Blood vessel blood flow speed measurement method based on optical flow method area tracking

Abstract

The invention discloses a blood vessel blood flow velocity measurement method based on optical flow method area tracking, which relates to the technical field of blood flow velocity measurement, and comprises the following steps: extracting multiple frames of blood vessel images from a blood vessel video, and determining an ROI area in each frame of blood vessel image according to a set ROI area division rule; performing movement estimation on the two adjacent frames of blood vessel images through a DIS optical flow method to obtain blood flow data of the two adjacent frames of blood vessel images; performing area tracking on the blood flow data through affine transformation to obtain affine transformation parameters of each frame of blood vessel image; inputting the radiation transformation parameters into a preset movement amount prediction model, predicting and obtaining the movement amounts of the ROI regions of the multiple groups of adjacent frames of blood vessel images, and performing speed estimation according to the multiple groups of movement amounts so as to output the blood flow speed; motion estimation is carried out on two adjacent frames of blood vessel images through the DIS optical flow method, the response capacity of the system to dynamic blood flow changes in a complex blood vessel structure is improved, and therefore accurate measurement under different blood vessel conditions is ensured.

Description

Technical Field

[0001] The present invention relates to the field of blood flow velocity measurement, and in particular to a blood vessel blood flow velocity measurement method based on optical flow method area tracking. Background Art

[0002] The blood flow velocity in the microcirculation is crucial to maintaining tissue health. Slowed blood flow or thrombosis can lead to local tissue ischemia, hypoxia, and even necrosis, which in turn can cause a variety of diseases. Therefore, as an important part of blood circulation, the blood flow velocity in the microcirculation is an important physiological parameter reflecting the state of microcirculation. In order to accurately measure the microcirculation blood flow velocity, the role of fast, non-invasive modern blood flow velocity measurement technology in medical diagnosis is becoming increasingly important.

[0003] Blood flow velocity measurement technology has undergone many years of development, gradually evolving from early contact measurement to modern non-invasive measurement technology based on blood flow imaging. Traditional contact methods are often invasive, complex to operate, and have low accuracy, while modern measurement methods provide more reliable, fast, and non-invasive options. Modern blood flow velocity measurement technology is mainly divided into three categories: frequency shift analysis method based on Doppler effect, analysis method based on tracer particle tracking, and motion estimation method based on image pixel features. The Doppler effect method is often used for blood flow velocity measurement in large blood vessels, but it is not widely used in microcirculation and low-speed blood flow. The method is easily disturbed by clutter; although the tracer particle tracking method is effective, tracer particles are not allowed to be placed in the blood, so there are many restrictions in practical applications. In contrast, the motion estimation method based on image pixel features analyzes the red blood cells or white blood cells in the blood as motion features to measure the velocity, which has become an important means of studying microcirculatory blood flow, especially in the non-invasive quantitative evaluation of nail fold microvascular blood flow. For example, a microcirculatory high-speed blood flow measurement system and method are proposed in the Chinese patent with announcement number CN111956200B. Combined with the existing technology, it can be found that: At present, it is difficult to achieve high-precision blood flow velocity detection in complex vascular structures. Especially when dealing with different vascular conditions and dynamic changes, the velocity measurement results are easily interfered by factors such as non-target areas, noise and poor image quality. In addition, the lack of an intelligent prediction mechanism based on historical data leads to insufficient accuracy of velocity estimation, weak robustness and anti-interference ability. Therefore, a technology is needed that can accurately divide the ROI area, stably capture the blood flow area and optimize the velocity prediction through historical movement, so as to improve the accuracy, continuity and anti-interference ability of blood flow velocity measurement. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a method for measuring blood flow velocity in blood vessels based on optical flow area tracking.

[0005] A method for measuring blood flow velocity in blood vessels based on optical flow area tracking, the method comprising: Extract multiple frames of vascular images from the vascular video, and determine the ROI area in each frame of the vascular image according to the established ROI area division rule; The DIS optical flow method is used to estimate the motion of two adjacent frames of vascular images to obtain the blood flow data of the two adjacent frames of vascular images; Perform regional tracking on blood flow data through affine transformation to obtain affine transformation parameters of each frame of vascular image; The radiation transformation parameters are input into a preset movement amount prediction model to predict the movement amount of the ROI area of ​​multiple sets of adjacent frame vascular images, and the velocity is estimated based on the multiple sets of movement amounts to output the blood flow velocity.

[0006] Furthermore, the setting logic of the ROI area division rule is: A target area with clear blood features in the blood vessel image is selected as the ROI area. The size of the ROI area is determined according to the width of the blood vessel. The width of the ROI area does not exceed the width of the narrowest part of the blood vessel. The ROI area is set in the middle of the blood vessel, and multiple ROI areas are drawn according to the determined position of the ROI area.

[0007] Furthermore, the blood flow data includes an optical flow field, an optical flow horizontal velocity component, and an optical flow vertical velocity component of a blood vessel image.

[0008] Furthermore, the DIS optical flow method is used to perform movement calculation on two adjacent frames of blood vessel images to obtain blood flow data, including: The DIS optical flow algorithm is used to calculate the optical flow field for the vascular images of two adjacent frames. The logical formula of the optical flow field is: ;in, is the optical flow field, is the horizontal velocity component of the optical flow, is the vertical velocity component of the optical flow.

[0009] Furthermore, the blood flow data is tracked by affine transformation, including: Extract the optical flow in the ROI area of ​​the optical flow field in the blood flow data, map the ROI area of ​​the t-1 frame vascular image to the t frame vascular image by fitting the affine transformation, and determine the affine transformation parameters, wherein the affine transformation parameters include translation parameters and scaling parameters; suppose the range of the ROI area from the t-1 frame vascular image to the t frame vascular image is ( , )arrive( , ), the fitting formula for horizontal motion is: ;in, is the horizontal translation component of the i-th ROI area, i is an integer greater than 0, is the horizontal scaling component of the ROI area, is the translation parameter of the fit, s is the scaling parameter of the fit, is the error term of horizontal motion; the fitting formula of vertical motion is: ;in, is the horizontal translation component of the ROI area, is the horizontal scaling component of the ROI area, is the error term of vertical motion; the translation parameter P and the scaling parameter S are obtained by the fitting formula of vertical motion and the fitting formula of horizontal motion through the least squares method.

[0010] Furthermore, the generation logic of the movement amount prediction model is: Q1, obtaining historical movement training data, and dividing the historical movement training data into a movement training set and a movement test set; the historical movement training data includes a radiation transformation parameter and its corresponding movement; Q2, construct a regression network, use the radiation transformation parameters in the movement training set as the first regression network input data, and use the estimated movement in the movement training set as the regression network output data, train the regression network, and obtain the initial machine learning network; Q3, use the movement test set to verify the model of the initial machine learning network, and output the initial machine learning network that is less than or equal to the preset test error threshold as the pre-built movement prediction model.

[0011] Furthermore, the logic for obtaining the movement amount is: According to the updated data of the ROI area of ​​two adjacent frames of vascular images in history, assuming that the two adjacent frames are the N-1th frame of vascular image and the Nth frame of vascular image, the ROI area of ​​the N-1th frame of vascular image is obtained and marked as The ROI area of ​​the N-1 frame vascular image is marked as the ROI area updated in the Nth frame vascular image. Region, where The area can be fully covered The area and the content in the area remain the same. Suppose the range of the ROI area from the N-1 frame vascular image to the N frame vascular image is ( , )arrive( , ), The update formula for the region is: ;in, is the historical data of the horizontal scaling component, is the historical data of the scaling component in the vertical direction, is the historical data of the horizontal translation component, is the historical data of the vertical translation component; according to The centroid point in the region and The centroid point inside is calculated and obtained The centroid point in the region and The distance between the center of mass points within is used as the movement amount.

[0012] Furthermore, velocity estimation is performed based on multiple sets of movement amounts to output blood flow velocity, including: The frame rate of the blood vessel image is obtained by calculating the time interval between two adjacent frames of the image, and the primary blood flow velocity is obtained based on the time and movement. The calculation equation group of the primary blood flow velocity is: ; Transform the calculation equations into the formula of first-order blood flow velocity: ; Where Tg is the time interval between two frames of images, ft is the frame rate of the vascular image, is the primary blood flow velocity, and R is the predicted movement amount; Suppose that d groups of primary blood flow velocities are generated according to the movement of d groups, the primary blood flow velocity mean Vj of the primary blood flow velocity of d groups is calculated, and the error threshold K is set, K is a constant greater than 0, and the blood flow velocity of z groups greater than and less than The primary blood flow velocity of the remaining dz group is averaged to obtain the secondary blood flow velocity Vz, and the secondary blood flow velocity is output as the blood flow velocity, wherein the flow direction of the blood flow velocity is determined by the centroid point of the ROI area of ​​the continuous frame.

[0013] A blood vessel blood flow velocity measurement system based on optical flow method area tracking is used to perform any one of the blood vessel blood flow velocity measurement methods based on optical flow method area tracking, the system comprising: ROI region division module: used to extract multiple frames of vascular images from vascular videos, and determine the ROI region in each frame of vascular images according to the established ROI region division rules; Motion estimation module: used to perform motion estimation on two adjacent frames of vascular images using the DIS optical flow method to obtain blood flow data of two adjacent frames of vascular images Affine tracking module: used to perform regional tracking of blood flow data through affine transformation to obtain the affine transformation parameters of each frame of vascular image; Velocity analysis module: used to input the radiation transformation parameters into the preset movement prediction model, predict the movement of the ROI area of ​​multiple sets of adjacent frame vascular images, and estimate the velocity based on the multiple sets of movement to output the blood flow velocity.

[0014] Compared with the prior art, the present invention has the following beneficial effects: The present invention realizes high-precision detection of blood vessel blood flow velocity by performing motion estimation on two adjacent frames of blood vessel images through the DIS optical flow method, improves the system's responsiveness to dynamic changes in blood flow in complex blood vessel structures, and ensures accurate measurement under different blood vessel conditions; the present invention also selects the middle area of ​​the blood vessel with obvious blood characteristics as the ROI area through a preset ROI area division rule, and limits the size of the ROI area according to the width of the narrowest part of the blood vessel, so as to ensure that the ROI area can accurately represent the blood flow characteristics in the blood vessel, reduce the interference of non-target areas on the calculation results, and realizes stable capture of the blood flow area by performing affine transformation tracking on the ROI area, thereby effectively improving the stability and continuity of blood flow velocity measurement, thereby improving the robustness and anti-interference ability of blood flow velocity measurement, in addition, a movement prediction model is constructed through historical movement training data, and radial transformation parameters are optimized based on a regression network, so as to realize intelligent analysis of blood flow velocity, further improve the accuracy of blood flow velocity prediction, and thereby reduce the velocity estimation error caused by noise or poor image quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments 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 also be obtained based on these drawings.

[0016] Figure 1 A flow chart of a method for measuring blood flow velocity in a blood vessel based on optical flow area tracking provided in Example 1 of the present invention; Figure 2 A ROI region division display diagram based on optical flow region tracking provided in Example 1 of the present invention; Figure 3 A schematic diagram of a region tracking result based on optical flow region tracking provided in Embodiment 1 of the present invention; Figure 4 This is a module diagram of a blood vessel blood flow velocity measurement system based on optical flow area tracking provided in Example 2 of the present invention. In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution 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 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 are within the scope of protection of the present invention.

[0017] Example 1 See also Figure 1As shown, this embodiment discloses a method for measuring blood flow velocity in a blood vessel based on optical flow area tracking, the method comprising: S110, extracting multiple frames of blood vessel images from the blood vessel video, and determining the ROI region in each frame of the blood vessel image according to a predetermined ROI region division rule; Specifically, see Figure 2 , the setting logic of ROI area division rules is: A target area with clear blood features in the blood vessel image is selected as the ROI area. The size of the ROI area is determined according to the width of the blood vessel. The width of the ROI area does not exceed the width of the narrowest part of the blood vessel. The ROI area is set in the middle of the blood vessel, and multiple ROI areas are continuously drawn according to the determined position of the ROI area. It should be noted that blood flow characteristics include blood flow velocity, direction, flow, pulsatility, laminar or turbulent state, etc. These data are mainly obtained through the following non-invasive collection methods: Ultrasound Doppler uses the Doppler effect to measure blood flow velocity and direction, magnetic resonance angiography (MRA) and computed tomography angiography (CTA) combine with contrast agents to provide three-dimensional vascular images to evaluate blood flow velocity and blockage, near-infrared spectroscopy (NIRS) indirectly measures local blood flow through light absorption, and laser Doppler imaging (LDI) uses laser reflection frequency shift to measure microcirculatory blood flow.

[0018] S120, performing motion estimation on two adjacent frames of blood vessel images by using a DIS optical flow method to obtain blood flow data of the two adjacent frames of blood vessel images; Specifically, the blood flow data includes an optical flow field, an optical flow horizontal velocity component, and an optical flow vertical velocity component of a blood vessel image; Specifically, the DIS optical flow method is used to perform movement calculation on two adjacent frames of vascular images to obtain blood flow data, including: The DIS optical flow algorithm is used to calculate the optical flow field for the vascular images of two adjacent frames. The logical formula of the optical flow field is: ;in, is the optical flow field, is the horizontal velocity component of the optical flow, is the vertical velocity component of the optical flow; It should be noted that the optical flow field is a 2D vector field, which assigns an expected movement vector from the current frame to the next frame to each pixel in the vascular image, that is, a pixel displacement vector used to describe the vascular image of the t-1 frame and the vascular image of the t frame, where the horizontal velocity component (x,y) and vertical velocity components (x,y) is obtained by calculating the optical flow equation.

[0019] S130, performing regional tracking on the blood flow data through affine transformation to obtain affine transformation parameters of each frame of the blood vessel image; Specifically, the blood flow data is tracked regionally through affine transformation, including: Extracting the optical flow in the ROI region of the optical flow field in the blood flow data, mapping the ROI region of the t-1 frame blood vessel image to the t frame blood vessel image by fitting the affine transformation to determine the affine transformation parameters, wherein the affine transformation parameters include translation parameters and scaling parameters; What you need to know is that optical flow refers to the motion vector of each pixel in the image between two consecutive image frames. It describes the movement or change of the pixel point in time; Suppose the range of the ROI area from the vascular image of frame t-1 to the vascular image of frame t is ( , )arrive( , ), the fitting formula for horizontal motion is: ;in, is the horizontal translation component of the i-th ROI area, i is an integer greater than 0, is the horizontal scaling component of the ROI area, is the translation parameter of the fit, s is the scaling parameter of the fit, is the error term of horizontal motion; What you need to know is: Error term Represents the horizontal velocity component of optical flow Displacement predicted by the affine transformation model By minimizing the error term, we can find the optimal translation parameter and scaling parameters ; The fitting formula for vertical motion is: ;in, is the horizontal translation component of the ROI area, is the horizontal scaling component of the ROI area, is the error term of vertical motion; What you need to know is: Error term Represents the vertical velocity component of optical flow Displacement predicted by the affine transformation model The square of the difference between The translation parameter P and the scaling parameter S are obtained by using the fitting formula of the vertical motion and the fitting formula of the horizontal motion through the least square method.

[0020] It should be noted that when tracking the vascular ROI area, due to the deformation of the vascular fluid, affine transformations such as rotation and scaling may occur in the vascular area. By fitting the affine transformation, the new position of the vascular area can be accurately estimated. Since the calculation of blood flow velocity depends on the precise change of position between consecutive frames, fitting the affine transformation is crucial for measuring blood flow velocity. The fitting of the affine transformation is to find the translation and scaling parameters that best suit the current ROI area movement, thereby effectively updating the position and size of the ROI area, and by minimizing the error between the optical flow field and the affine transformation prediction, the use of the affine transformation can provide a more accurate local motion estimate for the ROI area, further improving the accuracy of the tracking algorithm, especially when fast or complex motion occurs in the ROI area.

[0021] S140, inputting the radiation transformation parameters into a preset movement amount prediction model, predicting and acquiring the movement amounts of the ROI area of ​​multiple sets of adjacent frame blood vessel images, and performing velocity estimation based on the multiple sets of movement amounts to output the blood flow velocity; Specifically, the generation logic of the movement amount prediction model is: Q1, obtaining historical movement training data, and dividing the historical movement training data into a movement training set and a movement test set; the historical movement training data includes a radiation transformation parameter and its corresponding movement; Specifically, see Figure 3 It can be seen that the logic for obtaining the movement amount is: According to the historical update data of the ROI area of ​​two adjacent frames of vascular images, the two adjacent frames are assumed to be the N-1th frame of vascular images ( Figure 3 Upper vascular image) and the Nth frame vascular image ( Figure 3 The ROI area of ​​the N-1 frame vascular image is obtained and marked as The ROI area of ​​the N-1 frame vascular image is marked as the ROI area updated in the Nth frame vascular image. Region, where The area can be fully covered The area and the content in the area remain the same. Suppose the range of the ROI area from the N-1 frame vascular image to the N frame vascular image is ( , )arrive( , ), The update formula for the region is: ;in, is the historical data of the horizontal scaling component, is the historical data of the scaling component in the vertical direction, is the historical data of the horizontal translation component, is the historical data of the translation component in the vertical direction; It should be noted that: Figure 3 The box area is the ROI area. In the update formula of the region, for The new position of the coordinates in the region after translation and scaling. and Respectively The width and height of the area after scaling; according to The centroid point in the region and The centroid point inside is calculated and obtained The centroid point in the region and The distance between the center of mass points within is used as the movement amount.

[0022] It should be noted that the meaning of i in this step is the same as the above, but in this step i is the i-th ROI area in the past historical data, and the centroid point is The regional center point within the region; Q2, construct a regression network, use the radiation transformation parameters in the movement training set as the first regression network input data, and use the estimated movement in the movement training set as the regression network output data, train the regression network, and obtain the initial machine learning network; Q3, use the movement test set to verify the model of the initial machine learning network, and output the initial machine learning network that is less than or equal to the preset test error threshold as the pre-built movement prediction model; Specifically, velocity estimation is performed based on multiple groups of movement amounts to output blood flow velocity, including: The frame rate of the blood vessel image is obtained by calculating the time interval between two adjacent frames of the image, and the primary blood flow velocity is obtained based on the time and movement. The calculation equation group of the primary blood flow velocity is: ; Transform the calculation equations into the formula of first-order blood flow velocity: ; Where Tg is the time interval between two frames of images, ft is the frame rate of the vascular image, is the primary blood flow velocity, and R is the predicted movement amount; Suppose that d groups of primary blood flow velocities are generated according to the movement of d groups, the primary blood flow velocity mean Vj of the primary blood flow velocity of d groups is calculated, and the error threshold K is set, K is a constant greater than 0, and the blood flow velocity of z groups greater than and less than The primary blood flow velocity of the remaining dz group is averaged to obtain the secondary blood flow velocity Vz, and the secondary blood flow velocity is output as the blood flow velocity, wherein the flow direction of the blood flow velocity is determined by the centroid point of the ROI area of ​​the continuous frame.

[0023] It should be noted that: the time interval Tx can be obtained through a time timer.

[0024] Example 2 See also Figure 3 As shown, based on the unified inventive concept, this embodiment also discloses a blood vessel blood flow velocity measurement system based on optical flow method region tracking, the system includes a ROI region division module, a motion estimation module, an affine tracking module and a velocity analysis module: The ROI region division module S210 is used to extract multiple frames of blood vessel images from the blood vessel video, and determine the ROI region in each frame of the blood vessel image according to the established ROI region division rule; Specifically, the setting logic of the ROI area division rule is: A target area with clear blood features in the blood vessel image is selected as the ROI area. The size of the ROI area is determined according to the width of the blood vessel. The width of the ROI area does not exceed the width of the narrowest part of the blood vessel. The ROI area is set in the middle of the blood vessel, and multiple ROI areas are drawn according to the determined position of the ROI area.

[0025] The motion estimation module S220 is used to perform motion estimation on two adjacent frames of blood vessel images by using the DIS optical flow method to obtain blood flow data of the two adjacent frames of blood vessel images; Specifically, the blood flow data includes an optical flow field, an optical flow horizontal velocity component, and an optical flow vertical velocity component of a blood vessel image; Specifically, the DIS optical flow method is used to perform movement calculation on two adjacent frames of vascular images to obtain blood flow data, including: The DIS optical flow algorithm is used to calculate the optical flow field for the vascular images of two adjacent frames. The logical formula of the optical flow field is: ;in, is the optical flow field, is the horizontal velocity component of the optical flow, is the vertical velocity component of the optical flow.

[0026] Affine tracking module S230: used to perform regional tracking on blood flow data through affine transformation to obtain affine transformation parameters of each frame of blood vessel image; Specifically, the blood flow data is tracked regionally through affine transformation, including: Extracting the optical flow in the ROI region of the optical flow field in the blood flow data, mapping the ROI region of the t-1 frame blood vessel image to the t frame blood vessel image by fitting the affine transformation to determine the affine transformation parameters, wherein the affine transformation parameters include translation parameters and scaling parameters; Suppose the range of the ROI area from the vascular image of frame t-1 to the vascular image of frame t is ( , )arrive( , ), the fitting formula for horizontal motion is: ;in, is the horizontal translation component of the i-th ROI area, i is an integer greater than 0, is the horizontal scaling component of the ROI area, is the translation parameter of the fit, s is the scaling parameter of the fit, is the error term of horizontal motion; The fitting formula for vertical motion is: ;in, is the horizontal translation component of the ROI area, is the horizontal scaling component of the ROI area, is the error term of vertical motion; The translation parameter P and the scaling parameter S are obtained by using the fitting formula of the vertical motion and the fitting formula of the horizontal motion through the least square method.

[0027] The velocity analysis module S240 is used to input the radiation transformation parameters into a preset movement amount prediction model, predict the movement amount of the ROI area of ​​multiple sets of adjacent frame blood vessel images, and perform velocity estimation based on the multiple sets of movement amounts to output the blood flow velocity; Specifically, the generation logic of the movement amount prediction model is: Q1, obtaining historical movement training data, and dividing the historical movement training data into a movement training set and a movement test set; the historical movement training data includes a radiation transformation parameter and its corresponding movement; Specifically, the logic for obtaining the movement amount is: According to the updated data of the ROI area of ​​two adjacent frames of vascular images in history, assuming that the two adjacent frames are the N-1th frame of vascular image and the Nth frame of vascular image, the ROI area of ​​the N-1th frame of vascular image is obtained and marked as The ROI area of ​​the N-1 frame vascular image is marked as the ROI area updated in the Nth frame vascular image. Region, where The area can be fully covered The area and the content in the area remain the same. Suppose the range of the ROI area from the N-1 frame vascular image to the N frame vascular image is ( , )arrive( , ), The update formula for the region is: ;in, is the historical data of the horizontal scaling component, is the historical data of the scaling component in the vertical direction, is the historical data of the horizontal translation component, is the historical data of the translation component in the vertical direction; according to The centroid point in the region and The centroid point inside is calculated and obtained The centroid point in the region and The distance between the center of mass points within is used as the movement amount.

[0028] Q2, construct a regression network, use the radiation transformation parameters in the movement training set as the first regression network input data, and use the estimated movement in the movement training set as the regression network output data, train the regression network, and obtain the initial machine learning network; Q3, use the movement test set to verify the model of the initial machine learning network, and output the initial machine learning network that is less than or equal to the preset test error threshold as the pre-built movement prediction model; Specifically, velocity estimation is performed based on multiple groups of movement amounts to output blood flow velocity, including: The frame rate of the blood vessel image is obtained by calculating the time interval between two adjacent frames of the image, and the primary blood flow velocity is obtained based on the time and movement. The calculation equation group of the primary blood flow velocity is: ; Transform the calculation equations into the formula of first-order blood flow velocity: ; Where Tg is the time interval between two frames of images, ft is the frame rate of the vascular image, is the primary blood flow velocity, and R is the predicted movement amount; Suppose that d groups of primary blood flow velocities are generated according to the movement of d groups, the primary blood flow velocity mean Vj of the primary blood flow velocity of d groups is calculated, and the error threshold K is set, K is a constant greater than 0, and the blood flow velocity of z groups greater than and less than The primary blood flow velocity of the remaining dz group is averaged to obtain the secondary blood flow velocity Vz, and the secondary blood flow velocity is output as the blood flow velocity, wherein the flow direction of the blood flow velocity is determined by the centroid point of the ROI area of ​​the continuous frame.

[0029] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired network or a wireless network. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media sets. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD) or a semiconductor medium. The semiconductor medium may be a solid-state hard disk.

[0030] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0031] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0032] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a method for measuring blood flow velocity based on optical flow area tracking. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0033] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0034] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0035] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0036] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for measuring blood flow velocity based on optical flow area tracking, characterized in that: The method comprises: Extract multiple frames of vascular images from the vascular video, and determine the ROI area in each frame of the vascular image according to the established ROI area division rule; The DIS optical flow method is used to estimate the motion of two adjacent frames of vascular images to obtain the blood flow data of the two adjacent frames of vascular images; Perform regional tracking on blood flow data through affine transformation to obtain affine transformation parameters of each frame of vascular image; The radiation transformation parameters are input into a preset movement amount prediction model to predict the movement amount of the ROI area of ​​multiple sets of adjacent frame vascular images, and the velocity is estimated based on the multiple sets of movement amounts to output the blood flow velocity.

2. According to claim 1, a method for measuring blood flow velocity based on optical flow area tracking, characterized in that: The setting logic of ROI area division rules is: A target area with clear blood features in the blood vessel image is selected as the ROI area. The size of the ROI area is determined according to the width of the blood vessel. The width of the ROI area does not exceed the width of the narrowest part of the blood vessel. The ROI area is set in the middle of the blood vessel, and multiple ROI areas are drawn according to the determined position of the ROI area.

3. The method for measuring blood flow velocity based on optical flow area tracking according to claim 2, characterized in that: The blood flow data includes an optical flow field, an optical flow horizontal velocity component, and an optical flow vertical velocity component of a blood vessel image.

4. The method for measuring blood flow velocity based on optical flow area tracking according to claim 3, characterized in that: The DIS optical flow method is used to perform motion calculation on two adjacent frames of vascular images to obtain blood flow data, including: The DIS optical flow algorithm is used to calculate the optical flow field for the vascular images of two adjacent frames. The logical formula of the optical flow field is: ;in, is the optical flow field, is the horizontal velocity component of the optical flow, is the vertical velocity component of the optical flow.

5. The method for measuring blood flow velocity based on optical flow area tracking according to claim 4, characterized in that: Region tracking of blood flow data using affine transformation, including: Extract the optical flow in the ROI area of ​​the optical flow field in the blood flow data, map the ROI area of ​​the t-1 frame vascular image to the t frame vascular image by fitting the affine transformation, and determine the affine transformation parameters, wherein the affine transformation parameters include translation parameters and scaling parameters; suppose the range of the ROI area from the t-1 frame vascular image to the t frame vascular image is ( , )arrive( , ), the fitting formula for horizontal motion is: ;in, is the horizontal translation component of the i-th ROI area, i is an integer greater than 0, is the horizontal scaling component of the ROI area, is the translation parameter of the fit, s is the scaling parameter of the fit, is the error term of horizontal motion; the fitting formula of vertical motion is: ;in, is the horizontal translation component of the ROI area, is the horizontal scaling component of the ROI area, is the error term of vertical motion; the translation parameter P and the scaling parameter S are obtained by the fitting formula of vertical motion and the fitting formula of horizontal motion through the least squares method.

6. The method for measuring blood flow velocity based on optical flow area tracking according to claim 5, characterized in that: The generation logic of the movement prediction model is: Q1, obtaining historical movement training data, and dividing the historical movement training data into a movement training set and a movement test set; the historical movement training data includes a radiation transformation parameter and its corresponding movement; Q2, construct a regression network, use the radiation transformation parameters in the movement training set as the first regression network input data, and use the estimated movement in the movement training set as the regression network output data, train the regression network, and obtain the initial machine learning network; Q3, use the movement test set to verify the model of the initial machine learning network, and output the initial machine learning network that is less than or equal to the preset test error threshold as the pre-built movement prediction model.

7. The method for measuring blood flow velocity based on optical flow area tracking according to claim 6, characterized in that: The logic for obtaining the movement amount is: According to the updated data of the ROI area of ​​two adjacent frames of vascular images in history, assuming that the two adjacent frames are the N-1th frame of vascular image and the Nth frame of vascular image, the ROI area of ​​the N-1th frame of vascular image is obtained and marked as The ROI area of ​​the N-1 frame vascular image is marked as the ROI area updated in the Nth frame vascular image. Region, where The area can be fully covered The area and the content in the area remain the same. Suppose the range of the ROI area from the N-1 frame vascular image to the N frame vascular image is ( , )arrive( , ), The update formula for the region is: ;in, is the historical data of the horizontal scaling component, is the historical data of the scaling component in the vertical direction, is the historical data of the horizontal translation component, is the historical data of the vertical translation component; according to The centroid point in the region and The centroid point inside is calculated and obtained The centroid point in the region and The distance between the center of mass points within is used as the movement amount.

8. The method for measuring blood flow velocity based on optical flow area tracking according to claim 7, characterized in that: Velocity estimation is performed based on multiple sets of movement quantities to output blood flow velocity, including: The frame rate of the blood vessel image is obtained by calculating the time interval between two adjacent frames of the image, and the primary blood flow velocity is obtained based on the time and movement. The calculation equation group of the primary blood flow velocity is: ; Transform the calculation equations into the formula of first-order blood flow velocity: ; Where Tg is the time interval between two frames of images, ft is the frame rate of the vascular image, is the primary blood flow velocity, and R is the predicted movement amount; Suppose that d groups of primary blood flow velocities are generated according to the movement of d groups, the primary blood flow velocity mean Vj of the primary blood flow velocity of d groups is calculated, and the error threshold K is set, K is a constant greater than 0, and the blood flow velocity of z groups greater than and less than The primary blood flow velocity of the remaining dz group is averaged to obtain the secondary blood flow velocity Vz, and the secondary blood flow velocity is output as the blood flow velocity, wherein the flow direction of the blood flow velocity is determined by the centroid point of the ROI area of ​​the continuous frame.

9. A blood vessel blood flow velocity measurement system based on optical flow method area tracking, used to execute a blood vessel blood flow velocity measurement method based on optical flow method area tracking according to any one of claims 1 to 8, characterized in that: The system comprises: ROI region division module: used to extract multiple frames of vascular images from vascular videos, and determine the ROI region in each frame of vascular images according to the established ROI region division rules; Motion estimation module: used to perform motion estimation on two adjacent frames of vascular images using the DIS optical flow method to obtain blood flow data of two adjacent frames of vascular images Affine tracking module: used to perform regional tracking of blood flow data through affine transformation to obtain the affine transformation parameters of each frame of vascular image; Velocity analysis module: used to input the radiation transformation parameters into the preset movement prediction model, predict the movement of the ROI area of ​​multiple sets of adjacent frame vascular images, and estimate the velocity based on the multiple sets of movement to output the blood flow velocity.

Images