video of the binary image is enhanced to obtain a preprocessed video.

[0024] Preferably, determining the tracking point based on the pre-processed video includes:

[0025] Determining a preset coordinate point based on each frame of the preprocessed video;

[0026] Taking the preset coordinate point as the center of the circle, a tracking point is determined within a preset radius, and the tracking point is the pixel coordinate of the center line of the blood vessel closest to the center of the circle.

[0027] Preferably, before the microcirculation tracker is used to track the tracking point and determine the motion trajectory of the tracking point, the microcirculation tracker is trained and then further includes:

[0028] Simulate and construct 3D blood vessels, and create the flow direction and speed of blood cells in the blood vessels to obtain blood cell movement videos;

[0029] A microcirculation tracker is trained based on the blood cell movement video, wherein the blood cell movement video is annotated with position labels of blood cells.

[0030] Preferably, a microcirculation tracker is used to track the tracking point to determine the motion trajectory of the tracking point, including:

[0031] Inputting the preprocessed video into the microcirculation tracker to determine the features of each frame of the image, wherein the tracking points of the first frame of the image are marked in the preprocessed video;

[0032] Based on the features of each frame of image, interpolation points between two adjacent frames of image are determined, and the interpolation points are used as tracking features;

[0033] Based on the tracking feature, determining association information between different frame images;

[0034] Based on the association information, determining coordinate information of the tracking point in each frame of the image;

[0035] Based on the coordinate information of the tracking point in each frame of the image, the motion trajectory of the tracking point is determined.

[0036] Preferably, calculating the blood flow velocity based on the motion trajectory includes:

[0037] Based on the motion trajectory, determining the tracking point coordinates of the tracking point in each frame image;

[0038] Based on the coordinates of the tracking point in each frame of the image, the instantaneous blood flow velocity of the tracking point is obtained according to the following formula:

[0039]

[0040] Among them, v mn is the instantaneous blood flow velocity of the tracking point, z is the frame rate of the preprocessed video, (x i ,y i ) is the coordinate of the tracking point in any frame from the mth frame to the nth frame, (x i+1 ,y i+1 ) are the tracking point coordinates of any frame image in the next frame image.

[0041] Preferably, calculating the blood flow velocity based on the motion trajectory further includes:

[0042] Based on the tracking point, determine a nearby point, wherein the nearby point is determined within a preset distance of the tracking point;

[0043] Get the instantaneous blood flow velocity of nearby points;

[0044] Based on the instantaneous blood flow velocity of the tracking point and the instantaneous blood flow velocity of the nearby points, the average velocity within any L frames in the time and space range is determined, which is specifically obtained according to the following formula:

[0045]

[0046] Where L is the number of any frames in the space-time range, v (m-i)(n-i) and v (m+i)(n+1) are the instantaneous blood flow velocities of nearby points at different locations. is the average speed within any L frames in the space-time range.

[0047] Preferably, calculating the blood flow velocity based on the motion trajectory further includes:

[0048] Based on the instantaneous blood flow velocity of the tracking point, determining the instantaneous blood flow velocity of any two tracking points;

[0049] Determine an interpolation point between any two tracking points to obtain the instantaneous blood flow velocity of the interpolation point;

[0050] Based on the instantaneous blood flow velocities of the two arbitrary tracking points and the instantaneous blood flow velocity of the interpolation point, the average blood flow velocity at the interpolation point is determined, which is implemented according to the following formula:

[0051]

[0052] in, is the instantaneous blood flow velocity at the interpolation point, and is the instantaneous blood flow velocity of any two tracking points, is the average blood flow velocity at the interpolation point.

[0053] In a second aspect, the present invention further provides a blood flow velocity monitoring device for animal microcirculation, comprising:

[0054] An acquisition module, used to acquire a video of the microcirculation area of ​​an animal;

[0055] An obtaining module is used to preprocess the video to obtain a preprocessed video;

[0056] A tracking point determination module, used for determining a tracking point based on the pre-processed video;

[0057] A motion trajectory determination module, used to track the tracking point using a microcirculation tracker to determine the motion trajectory of the tracking point, wherein the microcirculation tracker is obtained through training;

[0058] A calculation module, used for calculating the blood flow velocity based on the motion trajectory;

[0059] A display module is used to display the blood flow velocity.

[0060] In a third aspect, the present invention further provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in the first aspect when executing the program.

[0061] In a fourth aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in the first aspect.

[0062] One or more technical solutions in the embodiments of the present invention have at least the following technical effects or advantages:

[0063] The present invention provides a method for monitoring blood flow velocity of animal microcirculation, comprising: acquiring a video of an animal microcirculation region; preprocessing the video to obtain a preprocessed video; determining a tracking point based on the preprocessed video; tracking the tracking point using a microcirculation tracker to determine a motion trajectory of the tracking point, wherein the microcirculation tracker is obtained through training; calculating the blood flow velocity based on the motion trajectory; and displaying the blood flow velocity. By using deep learning video pixel tracking technology, the accuracy and reliability of blood flow velocity monitoring are significantly improved, thereby providing strong technical support for biomedical research. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Also, throughout the accompanying drawings, the same reference figures are used to represent the same components. In the drawings:

[0065] Figure 1 A schematic diagram showing the steps of a method for monitoring blood flow velocity in animal microcirculation according to an embodiment of the present invention is shown;

[0066] Figure 2 The effect diagram of preprocessing a video in an embodiment of the present invention is shown;

[0067] Figure 3 A schematic diagram showing the structure of a blood flow velocity monitoring device for animal microcirculation in an embodiment of the present invention is shown;

[0068] Figure 4 A schematic diagram of the structure of a computer device for implementing a blood flow velocity monitoring method for animal microcirculation in an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0069] Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.

[0070] Embodiment 1:

[0071] The embodiment of the present invention provides a method for monitoring blood flow velocity in animal microcirculation, such as Figure 1 As shown, including:

[0072] S101, obtain a video of the microcirculatory area of ​​the animal;

[0073] S102, preprocessing the video to obtain a preprocessed video;

[0074] S103, determining a tracking point based on the pre-processed video;

[0075] S104, using a microcirculation tracker to track the tracking point and determine the motion trajectory of the tracking point, the microcirculation tracker is obtained through training;

[0076] S105, calculating the blood flow velocity based on the motion trajectory;

[0077] S106, displaying the blood flow velocity.

[0078] In a specific implementation, S101, obtaining a video of the microcirculation area of ​​the animal, specifically by photographing the microcirculation area of ​​the animal through a collection device.

[0079] By starting the acquisition device, initializing the settings, and configuring appropriate imaging parameters according to experimental requirements, such as exposure time and ISO value. Use the focus adjustment mechanism to automatically find the best focus position to ensure the clarity of the target area. The preview screen under the current settings is imaged on the user interface for researchers to check whether it meets the requirements. After confirming that the preview image meets the expected standards, the formal data collection process is started and video recording begins. The collected videos are stored in the specified location, and a unique identifier is assigned to each video for subsequent management and retrieval.

[0080] The video thus obtained is processed in step S102 to obtain a preprocessed video.

[0081] The preprocessing process specifically includes: video cropping, de-shaking, noise reduction, lighting correction, segmentation mask generation, enhancement, etc.

[0082] First, the video is cropped to obtain a cropped video, which is an unmoved segment. By cropping and matching feature points between frames, it is determined whether the camera moves or the object moves, and the largest unmoved segment is cropped for subsequent processing to ensure that each frame of the image can accurately reflect the changes in the same scene.

[0083] Next, the cropped video is subjected to shake correction processing to obtain a shake-corrected video. Specifically, the image offset is determined by calculating the correlation between each frame in the image sequence and the reference frame, and corresponding correction is performed to eliminate image instability caused by slight camera movement or external factors, ensure continuity and stability between video frames, and thus improve the accuracy of subsequent analysis.

[0084] Then, the shake-corrected video is subjected to noise reduction processing to obtain a noise-reduced video. Specifically, since there is a lot of background noise such as electronic noise and optical noise in the video, it is necessary to use a filter or other noise reduction technology to improve the video quality so that the blood cell movement trajectory is clearer and more visible.

[0085] Next, the noise reduction video is subjected to illumination correction to obtain an illumination-corrected video. Specifically, the correction strength is determined by calculating the mean and variance of the image, thereby automatically adjusting the video brightness and contrast to compensate for image quality fluctuations caused by changes in illumination conditions. This preprocessing operation is crucial to ensure the consistency of videos shot at different time periods or under different environmental conditions.

[0086] Next, the illumination correction video is processed to generate a segmentation mask to obtain a binary image video. Specifically, a binary image is created to distinguish the centerline area of ​​the blood vessel from other background parts through image processing techniques such as edge detection, morphological processing, and skeletonization algorithm.

[0087] Next, the binary image video is enhanced to obtain a preprocessed video. Specifically, the binary image video is sharpened, contrast enhanced, and other operations are performed to further improve the visibility of the microcirculation area, making the cells easier to identify and track.

[0088] Finally, a high-quality video stream is output to prepare for subsequent blood flow velocity measurement. The specific effects are as follows: Figure 2 shown.

[0089] After the preprocessing is performed to obtain the preprocessed video, S103 is executed to determine the tracking point based on the preprocessed video.

[0090] Specifically, based on each frame of the preprocessed video, a preset coordinate point is determined;

[0091] With the preset coordinate point as the center of the circle, a tracking point is determined within a preset radius. The tracking point is the pixel coordinate of the blood vessel centerline closest to the center of the circle.

[0092] First, the vascular area is identified in the preprocessed video by image recognition technology. In the vascular area, a preset coordinate point is manually selected, and the preset coordinate point can clearly display blood cells. The pixel coordinates of the vascular center line closest to the preset coordinate point within a preset radius with the preset coordinate point as the center of the circle are calculated, and the pixel coordinates are used as the tracking points for subsequent tracking.

[0093] After the tracking point is determined, S104 is executed to track the tracking point using a microcirculation tracker to determine the motion trajectory of the tracking point, and the microcirculation tracker is obtained through training.

[0094] First, before S104, the microcirculation tracker needs to be trained. Specifically, a physical simulation framework is used to randomly create 3D blood vessels, create initial blood cells in the blood vessels, and set the initial direction and speed of the blood cells, so as to generate a blood cell motion video with a fixed speed, and annotate the specific position of each frame of the simulated blood cells as a data label in the blood cell motion video. The blood cell motion video is then input into the tracker to train the microcirculation tracker.

[0095] In the process of training the microcirculation tracker, the tracker network model of the simulated blood cell movement video input is used as the teacher tracking network model, and the student tracking network model is trained with the provided real training data, thereby obtaining the microcirculation tracker.

[0096] Among them, when the real training data provided is input into the student tracking network model, the output of the student tracking network model is compared with the marked blood cell position coordinates, and the weights of each neuron in the student tracking network model are updated according to the comparison results. The above training process is repeated until the test results of the student tracking network model using the test set reach the expected accuracy. At this time, the training is stopped to obtain the microcirculation tracker.

[0097] Next, the microcirculation tracker is used to track the tracking points. Specifically, the preprocessed video is input into the microcirculation tracker, and the tracking points are marked in the first frame of the preprocessed video. Next, the convolutional neural network layer of the microcirculation tracker extracts the features of each frame of the preprocessed video; then, based on the features of each frame, the interpolation points of two adjacent frames are determined, and the interpolation points are used as tracking features; the tracking point features are input into the Transformer layer, thereby establishing the association information between different frame images; finally, the coordinate information of each tracking point in each frame is obtained based on the association information, thereby obtaining the motion trajectory of each tracking point.

[0098] After the motion trajectory of each tracking point is determined, S105 is executed to calculate the blood flow velocity based on the motion trajectory.

[0099] Specifically, based on the motion trajectory, the tracking point coordinates of the tracking point in each frame image are determined;

[0100] Based on the coordinates of the tracking point in each frame of the image, the instantaneous blood flow velocity of the tracking point is obtained according to the following formula:

[0101]

[0102] Among them, v mn is the instantaneous blood flow velocity of the tracking point, z is the frame rate of the preprocessed video, (x i ,y i ) is the coordinate of the tracking point in any frame from the mth frame to the nth frame, (x i+1 ,y i+1 ) is the coordinate of the tracking point in any frame of image in the next frame of image.

[0103] The m-th frame image to the n-th frame image represent continuous frame images, and the instantaneous blood flow velocity of the tracking point is calculated based on the coordinates of the tracking point in two adjacent frame images in the continuous frame images.

[0104] In order to smooth out speed fluctuations, the average speed within any L frames in the spatiotemporal range is calculated.

[0105] Specifically, based on the tracking point, a nearby point is determined, where the nearby point is determined within a preset distance of the tracking point;

[0106] Get the instantaneous blood flow velocity of nearby points;

[0107] Based on the instantaneous blood flow velocity of the tracking point and the instantaneous blood flow velocity of the nearby points, the average velocity within any L in the time and space range is determined, which is obtained according to the following formula:

[0108]

[0109] Where L is the number of any frames in the space-time range, v (m-i)(n-i) and v (m+i)(n+1) are the instantaneous blood flow velocities of nearby points at different locations. is the average speed within any L frames in the space-time range.

[0110] By performing average calculation within a local time and space range, velocity fluctuations are smoothed and the stability of velocity measurement is improved.

[0111] By introducing a speed constraint mechanism, it is ensured that the direction of the speed and the orientation of the blood vessel remain consistent during the tracking process, and the magnitude of the speed is also consistent with the normal range of animal blood flow, so as to improve the accuracy of tracking.

[0112] Next, calculating the blood flow velocity also includes: an average blood flow velocity at the interpolation point.

[0113] Specifically, based on the instantaneous blood flow velocity of the tracking points, determining the instantaneous blood flow velocity of any two tracking points;

[0114] An interpolation point is determined between any two tracking points to obtain the instantaneous blood flow velocity of the interpolation point; wherein the instantaneous blood flow velocity of the interpolation point between the two points is calculated using linear interpolation.

[0115] Based on the instantaneous blood flow velocity of any two tracking points and the instantaneous blood flow velocity of the interpolation point, the average blood flow velocity at the interpolation point is determined according to the following formula:

[0116]

[0117] in, is the instantaneous blood flow velocity at the interpolation point, and is the instantaneous blood flow velocity of any two tracking points, is the average blood flow velocity at the interpolation point.

[0118] After obtaining the above three blood flow velocities, they are converted into actual blood flow velocity units through velocity conversion to facilitate medical analysis and clinical application.

[0119] Finally, S106 is executed to display the blood flow velocity, so that the blood flow velocity of the animal's microcirculation can be clearly seen through the display, so as to effectively monitor the health status.

[0120] One or more technical solutions in the embodiments of the present invention have at least the following technical effects or advantages:

[0121] The present invention provides a method for monitoring blood flow velocity of animal microcirculation, comprising: acquiring a video of an animal microcirculation region; preprocessing the video to obtain a preprocessed video; determining a tracking point based on the preprocessed video; tracking the tracking point using a microcirculation tracker to determine a motion trajectory of the tracking point, wherein the microcirculation tracker is obtained through training; calculating the blood flow velocity based on the motion trajectory; displaying the blood flow velocity; and significantly improving the accuracy and reliability of blood flow velocity monitoring by using deep learning video pixel tracking technology, thereby providing strong technical support for biomedical research.

[0122] Embodiment 2:

[0123] Based on the same inventive concept, the embodiment of the present invention also provides a blood flow velocity monitoring device for animal microcirculation, such as Figure 3 As shown, including:

[0124] An acquisition module 301 is used to acquire a video of the microcirculation area of ​​an animal;

[0125] Obtaining module 302, for preprocessing the video to obtain a preprocessed video;

[0126] A tracking point determination module 303, configured to determine a tracking point based on the pre-processed video;

[0127] A motion trajectory determination module 304 is used to track the tracking point using a microcirculation tracker to determine the motion trajectory of the tracking point, wherein the microcirculation tracker is obtained through training;

[0128] A calculation module 305, configured to calculate the blood flow velocity based on the motion trajectory;

[0129] The display module 306 is used to display the blood flow velocity.

[0130] In an optional implementation, a module 302 is obtained for:

[0131] Cropping the video to obtain a cropped video, wherein the cropped video is an unmoved segment;

[0132] Performing shake correction processing on the cropped video to obtain a shake-corrected video;

[0133] Performing noise reduction processing on the shake-corrected video to obtain a noise-reduced video;

[0134] Performing illumination correction processing on the noise reduction video to obtain an illumination corrected video;

[0135] Generating a segmentation mask process on the illumination correction video to obtain a binary image video;

[0136] The video of the binary image is enhanced to obtain a preprocessed video.

[0137] In an optional implementation, the method further includes: a tracking point determination module 303, which is used to:

[0138] Determining a preset coordinate point based on each frame of the preprocessed video;

[0139] Taking the preset coordinate point as the center of the circle, a tracking point is determined within a preset radius, and the tracking point is the pixel coordinate of the center line of the blood vessel closest to the center of the circle.

[0140] In an optional implementation, the method further includes a training module for:

[0141] Simulate and construct 3D blood vessels, and create the flow direction and speed of blood cells in the blood vessels to obtain blood cell movement videos;

[0142] A microcirculation tracker is trained based on the blood cell movement video, wherein the blood cell movement video is annotated with position labels of blood cells.

[0143] In an optional implementation, the motion trajectory determination module 304 is used to

[0144] Inputting the preprocessed video into the microcirculation tracker to determine the features of each frame of the image, wherein the tracking points of the first frame of the image are marked in the preprocessed video;

[0145] Based on the features of each frame of image, interpolation points between two adjacent frames of image are determined, and the interpolation points are used as tracking features;

[0146] Based on the tracking feature, determining association information between different frame images;

[0147] Based on the association information, determining coordinate information of the tracking point in each frame of the image;

[0148] Based on the coordinate information of the tracking point in each frame of the image, the motion trajectory of the tracking point is determined.

[0149] In an optional implementation, the calculation module 305 is used to:

[0150] Based on the motion trajectory, determining the tracking point coordinates of the tracking point in each frame image;

[0151] Based on the coordinates of the tracking point in each frame of the image, the instantaneous blood flow velocity of the tracking point is obtained according to the following formula:

[0152]

[0153] Among them, v mn is the instantaneous blood flow velocity of the tracking point, z is the frame rate of the preprocessed video, (x i ,y i ) is the coordinate of the tracking point in any frame from the mth frame to the nth frame, (x i+1 ,y i+1 ) are the tracking point coordinates of any frame image in the next frame image.

[0154] In an optional implementation, the calculation module 305 is further configured to:

[0155] Based on the tracking point, determine a nearby point, wherein the nearby point is determined within a preset distance of the tracking point;

[0156] Get the instantaneous blood flow velocity of nearby points;

[0157] Based on the instantaneous blood flow velocity of the tracking point and the instantaneous blood flow velocity of the nearby points, the average velocity within any L frames in the time and space range is determined, which is specifically obtained according to the following formula:

[0158]

[0159] Where L is the number of any frames in the space-time range, v (m-i)(n-i) and v (m+i)(n+1) are the instantaneous blood flow velocities of nearby points at different locations. is the average speed within any L frames in the space-time range.

[0160] In an optional implementation, the calculation module 304 is further configured to:

[0161] Based on the instantaneous blood flow velocity of the tracking point, determining the instantaneous blood flow velocity of any two tracking points;

[0162] Determine an interpolation point between any two tracking points to obtain the instantaneous blood flow velocity of the interpolation point;

[0163] Based on the instantaneous blood flow velocities of the two arbitrary tracking points and the instantaneous blood flow velocity of the interpolation point, the average blood flow velocity at the interpolation point is determined, which is implemented according to the following formula:

[0164]

[0165] in, is the instantaneous blood flow velocity at the interpolation point, and is the instantaneous blood flow velocity of any two tracking points, is the average blood flow velocity at the interpolation point.

[0166] Embodiment three:

[0167] Based on the same inventive concept, an embodiment of the present invention provides a computer device, such as Figure 4 As shown, it includes a memory 404, a processor 402, and a computer program stored in the memory 404 and executable on the processor 402. When the processor 402 executes the program, the steps of the above-mentioned animal microcirculation blood flow velocity monitoring method are implemented.

[0168] Among them, Figure 4In the embodiment of the present invention, a bus architecture (represented by bus 400) is shown, which may include any number of interconnected buses and bridges, and bus 400 links various circuits including one or more processors represented by processor 402 and memory represented by memory 404. Bus 400 may also link various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. Bus interface 406 provides an interface between bus 400 and receiver 401 and transmitter 403. Receiver 401 and transmitter 403 may be the same element, namely a transceiver, providing a unit for communicating with various other devices over a transmission medium. Processor 402 is responsible for managing bus 400 and general processing, while memory 404 may be used to store data used by processor 402 when performing operations.

[0169] Embodiment 4:

[0170] Based on the same inventive concept, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-mentioned method for monitoring blood flow velocity of animal microcirculation.

[0171] The algorithm and display provided herein are not inherently related to any particular computer, virtual system or other device. Various general purpose systems can also be used together with the teachings based on this. According to the above description, it is obvious that the structure required for constructing such systems. In addition, the present invention is not directed to any specific programming language either. It should be understood that various programming languages ​​can be utilized to realize the content of the present invention described herein, and the description of the above specific languages ​​is for disclosing the best mode of the present invention.

[0172] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0173] Similarly, it should be understood that in order to streamline the present invention and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, the various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting the following intention: that the claimed invention requires more features than the features explicitly recorded in each embodiment. More specifically, as reflected in each embodiment, the inventive aspects lie in less than all the features of the single embodiment disclosed above. Therefore, the claims that follow the specific embodiment are hereby expressly incorporated into the specific embodiment, wherein each claim itself serves as a separate embodiment of the present invention.

[0174] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and in addition they may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this manner may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0175] In addition, those skilled in the art will appreciate that, although some embodiments herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present invention and form different embodiments. For example, in a specific embodiment, any one of the claimed embodiments may be used in any combination.

[0176] The various component embodiments of the present invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or digital signal processor (DSP) may be used in practice to implement some or all functions of some or all components of a blood flow velocity monitoring device for animal microcirculation and a computer device according to an embodiment of the present invention. The present invention may also be implemented as a device or device program (e.g., a computer program and a computer program product) for executing part or all of the methods described herein. Such a program for implementing the present invention may be stored on a computer-readable medium, or may be in the form of one or more signals. Such a signal may be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0177] It should be noted that the above embodiments illustrate the present invention rather than limit it, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets shall not be construed as a limitation on the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising a number of different elements and by means of a suitably programmed computer. In a unit claim enumerating a number of devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc., does not indicate any order. These words may be interpreted as names.

Claims

1. A method for monitoring blood flow velocity in animal microcirculation, characterized in that: include: Obtain videos of the animal's microcirculatory regions; Preprocessing the video to obtain a preprocessed video; Based on the preprocessed video, determining a tracking point; Using a microcirculation tracker to track the tracking point and determine the motion trajectory of the tracking point, the microcirculation tracker is obtained through training; Based on the motion trajectory, calculating the blood flow velocity; The blood flow velocity is displayed.

2. The method according to claim 1, characterized in that Preprocessing the video to obtain a preprocessed video includes: Cropping the video to obtain a cropped video, wherein the cropped video is an unmoved segment; Performing shake correction processing on the cropped video to obtain a shake-corrected video; Performing noise reduction processing on the shake-corrected video to obtain a noise-reduced video; Performing illumination correction processing on the noise reduction video to obtain an illumination corrected video; Generating a segmentation mask process on the illumination correction video to obtain a binary image video; The video of the binary image is enhanced to obtain a preprocessed video.

3. The method according to claim 1, characterized in that Based on the pre-processed video, determining a tracking point includes: Determining a preset coordinate point based on each frame of the preprocessed video; Taking the preset coordinate point as the center of the circle, a tracking point is determined within a preset radius, and the tracking point is the pixel coordinate of the center line of the blood vessel closest to the center of the circle.

4. The method according to claim 1, characterized in that Before the microcirculation tracker is used to track the tracking point and determine the motion trajectory of the tracking point, the microcirculation tracker is trained and obtained, and the method further includes: Simulate and construct 3D blood vessels, and create the flow direction and speed of blood cells in the blood vessels to obtain blood cell movement videos; A microcirculation tracker is trained based on the blood cell movement video, wherein the blood cell movement video is annotated with position labels of blood cells.

5. The method according to claim 1, characterized in that The microcirculation tracker is used to track the tracking point and determine the motion trajectory of the tracking point, including: Inputting the preprocessed video into the microcirculation tracker to determine the features of each frame of the image, wherein the tracking points of the first frame of the image are marked in the preprocessed video; Based on the features of each frame of image, interpolation points between two adjacent frames of image are determined, and the interpolation points are used as tracking features; Based on the tracking feature, determining association information between different frame images; Based on the association information, determining coordinate information of the tracking point in each frame of the image; Based on the coordinate information of the tracking point in each frame of the image, the motion trajectory of the tracking point is determined.

6. The method according to claim 1, characterized in that Based on the motion trajectory, the blood flow velocity is calculated, including: Based on the motion trajectory, determining the tracking point coordinates of the tracking point in each frame image; Based on the coordinates of the tracking point in each frame of the image, the instantaneous blood flow velocity of the tracking point is obtained according to the following formula: Among them, v mn is the instantaneous blood flow velocity of the tracking point, z is the frame rate of the preprocessed video, (x i ,y i ) is the coordinate of the tracking point in any frame from the mth frame to the nth frame, (x i+1 ,y i+1 ) are the tracking point coordinates of any frame image in the next frame image.

7. The method according to claim 6, characterized in that Calculating the blood flow velocity based on the motion trajectory also includes: Based on the tracking point, determine a nearby point, wherein the nearby point is determined within a preset distance of the tracking point; Get the instantaneous blood flow velocity of nearby points; Based on the instantaneous blood flow velocity of the tracking point and the instantaneous blood flow velocity of the nearby points, the average velocity within any L frames in the time and space range is determined, which is specifically obtained according to the following formula: Where L is the number of any frames in the space-time range, v (m-i)(n-i) and v (m+i)(n+1) are the instantaneous blood flow velocities of nearby points at different locations. is the average speed within any L frames in the space-time range.

8. The method according to claim 6, characterized in that Calculating the blood flow velocity based on the motion trajectory also includes: Based on the instantaneous blood flow velocity of the tracking point, determining the instantaneous blood flow velocity of any two tracking points; Determine an interpolation point between any two tracking points to obtain the instantaneous blood flow velocity of the interpolation point; Based on the instantaneous blood flow velocities of the two arbitrary tracking points and the instantaneous blood flow velocity of the interpolation point, the average blood flow velocity at the interpolation point is determined, which is implemented according to the following formula: in, is the instantaneous blood flow velocity at the interpolation point, and is the instantaneous blood flow velocity of any two tracking points, is the average blood flow velocity at the interpolation point.

9. A blood flow velocity monitoring device for animal microcirculation, characterized in that: include: An acquisition module, used to acquire a video of the microcirculation area of ​​an animal; Obtaining a module, used for preprocessing the video to obtain a preprocessed video; A tracking point determination module, used for determining a tracking point based on the pre-processed video; A motion trajectory determination module, used to track the tracking point using a microcirculation tracker to determine the motion trajectory of the tracking point, wherein the microcirculation tracker is obtained through training; A calculation module, used for calculating the blood flow velocity based on the motion trajectory; A display module is used to display the blood flow velocity.

10. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 8 is implemented.

Images