A method and device for detecting cardiac output, an electronic device and a storage medium

Abstract

The application discloses a method and device for detecting cardiac output, electronic equipment and storage medium. The method comprises the following steps: acquiring cardiac ultrasound data of a target scanning object, and determining the section type corresponding to each section image in the cardiac ultrasound data; acquiring a first section image with a section type of an apical three-chamber section or an apical five-chamber section from the cardiac ultrasound data, optimizing the frequency spectrum data corresponding to the first section image, and obtaining optimized frequency spectrum data; acquiring a second section image with a section type of a parasternal left ventricular long-axis section from the cardiac ultrasound data, and acquiring a left ventricular outflow tract diameter from the second section image; and calculating a target parameter according to the left ventricular outflow tract diameter and the optimized frequency spectrum data. The application can collect frequency spectrum data from a region of interest according to a sampling gate set by a region parameter of the region of interest, and automatically calculate the cardiac output according to the frequency spectrum data, so that the Doppler data collected by an ultrasonic probe is no longer needed, and the data analysis process is simplified.

Description

Technical Field

[0001] This application relates to the field of image processing, and more particularly to a method, apparatus, electronic device, and storage medium for detecting cardiac output. Background Technology

[0002] Echocardiography data refers to data obtained by measuring the periodic activity of structures such as the heart walls, ventricles, and valves through the chest wall and soft tissue using shortwave ranging principles. Various cross-sections are used during echocardiography data acquisition, such as the apical three-chamber view, the apical five-chamber view, and the parasternal left ventricular long-axis view. Currently, cardiac output calculation primarily involves acquiring Doppler data using an ultrasound probe and then analyzing it. This analysis process is complex and computationally intensive, making it difficult to quickly obtain cardiac output. Summary of the Invention

[0003] In order to solve the above-mentioned technical problems, or at least partially solve the above-mentioned technical problems, this application provides a method, apparatus, electronic device and storage medium for detecting cardiac output.

[0004] According to one aspect of the embodiments of this application, a method for detecting cardiac output is provided, comprising:

[0005] Acquire cardiac ultrasound data of the target scan object and determine the section type corresponding to each section image in the cardiac ultrasound data;

[0006] A first sectional image of either an apical three-chamber or apical five-chamber view is obtained from the cardiac ultrasound data. A region of interest is determined in the first sectional image. Acquisition parameters corresponding to the region of interest are obtained. The spectral data corresponding to the first sectional image is optimized based on the acquisition parameters to obtain optimized spectral data.

[0007] A second section image of the parasternal left ventricular long axis section is obtained from the cardiac ultrasound data, and the diameter of the left ventricular outflow passage along the parasternal left ventricular long axis is obtained from the second section image;

[0008] Based on the diameter of the left ventricular outflow channel and the optimized spectral data, target parameters are calculated, including cardiac output. The target parameters, including cardiac output, are displayed.

[0009] Furthermore, acquiring the cardiac ultrasound data of the target scan object includes:

[0010] Acquire ultrasound probe images captured by the ultrasound probe;

[0011] The ultrasonic probe image is analyzed to determine the current status information of the ultrasonic probe;

[0012] When the current state information matches the target state information, the cardiac ultrasound data is acquired based on the current state information.

[0013] Furthermore, determining the section type corresponding to each section image in the cardiac ultrasound data includes:

[0014] The cardiac ultrasound data is detected to obtain image features from the cardiac ultrasound data;

[0015] Based on the correspondence between preset image features and section types, the target section type corresponding to the image features is determined. The target section type includes: parasternal left ventricular long axis section, apical three-chamber section, and apical five-chamber section.

[0016] Further, determining the region of interest in the first cross-sectional image, obtaining the acquisition parameters corresponding to the region of interest, and optimizing the spectral data corresponding to the first cross-sectional image based on the acquisition parameters to obtain optimized spectral data includes:

[0017] The left ventricular outflow channel in the first cross-sectional image is detected, and the bounding box corresponding to the left ventricular outflow channel is determined as the region of interest.

[0018] A sampling gate for acquiring spectral data is generated based on the region parameters of the region of interest, and the initial spectral data in the first frame of the first cross-sectional image is acquired using the sampling gate.

[0019] Based on the initial spectrum data, the acquisition parameters corresponding to the region of interest are set, and the acquisition parameters are used to acquire the regions of interest of other images in the first cross-sectional image except for the first frame image, to obtain optimized spectrum data.

[0020] Furthermore, the initial spectral data includes at least one of the following: maximum blood flow velocity, maximum grayscale value, baseline position, and blood flow direction;

[0021] The step of setting the acquisition parameters corresponding to the region of interest based on the initial spectrum data includes at least one of the following:

[0022] Based on the maximum blood flow velocity, the preset PRF value is adjusted according to a preset ratio to obtain the target PRF value;

[0023] Based on the maximum grayscale value, the preset DRGain value is adjusted according to a preset ratio to obtain the target DRGain value;

[0024] The baseline position is used to determine the target baseline position;

[0025] The blood flow direction is determined as the target blood flow direction.

[0026] Furthermore, obtaining the diameter of the left ventricular outflow channel along the parasternal left ventricular long axis from the second cross-sectional image includes:

[0027] Each frame of the second cross-sectional image is detected to obtain the angle of the aortic opening angle in each frame. The image with the largest aortic opening angle in the second cross-sectional image is determined as the target cross-sectional image.

[0028] The location information of the left ventricular outflow channel in the target cross-sectional image is identified, and cross-sectional data of the parasternal left ventricular long axis is extracted based on the location information. The diameter of the left ventricular outflow channel is calculated based on the cross-sectional data.

[0029] Furthermore, the target parameters are calculated based on the diameter of the left ventricular outflow channel and the optimized spectral data, including:

[0030] The blood flow velocity time integral and heart rate value were calculated using the optimized spectral data.

[0031] Calculate the cross-sectional area of ​​the left ventricular outflow channel using the diameter of the left ventricular outflow channel;

[0032] The stroke volume is obtained by multiplying the cross-sectional area corresponding to the left ventricular outflow channel and the time integral of the blood flow velocity, and the cardiac output is calculated using the stroke volume and the heart rate value corresponding to the target scan object.

[0033] The blood flow velocity time integral, the heart rate value, the stroke volume, and the cardiac output are determined as the target parameters.

[0034] According to another aspect of the embodiments of this application, a cardiac output detection device is also provided, comprising:

[0035] The acquisition module is used to acquire cardiac ultrasound data of the target scan object and determine the section type corresponding to each section image in the cardiac ultrasound data;

[0036] The first processing module is used to acquire a first section image with a section type of apical three-chamber view or apical five-chamber view from the cardiac ultrasound data, determine the region of interest in the first section image, acquire the acquisition parameters corresponding to the region of interest, and optimize the spectral data corresponding to the first section image based on the acquisition parameters to obtain optimized spectral data.

[0037] The second processing module is used to obtain a second section image of the parasternal left ventricular long axis section from the cardiac ultrasound data, and to obtain the diameter of the left ventricular outflow channel of the parasternal left ventricular long axis from the second section image;

[0038] The calculation module is used to calculate target parameters based on the diameter of the left ventricular outflow channel and the optimized spectral data. The target parameters include cardiac output, and the module displays the target parameters including the cardiac output.

[0039] According to another aspect of the embodiments of this application, an ultrasound device is also provided, including a main unit and at least one ultrasound probe interface, the ultrasound probe interface being used to connect an ultrasound probe to the main unit, the main unit being used for...

[0040] Acquire cardiac ultrasound data of the target scan object and determine the section type corresponding to each section image in the cardiac ultrasound data;

[0041] A first sectional image of either an apical three-chamber or apical five-chamber view is obtained from the cardiac ultrasound data. A region of interest is determined in the first sectional image. Acquisition parameters corresponding to the region of interest are obtained. The spectral data corresponding to the first sectional image is optimized based on the acquisition parameters to obtain optimized spectral data.

[0042] A second section image of the parasternal left ventricular long axis section is obtained from the cardiac ultrasound data, and the diameter of the left ventricular outflow passage along the parasternal left ventricular long axis is obtained from the second section image;

[0043] Based on the diameter of the left ventricular outflow channel and the optimized spectral data, target parameters are calculated, including cardiac output. The target parameters, including cardiac output, are displayed.

[0044] According to another aspect of the embodiments of this application, a computer-readable storage medium is also provided, the computer-readable storage medium storing computer instructions for causing a computer to perform the above-described cardiac output detection method.

[0045] This application also provides a computer program product containing instructions that, when run on a computer, cause the computer to perform the steps in the above-described method.

[0046] Compared with the prior art, the above-mentioned technical solution provided in this application has the following advantages: The method provided in this application can quickly determine the section type of cardiac ultrasound data, and when the section type is the apical three-chamber view or the apical five-chamber view, it extracts the region of interest from the cardiac ultrasound data, sets the sampling gate according to the region parameters of the region of interest, collects spectral data from the region of interest using the sampling gate, and automatically calculates cardiac output based on the spectral data. Compared with the prior art, it is no longer necessary to collect Doppler data through an ultrasound probe, which simplifies the data analysis process and improves the calculation efficiency of cardiac output. Attached Figure Description

[0047] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0048] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 A flowchart illustrating a method for detecting cardiac output provided in this application embodiment;

[0050] Figure 2 A schematic diagram of a region of interest provided in an embodiment of this application;

[0051] Figure 3 A flowchart of a method for detecting cardiac output provided in another embodiment of this application;

[0052] Figure 4 A schematic diagram of a spectrum image provided in an embodiment of this application;

[0053] Figure 5 A schematic diagram of a spectrum image provided in an embodiment of this application;

[0054] Figure 6 A block diagram of a cardiac output detection device provided in an embodiment of this application;

[0055] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0056] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. The illustrative embodiments of this application and their descriptions are used to explain this application and do not constitute an improper limitation of this application. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0057] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another similar entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0058] This application provides a method, apparatus, electronic device, and storage medium for detecting cardiac output. The method provided by this invention can be applied to any electronic device as needed, such as a server, terminal, or other electronic device. No specific limitation is made here, and for ease of description, it will be referred to as an electronic device below.

[0059] According to one aspect of the embodiments of this application, a method embodiment for detecting cardiac output is provided. Figure 1 A flowchart of a method for detecting cardiac output provided in an embodiment of this application is shown below. Figure 1 As shown, the method includes:

[0060] Step S11: Obtain cardiac ultrasound data of the target scan object and determine the section type corresponding to each section image in the cardiac ultrasound data.

[0061] The method provided in this application embodiment can be applied to a control terminal. The control terminal sends an acquisition command to the acquisition device, which controls the acquisition device to acquire at least one cross-sectional image of the heart of the target scan object. After executing the acquisition command, the acquisition device transmits the acquired at least one cross-sectional image to the control terminal. The control terminal combines the at least one cross-sectional image to obtain cardiac ultrasound data. The control terminal can be a smart device such as a computer or mobile phone.

[0062] In this embodiment of the application, step S11, acquiring the cardiac ultrasound data of the target scan object, specifically includes the following steps A1-A3:

[0063] Step A1: Acquire the ultrasound probe image acquired by the ultrasound probe.

[0064] In this embodiment of the application, after the control terminal sends a collection command to the ultrasonic probe, it will display the ultrasonic probe image during the ultrasonic probe's collection process.

[0065] Step A2: Analyze the ultrasound probe image to determine the current status information of the ultrasound probe.

[0066] In this embodiment, a recognition model can be used to extract the features of the heart chambers in the ultrasound probe image. Then, each chamber is located and segmented to obtain the chamber parameters, including chamber size, chamber area, etc. It should be noted that the chamber parameters and the section type can reflect the current position information and / or current orientation information of the ultrasound probe, thereby determining the current position information and / or current orientation information as the current state information.

[0067] Step A3: When the current state information is consistent with the target state information, acquire cardiac ultrasound data based on the current state information.

[0068] In this embodiment, the target state information includes target position information and target direction information, where the target position and target direction are the standard positions and directions of the ultrasonic probe during data acquisition. Then, the current position information and current direction information in the current state information are compared with the target position information and target direction information in the target state information to determine whether the current state information matches the target state information.

[0069] In this embodiment, if the current location information and the target location information are consistent, and the current direction information and the target direction information are consistent, then the current state information and the target state information are determined to be consistent. The ultrasound probe is controlled to continue the acquisition operation to obtain at least one frame of cross-sectional image. Then, the control terminal generates cardiac ultrasound data based on the obtained at least one frame of cross-sectional image.

[0070] After obtaining the current status information of the ultrasound probe, this embodiment displays the current status information and generates prompts based on it to guide the user in controlling the ultrasound probe to acquire cardiac ultrasound data. The prompts can be in the form of text, images, animations, or voice messages to guide the user on the next steps for using the ultrasound probe.

[0071] In this embodiment of the application, step S11, determining the section type corresponding to the section image included in the cardiac ultrasound data, includes:

[0072] The echocardiogram data is examined to obtain the image features in the echocardiogram data; based on the correspondence between the preset image features and the section type, the target section type corresponding to the image features is determined, wherein the target section type includes: parasternal left ventricular long axis section, apical three-chamber section and apical five-chamber section.

[0073] In this embodiment of the application, the detection process may be as follows: inputting cardiac ultrasound data into a pre-trained detection model so that the detection model extracts the image features of the cardiac ultrasound data and determines the target section type of the cardiac ultrasound data based on the image features. The target section type includes: parasternal left ventricular long axis section, apical three-chamber section, and apical five-chamber section.

[0074] In this embodiment, the detection model can be a classification model established using artificial intelligence methods / traditional methods. This model can extract features from the input echocardiogram data and identify whether the cross-section in the echocardiogram data is a parasternal left ventricular long-axis cross-section, an apical three-chamber cross-section, an apical five-chamber cross-section, or others. The detection model can be, but is not limited to, Support Vector Machine (SVM), Extra-Limited Learning Machine (ELM), VGG, ResNet, etc.

[0075] In this embodiment, the training method for the detection model is as follows: A sample image set is obtained, including sample images of various different types of cross-sections; annotation information corresponding to the sample images is obtained, whereby the annotation information is used to annotate the cross-sectional features in the sample images and the cross-sectional types corresponding to the cross-sectional features. The cross-sectional types include: parasternal left ventricular long-axis cross-section, apical three-chamber cross-section, and apical five-chamber cross-section; the sample image set and annotation information are input to a preset neural network model, so that the initial neural network model learns the correlation between the cross-sectional features and cross-sectional types in the sample images of the sample image set, ultimately obtaining the detection model.

[0076] Step S12: Obtain a first section image with a section type of apical three-chamber view or apical five-chamber view from the cardiac ultrasound data, determine the region of interest in the first section image, obtain the acquisition parameters corresponding to the region of interest, and optimize the spectral data corresponding to the first section image based on the acquisition parameters to obtain the optimized spectral data.

[0077] In this embodiment of the application, the region of interest in the first cross-sectional image is determined, the acquisition parameters corresponding to the region of interest are obtained, and the spectral data corresponding to the first cross-sectional image is optimized based on the acquisition parameters to obtain optimized spectral data, including the following steps B1-B3:

[0078] Step B1: Detect the left ventricular outflow channel in the first cross-sectional image and determine the bounding box corresponding to the left ventricular outflow channel as the region of interest.

[0079] In this embodiment, since the first cross-sectional image belongs to a three-chamber view or an apical five-chamber view, a left ventricular outflow duct tracking algorithm is used to detect the left ventricular outflow duct in the three-chamber view or the apical five-chamber view to obtain the region of the left ventricular outflow duct. Then, based on this region, the left ventricular outflow duct is located (e.g., Figure 2 (As shown).

[0080] Step B2: Generate a sampling gate for acquiring spectral data based on the region parameters of the region of interest, and use the sampling gate to acquire the initial spectral data in the first frame of the first cross-sectional image.

[0081] In this embodiment, the sampling gate can be positioned at the center of the region of interest; the width of the sampling gate can also be determined, for example, one-third of the width of the region of interest. The initial spectral data includes at least one of the following: maximum blood flow velocity, maximum grayscale value, baseline position, and blood flow direction.

[0082] Step B3: Set the acquisition parameters corresponding to the region of interest based on the initial spectrum data, and use the acquisition parameters to acquire the regions of interest in other images in the first cross-sectional image except for the first frame image, to obtain the optimized spectrum data.

[0083] In this embodiment of the application, the acquisition parameters corresponding to the region of interest are set according to the initial spectrum data, including at least one of the following: adjusting the preset PRF value according to the maximum blood flow velocity according to the preset ratio to obtain the target PRF value; adjusting the preset DRGain value according to the maximum gray level value according to the preset ratio to obtain the target DRGain value; determining the baseline position as the target baseline position; and determining the blood flow direction as the target blood flow direction.

[0084] It should be noted that since the PRF value reflects the range of blood flow velocity, it can be adjusted based on the maximum blood flow velocity in the first frame image. For example, the PRF value can be adjusted so that two-thirds of the maximum value of the blood flow range is the maximum blood flow velocity in the first frame. Since the DRGain value reflects the grayscale of the spectrum display, it can be adjusted based on the maximum gain in the first frame image. For example, the DRGain value can be adjusted so that two-thirds of the maximum grayscale value is the maximum grayscale value in the first frame. Because the preset ultrasound parameters carry a preset baseline position, the preset baseline position can be updated based on the baseline position of the first frame image. For example, the baseline position of the first frame can be directly used as the preset baseline position. Similar to adjusting the preset baseline position, the blood flow direction of the first frame image can also be set to a preset blood flow direction.

[0085] This application embodiment determines the acquisition parameters based on the first frame of the image, thereby optimizing the spectral data. This method enables more accurate subsequent parameter calculations, simplifies the calculation process, and facilitates subsequent image display by locating the region of interest in the cardiac ultrasound data.

[0086] Step S13: Obtain a second-section image of the parasternal left ventricular long axis section from the cardiac ultrasound data, and obtain the diameter of the left ventricular outflow channel along the parasternal left ventricular long axis from the second-section image.

[0087] In this embodiment, by detecting each frame of the second cross-sectional image, the angle of the aortic opening angle in each frame is obtained, and the image with the largest aortic opening angle in the second cross-sectional image is determined as the target cross-sectional image. Then, the position information of the left ventricular outflow channel in the target cross-sectional image is identified, and cross-sectional data of the parasternal left ventricular long axis is extracted based on the position information. The diameter of the left ventricular outflow channel is calculated based on the cross-sectional data.

[0088] In this embodiment, the detection process for cardiac ultrasound data is as follows: When the cardiac ultrasound data includes multiple frames, a first recognition model can be established using artificial intelligence methods, level set segmentation, Unet, DeepLab, FCN, and other segmentation algorithms. This first recognition model is then used to detect and analyze the parasternal left ventricular long-axis section data to obtain the target section image with the best display effect. Specifically, in this embodiment, each frame is input into the first recognition model, which can directly output the aortic valve opening angle size (e.g., ...) in each frame. Figure 2 By calculating the aortic valve opening angle in each frame of the image and sorting them, the frame with the largest aortic valve opening angle is the target cross-sectional image.

[0089] Step S14: Based on the diameter of the left ventricular outflow channel and the optimized spectral data, the target parameters are calculated. The target parameters include cardiac output. The target parameters including cardiac output are displayed.

[0090] In this embodiment of the application, the target parameters are calculated based on the diameter of the left ventricular outflow channel and the optimized spectral data, including the following steps C1-C4:

[0091] Step C1: Calculate the blood flow velocity time integral and heart rate value using the optimized spectral data.

[0092] In this embodiment of the application, the spectral image of the optimized spectral data is as follows: Figure 4 As shown. Figure 4 VTI (Velocity-Time Integral) refers to the velocity-time integral (the area in red in the diagram); HR (Heart Rate) refers to... Figure 4Vmax refers to the time distance from the start / end point of the first triangular region to the start / end point of the second triangular region, or the time distance from the peak point of the first triangular region to the peak point of the second triangular region. Vmax indicates the maximum flow velocity. Figure 4 The vertical axis represents the peak point; Vmean is the average velocity value, i.e., the average velocity of each VTI region; VTI envelope index... Figure 5 The outer boundary line of the central triangular region.

[0093] Step C2: Calculate the cross-sectional area of ​​the left ventricular outflow channel using the diameter of the left ventricular outflow channel.

[0094] In this embodiment of the application, the calculation formula for the left ventricular outflow channel (LVOT CSA) is as follows:

[0095] LVOT CSA = (LVOT D)2 × k, where LVOT D is the diameter of the left ventricular outflow channel in the parasternal long axis section, and k is a constant whose value is set according to the actual situation.

[0096] Step C3: Based on the product of the cross-sectional area corresponding to the left ventricular outflow channel and the time integral of the blood flow velocity, the stroke volume is obtained, and the cardiac output is calculated using the stroke volume and the heart rate value corresponding to the target scan object.

[0097] In the embodiments of this application, the stroke volume sv and cardiac output co are calculated using the formulas sv = LVOT CSA × VTI and co = sv × HR, where VTI is the time integral of blood flow velocity and HR is the heart rate value.

[0098] Step C4: Determine the blood flow velocity time integral, heart rate, stroke volume, and cardiac output as target parameters.

[0099] The method provided in this application can quickly determine the section type of cardiac ultrasound data. When the section type is an apical three-chamber or apical five-chamber view, the region of interest is extracted from the cardiac ultrasound data, the acquisition parameters corresponding to the region of interest are obtained, and the spectral data corresponding to the first section image is optimized based on the acquisition parameters to obtain optimized spectral data. Based on the optimized spectral data and the diameter of the left ventricular outflow channel, the target parameters, including cardiac output, are automatically calculated. Compared with the prior art, it is no longer necessary to acquire Doppler data through an ultrasound probe, which simplifies the data analysis process and improves the calculation efficiency of cardiac output.

[0100] In this embodiment of the application, when the current state information and the target state information are inconsistent, the following steps D1-D2 are further included:

[0101] Step D1: Based on the comparison results between the current state information and the target state information, obtain the difference information between the current state information and the target state information.

[0102] In this embodiment of the application, the process of obtaining the comparison results includes the following steps D101-C102:

[0103] Step D101: Extract target position information and / or target direction information from target status information.

[0104] Step D102: Compare the current location information with the target location information and / or compare the current direction information with the target direction information to obtain the comparison result.

[0105] In this embodiment, the comparison result is used to indicate that when the current state information differs from the target state information, the position information in the current state information is compared with the position information in the target state information to obtain position deviation data. And / or the direction information in the current state information is compared with the direction information in the target state information to obtain direction deviation data. Then, the position deviation data and direction deviation data are used as difference information.

[0106] Step D2: Use the difference information to determine the correction parameters of the ultrasound probe, whereby the correction parameters are used to control the movement of the ultrasound probe.

[0107] In this embodiment of the application, the correction direction can be determined based on the direction offset data, and the correction distance can be determined based on the position offset data. The correction direction and correction distance are then used as correction parameters.

[0108] In this embodiment of the application, difference information is obtained by comparing the current state information with the target state information, and the correction parameters for controlling the ultrasonic probe are determined by using the difference information, thereby realizing real-time guidance of the ultrasonic probe when the ultrasonic probe deviates from the target state information.

[0109] Figure 6 This is a block diagram of a cardiac output detection device provided in an embodiment of this application. This device can be implemented as part or all of an electronic device through software, hardware, or a combination of both. Figure 6 As shown, the device includes:

[0110] The acquisition module 61 is used to acquire cardiac ultrasound data of the target scan object and determine the section type corresponding to each section image in the cardiac ultrasound data;

[0111] The first processing module 62 is used to acquire a first section image with a section type of apical three-chamber view or apical five-chamber view from cardiac ultrasound data, determine the region of interest in the first section image, acquire the acquisition parameters corresponding to the region of interest, and optimize the spectral data corresponding to the first section image based on the acquisition parameters to obtain optimized spectral data.

[0112] The second processing module 63 is used to obtain a second section image of the parasternal left ventricular long axis section from the cardiac ultrasound data, and to obtain the diameter of the left ventricular outflow channel of the parasternal left ventricular long axis from the second section image;

[0113] The calculation module 64 is used to calculate the target parameters based on the diameter of the left ventricular outflow channel and the optimized spectral data. The target parameters include cardiac output and the target parameters including cardiac output are displayed.

[0114] In this embodiment of the application, the acquisition module is used to acquire ultrasound probe images collected by the ultrasound probe; analyze the ultrasound probe images to determine the current status information of the ultrasound probe; and acquire cardiac ultrasound data based on the current status information when the current status information is consistent with the target status information.

[0115] In this embodiment of the application, the determining module is used to detect cardiac ultrasound data and obtain image features in the cardiac ultrasound data; based on the correspondence between preset image features and section types, the target section type corresponding to the image features is determined, wherein the target section type includes: parasternal left ventricular long axis section, apical three-chamber section and apical five-chamber section.

[0116] In this embodiment, the first processing module is used to detect the left ventricular outflow channel in the first cross-sectional image and determine the bounding box corresponding to the left ventricular outflow channel as the region of interest; generate a sampling gate for acquiring spectrum data based on the region parameters of the region of interest, and use the sampling gate to acquire the initial spectrum data in the first frame image of the first cross-sectional image; set the acquisition parameters corresponding to the region of interest based on the initial spectrum data, and use the acquisition parameters to acquire the regions of interest in other images of the first cross-sectional image except for the first frame image to obtain optimized spectrum data.

[0117] In this embodiment of the application, the initial spectral data includes at least one of the following: maximum blood flow velocity, maximum grayscale value, baseline position, and blood flow direction;

[0118] Set the acquisition parameters corresponding to the region of interest based on the initial spectrum data, including at least one of the following:

[0119] The target PRF value is obtained by adjusting the preset PRF value according to a preset ratio based on the maximum blood flow velocity.

[0120] The target DRGain value is obtained by adjusting the preset DRGain value according to the preset ratio based on the maximum gray level value.

[0121] Determine the target baseline location from the baseline location;

[0122] The direction of blood flow is determined as the target blood flow direction.

[0123] In this embodiment of the application, the second processing module is used to detect each frame of the second cross-sectional image, obtain the angle of the aortic opening angle in each frame of the image, and determine the image with the largest angle of the aortic opening angle in the second cross-sectional image as the target cross-sectional image;

[0124] The location information of the left ventricular outflow channel in the target cross-sectional image is identified, and cross-sectional data of the parasternal left ventricular long axis are extracted based on the location information. The diameter of the left ventricular outflow channel is calculated based on the cross-sectional data.

[0125] In this embodiment, the calculation module is used to calculate the blood flow velocity time integral and heart rate value using optimized spectral data; calculate the cross-sectional area corresponding to the left ventricular outflow channel using the diameter of the left ventricular outflow channel; obtain the stroke volume based on the product of the cross-sectional area corresponding to the left ventricular outflow channel and the blood flow velocity time integral; and calculate the cardiac output using the stroke volume and the heart rate value corresponding to the target scan object; and determine the blood flow velocity time integral, heart rate value, stroke volume, and cardiac output as target parameters.

[0126] This application embodiment also provides an ultrasonic device, including a main unit and at least one ultrasonic probe interface. The ultrasonic probe interface is used to connect an ultrasonic probe to the main unit, and the main unit is used for...

[0127] Acquire cardiac ultrasound data of the target scan object and determine the section type corresponding to each section image in the cardiac ultrasound data;

[0128] First-section images of apical three-chamber or apical five-chamber views are obtained from echocardiography data. Regions of interest are determined in the first-section images. Acquisition parameters corresponding to the regions of interest are obtained. The spectral data corresponding to the first-section images are optimized based on the acquisition parameters to obtain optimized spectral data.

[0129] A second-section image of the parasternal left ventricular long-axis section is obtained from echocardiography data, and the diameter of the left ventricular outflow passage along the parasternal left ventricular long axis is obtained from the second-section image.

[0130] Based on the diameter of the left ventricular outflow channel and the optimized spectral data, the target parameters, including cardiac output, are calculated and displayed.

[0131] This application also provides an electronic device, such as... Figure 7 As shown, the electronic device may include: a processor 1501, a communication interface 1502, a memory 1503, and a communication bus 1504, wherein the processor 1501, the communication interface 1502, and the memory 1503 communicate with each other through the communication bus 1504.

[0132] Memory 1503 is used to store computer programs;

[0133] When the processor 1501 executes the computer program stored in the memory 1503, it implements the steps of the above embodiments.

[0134] The communication bus mentioned above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not mean that there is only one bus or one type of bus.

[0135] The communication interface is used for communication between the aforementioned terminal and other devices.

[0136] The memory may include random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0137] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0138] In another embodiment provided in this application, a computer-readable storage medium is also provided, which stores instructions that, when executed on a computer, cause the computer to perform any of the cardiac output detection methods described in the above embodiments.

[0139] In another embodiment provided in this application, a computer-readable storage medium is also provided, which stores computer instructions for causing a computer to perform the above-described cardiac output detection method.

[0140] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as 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 described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., a solid-state drive).

[0141] The above description is merely a preferred embodiment of this application and is not intended to limit the scope of protection of this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application are included within the scope of protection of this application.

[0142] The above description is merely a specific embodiment of this application, enabling those skilled in the art to understand or implement this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A method of detecting cardiac output, characterized by, The method comprises: acquiring cardiac ultrasound data of a target scan object, and determining a section type corresponding to each section image in the cardiac ultrasound data; acquiring a first section image with a section type of an apical three-chamber section or an apical five-chamber section from the cardiac ultrasound data, determining a region of interest in the first section image, acquiring acquisition parameters corresponding to the region of interest, and optimizing spectral data corresponding to the first section image according to the acquisition parameters to obtain optimized spectral data; acquiring a second section image with a section type of a parasternal left ventricular long-axis section from the cardiac ultrasound data, and acquiring a left ventricular outflow tract diameter of the parasternal left ventricular long-axis from the second section image; calculating a target parameter according to the left ventricular outflow tract diameter and the optimized spectral data, the target parameter comprising cardiac output, and displaying the target parameter comprising the cardiac output; the determining of the region of interest in the first section image, the acquiring of the acquisition parameters corresponding to the region of interest, and the optimizing of the spectral data corresponding to the first section image according to the acquisition parameters to obtain the optimized spectral data comprise: detecting a left ventricular outflow tract in the first section image, and determining a bounding box corresponding to the left ventricular outflow tract as the region of interest; generating a sampling gate for acquiring spectral data according to a region parameter of the region of interest, and acquiring initial spectral data in a first frame image in the first section image by using the sampling gate; setting the acquisition parameters corresponding to the region of interest according to the initial spectral data, and acquiring the region of interest in images other than the first frame image in the first section image by using the acquisition parameters to obtain the optimized spectral data.

2. The method of claim 1, wherein, The method comprises: acquiring an ultrasound probe image acquired by an ultrasound probe; analyzing the ultrasound probe image to determine current state information of the ultrasound probe; when the current state information is consistent with target state information, acquiring the cardiac ultrasound data based on the current state information.

3. The method of claim 1, wherein, The method comprises: detecting the cardiac ultrasound data to obtain image features in the cardiac ultrasound data; determining a target section type corresponding to the image features based on a correspondence between preset image features and section types, wherein the target section type comprises a parasternal left ventricular long-axis section, an apical three-chamber section, and an apical five-chamber section.

4. The method of claim 1, wherein, The initial spectral data comprises at least one of the following: maximum blood flow velocity, maximum gray scale value, baseline position, and blood flow direction; The setting of the acquisition parameters corresponding to the region of interest according to the initial spectral data comprises at least one of the following: adjusting a preset PRF value according to a preset proportion based on the maximum blood flow velocity to obtain a target PRF value; adjusting a preset DRGain value according to a preset proportion based on the maximum gray scale value to obtain a target DRGain value; determining the baseline position as a target baseline position; determining the blood flow direction as a target blood flow direction.

5. The method of claim 1, wherein, The left ventricular outflow tract diameter of the parasternal left ventricular long axis is obtained from the second cross-section image, comprising: detecting each frame of image in the second cross-section image to obtain the angle of the aortic opening angle in each frame of image, and determining the image with the largest angle of the aortic opening angle in the second cross-section image as a target cross-section image; identifying the position information of the left ventricular outflow tract in the target cross-section image, and extracting the cross-section data of the parasternal left ventricular long axis based on the position information, and calculating the left ventricular outflow tract diameter based on the cross-section data.

6. The method of claim 1, wherein, The target parameter is calculated according to the left ventricular outflow tract diameter and the optimized frequency spectrum data, comprising: the blood flow velocity time integral and the heart rate value are calculated by using the optimized frequency spectrum data; the cross-sectional area corresponding to the left ventricular outflow tract is calculated by using the left ventricular outflow tract diameter; the stroke volume is obtained based on the product of the cross-sectional area corresponding to the left ventricular outflow tract and the blood flow velocity time integral, and the cardiac output is calculated by using the stroke volume and the heart rate value corresponding to the target scan object; the blood flow velocity time integral, the heart rate value, the stroke volume and the cardiac output are determined as the target parameter.

7. A cardiac output detection apparatus, characterized by comprising: an acquisition module, configured to acquire cardiac ultrasound data of a target scan object, and determine the cross-section type corresponding to each cross-section image in the cardiac ultrasound data; a first processing module, configured to obtain a first cross-section image with a cross-section type of an apical three-chamber heart cross-section or an apical five-chamber heart cross-section from the cardiac ultrasound data, determine a region of interest in the first cross-section image, acquire acquisition parameters corresponding to the region of interest, and optimize frequency spectrum data corresponding to the first cross-section image according to the acquisition parameters to obtain optimized frequency spectrum data; the determination of the region of interest in the first cross-section image, the acquisition of the acquisition parameters corresponding to the region of interest, and the optimization of the frequency spectrum data corresponding to the first cross-section image according to the acquisition parameters to obtain the optimized frequency spectrum data, comprising: detecting a left ventricular outflow tract in the first cross-section image, and determining a bounding box corresponding to the left ventricular outflow tract as the region of interest; generating a sampling gate for acquiring frequency spectrum data according to the region parameters of the region of interest, and acquiring initial frequency spectrum data in a first frame of image in the first cross-section image by using the sampling gate; setting the acquisition parameters corresponding to the region of interest according to the initial frequency spectrum data, and acquiring the region of interest in images other than the first frame of image in the first cross-section image by using the acquisition parameters to obtain the optimized frequency spectrum data; a second processing module, configured to obtain a second cross-section image with a cross-section type of a parasternal left ventricular long axis cross-section from the cardiac ultrasound data, and obtain a left ventricular outflow tract diameter of the parasternal left ventricular long axis from the second cross-section image; a calculation module, configured to calculate a target parameter according to the left ventricular outflow tract diameter and the optimized frequency spectrum data, the target parameter comprising a cardiac output, and display the target parameter comprising the cardiac output.

8. An ultrasound apparatus, characterized by The system comprises a host and at least one ultrasonic probe interface for connecting an ultrasonic probe to the host, and the host is configured to, acquire cardiac ultrasound data of a target scan object, and determine a type of each cross-section image in the cardiac ultrasound data; acquire a first cross-section image of which the type is an apical three-chamber cross-section or an apical five-chamber cross-section from the cardiac ultrasound data, determine a region of interest in the first cross-section image, acquire acquisition parameters corresponding to the region of interest, and optimize spectral data corresponding to the first cross-section image according to the acquisition parameters to obtain optimized spectral data; the determining of the region of interest in the first cross-section image, the acquiring of the acquisition parameters corresponding to the region of interest, and the optimizing of the spectral data corresponding to the first cross-section image according to the acquisition parameters to obtain the optimized spectral data comprise: detecting a left ventricular outflow tract in the first cross-section image, and determining a bounding box corresponding to the left ventricular outflow tract as the region of interest; generating a sampling gate for acquiring spectral data according to a region parameter of the region of interest, and acquiring initial spectral data in a first frame of image in the first cross-section image by using the sampling gate; setting the acquisition parameters corresponding to the region of interest according to the initial spectral data, and acquiring the region of interest in images other than the first frame of image in the first cross-section image by using the acquisition parameters to obtain the optimized spectral data; acquiring a second cross-section image of which the type is a parasternal left ventricular long-axis cross-section from the cardiac ultrasound data, and acquiring a left ventricular outflow tract diameter of the parasternal left ventricular long-axis from the second cross-section image; calculating a target parameter according to the left ventricular outflow tract diameter and the optimized spectral data, the target parameter comprising cardiac output, and displaying the target parameter including the cardiac output.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions for causing a computer to execute the method for detecting cardiac output according to any one of claims 1-6.

Images