Method and device for measuring heart valve annulus parameters, electronic equipment and storage medium

Abstract

The present application relates to the technical field of ultrasonic detection, and discloses a heart valve ring parameter measurement method and device, an electronic device and a storage medium, wherein the present application processes a heart section image sequence obtained in a first ultrasonic imaging mode to determine a sampling point of a target valve ring, wherein the first ultrasonic imaging mode is an imaging mode for displaying a two-dimensional image; imaging is performed at the sampling point using a second ultrasonic imaging mode to obtain a motion atlas of the target valve ring, wherein the second ultrasonic imaging mode is an imaging mode for displaying a motion atlas; the motion atlas of the target valve ring is processed to determine a motion trajectory curve of the target valve ring; and the valve ring parameter of the target valve ring is determined based on the motion trajectory curve of the target valve ring. Thus, the measurement process of the heart valve ring parameter is simplified, and the accuracy, consistency and repeatability of the measurement result are improved by automatically selecting a sampling line and automatically calculating a valve ring parameter.

Description

Technical Field

[0001] This invention relates to the field of ultrasound testing technology, specifically to methods, devices, electronic equipment, and storage media for measuring cardiac valve annulus parameters. Background Technology

[0002] Tricuspid annular systolic displacement (TAPSE) and mitral annular systolic displacement (MAPSE) are key indicators for assessing ventricular systolic function. Currently, the measurement of these two parameters primarily relies on manual measurement. Under M-mode echocardiography, the operator manually adjusts the M-mode sampling line to align with the lateral wall of the tricuspid or mitral annulus, and then manually measures the systolic displacement amplitude. This procedure is highly dependent on the operator's experience, is cumbersome and time-consuming, and makes it difficult to guarantee the accuracy, consistency, and repeatability of the measurement results. Summary of the Invention

[0003] This invention provides a method, apparatus, electronic device, and storage medium for measuring cardiac valve annulus parameters, in order to solve the problems of time-consuming measurement and difficulty in ensuring the accuracy, consistency, and repeatability of measurement results when manually measuring the systolic displacement of the tricuspid and mitral valve annulus.

[0004] In a first aspect, the present invention provides a method for measuring cardiac valve annulus parameters, the method comprising: In the first ultrasound imaging mode, the acquired cardiac cross-sectional image sequence is processed to determine the sampling point of the target valve annulus. The first ultrasound imaging mode is an imaging mode that displays two-dimensional images. The second ultrasound imaging mode is used to image at the sampling point to obtain the motion map of the target valve annulus. The second ultrasound imaging mode is the imaging mode that displays the motion map. The motion map of the target lobe ring is processed to determine the motion trajectory curve of the target lobe ring; Based on the motion trajectory curve of the target lobe, the lobe parameters of the target lobe are determined.

[0005] In one optional implementation, the acquired cardiac cross-sectional image sequence is processed to determine the sampling points of the target valve annulus, including: Preprocessing is performed on the cardiac cross-sectional image sequence to obtain the preprocessed cardiac cross-sectional image sequence; The preprocessed heart cross-sectional image sequence is input into a pre-trained sampling point localization model to obtain the sampling points of the target valve annulus.

[0006] In one alternative implementation, the sampling point localization model includes a backbone network, a neck network, and a head network. The backbone network is used for feature extraction, the neck network is used for feature fusion, and the head network is used to output the prediction results of the sampling points. The backbone network consists of a downsampling unit and multiple cascaded feature extraction units. The neck network consists of a bidirectional feature pyramid network and an attention module.

[0007] In one optional implementation, the motion map of the target lobe ring is processed to determine the motion trajectory curve of the target lobe ring, including: The motion map of the target lobe ring is binarized and smoothed to obtain the processed motion map. The upper and lower boundaries of the processed motion map are extracted to obtain the motion trajectory curve of the target lobe ring.

[0008] In one optional implementation, processing the motion map of the target lobe ring to determine the motion trajectory curve of the target lobe ring further includes: The motion map of the target lobe ring is subjected to median filtering and texture feature enhancement.

[0009] In one optional implementation, the valve parameters of the target valve are determined based on the motion trajectory curve of the target valve, including: Based on the preset detection algorithm, the motion trajectory curve of the target lobe ring is analyzed to determine the trough and peak points of each motion cycle in the motion trajectory curve of the target lobe ring. The vertical distance between the trough and crest points of each motion cycle is calculated to obtain the valve ring parameters of the target valve ring.

[0010] In one alternative implementation, the target valve annulus includes a tricuspid valve annulus and / or a mitral valve annulus; The annular parameters of the tricuspid valve annulus are the tricuspid valve systolic displacements, and the annular parameters of the mitral valve annulus are the mitral valve annulus systolic displacements.

[0011] In a second aspect, the present invention provides a device for measuring cardiac valve annulus parameters, the device comprising: The sampling point determination module is used to process the acquired cardiac cross-sectional image sequence in the first ultrasound imaging mode to determine the sampling point of the target valve annulus, wherein the first ultrasound imaging mode is an imaging mode that displays two-dimensional images. The motion map acquisition module is used to perform imaging at the sampling point using the second ultrasound imaging mode to obtain the motion map of the target valve annulus, wherein the second ultrasound imaging mode is an imaging mode that displays the motion map; The trajectory curve determination module is used to process the motion map of the target lobe ring and determine the motion trajectory curve of the target lobe ring. The valve annulus parameter determination module is used to determine the valve annulus parameters of the target valve annulus based on the motion trajectory curve of the target valve annulus.

[0012] Thirdly, the present invention provides an electronic device comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the method for measuring cardiac valve annulus parameters as described in the first aspect or any corresponding embodiment thereof.

[0013] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to perform the method for measuring cardiac valve annulus parameters according to the first aspect or any corresponding embodiment thereof.

[0014] Fifthly, the present invention provides a computer program product, including computer instructions for causing a computer to execute the method for measuring cardiac valve annulus parameters according to the first aspect or any corresponding embodiment thereof.

[0015] The method for measuring cardiac valve annulus parameters provided in this invention determines the sampling points of the target valve annulus based on a sequence of cardiac cross-sectional images acquired in a first ultrasound imaging mode. A second ultrasound imaging mode is then used to sample and image at these sampling points, obtaining a motion map of the target valve annulus. This eliminates the need for manual selection of sampling lines, ensuring the accuracy of the selected lines. Simultaneously, the motion map of the target valve annulus is processed to determine its motion trajectory curve. Based on this trajectory curve, the valve annulus parameters are determined, thus automatically calculating the parameters based on the acquired motion map. Therefore, by automatically selecting sampling lines and automatically calculating valve annulus parameters, the method simplifies the measurement process and improves the accuracy, consistency, and repeatability of the measurement results. Attached Figure Description

[0016] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0017] Figure 1 This is a schematic flowchart of a first method for measuring cardiac valve annulus parameters according to an embodiment of the present invention; Figure 2 This is a schematic diagram of a second method for measuring cardiac valve annulus parameters according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the sampling point localization model for cardiac valve annulus parameters according to an embodiment of the present invention; Figure 4This is a schematic diagram of the grouped shuffling convolution structure in the method for measuring cardiac valve annulus parameters according to an embodiment of the present invention; Figure 5 This is a schematic diagram of the attention module in the method for measuring cardiac valve annulus parameters according to an embodiment of the present invention; Figure 6 This is a schematic diagram of the third process for measuring cardiac valve annulus parameters according to an embodiment of the present invention; Figure 7 This is a schematic diagram of the fourth process for measuring cardiac valve annulus parameters according to an embodiment of the present invention; Figure 8 This is a structural block diagram of a device for measuring cardiac valve annulus parameters according to an embodiment of the present invention; Figure 9 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.

[0020] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0021] Tricuspid annular systolic displacement (TAPSE) and mitral annular systolic displacement (MAPSE) are key indicators for assessing ventricular systolic function. Currently, the measurement of these two parameters primarily relies on manual measurement. Under M-mode echocardiography, the operator manually adjusts the M-mode sampling line to align with the lateral wall of the tricuspid or mitral annulus, and then manually measures the systolic displacement amplitude. This procedure is highly dependent on the operator's experience, is cumbersome and time-consuming, and makes it difficult to guarantee the accuracy, consistency, and repeatability of the measurement results.

[0022] To address the aforementioned problems, this invention provides a method for measuring cardiac valve annulus parameters. In a first ultrasound imaging mode, the acquired cardiac cross-sectional image sequence is processed to determine sampling points for the target valve annulus. The first ultrasound imaging mode is a two-dimensional image display mode. A second ultrasound imaging mode is used to image at the sampling points, obtaining a motion atlas of the target valve annulus. The motion atlas of the target valve annulus is processed to determine its motion trajectory curve. Based on the motion trajectory curve, the valve annulus parameters are determined. By determining the sampling points for the target valve annulus based on the cardiac cross-sectional image sequence acquired in the first ultrasound imaging mode, and then using the second ultrasound imaging mode to sample and image at these points to obtain the motion atlas, the method eliminates the need for manual selection of sampling lines, ensuring the accuracy of the selected sampling lines. Simultaneously, the motion atlas of the target valve annulus is processed to determine its motion trajectory curve, and the valve annulus parameters are determined based on this curve. Therefore, the valve annulus parameters of the target valve annulus are automatically calculated based on the acquired motion atlas. Therefore, by automatically selecting sampling lines and automatically calculating valve annulus parameters, the measurement process of cardiac valve annulus parameters is simplified, and the accuracy, consistency and repeatability of measurement results are improved.

[0023] According to an embodiment of the present invention, a method for measuring cardiac valve annulus parameters is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0024] This embodiment provides a method for measuring cardiac valve annulus parameters. Figure 1 This is a schematic flowchart of a first method for measuring cardiac valve annulus parameters according to an embodiment of the present invention, as shown below. Figure 1 As shown, the process includes the following steps: Step S101: In the first ultrasound imaging mode, the acquired cardiac cross-sectional image sequence is processed to determine the sampling point of the target valve annulus.

[0025] In this embodiment of the invention, the first ultrasound imaging mode is an imaging mode that displays two-dimensional images, namely, B-mode imaging. In the first imaging mode, the user uses a phased array probe to scan the heart region, acquiring a sequence of cross-sectional images of the heart. The acquired heart cross-sectional image sequence is processed and identified to pinpoint the location of the target valve annulus, and this location is used as the sampling point for the target valve annulus. The target valve annulus can be the tricuspid valve annulus and / or the mitral valve annulus. If a tricuspid valve annulus is identified in the heart cross-sectional image sequence, the lateral ring of the tricuspid valve annulus is identified as the location point; if a mitral valve annulus is identified in the heart cross-sectional image sequence, the lateral ring of the mitral valve annulus is identified as the location point.

[0026] In one alternative implementation, before identifying the sampling points of the target valve annulus in the cardiac cross-sectional image sequence, the cross-sectional quality of the acquired cardiac cross-sectional image sequence is scored. The cross-sectional quality score is used to evaluate whether the cardiac cross-section shown in the cardiac cross-sectional image sequence conforms to the standard apical four-chamber cross-sectional image, so as to identify the sampling points of the target valve annulus under the standard apical four-chamber cross-sectional image and ensure the accuracy of the sampling imaging.

[0027] In one alternative implementation, the target valve annulus can be identified by performing image processing and key feature recognition on the cardiac cross-sectional image sequence, thereby locating the sampling point of the target valve annulus. Alternatively, a network model can be used to identify the sampling point in the cardiac cross-sectional image sequence.

[0028] Step S102: The second ultrasound imaging mode is used to image the sampling point to obtain the motion map of the target valve annulus.

[0029] In this embodiment of the invention, the second ultrasound imaging mode is an imaging mode that displays a motion spectrum, namely the M-mode imaging mode. After determining the sampling point of the target valve annulus, the system automatically switches to the second ultrasound imaging mode. In the second ultrasound imaging mode, imaging is performed at the sampling point to obtain the real-time motion curve spectrum of the target valve annulus, i.e., the motion spectrum of the target valve annulus. The motion spectrum of the target valve annulus reflects an approximate sine curve of the target valve annulus motion.

[0030] Step S103: Process the motion spectrum of the target lobe ring to determine the motion trajectory curve of the target lobe ring.

[0031] In this embodiment of the invention, the motion map of the target lobe ring is processed, and the boundary curve of the motion map is extracted to obtain the motion trajectory curve of the target lobe ring.

[0032] Step S104: Determine the valve parameters of the target valve ring based on the motion trajectory curve of the target valve ring.

[0033] In this embodiment of the invention, based on the motion trajectory curve of the target valve annulus, the valley points and peak points of the motion trajectory curve within each motion cycle are automatically identified, and the valve annulus parameters of the target valve annulus are calculated based on the distance between the valley points and peak points. The target valve annulus includes a tricuspid valve annulus and / or a mitral valve annulus. The valve annulus parameter of the tricuspid valve annulus is the tricuspid valve systolic displacement, and the valve annulus parameter of the mitral valve annulus is the mitral valve systolic displacement.

[0034] The method for measuring cardiac valve annulus parameters provided in this invention determines the sampling points of the target valve annulus based on a sequence of cardiac cross-sectional images acquired in a first ultrasound imaging mode. A second ultrasound imaging mode is then used to sample and image at these sampling points, obtaining a motion map of the target valve annulus. This eliminates the need for manual selection of sampling lines, ensuring the accuracy of the selected lines. Simultaneously, the motion map of the target valve annulus is processed to determine its motion trajectory curve. Based on this trajectory curve, the valve annulus parameters are determined, thus automatically calculating the parameters based on the acquired motion map. Therefore, by automatically selecting sampling lines and automatically calculating valve annulus parameters, the method simplifies the measurement process and improves the accuracy, consistency, and repeatability of the measurement results.

[0035] This embodiment provides a method for measuring cardiac valve annulus parameters. Figure 2 This is a schematic diagram of a second process for measuring cardiac valve annulus parameters according to an embodiment of the present invention, as shown below. Figure 2 As shown, the process includes the following steps: Step S201: In the first ultrasound imaging mode, the acquired cardiac cross-sectional image sequence is processed to determine the sampling point of the target valve annulus.

[0036] Specifically, step S201 includes: Step S2011: Preprocess the cardiac cross-sectional image sequence to obtain the preprocessed cardiac cross-sectional image sequence.

[0037] In this embodiment of the invention, the cardiac cross-sectional images are preprocessed, wherein the preprocessing operation includes at least filtering and denoising and smoothing, so as to improve the image quality of the cardiac cross-sectional images in the cardiac cross-sectional image sequence.

[0038] In step S2012, the preprocessed cardiac cross-sectional image sequence is input into the pre-trained sampling point localization model to obtain the sampling points of the target valve annulus.

[0039] In this embodiment of the invention, the preprocessed cardiac cross-sectional image sequence is input into a pre-trained sampling point model, and the sampling point model automatically identifies and outputs the sampling points of the target valve annulus in the cardiac cross-sectional image sequence.

[0040] In one alternative implementation, the sampling point localization model uses an improved YOLOv8-pose model. The sampling point localization model includes a backbone network, a neck network, and a head network. The backbone network is used for feature extraction, the neck network for feature fusion, and the head network for outputting the predicted results of the sampling points. Specifically, the backbone network includes a downsampling unit and multiple cascaded feature extraction units; the neck network includes a bidirectional feature pyramid network and an attention module.

[0041] In one alternative implementation, Figure 3 This is a schematic diagram of the sampling point localization model for cardiac valve annulus parameters according to an embodiment of the present invention, as shown below. Figure 3 As shown, the ShuffleNetv2 lightweight feature extraction network is used as the backbone network. This network reduces the number of parameters through operations such as channel separation, depthwise separable convolution, and channel rearrangement. The ShuffleNetv2 lightweight feature extraction network consists of a downsampling unit and multiple cascaded basic units, which maintains the feature extraction capability while having a relatively low computational cost.

[0042] In one alternative implementation, such as Figure 3 As shown, in the neck network, a bidirectional feature pyramid network (BiFPN) is introduced to replace the simple concatenation operation. Through bidirectional paths from top to bottom and bottom to top, feature maps of different resolutions are fused across scales, thereby enhancing the semantic expression of low-resolution features using the detailed information of high-resolution features. Simultaneously, grouped shuffling convolution (GSConv) is introduced into the BiFPN. Leveraging the advantage of grouped shuffling convolution, which only performs convolution operations on sparse locations, it effectively reduces the number of model parameters and improves runtime efficiency. Specifically, as... Figure 4 As shown, in grouped shuffle convolution, a portion of the feature map is first generated by standard convolution (Conv), and then another portion of the feature map is processed by depthwise separable convolution (DWConv). The Concat module is used to concatenate the two along the channel dimension. Finally, the feature shuffle operation is used to promote information interaction between channels, so that the model can maintain efficient and accurate feature extraction and fusion capabilities when dealing with complex scenarios.

[0043] In one alternative implementation, such as Figure 3 As shown, an attention module is introduced into the neck network to enhance the model's ability to focus on key regions of the lobe rings and suppress interference from irrelevant background information in the image. Specifically, as... Figure 5As shown, the attention module consists of two parts: channel attention and spatial attention. It aggregates the original input features with attention-weighted features through residual connections, thereby promoting the deep fusion of multi-level information. In channel attention, a local cross-channel interaction strategy is employed, eliminating dimensionality reduction and adaptively adjusting the size of the one-dimensional convolutional kernel according to the number of channels. This improves the modeling efficiency of inter-channel relationships and preserves subtle edge features of lobe-ring motion. In spatial attention, a dynamic weight generation mechanism is introduced based on the original spatial attention. Specifically, max pooling and average pooling are performed on the input features, and the results are concatenated along the channel dimension. Then, a convolutional layer is used for fusion and dimensionality reduction to generate a preliminary spatial weight map. Global average pooling is applied to the preliminary spatial weight map to extract global contextual information. Dynamic weight coefficients are generated through a 1×1 convolution and a sigmoid activation function. Finally, these coefficients are multiplied by the preliminary spatial weight map and normalized using the sigmoid function to obtain the final spatial attention map. This allows for adaptive adjustment of the weights of local features based on the global context, enhancing sensitivity to key regions.

[0044] In an optional implementation, the loss function of the YOLOv8-pose model consists of a focus loss function (DFLLoss) and a detection box loss function (CIoU Loss). The focus loss function addresses the classification imbalance problem in the object detection task, while the detection box loss function addresses the overlap between the predicted and actual detection boxes. The specific calculation method is not described here. In this embodiment, to address the problem that the detection box loss function cannot handle low-quality images and does not sufficiently emphasize the penalty term, resulting in a decrease in the model's generalization ability and thus affecting the detection performance, the WIoUv3 loss function is introduced. A wise gradient gain allocation strategy is adopted to dynamically adjust the gradient gain, effectively handling low-quality samples, thereby improving the model's performance and generalization ability. The WIoUv3 loss function is specifically shown in the following formula (1): ; ; Formula (1) in, For WIoUv3 loss function, For WIoUv1 loss function, The degree of anomaly used to describe the quality of the anchor frame. The smaller the value, the higher the quality of the anchor frame; Here, is a non-monotonic focusing coefficient, where, make when , This is a preset focus intensity coefficient. By setting a non-monotonic focus coefficient, the detection box loss is adjusted, that is, the detection box loss is adjusted according to different sample qualities, thereby avoiding overfitting to low-quality samples, preventing the bounding box loss from strengthening low-quality samples, and improving the model's detection performance.

[0045] Step S202: Imaging is performed at the sampling point using the second ultrasound imaging mode to obtain the motion map of the target lobe annulus. For details, please refer to [link to relevant documentation]. Figure 1 Step S102 of the illustrated embodiment will not be described again here.

[0046] Step S203: Process the motion map of the target lobe ring to determine its motion trajectory curve. For details, please refer to [link to relevant documentation]. Figure 1 Step S103 of the illustrated embodiment will not be described again here.

[0047] Step S204: Based on the motion trajectory curve of the target lobe annulus, determine the annulus parameters of the target lobe annulus. For details, please refer to [link to relevant documentation]. Figure 1 Step S104 of the illustrated embodiment will not be described again here.

[0048] This embodiment provides a method for measuring cardiac valve annulus parameters. Figure 6 This is a schematic diagram of the third process for measuring cardiac valve annulus parameters according to an embodiment of the present invention, as shown below. Figure 6 As shown, the process includes the following steps: Step S601: In the first ultrasound imaging mode, the acquired cardiac cross-sectional image sequence is processed to determine the sampling point of the target valve annulus. For details, please refer to [link to relevant documentation]. Figure 1 Step S101 of the illustrated embodiment will not be described again here.

[0049] Step S602: Imaging is performed at the sampling point using the second ultrasound imaging mode to obtain the motion map of the target lobe annulus. For details, please refer to [link to relevant documentation]. Figure 1 Step S102 of the illustrated embodiment will not be described again here.

[0050] Step S603: Process the motion map of the target lobe ring to determine the motion trajectory curve of the target lobe ring.

[0051] Specifically, step S603 includes: Step S6031: The motion map of the target lobe ring is binarized and smoothed to obtain the processed motion map.

[0052] In this embodiment of the invention, the motion map of the target lobe ring is binarized, and then morphological operations such as dilation and erosion are used to smooth the motion map of the target lobe ring to obtain the processed motion map.

[0053] Step S6032: Extract the upper and lower boundaries of the processed motion map to obtain the motion trajectory curve of the target lobe ring.

[0054] In this embodiment of the invention, the Sobel operator is used to extract the upper and lower boundaries from the processed motion map to obtain the motion trajectory curve of the target lobe ring.

[0055] In an optional implementation, the motion map of the target lobe ring is processed to determine the motion trajectory curve of the target lobe ring, and the process further includes: median filtering and texture feature enhancement processing of the motion map of the target lobe ring. An adaptive median filtering method is used as the median filtering method for the motion map of the target lobe ring, thereby improving the suppression effect on noise with high spatial density and more effectively preserving the edge structure information of the motion trajectory in the motion map while smoothing the noise. Gabor filtering is used as the texture feature enhancement method for the motion map of the target lobe ring. The Gabor filter is a frequency- and direction-based filter that combines the characteristics of Gaussian and sine functions, and can effectively analyze the texture features of the image in multiple directions and scales. In this embodiment, the real part of the two-dimensional Gabor wavelet is extracted as the result of the texture feature enhancement processing, as shown in the following formula (2): Formula (2) in, and These represent the pixel coordinates in the motion graph; Indicates the wavelength of the Gabor filter; This represents the tilt angle of the Gabor kernel function graph; This represents the phase offset, with a value range of -180 to 180. This represents the standard deviation of the Gaussian function; This represents the aspect ratio and determines the ellipticity of the Gabor kernel function image.

[0056] Step S604: Based on the motion trajectory curve of the target lobe annulus, determine the annulus parameters of the target lobe annulus. For details, please refer to [link to relevant documentation]. Figure 1 Step S104 of the illustrated embodiment will not be described again here.

[0057] This embodiment provides a method for measuring cardiac valve annulus parameters. Figure 7 This is a schematic diagram of the fourth process for measuring cardiac valve annulus parameters according to an embodiment of the present invention, as shown below. Figure 7 As shown, the process includes the following steps: Step S701: In the first ultrasound imaging mode, the acquired cardiac cross-sectional image sequence is processed to determine the sampling point of the target valve annulus. For details, please refer to [link to relevant documentation]. Figure 1Step S101 of the illustrated embodiment will not be described again here.

[0058] Step S702: Imaging is performed at the sampling point using the second ultrasound imaging mode to obtain the motion map of the target lobe annulus. For details, please refer to [link to relevant documentation]. Figure 1 Step S102 of the illustrated embodiment will not be described again here.

[0059] Step S703: Process the motion map of the target lobe ring to determine its motion trajectory curve. For details, please refer to [link to relevant documentation]. Figure 1 Step S103 of the illustrated embodiment will not be described again here.

[0060] Step S704: Determine the valve parameters of the target valve annulus based on the motion trajectory curve of the target valve annulus.

[0061] Specifically, step S704 includes: Step S7041: Based on the preset detection algorithm, analyze the motion trajectory curve of the target lobe ring to determine the trough and peak points of each motion cycle in the motion trajectory curve of the target lobe ring.

[0062] In this embodiment of the invention, the AMPD automatic peak detection algorithm is used as the preset detection algorithm to analyze the motion trajectory curve of the target valve annulus and identify the trough and peak points of each motion cycle in the motion trajectory curve. Each motion cycle in the motion trajectory curve corresponds to a cardiac cycle, with the trough point corresponding to the end of diastole and the peak point corresponding to the end of systole.

[0063] Step S7042: Calculate the vertical distance between the trough and crest points of each motion cycle to obtain the valve ring parameters of the target valve ring.

[0064] In this embodiment of the invention, the horizontal direction in the motion trajectory curve represents the direction of time progression, and the vertical direction represents the motion amplitude of the target lobe ring. The distance between the trough and peak points in the vertical direction of each motion cycle is calculated to obtain the lobe ring parameters of the target lobe ring.

[0065] This embodiment also provides a device for measuring cardiac valve annulus parameters, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0066] This embodiment provides a device for measuring cardiac valve annulus parameters, such as... Figure 8 As shown, it includes: The sampling point determination module 801 is used to process the acquired cardiac cross-sectional image sequence in the first ultrasound imaging mode to determine the sampling point of the target valve annulus, wherein the first ultrasound imaging mode is an imaging mode that displays two-dimensional images. The motion map acquisition module 802 is used to perform imaging at the sampling point using the second ultrasound imaging mode to obtain the motion map of the target valve annulus, wherein the second ultrasound imaging mode is an imaging mode that displays the motion map. The trajectory curve determination module 803 is used to process the motion spectrum of the target lobe ring and determine the motion trajectory curve of the target lobe ring; The annular parameter determination module 804 is used to determine the annular parameters of the target annular ring based on the motion trajectory curve of the target annular ring.

[0067] In one optional implementation, the sampling point determination module 801 includes: The preprocessing unit is used to preprocess the cardiac cross-sectional image sequence to obtain the preprocessed cardiac cross-sectional image sequence. The sampling point localization unit is used to input the preprocessed cardiac cross-sectional image sequence into the pre-trained sampling point localization model to obtain the sampling points of the target valve annulus.

[0068] In one alternative implementation, the sampling point localization model includes a backbone network, a neck network, and a head network. The backbone network is used for feature extraction, the neck network is used for feature fusion, and the head network is used to output the prediction results of the sampling points. The backbone network consists of a downsampling unit and multiple cascaded feature extraction units. The neck network consists of a bidirectional feature pyramid network and an attention module.

[0069] In one optional implementation, the trajectory curve determination module 803 includes: The motion map processing unit is used to perform binarization and smoothing on the motion map of the target lobe ring to obtain the processed motion map. The boundary extraction unit is used to extract the upper and lower boundaries of the processed motion map to obtain the motion trajectory curve of the target lobe ring.

[0070] In an optional implementation, the trajectory curve determination module 803 further includes: The motion map processing unit is also used to perform median filtering and texture feature enhancement processing on the motion map of the target lobe ring.

[0071] In one optional implementation, the lobe ring parameter determination module 804 includes: The trajectory analysis unit is used to analyze the motion trajectory curve of the target lobe ring based on a preset detection algorithm, and to determine the trough and peak points of each motion cycle in the motion trajectory curve of the target lobe ring. The distance calculation unit is used to calculate the vertical distance between the trough and crest points of each motion cycle to obtain the lobe parameters of the target lobe.

[0072] In one alternative implementation, the target valve annulus includes a tricuspid valve annulus and / or a mitral valve annulus; The annular parameters of the tricuspid valve annulus are the tricuspid valve systolic displacements, and the annular parameters of the mitral valve annulus are the mitral valve annulus systolic displacements.

[0073] The cardiac valve annulus parameter measuring device provided in this embodiment of the invention can execute the cardiac valve annulus parameter measuring method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects for executing the method. Further functional descriptions of the above modules and units are the same as in the corresponding embodiments described above, and will not be repeated here.

[0074] Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0075] The following is a detailed reference. Figure 9 This diagram illustrates a structural schematic suitable for implementing an electronic device according to embodiments of the present invention. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 901, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 902 or a program loaded from memory 908 into random access memory (RAM) 903. The RAM 903 also stores various programs and data required for the operation of the electronic device. The processor 901, ROM 902, and RAM 903 are interconnected via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0076] Typically, the following devices can be connected to I / O interface 905: input devices 906 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 907 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 908 including, for example, magnetic tapes, hard disks, etc.; and communication devices 909. Communication device 909 allows electronic devices to exchange data via wireless or wired communication with other devices. Although Figure 9 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0077] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 909, or installed from a memory 908, or installed from a ROM 902. When the computer program is executed by the processor 901, it performs the functions defined in the method for measuring cardiac valve annulus parameters according to embodiments of the present invention.

[0078] Figure 9 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of the present invention.

[0079] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the method for measuring cardiac valve annulus parameters shown in the above embodiments is implemented.

[0080] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0081] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for measuring cardiac valve annulus parameters, characterized in that, The method includes: In the first ultrasound imaging mode, the acquired cardiac cross-sectional image sequence is processed to determine the sampling point of the target valve annulus, wherein the first ultrasound imaging mode is an imaging mode that displays two-dimensional images. Imaging is performed at the sampling point using a second ultrasound imaging mode to obtain the motion map of the target valve annulus, wherein the second ultrasound imaging mode is an imaging mode that displays the motion map; The motion map of the target lobe ring is processed to determine the motion trajectory curve of the target lobe ring; Based on the motion trajectory curve of the target lobe, the lobe parameters of the target lobe are determined.

2. The method according to claim 1, characterized in that, The process of processing the acquired cardiac cross-sectional image sequence to determine the sampling points of the target valve annulus includes: The heart cross-sectional image sequence is preprocessed to obtain a preprocessed heart cross-sectional image sequence; The preprocessed cardiac cross-sectional image sequence is input into a pre-trained sampling point localization model to obtain the sampling points of the target valve annulus.

3. The method according to claim 2, characterized in that, The sampling point localization model includes a backbone network, a neck network, and a head network. The backbone network is used for feature extraction, the neck network is used for feature fusion, and the head network is used to output the prediction results of the sampling points. The backbone network includes a downsampling unit and multiple cascaded feature extraction units. The neck network includes a bidirectional feature pyramid network and an attention module.

4. The method according to claim 1, characterized in that, The process of processing the motion map of the target lobe annulus to determine the motion trajectory curve of the target lobe annulus includes: The motion map of the target lobe ring is binarized and smoothed to obtain the processed motion map. The upper and lower boundaries of the processed motion map are extracted to obtain the motion trajectory curve of the target lobe ring.

5. The method according to claim 4, characterized in that, The step of processing the motion map of the target lobe annulus to determine the motion trajectory curve of the target lobe annulus further includes: The motion map of the target lobe ring is subjected to median filtering and texture feature enhancement.

6. The method according to claim 1, characterized in that, The determination of the lobe parameters of the target lobe based on the motion trajectory curve of the target lobe includes: Based on a preset detection algorithm, the motion trajectory curve of the target lobe ring is analyzed to determine the trough and peak points of each motion cycle in the motion trajectory curve of the target lobe ring. The vertical distance between the trough and the crest of each motion cycle is calculated to obtain the valve ring parameters of the target valve ring.

7. The method according to any one of claims 1-6, characterized in that, The target valve annulus includes a tricuspid valve annulus and / or a mitral valve annulus; The annular parameters of the tricuspid valve annulus are the tricuspid valve systolic displacements, and the annular parameters of the mitral valve annulus are the mitral valve annulus systolic displacements.

8. A device for measuring cardiac valve annulus parameters, characterized in that, The device includes: The sampling point determination module is used to process the acquired cardiac cross-sectional image sequence in the first ultrasound imaging mode to determine the sampling point of the target valve annulus, wherein the first ultrasound imaging mode is an imaging mode that displays two-dimensional images. The motion map acquisition module is used to perform imaging at the sampling point using a second ultrasound imaging mode to obtain the motion map of the target valve annulus, wherein the second ultrasound imaging mode is an imaging mode that displays the motion map; The trajectory curve determination module is used to process the motion map of the target lobe ring and determine the motion trajectory curve of the target lobe ring. The valve annulus parameter determination module is used to determine the valve annulus parameters of the target valve annulus based on the motion trajectory curve of the target valve annulus.

9. An electronic device, characterized in that, include: A memory and a processor are communicatively connected, the memory storing computer instructions, and the processor executing the computer instructions to perform the method for measuring cardiac valve annulus parameters according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a computer to perform the method for measuring cardiac valve annulus parameters according to any one of claims 1 to 7.

Images