Ventricular septal defect detection method and device based on echocardiogram

By automatically detecting and quantifying ventricular septal defects in echocardiography using section classification models and quantizers, the problem of low accuracy of echocardiography detection is solved, the accuracy and efficiency of diagnosis is improved, the process is simplified, and the detection is improved reliability and popularity.

CN118982503APending Publication Date: 2024-11-19GENERAL HOSPITAL OF PLA
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202410988783.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-23
Publication Date
2024-11-19

AI Technical Summary

Technical Problem

The existing echocardiography has problems such as low accuracy in ventricular septal defect detection, requiring rich experience and skills, differences in interpretation, inaccurate positioning and complex evaluation processes, which makes it difficult to ensure diagnostic efficiency and consistency.

Method used

By obtaining ultrasound data monitored by heart function, using a preset section classification model to automatically screen multiple sections, and using a ventricular septal defect detector and quantizer to detect and quantify ventricular septal defects, automatically generate an ultrasound detection report, and recommend treatment methods.

Benefits of technology

It improves the accuracy and ultrasound diagnosis efficiency of ventricular septal defect diagnosis, simplifies the detection process, and improves the reliability and popularity of the diagnosis.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118982503A_ABST
    Figure CN118982503A_ABST
Patent Text Reader

Abstract

The embodiment of the invention discloses a ventricular septal defect detection method and device based on echocardiography, and the method comprises the steps: obtaining the ultrasonic data of cardiac function monitoring, and detecting a plurality of sections from the ultrasonic data through a preset section classification model; and aiming at each section, using a ventricular septal defect detector to detect whether ventricular septal defect exists, and using a ventricular septal defect quantizer to obtain ventricular septal defect quantized data. By means of the mode, the accuracy of ventricular septal defect diagnosis can be improved, and the ultrasonic diagnosis efficiency and the popularization degree can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of medical image recognition, and in particular to a method and device for detecting ventricular septal defect based on echocardiography. Background Art

[0002] Ventricular septal defect (VSD) is the most common congenital heart disease, accounting for about 40% of the overall incidence. Long-term left-to-right shunting of blood caused by VSD can induce symptoms such as ventricular volume overload and dysfunction, pulmonary hypertension, arrhythmia and heart failure. Therefore, early detection of VSD and timely intervention are key measures to improve patient prognosis.

[0003] At present, echocardiography is the most commonly used non-invasive imaging method for screening VSD. Whether in early screening of VSD, routine cardiac function monitoring during hospitalization after VSD repair, or providing prognostic information during follow-up, ultrasound examination plays an irreplaceable basic role. Echocardiography can not only detect the diameter, shape and position of the defect, but also measure the degree, pressure and direction of shunt, as well as changes in the size and function of the cardiac chamber, so as to comprehensively evaluate the severity of VSD. However, the realization of these tasks often requires doctors to have rich experience and skilled skills, which undoubtedly poses certain challenges to the current increasingly tight allocation of medical resources. The interpretation of imaging results may also have differences between observers, resulting in problems such as inaccurate manual positioning, cumbersome manual annotation, and complex evaluation process, making it difficult to ensure the accuracy and consistency of the examination. Therefore, in the current environment of increasingly tight medical resources, emerging technologies are urgently needed to be invested in the field of medical imaging to further improve the diagnostic efficiency and popularity of ultrasound. Summary of the invention

[0004] In view of the above problems, an embodiment of the present invention provides a method and device for detecting ventricular septal defect based on echocardiography, which overcomes the problem of low detection accuracy.

[0005] According to one aspect of an embodiment of the present invention, a ventricular septal defect detection method based on echocardiography is provided, the method comprising: acquiring ultrasound data for cardiac function monitoring, detecting multiple slices from the ultrasound data using a preset slice classification model; for each of the slices, applying a ventricular septal defect detector to detect whether a ventricular septal defect exists, and applying a ventricular septal defect quantifier to obtain ventricular septal defect quantification data.

[0006] In an optional manner, the detecting of multiple sections from the ultrasound data by using a preset section classification model includes: applying a preset section classification model to automatically screen out multiple sections required for ventricular septal defect detection from the ultrasound data, including the apical four-chamber view, the parasternal long-axis view, and the parasternal short-axis view.

[0007] In an optional manner, the use of a ventricular septal defect quantifier to obtain ventricular septal defect quantification data includes: using the ventricular septal defect quantifier to determine the boundary position of the ventricular septal defect in each section frame by frame; and obtaining the ventricular septal defect quantification data based on the boundary position.

[0008] In an optional manner, the use of a ventricular septal defect quantizer to determine the boundary position of the ventricular septal defect in each section frame by frame includes: using the ventricular septal defect quantizer to automatically locate the intersection of blood flow and tissue echo in each section frame by frame; using the ventricular septal defect quantizer to automatically locate the root of the atrioventricular valve in the apical four-chamber heart section frame by frame; using the ventricular septal defect quantizer to automatically locate the root of the aortic valve in the parasternal long axis section frame by frame.

[0009] Optionally, the obtaining of quantitative data of ventricular septal defect based on the boundary position includes: determining the diameter of the ventricular septal defect in each section according to the intersection of blood flow and tissue echo; determining the first stump tissue size in the apical four-chamber heart section according to the intersection of blood flow and tissue echo and the root of the atrioventricular valve; determining the second stump tissue size in the parasternal long axis section according to the intersection of blood flow and tissue echo and the root of the aortic valve.

[0010] Optionally, after the ventricular septal defect quantifier is used to obtain the ventricular septal defect quantitative data, an ultrasound detection report is automatically generated based on the quantitative data of each section to obtain recommended treatment measures, including: performing frame-by-frame comparative analysis between the quantitative data of each section and standard reference data; and obtaining recommended treatment measures based on the results of the frame-by-frame comparative analysis.

[0011] Optionally, obtaining the recommended treatment method based on the frame-by-frame comparative analysis results includes: if the ventricular septal defect diameter, the first stump tissue size and the second stump tissue size of multiple sections determined according to the frame-by-frame comparative analysis results meet preset conditions, interventional closure treatment is recommended, otherwise surgical operation is recommended; wherein the preset conditions include: the ventricular septal defect diameter is less than or equal to the reference diameter, the first stump tissue size detected according to the apical four-chamber heart view is greater than or equal to the first reference distance, and the first stump tissue size detected according to the parasternal long axis view is greater than or equal to the second reference distance; and automatically generating an ultrasound detection report based on the frame-by-frame comparative analysis results and the recommended treatment method.

[0012] Based on the same inventive concept, a ventricular septal defect detection device based on echocardiography is provided, including: a section classification unit, used to obtain ultrasound data for cardiac function monitoring, and detect multiple sections from the ultrasound data through a preset section classification model; a defect detection unit, used to apply a ventricular septal defect detector to detect whether a ventricular septal defect exists for each of the sections, and apply a ventricular septal defect quantifier to obtain ventricular septal defect quantification data.

[0013] Based on the same inventive concept, an embodiment of the present invention further proposes an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the aforementioned method when executing the program.

[0014] Based on the same inventive concept, an embodiment of the present invention further proposes a computer storage medium, in which at least one executable instruction is stored, and the executable instruction enables a processor to execute the aforementioned method.

[0015] The embodiment of the present invention acquires ultrasound data for cardiac function monitoring, and detects multiple slices from the ultrasound data using a preset slice classification model; for each slice, a ventricular septal defect detector is used to detect whether a ventricular septal defect exists, and a ventricular septal defect quantifier is used to obtain ventricular septal defect quantification data, thereby improving the accuracy of ventricular septal defect diagnosis and improving the diagnostic efficiency and popularity of ultrasound.

[0016] The above description is only an overview of the technical solution of the embodiment of the present invention. In order to more clearly understand the technical means of the embodiment of the present invention, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the embodiment of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] 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. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0018] Figure 1 A schematic diagram of a process of detecting ventricular septal defect (VSD) based on echocardiography according to an embodiment of the present invention is shown;

[0019] Figure 2 A schematic diagram of the process of a ventricular septal defect detection method based on echocardiography provided by an embodiment of the present invention is shown;

[0020] Figure 3 A schematic cross-sectional view of an echocardiogram according to an embodiment of the present invention is shown;

[0021] Figure 4 A schematic diagram showing a broken line presentation of a ventricular septal defect result corresponding to the A4C section according to an embodiment of the present invention is shown;

[0022] Figure 5 A schematic diagram showing a broken line presentation of a ventricular septal defect result corresponding to a PLAX section provided in an embodiment of the present invention is shown;

[0023] Figure 6 A schematic diagram showing a broken line presentation of a ventricular septal defect result corresponding to a PSAX section provided in an embodiment of the present invention is shown;

[0024] Figure 7 A schematic structural diagram of a ventricular septal defect detection device based on echocardiography provided in an embodiment of the present invention is shown;

[0025] Figure 8 A schematic diagram of an electronic device in an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0026] The exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the 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 enable the scope of the present invention to be fully communicated to those skilled in the art.

[0027] The process of detecting ventricular septal defect (VSD) based on echocardiography in the embodiment of the present invention is as follows: Figure 1 As shown in the figure, ultrasound data was screened from the echocardiography database, and the three sections, namely the apical four-chamber view (A4C), the parasternal long axis view (PLAX), and the parasternal short axis view (PSAX), were automatically screened using the section classification model. The VSD detector was used to detect the presence of VSD in each section, and then the VSD quantifier was used to quantify the ventricular septal defect, and an ultrasound report was automatically generated. The ultrasound report contained at least the following information: the diagnosis of the presence of ventricular septal defect, the defect range and stump size in each section, and the recommended treatment.

[0028] Figure 2 FIG. 2 is a flow chart of a method for detecting ventricular septal defect based on echocardiography provided by an embodiment of the present invention. Figure 2 As shown, the ventricular septal defect detection method based on echocardiography includes:

[0029] Step S11: Acquire ultrasound data for cardiac function monitoring, and detect multiple sections from the ultrasound data using a preset section classification model.

[0030] With the improvement of medical databases and the substantial increase in the computing power of smart chips, deep learning algorithms have demonstrated powerful image data processing capabilities. With the advantages of accuracy, objectivity and repeatability, the potential of deep learning algorithms in ultrasound diagnosis has gradually attracted the attention of many researchers.

[0031] In an embodiment of the present invention, ultrasound data of cardiac function monitoring of the heart to be detected is obtained from an ultrasound database. A section classification model is constructed using Xception Net, and a preset section classification model is applied to automatically screen out multiple sections required for ventricular septal defect detection from the ultrasound data, including the apical four-chamber view (A4C), the parasternal long axis view (PLAX), and the parasternal short axis view (PSAX).

[0032] Step S12: for each of the sections, a ventricular septal defect detector is used to detect whether a ventricular septal defect exists, and a ventricular septal defect quantifier is used to obtain ventricular septal defect quantitative data.

[0033] In the embodiment of the present invention, for each section screened in step S11, a ventricular septal defect detector is applied to detect whether there is a ventricular septal defect in each section. The ventricular septal defect detector is constructed using an existing deep residual network (ResNet).

[0034] The embodiment of the present invention also uses a ventricular septal defect quantizer to determine the boundary position of the ventricular septal defect in each section frame by frame; and obtains ventricular septal defect quantization data based on the boundary position. Optionally, the ventricular septal defect quantizer is used to automatically locate the intersection of blood flow and tissue echo in each section frame by frame; the ventricular septal defect quantizer is used to automatically locate the root of the atrioventricular valve in the apical four-chamber heart section frame by frame; the ventricular septal defect quantizer is used to automatically locate the root of the aortic valve in the parasternal long axis section frame by frame. The ventricular septal defect (VSD) quantizer is constructed using the existing U-Net. As Figure 3 The echocardiographic cross section in Figure 3 A is the A4C section. Figure 3 B is the PLAX section. Figure 3 C is the PSAX section. The color flow width detected on the color Doppler ultrasound image is used as the diameter of the ventricular septal defect (solid white line), which is calculated by the model automatically locating the intersection of blood flow and tissue echo (white star-shaped point). In the A4C section, the model automatically locates the root of the atrioventricular valve (gray square dot) and measures the distance from it to the intersection of blood flow as the size of the stump tissue (dashed line); in the PLAX section, the model automatically locates the root of the aortic valve (gray square dot) and measures the distance from it to the intersection of blood flow as the size of the stump tissue (gray line); in the PSAX section, the model only measures the diameter of the ventricular septal defect.

[0035] After determining the boundary position of the ventricular septal defect in each section, the diameter of the ventricular septal defect in each section is determined according to the intersection of blood flow and tissue echo; the first stump tissue size in the apical four-chamber heart section is determined according to the intersection of blood flow and tissue echo and the root of the atrioventricular valve; the second stump tissue size in the parasternal long axis section is determined according to the intersection of blood flow and tissue echo and the root of the aortic valve.

[0036] The defect diameter and stump size automatically measured by the VSD quantitative model in multiple sections are compared and analyzed frame by frame with the defect diameter and stump size annotated by medical experts. Figure 4-Figure 6 The results of the model's frame-by-frame analysis of ventricular septal defects are presented in the form of a line graph, where the horizontal axis represents the number of frames and the vertical axis represents pixels. septum_pred is the stump size, septum_label is the standard stump size, vsd_pred is the defect diameter, and vsd_label is the standard defect diameter. The standard stump size and standard defect diameter are the stump size and defect diameter marked by medical experts, respectively. Figure 4 The polyline in Figure 3 A is an echocardiographic cross-sectional view of ventricular septal defect, where Figure 4 a is the residual size result, Figure 4 b is the defect diameter result, Figure 5 The polyline in Figure 3 B shows the ventricular septal defect in the echocardiographic cross section. Figure 5 a is the residual size result, Figure 5 b is the defect diameter result, Figure 6 The polyline in Figure 3 The ventricular septal defect result of the echocardiogram section C. The embodiment of the present invention can obtain the maximum value of the stump size and the defect diameter in multiple frames of echocardiograms, and compare the maximum value with the corresponding standard value. If it is within the preset range of the standard value, the ventricular septal defect is within the normal range.

[0037] In an embodiment of the present invention, after step S12, an ultrasound detection report is automatically generated according to the quantitative data of each section, and a recommended treatment method is obtained. Optionally, a frame-by-frame comparison and analysis is performed based on the quantitative data of each section and the standard reference data; an ultrasound detection report is generated based on the frame-by-frame comparison and analysis results, and a recommended treatment method is obtained at the same time. If the ventricular septal defect diameter, the first stump tissue size, and the second stump tissue size of multiple sections are determined to meet the preset conditions according to the frame-by-frame comparison and analysis results, interventional occlusion treatment is recommended, otherwise surgical operation is recommended; wherein the preset conditions include: the ventricular septal defect diameter is less than or equal to the reference diameter, the first stump tissue size detected according to the apical four-chamber heart section is greater than or equal to the first reference distance, and the first stump tissue size detected according to the parasternal long axis section is greater than or equal to the second reference distance; an ultrasound detection report is automatically generated based on the frame-by-frame comparison and analysis results and the recommended treatment method. The reference diameter, the first reference distance, and the second reference distance can be set according to the stump size and defect diameter marked by medical experts, and the specific values ​​are not limited here. Preferably, they can be 14mm, 2mm, and 2mm respectively.

[0038] In this way, an ultrasound report is automatically generated based on the frame-by-frame comparative analysis results, and treatment methods are intelligently recommended based on the quantitative analysis results combined with the requirements of the percutaneous interventional treatment guidelines for common congenital heart disease. If the following preset conditions are met, the patient is recommended for interventional occlusion treatment: (1) On multiple sections ( Figure 3-Figure 6 ), the diameter of the ventricular septal defect measured by the model is ≤14mm, (2) on the A4C section ( Figure 3 A and Figure 4 ), the distance between the posterior edge of VSD and the tricuspid valve (the size of the first stump tissue) is ≥ 2 mm, (3) on the PLAX section ( Figure 3 B and Figure 5 ), the distance between the upper edge of VSD and the aortic valve (the size of the stump tissue) is ≥ 2 mm. Otherwise, surgical operation is recommended.

[0039] The echocardiography-based ventricular septal defect detection method of the embodiment of the present invention can accurately and reliably diagnose ventricular septal defect by performing section screening, disease detection and quantitative evaluation, improve the efficiency of the current clinical diagnostic process, and promote the development of precise management of ventricular septal defect patients.

[0040] In summary, the ventricular septal defect detection method based on echocardiography in the embodiment of the present invention obtains ultrasonic data for cardiac function monitoring, and detects multiple slices from the ultrasonic data through a preset slice classification model; for each of the slices, a ventricular septal defect detector is used to detect whether a ventricular septal defect exists, and a ventricular septal defect quantifier is used to obtain ventricular septal defect quantification data, which can improve the accuracy of ventricular septal defect diagnosis and improve the diagnostic efficiency and popularity of ultrasound.

[0041] The above specific embodiments of the present invention are described. In some cases, the actions or steps recorded in the embodiments of the present invention can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0042] Based on the same concept, the embodiment of the present invention also provides a ventricular septal defect detection device based on echocardiography. Applied to a server. Figure 7 As shown, the ventricular septal defect detection based on echocardiography includes: a section classification unit and a defect detection unit. Among them,

[0043] A section classification unit, used to obtain ultrasound data for cardiac function monitoring, and detect multiple sections from the ultrasound data using a preset section classification model;

[0044] The defect detection unit is used to detect whether there is a ventricular septal defect for each of the sections using a ventricular septal defect detector, and to obtain ventricular septal defect quantification data using a ventricular septal defect quantifier.

[0045] For the convenience of description, the above device is described as various modules according to their functions. Of course, when implementing the embodiment of the present invention, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0046] The device of the above embodiment is applied to the corresponding method in the above embodiment, and has the beneficial effects of the corresponding method embodiment, which will not be described in detail here.

[0047] Based on the same inventive concept, an embodiment of the present invention further provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method described in any one of the above embodiments is implemented.

[0048] An embodiment of the present invention provides a non-volatile computer storage medium, wherein the computer storage medium stores at least one executable instruction, and the computer executable instruction can execute the method described in any of the above embodiments.

[0049] Figure 8 A more specific schematic diagram of the hardware structure of an electronic device provided in this embodiment is shown, and the device may include: a processor 801, a memory 802, an input / output interface 803, a communication interface 804, and a bus 805. The processor 801, the memory 802, the input / output interface 803, and the communication interface 804 are connected to each other in communication within the device through the bus 805.

[0050] The processor 801 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solution provided by the method embodiment of the present invention.

[0051] The memory 802 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 802 can store an operating system and other application programs. When the technical solution provided by the method embodiment of the present invention is implemented by software or firmware, the relevant program code is stored in the memory 802 and called and executed by the processor 801.

[0052] The input / output interface 803 is used to connect the input / output module to realize information input and output. The input / output module can be configured in the device as a component (not shown in the figure), or it can be externally connected to the device to provide corresponding functions. The input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0053] The communication interface 804 is used to connect a communication module (not shown) to realize communication interaction between the device and other devices. The communication module can realize communication through wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WIFI, Bluetooth, etc.).

[0054] The bus 805 includes a path to transmit information between various components of the device (eg, the processor 801 , the memory 802 , the input / output interface 803 , and the communication interface 804 ).

[0055] It should be noted that, although the above device only shows the processor 801, the memory 802, the input / output interface 803, the communication interface 804 and the bus 805, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include the components necessary for implementing the embodiment of the present invention, and does not necessarily include all the components shown in the figure.

[0056] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present disclosure is limited to these examples. Based on the concept of the present disclosure, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present invention as described above, which are not provided in detail for the sake of simplicity.

[0057] This application is intended to cover all such substitutions, modifications and variations that fall within the broad scope of all embodiments. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present invention should be included in the scope of protection of this disclosure.

Claims

1. A method for detecting ventricular septal defect based on echocardiography, Its characteristics are: The method comprises: Acquire ultrasound data for cardiac function monitoring, and detect multiple sections from the ultrasound data using a preset section classification model; For each of the sections, a ventricular septal defect detector is used to detect whether a ventricular septal defect exists, and a ventricular septal defect quantifier is used to obtain ventricular septal defect quantitative data.

2. The method according to claim 1, It is characterized in that The detecting a plurality of sections from the ultrasound data by using a preset section classification model comprises: A preset section classification model is used to automatically screen out multiple sections required for ventricular septal defect detection from ultrasound data, including the apical four-chamber view, the parasternal long-axis view, and the parasternal short-axis view.

3. The method according to claim 2, It is characterized in that The method of using a ventricular septal defect quantifier to obtain ventricular septal defect quantitative data includes: The ventricular septal defect quantifier was used to determine the border position of the ventricular septal defect in each section frame by frame. The quantitative data of the ventricular septal defect is acquired based on the boundary position.

4. The method according to claim 3, It is characterized in that The method of using a ventricular septal defect quantizer to determine the boundary position of the ventricular septal defect in each section frame by frame includes: The ventricular septal defect quantifier was used to automatically locate the intersection of blood flow and tissue echo in each section frame by frame; Using a ventricular septal defect quantizer to automatically locate the root of the atrioventricular valve in the apical four-chamber heart view frame by frame; The aortic valve root in the parasternal long axis view was automatically located frame by frame using a ventricular septal defect quantifier.

5. The method according to claim 4, It is characterized in that The step of acquiring quantitative data of ventricular septal defect based on the boundary position includes: The diameter of the ventricular septal defect in each section was determined based on the intersection of blood flow and tissue echo; Determining the size of the first stump tissue in the apical four-chamber heart section according to the intersection point of blood flow and tissue echo and the root of the atrioventricular valve; The size of the second stump tissue in the parasternal long-axis section was determined based on the intersection of blood flow and tissue echogenicity and the aortic valve root.

6. The method according to claim 5, It is characterized in that After the ventricular septal defect quantification data is obtained by using the ventricular septal defect quantifier, an ultrasound detection report is automatically generated according to the quantification data of each section to obtain recommended treatment measures, including: Perform frame-by-frame comparative analysis based on the quantitative data of each section and standard reference data; Get recommended treatments based on frame-by-frame comparative analysis results.

7. The method according to claim 6, It is characterized in that The obtaining of the recommended treatment method based on the frame-by-frame comparative analysis results includes: If the ventricular septal defect diameter, the first stump tissue size, and the second stump tissue size of multiple sections are determined to meet preset conditions based on the frame-by-frame comparative analysis results, interventional closure treatment is recommended, otherwise surgical operation is recommended; wherein the preset conditions include: the ventricular septal defect diameter is less than or equal to the reference diameter, the first stump tissue size detected according to the apical four-chamber heart section is greater than or equal to the first reference distance, and the first stump tissue size detected according to the parasternal long axis section is greater than or equal to the second reference distance; Automatically generate ultrasound inspection reports based on frame-by-frame comparative analysis results and recommended treatments.

8. A ventricular septal defect detection device based on echocardiography, Its characteristics are: The device comprises: A section classification unit, used to obtain ultrasound data for cardiac function monitoring, and detect multiple sections from the ultrasound data using a preset section classification model; The defect detection unit is used to detect whether there is a ventricular septal defect for each of the sections using a ventricular septal defect detector, and to obtain ventricular septal defect quantification data using a ventricular septal defect quantifier.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, Its characteristics are: When the processor executes the program, the method according to any one of claims 1 to 7 is implemented.

10. A computer storage medium, Its characteristics are: The storage medium stores at least one executable instruction, and the executable instruction enables the processor to execute the method according to any one of claims 1 to 7.

Citation Information

Cited By

  • Congenital heart disease four-dimensional echocardiogram dynamic segmentation system

    CN120672778A