A signal detection system and device based on IABP

Abstract

The embodiment of the present application provides a signal detection system and device based on IABP, which relates to the field of medical device technology. The signal detection device performs the following signal detection method when detecting signal feature points: obtaining the electrocardiogram (ECG) signal to be detected and converting the ECG signal into an ECG image; extracting the target waveform feature representing the signal morphology information in the ECG image, and determining the target ECG tag to which the ECG signal belongs based on the target waveform feature; determining the target parameter value that matches the target ECG tag, and updating the value of the detection parameter item for detecting signal feature points in the preset detection strategy to the target parameter value; and detecting the signal feature points of the ECG signal according to the preset detection strategy with the updated parameters. The solution provided by the embodiment of the present application is applied to accurately detect the signal feature points of the ECG signal.

Description

Technical Field

[0001] The present application relates to the field of medical device technology, and in particular to a signal detection system and device based on IABP. Background Art

[0002] An intra-aortic balloon pump (IABP) is a medical device commonly used to treat acute heart failure, cardiogenic shock, and cardiac pump failure caused by coronary artery disease (such as myocardial infarction). The primary function of an IABP is to cyclically increase aortic pressure through inflation and deflation, thereby improving cardiac perfusion and reducing cardiac afterload.

[0003] To ensure that the IABP can effectively support the heart, the timing of its inflation and deflation must be synchronized with the heart's contraction and relaxation. Specifically, inflation of the IABP usually occurs during diastole, while deflation occurs during systole.

[0004] Detecting the characteristic points of the ECG signal is a key factor in synchronously controlling balloon inflation and deflation. By accurately detecting the characteristic points in the ECG signal, the IABP device can inflate and deflate at the correct time to ensure optimal support for the heart. Summary of the Invention

[0005] The purpose of the embodiments of the present application is to provide a signal detection system and device based on IABP to accurately detect the signal feature points of the electrocardiogram signal. The specific technical solution is as follows:

[0006] In a first aspect, an embodiment of the present application provides an IABP-based signal detection system, the system comprising an IABP balloon catheter and a signal detection device. The IABP balloon catheter utilizes balloon inflation and deflation to unload the heart load. The signal detection device is configured to detect signal feature points of an electrocardiogram signal during operation of the IABP balloon catheter. The signal detection device performs the following signal detection method when detecting the signal feature points:

[0007] Acquiring an electrocardiogram signal to be detected, and converting the electrocardiogram signal into an electrocardiogram image;

[0008] extracting target waveform features representing signal morphology information from the electrocardiogram image, and determining a target electrocardiogram label to which the electrocardiogram signal belongs based on the target waveform features;

[0009] Determine a target parameter value that matches the target ECG tag, and update the value of the detection parameter item for detecting signal feature points in the preset detection strategy to the target parameter value;

[0010] According to the preset detection strategy of the updated parameters, the signal feature points of the electrocardiogram signal are detected.

[0011] In one embodiment of the present application, the signal detection device integrates a pre-trained lightweight label classification model;

[0012] The step of extracting target waveform features representing signal morphology information from the electrocardiogram image and determining a target electrocardiogram label to which the electrocardiogram signal belongs based on the target waveform features includes:

[0013] inputting the electrocardiogram image into the label classification model;

[0014] The label classification model extracts target waveform features representing signal morphology information in the electrocardiogram image, performs electrocardiogram label type matching based on the target waveform features, and outputs an electrocardiogram label;

[0015] The ECG label output by the label classification model is used as the target ECG label to which the ECG signal belongs.

[0016] In one embodiment of the present application, determining the target parameter value that matches the target ECG tag includes:

[0017] Determining a reference parameter value corresponding to the target ECG tag, wherein the reference parameter value is a detection parameter value for detecting a signal feature point of a standard signal corresponding to the target ECG tag;

[0018] Based on the reference parameter value, a target parameter value is determined.

[0019] In one embodiment of the present application, determining the target parameter value based on the reference parameter value includes:

[0020] Calculating a characteristic difference value between the target waveform characteristic and the waveform characteristic of the standard signal;

[0021] A reference parameter adjustment value corresponding to the characteristic difference value is determined, the reference parameter value is adjusted according to the reference parameter adjustment value, and the adjusted reference parameter value is determined as the target parameter value.

[0022] In a second aspect, an embodiment of the present application provides a signal detection device based on IABP, the device comprising:

[0023] An image conversion module, configured to obtain an electrocardiogram signal to be detected and convert the electrocardiogram signal into an electrocardiogram image;

[0024] a label determination module, configured to extract target waveform features representing signal morphology information from the electrocardiogram image, and determine a target electrocardiogram label to which the electrocardiogram signal belongs based on the target waveform features;

[0025] A parameter updating module is used to determine a target parameter value that matches the target ECG tag, and update the value of the detection parameter item used for detecting signal feature points in the preset detection strategy to the target parameter value;

[0026] The signal detection module is used to detect the signal feature points of the electrocardiogram signal according to a preset detection strategy of the updated parameters.

[0027] In one embodiment of the present application, the above-mentioned device integrates a pre-trained lightweight label classification model; the label determination module is specifically used to input the electrocardiogram image into the label classification model; the label classification model extracts the target waveform features representing the signal morphology information in the electrocardiogram image, performs electrocardiogram label type matching based on the target waveform features, and outputs the electrocardiogram label; the electrocardiogram label output by the label classification model is used as the target electrocardiogram label to which the electrocardiogram signal belongs.

[0028] In one embodiment of the present application, the parameter updating module includes:

[0029] a parameter determination submodule, configured to determine a reference parameter value corresponding to the target ECG tag, wherein the reference parameter value is a detection parameter value for detecting a signal feature point of a standard signal corresponding to the target ECG tag;

[0030] The parameter updating submodule is used to determine a target parameter value based on the reference parameter value, and update the value of the detection parameter item used to detect the signal feature point in the preset detection strategy to the target parameter value.

[0031] In one embodiment of the present application, the above-mentioned parameter updating submodule is specifically used to calculate the characteristic difference value between the target waveform characteristic and the waveform characteristic of the standard signal; determine the benchmark parameter adjustment value corresponding to the characteristic difference value, adjust the benchmark parameter value according to the benchmark parameter adjustment value, and determine the adjusted benchmark parameter value as the target parameter value.

[0032] In a third aspect, an embodiment of the present application provides an electronic medical device, comprising a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus;

[0033] Memory for storing computer programs;

[0034] The processor is configured to implement the method steps described in the first aspect when executing the program stored in the memory.

[0035] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method steps described in the first aspect are implemented.

[0036] From the above, it can be seen that when applying the solution provided in the embodiment of the present application, the signal feature points of the ECG signal are detected according to the preset detection strategy of the updated parameters, and the updated parameter values are determined dynamically in real time based on the target ECG tag to which the current ECG signal belongs. The target ECG tag represents the signal state of the current ECG signal. Accordingly, the updated parameter values are adaptive to the signal state of the current ECG signal. Then, according to the preset detection strategy of the updated parameters, it is possible to adapt to the signal state of the current ECG signal and accurately detect the signal feature points of the current ECG signal, thereby improving the detection accuracy of the signal feature points.

[0037] Of course, it is not necessary to achieve all the advantages described above at the same time when implementing any product or method of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other embodiments can also be obtained based on these drawings.

[0039] Figure 1 A schematic diagram of the structure of a signal detection system provided in an embodiment of the present application;

[0040] Figure 2 A schematic flow chart of the first signal detection method provided in an embodiment of the present application;

[0041] Figure 3 A schematic flow chart of a second signal detection method provided in an embodiment of the present application;

[0042] Figure 4 A schematic flow chart of a third signal detection method provided in an embodiment of the present application;

[0043] Figure 5 A schematic structural diagram of a signal detection device provided in an embodiment of the present application;

[0044] Figure 6 A schematic structural diagram of an electronic medical device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field based on this application are within the scope of protection of this application.

[0046] Before introducing the embodiments of the present application, the signal detection system provided by the present application is first described.

[0047] See also Figure 1 , Figure 1 This is a structural diagram of a signal detection system provided in an embodiment of the present application. The system includes an IABP balloon catheter 11 and a signal detection device 12.

[0048] The IABP balloon catheter 11 is placed in the patient's heart to provide cardiac circulation assistance.

[0049] The signal detection device 12 is used to detect signal feature points of the electrocardiogram signal during the operation of the IABP. The signal feature points generally include the QRS complex, R wave peak, P wave, T wave, etc.

[0050] The signal detection device 12 is integrated into the IABP host and placed outside the patient's body. The operation of the IABP balloon catheter 11 is controlled by the IABP host. The processor of the IABP host determines the IABP triggering time based on the signal feature points detected by the signal detection device 12.

[0051] Since the IABP triggering timing directly determines the operating quality of the IABP balloon catheter 11, if the IABP is triggered at an incorrect triggering time, it will cause serious damage to the patient's life and health. Therefore, accurate detection of signal feature points is very critical.

[0052] When the signal detection device detects the signal feature point, it performs the following Figure 2 The method steps of the corresponding embodiment.

[0053] See also Figure 2 , Figure 2 This is a flow chart of a first signal detection method provided in an embodiment of the present application. The method includes the following steps S201-S204.

[0054] Step S201: Acquire the electrocardiogram signal to be detected, and convert the electrocardiogram signal into an electrocardiogram image.

[0055] The above-mentioned ECG signals are collected in real time. For example, if an ECG lead wire is pre-attached to the patient's skin surface, and the signal detection device is connected to the above-mentioned ECG lead wire, the currently collected ECG signal can be obtained in real time.

[0056] The acquired ECG signal may be a signal obtained by preprocessing the collected initial ECG signal, such as filtering, standardization, and other preprocessing methods.

[0057] Compared with ECG signals, ECG images are two-dimensional data, which can directly and accurately represent the signal waveform characteristics of ECG signals from the perspective of timing information.

[0058] One implementation method for converting an ECG signal into an ECG image is as follows: using a preset coarse screening threshold to preliminarily screen candidate signal feature points in the ECG signal, where the candidate signal feature points represent feature points in the ECG signal that may be signal feature points; setting a preset number of sampling points before and after the candidate signal feature points, and using the patient's cardiac cycle to segment and intercept the set signal points, performing two-dimensional image conversion on the intercepted ECG signal to obtain an ECG image.

[0059] Step S202: extracting target waveform features representing signal morphology information from the electrocardiogram image, and determining a target electrocardiogram label to which the electrocardiogram signal belongs based on the target waveform features.

[0060] The target waveform features may include signal amplitude, kurtosis, skewness, frequency, etc. The target waveform features may be extracted using a preset feature extraction algorithm.

[0061] The target ECG labels described above can be understood as representing the patient's current cardiac state from the perspective of their ECG signals. Patients with different cardiac states will have different ECG signal appearances and, as a result, different target ECG labels. For example, the classification standards of the Association for the Advancement of Medical Instrumentation (AAMI) in the United States categorize ECG signals into 15 types of ECG labels, including normal heartbeats, premature ventricular beats, and premature atrial beats.

[0062] One implementation method for determining the target ECG label is to calculate the similarity between the target waveform feature and the waveform feature corresponding to each preset ECG label, and use the preset ECG label corresponding to the highest similarity as the target ECG label to which the ECG signal belongs.

[0063] Other implementations for determining target waveform characteristics can be found in the following Figure 3 The corresponding embodiments are not described in detail here.

[0064] Step S203: determining a target parameter value that matches the target ECG tag, and updating the value of the detection parameter item for detecting signal feature points in the preset detection strategy to the target parameter value.

[0065] Target parameter values may include detection thresholds, detection ranges, and the like.

[0066] The above-mentioned preset detection strategy can be any signal feature point detection strategy in the existing technology. For example, for the signal feature point R wave, the preset detection strategy includes bandpass filtering, differentiation, squaring, and moving integration of the electrocardiogram signal in sequence to enhance the R wave signal, and using the R wave detection threshold to detect the R wave position. The detection parameter items include parameter items such as the filter cutoff frequency, the moving integration window width, and the differential threshold iteration parameter.

[0067] Since the target parameter value is used as the value of the detection parameter item in the preset detection strategy, that is, the detection value used to detect the signal feature point in the preset detection strategy is updated in real time rather than being fixed.

[0068] One implementation method for determining the target detection parameter value is to pre-set a correspondence between the ECG tag and the detection parameter value, and determine the detection parameter value corresponding to the target ECG tag according to the correspondence as the target detection parameter value.

[0069] For other implementations of determining target detection parameter values, see the following Figure 4 The corresponding embodiments are not described in detail here.

[0070] Step S204: detecting signal feature points of the electrocardiogram signal according to the preset detection strategy of the updated parameters.

[0071] From the above, it can be seen that when applying the solution provided in this embodiment, the signal feature points of the ECG signal are detected according to the preset detection strategy of the updated parameters, and the updated parameter values are determined dynamically in real time based on the target ECG tag to which the current ECG signal belongs. The target ECG tag represents the signal state of the current ECG signal. Accordingly, the updated parameter values are adaptive to the signal state of the current ECG signal. Then, according to the preset detection strategy of the updated parameters, it is possible to adapt to the signal state of the current ECG signal and accurately detect the signal feature points of the current ECG signal, thereby improving the detection accuracy of the signal feature points.

[0072] The foregoing Figure 2 In a corresponding embodiment, the signal detection device can integrate a pre-trained lightweight label classification model. Since the label classification model is a lightweight model, it can be used on mobile devices and embedded devices, ensuring accuracy while reducing computing resources and memory consumption.

[0073] The above-mentioned label classification model is obtained through pre-training. Specifically, the ECG signals in the existing ECG database are divided into three groups of data: testing, training, and verification. The above-mentioned ECG signals are converted into two-dimensional images. A lightweight neural network is used for training and testing, such as modifying the input shape of the model and performing weight averaging on the initial convolutional layer. The model after training is used as the label classification model.

[0074] The above-mentioned lightweight neural network can be MobileNetV2. MobileNetV2 is based on key technologies such as depthwise separable convolution and inverted residual structure, which significantly improves computational efficiency while maintaining high accuracy.

[0075] Based on this, the aforementioned step S202 can be implemented according to the following steps S302-S304. Based on this, see Figure 3 , Figure 3This is a flow chart of a second signal detection method provided in an embodiment of the present application. The above method includes the following steps S301-S306.

[0076] Step S301: Acquire the electrocardiogram signal to be detected, and convert the electrocardiogram signal into an electrocardiogram image.

[0077] The above step S301 is the same as the above step S201 and will not be described again here.

[0078] Step S302: Input the electrocardiogram image into the label classification model.

[0079] Step S303: The label classification model extracts target waveform features representing signal morphology information in the ECG image, performs ECG label type matching based on the target waveform features, and outputs an ECG label.

[0080] The label classification model is pre-trained based on a large amount of training sample data. The label classification model has learned the law of the characteristic relationship between ECG images and ECG labels. Therefore, when the ECG image is input into the label classification model, the output ECG label can accurately represent the label to which the ECG signal belongs.

[0081] Label classification models can utilize depthwise separable convolutions, which decompose standard convolution into two simpler operations: channel-by-channel convolution and central convolution. These operations output ECG labels. Compared to standard convolutions, these two types of convolutions significantly reduce computational effort and the number of parameters, resulting in a lightweight model architecture.

[0082] Step S304: The ECG label output by the label classification model is used as the target ECG label to which the ECG signal belongs.

[0083] Step S305: determining a target parameter value that matches the target ECG tag, and updating the value of the detection parameter item for detecting signal feature points in the preset detection strategy to the target parameter value.

[0084] Step S306: Detecting signal feature points of the ECG signal according to the preset detection strategy of the updated parameters.

[0085] The above steps S305-S306 are the same as the above Figure 2 Steps S203 - S204 of the corresponding embodiment are the same and will not be described again here.

[0086] The foregoing Figure 2 In the corresponding embodiment, in addition to determining the target parameter value using the aforementioned implementation, step S203 can also be implemented according to the following steps S403-S404. Figure 4 , Figure 4This is a flow chart of a third signal detection method provided in an embodiment of the present application. The method includes the following steps S401-S405.

[0087] Step S401: Acquire the electrocardiogram signal to be detected, and convert the electrocardiogram signal into an electrocardiogram image.

[0088] Step S402: extracting target waveform features representing signal morphology information from the ECG image, and determining a target ECG label to which the ECG signal belongs based on the target waveform features.

[0089] The above steps S401-S402 are the same as the above Figure 2 Steps S201 - S202 of the corresponding embodiment are the same and will not be described again here.

[0090] Step S403: Determine the reference parameter value corresponding to the target ECG tag.

[0091] The above-mentioned reference parameter values are detection parameter values used to detect the signal feature points of the standard signal corresponding to the target ECG tag.

[0092] One implementation method for determining the reference parameter value is: according to the pre-set correspondence between the ECG tag and the standard signal, determine the standard signal corresponding to the target ECG tag, and obtain the detection parameter value of the signal feature point used to detect the standard signal as the reference parameter value.

[0093] In this embodiment, the detection parameter values of the detection signal characteristic points corresponding to various types of standard signals may be preset, and the reference parameter values may be determined according to the preset relationship.

[0094] Step S404: Based on the reference parameter value, a target parameter value is determined, and the value of the detection parameter item for detecting the signal feature point in the preset detection strategy is updated to the target parameter value.

[0095] A first implementation method for determining the target parameter value is to directly determine the reference parameter value as the target parameter value.

[0096] The second implementation method for determining the target parameter value is: calculating the characteristic difference value between the target waveform characteristics and the waveform characteristics of the standard signal; determining the reference parameter adjustment value corresponding to the characteristic difference value, adjusting the reference parameter value according to the reference parameter adjustment value, and determining the adjusted reference parameter value as the target parameter value.

[0097] The standard signal is the standard signal of the target ECG tag to which the current ECG signal belongs. Even two signals belonging to the same ECG tag still have signal differences. Therefore, the characteristic difference value represents the specific difference between the current ECG signal and the standard signal. The target parameter value adjusted based on the characteristic difference value is then more suitable for the signal specificity of the current ECG signal, thereby more accurately detecting the signal feature points of the ECG signal.

[0098] One implementation method for determining the reference parameter adjustment value is to pre-set a correspondence between the characteristic difference and the adjustment value, and determine the reference parameter adjustment value corresponding to the characteristic difference value according to the correspondence.

[0099] One implementation of adjusting the reference parameter value is: calculating a sum of the reference parameter adjustment value and the reference parameter value, and determining the calculated sum as the adjusted reference parameter value.

[0100] Step S405: Detecting signal feature points of the electrocardiogram signal according to the preset detection strategy of the updated parameters.

[0101] The above step S405 is the same as the above step S204 and will not be repeated here.

[0102] It can be seen that in this embodiment, since the determined reference parameter value is the detection parameter value corresponding to the standard signal in the target ECG tag, the detection accuracy of the above detection parameter value is relatively high. Therefore, the detection accuracy of the determined reference parameter value is relatively high, thereby achieving accurate detection of the signal feature points of the ECG signal.

[0103] Corresponding to the above-mentioned IABP-based signal detection system, an embodiment of the present application further provides an IABP-based signal detection device.

[0104] See also Figure 5 , Figure 5 This is a schematic diagram of the structure of a signal detection device provided in an embodiment of the present application, the device comprising:

[0105] An image conversion module 501 is configured to obtain an electrocardiogram signal to be detected and convert the electrocardiogram signal into an electrocardiogram image;

[0106] a label determination module 502 for extracting target waveform features representing signal morphology information from the electrocardiogram image, and determining a target electrocardiogram label to which the electrocardiogram signal belongs based on the target waveform features;

[0107] The parameter updating module 503 is used to determine a target parameter value that matches the target ECG tag, and update the value of the detection parameter item used for detecting the signal feature point in the preset detection strategy to the target parameter value;

[0108] The signal detection module 504 is configured to detect signal feature points of the electrocardiogram signal according to a preset detection strategy of the updated parameters.

[0109] From the above, it can be seen that when applying the solution provided in this embodiment, the signal feature points of the ECG signal are detected according to the preset detection strategy of the updated parameters, and the updated parameter values are determined dynamically in real time based on the target ECG tag to which the current ECG signal belongs. The target ECG tag represents the signal state of the current ECG signal. Accordingly, the updated parameter values are adaptive to the signal state of the current ECG signal. Then, according to the preset detection strategy of the updated parameters, it is possible to adapt to the signal state of the current ECG signal and accurately detect the signal feature points of the current ECG signal, thereby improving the detection accuracy of the signal feature points.

[0110] In one embodiment of the present application, the above-mentioned device integrates a pre-trained lightweight label classification model; the label determination module 502 is specifically used to input the ECG image into the label classification model; the label classification model extracts the target waveform features representing the signal morphology information in the ECG image, performs ECG label type matching based on the target waveform features, and outputs the ECG label; the ECG label output by the label classification model is used as the target ECG label to which the ECG signal belongs.

[0111] The label classification model is a lightweight model suitable for use on mobile and embedded devices, ensuring accuracy while reducing computing resources and memory consumption. Furthermore, the label classification model is pre-trained based on a large amount of training sample data. The label classification model has learned the relationship between the characteristics of ECG images and ECG labels. Therefore, when an ECG image is input into the label classification model, the output ECG label accurately represents the label to which the ECG signal belongs.

[0112] In one embodiment of the present application, the parameter updating module 503 includes:

[0113] A parameter determination submodule, configured to determine a reference parameter value corresponding to the target ECG tag, wherein the reference parameter value is a detection parameter value for detecting a signal feature point of a standard signal corresponding to the target ECG tag;

[0114] The parameter updating submodule is used to determine a target parameter value based on the reference parameter value, and update the value of the detection parameter item used to detect the signal feature point in the preset detection strategy to the target parameter value.

[0115] It can be seen that in this embodiment, since the determined reference parameter value is the detection parameter value corresponding to the standard signal in the target ECG tag, the detection accuracy of the above detection parameter value is relatively high. Therefore, the detection accuracy of the determined reference parameter value is relatively high, thereby achieving accurate detection of the signal feature points of the ECG signal.

[0116] In one embodiment of the present application, the above-mentioned parameter updating submodule is specifically used to calculate the characteristic difference value between the target waveform characteristic and the waveform characteristic of the standard signal; determine the benchmark parameter adjustment value corresponding to the characteristic difference value, adjust the benchmark parameter value according to the benchmark parameter adjustment value, and determine the adjusted benchmark parameter value as the target parameter value.

[0117] As can be seen, the characteristic difference value above represents the specific difference between the current ECG signal and the standard signal. Therefore, the target parameter value adjusted based on the characteristic difference value is more suitable for the signal specificity of the current ECG signal, thereby more accurately detecting the signal feature points of the ECG signal.

[0118] Corresponding to the above-mentioned IABP-based signal detection system, the present application embodiment provides an electronic medical device, see Figure 6 , Figure 6 This is a schematic diagram of the structure of an electronic medical device provided in an embodiment of the present application. The electronic medical device includes a processor 601, a communication interface 602, a memory 603, and a communication bus 604. The processor 601, the communication interface 602, and the memory 603 communicate with each other via the communication bus 604.

[0119] Memory 603, used for storing computer programs;

[0120] The processor 601 is configured to implement the above signal detection method steps when executing the program stored in the memory 603 .

[0121] The communication bus mentioned in the controllers above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. This communication bus can be divided into address buses, data buses, and control buses. For ease of illustration, the figure uses only a single thick line, but this does not mean that there is only one bus or only one type of bus.

[0122] The communication interface is used for communication between the above controller and other devices.

[0123] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage. Alternatively, the memory may be at least one storage device located away from the processor.

[0124] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components.

[0125] In another embodiment provided in the present application, a computer-readable storage medium is further provided, in which a computer program is stored. When the computer program is executed by a processor, the signal detection method provided in the embodiment of the present application is implemented.

[0126] In another embodiment provided by the present application, a computer program product including instructions is also provided, which, when executed on a computer, enables the computer to implement the above-mentioned signal detection method provided by the embodiment of the present application.

[0127] From the above, it can be seen that when applying the solution provided in this embodiment, the signal feature points of the ECG signal are detected according to the preset detection strategy of the updated parameters, and the updated parameter values are determined dynamically in real time based on the target ECG tag to which the current ECG signal belongs. The target ECG tag represents the signal state of the current ECG signal. Accordingly, the updated parameter values are adaptive to the signal state of the current ECG signal. Then, according to the preset detection strategy of the updated parameters, it is possible to adapt to the signal state of the current ECG signal and accurately detect the signal feature points of the current ECG signal, thereby improving the detection accuracy of the signal feature points.

[0128] In the above embodiments, all or part of the embodiments can be implemented using software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media. The available medium can be a magnetic medium (e.g., a floppy disk, hard disk, tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).

[0129] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0130] Each embodiment in this specification is described in a related manner. Similar portions between the various embodiments can be referenced to each other. Each embodiment focuses on the differences between the other embodiments. In particular, the apparatus, electronic medical device, and computer-readable storage medium embodiments are generally similar to the method embodiments, so their descriptions are relatively simplified. For relevant portions, reference can be made to the descriptions of the method embodiments.

[0131] The above description is only a preferred embodiment of the present application and is not intended to limit the scope of protection of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application are included in the scope of protection of the present application.

Claims

1. A signal detection system based on IABP, characterized in that: The system includes an IABP balloon catheter and a signal detection device. The IABP balloon catheter unloads the heart load by inflating and deflating the balloon. The signal detection device is used to detect signal feature points of the electrocardiogram signal when the IABP balloon catheter is in operation. The signal detection device performs the following signal detection method when detecting the signal feature points: Acquiring an electrocardiogram signal to be detected, and converting the electrocardiogram signal into an electrocardiogram image; extracting target waveform features representing signal morphology information from the electrocardiogram image, and determining a target electrocardiogram label to which the electrocardiogram signal belongs based on the target waveform features; Determine a target parameter value that matches the target ECG tag, and update the value of the detection parameter item for detecting signal feature points in the preset detection strategy to the target parameter value; wherein the target parameter value includes a detection threshold and a detection range, and the detection value for detecting signal feature points in the preset detection strategy is updated in real time; Detecting signal feature points of the electrocardiogram signal according to a preset detection strategy of the updated parameters; Determining the target parameter value that matches the target ECG tag includes: Determining a reference parameter value corresponding to the target ECG tag, wherein the reference parameter value is a detection parameter value for detecting a signal feature point of a standard signal corresponding to the target ECG tag; determining a target parameter value based on the reference parameter value; The determining of the target parameter value based on the reference parameter value includes: Calculating a characteristic difference value between the target waveform characteristic and the waveform characteristic of the standard signal; A reference parameter adjustment value corresponding to the characteristic difference value is determined, the reference parameter value is adjusted according to the reference parameter adjustment value, and the adjusted reference parameter value is determined as the target parameter value.

2. The system according to claim 1, wherein: The signal detection device integrates a pre-trained lightweight label classification model; The step of extracting target waveform features representing signal morphology information from the electrocardiogram image and determining a target electrocardiogram label to which the electrocardiogram signal belongs based on the target waveform features includes: inputting the electrocardiogram image into the label classification model; The label classification model extracts target waveform features representing signal morphology information in the electrocardiogram image, performs electrocardiogram label type matching based on the target waveform features, and outputs an electrocardiogram label; The ECG label output by the label classification model is used as the target ECG label to which the ECG signal belongs.

3. A signal detection device based on IABP, characterized in that: The device comprises: An image conversion module, configured to obtain an electrocardiogram signal to be detected and convert the electrocardiogram signal into an electrocardiogram image; a label determination module, configured to extract target waveform features representing signal morphology information from the electrocardiogram image, and determine a target electrocardiogram label to which the electrocardiogram signal belongs based on the target waveform features; a parameter updating module, configured to determine a target parameter value that matches the target ECG tag, and update the value of a detection parameter item used to detect signal feature points in a preset detection strategy to the target parameter value; wherein the target parameter value includes a detection threshold and a detection range, and the detection value used to detect signal feature points in the preset detection strategy is updated in real time; a signal detection module, configured to detect signal feature points of the electrocardiogram signal according to a preset detection strategy of the updated parameters; The parameter updating module includes: a parameter determination submodule, configured to determine a reference parameter value corresponding to the target ECG tag, wherein the reference parameter value is a detection parameter value for detecting a signal feature point of a standard signal corresponding to the target ECG tag; A parameter updating submodule, configured to determine a target parameter value based on the reference parameter value, and update the value of a detection parameter item used to detect signal feature points in a preset detection strategy to the target parameter value; The parameter updating submodule is specifically used to calculate the characteristic difference value between the target waveform characteristic and the waveform characteristic of the standard signal; determine the reference parameter adjustment value corresponding to the characteristic difference value, adjust the reference parameter value according to the reference parameter adjustment value, and determine the adjusted reference parameter value as the target parameter value.

4. The device according to claim 3, characterized in that The device integrates a pre-trained lightweight label classification model; the label determination module is specifically used to input the electrocardiogram image into the label classification model; the label classification model extracts the target waveform features representing the signal morphology information in the electrocardiogram image, performs electrocardiogram label type matching based on the target waveform features, and outputs the electrocardiogram label; The ECG label output by the label classification model is used as the target ECG label to which the ECG signal belongs.

5. An electronic medical device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; Memory for storing computer programs; The processor is configured to implement the method steps described in claim 1 or 2 when executing a program stored in the memory.

6. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method steps of claim 1 or 2 are implemented.

Images