Processing method and device of electrocardiogram, medical equipment and storage medium

Abstract

This application provides a method, apparatus, medical device, and storage medium for processing electrocardiograms (ECGs). The method includes: plotting an ECG scatter plot based on a target ECG; performing ECG waveform analysis on heartbeats on the target ECG based on the ECG scatter plot to obtain waveform parameters of the heartbeats; and superimposing the waveform parameters onto the heartbeats to display them on the target ECG. This application enables accurate ECG waveform analysis, eliminating the need for doctors to manually measure ECG waveform parameters when analyzing Holter monitors, thus reducing the doctor's analysis time and alleviating their workload.

Description

Technical Field

[0001] This application relates to the field of medical technology, specifically to a method and apparatus for processing electrocardiograms, a medical device, and a computer-readable storage medium. Background Technology

[0002] Electrocardiogram (ECG) signals effectively reflect the electrical activity and health status of the heart. ECG signals are easily obtained from an ECG, and doctors observe the waveform. Precisely locating the characteristic points of the ECG waveform and calculating its relevant parameters can help doctors in disease analysis and pathological research, reducing their workload and aiding in diagnosis.

[0003] The existing method of Holter monitoring diagnosis involves classifying heartbeats into different categories, and then further subdividing each category into multiple templates. Doctors then perform diagnostic analysis based on the heartbeat category and templates. Specifically, heartbeat template classification means that in a given Holter monitor, heartbeats with similar morphologies are grouped into the same category, which constitutes one heartbeat template. Heartbeats with different morphologies are classified into different templates.

[0004] The aforementioned analysis model demands high accuracy in heartbeat classification. If the accuracy is low, doctors must manually classify each heartbeat individually, which is time-consuming, laborious, and inefficient. Furthermore, the overall accuracy of current heartbeat classification algorithms is not high, requiring doctors to spend a significant amount of time interpreting images during the diagnostic process. Moreover, current auxiliary diagnostic tools typically only output the heartbeat category; other auxiliary analysis parameters require manual measurement by doctors, further reducing their workload. Summary of the Invention

[0005] The purpose of this application is to provide a method, apparatus, medical device, and computer-readable storage medium for processing electrocardiograms, which can accurately analyze electrocardiogram waveforms and reduce the workload of doctors.

[0006] The first aspect of this application provides a method for processing an electrocardiogram, comprising:

[0007] Draw an electrocardiogram scatter plot based on the target electrocardiogram;

[0008] Based on the electrocardiogram scatter plot, the heartbeats on the target electrocardiogram are analyzed to obtain the waveform parameters of the heartbeats;

[0009] The waveform parameters are superimposed on the heartbeat to display on the target electrocardiogram.

[0010] In one possible implementation, in the method provided in this application, the step of drawing an electrocardiogram scatter plot based on the target electrocardiogram includes:

[0011] Denoising the target electrocardiogram signal;

[0012] R-wave localization is performed on the target electrocardiogram after signal denoising to generate an RR interval sequence;

[0013] An electrocardiogram scatter plot was drawn based on the RR interval sequence.

[0014] In one possible implementation, the method provided in this application, wherein the signal denoising of the target electrocardiogram includes:

[0015] Baseline drift and power frequency interference in the target electrocardiogram are removed, and bandpass filtering is applied to the target electrocardiogram to obtain the target electrocardiogram after signal denoising.

[0016] In one possible implementation, in the method provided in this application, the step of performing electrocardiogram waveform analysis on the heartbeats on the target electrocardiogram based on the electrocardiogram scatter plot to obtain the waveform parameters of the heartbeats includes:

[0017] Based on the ECG scatter plot, all heartbeats on the target ECG are classified into template class or non-template class;

[0018] From each type of template, a heartbeat is determined as the heartbeat template for that type of template, and the electrocardiogram waveform is segmented for each heartbeat in that type of template according to the heartbeat template;

[0019] For each heartbeat in the non-template class, artifact identification is performed to obtain non-artifact heartbeats and artifact heartbeats, and electrocardiogram waveform segmentation is performed on each of the non-artifact heartbeats;

[0020] The ECG waveform feature points of each heartbeat are determined based on the ECG waveform segmentation results of each heartbeat.

[0021] The waveform parameters of the heartbeat are obtained based on the ECG waveform feature points.

[0022] In one possible implementation, in the method provided in this application, classifying all heartbeats on the target electrocardiogram into a template class or a non-template class based on the electrocardiogram scatter plot includes:

[0023] The electrocardiogram scatter plot is segmented to obtain multiple corresponding segmented regions;

[0024] For each segmented region, the heartbeats corresponding to the scattered points in the segmented region are superimposed to generate a superimposed waveform diagram;

[0025] The superimposed waveform is decomposed, and N heartbeats are classified into one template according to morphological similarity, resulting in M ​​template classes, where N is greater than a preset threshold K.

[0026] The heartbeats corresponding to each segmented region on the electrocardiogram scatter plot are classified, and all heartbeats are classified into template class or non-template class.

[0027] In one possible implementation, in the method provided in this application, the step of segmenting the electrocardiogram waveform for each heartbeat in the template according to the heartbeat template includes:

[0028] The electrocardiogram waveform of the heartbeat template is segmented to obtain the template segmentation result;

[0029] Determine the offset between each heartbeat in the template corresponding to the heartbeat template and the heartbeat template;

[0030] Based on the coordinates of the heartbeat, the offset, and the template segmentation result, the ECG waveform segmentation result for each heartbeat in the template is determined.

[0031] In one possible implementation, the method provided in this application further includes:

[0032] Store user-added corrections and annotations to the ECG scatter plot or the waveform parameters.

[0033] A second aspect of this application provides an electrocardiogram (ECG) processing apparatus, comprising:

[0034] The plotting module is used to draw an electrocardiogram scatter plot based on the target electrocardiogram.

[0035] The analysis module is used to perform electrocardiogram waveform analysis on the heartbeats on the target electrocardiogram based on the electrocardiogram scatter plot, and obtain the waveform parameters of the heartbeats;

[0036] A visualization module is used to overlay the waveform parameters onto the heartbeat to display it on the target electrocardiogram.

[0037] In one possible implementation, in the apparatus provided in this application, the drawing module is specifically used for:

[0038] Denoising the target electrocardiogram signal;

[0039] R-wave localization is performed on the target electrocardiogram after signal denoising to generate an RR interval sequence;

[0040] An electrocardiogram scatter plot was drawn based on the RR interval sequence.

[0041] In one possible implementation, in the apparatus provided in this application, the drawing module is specifically used to: remove baseline drift and power frequency interference from the target electrocardiogram, and perform bandpass filtering on the target electrocardiogram to obtain a target electrocardiogram after signal denoising.

[0042] In one possible implementation, in the apparatus provided in this application, the analysis module is specifically used for:

[0043] Based on the ECG scatter plot, all heartbeats on the target ECG are classified into template class or non-template class;

[0044] From each type of template, a heartbeat is determined as the heartbeat template for that type of template, and the electrocardiogram waveform is segmented for each heartbeat in that type of template according to the heartbeat template;

[0045] For each heartbeat in the non-template class, artifact identification is performed to obtain non-artifact heartbeats and artifact heartbeats, and electrocardiogram waveform segmentation is performed on each of the non-artifact heartbeats;

[0046] The ECG waveform feature points of each heartbeat are determined based on the ECG waveform segmentation results of each heartbeat.

[0047] The waveform parameters of the heartbeat are obtained based on the ECG waveform feature points.

[0048] In one possible implementation, in the apparatus provided in this application, the analysis module is specifically used for:

[0049] The electrocardiogram scatter plot is segmented to obtain multiple corresponding segmented regions;

[0050] For each segmented region, the heartbeats corresponding to the scattered points in the segmented region are superimposed to generate a superimposed waveform diagram;

[0051] The superimposed waveform is decomposed, and N heartbeats are classified into one template according to morphological similarity, resulting in M ​​template classes, where N is greater than a preset threshold K.

[0052] The heartbeats corresponding to each segmented region on the electrocardiogram scatter plot are classified, and all heartbeats are classified into template class or non-template class.

[0053] In one possible implementation, in the apparatus provided in this application, the analysis module is specifically used for:

[0054] The electrocardiogram waveform of the heartbeat template is segmented to obtain the template segmentation result;

[0055] Determine the offset between each heartbeat in the template corresponding to the heartbeat template and the heartbeat template;

[0056] Based on the coordinates of the heartbeat, the offset, and the template segmentation result, the ECG waveform segmentation result for each heartbeat in the template is determined.

[0057] In one possible implementation, in the apparatus provided in this application, the visualization module is further configured to:

[0058] Store user-added corrections and annotations to the ECG scatter plot or the waveform parameters.

[0059] A third aspect of this application provides a medical device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when running the computer program, performs an action to implement the method described in the first aspect of this application.

[0060] A fourth aspect of this application provides a computer-readable medium having computer-readable instructions stored thereon, the computer-readable instructions being executable by a processor to implement the method described in the first aspect of this application.

[0061] Compared to existing technologies, the electrocardiogram (ECG) processing method, apparatus, medical device, and storage medium provided in this application generate an ECG scatter plot based on a target ECG; perform ECG waveform analysis on the heartbeats on the target ECG based on the ECG scatter plot to obtain the waveform parameters of the heartbeats; and superimpose the waveform parameters onto the heartbeats to display them on the target ECG. This application enables accurate ECG waveform analysis, eliminating the need for doctors to manually measure ECG waveform parameters when analyzing Holter monitors, thus shortening their analysis time and reducing their workload. Attached Figure Description

[0062] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the scope of this application. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0063] Figure 1 A flowchart of an electrocardiogram processing method provided in this application is shown;

[0064] Figure 2 A flowchart of step S101 provided in this application is shown;

[0065] Figure 3 A flowchart of step S102 provided in this application is shown;

[0066] Figure 4 A schematic diagram of the segmentation results of the electrocardiogram waveform provided in this application is shown;

[0067] Figure 5 This paper presents a schematic diagram of the ECG waveform feature point detection results provided in this application.

[0068] Figure 6 One of the waveform parameters of the heartbeat provided in this application is shown;

[0069] Figure 7 This is the second schematic diagram of the waveform parameters of the heartbeat provided in this application;

[0070] Figure 8 A flowchart illustrating a specific electrocardiogram processing method provided in this application is shown;

[0071] Figure 9 A schematic diagram of an electrocardiogram processing device provided in this application is shown;

[0072] Figure 10 A schematic diagram of a medical device provided in this application is shown;

[0073] Figure 11 A schematic diagram of a computer-readable storage medium provided in this application is shown. Detailed Implementation

[0074] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0075] It should be noted that, unless otherwise stated, the technical or scientific terms used in this application shall have the ordinary meaning as understood by one of ordinary skill in the art to which this application pertains.

[0076] Furthermore, the terms "first" and "second," etc., are used to distinguish different objects, not to describe a specific order. Additionally, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to those processes, methods, products, or apparatuses.

[0077] This application provides a method and apparatus for processing electrocardiograms, a medical device, and a computer-readable medium, which will be described below with reference to the accompanying drawings.

[0078] An electrocardiogram (ECG) records heartbeats. The characteristic waveforms of a heartbeat include the P wave, QRS complex, T wave, and a relatively flat waveform during the refractory period. The corresponding characteristic points include the start, end, and peak of the P wave; the start, end, and peak of the QRS complex and the Q, R, and S waves; and the start, end, and peak of the T wave.

[0079] Heartbeat types include normal, atrial premature beats, ventricular premature beats, pacing, etc., and the heartbeat type can be determined based on the characteristic waveform of the heartbeat.

[0080] Holter monitoring is a continuous recording of the patient's surface electrocardiogram during daily life. It contains far more information than a conventional electrocardiogram, which increases the workload of electrocardiogram analysis. This makes automatic detection and analysis technology of electrocardiogram necessary.

[0081] Please refer to Figure 1 The figure shows a flowchart of an electrocardiogram (ECG) processing method provided by some embodiments of this application. As shown, the ECG processing method may include the following steps S101 to S103:

[0082] S101. Draw an electrocardiogram scatter plot based on the target electrocardiogram;

[0083] The target ECG is the ECG to be processed, which can be either a Holter monitor or a standard ECG. The target ECG can be acquired in real-time by the device or pre-stored ECG data in a database.

[0084] A scatter plot of electrocardiogram (ECG), also known as a Lorenz plot, is drawn from the RR interval sequence of an ECG waveform. It employs a nonlinear chaotic methodology to interpret the RR interval sequence; the RR interval is the duration of the R wave between two consecutive QRS waves. The cardiac rhythm represented by continuous RR intervals is an important manifestation of the dynamic changes in the human body over time, containing crucial electrophysiological information. Furthermore, ECG scatter plots can be used for rapid analysis of ECGs, shortening the time required to analyze long-term Holter ECGs and improving the efficiency of physicians.

[0085] Specifically, such as Figure 2 As shown, step S101 includes the following steps:

[0086] S201. Perform signal noise reduction on the target electrocardiogram;

[0087] The signal noise reduction includes: removing baseline drift and power frequency interference, and performing bandpass filtering.

[0088] Specifically, baseline drift and power frequency interference in the target electrocardiogram can be removed first, and then bandpass filtering can be performed to obtain the target electrocardiogram after signal denoising.

[0089] S202. Locate the R-wave in the target electrocardiogram after signal denoising and generate an RR interval sequence;

[0090] The R wave is part of the QRS complex on an electrocardiogram. The R wave can be located using the Pan-Tompkins algorithm, the specific process of which will not be elaborated here.

[0091] S203. Draw an electrocardiogram scatter plot based on the RR interval sequence.

[0092] The generated ECG scatter plots can include time-sharing scatter plots, 24-hour scatter plots, and difference scatter plots. Among them, time-sharing scatter plots are generated according to a set time length, such as drawing a scatter plot once per hour, and the plot also records the collection time and heart rate.

[0093] S102. Based on the electrocardiogram scatter plot, perform electrocardiogram waveform analysis on the heartbeats on the target electrocardiogram to obtain the waveform parameters of the heartbeats;

[0094] The waveform parameters of a heartbeat include the PR interval, PR segment, QRS interval, QT interval, and ST segment.

[0095] Specifically, such as Figure 3 As shown, step S102 can be achieved as follows:

[0096] S301. Based on the ECG scatter plot, classify all heartbeats on the target ECG into template class or non-template class;

[0097] Classifying all heartbeats into template or non-template categories means that, in the target electrocardiogram, heartbeats with similar morphologies are grouped into the same category, which is a template category. Heartbeats with different morphologies are classified into different template categories, and heartbeats that cannot be classified into a particular template category are classified into non-template categories.

[0098] Template classes can correspond to heart rate types, such as normal, atrial premature beats, ventricular premature beats, pacing, etc.

[0099] Specifically, the ECG scatter plot is first segmented to obtain multiple corresponding segmented regions; for each segmented region, the heartbeats corresponding to the scatter points in the segmented region are superimposed to generate a superimposed waveform; the superimposed waveform is decomposed, and N heartbeats with similar shapes are classified into a template according to morphological similarity, resulting in M ​​template classes, where N is greater than a preset threshold K to prevent the number of template classes from being too large; the heartbeats corresponding to each segmented region on the ECG scatter plot are classified, and all heartbeats are classified into template classes or non-template classes.

[0100] For example, for time-sharing scatter plots, generating scatter plots by hour can yield 24 scatter plots. First, the heartbeats corresponding to each segmented region on the 1-hour scatter plot are classified, and this process is repeated 24 times to process the 24-hour data. Finally, all heartbeats are classified into template class and non-template class.

[0101] The calculation of morphological similarity can be based on the feature parameters of the heartbeat. The feature parameters of the heartbeat can include the normalized area, normalized width, and normalized height of the heartbeat. For example, heartbeats with a similarity greater than 0.99 can be merged into a single template.

[0102] The segmentation of the generated scatter plot, the generation of the superimposed waveform, and the decomposition of the superimposed waveform can all be performed using traditional algorithms or pre-trained deep learning algorithms, which will not be elaborated upon here.

[0103] S302. Determine a heartbeat from each type of template as the heartbeat template for that type of template, and perform ECG waveform segmentation on each heartbeat in that type of template according to the heartbeat template;

[0104] Specifically, by selecting one heartbeat from each type of template as the heartbeat template for that type of template, M heartbeat templates can be obtained.

[0105] Furthermore, for each heartbeat template, the heartbeat template is segmented into an electrocardiogram waveform to obtain a template segmentation result. The offset of each heartbeat in the template corresponding to the heartbeat template from the heartbeat template is determined. Based on the coordinates of the heartbeat, the offset, and the template segmentation result, the electrocardiogram waveform segmentation result of each heartbeat in the template is determined.

[0106] For example, segmenting the electrocardiogram waveforms of M heartbeat templates can yield the segmentation results of the P wave, QRS complex, and T wave of the M heartbeat templates, such as... Figure 4 The diagram shows the segmentation results of an electrocardiogram (ECG) waveform. For each template, based on the segmentation results of the heartbeat template, the offset of each heartbeat within that template class relative to the template is determined. This offset can include horizontal and vertical offsets. The coordinates of a heartbeat refer to its position on the ECG. Based on the coordinates and offsets of the heartbeats, the ECG waveform segmentation results for each heartbeat within the same template can be quickly determined.

[0107] S303. Perform artifact identification on each heartbeat in the non-template class to obtain non-artifact heartbeats and artifact heartbeats, and perform ECG waveform segmentation on each of the non-artifact heartbeats.

[0108] Any changes on an electrocardiogram that are not caused by cardiac excitation are called artifacts.

[0109] In non-template type heart beats, artifact identification is performed on each heart beat. If it is an artifact, no processing is performed. If it is a non-artifact heart beat, ECG waveform segmentation is performed on each non-artifact heart beat to obtain the ECG waveform segmentation result for each non-artifact heart beat in the non-template type.

[0110] The ECG waveform segmentation in steps S302 and S303 above can be performed using traditional analysis methods or deep learning-based methods.

[0111] S304. Determine the ECG waveform feature points of each heartbeat based on the ECG waveform segmentation results of each heartbeat.

[0112] Specifically, the start, end, and peak points of the P wave, QRS complex, and T wave in the heartbeat are determined. Algorithms for determining ECG waveform feature points can include: processing through algorithms that search for local extrema and maximum values, while simultaneously combining the results of R wave localization with prior information such as the spatial positions of the P wave, QRS complex, and T wave. ECG waveform feature point detection can employ traditional algorithms or deep learning algorithms. For example... Figure 5 The image shows a schematic diagram of the detection results for ECG waveform feature points.

[0113] The key to calculating ECG waveform parameters lies in the detection of characteristic points of the ECG waveform, and the methods can be divided into:

[0114] 1. Feature point detection using the morphological characteristics of ECG waveforms; 2. Feature point detection using the basal unfolding method; 3. Fitting the ECG signal waveform model (such as the Gaussian model) to determine the positions of the P wave, T wave, and QRS complex based on the fitting results.

[0115] After locating the feature points of the electrocardiogram waveform, the electrocardiogram waveform parameters can be further calculated.

[0116] S305. Obtain the waveform parameters of the heartbeat based on the ECG waveform feature points.

[0117] The waveform parameters of a heartbeat can include the PR segment, ST segment, PR interval, QRS interval, QT interval, and can also include P wave width, T wave width, PP interval, RR interval, P wave amplitude, QRS amplitude, T wave amplitude, etc. For example... Figure 6 The image shown is one of the schematic diagrams of the waveform parameters of a heartbeat, as follows: Figure 7 The second diagram shows the waveform parameters of a heartbeat.

[0118] In this application, all heartbeats are categorized into template-based and non-template-based beats. For template-based beats, doctors only need to review the template to identify all beats within that template, eliminating most repetitive tasks. Doctors' primary diagnostic work involves non-template-based beats, which are typically the more complex and challenging beats they focus on. This analytical approach effectively improves doctors' analytical efficiency.

[0119] S103. The waveform parameters are superimposed on the heartbeat to be displayed on the target electrocardiogram.

[0120] Specifically, after obtaining the waveform parameters of the heartbeat, the waveform parameters are superimposed on the corresponding original heartbeat and displayed on the terminal interface to assist doctors in diagnosis.

[0121] In practical applications, template-based heart rate clips can be displayed in M ​​small windows according to the template for easy viewing by doctors. Non-template-based heart rate clips are displayed in separate small windows for easy differentiation.

[0122] The waveform parameters of the heartbeat can be selectively displayed by the doctor on the terminal interface. Selectable waveform parameters include the peak points and intervals of the P, QRS, and T waves. Other parameters are manually adjusted by the doctor during the diagnostic process to assist in ECG diagnosis. The display effect is as follows: Figure 6 and Figure 7 As shown.

[0123] The electrocardiogram (ECG) processing method provided in this application embodiment can quickly and accurately analyze ECG waveforms. When analyzing dynamic ECGs, doctors do not need to manually measure ECG waveform parameters, which shortens the doctor's analysis time. Therefore, the above method can reduce the workload of doctors.

[0124] In one possible implementation, the electrocardiogram processing method provided in this application may further include the step of: storing user-added correction annotations to the electrocardiogram scatter plot or the waveform parameters.

[0125] In practical applications, doctors make clinical diagnoses based on the ECG scatter plot, ECG waveform, marked P wave, QRS complex, T wave characteristic points, and ECG waveform parameters displayed on the terminal interface.

[0126] The ECG scatter plot, ECG waveform, marked P waves, QRS complexes, T wave feature points, and ECG waveform parameters displayed on the terminal interface can be selected by the doctor for display to facilitate diagnosis. During the diagnostic process, the doctor can reconfirm the displayed data and manually correct any inaccuracies in the ECG scatter plot segmentation or ECG waveform feature point detection by adding correction annotations. These correction annotations are recorded and saved. The data from these corrections can then be used to iterate the analysis algorithm used in the ECG waveform analysis. Therefore, this application, through the aforementioned correction feedback mechanism, can further improve the accuracy of ECG waveform analysis and better assist doctors in clinical diagnosis.

[0127] For ease of understanding, such as Figure 8 As shown, this application also provides a flowchart of a specific electrocardiogram processing method.

[0128] In the above embodiments, a method for processing an electrocardiogram (ECG) is provided. Correspondingly, this application also provides an ECG processing apparatus. The ECG processing apparatus provided in this application can implement the above-described ECG processing method. This ECG processing apparatus can be implemented through software, hardware, or a combination of both. For example, the ECG processing apparatus may include integrated or separate functional modules or units to perform the corresponding steps in the above methods. Please refer to... Figure 9 This illustration shows a schematic diagram of an electrocardiogram processing apparatus provided by some embodiments of this application. Since the apparatus embodiments are basically similar to the method embodiments, the description is relatively simple; relevant details can be found in the description of the method embodiments. The apparatus embodiments described below are merely illustrative.

[0129] like Figure 9 As shown, the electrocardiogram processing device 10 may include:

[0130] The drawing module 101 is used to draw an electrocardiogram scatter plot based on the target electrocardiogram.

[0131] Analysis module 102 is used to perform electrocardiogram waveform analysis on the heartbeats on the target electrocardiogram based on the electrocardiogram scatter plot, and obtain the waveform parameters of the heartbeats;

[0132] The visualization module 103 is used to superimpose the waveform parameters onto the heartbeat to display it on the target electrocardiogram.

[0133] In one possible implementation, in the apparatus provided in this application, the drawing module 101 is specifically used for:

[0134] Denoising the target electrocardiogram signal;

[0135] R-wave localization is performed on the target electrocardiogram after signal denoising to generate an RR interval sequence;

[0136] An electrocardiogram scatter plot was drawn based on the RR interval sequence.

[0137] In one possible implementation, in the apparatus provided in this application, the drawing module 101 is specifically used to: remove baseline drift and power frequency interference from the target electrocardiogram, and perform bandpass filtering on the target electrocardiogram to obtain a target electrocardiogram after signal denoising.

[0138] In one possible implementation, in the apparatus provided in this application, the analysis module 102 is specifically used for:

[0139] Based on the ECG scatter plot, all heartbeats on the target ECG are classified into template class or non-template class;

[0140] From each type of template, a heartbeat is determined as the heartbeat template for that type of template, and the electrocardiogram waveform is segmented for each heartbeat in that type of template according to the heartbeat template;

[0141] For each heartbeat in the non-template class, artifact identification is performed to obtain non-artifact heartbeats and artifact heartbeats, and electrocardiogram waveform segmentation is performed on each of the non-artifact heartbeats;

[0142] The ECG waveform feature points of each heartbeat are determined based on the ECG waveform segmentation results of each heartbeat.

[0143] The waveform parameters of the heartbeat are obtained based on the ECG waveform feature points.

[0144] In one possible implementation, in the apparatus provided in this application, the analysis module 102 is specifically used for:

[0145] The electrocardiogram scatter plot is segmented to obtain multiple corresponding segmented regions;

[0146] For each segmented region, the heartbeats corresponding to the scattered points in the segmented region are superimposed to generate a superimposed waveform diagram;

[0147] The superimposed waveform is decomposed, and N heartbeats are classified into one template according to morphological similarity, resulting in M ​​template classes, where N is greater than a preset threshold K.

[0148] The heartbeats corresponding to each segmented region on the electrocardiogram scatter plot are classified, and all heartbeats are classified into template class or non-template class.

[0149] In one possible implementation, in the apparatus provided in this application, the analysis module 102 is specifically used for:

[0150] The electrocardiogram waveform of the heartbeat template is segmented to obtain the template segmentation result;

[0151] Determine the offset between each heartbeat in the template corresponding to the heartbeat template and the heartbeat template;

[0152] Based on the coordinates of the heartbeat, the offset, and the template segmentation result, the ECG waveform segmentation result for each heartbeat in the template is determined.

[0153] In one possible implementation, in the apparatus provided in this application, the visualization module 103 is further configured to:

[0154] Store user-added corrections and annotations to the ECG scatter plot or the waveform parameters.

[0155] The electrocardiogram processing device 10 provided in this application embodiment is based on the same inventive concept as the electrocardiogram processing method provided in the foregoing embodiments of this application and has the same beneficial effects.

[0156] This application also provides a medical device corresponding to the electrocardiogram processing method provided in the foregoing embodiments, such as an auxiliary analysis device for medical use, to perform the above-described electrocardiogram processing method.

[0157] Please refer to Figure 10 This illustrates a schematic diagram of a medical device provided by some embodiments of this application. For example... Figure 10 As shown, the medical device 20 includes: a processor 200, a memory 201, a bus 202, and a communication interface 203. The processor 200, the communication interface 203, and the memory 201 are connected via the bus 202. The memory 201 stores a computer program that can run on the processor 200. When the processor 200 runs the computer program, it executes the electrocardiogram processing method provided in any of the foregoing embodiments of this application.

[0158] The memory 201 may include high-speed random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Communication between this system network element and at least one other network element is achieved through at least one communication interface 203 (which can be wired or wireless), such as the Internet, wide area network, local area network, or metropolitan area network.

[0159] Bus 202 can be an ISA bus, PCI bus, or EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. The memory 201 is used to store programs. After receiving an execution instruction, the processor 200 executes the program. The electrocardiogram processing method disclosed in any of the foregoing embodiments of this application can be applied to the processor 200, or implemented by the processor 200.

[0160] The processor 200 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of the processor 200 or by instructions in software form. The processor 200 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules may reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory 201. The processor 200 reads the information in memory 201 and, in conjunction with its hardware, completes the steps of the above method.

[0161] The medical device and the electrocardiogram processing method provided in this application are based on the same inventive concept and have the same beneficial effects as the methods they employ, operate, or implement.

[0162] This application also provides a computer-readable medium corresponding to the electrocardiogram processing method provided in the foregoing embodiments. Please refer to [link / reference]. Figure 11 The computer-readable storage medium shown is an optical disc 30, on which a computer program (i.e., a program product) is stored. When the computer program is run by a processor, it executes the electrocardiogram processing method provided in any of the foregoing embodiments.

[0163] It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical and magnetic storage media, which will not be elaborated here.

[0164] The computer-readable storage medium provided in the above embodiments of this application and the electrocardiogram processing method provided in the embodiments of this application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0165] It should be noted that the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0166] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0167] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some communication interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0168] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0169] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0170] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0171] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application, and they should all be covered within the scope of the claims and specification of this application.

Claims

1. A method for processing an electrocardiogram, characterized in that, include: Draw an electrocardiogram scatter plot based on the target electrocardiogram; Based on the electrocardiogram scatter plot, the heartbeats on the target electrocardiogram are analyzed to obtain the waveform parameters of the heartbeats; The waveform parameters are superimposed on the heartbeat to display on the target electrocardiogram; The step of performing electrocardiogram waveform analysis on the target electrocardiogram based on the electrocardiogram scatter plot to obtain the waveform parameters of the heartbeat includes: Based on the ECG scatter plot, all heartbeats on the target ECG are classified into template class or non-template class; From each type of template, a heartbeat is selected as the heartbeat template for that type of template. The heartbeat template is segmented into an electrocardiogram waveform to obtain the template segmentation result. The offset of each heartbeat in the template corresponding to the heartbeat template from the heartbeat template is determined. Based on the coordinates of the heartbeat, the offset, and the template segmentation result, the electrocardiogram waveform segmentation result of each heartbeat in the template is determined. For each heartbeat in the non-template class, artifact identification is performed to obtain non-artifact heartbeats and artifact heartbeats, and electrocardiogram waveform segmentation is performed on each of the non-artifact heartbeats; The ECG waveform feature points of each heartbeat are determined based on the ECG waveform segmentation results of each heartbeat. The waveform parameters of the heartbeat are obtained based on the ECG waveform feature points.

2. The method according to claim 1, characterized in that, The step of drawing an electrocardiogram scatter plot based on the target electrocardiogram includes: Denoising the target electrocardiogram signal; R-wave localization is performed on the target electrocardiogram after signal denoising to generate an RR interval sequence; An electrocardiogram scatter plot was drawn based on the RR interval sequence.

3. The method according to claim 2, characterized in that, The signal denoising of the target electrocardiogram includes: Baseline drift and power frequency interference in the target electrocardiogram are removed, and bandpass filtering is applied to the target electrocardiogram to obtain the target electrocardiogram after signal denoising.

4. The method according to claim 1, characterized in that, The step of classifying all heartbeats on the target electrocardiogram into template or non-template classes based on the electrocardiogram scatter plot includes: The electrocardiogram scatter plot is segmented to obtain multiple corresponding segmented regions; For each segmented region, the heartbeats corresponding to the scattered points in the segmented region are superimposed to generate a superimposed waveform diagram; The superimposed waveform is decomposed, and N heartbeats are classified into one template according to morphological similarity, resulting in M ​​template classes, where N is greater than a preset threshold K. The heartbeats corresponding to each segmented region on the electrocardiogram scatter plot are classified, and all heartbeats are classified into template class or non-template class.

5. The method according to claim 1, characterized in that, The method further includes: Store user-added corrections and annotations to the ECG scatter plot or the waveform parameters.

6. An electrocardiogram (ECG) processing device, characterized in that, include: The plotting module is used to draw an electrocardiogram scatter plot based on the target electrocardiogram. The analysis module is used to perform electrocardiogram waveform analysis on the heartbeats on the target electrocardiogram based on the electrocardiogram scatter plot, and obtain the waveform parameters of the heartbeats; A visualization module is used to overlay the waveform parameters onto the heartbeat to display it on the target electrocardiogram; The analysis module is specifically used for: Based on the ECG scatter plot, all heartbeats on the target ECG are classified into template class or non-template class; From each type of template, a heartbeat is determined as the heartbeat template for that type of template. The heartbeat template is then segmented using electrocardiogram waveforms to obtain the template segmentation result. Determine the offset between each heartbeat in the template corresponding to the heartbeat template and the heartbeat template; Based on the coordinates of the heartbeat, the offset, and the template segmentation result, the ECG waveform segmentation result for each heartbeat in the template is determined; For each heartbeat in the non-template class, artifact identification is performed to obtain non-artifact heartbeats and artifact heartbeats, and electrocardiogram waveform segmentation is performed on each of the non-artifact heartbeats; The ECG waveform feature points of each heartbeat are determined based on the ECG waveform segmentation results of each heartbeat. The waveform parameters of the heartbeat are obtained based on the ECG waveform feature points.

7. A medical device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the method as described in any one of claims 1 to 5.

8. A computer-readable medium, characterized in that, It stores computer-readable instructions that can be executed by a processor to implement the method as described in any one of claims 1 to 5.

Images