Heart ultrasound mode switching method, system, medium, product and computer device

Abstract

The application belongs to the technical field of heart ultrasonic detection. A heart ultrasonic mode switching method, system, medium, product and computer equipment are provided. The ultrasonic probe is prompted and guided according to the B-ultrasonic video stream data in the B-ultrasonic mode, so that the ultrasonic probe moves to the standard section of the heart ultrasonic examination. The switching selection of the color Doppler ultrasound mode and the M-ultrasonic mode is carried out based on the standard section. Through the method of artificial intelligence, the automatic movement adjustment of the ultrasonic probe and the automatic switching between the B-ultrasound, color Doppler ultrasound and M-ultrasound are guided, and the full-process and automation of the heart ultrasonic examination are realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of cardiac ultrasound detection, and in particular to a cardiac ultrasound mode switching method, system, medium, product and computer device. BACKGROUND

[0002] The statements in this section merely provide background technology related to the present application and do not necessarily constitute prior art.

[0003] Cardiac ultrasound examination, as a non-invasive medical examination method, provides a unique perspective for doctors to understand the structure and function of the heart, and plays an irreplaceable role in the diagnosis and treatment monitoring of heart disease. Existing cardiac ultrasound automatic examination technology is mostly guided by deep learning or traditional machine learning methods to realize the automatic acquisition of B-mode (two-dimensional ultrasound) standard sections and downstream segmentation, measurement, classification and other tasks.

[0004] However, the standard examination procedure of cardiac ultrasound in the clinic is not only B-mode, but also color Doppler ultrasound (color Doppler ultrasound) and optional M-mode. B-mode or M-mode can quantitatively measure indicators of the heart and blood vessels and make evaluative descriptions, such as whether the main and pulmonary artery diameters are widened, whether there is a defect in the atrial septum and interventricular septum, whether the valve is adhered or thickened, whether the opening of each valve is limited, whether the echo is enhanced, and whether the shape is normal, etc. Color Doppler ultrasound can make evaluative descriptions through blood flow, such as whether the mitral valve is regurgitated and the degree of regurgitation, etc. At present, the mode switching strategy of B-mode, color Doppler ultrasound and M-mode cannot be realized, which may result in that the patient needs to be detected continuously for multiple times, which not only consumes time but also may delay the illness. SUMMARY

[0005] In order to solve the problems of the prior art, the present application provides a cardiac ultrasound mode switching method, system, medium, product and computer device, and proposes a full-process automatic cardiac ultrasound examination strategy under the guidance of prompts. Through the method of artificial intelligence (including but not limited to deep learning, deep reinforcement learning, etc.), the automatic movement adjustment of the ultrasound probe and the automatic switching between each mode (B-mode, color Doppler ultrasound and M-mode) are guided, and the full-process and automation of cardiac ultrasound examination are realized.

[0006] In order to achieve the above purpose, the present application adopts the following technical scheme:

[0007] In the first aspect, the present application provides a cardiac ultrasound mode switching method.

[0008] A cardiac ultrasound mode switching method, comprising the following processes:

[0009] The B-ultrasound probe is guided according to the B-ultrasound video stream data in the B-ultrasound mode, so that the B-ultrasound probe is moved to a standard section of a heart ultrasound examination.

[0010] After the standard section is obtained, a region of interest is detected, when the region of interest is continuously detected within a set time and the difference between the region of interest detected multiple times is less than a set threshold, it is prompted to switch to the color ultrasound mode, and disease prediction is performed according to the color ultrasound video in the color ultrasound mode, and after the prediction is completed, it is switched to the B-ultrasound mode.

[0011] Whether to start M-ultrasound is judged according to the current standard section index or the disease prediction result, if M-ultrasound is needed, the M-ultrasound mode is entered, and the final diagnosis of the disease is performed according to the M-ultrasound video stream in the M-ultrasound mode, if M-ultrasound is not needed, the B-ultrasound probe is guided according to the current B-ultrasound video stream data to find the next standard section, and the detection of the last standard section is completed.

[0012] As a further limitation of the first aspect of the application, the six-degree-of-freedom prediction algorithm based on deep learning guides the B-ultrasound probe according to the B-ultrasound video stream data, and the six degrees of freedom include the translation direction of the X, Y and Z coordinate axes and the rotation direction of the pitch angle, yaw angle and roll angle of the B-ultrasound probe.

[0013] As a further limitation of the first aspect of the application, the B-ultrasound probe is moved according to the six-degree-of-freedom prediction result, a new B-ultrasound video is obtained, and the six-degree-of-freedom prediction is performed on the new B-ultrasound video, the prediction process is repeated until the six-degree-of-freedom prediction result is that there is no need to move and no need to rotate, and at this time a standard section of the heart ultrasound examination is obtained.

[0014] As a further limitation of the first aspect of the application, disease prediction is performed according to the color ultrasound video in the color ultrasound mode, including:

[0015] The color ultrasound video is analyzed using a deep learning model to generate a prediction result of whether there is a disease and a prediction result of the degree of the disease.

[0016] As a further limitation of the first aspect of the application, when the disease is mitral regurgitation, a mitral valve position frame is selected according to the color ultrasound video frame image, the color ultrasound video frame image corresponding to the mitral valve position frame is used as the input of the deep learning model, and the deep learning model outputs whether there is regurgitation and the degree of regurgitation, the degree of regurgitation including mild, moderate and severe.

[0017] As a further limitation of the first aspect of the application, whether to start M-ultrasound is judged according to the current standard section index or the disease prediction result, including:

[0018] When the disease degree of the disease prediction result is moderate or above, M-ultrasound is directly started; wherein the disease degree includes mild, moderate and severe;

[0019] When one or more of the standard section indicators are abnormal, M-ultrasound is directly started; wherein the abnormality includes that the interventricular septum thickness is greater than a set threshold, and the motion law of the interventricular septum is inconsistent with the standard motion law.

[0020] As a further limitation of the first aspect of the application, the final diagnosis of the disease is made according to the M-ultrasound video stream under the M-ultrasound mode, which includes:

[0021] The line connecting the center point P2 of the region of interest and the vertex P1 is selected as the position of the M-ultrasound sampling line to obtain the continuous waveform video of M-ultrasound, the M-ultrasound indicators are measured according to the continuous waveform video of M-ultrasound, and the final diagnosis of the disease is made according to the M-ultrasound indicators.

[0022] Secondly, the application provides a heart ultrasound mode switching system.

[0023] The heart ultrasound mode switching system includes the following processes:

[0024] The B-ultrasound detection unit is configured to guide the ultrasound probe to move to the standard section of the heart ultrasound examination according to the B-ultrasound video stream data under the B-ultrasound mode.

[0025] The color Doppler ultrasound detection unit is configured to detect the region of interest after obtaining the standard section, and when the region of interest is continuously detected for a set time and the difference between the region of interest detected multiple times is less than a set threshold, it is prompted to switch to the color Doppler ultrasound mode, and disease prediction is performed according to the color Doppler ultrasound video under the color Doppler ultrasound mode, and after the prediction is completed, it is switched to the B-ultrasound mode.

[0026] The M-ultrasound detection unit is configured to determine whether to start M-ultrasound according to the current standard section indicators or disease prediction result, if M-ultrasound needs to be started, it enters the M-ultrasound mode, and the final diagnosis of the disease is made according to the M-ultrasound video stream under the M-ultrasound mode, if M-ultrasound does not need to be started, the ultrasound probe is guided to find the next standard section according to the current B-ultrasound video stream data, and the detection of the last standard section is completed.

[0027] Thirdly, the application provides a heart ultrasound mode switching system, which includes the following processes:

[0028] The B-ultrasound device, the color Doppler ultrasound device, the M-ultrasound device, the first multi-degree-of-freedom machine, the second multi-degree-of-freedom machine, the third multi-degree-of-freedom machine and the control terminal, the B-ultrasound device includes a B-ultrasound probe, the color Doppler ultrasound device includes a color Doppler ultrasound probe, and the M-ultrasound device includes an M-ultrasound probe.

[0029] The B-ultrasound probe is connected with a first multi-degree-of-freedom mechanical arm, the color Doppler ultrasound probe is connected with a second multi-degree-of-freedom mechanical arm, and the M-ultrasound probe is connected with a third multi-degree-of-freedom mechanical arm.

[0030] The B-ultrasound device, the color Doppler ultrasound device, the M-ultrasound device, the first multi-degree-of-freedom mechanical arm, the second multi-degree-of-freedom mechanical arm and the third multi-degree-of-freedom mechanical arm are respectively connected with a control terminal, and the control terminal is configured to execute the cardiac ultrasound mode switching method of the first aspect of the present application.

[0031] In a fourth aspect, the present application provides a computer device, comprising: a processor and a computer readable storage medium.

[0032] The processor is adapted to execute the computer program.

[0033] The computer readable storage medium has a computer program stored therein, and the computer program is executed by the processor to realize the cardiac ultrasound mode switching method of the first aspect of the present application.

[0034] In a fifth aspect, the present application provides a computer readable storage medium, which stores a computer program, and the computer program is adapted to be loaded and executed by a processor to realize the cardiac ultrasound mode switching method of the first aspect of the present application.

[0035] In a sixth aspect, the present application provides a computer program product, which comprises a computer program, and the computer program is executed by a processor to realize the cardiac ultrasound mode switching method of the first aspect of the present application.

[0036] Compared with the prior art, the present application has the following beneficial effects:

[0037] 1. The present application innovatively proposes a cardiac ultrasound mode switching strategy, and proposes a whole-process automatic cardiac ultrasound examination strategy under the guidance of prompting, which realizes the whole-process and automation of cardiac ultrasound examination by the method of artificial intelligence (including but not limited to deep learning, deep reinforcement learning, etc.) to guide the automatic movement adjustment of the ultrasound probe and the automatic switching between modes (B-ultrasound, color Doppler ultrasound and M-ultrasound).

[0038] 2. The present application moves the ultrasound probe according to the six-degree-of-freedom prediction result to obtain a new B-ultrasound video, and then performs six-degree-of-freedom prediction on the new B-ultrasound video, repeatedly performs the prediction process until the result of six-degree-of-freedom prediction is that there is no need to move and rotate, at this time a standard section of cardiac ultrasound examination is obtained, the accurate acquisition of the standard section is realized, and higher-precision B-ultrasound detection is realized.

[0039] 3、The six-degree-of-freedom prediction algorithm based on deep learning of the application, according to the B-ultrasonic video stream data, the six-degree-of-freedom includes the translation direction of X, Y, Z coordinate axis direction and the rotation direction of the pitch angle, yaw angle, roll angle of the ultrasonic probe, the high-precision guidance of the B-ultrasonic probe can be realized without artificial intervention to obtain the first standard section, and the automation degree of detection is improved.

[0040] 4、In the application, after obtaining the standard section, the detection of the region of interest is carried out, the difference between the region of interest continuously detected within the set time and the region of interest detected multiple times is less than the set threshold, the switching to the color ultrasonic mode is prompted, the color ultrasonic detection is carried out on the premise of high-precision region of interest, and the color ultrasonic detection precision is greatly improved.

[0041] 5、In the application, the line connecting the center point P2 and the vertex P1 of the region of interest is selected as the position of the M-super sampling line, the continuous wave video of M-super is obtained, the M-super index is measured according to the continuous wave video of M-super, the final diagnosis of diseases is carried out according to the M-super index, the automatic and high-precision M-super detection is realized, and the whole-process B-ultrasonic, color ultrasonic and M-super detection is realized.

[0042] The advantages of the additional aspects of the application will be partially given in the following description, partially become obvious from the following description, or be known by the practice of the application. BRIEF DESCRIPTION OF DRAWINGS

[0043] The drawings accompanying the specification of the application are used to provide further understanding of the application, the illustrative embodiments of the application and the description thereof are used to explain the application, and do not constitute improper limitation on the application.

[0044] Figure 1 The flowchart of the heart ultrasonic mode switching method provided for embodiment 1 of the application is shown in the figure;

[0045] Figure 2 The initial B-ultrasonic video schematic diagram provided for embodiment 1 of the application is shown in the figure;

[0046] Figure 3 The B-ultrasonic standard section schematic diagram provided for the six-degree-of-freedom prediction and adjustment of the probe in embodiment 1 of the application is shown in the figure;

[0047] Figure 4 The color ultrasonic mode schematic diagram provided for the region of interest in embodiment 1 of the application is shown in the figure;

[0048] Figure 5 The M-super mode schematic diagram provided for embodiment 1 of the application is shown in the figure;

[0049] Figure 6 The sampling line default position schematic diagram provided for embodiment 1 of the application is shown in the figure;

[0050] Figure 7 FIG. 1 is a schematic diagram of a cardiac ultrasound mode switching system according to an embodiment of the present application;

[0051] Figure 8 FIG. 4 is a schematic diagram of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0052] The present application will be further described with reference to the drawings and embodiments.

[0053] It should be noted that the following detailed description is exemplary in nature and is intended to provide further description of the application. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0054] The embodiments in the present application and the features in the embodiments can be combined with each other in the case of no conflict.

[0055] Embodiment 1:

[0056] The present implementation proposes a cardiac ultrasound mode switching method, which guides the automatic movement of the ultrasound probe to adjust the position and the automatic switching between each mode (B-mode, color Doppler, M-mode) by the method of artificial intelligence. Specifically, as shown in FIG. 1, it includes the following steps: Figure 1

[0057] Step 1: Take the B-mode video stream collected by the ultrasound probe in real time as the initial input, as shown in FIG. 2 (the video quality is poor and cannot effectively measure and diagnose the heart). Figure 2

[0058] Step 2: Input the B-mode video stream of the initial input into the B-mode prompt guidance module, and use the six-degree-of-freedom (X, Y, Z coordinate axis direction translation direction and pitch angle, yaw angle, roll angle rotation direction) prediction algorithm based on deep learning for the B-mode video of the initial input.

[0059] For example, a Transformer network with six prediction heads that can implement six prediction tasks can be used to guide the subsequent operation of the ultrasound probe, such as moving upwards and rotating clockwise by 3°, so as to move the ultrasound probe to the first standard section of the cardiac ultrasound examination, as shown in FIG. 3. Figure 3 ​​The process is to move the ultrasound probe according to the prediction result of six degrees of freedom prediction on the B-ultrasound video, so as to obtain a new B-ultrasound video, and then repeat the process until the result of six degrees of freedom prediction is that no further movement or rotation is needed (for example, the prediction result is that the movement / rotation value is all 0), that is, the first standard section of the cardiac ultrasound examination is obtained, and then other index measurement and auxiliary diagnosis tasks are performed, such as whether there is a defect in the atrial septum and the ventricular septum, whether the valve is adhered, thickened, and the like.

[0060] Step 3: After obtaining the first standard section of B-ultrasound, the detection of the region of interest is performed, for example, the diagnosis of mitral regurgitation, and then the position of the mitral valve is detected. Here, the method of target detection (such as Yolo) can be used to detect the position of the mitral valve using a rectangular frame. Since the mitral valve in the video is constantly moving, the largest rectangular frame is selected as the position of the mitral valve.

[0061] Step 4: After continuously and stably (for example, the region of interest is basically unchanged within 2 seconds, that is, the change range of the recognition frame of the region of interest is less than a set threshold) detecting the region of interest such as the mitral valve, it is prompted to switch to the color ultrasound mode, that is, to simulate the operation of the doctor pressing button C, as shown in FIG. 5. Figure 4

[0062] Step 5: The method of deep learning is used to analyze the color ultrasound video, to detect the color ultrasound index and to assist in the diagnosis of heart disease. Taking the detection of mitral regurgitation as an example, the color ultrasound video frame image corresponding to the mitral valve position frame is used as the input of the neural network, and the label is whether there is regurgitation and the degree of regurgitation (mild, moderate, severe) (if the color ultrasound video of the mitral valve position is mainly red, but there is a clear blue area (not pseudo-color) at the connection of the mitral valve, it indicates that there is moderate or even severe mitral regurgitation), and the neural network is used to predict the regurgitation result in the color ultrasound video.

[0063] Step 6: After the color ultrasound measurement and analysis are completed, the color ultrasound is turned off, that is, switched to B-ultrasound, and whether to start M-ultrasound is determined according to the current standard section or the severity of the disease, for example, in the parasternal left ventricular long axis section, the B-ultrasound of the interventricular septum shows abnormal performance such as thickening or irregular movement, and then M-ultrasound is further started for examination, as shown in FIG. 6, to more accurately measure the volume of the heart and the thickness of the ventricular wall. If M-ultrasound needs to be started, step 7 is continued, and if M-ultrasound does not need to be started, step 8 is skipped. Figure 5

[0064] Step 7: According to the position of the region of interest, the position of the M-ultrasound sampling line is prompted and guided. If there is no doctor intervention, the line connecting the center point P2 of the region of interest and the vertex P1 is selected as the position of the M-ultrasound sampling line by default, as shown in FIG. 7. Figure 6 ​​As shown, M super is turned on to obtain continuous wave video of M super, corresponding indicators are measured according to the wave, and the disease is diagnosed according to the indicators.

[0065] Step 8: If it is the last standard section of the heart examination, end, otherwise jump to step 2.

[0066] Embodiment 2

[0067] As Figure 7 As shown, the present implementation provides a heart ultrasound mode switching system, comprising:

[0068] The B-ultrasound detection unit is configured to guide the ultrasound probe according to the B-ultrasound video stream data in the B-ultrasound mode to move to a standard section of the heart ultrasound examination.

[0069] The color Doppler ultrasound detection unit is configured to detect the region of interest after obtaining the standard section, and when the region of interest is continuously detected within a set time and the difference between the region of interest detected multiple times is less than a set threshold, it is prompted to switch to the color Doppler ultrasound mode, and disease prediction is performed according to the color Doppler ultrasound video in the color Doppler ultrasound mode, and after the prediction is completed, it is switched to the B-ultrasound mode.

[0070] The M-ultrasound detection unit is configured to determine whether to turn on M-ultrasound according to the current standard section indicator or disease prediction result, and if M-ultrasound needs to be turned on, it enters the M-ultrasound mode, and performs final diagnosis of the disease according to the M-ultrasound video stream in the M-ultrasound mode, and if M-ultrasound does not need to be turned on, it continues to guide the ultrasound probe according to the current B-ultrasound video stream to find the next standard section until the detection of the last standard section is completed.

[0071] The specific working process of each unit is described in Embodiment 1, which will not be repeated here.

[0072] It can be understood that the above-mentioned units can be combined into one or several other units respectively or entirely, or some of the units can be further divided into a plurality of units with smaller functions to constitute, which can achieve the same operation without affecting the realization of the technical effects of the embodiments of the present application. The above-mentioned units are divided based on logical functions, and the functions of one unit can also be realized by multiple units, or the functions of multiple units can be realized by one unit. In other embodiments of the present application, the system can also include other units, and these functions can also be realized by other units in actual application, and can be realized by multiple units.

[0073] According to another embodiment of the present application, the system described in the present embodiment can be configured and the method of the present embodiment 1 can be implemented by running a computer program (including program codes) capable of performing each step involved in the corresponding method described in the present embodiment 1 on a general-purpose computing device such as a computer including processing elements and storage elements such as a Central Processing Unit (CPU), a Random Access Memory (RAM), a Read Only Memory (ROM), and the like, the computer program can be recorded on a computer-readable recording medium and loaded into the above-mentioned computing device through the computer-readable recording medium and run therein.

[0074] Embodiment 3

[0075] The present embodiment provides a heart ultrasound mode switching system, comprising: a B-ultrasound device, a color ultrasound device, an M-ultrasound device, a first multi-degree-of-freedom robot, a second multi-degree-of-freedom robot, a third multi-degree-of-freedom robot, and a control terminal, the B-ultrasound device comprises a B-ultrasound probe, the color ultrasound device comprises a color ultrasound probe, and the M-ultrasound device comprises an M-ultrasound probe.

[0076] The B-ultrasound probe is connected with the first multi-degree-of-freedom robot arm, the color ultrasound probe is connected with the second multi-degree-of-freedom robot arm, and the M-ultrasound probe is connected with the third multi-degree-of-freedom robot arm.

[0077] The B-ultrasound device, the color ultrasound device, the M-ultrasound device, the first multi-degree-of-freedom robot arm, the second multi-degree-of-freedom robot arm, and the third multi-degree-of-freedom robot arm are respectively connected with the control terminal, and the control terminal is configured to execute the heart ultrasound mode switching method described in the present embodiment 1.

[0078] Embodiment 4

[0079] As shown in Figure 8 The present embodiment provides an electronic device, which comprises a processor 1001, a communication interface 1002, and a computer readable storage medium 1003. The processor 1001, the communication interface 1002, and the computer readable storage medium 1003 can be connected through a bus or other means.

[0080] The communication interface 1002 is configured to receive and send data, the computer readable storage medium 1003 can be stored in the memory of the electronic device, the computer readable storage medium 1003 is configured to store a computer program, the computer program comprises program instructions, and the processor 1001 is configured to execute the program instructions stored in the computer readable storage medium 1003.

[0081] The processor 1001 (or CPU (Central Processing Unit)) is the computing core and control core of the electronic device, which is suitable for implementing one or more instructions, and is particularly suitable for loading and executing one or more instructions to implement a corresponding method flow or a corresponding function.

[0082] The processor 1001 is configured to perform the following process:

[0083] The B-ultrasound video stream data in the B-ultrasound mode is used for prompting and guiding the ultrasound probe to move to the standard section of the heart ultrasound examination.

[0084] After obtaining the standard section, the detection of the region of interest is performed, and when the region of interest is continuously detected within a set time and the difference between the region of interest detected multiple times is less than a set threshold, it is prompted to switch to the color ultrasound mode, and disease prediction is performed according to the color ultrasound video in the color ultrasound mode, and after the prediction is completed, it is switched to the B-ultrasound mode.

[0085] According to the current standard section index or disease prediction result, it is judged whether to start M-ultrasound, if M-ultrasound is needed, the M-ultrasound mode is entered, and the M-ultrasound video stream in the M-ultrasound mode is used for final diagnosis of the disease, if M-ultrasound is not needed, the B-ultrasound video stream data is used for prompting and guiding the ultrasound probe to find the next standard section until the detection of the last standard section is completed.

[0086] In the implementation mode, preferably, a six-degree-of-freedom prediction algorithm based on deep learning is used for prompting and guiding the ultrasound probe according to the B-ultrasound video stream data, and the six degrees of freedom include the translation directions of X, Y and Z coordinate axes and the rotation directions of the pitch angle, yaw angle and roll angle of the ultrasound probe.

[0087] The specific working process is described in Embodiment 1, which will not be repeated here.

[0088] Embodiment 4

[0089] The implementation mode provides a computer readable storage medium (Memory), which is a memory device in an electronic device, used for storing programs and data. It can be understood that the computer readable storage medium herein can include a built-in storage medium in the electronic device, and of course can also include an expansion storage medium supported by the electronic device. The computer readable storage medium provides a storage space, and the storage space stores a processing system of the electronic device.

[0090] Also, stored in the storage space are one or more instructions adapted to be loaded and executed by the processor, which can be one or more computer programs (including program code). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory, or a non-volatile memory such as at least one disk memory; optionally, it can also be at least one computer-readable storage medium located remotely from the aforementioned processor.

[0091] In one embodiment, the computer-readable storage medium stores one or more instructions; the processor loads and executes the one or more instructions stored in the computer-readable storage medium to implement the following process:

[0092] According to the B-ultrasound video stream data in the B-ultrasound mode, the ultrasound probe is prompted and guided, so that the ultrasound probe moves to a standard section for cardiac ultrasound examination;

[0093] After the standard section is obtained, a region of interest is detected, and when the region of interest is continuously detected within a set time and the difference between the region of interest detected multiple times is less than a set threshold, it is prompted to switch to the color ultrasound mode, and according to the color ultrasound video in the color ultrasound mode, disease prediction is performed, and after the prediction is completed, it is switched to the B-ultrasound mode;

[0094] According to the current standard section index or disease prediction result, it is judged whether to start M-ultrasound, if M-ultrasound is needed, the M-ultrasound mode is entered, and according to the M-ultrasound video stream in the M-ultrasound mode, the final diagnosis of the disease is performed, if M-ultrasound is not needed, the ultrasound probe is prompted and guided according to the current B-ultrasound video stream data to find the next standard section, until the detection of the last standard section is completed.

[0095] In the present implementation, preferably, a six-degree-of-freedom prediction algorithm based on deep learning is used to guide the ultrasound probe according to the B-ultrasound video stream data, and the six degrees of freedom include translation directions in X, Y and Z coordinate axis directions and rotation directions of the pitch angle, yaw angle and roll angle of the ultrasound probe.

[0096] The specific working process is described in Embodiment 1, which will not be repeated here.

[0097] Embodiment 5:

[0098] The present implementation provides a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. The processor of the electronic device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to make the electronic device perform the following process:

[0099] According to the B-ultrasound video stream data under the B-ultrasound mode, the ultrasound probe is prompted and guided, so that the ultrasound probe is moved to the standard section of the heart ultrasound examination.

[0100] After the standard section is obtained, the detection of the region of interest is performed, and when the region of interest is continuously detected within a set time and the difference between the region of interest detected multiple times is less than a set threshold, it is prompted to switch to the color ultrasound mode, and according to the color ultrasound video under the color ultrasound mode, the disease prediction is performed, and after the prediction is completed, it is switched to the B-ultrasound mode.

[0101] According to the current standard section index or the disease prediction result, it is judged whether to start M-ultrasound, if M-ultrasound is needed, the M-ultrasound mode is entered, and according to the M-ultrasound video stream under the M-ultrasound mode, the final diagnosis of the disease is performed, if M-ultrasound is not needed, the ultrasound probe is prompted and guided according to the current B-ultrasound video stream data to find the next standard section, until the detection of the last standard section is completed.

[0102] In the present embodiment, preferably, based on the six-degree-of-freedom prediction algorithm of deep learning, the ultrasound probe is prompted and guided according to the B-ultrasound video stream data, and the six degrees of freedom include the translation direction of the X, Y and Z coordinate axis directions and the rotation direction of the pitch angle, yaw angle and roll angle of the ultrasound probe.

[0103] The specific working process is described in Example 1, which will not be repeated here.

[0104] Those skilled in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in the present application can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Professional technical objects can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0105] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions according to the embodiments of the present application are generated. The computer can be a general purpose computer, a special purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in or transmitted by a computer readable storage medium. The computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center through a wired (for example, coaxial cable, optical fiber, digital line (DSL)) or wireless (for example, infrared, wireless, microwave, etc.) manner. The computer readable storage medium can be any available medium that can be accessed by a computer or a data processing device such as a server, data center, etc. integrated with one or more available media. The available media can be a magnetic medium (for example, floppy disk, hard disk, magnetic tape), an optical medium (for example, DVD), or a semiconductor medium (for example, solid state disk (SSD)) and the like.

[0106] The above only describes the preferred embodiments of the present application and is not intended to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method of switching modes of echocardiography, characterized by, The method comprises the following steps: prompting and guiding the ultrasound probe according to the B-ultrasound video stream data in the B-ultrasound mode, so that the ultrasound probe moves to a standard section of a heart ultrasound examination; after obtaining the standard section, detecting a region of interest, and when the region of interest is continuously detected within a set time and the difference between the region of interest detected multiple times is less than a set threshold, prompting switching to the color-ultrasound mode, and performing disease prediction according to the color-ultrasound video in the color-ultrasound mode, and after the prediction is completed, switching to the B-ultrasound mode; judging whether to start M-ultrasound according to the current standard section index or the disease prediction result, if M-ultrasound needs to be started, entering the M-ultrasound mode, performing final diagnosis of the disease according to the M-ultrasound video stream in the M-ultrasound mode, if M-ultrasound does not need to be started, continuing to prompt and guide the ultrasound probe according to the current B-ultrasound video stream data to find the next standard section, until the detection of the last standard section is completed; moving the ultrasound probe according to the six-degree-of-freedom prediction result, obtaining a new B-ultrasound video, and repeatedly predicting the new B-ultrasound video until the six-degree-of-freedom prediction result is that no further movement and rotation are needed, at which time a standard section of the heart ultrasound examination is obtained; judging whether to start M-ultrasound according to the current standard section index or the disease prediction result, comprising: when the disease prediction result is moderate or above, directly starting M-ultrasound; wherein the disease degree comprises mild, moderate and severe; when one or more of the standard section indexes are abnormal, directly starting M-ultrasound; wherein the abnormality includes that the interventricular septum thickness is greater than a set threshold, and the motion law of the interventricular septum is inconsistent with the standard motion law; performing final diagnosis of the disease according to the M-ultrasound video stream in the M-ultrasound mode, comprising: selecting a line connecting a center point P2 of the region of interest and a vertex P1 as the position of the M-ultrasound sampling line to obtain a continuous waveform video of the M-ultrasound, measuring the M-ultrasound index according to the continuous waveform video of the M-ultrasound, and performing final diagnosis of the disease according to the M-ultrasound index.

2. The heart ultrasound mode switching method of claim 1, wherein: a six-degree-of-freedom prediction algorithm based on deep learning is used to prompt and guide the ultrasound probe according to the B-ultrasound video stream data, and the six degrees of freedom include translation directions in X, Y and Z coordinate axis directions and rotation directions of the pitch angle, yaw angle and roll angle of the ultrasound probe.

3. The heart ultrasound mode switching method of claim 1 or 2, wherein: performing disease prediction according to the color-ultrasound video in the color-ultrasound mode comprises: using a deep learning model to analyze the color-ultrasound video to generate a prediction result of whether a disease exists and a prediction result of the disease degree.

4. The heart ultrasound mode switching method of claim 3, wherein: when the disease is mitral regurgitation, a mitral valve position is framed according to the color-ultrasound video frame image, the color-ultrasound video frame image corresponding to the mitral valve position frame is used as the input of the deep learning model, and the deep learning model outputs whether the regurgitation exists and the degree of the regurgitation, and the degree of the regurgitation includes mild, moderate and severe.

5. A cardiac ultrasound mode switching system, characterized by, The heart ultrasound mode switching method of any one of claims 1-4 comprises: The B-ultrasound detection unit is configured to guide the ultrasound probe to move to a standard section of a heart ultrasound examination according to a B-ultrasound video stream in a B-ultrasound mode; The color ultrasound detection unit is configured to detect a region of interest after obtaining the standard section, and when the region of interest is continuously detected for a set time and a difference between the region of interest detected multiple times is less than a set threshold, it is prompted to switch to a color ultrasound mode, and disease prediction is performed according to a color ultrasound video in the color ultrasound mode, and after the prediction is completed, it is switched to the B-ultrasound mode; The M-ultrasound detection unit is configured to determine whether to start M-ultrasound according to a current standard section index or a disease prediction result, and if M-ultrasound needs to be started, it enters an M-ultrasound mode, and performs final diagnosis of the disease according to an M-ultrasound video stream in the M-ultrasound mode, and if M-ultrasound does not need to be started, it continues to guide the ultrasound probe according to the current B-ultrasound video stream to find the next standard section until the detection of the last standard section is completed.

6. A cardiac ultrasound mode switching system, characterized by, The method comprises the following steps: The B-ultrasound device, the color ultrasound device, the M-ultrasound device, the first multi-degree-of-freedom machine, the second multi-degree-of-freedom machine, the third multi-degree-of-freedom machine, and the control terminal are connected, the B-ultrasound device comprises a B-ultrasound probe, the color ultrasound device comprises a color ultrasound probe, and the M-ultrasound device comprises an M-ultrasound probe; The B-ultrasound probe is connected with the first multi-degree-of-freedom mechanical arm, the color ultrasound probe is connected with the second multi-degree-of-freedom mechanical arm, and the M-ultrasound probe is connected with the third multi-degree-of-freedom mechanical arm; The B-ultrasound device, the color ultrasound device, the M-ultrasound device, the first multi-degree-of-freedom mechanical arm, the second multi-degree-of-freedom mechanical arm, and the third multi-degree-of-freedom mechanical arm are connected with the control terminal respectively, and the control terminal is configured to execute the heart ultrasound mode switching method in any one of claims 1-4.

7. A computer device, comprising: The method comprises: A processor and a computer readable storage medium; The processor is adapted to execute a computer program; The computer readable storage medium stores a computer program, and the computer program is executed by the processor to realize the heart ultrasound mode switching method in any one of claims 1-4.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program is adapted to be loaded and executed by the processor to realize the heart ultrasound mode switching method in any one of claims 1-4.

9. A computer program product, characterised in that, The computer program product comprises a computer program, and the computer program is executed by the processor to realize the heart ultrasound mode switching method in any one of claims 1-4.

Images