An echocardiogram image analysis system based on intelligent algorithms

Abstract

The present application provides an echocardiogram image analysis system based on an intelligent algorithm, including: an image acquisition module for acquiring echocardiogram image data based on color Doppler imaging; a feature extraction module for extracting features from the echocardiogram image data and respectively performing point marking on n points of cardiac blood flow based on the extracted features to obtain n marked blood flow points, where n is a positive integer greater than 1; an intelligent algorithm module for respectively using each of the n marked blood flow points as a target marked blood flow point and performing corresponding steps to determine the position information and flow velocity information of the target marked blood flow point in the image frame; and a result output module for respectively outputting and displaying the position information and flow velocity information for the marked blood flow points corresponding to the n points of each image frame in the echocardiogram image data. The system provided by the present application can achieve cardiac blood marking tracking and flow velocity monitoring.

Description

Technical Field

[0001] This application relates to the field of image processing. Specifically, it relates to an echocardiogram image analysis system based on intelligent algorithms. Background Art

[0002] Currently, artificial intelligence technology in the medical field has been gradually popularized. Using artificial intelligence technology to automatically measure, analyze, and interpret cardiac ultrasound images shows significant advantages compared to the process manually performed by doctors. This technology can ensure the consistency of data processing and recognition, eliminate the influence of subjective judgment, reduce the differences in evaluating cardiac ultrasound results among different doctors and by the same doctor at different time points, thereby improving the accuracy and stability of image interpretation. In addition, the application of artificial intelligence has greatly improved the efficiency of cardiac ultrasound examinations, better meeting the needs of clinical practice, and thus helping to improve the overall efficiency of the medical industry, reduce medical costs, and relieve the economic pressure on families and society.

[0003] In related technologies, with the increasing demand for automatic measurement of cardiac ultrasound dynamic images, the research and development of artificial intelligence for cardiac ultrasound dynamic image measurement have also been correspondingly in-depth. However, currently, the artificial intelligence-based measurement of cardiac ultrasound dynamic images can only achieve a simple restoration of the blood flow direction in the heart, and cannot accurately estimate and mark-track the blood flow velocity, resulting in limited usability of cardiac ultrasound dynamic images.

[0004] Therefore, this application provides an echocardiogram image analysis system based on intelligent algorithms to solve one of the above technical problems. Summary of the Invention

[0005] The purpose of this application is to provide an echocardiogram image analysis system based on intelligent algorithms, which can solve at least one of the above-mentioned technical problems. The specific solutions are as follows:

[0006] According to the specific embodiments of this application, in the first aspect, this application provides an echocardiogram image analysis system based on intelligent algorithms, including:

[0007] An image acquisition module for acquiring echocardiogram image data based on color Doppler imaging; a feature extraction module for extracting features from the echocardiogram image data and respectively performing point marking on n points of the cardiac blood flow based on the extracted features to obtain n marked blood flow points, where n is a positive integer greater than 1; an intelligent algorithm module for respectively using each of the n marked blood flow points as a target marked blood flow point and performing the following steps: for adjacent image frames of the echocardiogram image data, determining the Kasman compensation value Ks based on the feature information corresponding to the target marked blood flow point in the previous image frame of the adjacent image frames; based on the Kasman compensation value Ks, determining the corrected feature information corresponding to the target marked blood flow point in the subsequent image frame of the adjacent image frames through the following formula: T z = ST z-1 + Ks * (ST z - ST z-1 ) where Ks represents the Kasman compensation value, z represents the subsequent image frame in the adjacent image frames, z - 1 represents the previous image frame in the adjacent image frames, STz represents the feature information corresponding to the target marked blood flow point in the subsequent image frame of the adjacent image frames, STz - 1 represents the feature information corresponding to the target marked blood flow point in the previous image frame of the adjacent image frames, and Tz represents the corrected feature information corresponding to the target marked blood flow point in the subsequent image frame of the adjacent image frames; determining the position information and flow velocity information of the target marked blood flow point in the subsequent image frame based on the corrected feature information corresponding to the target marked blood flow point in the subsequent image frame of the adjacent image frames; a result output module for respectively outputting and displaying the position information and flow velocity information for the marked blood flow points corresponding to each of the n points of each image frame in the echocardiogram image data.

[0008] In one implementation, the intelligent algorithm module determines the position information of the target marked blood flow point in the subsequent image frame in the following manner: performing position feature recognition based on the corrected feature information corresponding to the target marked blood flow point in the subsequent image frame of the adjacent image frames to obtain the position information of the target marked blood flow point in the subsequent image frame.

[0009] In one implementation, the intelligent algorithm module determines the flow velocity information of the target marked blood flow point in the subsequent image frame using the following formula: where Y represents the flow velocity information of the target marked blood flow point in the subsequent image frame, a represents the acceleration information of the target marked blood flow point in the subsequent image frame, λ represents the frame interval of the adjacent image frames, φ represents the correction coefficient, and the correction coefficient is determined based on the target region where the marked point is located in multiple different regions, and the multiple different regions correspond one-to-one to multiple different parts of the heart in the echocardiogram image; where the intelligent algorithm module determines the acceleration information of the target marked blood flow point in the subsequent image frame using the following formula: Among them, a represents the acceleration of the target marked blood flow point, γ represents the compensation coefficient corresponding to the area where the target marked blood flow point is located, ld represents the first marked blood flow point in the echocardiogram image that is in the same area as the target marked blood flow point and is located at the lower left position of the target marked blood flow point, ru represents the second marked blood flow point in the echocardiogram image that is in the same area as the target marked blood flow point and is located at the upper right position of the target marked blood flow point, rd represents the third marked blood flow point in the echocardiogram image that is in the same area as the target marked blood flow point and is located at the lower right position of the target marked blood flow point, lu represents the fourth marked blood flow point in the echocardiogram image that is in the same area as the target marked blood flow point and is located at the upper left position of the target marked blood flow point, flld is the flow coordinate of the first marked point in the echocardiogram image, flru is the flow coordinate of the second marked point in the echocardiogram image, flrd is the flow coordinate of the third marked point in the echocardiogram image, fllu is the flow coordinate of the fourth marked point in the echocardiogram image, Lldru represents the distance between the first marked blood flow point and the second marked blood flow point in the echocardiogram image, and Lrdlu represents the distance between the third marked blood flow point and the fourth marked blood flow point in the echocardiogram image.

[0010] In one implementation, the feature extraction module includes: an edge detection module for detecting edge features in the echocardiogram image; a region feature extraction module for extracting region features from the echocardiogram image.

[0011] In one implementation, the result output module includes: a classification result output module for outputting the classification result of the marked blood flow points in the echocardiogram image; an analysis report generation module for generating and outputting an echocardiogram image analysis report based on the position information and the flow velocity information.

[0012] In one implementation, the image acquisition module includes: an echocardiogram device interface for performing data communication with an echocardiogram device; a data acquisition module for acquiring image data in the echocardiogram device.

[0013] In one implementation, the result output module supports multiple output methods, including print output, electronic document output, and online display.

[0014] In one implementation, the intelligent algorithm module: a model training module for training and optimizing the Kasman compensation value Ks; a model update module for updating and optimizing the Kasman compensation value Ks based on the manual annotation of the output result of the result output module. Description of the Drawings

[0015] Figure 1 Shows a block diagram of an echocardiogram image analysis system 1 based on an intelligent algorithm;

[0016] Figure 2 A block diagram of an image acquisition module 11 is shown;

[0017] Figure 3 A block diagram of a feature extraction module 12 is shown;

[0018] Figure 4 A block diagram of an intelligent algorithm module 13 is shown;

[0019] Figure 5 A block diagram of a result output module 14 is shown. Detailed implementation manners

[0020] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part rather than all of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the protection scope of the present application.

[0021] The terms used in the embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit the present application. The singular forms of "a", "an" and "the" used in the embodiments of the present application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. "Plural" generally includes at least two.

[0022] It should be understood that the term "and / or" used herein is only an association relationship describing associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " herein generally represents an "or" relationship between the associated objects before and after.

[0023] It should be understood that although the terms first, second, third, etc. may be used in the embodiments of the present application for description, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, without departing from the scope of the embodiments of the present application, the first may also be referred to as the second, and similarly, the second may also be referred to as the first.

[0024] Depending on the context, the words "if", "when" as used herein may be interpreted as "when...", "when...", "in response to determining" or "in response to detecting". Similarly, depending on the context, the phrase "if determining" or "if detecting (stated condition or event)" may be interpreted as "when determining", "in response to determining", "when detecting (stated condition or event)", or "in response to detecting (stated condition or event)".

[0025] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a commodity or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such commodity or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the commodity or device comprising the element.

[0026] It should be particularly noted that symbols and / or numbers existing in the specification, if not marked in the description of the drawings, are not reference numerals.

[0027] Currently, with the increasing demand for automatic measurement of cardiac ultrasound dynamic images, the artificial intelligence research and development for cardiac ultrasound dynamic image measurement has also deepened accordingly. In related technologies, it is considered to use color Doppler imaging to extract image features and perform feature classification and recognition on a single-frame video frame of ultrasonic imaging. This method, in the way of "taking pictures + observing", discriminates the blood flow direction based on the local characteristics of the image formed by blood flow through algorithm training. For the above-mentioned related technologies, on the one hand, it is easy to cause a large error in flow direction judgment due to the noise existing in single-frame imaging. On the other hand, since the blood flow direction in some parts of the heart will change significantly with the heartbeat (for example, the heartbeat is accompanied by the rapid expansion and contraction of the heart cavity), even if there is no noise in single-frame imaging, there will still be a problem of large error in flow direction judgment. In addition, based on the analysis of single-frame images, only low-level features such as shape and distribution can be applied, and complex content feature recognition and related applications cannot be carried out. Therefore, related technologies cannot analyze complex data, such as monitoring and tracking the blood flow velocity at specific points. In summary, only a simple restoration of the cardiac blood flow direction can be achieved in related technologies, and the blood flow velocity cannot be accurately estimated and marked and tracked, resulting in limited usability of cardiac ultrasound dynamic images.

[0028] The optional embodiments of the present application will be described in detail below with reference to the drawings.

[0029] The present application provides an ultrasonic echocardiogram image analysis system based on an intelligent algorithm. Among them, the ultrasonic echocardiogram image refers to a cardiac dynamic image obtained based on ultrasonic detection, which is obtained by continuously capturing ultrasonic frames of cardiac movements. Through the analysis of the ultrasonic echocardiogram image, the present application can monitor specific regions or points of the heart, and further realize functions such as blood flow point monitoring, tracking, flow velocity analysis, and flow direction analysis.

[0030] Figure 1 A block diagram of an ultrasonic echocardiogram image analysis system 1 based on an intelligent algorithm is shown, as Figure 1As shown in the figure, the echocardiogram image analysis system 1 includes an image acquisition module 11, a feature extraction module 12, an intelligent algorithm module 13, and a result output module 14.

[0031] The image acquisition module 11 is used to acquire echocardiogram image data based on the color Doppler imaging method. Among them, color Doppler imaging is conducive to the description of the dynamics of the image. When the echocardiogram image analysis system 1 determines the marked points, the marked points can be displayed dynamically one by one based on the flow direction of the corresponding points in the blood flow.

[0032] The feature extraction module 12 is used to extract features from the echocardiogram image data, and respectively mark n points of the cardiac blood flow based on the extracted features to obtain n marked blood flow points, where n is a positive integer greater than 1.

[0033] Exemplarily, the marked blood flow points are the points selected by artificial or the system in the blood flow area of the echocardiogram image data. Information such as trailing shadows, contour clarity, and brightness shown by the marked blood flow points in the echocardiogram image data can be applied to the recognition of the blood flow motion state at the marked blood flow points. In this application, the feature extraction module 12 extracts the corresponding information of the echocardiogram image data, and the extracted features can be used by the system as feature information related to the motion state of the marked blood flow points, and then applied to the analysis of blood flow direction and blood flow velocity.

[0034] The intelligent algorithm module 13 is used to respectively use each marked blood flow point among the n marked blood flow points as the target marked blood flow point, and execute the following steps 1 to step 3.

[0035] Step 1, for adjacent image frames of the echocardiogram image data, based on the feature information corresponding to the target marked blood flow point in the previous image frame of the adjacent image frames, determine the Kasman compensation value Ks.

[0036] Step 2, based on the Kasman compensation value Ks, determine the corrected feature information corresponding to the target marked blood flow point in the subsequent image frame of the adjacent image frames through the following formula:

[0037] T z =ST z-1 +Ks*(ST z -ST z-1 )

[0038] Among them, Ks represents the Kasman compensation value, z represents the subsequent image frame in the adjacent image frames, z - 1 represents the previous image frame in the adjacent image frames, ST z represents the feature information corresponding to the target marked blood flow point in the subsequent image frame of the adjacent image frames, ST z-1 represents the feature information corresponding to the target marked blood flow point in the previous image frame of the adjacent image frames, Tz Represents the corrected feature information corresponding to the target marked blood flow point in the subsequent image frame among adjacent image frames.

[0039] Step 3: Based on the corrected feature information corresponding to the target marked blood flow point in the subsequent image frame among adjacent image frames, determine the position information and flow velocity information of the target marked blood flow point in the subsequent image frame.

[0040] For example, for the first marked blood flow point, the intelligent algorithm module 13 executes steps 1 to 3,..., until for the nth marked blood flow point, the intelligent algorithm module 13 executes steps 1 to 3.

[0041] In this application, the Kasman compensation value Ks is used to predict and correct errors in the feature information. Exemplarily, the intelligent algorithm module 13 can perform error simulation through a pre-trained network for error correction. Specifically, the first sub-network of the pre-trained network simulates the image data process error generated in the current frame of image data, and at the same time, the intelligent algorithm module 13 obtains the motion prediction error of the target marked blood flow point in the previous frame of image data obtained by the second sub-network of the pre-trained network during the error fitting of the previous frame. On this basis, the second sub-network of the pre-trained network fits the image data process error of the current frame and the motion prediction error of the previous frame to obtain the motion prediction error of the target marked blood flow point in the current frame. The calculation of the second sub-network can be represented by the formula X = Bf_X + Q, where X represents the motion prediction error of the target marked blood flow point in the current frame of image data, Last_X represents the motion prediction error of the target marked blood flow point in the previous frame of image data, and Q represents the image data process error of the current frame of image data simulated by the first sub-network. In addition, when the current frame of image data is the first frame of echocardiogram image data, Bf_X is set to a default value, and the default value is related to the age, gender, and body mass index (Ballistic Missile Intercept, BMI) of the person being measured, and is configured to have a corresponding relationship with the age, gender, and body mass index. For example, under age A, gender B, and body mass index C, the default value is D corresponding to A, B, and C respectively.

[0042] The result output module 14 is used to respectively output and display the position information and flow velocity information for the marked blood flow points corresponding to each of the n points of each image frame in the echocardiogram image data.

[0043] In this application, the intelligent algorithm module 13 performs position feature recognition based on the corrected feature information corresponding to the target marked blood flow point in the subsequent image frame among adjacent image frames, and then obtains the position information of the target marked blood flow point in the subsequent image frame.

[0044] In this application, the intelligent algorithm module 13 uses the formula Determine the flow velocity information of the target marked blood flow point in the subsequent image frame.

[0045] Wherein, Y represents the flow velocity information of the target marked blood flow point in the subsequent image frame, a represents the acceleration information of the target marked blood flow point in the subsequent image frame, λ represents the frame interval between adjacent image frames, φ represents the correction coefficient, and the correction coefficient is determined based on the target area where the marked point is located in multiple different areas. The multiple different areas correspond one-to-one to multiple different parts of the heart in the echocardiogram image. For example, the correction coefficient of the left ventricle is φ1, and the correction coefficient of the right ventricle is φ2.

[0046] Exemplarily, the intelligent algorithm module 13 can determine the correction coefficient in the following manner. For example, determine the first position area where the target marked blood flow point is currently located in the subsequent image frame, and obtain the second position area of the marked point. The second position area is the position area where the marked point was located before entering the first position area. For example, when the blood flows from the right atrium into the right ventricle, when the first position area is the right ventricle, the second position area is the right atrium. Further, there is a pre-configured correspondence relationship among the first position area, the second position area, and the correction coefficient. When the intelligent algorithm module 13 determines the first position area and the second position area, the correction coefficient corresponding to the first position area and the second position area of the corresponding marked point can be determined based on the correspondence relationship among the first position area, the second position area, and the correction coefficient.

[0047] In this application, the intelligent algorithm module 13 uses the formula to determine the acceleration information of the target marked blood flow point in the subsequent image frame. Wherein, a represents the acceleration of the target marked blood flow point, γ represents the compensation coefficient corresponding to the area where the target marked blood flow point is located, ld represents the first marked blood flow point in the echocardiogram image that is in the same area as the target marked blood flow point and is located at the lower left position of the target marked blood flow point, ru represents the second marked blood flow point in the echocardiogram image that is in the same area as the target marked blood flow point and is located at the upper right position of the target marked blood flow point, rd represents the third marked blood flow point in the echocardiogram image that is in the same area as the target marked blood flow point and is located at the lower right position of the target marked blood flow point, lu represents the fourth marked blood flow point in the echocardiogram image that is in the same area as the target marked blood flow point and is located at the upper left position of the target marked blood flow point, flld is the flow coordinate of the first marked point in the echocardiogram image, flru is the flow coordinate of the second marked point in the echocardiogram image, flrd is the flow coordinate of the third marked point in the echocardiogram image, fllu is the flow coordinate of the fourth marked point in the echocardiogram image, Lldru represents the distance between the first marked blood flow point and the second marked blood flow point in the echocardiogram image, and Lrdlu represents the distance between the third marked blood flow point and the fourth marked blood flow point in the echocardiogram image.

[0048] Among them, the addition method of the flow direction is the modulus value of the vector sum. For example, first perform vector addition on flld and flru, and then calculate the modulus value of the vector sum.

[0049] Among them, it can be understood that the echocardiogram image data is two-dimensional image data. This application is based on the three-dimensional characteristics of the heart structure, simulates the blood flow direction in the two-dimensional plane based on the relationship between points, and then determines the acceleration of the target marked blood point in the two-dimensional plane through the two-dimensional relationship between points. It is a method that can determine the acceleration of the marked point based on the flow directions of multiple points in a specific area.

[0050] Generally, since the blood flow velocity in the heart will increase or decrease sharply based on the heart beating rhythm, therefore, in the traditional method, the method of estimating the blood flow point velocity based on the position information of the previous and next frames (the method of determining velocity based on displacement) is very likely to have a large error at a certain time point, which will cause difficulties in the analysis of echocardiogram images. In this application, the intelligent algorithm module 13 utilizes the three-dimensional characteristics of the heart structure to perform point fitting in the two-dimensional plane, and can obtain high-precision acceleration information, improving the problem of large monitoring errors of acceleration information caused by excessive monitoring requirements in the time dimension. Furthermore, it realizes the acceleration monitoring of specific points in the heart blood, and can provide high-precision blood flow velocity information at the same time.

[0051] Figure 2 Shows a block diagram of an image acquisition module 11, as Figure 2 shown, the image acquisition module 11 includes an echocardiogram device interface 111 and a data acquisition module 112.

[0052] The echocardiogram device interface 111 is used for data communication with the echocardiogram device.

[0053] The data acquisition module 112 is used for acquiring the image data in the echocardiogram device.

[0054] Figure 3 Shows a block diagram of a feature extraction module 12, as Figure 3 shown, the feature extraction module 12 includes an edge detection module 121 and, the edge detection module 121.

[0055] The edge detection module 121 is used for detecting the edge features in the echocardiogram image.

[0056] The region feature extraction module 122 is used for extracting the region features from the echocardiogram image.

[0057] Figure 4 Shows a block diagram of an intelligent algorithm module 13, as Figure 4 shown, the intelligent algorithm module 13 includes a model training module 131 and a model updating module 132.

[0058] The model training module 131 is used to train and optimize the Casman compensation value Ks.

[0059] The model update module 132 is used to update and optimize the Casman compensation value Ks based on the manual annotation made on the output result of the result output module.

[0060] Figure 5 A block diagram of a result output module 14 is shown, as Figure 5 shown, the result output module includes a classification result output module 141 and an analysis report generation module 142.

[0061] The classification result output module 141 is used to output the classification result of the marked blood flow points in the echocardiogram image.

[0062] The analysis report generation module 142 is used to generate and output an echocardiogram image analysis report based on the position information and the flow velocity information.

[0063] In this application, the result output module 14 supports multiple output methods, including print output, electronic document output, and online display, etc. Among them, taking the online display as an example, it can display the complete dynamic structure of the heart, and based on the system's self-selection or manual selection of marked blood flow points, dynamically display the dynamic changes of the heart, and at the same time display the movement of the marked blood flow points in the blood flow (such as flowing from the left ventricle into the artery).

[0064] Although the operations are described in a specific order in the drawings, it should not be understood as requiring these operations to be performed in the specific order shown or in a serial order, or requiring all the operations shown to obtain the desired result. In certain environments, multitasking and parallel processing may be advantageous.

[0065] The methods and apparatuses of this application can be accomplished using standard programming techniques, implementing various method steps using rule-based logic or other logics. It should also be noted that the terms "apparatus" and "module" used herein and in the claims are intended to include implementations using one or more lines of software code and / or hardware implementations and / or devices for receiving inputs.

[0066] Any of the steps, operations, or procedures described herein can be performed or implemented using one or more hardware or software modules alone or in combination with other devices. In one embodiment, the software module is implemented using a computer program product including a computer-readable medium containing computer program code, which can be executed by a computer processor to perform any or all of the described steps, operations, or procedures.

[0067] For purposes of illustration and description, the foregoing description of the implementation of the present application has been given. The foregoing description is not exhaustive nor is it intended to limit the present application to the exact forms disclosed, and various variations and modifications are possible in light of the above teachings, or may be obtained from practice of the present application. These embodiments are chosen and described in order to illustrate the principles of the present application and its practical application, so that those skilled in the art can utilize the present application in various embodiments and various modifications suitable for the particular purposes contemplated.

[0068] Regarding the devices in the above embodiments, the specific manner in which each module performs operations has been described in detail in the embodiments related to the method, and will not be elaborated here.

[0069] It can be further understood that, unless otherwise specified, "connection" includes direct connection between two parties without other components therebetween, and also includes indirect connection between two parties with other elements therebetween.

[0070] It can be further understood that although the operations are described in a specific order in the drawings in the embodiments of the present application, it should not be construed as requiring the operations to be performed in the specific order shown or in a serial order, or requiring all the operations shown to obtain the desired result. In certain environments, multitasking and parallel processing may be advantageous.

[0071] Those skilled in the art will readily conceive of other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of the present application and include known common general knowledge or conventional technical means in the art not disclosed in the present application. The specification and embodiments are only to be considered as exemplary, and the true scope and spirit of the present application are pointed out by the following claims.

[0072] It should be understood that the present application is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present application is only limited by the appended claims.

[0073] The above embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An echocardiogram image analysis system based on intelligent algorithms, comprising: An image acquisition module, configured to acquire echocardiogram image data based on color Doppler imaging; A feature extraction module, configured to extract features from the echocardiogram image data, and respectively perform point marking on n points of the cardiac blood flow based on the extracted features to obtain n marked blood flow points, where n is a positive integer greater than 1; An intelligent algorithm module, configured to respectively use each of the n marked blood flow points as a target marked blood flow point and perform the following steps: For adjacent image frames of the echocardiogram image data, determine the Kasman compensation value Ks based on the feature information corresponding to the target marked blood flow point in the previous image frame of the adjacent image frames; Based on the Kasman compensation value Ks, determine the corrected feature information corresponding to the target marked blood flow point in the subsequent image frame of the adjacent image frames through the following formula: Among them, Ks represents the Casman compensation value, z represents the subsequent image frame in adjacent image frames, z - 1 represents the previous image frame in adjacent image frames, ST z represents the feature information corresponding to the target - marked blood - flow point in the subsequent image frame of adjacent image frames, ST z-1 represents the feature information corresponding to the target - marked blood - flow point in the previous image frame of adjacent image frames, T z represents the corrected feature information corresponding to the target - marked blood - flow point in the subsequent image frame of adjacent image frames; Based on the corrected feature information corresponding to the target marked blood flow point in the subsequent image frame of the adjacent image frames, determine the position information and flow velocity information of the target marked blood flow point in the subsequent image frame; A result output module, configured to respectively output and display the position information and flow velocity information for the marked blood flow points corresponding to the n points of each image frame in the echocardiogram image data; Wherein, the intelligent algorithm module determines the position information of the target marked blood flow point in the subsequent image frame in the following manner: Perform position feature recognition based on the corrected feature information corresponding to the target marked blood flow point in the subsequent image frame of the adjacent image frames to obtain the position information of the target marked blood flow point in the subsequent image frame; Wherein, the intelligent algorithm module determines the flow velocity information of the target marked blood flow point in the subsequent image frame through the following formula: Wherein, Y represents the flow velocity information of the target marked blood flow point in the subsequent image frame, a represents the acceleration information of the target marked blood flow point in the subsequent image frame, λ represents the frame interval of the adjacent image frames, φ represents a correction coefficient, and the correction coefficient is determined based on the target area where the marked point is located in multiple different areas, and the multiple different areas correspond one-to-one to multiple different parts of the heart in the echocardiogram image; Wherein, the intelligent algorithm module determines the acceleration information of the target marked blood flow point in the subsequent image frame through the following formula: Wherein, a represents the acceleration of the target marked blood flow point, γ represents the compensation coefficient corresponding to the area where the target marked blood flow point is located, ld represents the first marked blood flow point in the echocardiogram image that is in the same area as the target marked blood flow point and is located at the lower left position of the target marked blood flow point, ru represents the second marked blood flow point in the echocardiogram image that is in the same area as the target marked blood flow point and is located at the upper right position of the target marked blood flow point, rd represents the third marked blood flow point in the echocardiogram image that is in the same area as the target marked blood flow point and is located at the lower right position of the target marked blood flow point, lu represents the fourth marked blood flow point in the echocardiogram image that is in the same area as the target marked blood flow point and is located at the upper left position of the target marked blood flow point, flld is the flow coordinate of the first marked point in the echocardiogram image, flru is the flow coordinate of the second marked point in the echocardiogram image, flrd is the flow coordinate of the third marked point in the echocardiogram image, fllu is the flow coordinate of the fourth marked point in the echocardiogram image, Lldru represents the distance between the first marked blood flow point and the second marked blood flow point in the echocardiogram image, and Lrdlu represents the distance between the third marked blood flow point and the fourth marked blood flow point in the echocardiogram image.

2. The system according to claim 1, wherein The feature extraction module includes: An edge detection module for detecting edge features in the echocardiogram image; A region feature extraction module for extracting region features from the echocardiogram image.

3. The system according to claim 1, wherein The result output module includes: A classification result output module for outputting the classification result of the marked blood flow points in the echocardiogram image; An analysis report generation module for generating and outputting an echocardiogram image analysis report based on the position information and the flow velocity information.

4. The system according to claim 1, wherein, The image acquisition module includes: An echocardiogram device interface for performing data communication with the echocardiogram device; A data acquisition module for acquiring image data in the echocardiogram device.

5. The system according to claim 1, wherein The result output module supports multiple output methods, including print output, electronic document output, and online display.

6. The system according to claim 1, characterized in that, Intelligent algorithm module: A model training module for training and optimizing the Casman compensation value Ks; A model update module for updating and optimizing the Casman compensation value Ks based on the manual annotation made on the output result of the result output module.

Images