Method, apparatus and electronic device for generating a cardiac video based on electromagnetic signals

Abstract

The present invention provides a method, device and electronic device for generating a cardiac video based on electromagnetic signals, which can be applied to the field of electromagnetic induction technology. The method for generating a cardiac video based on electromagnetic signals includes: determining a target electromagnetic echo signal corresponding to the cardiac region of a to-be-detected object, wherein the target electromagnetic echo signal includes the heartbeat motion characteristics after eliminating the respiratory motion characteristics; performing feature mapping processing on the target electromagnetic echo signal by using an encoder of an electromechanical modal conversion model to obtain the target mechanical motion state characteristics of the cardiac region, wherein the target mechanical motion state characteristics correspond to the characteristics of the electrocardiogram motion state of the to-be-detected object; and using an ultrasonic cardiac video sub-model of the electromechanical modal conversion model to process the target mechanical motion state characteristics and a conditional image to generate a target ultrasonic cardiac video of the to-be-detected object, wherein the conditional image represents an ultrasonic cardiac template image.

Description

Technical Field

[0001] The present invention relates to the technical field of electromagnetic induction, and more particularly to a method, apparatus, and electronic device for generating a cardiac video based on electromagnetic signals. Background Art

[0002] Echocardiographic video is one of the current important biomedical images. Since the process of obtaining the echocardiographic video of the target using an ultrasound device has the advantages of non-invasiveness and high safety, it is widely used in medical examinations to serve as an intermediate result for targeted diagnosis of the above-mentioned target. Further, due to the large volume of the ultrasound probe and the need to connect it to a large control device, the acquisition scenario of the echocardiographic video is limited. Therefore, scientific researchers use electromagnetic signals to monitor the cardiac activity of the target.

[0003] In the process of implementing the above inventive concept, it is found that in the related art, since only some parameters related to the heart can be obtained from the electromagnetic signal, it is difficult to obtain a complete and accurate cardiac activity image. Further, due to the relatively weak floating of the thoracic surface caused by the heartbeat, it is difficult to obtain high-precision heartbeat characteristics from the electromagnetic signal, and thus it is difficult to accurately convert the body surface movement - cardiac movement. Summary of the Invention

[0004] In view of the above problems, the present invention provides a method, apparatus, and electronic device for generating a cardiac video based on electromagnetic signals.

[0005] According to a first aspect of the present invention, there is provided a method for generating a cardiac video based on electromagnetic signals, including: determining a target electromagnetic echo signal corresponding to the cardiac region of a to-be-measured object, where the target electromagnetic echo signal includes a heartbeat motion feature after eliminating the respiratory motion feature; performing feature mapping processing on the target electromagnetic echo signal by an encoder of an electromechanical modal conversion model to obtain a target mechanical motion state feature of the cardiac region, where the target mechanical motion state feature corresponds to the feature of the electrocardiographic motion state of the to-be-measured object; and processing the target mechanical motion state feature and a conditional image by an echocardiographic video sub-model of the electromechanical modal conversion model to generate a target echocardiographic video of the to-be-measured object, where the conditional image represents an echocardiographic template image.

[0006] According to an embodiment of the present invention, determining a target electromagnetic echo signal corresponding to the cardiac region of an object to be measured includes: obtaining a plurality of initial electromagnetic echo signals of the object to be measured, where the initial electromagnetic echo signals include a plurality of signals that are spatially aliased with each other and reflected by a plurality of body regions of the object to be measured within a predetermined time period; performing a fast Fourier transform on the plurality of initial electromagnetic echo signals to determine the round-trip propagation distance of each initial electromagnetic echo signal, where the round-trip propagation distance represents the propagation distance of the transmitted signal from the transmitting antenna to the body region and the propagation distance of the initial electromagnetic echo signal from the body region to the receiving antenna; determining a target round-trip propagation distance from the plurality of round-trip propagation distances based on the position information of the object to be measured; and processing each initial electromagnetic echo signal corresponding to the target round-trip propagation distance to obtain the target electromagnetic echo signal.

[0007] According to an embodiment of the present invention, processing each initial electromagnetic echo signal corresponding to the target round-trip propagation distance to obtain the target electromagnetic echo signal includes: determining each initial electromagnetic echo signal corresponding to the target round-trip propagation distance as a plurality of intermediate electromagnetic echo signals; performing a fast Fourier transform on the plurality of intermediate electromagnetic echo signals to determine the propagation angle of each intermediate electromagnetic echo signal, where the propagation angle represents the angle between the intermediate electromagnetic echo signal and the object to be measured; determining a target propagation angle from the plurality of propagation angles based on the angle information of the object to be measured relative to the receiving antenna; and performing a second-order difference filtering process on the intermediate electromagnetic echo signal corresponding to the target propagation angle to obtain the target electromagnetic echo signal.

[0008] According to an embodiment of the present invention, using the ultrasonic echocardiogram video sub-model of the electromechanical modal conversion model to process the target mechanical motion state characteristics and the conditional image to generate the target ultrasonic echocardiogram video of the object to be measured includes: obtaining a Gaussian noise matrix for the ultrasonic echocardiogram video; inputting the Gaussian noise matrix, the target mechanical motion state characteristics, and the conditional image into the ultrasonic echocardiogram video sub-model, and based on the target mechanical motion state characteristics and the conditional image, the ultrasonic echocardiogram video sub-model performs a denoising process on the Gaussian noise matrix to generate the target ultrasonic echocardiogram video of the object to be measured.

[0009] According to an embodiment of the present invention, the electromechanical modal conversion model is trained in the following manner, including: obtaining the electromechanical modal conversion model to be trained and a training sample data set, wherein the electromechanical modal conversion model to be trained includes an encoder and an ultrasonic echocardiogram video sub-model to be trained, and the training sample data set includes electromagnetic echo signal samples, ultrasonic electrocardiogram signal samples, ultrasonic echocardiogram video samples, and Gaussian noise samples; inputting the ultrasonic electrocardiogram signal samples into the encoder for feature mapping processing to output electrocardiogram motion state feature samples; inputting the electrocardiogram motion state feature samples and the ultrasonic echocardiogram video samples into the ultrasonic echocardiogram video sub-model to be trained for processing to generate training ultrasonic video noise features; based on a video noise loss function, obtaining a video noise loss value according to the training ultrasonic video noise features and the Gaussian noise samples; and adjusting the model parameters of the ultrasonic echocardiogram video sub-model to be trained according to the video noise loss value to obtain the trained electromechanical modal conversion model.

[0010] According to an embodiment of the present invention, the encoder of the electromechanical modal conversion model to be trained is trained in the following manner, including: obtaining an initial encoder to be trained and a decoder to be trained for electrocardiogram, wherein the initial encoder includes an electromagnetic encoder to be trained and an electrocardiogram encoder to be trained; inputting the electromagnetic echo signal samples into the electromagnetic encoder to be trained for feature mapping processing to generate mechanical motion state feature samples; inputting the ultrasonic electrocardiogram signal samples into the electrocardiogram encoder to be trained for feature mapping processing to obtain electrocardiogram motion state feature samples; inputting the electrocardiogram motion state feature samples into the decoder to be trained for electrocardiogram for signal reconstruction processing to obtain ultrasonic electrocardiogram reconstruction signals; obtaining a modal conversion loss value according to a predetermined modal conversion loss function, the mechanical motion state feature samples, the electrocardiogram motion state feature samples, the ultrasonic electrocardiogram reconstruction signals, and the ultrasonic electrocardiogram signal samples; adjusting the model parameters of the initial encoder to be trained and the decoder to be trained for electrocardiogram according to the modal conversion loss value to obtain the trained encoder and decoder for electrocardiogram; and determining the trained encoder as the encoder of the electromechanical modal conversion model to be trained.

[0011] According to an embodiment of the present invention, obtaining a modal conversion loss value according to a predetermined modal conversion loss function, the mechanical motion state feature samples, the electrocardiogram motion state feature samples, the ultrasonic electrocardiogram reconstruction signals, and the ultrasonic electrocardiogram signal samples includes: obtaining a motion state feature similarity according to a predetermined motion state feature similarity function, the mechanical motion state feature samples, and the electrocardiogram motion state feature samples; obtaining a reconstruction signal feature similarity according to a predetermined reconstruction signal feature similarity function, the ultrasonic electrocardiogram reconstruction signals, and the ultrasonic electrocardiogram signal samples; and obtaining a modal conversion loss value according to a predetermined modal conversion loss function, a balance parameter, the motion state feature similarity, and the reconstruction signal feature similarity.

[0012] According to an embodiment of the present invention, an electrocardiogram exercise state feature sample and an echocardiogram video sample are input into an echocardiogram video sub-model to be trained for processing, and training echocardiogram video noise features are output, including: adding a Gaussian noise sample to the echocardiogram video sample to obtain an echocardiogram noise video; inputting the echocardiogram noise video, the electrocardiogram exercise state feature sample, and the echocardiogram video sample into the echocardiogram video sub-model to be trained for denoising processing, and outputting training echocardiogram video noise features.

[0013] A second aspect of the present invention provides a device for generating an echocardiogram video based on electromagnetic signals. The device includes: a determination module for determining a target electromagnetic echo signal corresponding to the cardiac region of a to-be-detected object, where the target electromagnetic echo signal includes a heartbeat motion feature after eliminating the respiratory motion feature; a feature mapping module for performing feature mapping processing on the target electromagnetic echo signal by using an encoder of an electromechanical modal conversion model to obtain a target mechanical motion state feature of the cardiac region, where the target mechanical motion state feature corresponds to the feature of the electrocardiogram motion state of the to-be-detected object; a generation module for processing the target mechanical motion state feature and a conditional image by using an echocardiogram video sub-model of the electromechanical modal conversion model to generate a target echocardiogram video of the to-be-detected object, where the conditional image represents an echocardiogram template image.

[0014] A third aspect of the present invention provides an electronic device, including: one or more processors; a memory for storing one or more programs, where when the one or more programs are executed by the one or more processors, the one or more processors are caused to execute the above method.

[0015] A fourth aspect of the present invention further provides a computer-readable storage medium, on which executable instructions are stored, and when the instructions are executed by a processor, the processor is caused to execute the above method.

[0016] A fifth aspect of the present invention further provides a computer program product, including a computer program, and when the computer program is executed by a processor, the above method is implemented.

[0017] The method, device and electronic device for generating an echocardiogram video based on electromagnetic signals according to the present invention determine a target electromagnetic echo signal corresponding to the heart region of a subject to be measured, perform feature mapping processing on the target electromagnetic echo signal by using an encoder of an electromechanical modal conversion model to obtain target mechanical motion state features of the heart region, and use an echocardiogram video sub-model of the electromechanical modal conversion model to process the target mechanical motion state features and a conditional image to generate a target echocardiogram video of the subject to be measured. It realizes high-precision measurement of the subject to be measured without using ultrasound equipment limited by the scene, and extracts the received electromagnetic echo signals. Based on the electromagnetic echo signals corresponding only to the heart region, high-precision heartbeat mechanical motion state features of the subject to be measured can be obtained, so as to accurately convert the body surface motion of the subject to be measured into heart motion, obtain relevant features that can be used to generate heart activity images, and generate a precise and complete echocardiogram video of the subject to be measured. Without contacting the subject to be measured, the monitoring experience of the subject to be measured is improved, and it is easier for professionals and the subject to be measured to perform convenient operations.

[0018] According to an embodiment of the present invention, further, an electromechanical modal conversion model is built based on the encoder and the echocardiogram video sub-model, and a large number of model trainings are performed on the built electromechanical modal conversion model. By using the encoder of the pre-trained electromechanical modal conversion model to process the target electromagnetic echo signal, high-precision target mechanical motion state features of the heart of the subject to be measured are obtained. Also, since the target mechanical motion state features extracted by the encoder of the model are similar to the features of the electrocardiogram motion state of the subject to be measured, the target mechanical motion state features extracted by the encoder can be infinitely close to the true heart mechanical activity features of the subject to be measured. So as to input the target mechanical motion state features as the features of the electrocardiogram motion state into the echocardiogram video sub-model of the pre-trained electromechanical modal conversion model, and perform related video generation processing on the pre-prepared echocardiogram template image of the heart according to the target mechanical motion state features, improving the processing efficiency in the application process and reducing the working cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Through the following description of the embodiments of the present invention with reference to the drawings, the above content and other objects, features and advantages of the present invention will become clearer. In the drawings:

[0020] Figure 1 An application scenario diagram of the method for generating an echocardiogram video based on electromagnetic signals according to an embodiment of the present invention is shown;

[0021] Figure 2 A flowchart of the method for generating an echocardiogram video based on electromagnetic signals according to an embodiment of the present invention is shown;

[0022] Figure 3a Shows a schematic diagram of an actual echocardiogram according to an embodiment of the present invention;

[0023] Figure 3b Shows a schematic diagram of a radar image of the heart obtained by using the method of the present invention according to an embodiment of the present invention;

[0024] Figure 4 Shows a schematic diagram of a comparison of the left ventricular volume obtained from partial mechanical motion state characteristics and actual partial heart motion states according to the present invention according to an embodiment of the present invention;

[0025] Figure 5 Shows a schematic diagram of a comparison of the left ventricular volume obtained from all mechanical motion state characteristics and actual all heart motion states according to the present invention according to an embodiment of the present invention;

[0026] Figure 6 Shows a block diagram of a device for generating a cardiac video based on electromagnetic signals according to an embodiment of the present invention;

[0027] Figure 7 Shows a block diagram of an electronic device for a method of generating a cardiac video based on electromagnetic signals according to an embodiment of the present invention. Detailed implementation manners

[0028] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are merely exemplary and are not intended to limit the scope of the present invention. In the following detailed description, for the sake of explanation, many specific details are set forth in order to provide a thorough understanding of the embodiments of the present invention. However, obviously, one or more embodiments can be implemented without these specific details. In addition, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessarily obscuring the concepts of the present invention.

[0029] The terms used herein are merely for describing specific embodiments and are not intended to limit the present invention. The terms "including", "comprising", etc. used herein indicate the presence of the described features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0030] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0031] In the case of using expressions such as "at least one of A, B, and C", generally, it should be interpreted according to the meaning that those skilled in the art usually understand this expression (for example, "a system having at least one of A, B, and C" should include, but not be limited to, a system having only A, only B, only C, having A and B, having A and C, having B and C, and / or having A, B, and C, etc.).

[0032] In the technical solution of the present invention, the user information involved (including but not limited to user personal information, user image information, user device information, such as location information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) are all information and data authorized by the user or fully authorized by all parties. Moreover, the processing of relevant data, such as collection, storage, use, processing, transmission, provision, disclosure, and application, all comply with relevant laws, regulations, and standards, adopt necessary confidentiality measures, do not violate public order and good customs, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0033] As a non-invasive, safe, and effective method, echocardiographic videos are widely used in medical examinations to help provide targeted diagnoses as intermediate results. By observing the propagation of ultrasonic waves in the human body, echocardiographic videos can display the motion state of the heart, thereby providing video image information that can assist in the diagnosis of diseases. However, the acquisition process of echocardiographic videos is restricted by factors such as the standardization of the operator's acquisition process and the variability of the instrument, and common ultrasonic probes are relatively large in size and need to be connected to large control devices, thus greatly limiting the acquisition scenarios of echocardiographic videos.

[0034] On this basis, since physiological activity monitoring based on electromagnetic signals has advantages such as dynamic monitoring, non-invasiveness, and ease of use, it has been widely applied in monitoring fields such as home health monitoring, remote patient monitoring, and public place health monitoring to help relevant professionals with auxiliary diagnoses. During the research and development process, it was found that in related technologies, since only some parameters related to the heart can be obtained from electromagnetic signals, it is difficult to obtain a complete and accurate image of heart activity. Further, due to the relatively weak floating of the chest surface caused by heartbeats, it is difficult to obtain high-precision heartbeat characteristics from electromagnetic signals, and thus it is difficult to achieve an accurate conversion of body surface motion - heart motion.

[0035] In view of this, an embodiment of the present invention provides a method for generating a cardiac video based on electromagnetic signals, including: determining a target electromagnetic echo signal corresponding to the cardiac region of a subject to be measured, where the target electromagnetic echo signal includes the cardiac motion characteristics after eliminating the respiratory motion characteristics; performing feature mapping processing on the target electromagnetic echo signal by using an encoder of an electromechanical modal conversion model to obtain the target mechanical motion state characteristics of the cardiac region, where the target mechanical motion state characteristics correspond to the characteristics of the electrocardiogram motion state of the subject to be measured; and using an ultrasonic cardiogram video sub-model of the electromechanical modal conversion model to process the target mechanical motion state characteristics and a conditional image to generate a target ultrasonic cardiogram video of the subject to be measured, where the conditional image represents an ultrasonic cardiogram template image.

[0036] Figure 1 FIG. shows an application scenario diagram of a method for generating a cardiac video based on electromagnetic signals according to an embodiment of the present invention.

[0037] As Figure 1 shown, the application scenario according to this embodiment may include a first radar device 101, a target object 102, and a receiver 103. The first radar device 101 is used to send an electromagnetic wave signal to the target object 102.

[0038] The user can use the first radar device 101 to interact with the target object 102 and the receiver 103 to receive or send signals, etc.

[0039] The receiver 103 may be a receiver that receives various electromagnetic echo signals, such as receiving and processing the electromagnetic signals sent by the first radar device 101 (only for example). The receiver 103 can analyze and process data such as the received electromagnetic echo signals, and feedback the processing results (such as obtaining or generating relevant measurement data according to a user request, etc.) to the terminal device.

[0040] It should be noted that the method for generating a cardiac video based on electromagnetic signals provided by the embodiment of the present invention can generally be executed by the receiver 103. Correspondingly, the device for generating a cardiac video based on electromagnetic signals provided by the embodiment of the present invention can generally be set in the receiver 103. The method for generating a cardiac video based on electromagnetic signals provided by the embodiment of the present invention can also be executed by a receiver or a cluster of receivers that is different from the receiver 103 and can communicate with the first radar device 101 and / or the receiver 103. Correspondingly, the device for generating a cardiac video based on electromagnetic signals provided by the embodiment of the present invention can also be set in a receiver or a cluster of receivers that is different from the receiver 103 and can communicate with the first radar device 101 and / or the receiver 103.

[0041] It should be understood, Figure 1The numbers of the first radar device, the target object, and the receiver in [description] are merely illustrative. According to the implementation requirements, any number of radar devices, observed objects, and receivers can be provided.

[0042] Based on the Figure 1 described scenario, the method for generating a cardiac video based on electromagnetic signals according to the embodiments of the invention will be described in detail through Figures 2 to 5 the following.

[0043] Figure 2 FIG. shows a flowchart of a method for generating a cardiac video based on electromagnetic signals according to an embodiment of the present invention.

[0044] As Figure 2 shown, the method for generating a cardiac video based on electromagnetic signals in this embodiment includes operations S210 to S230.

[0045] In operation S210, a target electromagnetic echo signal corresponding to the cardiac region of the object to be measured is determined.

[0046] According to an embodiment of the present invention, the target electromagnetic echo signal includes a heartbeat motion feature after eliminating the respiratory motion feature.

[0047] According to an embodiment of the present invention, an electromagnetic signal is transmitted to multiple body regions of the object to be measured by using a transmitting antenna. When the multiple body regions of the object to be measured receive the electromagnetic signal, an electromagnetic echo signal is generated and the electromagnetic echo signal is reflected to the receiving antenna. Thus, a target electromagnetic echo signal corresponding to the cardiac region of the object to be measured can be determined from the multiple electromagnetic echo signals, so as to process the heart of the object to be measured according to the target electromagnetic echo signal corresponding to the cardiac region and obtain an accurate echocardiogram video.

[0048] In operation S220, the target electromagnetic echo signal is subjected to feature mapping processing by using an encoder of an electromechanical modal conversion model to obtain a target mechanical motion state feature of the cardiac region.

[0049] According to an embodiment of the present invention, the target mechanical motion state feature corresponds to the feature of the electrocardiogram motion state of the object to be measured, that is, the target mechanical motion state feature is similar to the feature of the electrocardiogram motion state, so that both features are infinitely close to the true cardiac mechanical activity feature.

[0050] According to an embodiment of the present invention, an encoder of a pre-trained electromechanical modal conversion model is used to perform extraction and mapping processing on the features in the obtained accurate target electromagnetic echo signal to obtain a target mechanical motion state feature of the cardiac region of the object to be measured.

[0051] In operation S230, the echocardiogram video sub-model of the electromechanical modal conversion model processes the target mechanical motion state features and the conditional image to generate the target echocardiogram video of the object to be measured.

[0052] According to an embodiment of the present invention, the conditional image can represent an echocardiogram template image.

[0053] According to an embodiment of the present invention, when the echocardiogram historical image of the object to be measured is included in the template image database, the echocardiogram historical image of the object to be measured can be input into the echocardiogram video sub-model of the electromechanical modal conversion model as the conditional image to generate the target echocardiogram video of the object to be measured. When the echocardiogram historical image of the object to be measured is not included in the template image database, the echocardiogram template image can be input into the echocardiogram video sub-model of the electromechanical modal conversion model to generate the target echocardiogram video of the object to be measured.

[0054] According to an embodiment of the present invention, based on the obtained target echocardiogram video, it can help relevant personnel to judge the relevant functions of the target.

[0055] For example, an electromagnetic signal is emitted to the heart of the target object, multiple electromagnetic echo signals are received by a receiving antenna, the target electromagnetic echo signal corresponding to the heart region of the target object is determined from the multiple electromagnetic echo signals, the target electromagnetic echo signal is subjected to feature mapping processing by the encoder of the trained electromechanical modal conversion model, the mechanical motion features of the heart in the target electromagnetic echo signal of the target object are extracted to obtain the target mechanical motion state features, and then the target mechanical motion state features and the echocardiogram template image are input into the echocardiogram video sub-model of the trained electromechanical modal conversion model for processing to generate the target echocardiogram video of the target object, so that scientific personnel or professionals in related fields can distinguish the heart function of the target object according to the target echocardiogram video of the target object, and thus make a judgment suitable for the target object.

[0056] According to an embodiment of the present invention, by determining a target electromagnetic echo signal corresponding to the cardiac region of the object to be measured, using the encoder of the electromechanical modal conversion model to perform feature mapping processing on the target electromagnetic echo signal, obtaining the target mechanical motion state feature of the cardiac region, and using the echocardiogram video sub-model of the electromechanical modal conversion model to process the target mechanical motion state feature and the conditional image, a target echocardiogram video of the object to be measured is generated. It is realized that without using an ultrasound device limited by the scenario, a non-contact radar device can be used to perform high-fine-grained measurement on the object to be measured and extract the received electromagnetic echo signal. Based on the electromagnetic echo signal corresponding only to the cardiac region, the high-precision heartbeat mechanical motion state feature of the object to be measured can be obtained, so as to realize the accurate conversion from the body surface motion to the cardiac motion of the object to be measured, obtain the relevant features that can be used to generate cardiac activity images, and generate a precise and complete echocardiogram video of the object to be measured. Without contacting the object to be measured, the monitoring experience of the object to be measured is improved, and it is easier for professionals and the object to be measured to perform convenient operations.

[0057] According to an embodiment of the present invention, further, an electromechanical modal conversion model is built based on the encoder and the echocardiogram video sub-model, and a large number of model trainings are performed on the built electromechanical modal conversion model. By using the encoder of the pre-trained electromechanical modal conversion model to process the target electromagnetic echo signal, the high-fine-grained target mechanical motion state feature of the heart of the object to be measured is obtained. Also, since the target mechanical motion state feature extracted by the encoder of the model is similar to the feature of the electrocardiogram motion state of the object to be measured, the target mechanical motion state feature extracted by the encoder can be infinitely close to the true cardiac mechanical activity feature of the object to be measured. So as to input the target mechanical motion state feature as the feature of the electrocardiogram motion state into the echocardiogram video sub-model of the pre-trained electromechanical modal conversion model, and perform relevant video generation processing on the pre-prepared echocardiogram template image of the heart according to the target mechanical motion state feature, improving the processing efficiency in the application process and reducing the working cost.

[0058] It should be noted that the target echocardiogram video obtained by the present invention is only used as an intermediate result, and the diagnostic result or health status cannot be directly obtained from the target echocardiogram video obtained by the method according to the present invention.

[0059] According to an embodiment of the present invention, the method for determining the target electromagnetic echo signal corresponding to the cardiac region of the object to be measured includes the following operations.

[0060] According to an embodiment of the present invention, a plurality of initial electromagnetic echo signals of the object to be measured are obtained.

[0061] According to an embodiment of the present invention, the initial electromagnetic echo signal includes a plurality of signals that are spatially aliased with each other and reflected by multiple body regions of the object to be measured within a predetermined time period.

[0062] According to an embodiment of the present invention, an electromagnetic signal is transmitted to multiple body regions of the object to be measured by using a transmitting antenna, so that multiple body regions generate a plurality of electromagnetic echo signals that are spatially aliased with each other after receiving the electromagnetic signal, and the plurality of spatially aliased electromagnetic echo signals are reflected to the receiving antenna.

[0063] According to an embodiment of the present invention, a plurality of initial electromagnetic echo signals can be represented according to formula (1).

[0064] (1);

[0065] Wherein, S(x, y, z, m) can be characterized as the initial electromagnetic echo signal, N can be characterized as the total number of channels for transmitting signals composed of the transmitting antenna and the receiving antenna, n can be characterized as the nth channel, M can be characterized as the total duration of receiving the electromagnetic echo signal, m can be characterized as the tth moment, y n,t can be characterized as the electromagnetic echo signal received by the nth channel at the tth moment, k can be characterized as the frequency modulation slope, can be characterized as the wavelength of the radio frequency signal, (x, y, z) can be characterized as the coordinates in the three-dimensional space, and r(x, y, z, n) can be characterized as the round-trip propagation distance of the electromagnetic echo signal reflected to (x, y, z) in the nth channel.

[0066] According to an embodiment of the present invention, a fast Fourier transform is performed on a plurality of initial electromagnetic echo signals to determine the round-trip propagation distance of each initial electromagnetic echo signal.

[0067] According to an embodiment of the present invention, the round-trip propagation distance characterizes the propagation distance of the transmitted signal from the transmitting antenna to the body region and the propagation distance of the initial electromagnetic echo signal from the body region to the receiving antenna.

[0068] According to an embodiment of the present invention, there are multiple channels for transmitting electromagnetic signals and initial electromagnetic echo signals, and the round-trip propagation distance can be the sum of the round-trip transmission distances of the radar signal in any one channel.

[0069] According to an embodiment of the present invention, the round-trip propagation distances of multiple initial electromagnetic echo signals can be the same.

[0070] According to an embodiment of the present invention, based on the position information of the object to be measured, a target round-trip propagation distance is determined from a plurality of round-trip propagation distances.

[0071] According to an embodiment of the present invention, the position information of the chest region of the object to be measured can be obtained, and based on the position information of the object to be measured, the target round-trip propagation distance can be determined. For example, if the distance between the chest region of the object to be measured and the radar antenna is 1 m, then the target round-trip propagation distance is determined to be 2 m.

[0072] According to an embodiment of the present invention, each initial electromagnetic echo signal corresponding to the target round-trip propagation distance is processed to obtain a target electromagnetic echo signal.

[0073] According to an embodiment of the present invention, a plurality of initial electromagnetic echo signals corresponding to the target round-trip distance are determined according to the target round-trip distance, and the determined initial electromagnetic echo signals are processed to obtain a target electromagnetic echo signal. For example, if the target round-trip propagation distance is 2 m, the round-trip propagation distance of the first initial electromagnetic echo signal in the channel is 3 m, the round-trip propagation distance of the second initial electromagnetic echo signal in the channel is 2 m, the round-trip propagation distance of the third initial electromagnetic echo signal in the channel is 9 m, and the round-trip propagation distance of the fourth initial electromagnetic echo signal in the channel is 2 m, then from all the initial electromagnetic echo signals, it is determined that the second initial electromagnetic echo signal and the fourth initial electromagnetic echo signal corresponding to the target round-trip propagation distance are processed to obtain a target electromagnetic echo signal.

[0074] According to an embodiment of the present invention, by acquiring a plurality of initial electromagnetic echo signals of the object to be measured, performing a fast Fourier transform on the plurality of initial electromagnetic echo signals, determining the round-trip propagation distance of each initial electromagnetic echo signal, and based on the position information of the object to be measured, determining the target round-trip propagation distance from the plurality of round-trip propagation distances, and processing each initial electromagnetic echo signal corresponding to the target round-trip propagation distance to obtain a target electromagnetic echo signal, it is realized to obtain a target electromagnetic echo signal corresponding to the heart region from the initial electromagnetic echo signals corresponding to a plurality of body regions based on the electromagnetic signal emitted by the radar device and the initially received reflected electromagnetic echo signal, so as to process the target electromagnetic echo signal corresponding to the heart region, thereby accurately extracting the high-precision heartbeat characteristics of the object to be measured, and further realizing the accurate conversion of body surface movement-heart movement, so as to obtain more accurate and comprehensive partial parameters related to the heart, and thus generate a complete and accurate heart activity image.

[0075] According to an embodiment of the present invention, the method for processing each initial electromagnetic echo signal corresponding to the target round-trip propagation distance to obtain a target electromagnetic echo signal includes the following operations.

[0076] According to an embodiment of the present invention, each initial electromagnetic echo signal corresponding to the target round-trip propagation distance is determined as a plurality of intermediate electromagnetic echo signals.

[0077] For example, if the target round-trip propagation distance is 2m, the round-trip propagation distance of the first initial electromagnetic echo signal in the channel is 3m, the round-trip propagation distance of the second initial electromagnetic echo signal in the channel is 2m, the round-trip propagation distance of the third initial electromagnetic echo signal in the channel is 9m, and the round-trip propagation distance of the fourth initial electromagnetic echo signal in the channel is 2m, then from all the initial electromagnetic echo signals, the second and fourth initial electromagnetic echo signals corresponding to the target round-trip propagation distance are determined as the intermediate electromagnetic echo signals.

[0078] According to an embodiment of the present invention, perform a fast Fourier transform on multiple intermediate electromagnetic echo signals to determine the propagation angle of each intermediate electromagnetic echo signal.

[0079] According to an embodiment of the present invention, the propagation angle can be characterized as the angle between the intermediate electromagnetic echo signal and the object to be measured.

[0080] According to an embodiment of the present invention, based on the angle information of the object to be measured relative to the receiving antenna, determine the target propagation angle from multiple propagation angles.

[0081] According to an embodiment of the present invention, determine the angle that is close to the angle information of the object to be measured relative to the receiving antenna from multiple propagation angles as the target propagation angle. For example, if the angle of the object to be measured relative to the receiving antenna is 50°, the angle of the first intermediate electromagnetic echo signal is 88°, the angle of the second intermediate electromagnetic echo signal is 51°, and the angle of the third intermediate electromagnetic echo signal is 26°, then it is confirmed that the target propagation angle is 51°.

[0082] According to an embodiment of the present invention, perform a second-order difference filtering process on the intermediate electromagnetic echo signal corresponding to the target propagation angle to obtain the target electromagnetic echo signal.

[0083] For example, if the angle of the first intermediate electromagnetic echo signal is 88°, the angle of the second intermediate electromagnetic echo signal is 51°, the angle of the third intermediate electromagnetic echo signal is 26°, and the target propagation angle is 51°, then perform a second-order difference filtering process on the second intermediate electromagnetic echo signal to obtain the target electromagnetic echo signal.

[0084] According to an embodiment of the present invention, since the acceleration of respiratory movement is less than the acceleration of heartbeats, the respiratory movement characteristics in the intermediate electromagnetic echo signal are removed through the second-order difference filtering process, so as to retain the heartbeat movement characteristics.

[0085] According to an embodiment of the present invention, the target electromagnetic echo signal after the second-order difference filtering process is as shown in formula (2).

[0086] (2);

[0087] Among them, can be characterized as the target electromagnetic echo signal, h can be characterized as the frame period time, s 0 can be characterized as the phase result of the electromagnetic echo signal received at the current moment, s 1 can be characterized as the phase result of the electromagnetic echo signal received at a moment after the current moment, s -1 can be characterized as the phase result of the electromagnetic echo signal received at a moment before the current moment, s 2 can be characterized as the phase result of the electromagnetic echo signal received at two moments after the current moment, s -2 can be characterized as the phase result of the electromagnetic echo signal received at two moments before the current moment, s 3 can be characterized as the phase result of the electromagnetic echo signal received at three moments after the current moment, s -3 can be characterized as the phase result of the electromagnetic echo signal received at three moments before the current moment.

[0088] According to an embodiment of the present invention, by determining each initial electromagnetic echo signal corresponding to the target two-way propagation distance as a plurality of intermediate electromagnetic echo signals, performing a fast Fourier transform on the plurality of intermediate electromagnetic echo signals, determining the propagation angle of each intermediate electromagnetic echo signal, based on the angle information of the object to be measured relative to the receiving antenna, determining the target propagation angle from the plurality of propagation angles, performing a second-order difference filtering process on the intermediate electromagnetic echo signal corresponding to the target propagation angle, obtaining the target electromagnetic echo signal, realizing the determination of the intermediate electromagnetic echo signal of the heart region of the object to be measured from the plurality of intermediate electromagnetic echo signals, and the determined intermediate electromagnetic echo signal includes respiratory motion characteristics. Therefore, based on the characteristics between respiratory motion and heartbeat motion, the respiratory motion characteristics are filtered out by using second-order difference filtering, and the high-fine-grained target electromagnetic echo signal containing heartbeat motion characteristics is retained, so as to facilitate the processing of the high-fine-grained target electromagnetic echo signal, obtain high-precision heartbeat characteristics, and further realize the accurate conversion of body surface motion - heart motion, so as to obtain more accurate and comprehensive partial parameters related to the heart, thereby generating a complete and accurate heart activity image.

[0089] According to an embodiment of the present invention, beamforming processing can also be performed on the plurality of initial electromagnetic echo signals, so as to separate signals that are spatially aliased with each other, thereby extracting the intermediate electromagnetic echo signal of the heart region of the object to be measured, and then performing a second-order difference filtering process on the intermediate electromagnetic echo signal after beamforming processing to obtain the target electromagnetic echo signal.

[0090] According to an embodiment of the present invention, a method for generating a target echocardiogram video of a to-be-measured object by processing a target mechanical motion state feature and a conditional image using an echocardiogram video sub-model of an electromechanical modal conversion model includes the following operations.

[0091] According to an embodiment of the present invention, a Gaussian noise matrix for an echocardiogram video is obtained.

[0092] According to an embodiment of the present invention, a group of Gaussian noise matrices can be randomly generated, or a random group of Gaussian noise matrices can be obtained from an echocardiogram noise library.

[0093] According to an embodiment of the present invention, the Gaussian noise matrix can be used together with the target mechanical motion state feature and the conditional image to generate a target echocardiogram video of the to-be-measured object.

[0094] According to an embodiment of the present invention, the Gaussian noise matrix, the target mechanical motion state feature, and the conditional image are input into the echocardiogram video sub-model. Based on the target mechanical motion state feature and the conditional image, the echocardiogram video sub-model performs denoising processing on the Gaussian noise matrix to generate a target echocardiogram video of the to-be-measured object.

[0095] According to an embodiment of the present invention, the randomly generated Gaussian noise matrix is denoised by using a pre-trained echocardiogram video sub-model to restore the ultrasonic video information without noise. Then, in combination with the target mechanical motion state feature and the ultrasonic template image, further video processing is performed on the ultrasonic video information without noise to generate a target echocardiogram video of the to-be-measured object.

[0096] According to an embodiment of the present invention, by obtaining a Gaussian noise matrix for an echocardiogram video, inputting the Gaussian noise matrix, the target mechanical motion state feature, and the conditional image into the echocardiogram video sub-model, and based on the target mechanical motion state feature and the conditional image, the echocardiogram video sub-model performs denoising processing on the Gaussian noise matrix to generate a target echocardiogram video of the to-be-measured object, it is realized that based on the electromagnetic echo signal, through a pre-trained electromechanical modal conversion model, the mechanical motion state of the heart in the electromagnetic echo signal is converted into the electrocardiogram motion state in the ultrasonic video, and an accurate target echocardiogram video of the heart region of the to-be-measured object is generated. Under the condition of improving the application scenario adaptability and operation convenience, an accurate and complete target echocardiogram video is obtained. Moreover, since only the electromagnetic echo signal needs to be processed, various signal or video information that can assist in diagnosis of the heart region of the to-be-measured object can be obtained simultaneously, thereby improving the processing efficiency and the experience comfort of the to-be-measured object.

[0097] According to an embodiment of the present invention, the electromechanical modal conversion model is trained by the following method.

[0098] According to an embodiment of the present invention, an electromechanical modal conversion model to be trained and a training sample data set are obtained.

[0099] According to an embodiment of the present invention, the electromechanical modal conversion model to be trained includes an encoder and an ultrasonic echocardiogram video sub-model to be trained, and the training sample data set includes electromagnetic echo signal samples, ultrasonic electrocardiogram signal samples, ultrasonic echocardiogram video samples, and Gaussian noise samples.

[0100] According to an embodiment of the present invention, the encoder in the electromechanical modal conversion model to be trained can be a pre-trained encoder, and the pre-trained encoder and the ultrasonic echocardiogram video sub-model to be trained are used for training to obtain a trained ultrasonic echocardiogram video sub-model.

[0101] According to an embodiment of the present invention, the ultrasonic electrocardiogram signal sample is input into the encoder for feature mapping processing to generate an electrocardiogram motion state feature sample.

[0102] According to an embodiment of the present invention, the electrocardiogram motion state feature sample is extracted and mapped from the ultrasonic electrocardiogram signal sample to facilitate training the ultrasonic echocardiogram video sub-model to generate an accurate ultrasonic echocardiogram video.

[0103] According to an embodiment of the present invention, the electrocardiogram motion state feature sample and the ultrasonic echocardiogram video sample are input into the ultrasonic echocardiogram video sub-model to be trained for processing, and a training ultrasonic video noise feature is output.

[0104] According to an embodiment of the present invention, the method of inputting the electrocardiogram motion state feature sample and the ultrasonic echocardiogram video sample into the ultrasonic echocardiogram video sub-model to be trained for processing and outputting a training ultrasonic video noise feature includes the following operations.

[0105] According to an embodiment of the present invention, Gaussian noise samples are added to the ultrasonic echocardiogram video sample to obtain an ultrasonic echocardiogram noise video.

[0106] According to an embodiment of the present invention, Gaussian ultrasonic samples are randomly obtained, and Gaussian noise samples are added to the ultrasonic echocardiogram video multiple times to obtain multiple ultrasonic echocardiogram noise videos.

[0107] According to an embodiment of the present invention, after adding the last Gaussian noise sample to the ultrasonic echocardiogram video, the obtained ultrasonic echocardiogram noise video can be as shown in formula (3).

[0108] (3);

[0109] Wherein, can be characterized as, T can be characterized as the total number of times of adding Gaussian noise samples to the ultrasonic echocardiogram video, and t can be characterized as the t-th time of adding Gaussian noise samples to the ultrasonic echocardiogram video, can be characterized as an echocardiogram noise video obtained by adding the t-th Gaussian noise sample to the echocardiogram video after adding the (t - 1)-th Gaussian noise sample, \(x\) 0 can be characterized as an echocardiogram video without adding Gaussian noise samples, \(x\) 1:T can be characterized as an echocardiogram noise video obtained by cumulatively adding T Gaussian noise samples to the echocardiogram video, \(x\) t can be characterized as an echocardiogram noise video obtained by adding the t-th Gaussian noise sample to the echocardiogram video, \(x\) t-1 can be characterized as an echocardiogram noise video obtained by adding the (t - 1)-th Gaussian noise sample to the echocardiogram video.

[0110] According to an embodiment of the present invention, after adding the (t - 1)-th Gaussian noise sample to the echocardiogram video sample, the echocardiogram noise video obtained by continuing to add the t-th Gaussian noise sample to the echocardiogram video sample can be as shown in formula (4).

[0111] (4);

[0112] Wherein, can be characterized as a noise parameter, I can be characterized as an identity matrix, can be characterized as a Gaussian distribution.

[0113] According to an embodiment of the present invention, the echocardiogram noise video, the electrocardiogram motion state feature sample, and the echocardiogram video sample are input into the echocardiogram video sub-model to be trained for denoising processing, and the training ultrasonic video noise features are output.

[0114] According to an embodiment of the present invention, multiple echocardiogram noise videos added with multiple Gaussian noise samples, the original echocardiogram video samples, and the electrocardiogram motion state feature samples obtained by performing extraction mapping processing on a pre-trained encoder are input into the echocardiogram video sub-model to be trained. The echocardiogram video sub-model to be trained repeatedly performs denoising processing on the multiple echocardiogram noise videos based on the echocardiogram video samples and the electrocardiogram motion state features, so as to obtain multiple training ultrasonic video noise features.

[0115] According to an embodiment of the present invention, by adding Gaussian noise samples to an echocardiogram video multiple times, a plurality of echocardiogram noise videos are obtained. The plurality of echocardiogram noise videos, the echocardiogram video sample, and the electrocardiogram motion state feature sample are input into the echocardiogram video sub-model to be trained. The echocardiogram video sub-model to be trained performs denoising processing on the plurality of echocardiogram noise videos repeatedly based on the echocardiogram video sample and the electrocardiogram motion state feature, so as to obtain a plurality of training echocardiogram video noise features, realizing the training of the echocardiogram video sub-model, so as to use the trained echocardiogram video sub-model to process the input data and generate an accurate target echocardiogram video. At the same time, by performing denoising processing on the plurality of echocardiogram noise videos repeatedly, the echocardiogram video sub-model to be trained can learn to obtain training echocardiogram video noise features that can be applied to the elimination of various Gaussian noises, improving the recognition ability of echocardiogram video noise features, so that in the application process, based on the target mechanical motion state feature and the conditional image, denoising processing can be performed on the Gaussian noise matrix used to generate the echocardiogram video, further improving the processing efficiency and the generation accuracy rate.

[0116] According to an embodiment of the present invention, according to the video noise loss function, the training echocardiogram video noise features, and the Gaussian noise samples, a video noise loss value is obtained.

[0117] According to an embodiment of the present invention, the video noise loss function can be as shown in formula (5).

[0118] (5);

[0119] Wherein, can be characterized as the video noise loss function, can be characterized as the Gaussian noise sample added for the t-th time, can be characterized as the training echocardiogram video noise features, can be characterized as the noise parameter, z e can be characterized as the electrocardiogram motion state feature sample.

[0120] According to an embodiment of the present invention, according to the video noise loss value, the model parameters of the echocardiogram video sub-model to be trained are adjusted to obtain a trained electro-mechanical modal conversion model.

[0121] According to an embodiment of the present invention, when the training of the echocardiogram video sub-model of the electro-mechanical modal conversion model is completed, the echocardiogram video sub-model can, under the given conditional image, based on the electrocardiogram motion state feature sample satisfying the standard Gaussian distribution x T ∼N(0,I), restore the echocardiogram video sample.

[0122] According to an embodiment of the present invention, by adjusting the model parameters of the ultrasonic echocardiogram video sub-model to be trained, a trained ultrasonic echocardiogram video sub-model is obtained. Combining with the pre-trained encoder, a trained electromechanical modality conversion model can be obtained.

[0123] According to an embodiment of the present invention, by performing feature mapping processing on the ultrasonic electrocardiogram signal samples in the training sample dataset using the pre-trained encoder, generating electrocardiogram motion state feature samples, inputting the electrocardiogram motion state feature samples and ultrasonic echocardiogram video samples obtained by the encoder into the ultrasonic echocardiogram video sub-model to be trained, outputting training ultrasonic video noise features, obtaining a video noise loss value according to the video noise loss function, the training ultrasonic video noise features and Gaussian noise samples, thereby adjusting the model parameters of the ultrasonic echocardiogram video sub-model to be trained, obtaining a trained electromechanical modality conversion model, realizing the training of the ultrasonic echocardiogram video sub-model in the electromechanical modality conversion model to be trained according to the electrocardiogram motion state feature samples processed by the pre-trained encoder, thereby improving the correlation of feature processing between the ultrasonic echocardiogram video sub-model and the pre-trained encoder, so that the trained ultrasonic echocardiogram video sub-model can perform video generation processing according to the features obtained by the encoder, obtaining an accurate ultrasonic echocardiogram corresponding to the features output by the encoder, and at the same time, this ultrasonic echocardiogram is also the accurate target ultrasonic echocardiogram of the object to be measured. Further, by using a large number of data samples in the training sample dataset to train the electromechanical modality conversion model to be trained, the robustness of the electromechanical modality conversion model is improved, so that the trained electromechanical modality conversion model can process the features of the actually measured signals to generate an accurate target ultrasonic echocardiogram and improve the model processing efficiency.

[0124] According to an embodiment of the present invention, the encoder of the electromechanical modality conversion model to be trained is pre-trained.

[0125] According to an embodiment of the present invention, the encoder of the electromechanical modality conversion model to be trained is trained in the following manner.

[0126] According to an embodiment of the present invention, an initial encoder to be trained and a decoder for electrocardiogram to be trained are obtained.

[0127] According to an embodiment of the present invention, the initial encoder includes an electromagnetic encoder to be trained and an electrocardiogram encoder to be trained.

[0128] According to an embodiment of the present invention, the electromagnetic encoder to be trained can be a spatio-temporal encoder to be trained, wherein the spatio-temporal encoder can include a spatial encoder and a temporal encoder, and the electrocardiogram encoder to be trained can be a temporal encoder to be trained.

[0129] According to an embodiment of the present invention, an electromagnetic echo signal sample is input into an electromagnetic encoder to be trained for feature mapping processing, generating a mechanical motion state feature sample.

[0130] According to an embodiment of the present invention, the mechanical motion state feature sample may include the temporal feature and spatial feature of cardiac mechanical motion.

[0131] According to an embodiment of the present invention, an ultrasonic electrocardiogram signal sample is input into an electrocardiogram encoder to be trained for feature mapping processing, obtaining an electrocardiogram motion state feature sample.

[0132] According to an embodiment of the present invention, the electrocardiogram motion state feature sample may include the temporal feature of the heart.

[0133] According to an embodiment of the present invention, based on the mechanical motion state feature sample and the electrocardiogram motion state feature sample, the similarity between the two features can be obtained first, and the parameters of the electromagnetic encoder to be trained and the electrocardiogram encoder to be trained are adjusted according to the similarity, thereby obtaining a preliminarily trained electromagnetic encoder and electrocardiogram encoder.

[0134] According to an embodiment of the present invention, by aligning the mechanical motion state feature sample and the electrocardiogram motion state feature sample, so that the two features can be infinitely close to the cardiac mechanical activity feature, a high-precision encoder is obtained, and then an accurate conversion of body surface motion - cardiac motion is realized, so that the training result obtained by the encoder can be directly used to train the ultrasonic echocardiogram sub-model to be trained.

[0135] According to an embodiment of the present invention, the electrocardiogram motion state feature sample is input into an electrocardiogram decoder to be trained for signal reconstruction processing, obtaining an ultrasonic electrocardiogram reconstruction signal.

[0136] According to an embodiment of the present invention, the electrocardiogram motion state feature sample processed by the electrocardiogram encoder to be trained is input into the electrocardiogram decoder to be trained, so that the electrocardiogram decoder to be trained can perform reconstruction according to the electrocardiogram motion state feature sample and restore an ultrasonic electrocardiogram reconstruction signal similar to the ultrasonic electrocardiogram signal sample that has not been processed by the electrocardiogram encoder.

[0137] According to an embodiment of the present invention, the signal similarity can be obtained based on the ultrasonic electrocardiogram reconstruction signal output by the electrocardiogram decoder to be trained and the ultrasonic electrocardiogram signal sample, and the parameters of the electrocardiogram decoder to be trained are adjusted according to the signal similarity, thereby obtaining a preliminarily trained electrocardiogram decoder.

[0138] According to an embodiment of the present invention, based on a predetermined modal conversion loss function, the mechanical motion state feature sample, the electrocardiogram motion state feature sample, the ultrasonic electrocardiogram reconstruction signal, and the ultrasonic electrocardiogram signal sample, a modal conversion loss value is obtained.

[0139] According to an embodiment of the present invention, the model parameters of the electromagnetic encoder to be trained, the electrocardiogram encoder to be trained, and the electrocardiogram decoder to be trained can be adjusted again according to the obtained modal conversion loss value, so as to obtain an encoder and a decoder that can output accurate features or signals.

[0140] According to an embodiment of the present invention, the method for obtaining the modal conversion loss value according to a predetermined modal conversion loss function, mechanical motion state feature samples, electrocardiogram motion state feature samples, ultrasonic electrocardiogram reconstruction signals, and ultrasonic electrocardiogram signal samples includes the following operations.

[0141] According to an embodiment of the present invention, the motion state feature similarity is obtained according to a predetermined motion state feature similarity function, mechanical motion state feature samples, and electrocardiogram motion state feature samples.

[0142] According to an embodiment of the present invention, the motion state feature similarity function can be as shown in formula (6), and the motion state feature similarity can be calculated according to formula (6).

[0143] (6);

[0144] where l z can be characterized as the motion state feature similarity, z r can be characterized as the mechanical motion state feature sample, and z e can be characterized as the electrocardiogram motion state feature sample.

[0145] According to an embodiment of the present invention, based on the motion state feature similarity, the model parameters of the electromagnetic encoder to be trained and the electrocardiogram encoder to be trained can be preliminarily adjusted, so that the mechanical motion state feature samples generated by using the electromagnetic encoder to be trained and the electrocardiogram motion state feature samples generated by using the electrocardiogram encoder to be trained have a high feature similarity. Thus, when training the ultrasonic electrocardiogram video sub-model to be trained with the electrocardiogram motion state feature samples, it is equivalent to training the ultrasonic electrocardiogram video sub-model to be trained with the mechanical motion state feature samples, improving the output accuracy of the model and the encoder.

[0146] According to an embodiment of the present invention, the reconstruction signal feature similarity is obtained according to a predetermined reconstruction signal feature similarity function, ultrasonic electrocardiogram reconstruction signals, and ultrasonic electrocardiogram signal samples.

[0147] According to an embodiment of the present invention, the reconstruction signal feature similarity function can be as shown in formula (7), and the reconstruction signal feature similarity can be calculated according to formula (7).

[0148] (7);

[0149] where, l rec can be characterized as the similarity of the reconstructed signal features, can be characterized as the ultrasonic electrocardiogram reconstruction signal, e i can be characterized as the ultrasonic electrocardiogram signal sample.

[0150] According to an embodiment of the present invention, based on the similarity of the reconstructed signal features, preliminary parameter adjustment can be performed on the electrocardiogram decoder to be trained, so that the ultrasonic electrocardiogram reconstruction signal reconstructed and restored by using the electrocardiogram decoder to be trained can be consistent with the original ultrasonic electrocardiogram signal sample.

[0151] According to an embodiment of the present invention, according to a predetermined modal conversion loss function, balance parameter, motion state feature similarity, and reconstructed signal feature similarity, a modal conversion loss value is obtained.

[0152] According to an embodiment of the present invention, the modal conversion loss function can be as shown in formula (8), and the modal conversion loss value can be calculated according to formula (8).

[0153] (8);

[0154] where, can be characterized as the modal conversion loss value, can be characterized as the balance weight.

[0155] According to an embodiment of the present invention, by obtaining the motion state feature similarity according to a predetermined motion state feature similarity function, mechanical motion state feature sample, and electrocardiogram motion state feature sample, obtaining the reconstructed signal feature similarity according to a predetermined reconstructed signal feature similarity function, ultrasonic electrocardiogram reconstruction signal, and ultrasonic electrocardiogram signal sample, and obtaining the modal conversion loss value according to a predetermined modal conversion loss function, balance parameter, motion state feature similarity, and reconstructed signal feature similarity, parameter adjustment can be performed on the electromagnetic encoder to be trained and the electrocardiogram encoder to be trained once according to the motion state feature similarity, so as to obtain electromagnetic encoders and electrocardiogram encoders with similar feature similarities. Then, parameter adjustment can be performed on the electrocardiogram decoder to be trained once according to the reconstructed signal feature similarity, so as to obtain an electrocardiogram decoder that can reconstruct a signal consistent with the original ultrasonic electrocardiogram sample signal. Finally, based on the modal conversion loss value, parameter weights of the adjusted electromagnetic encoder, electrocardiogram encoder, and electrocardiogram decoder are adjusted again, so as to obtain electromagnetic encoders and electrocardiogram encoders that can output high-precision features, thereby realizing accurate conversion of body surface motion - cardiac motion and improving the output accuracy and processing efficiency of the encoder.

[0156] According to an embodiment of the present invention, the model parameters of the initial encoder to be trained and the electrocardiogram decoder to be trained are adjusted according to the modal conversion loss value to obtain the trained encoder and electrocardiogram decoder.

[0157] According to an embodiment of the present invention, based on the modal conversion loss value, the parameters of the electromagnetic encoder to be trained, the electrocardiogram encoder to be trained, and the electrocardiogram decoder to be trained can be adjusted, so that the mechanical motion state features generated by the electromagnetic encoder to be trained can have a high feature similarity with the electrocardiogram motion state features generated by the electrocardiogram encoder to be trained, and the ultrasonic electrocardiogram reconstruction signal reconstructed and restored by the electrocardiogram decoder to be trained can be consistent with the original ultrasonic electrocardiogram signal sample, thereby obtaining the trained encoder and electrocardiogram decoder.

[0158] According to an embodiment of the present invention, the trained encoder is determined as the encoder of the electromechanical modal conversion model to be trained.

[0159] According to an embodiment of the present invention, the electrocardiogram decoder can only be used to assist in training the encoder to be trained, so that only the electromagnetic encoder and the electrocardiogram encoder obtained after training need to be retained as the trained encoder, so as to use the trained encoder to assist in the training of the ultrasonic echocardiogram sub-model to be trained.

[0160] According to an embodiment of the present invention, first obtain an initial encoder to be trained and an electrocardiogram decoder to be trained. Input the electromagnetic echo signal samples and ultrasonic electrocardiogram signal samples in the training sample set into the electromagnetic encoder to be trained and the electrocardiogram encoder to be trained respectively for training and learning, and obtain mechanical motion state feature samples and electrocardiogram motion state feature samples respectively. Then, use the electrocardiogram motion state feature samples output by the electrocardiogram encoder to be trained to train and learn the electrocardiogram decoder to be trained, so that the electrocardiogram decoder to be trained can reconstruct the ultrasonic electrocardiogram reconstruction signal. Based on a predetermined modal conversion loss function, obtain a modal conversion loss value according to the mechanical motion state feature samples, electrocardiogram motion state feature samples, ultrasonic electrocardiogram reconstruction signal, and ultrasonic electrocardiogram signal samples, and adjust the model parameters of the initial encoder to be trained and the electrocardiogram decoder to be trained to obtain a trained encoder and electrocardiogram decoder. Since only the trained electromagnetic encoder and electrocardiogram encoder are required for subsequent training of the ultrasonic echocardiogram submodel, the trained electromagnetic encoder and electrocardiogram encoder are retained as the encoders of the electromechanical modal conversion model, realizing pre-training of the encoder. Through repeated training, the mechanical motion state feature samples output by the encoder can be infinitely close to the electrocardiogram motion state feature samples and infinitely close to the true cardiac mechanical activity features, so that when using the electrocardiogram motion state feature samples to train the ultrasonic echocardiogram submodel to be trained, it is equivalent to using the mechanical motion state feature samples to train the ultrasonic echocardiogram submodel to be trained. Further, in addition to adjusting the parameters of the electromagnetic encoder and electrocardiogram encoder to be trained according to the similarity between the mechanical motion state feature samples and the electrocardiogram motion state feature samples, the parameters of the electromagnetic encoder and electrocardiogram encoder to be trained can also be adjusted according to the ultrasonic electrocardiogram reconstruction signal restored by the electrocardiogram decoder to be trained, which can improve the accuracy of the encoder output and also improve the correlation between the encoder, decoder, and ultrasonic echocardiogram submodel to be trained.

[0161] According to an embodiment of the present invention, when using the trained electromechanical modal conversion model to process the target electromagnetic echo signal extracted from actual measurement, the encoder only needs to use the trained electromagnetic encoder to perform feature mapping processing on the target electromagnetic echo signal.

[0162] Figure 3a A schematic diagram of an actual echocardiogram according to an embodiment of the present invention is shown. Figure 3b A schematic diagram of a radar image of the heart obtained by using the method of the present invention according to an embodiment of the present invention is shown.

[0163] As Figures 3a to 3b shown, Figures 3a to 3bThe radar image and echocardiogram of the heart obtained by using the method of the present invention are shown. By comparison, it can be seen that the structural shape and heat map distribution between the radar image obtained by the method of the present invention and the actual echocardiogram are basically the same.

[0164] Figure 4 A schematic diagram showing the comparison of the left ventricular volume obtained from some mechanical motion state characteristics obtained according to the present invention and the actual partial heart motion state according to an embodiment of the present invention is shown.

[0165] As Figure 4 shown, Figure 4 A comparison of the left ventricular volume obtained from some mechanical motion state characteristics and the actual partial heart motion state is shown. The solid line can represent the left ventricular volume obtained from the actual partial heart motion state, and the dashed line can represent the left ventricular volume obtained from some mechanical motion state characteristics obtained according to the present invention. The minimum value A point of the curve can represent the cardiac systolic frame, and the maximum value B point of the curve can represent the cardiac diastolic frame. 401 can represent the rapid filling period, 402 can represent the total cardiac diastolic period, 403 can represent the atrial contraction period, 404 can represent the isovolumic contraction period, and 405 can represent the ejection period. It can be seen from the figure that the change trend of the left ventricular volume obtained by the method of the present invention is consistent with the actual change trend.

[0166] Figure 5 A schematic diagram showing the comparison of the left ventricular volume obtained from all mechanical motion state characteristics obtained according to the present invention and the actual all heart motion state according to an embodiment of the present invention is shown.

[0167] As Figure 5 shown, Figure 5 A comparison of the left ventricular volume obtained from some mechanical motion state characteristics and the actual partial heart motion state is shown. The solid line can represent the left ventricular volume obtained from the actual partial heart motion state, and the dashed line can represent the left ventricular volume obtained from some mechanical motion state characteristics obtained according to the present invention. It can be seen from the figure that the change trend of the left ventricular volume obtained by the method of the present invention is consistent with the actual change trend.

[0168] Figure 6 A structural block diagram of a device for generating a cardiac motion video based on electromagnetic signals according to an embodiment of the present invention is shown.

[0169] As Figure 6 shown, the device for generating a cardiac motion video based on electromagnetic signals in this embodiment includes: a determination module 610, a feature mapping module 620, and a generation module 630.

[0170] A determination module 610 is configured to determine a target electromagnetic echo signal corresponding to the cardiac region of an object to be measured, where the target electromagnetic echo signal includes a cardiac motion feature after eliminating the respiratory motion feature. The determination module 610 can be used to perform the operation S210 described above, which will not be elaborated here.

[0171] A feature mapping module 620 is configured to perform feature mapping processing on the target electromagnetic echo signal by using an encoder of an electromechanical modal conversion model to obtain a target mechanical motion state feature of the cardiac region, where the target mechanical motion state feature corresponds to the feature of the electrocardiogram motion state of the object to be measured. The feature mapping module 620 can be used to perform the operation S220 described above, which will not be elaborated here.

[0172] A generation module 630 is configured to process the target mechanical motion state feature and a conditional image by using an echocardiogram video sub-model of the electromechanical modal conversion model to generate a target echocardiogram video of the object to be measured, where the conditional image represents an echocardiogram template image. The generation module 630 can be used to perform the operation S230 described above, which will not be elaborated here.

[0173] According to an embodiment of the present invention, the determination module 610 includes: a first acquisition sub-module, a first determination sub-module, a second determination sub-module, and a first processing sub-module.

[0174] The first acquisition sub-module is configured to acquire a plurality of initial electromagnetic echo signals of the object to be measured, where the initial electromagnetic echo signals include a plurality of signals that are spatially aliased with each other and reflected by a plurality of body regions of the object to be measured within a predetermined time period.

[0175] The first determination sub-module is configured to perform a fast Fourier transform on the plurality of initial electromagnetic echo signals to determine the two-way propagation distance of each initial electromagnetic echo signal, where the two-way propagation distance represents the propagation distance of the transmitted signal from the transmitting antenna to the body region and the propagation distance of the initial electromagnetic echo signal from the body region to the receiving antenna.

[0176] The second determination sub-module is configured to determine a target two-way propagation distance from the plurality of two-way propagation distances based on the position information of the object to be measured.

[0177] The first processing sub-module is configured to process each initial electromagnetic echo signal corresponding to the target two-way propagation distance to obtain the target electromagnetic echo signal.

[0178] According to an embodiment of the present invention, the first processing sub-module includes: a first determination unit, a second determination unit, a third determination unit, and a first filtering unit.

[0179] The first determination unit is configured to determine each initial electromagnetic echo signal corresponding to the target two-way propagation distance as a plurality of intermediate electromagnetic echo signals.

[0180] The second determination unit is configured to perform fast Fourier transform on the plurality of intermediate electromagnetic echo signals to determine the propagation angle of each intermediate electromagnetic echo signal, where the propagation angle is characterized as the included angle between the intermediate electromagnetic echo signal and the object to be measured.

[0181] The third determination unit is configured to determine a target propagation angle from the plurality of propagation angles based on the angle information of the object to be measured relative to the receiving antenna.

[0182] The first filtering unit is configured to perform second-order difference filtering on the intermediate electromagnetic echo signal corresponding to the target propagation angle to obtain a target electromagnetic echo signal.

[0183] According to an embodiment of the present invention, the generation module 630 includes: a second acquisition sub-module and a first generation sub-module.

[0184] The second acquisition sub-module is configured to acquire a Gaussian noise matrix for the echocardiogram video.

[0185] The first generation sub-module is configured to input the Gaussian noise matrix, the target mechanical motion state feature, and the conditional image into the echocardiogram video sub-model. Based on the target mechanical motion state feature and the conditional image, the echocardiogram video sub-model performs denoising processing on the Gaussian noise matrix to generate a target echocardiogram video of the object to be measured.

[0186] According to an embodiment of the present invention, the apparatus for generating an echocardiogram video based on electromagnetic signals further includes: a training module.

[0187] The training module is configured to train the electromechanical modal conversion model to be trained.

[0188] According to an embodiment of the present invention, the training module includes: a third acquisition sub-module, a first mapping sub-module, a second generation sub-module, a first obtaining sub-module, and a first adjustment sub-module.

[0189] The third acquisition sub-module is configured to acquire the electromechanical modal conversion model to be trained and a training sample data set. The electromechanical modal conversion model to be trained includes an encoder and an echocardiogram video sub-model to be trained. The training sample data set includes electromagnetic echo signal samples, echocardiogram signal samples, echocardiogram video samples, and Gaussian noise samples.

[0190] The first mapping sub-module is configured to input the echocardiogram signal sample into the encoder for feature mapping processing and output an echocardiogram motion state feature sample.

[0191] A second generation sub-module, configured to input the electrocardiogram motion state feature samples and echocardiogram video samples into an echocardiogram video sub-model to be trained for processing, so as to generate training echocardiogram video noise features.

[0192] A first obtaining sub-module, configured to obtain a video noise loss value based on a video noise loss function according to the training echocardiogram video noise features and Gaussian noise samples.

[0193] A first adjustment sub-module, configured to adjust the model parameters of the echocardiogram video sub-model to be trained according to the video noise loss value, so as to obtain a trained electromechanical modality conversion model.

[0194] According to an embodiment of the present invention, the first obtaining sub-module includes: a first obtaining unit, a first mapping unit, a first obtaining unit, a first reconstruction unit, a second obtaining unit, a first adjustment unit, and a fourth determination unit.

[0195] The first obtaining unit is configured to obtain an initial encoder to be trained and a decoder for electrocardiogram to be trained, wherein the initial encoder includes an electromagnetic encoder to be trained and an electrocardiogram encoder to be trained.

[0196] The first mapping unit is configured to input electromagnetic echo signal samples into the electromagnetic encoder to be trained for feature mapping processing, so as to generate mechanical motion state feature samples.

[0197] The first obtaining unit is configured to input ultrasonic electrocardiogram signal samples into the electrocardiogram encoder to be trained for feature mapping processing, so as to obtain electrocardiogram motion state feature samples.

[0198] The first reconstruction unit is configured to input the electrocardiogram motion state feature samples into the decoder for electrocardiogram to be trained for signal reconstruction processing, so as to obtain ultrasonic electrocardiogram reconstruction signals.

[0199] The second obtaining unit is configured to obtain a modality conversion loss value based on a predetermined modality conversion loss function according to the mechanical motion state feature samples, the electrocardiogram motion state feature samples, the ultrasonic electrocardiogram reconstruction signals, and the ultrasonic electrocardiogram signal samples.

[0200] The first adjustment unit is configured to adjust the model parameters of the initial encoder to be trained and the decoder for electrocardiogram to be trained according to the modality conversion loss value, so as to obtain a trained encoder and a decoder for electrocardiogram.

[0201] The fourth determination unit is configured to determine the trained encoder as the encoder of the electromechanical modality conversion model to be trained.

[0202] According to an embodiment of the present invention, the second obtaining unit includes: a fifth obtaining sub-unit, a sixth obtaining sub-unit, and a seventh obtaining sub-unit.

[0203] A fifth obtaining subunit, configured to obtain a motion state feature similarity degree according to a predetermined motion state feature similarity function, a mechanical motion state feature sample, and an electrocardiogram motion state feature sample.

[0204] A sixth obtaining subunit, configured to obtain a reconstructed signal feature similarity degree according to a predetermined reconstructed signal feature similarity function, an ultrasonic electrocardiogram reconstructed signal, and an ultrasonic electrocardiogram signal sample.

[0205] A seventh obtaining subunit, configured to obtain a modal conversion loss value according to a predetermined modal conversion loss function, a balance parameter, a motion state feature similarity degree, and a reconstructed signal feature similarity degree.

[0206] According to an embodiment of the present invention, the second generating sub-module includes: a fourth obtaining unit and a first denoising unit.

[0207] The fourth obtaining unit is configured to add Gaussian noise samples to an ultrasonic cardiogram video sample to obtain an ultrasonic cardiogram noise video.

[0208] The first denoising unit is configured to input the ultrasonic cardiogram noise video, the electrocardiogram motion state feature sample, and the ultrasonic cardiogram video sample into an ultrasonic cardiogram video sub-model to be trained for denoising processing, and output training ultrasonic video noise features.

[0209] According to an embodiment of the present invention, any multiple of the determination module 610, the feature mapping module 620, and the generating module 630 may be combined and implemented in one module, or any one of them may be split into multiple modules. Or, at least part of the functions of one or more of these modules may be combined with at least part of the functions of other modules and implemented in one module. According to an embodiment of the present invention, at least one of the determination module 610, the feature mapping module 620, and the generating module 630 may be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on chip, a system on a substrate, a system on a package, an application specific integrated circuit (ASIC), or may be implemented by any other reasonable way of integrating or packaging circuits, etc., in hardware or firmware, or implemented in any one of the three implementation manners of software, hardware, and firmware, or in an appropriate combination of any several of them. Or, at least one of the determination module 610, the feature mapping module 620, and the generating module 630 may be at least partially implemented as a computer program module, and when the computer program module runs, it may execute the corresponding functions.

[0210] Figure 7 A block diagram of an electronic device for a method of generating a cardiogram video based on electromagnetic signals according to an embodiment of the present invention is shown.

[0211] As Figure 7As shown, the electronic device according to an embodiment of the present invention includes a processor 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage section 708 into a random access memory (RAM) 703. The processor 701 may include, for example, a general-purpose microprocessor (such as a CPU), an instruction set processor, and / or a related chipset, and / or a dedicated microprocessor (such as, an application specific integrated circuit (ASIC)), etc. The processor 701 may also include on-board memory for caching purposes. The processor 701 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present invention.

[0212] In the RAM 703, various programs and data required for the operation of the electronic device are stored. The processor 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. The processor 701 performs various operations of the method flow according to an embodiment of the present invention by executing the programs in the ROM 702 and / or the RAM 703. It should be noted that the program may also be stored in one or more memories other than the ROM 702 and the RAM 703. The processor 701 may also perform various operations of the method flow according to an embodiment of the present invention by executing the programs stored in the one or more memories.

[0213] According to an embodiment of the present invention, the electronic device may further include an input / output (I / O) interface 705, and the input / output (I / O) interface 705 is also connected to the bus 704. The electronic device may further include one or more of the following components connected to the I / O interface 705: an input section 706 including a keyboard, a mouse, etc.; an output section 707 including, for example, a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 708 including a hard disk, etc.; and a communication section 709 including a network interface card such as a LAN card, a modem, etc. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I / O interface 705 as needed. A removable medium 711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 710 as needed so that a computer program read from it can be installed into the storage section 708 as needed.

[0214] The present invention also provides a computer-readable storage medium, which may be included in the device / device / system described in the above embodiment; or may exist separately without being assembled into the device / device / system. The above computer-readable storage medium carries one or more programs, and when the one or more programs are executed, the method according to an embodiment of the present invention is implemented.

[0215] According to an embodiment of the present invention, the computer-readable storage medium may be a non-volatile computer-readable storage medium, which may include, for example, but not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In the present invention, the computer-readable storage medium may be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, device, or apparatus. For example, according to an embodiment of the present invention, the computer-readable storage medium may include the above-described ROM 702 and / or RAM 703 and / or one or more memories other than ROM 702 and RAM 703.

[0216] An embodiment of the present invention also includes a computer program product, which includes a computer program that contains program code for executing the method shown in the flowchart. When the computer program product runs in a computer system, the program code is used to enable the computer system to implement the method for generating a cardiac video based on electromagnetic signals provided by the embodiments of the present invention.

[0217] When the computer program is executed by the processor 701, it executes the above-described functions defined in the system / apparatus of the embodiments of the present invention. According to an embodiment of the present invention, the above-described systems, apparatuses, modules, units, etc. can be implemented by computer program modules.

[0218] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices and magnetic storage devices. In another embodiment, the computer program may also be transmitted and distributed in the form of a signal on a network medium, and be downloaded and installed through the communication part 709, and / or be installed from the removable medium 711. The program code contained in the computer program can be transmitted by any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0219] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 709, and / or be installed from the removable medium 711. When the computer program is executed by the processor 701, it executes the above-described functions defined in the system of the embodiments of the present invention. According to an embodiment of the present invention, the above-described systems, devices, apparatuses, modules, units, etc. can be implemented by computer program modules.

[0220] Those skilled in the art will appreciate that the features recited in the various embodiments of the present invention can be combined or / and combined in various ways, even if such combinations or combinations are not explicitly recited in the present invention. In particular, without departing from the spirit and teachings of the present invention, the features recited in the various embodiments of the present invention can be combined and / or combined in various ways. All such combinations and / or combinations fall within the scope of the present invention.

Claims

1. A method for generating a cardiac video based on an electromagnetic signal, characterized in that: include: Determining a target electromagnetic echo signal corresponding to a heart region of the subject to be measured, wherein the target electromagnetic echo signal includes a heartbeat motion feature after eliminating a respiratory motion feature; Performing feature mapping processing on the target electromagnetic echo signal using an encoder of an electromechanical modal conversion model to obtain target mechanical motion state characteristics of the heart region, wherein the target mechanical motion state characteristics correspond to the characteristics of the electrocardiographic motion state of the object to be measured; The target mechanical motion state characteristics and the conditional image are processed by the ultrasonic video sub-model of the electromechanical modal conversion model to generate the target ultrasonic video of the object to be measured, wherein the conditional image represents the ultrasonic template image, and generating the target ultrasonic video includes: obtaining a Gaussian noise matrix for the ultrasonic video; inputting the Gaussian noise matrix, the target mechanical motion state characteristics and the conditional image into the ultrasonic video sub-model, and based on the target mechanical motion state characteristics and the conditional image, the ultrasonic video sub-model denoises the Gaussian noise matrix to generate the target ultrasonic video of the object to be measured.

2. The method according to claim 1, characterized in that The step of determining a target electromagnetic echo signal corresponding to a heart region of the object to be measured comprises: Acquire a plurality of initial electromagnetic echo signals of the object to be measured, wherein the initial electromagnetic echo signals include a plurality of signals spatially overlapped with each other and reflected by a plurality of body regions of the object to be measured within a predetermined period of time; Performing fast Fourier transform on the multiple initial electromagnetic echo signals to determine a two-way propagation distance of each of the initial electromagnetic echo signals, wherein the two-way propagation distance represents a propagation distance of a transmission signal transmitted from a transmitting antenna to the body region and a propagation distance of the initial electromagnetic echo signal reflected from the body region to a receiving antenna; Determining a target two-way propagation distance from a plurality of the two-way propagation distances based on the position information of the object to be measured; Each of the initial electromagnetic echo signals corresponding to the target round-trip propagation distance is processed to obtain the target electromagnetic echo signal.

3. The method according to claim 2, characterized in that The processing of each of the initial electromagnetic echo signals corresponding to the target two-way propagation distance to obtain the target electromagnetic echo signal includes: Determining each of the initial electromagnetic echo signals corresponding to the target round-trip propagation distance as a plurality of intermediate electromagnetic echo signals; Performing a fast Fourier transform on the multiple intermediate electromagnetic echo signals to determine a propagation angle of each of the intermediate electromagnetic echo signals, wherein the propagation angle is characterized by an angle between the intermediate electromagnetic echo signal and the object to be measured; Determining a target propagation angle from a plurality of propagation angles based on the angle information of the object to be measured relative to the receiving antenna; A second-order differential filtering process is performed on the intermediate electromagnetic echo signal corresponding to the target propagation angle to obtain the target electromagnetic echo signal.

4. The method according to claim 1, characterized in that: The electromechanical mode conversion model is trained using the following methods, including: Acquire an electromechanical modal conversion model to be trained and a training sample data set, wherein the electromechanical modal conversion model to be trained includes an encoder and an ultrasonic video sub-model to be trained, and the training sample data set includes electromagnetic echo signal samples, ultrasonic electrocardiogram signal samples, ultrasonic video samples and Gaussian noise samples; Inputting the ultrasonic electrocardiogram signal sample into the encoder for feature mapping processing to generate electrocardiogram motion state feature samples; Inputting the electrocardiographic motion state feature samples and the ultrasonic cardiography video samples into the ultrasonic cardiography video sub-model to be trained for processing, and outputting training ultrasonic video noise features; Based on the video noise loss function, a video noise loss value is obtained according to the training ultrasound video noise feature and the Gaussian noise sample; According to the video noise loss value, the model parameters of the ultrasonic cardiology video sub-model to be trained are adjusted to obtain a trained electromechanical mode conversion model.

5. The method according to claim 4, characterized in that The encoder of the electromechanical modal conversion model to be trained is trained in the following manner, including: Acquire an initial encoder to be trained and an ECG decoder to be trained, wherein the initial encoder includes an electromagnetic encoder to be trained and an ECG encoder to be trained; Inputting the electromagnetic echo signal sample into the electromagnetic encoder to be trained for feature mapping processing to generate a mechanical motion state feature sample; Inputting the ultrasonic electrocardiogram signal sample into the electrocardiogram encoder to be trained for feature mapping processing to obtain an electrocardiogram motion state feature sample; Inputting the ECG motion state characteristic sample into the ECG decoder to be trained for signal reconstruction processing to obtain an ultrasonic ECG reconstruction signal; Obtaining a modal conversion loss value according to a predetermined modal conversion loss function, the mechanical motion state characteristic sample, the electrocardiographic motion state characteristic sample, the ultrasonic electrocardiographic reconstruction signal and the ultrasonic electrocardiographic signal sample; According to the modal conversion loss value, adjusting the model parameters of the initial encoder to be trained and the ECG decoder to be trained to obtain a trained encoder and ECG decoder; The trained encoder is determined as the encoder of the electromechanical modal conversion model to be trained.

6. The method according to claim 5, characterized in that The method of obtaining a modal conversion loss value according to a predetermined modal conversion loss function, the mechanical motion state characteristic sample, the electrocardiographic motion state characteristic sample, the ultrasonic electrocardiographic reconstruction signal and the ultrasonic electrocardiographic signal sample comprises: Obtaining motion state feature similarity according to a predetermined motion state feature similarity function, the mechanical motion state feature sample and the electrocardiogram motion state feature sample; Obtaining a reconstructed signal feature similarity according to a predetermined reconstructed signal feature similarity function, the ultrasonic electrocardiogram reconstructed signal and the ultrasonic electrocardiogram signal sample; The modal conversion loss value is obtained according to a predetermined modal conversion loss function, a balance parameter, the motion state feature similarity and the reconstructed signal feature similarity.

7. The method according to claim 4, characterized in that The step of inputting the electrocardiographic motion state feature sample and the ultrasonic cardiography video sample into the ultrasonic cardiography video sub-model to be trained for processing and outputting the training ultrasonic cardiography video noise feature comprises: Adding the Gaussian noise sample to the ultrasonic cardiography video sample to obtain an ultrasonic cardiography noise video; The ultrasonic cardiology noise video, the electrocardiographic motion state characteristic sample and the ultrasonic cardiology video sample are input into the ultrasonic cardiology video sub-model to be trained for denoising, and the training ultrasonic cardiology video noise characteristic is output.

8. A device for generating a cardiac video based on an electromagnetic signal, characterized in that: The device comprises: A determination module, used to determine a target electromagnetic echo signal corresponding to a heart region of the object to be measured, wherein the target electromagnetic echo signal includes a heartbeat motion feature after eliminating a respiratory motion feature; A feature mapping module, used to perform feature mapping processing on the target electromagnetic echo signal using an encoder of an electromechanical modal conversion model to obtain a target mechanical motion state feature of the heart region, wherein the target mechanical motion state feature corresponds to a feature of the electrocardiographic motion state of the object to be measured; A generation module is used to process the target mechanical motion state characteristics and the conditional image using the ultrasonic video sub-model of the electromechanical modal conversion model to generate the target ultrasonic video of the object to be measured, wherein the conditional image represents the ultrasonic template image, and generating the target ultrasonic video includes: obtaining a Gaussian noise matrix for the ultrasonic video; inputting the Gaussian noise matrix, the target mechanical motion state characteristics and the conditional image into the ultrasonic video sub-model, and based on the target mechanical motion state characteristics and the conditional image, the ultrasonic video sub-model denoising the Gaussian noise matrix to generate the target ultrasonic video of the object to be measured.

9. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors execute the method according to any one of claims 1 to 7.

Images