Scanning triggering method, device and system and storage medium

Abstract

The invention relates to a scanning triggering method, device and system and a storage medium, and the method comprises the steps: obtaining a heart movement signal, collected in real time, of a scanning object; judging whether newest signal data in the heart movement signal meets a preset triggering condition or not; generating a trigger instruction under the condition that the newest signal data meets a preset trigger condition; the trigger instruction is used for triggering the medical imaging equipment to perform medical scanning on the scanned object. According to the method and the device, the problem that accurate scanning triggering cannot be realized is solved, and scanning is accurately triggered by utilizing the acquired heart movement signals.

Description

Technical Field

[0001] The present application relates to the field of medical imaging technology, and in particular to a scan triggering method, device, system and storage medium. Background Art

[0002] When using medical imaging devices such as computed tomography (CT) and magnetic resonance imaging (MR) equipment to obtain cardiac images, accurate real-time triggering of cardiac movement is required.

[0003] In the existing cardiac motion detection method, the displacement curve containing the volume change information of the human heart is determined according to the change in the distance between the acquisition device and the skin surface. By performing derivative processing on the displacement curve, the time of contraction and relaxation of the atria and ventricles, volume change and other information are obtained for scanning triggering. However, the derivative processing method used in the above method does not have good robustness for data with respiratory interference, and cannot achieve accurate scanning triggering.

[0004] With regard to the problem that accurate scanning triggering cannot be achieved in related technologies, no effective solution has been proposed so far. Summary of the invention

[0005] In this embodiment, a scan triggering method, device, system and storage medium are provided to solve the problem that accurate scan triggering cannot be achieved in the related art.

[0006] In a first aspect, a scanning triggering method is provided in this embodiment, and the method includes:

[0007] Acquire a heart motion signal of a scanned object acquired in real time;

[0008] Determining whether the latest signal data in the cardiac motion signal meets a preset trigger condition;

[0009] When the latest signal data meets the preset trigger condition, a trigger instruction is generated; the trigger instruction is used to trigger a medical imaging device to perform a medical scan on the scan object.

[0010] In some embodiments, determining whether the latest signal data in the cardiac motion signal meets a preset trigger condition includes:

[0011] Determine the target data point in the latest signal data according to a preset selection rule;

[0012] Determine a prediction probability corresponding to the target data point; the prediction probability is used to indicate the probability that the target data point is a specific point of the cardiac motion signal;

[0013] According to the predicted probability, it is determined whether the target data point meets the preset trigger condition; the preset trigger condition refers to that the target data point is a specific point of the cardiac motion signal.

[0014] In some embodiments, judging whether the target data point meets the preset trigger condition according to the predicted probability includes:

[0015] Comparing the predicted probability of the target data point with a preset probability threshold;

[0016] When the predicted probability of the target data point is greater than the probability threshold, comparing the first waveform amplitude corresponding to the target data point with a preset second waveform amplitude;

[0017] When the difference between the first waveform amplitude and the second waveform amplitude is within a preset range, it is determined that the target data point meets the preset trigger condition.

[0018] In some embodiments, determining the target data point in the latest signal data according to a preset selection rule includes:

[0019] Extracting the latest signal data from the cardiac motion signal;

[0020] Performing windowing processing on the latest signal data to obtain corresponding windowed data;

[0021] According to the preset selection rule, the target data point in the windowed data is determined.

[0022] In some embodiments, determining the predicted probability corresponding to the target data point includes:

[0023] The target data point is processed by a signal detection model to obtain a prediction probability corresponding to the target data point; wherein the training of the signal detection model is:

[0024] Labeling sample-specific points and non-sample-specific points of multiple cardiac motion signals used for model training;

[0025] Based on a preset data window length, segmenting the annotated cardiac motion signal to obtain multiple sample signals;

[0026] A sample data set corresponding to each of the sample signals is constructed, and the signal detection model is trained according to the sample data set.

[0027] In some embodiments, when the latest signal data meets the preset trigger condition, a trigger instruction is generated; the trigger instruction is used to trigger a medical imaging device to perform a medical scan on the scanned object, including:

[0028] When the target data point is detected to be a specific point of the cardiac motion signal, generating a corresponding trigger instruction;

[0029] The trigger instruction is transmitted to the medical imaging device; the trigger instruction is used to instruct the medical imaging device to perform a medical scan on the scanned object.

[0030] In some embodiments, the step of acquiring the heart motion signal of the scanned object acquired in real time includes:

[0031] The heart motion signal of the scanned object is collected in real time by a radar collection device.

[0032] In a second aspect, a scanning trigger device is provided in this embodiment, and the device includes:

[0033] An acquisition module, used for acquiring a heart motion signal of a scanned object acquired in real time;

[0034] A judging module, used for judging whether the latest signal data in the cardiac motion signal meets a preset trigger condition;

[0035] The trigger module is used to generate a trigger instruction when the latest signal data meets the preset trigger condition; the trigger instruction is used to trigger the medical imaging device to perform a medical scan on the scanned object.

[0036] In a third aspect, a scanning trigger system is provided in this embodiment, the system comprising: an acquisition device, a processing unit and a medical imaging device; wherein the acquisition device is communicatively connected to the processing unit, and the processing unit is connected to the medical imaging device;

[0037] The acquisition device is used to acquire the cardiac motion signal of the scanned object in real time;

[0038] The processing unit is used to execute the scan triggering method described in the first aspect above.

[0039] In a fourth aspect, a storage medium is provided in this embodiment, on which a computer program is stored, and when the program is executed by a processor, the scanning triggering method described in the first aspect is implemented.

[0040] Compared with the related art, in the scan trigger method, device, system and storage medium provided in this embodiment, the scan trigger system includes an acquisition device, a processing unit and a medical imaging device; wherein the acquisition device is used to acquire the cardiac motion signal of the scanned object in real time; by acquiring the cardiac motion signal of the scanned object acquired in real time, it is determined whether the latest signal data in the cardiac motion signal meets the preset trigger condition; when the latest signal data meets the preset trigger condition, a trigger instruction is generated; the trigger instruction is used to trigger the medical imaging device to perform a medical scan on the scanned object, which solves the problem of being unable to achieve accurate scan triggering and realizes accurate triggering of scanning using the acquired cardiac motion signal.

[0041] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0043] Figure 1 It is a hardware structure block diagram of a terminal device of a scan triggering method provided in an embodiment of the present application;

[0044] Figure 2 is a flow chart of a scan triggering method provided by an embodiment of the present application;

[0045] Figure 3 is a structural block diagram of a scan trigger system provided by an embodiment of the present application;

[0046] Figure 4 is a flow chart of a scan triggering method provided by another embodiment of the present application;

[0047] Figure 5 is a flowchart of a scan triggering method provided in an embodiment of the present application;

[0048] Figure 6 is a flowchart of a scan triggering method provided by another embodiment of the present application;

[0049] Figure 7 It is a flowchart of a signal detection model training and detection method provided in one embodiment of the present application;

[0050] Figure 8 is a flow chart of a scan triggering method provided by a preferred embodiment of the present application;

[0051] Fig. 9 It is a structural block diagram of a scan trigger device provided in one embodiment of the present application.

[0052] In the figure: 102, processor; 104, memory; 106, transmission device; 108, input and output device; 10, acquisition module; 20, judgment module; 30, trigger module. DETAILED DESCRIPTION

[0053] In order to more clearly understand the purpose, technical solutions and advantages of the present application, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments.

[0054] Unless otherwise defined, the technical terms or scientific terms involved in this application shall have the general meaning understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the", "these" and the like in this application do not represent quantitative restrictions, and they can be singular or plural. The terms "include", "comprise", "have" and any variants thereof involved in this application are intended to cover non-exclusive inclusions; for example, a process, method and system, product or device comprising a series of steps or modules (units) is not limited to the listed steps or modules (units), but may include unlisted steps or modules (units), or may include other steps or modules (units) inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether directly or indirectly. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships. For example, "A and / or B" can mean: A exists alone, A and B exist at the same time, and B exists alone. Usually, the character " / " indicates that the objects associated with each other are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0055] The method embodiment provided in this embodiment can be executed in a terminal, a computer or a similar computing device. For example, running on a terminal, Figure 1 FIG. 1 is a hardware structure diagram of a terminal of the scanning triggering method of this embodiment. Figure 1 As shown, the terminal may include one or more ( Figure 1 Only one is shown in the figure) processor 102 and memory 104 for storing data, wherein processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA. The above terminal may also include a transmission device 106 and an input and output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1The structure shown is only for illustration and does not limit the structure of the above terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0056] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the scan trigger method in this embodiment. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the terminal via a network. Examples of the above network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0057] The transmission device 106 is used to receive or send data via a network. The above network includes a wireless network provided by the communication provider of the terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet wirelessly.

[0058] In this embodiment, a scanning trigger method is provided. Figure 2 is a flow chart of the scan triggering method of this embodiment. Figure 2 As shown, the process includes the following steps:

[0059] Step S210, acquiring a heart motion signal of the scanned object collected in real time;

[0060] Step S220, determining whether the latest signal data in the cardiac motion signal meets a preset trigger condition;

[0061] Step S230: When the latest signal data meets the preset trigger condition, a trigger instruction is generated; the trigger instruction is used to trigger the medical imaging device to perform a medical scan on the scanned object.

[0062] Specifically, this embodiment is applicable to a scanning trigger system, such as Figure 3As shown, the system includes a collection device, a processing unit and a medical imaging device, wherein the collection device is connected to the processing unit in communication, and the processing unit is connected to the medical imaging device. The collection device is used to collect the heart motion signal of the scanned object in real time, and the heart motion signal is a signal collected directly on the heart surface or the heart body, and can adopt a Doppler radar collection device, a radio frequency sensor and other collection devices, and this embodiment does not limit the specific collection device used.

[0063] Taking the Doppler radar acquisition device as an example, a continuous wave radar signal is transmitted to the chest cavity of the scanned object through a radar antenna, and the returned echo signal and the transmitted oscillation frequency signal are mixed to extract the heart motion analog signal of the scanned object from the mixing result; impedance matching is performed on the heart motion analog signal extracted by the Doppler radar, and a high-pass filter is used to filter out the DC component in the low-frequency signal. The cutoff frequency of the high-pass filter is preferably 0.25 Hz. The processed heart motion analog signal is amplified and then converted into a corresponding heart motion digital signal through an analog-to-digital converter; the heart motion digital signal is input into a microprocessor, and in the microprocessor, the heart motion digital signal is median filtered to remove high-frequency interference, so as to obtain a heart displacement signal waveform processed by a median filtering algorithm, and then the signal after the median filtering is input into a digital signal processing filter, and the filter is preferably a second-order infinite impulse response (IIR) digital bandpass filter of 0.5 to 10 Hz to filter out other interference signals other than heart motion to obtain the final heart motion signal.

[0064] The heart motion signal of the scanned object collected in real time is wirelessly transmitted to the processing unit, the latest signal data in the heart motion signal is obtained, and the target data point in the latest signal data is determined according to a preset selection rule. The selection rule is used to indicate the specific definition of the target data point, such as defining the latest data point in the latest signal data as the target data point, or defining the data point 0.01 seconds before the latest data point as the target data point, etc. through a preset rule.

[0065] Furthermore, the probability of the target data point being a specific point of the cardiac motion signal is predicted, and the corresponding prediction probability is obtained. The specific point of the cardiac motion signal can be a peak point or other pre-selected data point, which can be set by the user according to actual application requirements. For example, the signal value of the target data point is compared with the set value of the specific point, and based on the comparison result, the probability of the target data point being the specific point is predicted in combination with the signal value change trend of the data points near the target data point; or, the target data point is predicted through a signal detection model, and the prediction probability corresponding to the target data point is output.

[0066] In the training process of the above-mentioned signal detection model, the multiple cardiac motion signals used for model training are pre-labeled with sample-specific points and non-sample-specific points, and the labeled cardiac motion signals are segmented based on a preset data window length, such as two-second window data, to obtain multiple sample signals, and then a sample data set corresponding to each sample signal is constructed. The sample data set can usually be divided into a training set and a validation set, and the signal detection model is trained according to the sample data set. It can be understood that the signal detection model in this embodiment can be adaptively adjusted according to the latest prediction results to better adapt to the actual application environment and improve the accuracy of probability prediction.

[0067] Afterwards, the predicted probability is compared with a preset probability threshold. When it is detected that the predicted probability of the target data point is greater than the probability threshold, the first waveform amplitude corresponding to the target data point is compared with the preset second waveform amplitude. The preset second waveform amplitude is the theoretical waveform amplitude or the empirical waveform amplitude corresponding to the specific point. The user can customize the setting according to the general waveform characteristics of the cardiac motion signal in actual applications to determine whether the difference between the first waveform amplitude and the second waveform amplitude is within a preset range, such as taking the preset range as 0.5% of the maximum amplitude difference of the cardiac motion signal. If the difference between the first waveform amplitude and the second waveform amplitude is within the preset range, it is determined that the target data point meets the preset trigger condition, that is, the target data point is determined to be a specific point of the cardiac motion signal, indicating that the latest signal data meets the preset trigger condition, and then a trigger instruction is generated to trigger the medical imaging device to perform a medical scan on the scanned object. In this embodiment, the medical imaging device includes but is not limited to a computer tomography scanner and a magnetic resonance imaging device.

[0068] It should be noted that in addition to defining the preset trigger condition as a specific point at which the target data point is detected as a cardiac motion signal, it is possible to determine whether the current heart has abnormal electrical activity corresponding to a specific physiological or pathological event for the specific physiological or pathological event to be examined, such as arrhythmia, heart valve closure, etc., based on the latest signal data in the cardiac motion signal. When abnormal electrical activity is detected in the heart, a scan can be triggered to better observe the heart structure in an abnormal state.

[0069] In the existing cardiac motion detection method, the displacement curve containing the volume change information of the human heart is determined according to the change in the distance between the acquisition device and the skin surface. By performing derivative processing on the displacement curve, the time of contraction and relaxation of the atria and ventricles, volume change and other information are obtained for scanning triggering. However, the derivative processing method used in the above method does not have good robustness for data with respiratory interference, and cannot achieve accurate scanning triggering.

[0070] Compared with the prior art, the present application obtains the cardiac motion signal of the scanned object collected in real time; determines whether the latest signal data in the cardiac motion signal meets the preset trigger condition; and triggers the medical imaging device to perform a medical scan on the scanned object when the latest signal data meets the preset trigger condition. Based on this, by collecting and analyzing accurate cardiac motion signals in real time, when it is detected that the latest signal data in the cardiac motion signal meets the preset trigger condition, the medical imaging device is triggered to perform a medical scan on the scanned object, which solves the problem of being unable to achieve accurate scan triggering and achieves accurate triggering of scanning using the collected cardiac motion signal.

[0071] In some of the embodiments, Figure 4 As shown, the step S220 of determining whether the latest signal data in the cardiac motion signal meets the preset trigger condition includes the following steps:

[0072] Step S221, determining the target data point in the latest signal data according to a preset selection rule;

[0073] Step S222, determining the prediction probability corresponding to the target data point; the prediction probability is used to indicate the probability that the target data point is a specific point of the cardiac motion signal;

[0074] Step S223, judging whether the target data point meets a preset trigger condition according to the predicted probability; the preset trigger condition refers to whether the target data point is a specific point of the cardiac motion signal.

[0075] Specifically, the latest signal data in the cardiac motion signal is obtained, and the target data point in the latest signal data is determined according to a preset selection rule; or the latest signal data in the cardiac motion signal is windowed to obtain corresponding windowed data, and the target data point in the windowed data is determined according to a preset selection rule. The selection rule is used to indicate the specific definition of the target data point.

[0076] Exemplarily, by presetting rules, the latest data point in the latest signal data is defined as the target data point, or the data point 0.01 seconds before the latest data point is defined as the target data point. In this embodiment, the specific definition of the target data point is not limited and can be set according to actual application requirements.

[0077] Through this embodiment, the target data point in the latest signal data is determined, and the prediction probability corresponding to the target data point is determined, and the prediction probability is used to indicate the probability that the target data point is a specific point of the cardiac motion signal. According to the prediction probability, it is determined whether the target data point meets the preset trigger condition, so as to accurately determine whether the target data point is a specific point of the cardiac motion signal, which helps to improve the accuracy of the scan trigger.

[0078] In some embodiments, judging whether the target data point meets the preset trigger condition according to the predicted probability in step S223 includes the following steps:

[0079] Compare the predicted probability of the target data point with a preset probability threshold;

[0080] When the predicted probability of the target data point is greater than the probability threshold, comparing the first waveform amplitude corresponding to the target data point with the preset second waveform amplitude;

[0081] When the difference between the first waveform amplitude and the second waveform amplitude is within a preset range, it is determined that the target data point meets the preset trigger condition.

[0082] Specifically, the predicted probability of the target data point is compared with a preset probability threshold to determine whether the predicted probability of the target data point is greater than the probability threshold. When it is detected that the predicted probability of the target data point is greater than the probability threshold, the first waveform amplitude corresponding to the target data point is compared with the preset second waveform amplitude. The preset second waveform amplitude is the theoretical waveform amplitude or the empirical waveform amplitude corresponding to the specific point. The user can customize the setting according to the general waveform characteristics of the cardiac motion signal in actual applications. If it is detected that the difference between the first waveform amplitude and the second waveform amplitude is within the preset range, it is determined that the target data point meets the preset trigger condition, that is, the target data point is a specific point of the cardiac motion signal. Among them, the specific point of the cardiac motion signal can be a peak point or other pre-selected data point.

[0083] Taking the selection of the peak point as the specific point of the cardiac motion signal as an example, when the predicted probability of the target data point being the peak point is detected to be greater than the probability threshold, the waveform amplitude corresponding to the target data point is compared with the waveform amplitude corresponding to the peak point to determine whether the difference between the two waveform amplitudes is within a preset range, such as taking the preset range as 0.5% of the maximum amplitude difference of the cardiac motion signal. If the difference between the two waveform amplitudes is within the preset range, the target data point is determined to be the peak point of the cardiac motion signal, indicating that the current target data point meets the preset trigger condition.

[0084] Through this embodiment, the predicted probability of the target data point is compared with a preset probability threshold. When the predicted probability of the target data point is greater than the probability threshold, the first waveform amplitude corresponding to the target data point is compared with the preset second waveform amplitude. When the difference between the first waveform amplitude and the second waveform amplitude is within a preset range, it is determined that the target data point meets the preset trigger condition, thereby achieving accurate analysis of whether the target data point is a specific point of the cardiac motion signal.

[0085] In some embodiments, determining the target data point in the latest signal data according to a preset selection rule in step S221 includes the following steps:

[0086] Extract the latest signal data from the cardiac motion signal;

[0087] Perform windowing processing on the latest signal data to obtain corresponding windowed data;

[0088] According to the preset selection rules, the target data points in the windowed data are determined.

[0089] Specifically, the latest signal data is extracted from the received cardiac motion signal, the latest signal data is windowed according to the preset data window length, the corresponding windowed data is obtained, and the windowed data is normalized. It should be noted that the present embodiment performs data windowing with a preset duration as the window, for example, the preset duration is 2 seconds, and the principle of sampling one by one and real-time transmission is followed during data acquisition, that is, each time a data point is obtained, it is filled into the window of the current preset duration, and when the window data is filled, that is, the accumulated duration reaches the preset duration, the current windowed data is subsequently processed to ensure the continuity and real-time nature of the data.

[0090] Exemplarily, the latest signal data extracted is windowed according to the latest two seconds of data to obtain two-second window data, and the windowed data is normalized according to [-1, 1] to map the numerical range of the windowed data to between [-1, 1].

[0091] Further, the target data point in the windowed data is determined according to a preset selection rule, wherein the preset selection rule is used to indicate a specific definition of the target data point, for example, the latest data point in the latest signal data is defined as the target data point, or the data point 0.01 seconds before the latest data point is defined as the target data point, etc.

[0092] Through this embodiment, the latest signal data in the cardiac motion signal is extracted, the latest signal data is windowed to obtain corresponding windowed data, and the target data points in the windowed data are determined according to preset selection rules, thereby improving the accuracy of data processing and minimizing the amount of calculation in the data processing process through windowing processing to improve efficiency.

[0093] In some embodiments, determining the predicted probability corresponding to the target data point in step S222 includes the following steps:

[0094] The target data point is processed by the signal detection model to obtain the prediction probability corresponding to the target data point; the training of the signal detection model is:

[0095] Labeling sample-specific points and non-sample-specific points of multiple cardiac motion signals used for model training;

[0096] Based on a preset data window length, segmenting the annotated cardiac motion signal to obtain multiple sample signals;

[0097] A sample data set corresponding to each sample signal is constructed, and the signal detection model is trained according to the sample data set.

[0098] Specifically, multiple cardiac motion signals for model training are obtained, the multiple cardiac motion signals are subjected to median filtering to remove high-frequency interference, and each cardiac motion signal after median filtering is subjected to sample-specific point labeling and non-sample-specific point labeling. The sample-specific point of the cardiac motion signal and the vicinity of the sample-specific point are labeled as 1, while other non-sample-specific points in the cardiac motion signal are labeled as 0. For example, when the sample-specific point of the cardiac motion signal is a peak point, the peak point and the vicinity of the peak point are labeled as 1, and other non-peak points are labeled as 0. The multiple cardiac motion signals used for model training can be cardiac motion signals of different scanned objects, or multiple cardiac motion signals obtained by scanning the same scanned object multiple times, which is not limited here.

[0099] Furthermore, according to a preset data window length, such as two-second window data, the labeled cardiac motion signal is segmented to obtain multiple sample signals, each sample signal is normalized according to [-1,1], and a sample data set corresponding to each sample signal is constructed. The sample data set can be divided into a training set and a validation set. The signal detection model is trained based on the sample data set to obtain the optimal signal detection model parameters.

[0100] It should be noted that the signal detection model obtained by the above training is used to predict the probability value of the target data point in the actually collected cardiac motion signal being a specific point, and the signal detection model can be adaptively adjusted according to the latest prediction results to better adapt to the actual application environment and improve the accuracy of probability prediction.

[0101] Through this embodiment, sample-specific points and non-sample-specific points of multiple cardiac motion signals used for model training are labeled, and the labeled cardiac motion signals are segmented based on a preset data window length to obtain multiple sample signals, and a sample data set corresponding to each sample signal is constructed. The signal detection model is trained based on the sample data set, so that the signal detection model can accurately predict whether the target data point is a specific point of the cardiac motion signal, and at the same time has strong robustness.

[0102] In some embodiments, in step S230, when the latest signal data meets the preset trigger condition, a trigger instruction is generated; the trigger instruction is used to trigger the medical imaging device to perform a medical scan on the scanned object, and includes the following steps:

[0103] When the target data point is detected to be a specific point of the cardiac motion signal, a corresponding trigger instruction is generated;

[0104] The trigger instruction is transmitted to the medical imaging device; the trigger instruction is used to instruct the medical imaging device to perform a medical scan on the scanned object.

[0105] Specifically, when it is detected that the target data point is a specific point of the cardiac motion signal, a trigger instruction is generated and transmitted to the medical imaging device to instruct the medical imaging device to perform a medical scan on the scanned object.

[0106] It should be noted that the above-mentioned medical imaging equipment includes but is not limited to computer tomography scanners and magnetic resonance imaging equipment. While instructing the medical imaging equipment to scan by transmitting trigger instructions, the current cardiac motion signal and the data points that trigger the scan are displayed in real time on the display terminal, so as to visualize the scanning trigger points of the medical imaging equipment for user reference and confirmation, thereby ensuring the accuracy of the scan trigger.

[0107] Through this embodiment, when the target data point is detected to be a specific point of the cardiac motion signal, a corresponding trigger instruction is generated and transmitted to the medical imaging device. The trigger instruction is used to instruct the medical imaging device to perform a medical scan on the scanned object, thereby realizing real-time and accurate triggering of the scan using the cardiac motion signal.

[0108] In some embodiments, obtaining a heart motion signal of a scanned object acquired in real time includes the following steps:

[0109] The radar acquisition device is used to collect the cardiac motion signal of the scanned object in real time.

[0110] Specifically, the acquisition device may be a radar acquisition device, a radio frequency sensor, etc. The radar acquisition device includes but is not limited to a Doppler radar, a frequency modulated continuous wave radar, and an ultra-wideband radar, and this embodiment does not limit the specific acquisition device used.

[0111] Exemplarily, a Doppler radar acquisition device is used for signal acquisition, and a continuous wave radar signal is emitted to the chest cavity of the scanned object through a radar antenna, and the echo signal and the emission oscillation frequency signal are mixed to process the signal, and the cardiac motion analog signal of the scanned object is extracted from the mixing result. The cardiac motion analog signal extracted by the Doppler radar is impedance matched, and a high-pass filter is used to filter out the DC component in the low-frequency signal. The cutoff frequency of the high-pass filter is preferably 0.25Hz. The processed cardiac motion analog signal is amplified and then converted into a corresponding cardiac motion digital signal through an analog-to-digital converter. Further, the cardiac motion digital signal is input into a microprocessor, and the cardiac motion digital signal is median filtered to remove high-frequency interference in the signal, and the signal after the median filtering is input into a digital signal processing filter, and the filter is preferably an IIR digital bandpass filter of 0.5 to 10Hz to filter out other interference signals other than cardiac motion, and obtain the final cardiac motion signal. It should be noted that the Doppler radar used in this embodiment can perform non-contact cardiac motion signal monitoring under a high magnetic field, avoiding the cumbersome electrode pasting process. At the same time, the Doppler radar can penetrate human tissue and directly collect signals from the heart surface or the heart body to detect the movement of the left and right ventricles of the heart in the human body, thereby providing a more accurate cardiac motion signal.

[0112] Through this embodiment, the cardiac motion signal of the scanned object is collected in real time by a radar collection device, and the accuracy of the acquired cardiac motion signal is ensured while the cardiac motion signal is collected in a non-contact manner.

[0113] The present embodiment is described and illustrated by means of specific examples below.

[0114] Figure 5 is a flow chart of the scan triggering method of this embodiment. Figure 5 As shown, the scanning triggering method specifically includes the following steps:

[0115] The patient to be scanned lies in the medical imaging device, and the antenna of the Doppler radar is placed in the middle or upper middle part of the patient's chest. At the front end of the Doppler radar heartbeat acquisition, a continuous wave radar signal is transmitted to the human chest cavity through the radar antenna, and the corresponding echo signal S501 is returned. The echo signal and the transmitted oscillation frequency signal are mixed and processed, and the human heart motion signal is extracted from them S502. The heart motion signal extracted by the Doppler radar is impedance matched, and a high-pass filter with a cutoff frequency of 0.25Hz is used to filter out the DC component in the low-frequency signal, and the processed heart motion signal is amplified. The amplified heart motion signal is converted into the corresponding heart motion digital signal S503 through an AD converter.

[0116] Furthermore, the cardiac motion digital signal is input into the microprocessor S504, in which the cardiac motion digital signal is subjected to median filtering to remove high-frequency interference, thereby obtaining a cardiac displacement signal waveform after the median filtering algorithm, and then the signal after the median filtering is passed through a second-order IIR digital bandpass filter of 0.5-10Hz to filter out other interference signals other than cardiac motion.

[0117] Afterwards, the processed Doppler radar heart motion signal is wirelessly transmitted to the AI ​​algorithm intelligent processing end S505, and the heart motion signal is windowed according to the latest two-second data. The current two-second window data contains the data of the current latest point. The two-second window data is preprocessed, that is, the two-second window data is normalized according to [-1,1]. The Doppler radar heartbeat signals of a large number of people are obtained and preprocessed S506, and the signal detection model is trained by the preprocessed Doppler radar heartbeat signals S507 to obtain the trained signal detection model S508. The normalized two-second window data is sent to the trained signal detection model, and the signal detection model can calculate each data point in the two-second window data, and then the trained signal detection model is used to calculate and output the predicted probability that each data point in the two-second window data is a peak point. According to the probability judgment of the current data point and the post-processing judgment of whether the waveform amplitude after the median filter of the current data point is the peak, it is determined whether the current data point is a peak trigger point S509. When the current data point is detected as a peak trigger point, the current data point and the cardiac motion waveform are transmitted to the imaging device display and trigger terminal to implement waveform display and cardiac triggered scanning S510.

[0118] Figure 6 is a flow chart of the scan triggering method of this embodiment. Figure 6 As shown, the scanning triggering method specifically includes the following steps:

[0119] The antenna of the Doppler radar is placed in the middle or upper middle part of the patient's chest S601, and a continuous wave radar signal is transmitted to the human chest cavity through the radar antenna, and the returned echo signal and the transmitted oscillation frequency signal are mixed and processed, and the human heart motion signal is extracted from them S602. The heart motion signal extracted by the Doppler radar is impedance matched, and a high-pass filter with a cutoff frequency of 0.25Hz is used to filter out the DC component in the low-frequency signal S603, and the processed heart motion signal is amplified S604, and the amplified heart motion signal is converted into a corresponding heart motion digital signal S605 through an AD converter.

[0120] Furthermore, the cardiac motion digital signal is input into the microprocessor for processing S606. After the cardiac motion digital signal is subjected to median filtering to remove high-frequency interference, it is then subjected to a 0.5-10 Hz second-order IIR digital bandpass filter to filter out other interference signals other than cardiac motion. Afterwards, the real-time cardiac motion signal is windowed according to the latest two-second data, and the current two-second window data includes the data of the current latest point S607, and the two-second window data is preprocessed, that is, the two-second window data is normalized according to [-1,1] S608.

[0121] The Doppler radar heartbeat signals of a large number of people are obtained and preprocessed S609, and the signal detection model is trained by the preprocessed Doppler radar heartbeat signals to obtain the trained signal detection model S610. The preprocessed two-second window data is sent to the trained signal detection model S611, and the signal detection model can calculate each data point in the two-second window data, and then the trained signal detection model is used to calculate and output the predicted probability that each data point in the two-second window data is a peak point S612. According to the probability judgment of the current data point and the post-processing judgment of whether the waveform amplitude after the median filtering of the current data point is the peak value, it is determined whether the current data point is a peak trigger point S613. When the current data point is detected as a peak trigger point, the current data point and the heart motion waveform are transmitted to the imaging device display and trigger terminal to realize the waveform display and heart trigger scanning S614.

[0122] Figure 7 is a flow chart of the signal detection model training and detection method of this embodiment, such as Figure 7 As shown, the method specifically comprises the following steps:

[0123] A large number of cardiac motion signal samples of different groups of people are obtained in advance S710, including data of people with different heart rates, and the cardiac motion signal samples are subjected to median filtering to remove high-frequency interference S720, and the processed cardiac motion signal is preliminarily labeled in the form of marking the peak and the surrounding of the peak as 1, and the non-peak as 0, and then the cardiac motion signal and the label are cut according to the data window length of two seconds to complete the construction of data sample features and labels, and obtain multiple cardiac motion signal samples S730. Each cardiac motion signal sample is normalized according to [-1,1], and the cardiac motion signal samples and labels are divided according to the training set and the verification set, and the signal detection model is trained and verified to obtain the optimal model parameters S740.

[0124] In actual application, the patient's Doppler Ray cardiac motion signal is collected in real time S750, the collected Doppler Ray cardiac motion signal is subjected to median filtering, and then the median filtered data is passed through a 0.5-10Hz second-order IIR digital bandpass filter S760. Further, the input signal features are intercepted in the form of a sliding window, that is, the filtered signal is intercepted according to the latest two-second data window S770, and the intercepted two-second data window is normalized to [-1,1] S780, and the normalized data is analyzed and calculated by the trained signal detection model to obtain the predicted probability that the current data point is the peak value S790.

[0125] The present embodiment is described and illustrated below through preferred embodiments.

[0126] Figure 8 is a flow chart of the scan triggering method of this preferred embodiment. Figure 8 As shown, the scanning triggering method includes the following steps:

[0127] Step S810, inputting the cardiac motion signal of the scanned object collected in real time into the processing unit, and extracting the latest signal data in the cardiac motion signal;

[0128] Step S820, performing windowing processing on the latest signal data to obtain corresponding windowed data, and determining the target data point in the windowed data according to a preset selection rule;

[0129] Step S830, processing the target data point through the signal detection model to obtain a prediction probability corresponding to the target data point; the prediction probability is used to indicate the probability that the target data point is a specific point of the cardiac motion signal;

[0130] Step S840, judging whether the target data point meets a preset trigger condition according to the predicted probability; the preset trigger condition refers to that the target data point is a specific point of the cardiac motion signal;

[0131] Step S850: When the latest signal data meets the preset trigger condition, trigger the medical imaging device to perform a medical scan on the scan object.

[0132] Through this embodiment, the cardiac motion signal of the scanned object collected in real time is input into the processing unit, the latest signal data in the cardiac motion signal is extracted, and the latest signal data is windowed to obtain the corresponding windowed data. The target data point in the windowed data is determined according to the preset selection rule, and the target data point is processed by the signal detection model to obtain the predicted probability that the target data point is a specific point of the cardiac motion signal, so that it is possible to judge whether the target data point meets the preset trigger condition according to the predicted probability. When the latest signal data meets the preset trigger condition, the medical imaging device is triggered to perform a medical scan on the scanned object, which solves the problem of being unable to achieve accurate scanning triggering, and realizes the use of a non-contact method to obtain the cardiac motion signal of the scanned object, avoiding the use of a collection device that needs to be in direct contact with the skin surface of the scanned object, and using the collected cardiac motion signal to accurately trigger the scan.

[0133] It should be noted that the steps shown in the above process or the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0134] In this embodiment, a scanning trigger device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and will not be repeated hereafter. The terms "module", "unit", "subunit", etc. used below may be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation in hardware, or a combination of software and hardware, is also possible and conceivable.

[0135] Fig. 9 is a structural block diagram of the scanning trigger device of this embodiment, such as Fig. 9 As shown, the device comprises:

[0136] An acquisition module 10 is used to acquire a heart motion signal of a scanned object acquired in real time;

[0137] A determination module 20, used to determine whether the latest signal data in the cardiac motion signal meets a preset trigger condition;

[0138] The trigger module 30 is used to generate a trigger instruction when the latest signal data meets the preset trigger condition; the trigger instruction is used to trigger the medical imaging device to perform a medical scan on the scanned object.

[0139] Through the device provided in this embodiment, the cardiac motion signal of the scanned object is acquired in real time, and the cardiac motion signal is acquired by the acquisition device; it is determined whether the latest signal data in the cardiac motion signal meets the preset trigger condition; when the latest signal data meets the preset trigger condition, a trigger instruction is generated; the trigger instruction is used to trigger the medical imaging device to perform a medical scan on the scanned object, which solves the problem of being unable to achieve accurate scan triggering and realizes accurate triggering of scanning using the acquired cardiac motion signal.

[0140] In some of the embodiments, the judgment module 20 is also used to determine the target data point in the latest signal data according to a preset selection rule; determine the predicted probability corresponding to the target data point; the predicted probability is used to indicate the probability that the target data point is a specific point of the cardiac motion signal; based on the predicted probability, determine whether the target data point meets the preset trigger condition; the preset trigger condition refers to the target data point being a specific point of the cardiac motion signal.

[0141] In some of the embodiments, the judgment module 20 is also used to compare the predicted probability of the target data point with a preset probability threshold; when the predicted probability of the target data point is greater than the probability threshold, the first waveform amplitude corresponding to the target data point is compared with the preset second waveform amplitude; when the difference between the first waveform amplitude and the second waveform amplitude is within a preset range, it is determined that the target data point meets the preset trigger condition.

[0142] In some embodiments, the judgment module 20 is further used to extract the latest signal data in the cardiac motion signal; perform windowing processing on the latest signal data to obtain corresponding windowed data; and determine the target data point in the windowed data according to a preset selection rule;

[0143] In some of the embodiments, the judgment module 20 is also used to process the target data point through the signal detection model to obtain the predicted probability corresponding to the target data point; wherein, the training of the signal detection model is: labeling the sample specific points and non-sample specific points of multiple cardiac motion signals used for model training; based on the preset data window length, segmenting the labeled cardiac motion signal to obtain multiple sample signals; constructing a sample data set corresponding to each sample signal, and training the signal detection model according to the sample data set.

[0144] In some of the embodiments, the trigger module 30 is also used to generate a corresponding trigger instruction when the target data point is detected to be a specific point of the cardiac motion signal; transmit the trigger instruction to the medical imaging device; the trigger instruction is used to instruct the medical imaging device to perform a medical scan on the scanned object.

[0145] In some of the embodiments, the acquisition module 10 is further used to acquire the heart motion signal of the scanned object in real time through a radar acquisition device.

[0146] It should be noted that the above modules can be functional modules or program modules, and can be implemented by software or hardware. For modules implemented by hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0147] In this embodiment, a scanning trigger system is also provided, which includes an acquisition device, a processing unit and a medical imaging device; wherein the acquisition device is communicatively connected with the processing unit, and the processing unit is connected with the medical imaging device;

[0148] An acquisition device, used for acquiring the cardiac motion signal of the scanned object in real time;

[0149] A processing unit is used to execute the steps in any of the above method embodiments.

[0150] Optionally, in this embodiment, the above processing may be configured to execute the following steps through a computer program:

[0151] S1, acquiring a cardiac motion signal of a scanned object collected in real time;

[0152] S2, determining whether the latest signal data in the cardiac motion signal meets a preset trigger condition;

[0153] S3, when the latest signal data meets the preset trigger condition, a trigger instruction is generated; the trigger instruction is used to trigger the medical imaging device to perform a medical scan on the scanned object.

[0154] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and will not be repeated in this embodiment.

[0155] In addition, in combination with the scan triggering method provided in the above embodiments, a storage medium may be provided in this embodiment to implement the scan triggering method. The storage medium stores a computer program, and when the computer program is executed by a processor, any scan triggering method in the above embodiments is implemented.

[0156] It should be understood that the specific embodiments described herein are only used to explain the application, rather than to limit it. Based on the embodiments provided in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the protection scope of this application.

[0157] Obviously, the drawings are only some examples or embodiments of the present application. For ordinary technicians in the field, the present application can also be applied to other similar situations based on these drawings without creative work. In addition, it is understandable that although the work done in this development process may be complicated and lengthy, for ordinary technicians in the field, certain changes in design, manufacturing or production based on the technical content disclosed in this application are only conventional technical means and should not be regarded as insufficient content disclosed in this application.

[0158] The term "embodiment" in this application refers to a specific feature, structure or characteristic described in conjunction with the embodiment that can be included in at least one embodiment of the present application. The appearance of this phrase in various locations in the specification does not necessarily mean the same embodiment, nor does it mean that it is mutually exclusive with other embodiments and is independent or optional. It is clearly or implicitly understood by those of ordinary skill in the art that the embodiments described in this application can be combined with other embodiments without conflict.

[0159] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of patent protection. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the scope of protection of the present application. Therefore, the scope of protection of the present application shall be subject to the attached claims.

Claims

1. A scanning triggering method, characterized in that: The method comprises: Acquire a heart motion signal of a scanned object acquired in real time; Determining whether the latest signal data in the cardiac motion signal meets a preset trigger condition; When the latest signal data meets the preset trigger condition, a trigger instruction is generated; the trigger instruction is used to trigger a medical imaging device to perform a medical scan on the scan object.

2. The scanning triggering method according to claim 1, characterized in that: The determining whether the latest signal data in the cardiac motion signal meets a preset trigger condition includes: Determine the target data point in the latest signal data according to a preset selection rule; Determine a prediction probability corresponding to the target data point; the prediction probability is used to indicate the probability that the target data point is a specific point of the cardiac motion signal; According to the predicted probability, it is determined whether the target data point meets the preset trigger condition; the preset trigger condition refers to that the target data point is a specific point of the cardiac motion signal.

3. The scanning triggering method according to claim 2, characterized in that: The step of judging whether the target data point meets the preset trigger condition according to the predicted probability includes: Comparing the predicted probability of the target data point with a preset probability threshold; When the predicted probability of the target data point is greater than the probability threshold, comparing the first waveform amplitude corresponding to the target data point with a preset second waveform amplitude; When the difference between the first waveform amplitude and the second waveform amplitude is within a preset range, it is determined that the target data point meets the preset trigger condition.

4. The scanning triggering method according to claim 2, characterized in that: The step of determining the target data point in the latest signal data according to a preset selection rule includes: Extracting the latest signal data from the cardiac motion signal; Performing windowing processing on the latest signal data to obtain corresponding windowed data; According to the preset selection rule, the target data point in the windowed data is determined.

5. The scanning triggering method according to claim 2, characterized in that: Determining the predicted probability corresponding to the target data point includes: The target data point is processed by a signal detection model to obtain a prediction probability corresponding to the target data point; wherein the training of the signal detection model is: Labeling sample-specific points and non-sample-specific points of multiple cardiac motion signals used for model training; Based on a preset data window length, segmenting the annotated cardiac motion signal to obtain multiple sample signals; A sample data set corresponding to each of the sample signals is constructed, and the signal detection model is trained according to the sample data set.

6. The scanning triggering method according to claim 2, characterized in that: generating a trigger instruction when the latest signal data meets the preset trigger condition; The trigger instruction is used to trigger the medical imaging device to perform a medical scan on the scanned object, including: When the target data point is detected to be a specific point of the cardiac motion signal, generating a corresponding trigger instruction; The trigger instruction is transmitted to the medical imaging device; the trigger instruction is used to instruct the medical imaging device to perform a medical scan on the scanned object.

7. The scanning triggering method according to claim 1, characterized in that: The step of acquiring the heart motion signal of the scanned object collected in real time includes: The heart motion signal of the scanned object is collected in real time by a radar collection device.

8. A scanning trigger device, characterized in that: The device comprises: An acquisition module, used to acquire the cardiac motion signal collected in real time; A judging module, used for judging whether the latest signal data in the cardiac motion signal meets a preset trigger condition; The trigger module is used to generate a trigger instruction when the latest signal data meets the preset trigger condition; the trigger instruction is used to trigger the medical imaging device to perform a medical scan on the scanned object.

9. A scanning trigger system, characterized in that: The system comprises: an acquisition device, a processing unit and a medical imaging device; wherein the acquisition device is communicatively connected to the processing unit, and the processing unit is connected to the medical imaging device; The acquisition device is used to acquire the cardiac motion signal of the scanned object in real time; The processing unit is used to execute the scan triggering method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the scan triggering method according to any one of claims 1 to 7 are implemented.

Images