A method and device for analyzing a heart beat overlay, a medical device and a storage medium

Abstract

The application discloses a heart beat superposition graph analysis method and device, medical equipment and a storage medium. The method comprises the following steps: obtaining a heart beat superposition graph according to an electrocardiogram scatter diagram; obtaining a heart beat template based on the heart beat superposition graph; classifying heart beats in the heart beat superposition graph based on the difference degree of the heart beat template and each heart beat in the heart beat superposition graph, and obtaining multiple classifications; and displaying the heart beats belonging to the same classification in the heart beat superposition graph in the corresponding window, wherein one classification corresponds to one window. In this way, the user does not need to manually sort the heart beat superposition graph by experience, so that the user can intelligently and batch process during the analysis of the heart beat superposition graph, and the working efficiency of the user is effectively improved. Moreover, the machine automatically divides based on the difference degree of the heart beat template and each heart beat in the heart beat superposition graph, which can also improve the analysis accuracy and avoid the misjudgment and omission caused by manual division.

Description

Technical Field

[0001] This invention relates to the field of electrocardiogram signal analysis technology, specifically to a method, apparatus, medical device, and storage medium for analyzing cardiac beat overlay diagrams. Background Technology

[0002] In an electrocardiogram (ECG) analysis system, users can select a target area in an ECG scatter plot, and the heartbeat overlay plot of that target area can be automatically displayed using heartbeat overlay technology. Heartbeat overlay plots are generally used in a wide range of scenarios, such as artifact removal, batch processing of different types of heartbeats, and correction of heartbeat categories.

[0003] In related technologies, users need to operate manually, observe the heartbeat overlay image, select some heartbeats with large waveform differences in the heartbeat overlay image, and then move these heartbeats to a sub-window for specific analysis.

[0004] However, users need to analyze a large amount of dynamic electrocardiogram data in their work. This manual sorting of heartbeat overlays can bring a heavy workload to users and may lead to misjudgment or omission due to human negligence, which may delay the patient's condition. Summary of the Invention

[0005] The purpose of this invention is to address the shortcomings of the prior art by providing a method, apparatus, medical device, and storage medium for analyzing cardiac beat overlay diagrams. This purpose is achieved through the following technical solutions.

[0006] A first aspect of the present invention provides a method for analyzing heartbeat overlay diagrams, the method comprising:

[0007] Obtain a heartbeat overlay plot from the electrocardiogram scatter plot;

[0008] A heartbeat template is obtained based on the aforementioned heartbeat overlay image;

[0009] Based on the degree of difference between the heartbeat template and each heartbeat in the heartbeat overlay image, the heartbeats in the heartbeat overlay image are classified to obtain multiple classifications;

[0010] Heartbeats belonging to the same category in the heartbeat overlay image are moved to the corresponding window for display, with one window corresponding to one category.

[0011] A second aspect of the present invention provides an analysis apparatus for heartbeat overlay maps, the apparatus comprising:

[0012] The overlay plot acquisition module is used to acquire a cardiac overlay plot based on the electrocardiogram scatter plot;

[0013] The template acquisition module is used to obtain a heartbeat template based on the heartbeat overlay image;

[0014] The classification module is used to classify the heartbeats in the heartbeat overlay image based on the degree of difference between the heartbeat template and each heartbeat in the heartbeat overlay image, thereby obtaining multiple classifications.

[0015] The window display module is used to move heartbeats belonging to the same category in the heartbeat overlay image to the corresponding window for display, with one window corresponding to one category.

[0016] A third aspect of the present invention 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 executing the program, performs the steps of the method described in the first aspect above.

[0017] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in the first aspect above.

[0018] Based on the analysis method and apparatus for cardiac beat overlay diagrams described in the first and second aspects above, the present invention has at least the following beneficial effects or advantages:

[0019] After obtaining the heartbeat overlay image, the system acquires the heartbeat template from the overlay image and automatically classifies the heartbeats based on the degree of difference between the template and the overlay image. The classification results then automatically display each heartbeat in a different window, allowing for easy and intuitive viewing of dissimilar heartbeat waveforms. This eliminates the need for manual sorting of the overlay image based on user experience, enabling intelligent and batch operations during analysis and significantly improving user efficiency. Furthermore, the machine's automatic classification based on the degree of difference between the template and the overlay image enhances analysis accuracy, avoiding misjudgments and omissions caused by manual classification. Attached Figure Description

[0020] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this invention, illustrate exemplary embodiments of the invention and are used to explain the invention, but do not constitute an undue limitation of the invention. In the drawings:

[0021] Figure 1 This is a schematic diagram of manual sorting of heart rate superimposed images according to an exemplary embodiment of the present invention;

[0022] Figure 2 This is a flowchart illustrating an embodiment of the present invention, according to an exemplary embodiment, of a method for analyzing heartbeat overlay maps;

[0023] Figure 3 This is an electrocardiogram scatter plot according to an exemplary embodiment of the present invention;

[0024] Figure 4 This is a schematic diagram illustrating the region segmentation results of two types of electrocardiogram scatter plots according to an exemplary embodiment of the present invention.

[0025] Figure 5 This is a superimposed image of heartbeats corresponding to each segmented region of an electrocardiogram scatter plot according to an exemplary embodiment of the present invention.

[0026] Figure 6 This is a display window diagram of the sorted heart rate overlay image according to an exemplary embodiment of the present invention;

[0027] Figure 7 This is a schematic diagram illustrating a process for correcting heart rate categories in a heart rate overlay image according to an exemplary embodiment of the present invention;

[0028] Figure 8 This is a schematic diagram illustrating the structure of a deep learning model according to an exemplary embodiment of the present invention;

[0029] Figure 9 This is a schematic diagram illustrating the display of heartbeats in a heartbeat overlay image according to an exemplary embodiment of the present invention;

[0030] Figure 10 This is a schematic diagram of the structure of a cardiac beat overlay analysis device according to an exemplary embodiment of the present invention;

[0031] Figure 11 This is a schematic diagram of the hardware structure of a medical device according to an exemplary embodiment of the present invention;

[0032] Figure 12 This is a schematic diagram illustrating the structure of a storage medium according to an exemplary embodiment of the present invention. Detailed Implementation

[0033] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the invention as detailed in the appended claims.

[0034] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The singular forms “a,” “the,” and “the” used in this invention and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0035] It should be understood that although the terms first, second, third, etc., may be used in this invention to describe various information, this information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, first information may also be referred to as second information without departing from the scope of this invention, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to a determination."

[0036] The data used to plot the ECG scatter plot comes from the RR interval information of dynamic ECG data. The continuous RR intervals represent the heart rhythm, which is an important manifestation of the dynamic changes in the human body over time. When analyzing the ECG scatter plot, users need to select some specific areas on the ECG scatter plot to overlay multiple heartbeat waveforms in that area to obtain a heartbeat overlay plot. When sorting the heartbeat overlay plot, the heartbeats with large differences in the heartbeat overlay plot are circled and moved to a sub-window for further analysis.

[0037] like Figure 1 As shown, the heartbeat waveforms in the upper left corner of Figure (1a) have relatively large differences. By circling these heartbeat waveforms with relatively large differences (white circles), these heartbeat waveforms are moved to the sub-window Figure (1b) for display.

[0038] However, since users need to analyze a large amount of dynamic electrocardiogram data in their work, this method of manually sorting the heartbeat overlay images will bring a heavy workload to users, and may lead to misjudgment or omission due to human negligence, which may delay the patient's condition.

[0039] To address the aforementioned technical issues, this application proposes an analysis method for heartbeat overlay maps. This method involves obtaining a heartbeat overlay map based on an electrocardiogram scatter plot, acquiring a heartbeat template based on the overlay map, and then classifying the heartbeats in the overlay map based on the degree of difference between the heartbeat template and each heartbeat in the overlay map. This results in multiple classifications, and heartbeats belonging to the same classification in the overlay map are moved to the corresponding window for display, with one window corresponding to one classification.

[0040] The technical effects that can be achieved based on the above description are:

[0041] By acquiring the heartbeat template from the heartbeat overlay image and automatically classifying the heartbeats based on the degree of difference between the template and the overlay image, the system automatically displays each heartbeat in a different window based on the classification results. This allows for easy and intuitive viewing of dissimilar heartbeat waveforms, eliminating the need for manual sorting based on user experience. This intelligent and batch operation significantly improves user efficiency during heartbeat overlay image analysis. Furthermore, the machine's automatic classification based on the degree of difference between the template and the overlay image enhances analysis accuracy, avoiding misjudgments and omissions caused by manual classification.

[0042] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0043] Example 1:

[0044] Figure 2 This is a flowchart illustrating an embodiment of a method for analyzing a cardiac overlay graph according to an exemplary embodiment of the present invention. The method for analyzing the cardiac overlay graph includes the following steps:

[0045] Step 201: Obtain the heartbeat overlay plot based on the electrocardiogram scatter plot.

[0046] Before performing step 201, the process of drawing the ECG scatter plot involves detecting the QRS complex in the dynamic ECG data to obtain the R wave position of each heartbeat. Then, based on the R wave position of each heartbeat, a continuous RR interval sequence is obtained, and a two-dimensional rectangular coordinate system is established. Starting from the first RR interval, the system iterates through the data, using the currently iterated RR interval as the x-axis and the next RR interval as the y-axis, and so on, to obtain a large number of coordinate points, i.e., scatter plots. These scatter plots are then superimposed to form a scatter plot. Figure 3 The electrocardiogram scatter plot shown.

[0047] Among them, the electrocardiogram scatter plot reflects the relationship of RR intervals and their changing patterns. Different types of arrhythmias have different types of RR interval relationships and their changing patterns, which can be represented by characteristic scatter plot graphs.

[0048] It should be noted that after obtaining the ECG scatter plot, deep learning algorithms can be used to classify arrhythmias based on the ECG scatter plot, obtain the arrhythmia category, and then output the arrhythmia category as a preliminary analysis result for user reference.

[0049] Among them, the classification of arrhythmias based on electrocardiogram scatter plots is a qualitative analysis of the entire scatter plot, which can provide a preliminary analysis result.

[0050] For example, the classification results of deep learning algorithms may include normal sinus rhythm, premature ventricular contractions, premature supraventricular contractions, ventricular / supraventricular bigeminy and trigeminy, ventricular / supraventricular tachycardia, atrioventricular block, junctional escape beats and escape rhythms, atrial fibrillation, atrial flutter, etc.

[0051] Regarding the process of obtaining the heart rate overlay map in step 101, in one possible implementation, the ECG scatter plot can be divided into regions, and then for each region obtained by the division, a heart rate overlay map of that region can be generated based on the scatter data contained in that region.

[0052] Different types of electrocardiogram scatter plots segment different regions. For example, ... Figure 4 As shown in (4a), for the electrocardiogram scatter plots of ventricular premature beats and supraventricular premature beats, three regions can be segmented: the interference region, the premature beat region, and the sinus rhythm region. For example, as... Figure 4 As shown in (4b), for an electrocardiogram of atrial fibrillation type, two regions can be divided: the atrial fibrillation region and the interference region.

[0053] Therefore, the region segmentation of an ECG scatter plot is related to the type of ECG scatter plot. Based on the preliminary analysis results of the ECG scatter plot, region segmentation can be performed. Furthermore, a deep learning model can be used for region segmentation. Specifically, the deep learning model can be trained using ECG scatter plots with type labels.

[0054] After segmenting the scatter plot of the electrocardiogram into regions, a heartbeat overlay plot for each region can be generated based on the scatter data in each region. The x and y coordinates of each scatter point are represented by two adjacent RR intervals, thus allowing the corresponding heartbeat to be obtained from the adjacent RR intervals. These heartbeats can then be overlaid to create the heartbeat overlay plot.

[0055] like Figure 5 As shown, Figure (5a) is a superimposed image of heartbeats corresponding to the premature beat area in the electrocardiogram scatter plot, Figure (5b) is a superimposed image of heartbeats corresponding to the sinus rhythm area in the electrocardiogram scatter plot, and Figure (5c) is a superimposed image of heartbeats corresponding to the interference area in the electrocardiogram scatter plot.

[0056] It should be noted that since a heart rate overlay image can be obtained for each segmented region, each heart rate overlay image can be analyzed separately in subsequent processes, allowing the heart rate categories in each overlay image to be displayed in different windows. Alternatively, depending on the specific needs, the heart rate overlay image of only one region can be selected for analysis.

[0057] Step 202: Obtain the heartbeat template based on the heartbeat overlay image.

[0058] Among them, the heartbeat template serves as a standard template. Since the heartbeat template is obtained from the heartbeat overlay image, each heartbeat overlay image corresponds to its own heartbeat template, which can provide a more accurate standard reference for the heartbeat overlay image.

[0059] In one possible implementation of obtaining the heartbeat template, a target region in the heartbeat overlay image is determined, which is a region with high heartbeat overlap. Then, along the direction of heartbeat amplitude, the median line between two relative boundaries on the target region is selected as the heartbeat template.

[0060] In other words, see Figure 5 The heart rate overlay diagrams shown in (5a), (5b), and (5c) have the vertical axis representing the direction of heart rate amplitude, and the dark gray area in the middle of each diagram represents the area with high overlap. The value of the heart rate template is the median of the vertical coordinates of the upper and lower boundaries of the area.

[0061] Those skilled in the art will understand that the determination of the target region in the cardiac beat overlay image can be achieved using relevant technologies, and this application does not impose any specific limitations on this.

[0062] Step 203: Based on the degree of difference between the heartbeat template and each heartbeat in the heartbeat overlay image, classify the heartbeats in the heartbeat overlay image to obtain multiple classifications.

[0063] Since users analyze heartbeats by observing the abnormal heartbeats mixed in, this solution classifies heartbeats based on the degree of difference between the heartbeats and the standard heartbeat template, and displays the classification results for users' reference.

[0064] In one possible implementation, the difference level of each heartbeat relative to the heartbeat template in the heartbeat overlay image is determined, and heartbeats with the same difference level are classified into a category. This method of calculating the heartbeat difference level is simple to implement and has high analysis efficiency.

[0065] In other words, heartbeats belonging to a certain degree of difference should be classified into a category.

[0066] In an optional embodiment, the process for determining the degree of difference of a heartbeat involves determining the similarity between the heartbeat and the heartbeat template for each heartbeat, and determining the degree of difference of the heartbeat relative to the heartbeat template based on the similarity.

[0067] In practice, firstly, the Pearson coefficient between the time series data of the heartbeat and the time series data of the heartbeat template is used, and this Pearson coefficient is used as the similarity.

[0068] Since both the heartbeat template and each heartbeat belong to time series, the Pearson coefficient can be used as a similarity measure based on correlation between time series. The formula for calculating the Pearson coefficient is as follows:

[0069]

[0070] In the above formula, X T and Y T These are the cardiac template and the time series of the heartbeat, respectively. t and y t These represent the values ​​of the two time series at different times. and These are the means of the two time series, respectively.

[0071] It is worth noting that when the Pearson coefficient is 1, it means that the heartbeat is completely consistent with the heartbeat template, and when the Pearson coefficient is 0, it means that the heartbeat is very weakly correlated with the heartbeat template or has no correlation.

[0072] Then, the similarity is compared with multiple preset ranges, and the level corresponding to the range to which the similarity belongs is determined as the difference level of the heartbeat relative to the heartbeat template.

[0073] Specifically, four ranges are set, each corresponding to a difference level, with levels 1-4: Level 1 indicates virtually no difference, Level 2 indicates low difference, Level 3 indicates moderate difference, and Level 4 indicates high difference. That is, if the similarity is between 0.8 and 1, the difference level of the heartbeat relative to the heartbeat template is determined to be 1; if the similarity is between 0.6 and 0.8, the difference level of the heartbeat relative to the heartbeat template is determined to be 2; if the similarity is between 0.4 and 0.6, the difference level of the heartbeat relative to the heartbeat template is determined to be 3; and if the similarity is between 0 and 0.4, the difference level of the heartbeat relative to the heartbeat template is determined to be 4.

[0074] Therefore, the higher the similarity, the lower the corresponding level of difference.

[0075] Step 204: Move the heartbeats belonging to the same category in the heartbeat overlay image to the corresponding window for display, with one window corresponding to one category.

[0076] See Figure 6 As shown, this is the above. Figure 5The sorting results of the cardiac beat overlay images (5a) in the premature beat zone are shown in Figure (6a), where Figure (6b) is the cardiac beat overlay display window 1 with a difference level of basically no difference, Figure (6c) is the cardiac beat overlay display window 2 with a difference level of low difference, Figure (6d) is the cardiac beat overlay display window 3 with a difference level of moderate difference, and Figure (6d) is the cardiac beat overlay display window 4 with a difference level of high difference.

[0077] It should be noted that if users want to make manual modifications, they can do so directly on the window, for example, moving part of the heartbeat from window 1 to window 2.

[0078] This completes the above. Figure 2 The analysis process shown involves obtaining a heartbeat overlay image, acquiring a heartbeat template from the overlay image, and automatically classifying the heartbeats based on the degree of difference between the template and the overlay image. The classification results then automatically display each heartbeat in a different window, allowing for easy and intuitive viewing of dissimilar heartbeat waveforms. This eliminates the need for manual sorting of the overlay image based on user experience, enabling intelligent and batch operations during analysis and significantly improving user efficiency. Furthermore, the automatic classification based on the degree of difference between the template and the overlay image enhances accuracy and avoids misjudgments and omissions caused by manual classification.

[0079] After the automatic analysis of the heartbeat overlay is completed, in the existing technology, users usually check each heartbeat in each window and correct the misclassified heartbeats to the correct category, and finally generate an accurate dynamic electrocardiogram report. However, checking each heartbeat one by one will bring a lot of workload to the user.

[0080] Example 2:

[0081] Figure 7 This is a schematic diagram illustrating the correction process for heart rate categories in a heart rate overlay image according to an exemplary embodiment of the present invention. Based on the solution described in the above embodiment, this embodiment aims to better assist users in analysis by automatically correcting the heart rate categories in the heart rate overlay image. The correction process includes the following steps:

[0082] Step 701: Obtain the initial heartbeat category for each heartbeat in the heartbeat overlay image.

[0083] The initial heartbeat category is obtained during the generation of the electrocardiogram scatter plot based on the QRS wave morphology and RR interval changes.

[0084] In the embodiments of this application, heartbeats are classified into five categories: normal heartbeat (N), supraventricular heartbeat (S), ventricular heartbeat (V), artifact (X), and others (O).

[0085] Step 702: For each heartbeat, use a deep learning algorithm to predict the heartbeat category based on the time series data of the heartbeat, and compare the predicted heartbeat category with the initial heartbeat category. If they do not match, proceed to step 703; if they match, proceed to step 704.

[0086] One heartbeat is one cardiac cycle. The electrocardiogram (ECG) signal values ​​collected within this cardiac cycle are composed of time series data. This time series data can well reflect the situation of this heartbeat. Therefore, by using the time-domain signal morphology of the heartbeat as input to a deep learning model, the heartbeat category can be accurately predicted after model inference.

[0087] See Figure 8 The deep learning model structure shown can be used to extract and fit high-dimensional features of electrocardiogram signals through nonlinear transformations of neural network layers, thereby achieving more accurate classification of heartbeats.

[0088] Furthermore, by comparing the predicted heartbeat category with the initial heartbeat category, if the comparison is inconsistent, it indicates that the heartbeat category needs to be corrected; if the comparison is consistent, it indicates that the heartbeat category does not need to be corrected.

[0089] Step 703: Add a label to the heartbeat and determine the predicted heartbeat category as the actual heartbeat category.

[0090] In cases of inconsistency, the predicted heartbeat category is corrected to the true heartbeat category; that is, the initial heartbeat category is now considered incorrect. A marker is added to the corrected heartbeat category for easy user review.

[0091] Step 704: Determine the initial heartbeat category as the true heartbeat category for that heartbeat.

[0092] When the comparison is consistent, no correction is needed; the initial heartbeat category is used directly as the true heartbeat category.

[0093] It should be noted that after the correction of the heartbeat category in the heartbeat overlay is completed, the output displays the waveform of each heartbeat and the actual heartbeat category in the heartbeat overlay. The background color of the waveform of the heartbeat with the added mark is different from the background color of the waveform of the heartbeat without the added mark, so that users can see at a glance which heartbeat categories have been corrected and can review the corrected heartbeat categories.

[0094] See Figure 9As shown, among the 21 heartbeat waveforms displayed, those with a dark background are heartbeats whose heartbeat categories have been corrected, so users only need to verify the automatically labeled heartbeat categories.

[0095] It is worth noting that, Figure 9 The heart rate category for each heartbeat is hidden; when the mouse hovers over a heartbeat, the corresponding heart rate category is displayed.

[0096] This completes the above. Figure 7 The heartbeat category correction process shown uses a deep learning algorithm to predict the heartbeat category based on the time-domain signal morphology of each heartbeat. Since the neural network model can automatically extract and fit the high-dimensional features of the electrocardiogram signal, it can achieve more accurate heartbeat classification. Furthermore, when the predicted heartbeat category is inconsistent with the initial heartbeat category, in addition to taking the predicted heartbeat category as the true category of the heartbeat, a label is added to the heartbeat to facilitate user review and verification.

[0097] Corresponding to the aforementioned embodiments of the cardiac beat overlay analysis method, the present invention also provides embodiments of the cardiac beat overlay analysis apparatus.

[0098] Figure 10 This is a schematic diagram of a cardiac beat overlay analysis device according to an exemplary embodiment of the present invention. The device is used to perform the cardiac beat overlay analysis method provided in any of the above embodiments, such as... Figure 10 As shown, the analysis device for the heartbeat overlay diagram includes:

[0099] The overlay plot acquisition module 1010 is used to acquire a cardiac overlay plot based on the electrocardiogram scatter plot;

[0100] Template acquisition module 1020 is used to obtain a heartbeat template based on the heartbeat overlay image;

[0101] The classification module 1030 is used to classify the heartbeats in the heartbeat overlay image based on the degree of difference between the heartbeat template and each heartbeat in the heartbeat overlay image, thereby obtaining multiple classifications.

[0102] The window display module 1040 is used to move heartbeats belonging to the same category in the heartbeat overlay image to the corresponding window for display, with one window corresponding to one category.

[0103] In an optional implementation, the template acquisition module 1020 is specifically used to determine the target region in the heartbeat overlay image, the target region being a region with high heartbeat overlap; and to select the median line between two relative boundaries on the target region as the heartbeat template along the heartbeat amplitude direction.

[0104] In an optional implementation, the classification module 1030 is specifically used to determine the degree of difference of each heartbeat in the heartbeat overlay image relative to the heartbeat template; and to classify heartbeats with the same degree of difference into one category.

[0105] In an optional implementation, the classification module 1030 is specifically used to determine the similarity between each heartbeat in the heartbeat overlay image and the heartbeat template during the process of determining the degree of difference between each heartbeat and the heartbeat template in the heartbeat overlay image; and to determine the degree of difference between the heartbeat and the heartbeat template based on the similarity.

[0106] In an optional implementation, the classification module 1030 is specifically used to determine the Pearson coefficient between the time series data of the heartbeat and the time series data of the heartbeat template during the process of determining the similarity between the heartbeat and the heartbeat template; and to determine the Pearson coefficient as the similarity.

[0107] In an optional implementation, the classification module 1030 is specifically used to compare the similarity with a preset number of ranges during the process of determining the difference level of the heartbeat relative to the heartbeat template based on the similarity; and to determine the level corresponding to the range to which the similarity belongs as the difference level of the heartbeat relative to the heartbeat template; wherein, the higher the similarity, the lower the corresponding difference level.

[0108] In an optional implementation, the overlay image acquisition module 1010 is specifically used to segment the electrocardiogram scatter plot into regions; for each segmented region, a cardiac overlay image of the region is generated based on the scatter data contained in the region.

[0109] In an alternative implementation, the apparatus further includes ( Figure 10 (Not shown in the image):

[0110] The correction module is used to obtain the initial heartbeat category of each heartbeat in the heartbeat overlay map after obtaining the heartbeat overlay map based on the electrocardiogram scatter plot; for each heartbeat, a deep learning algorithm is used to predict the heartbeat category of the heartbeat based on the time series data of the heartbeat, and the predicted heartbeat category is compared with the initial heartbeat category of the heartbeat; if they are inconsistent, a label is added to the heartbeat, and the predicted heartbeat category is determined as the true heartbeat category of the heartbeat; if they are consistent, the initial heartbeat category is determined as the true heartbeat category of the heartbeat.

[0111] In an alternative implementation, the apparatus further includes ( Figure 10 (Not shown in the image):

[0112] The display module is used to output and display the waveforms and actual heartbeat categories of each heartbeat in the heartbeat overlay graph; wherein, the background color of the waveform of the heartbeat with added markings is different from the background color of the waveform of the heartbeat without added markings.

[0113] In an alternative implementation, the apparatus further includes ( Figure 10 (Not shown in the image):

[0114] The preliminary classification module is used to classify arrhythmias based on the electrocardiogram scatter plot using a deep learning algorithm to obtain arrhythmia categories; the arrhythmia categories are then output and displayed as preliminary analysis results.

[0115] The specific implementation process of the functions and roles of each unit in the above device can be found in the implementation process of the corresponding steps in the above method, and will not be repeated here.

[0116] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and 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 modules can be selected to achieve the purpose of the present invention according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0117] The present invention also provides a medical device corresponding to the cardiac overlay graph analysis method provided in the foregoing embodiments, for performing the cardiac overlay graph analysis method described above.

[0118] Figure 11 This is a hardware structure diagram of a medical device according to an exemplary embodiment of the present invention. The medical device includes: a communication interface 601, a processor 602, a memory 603, and a bus 604; wherein the communication interface 601, the processor 602, and the memory 603 communicate with each other through the bus 604. The processor 602 can execute the heartbeat overlay analysis method described above by reading and executing machine-executable instructions corresponding to the control logic of the heartbeat overlay analysis method in the memory 603. The specific content of the method is described in the above embodiment and will not be repeated here.

[0119] The memory 603 mentioned in this invention can be any electronic, magnetic, optical, or other physical storage device, and can contain stored information such as executable instructions, data, etc. Specifically, the memory 603 can be RAM (Random Access Memory), flash memory, storage drive (such as hard disk drive), any type of storage disk (such as optical disc, DVD, etc.), or similar storage media, or combinations thereof. Communication between this system network element and at least one other network element is achieved through at least one communication interface 601 (which can be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc., can be used.

[0120] Bus 604 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 603 is used to store programs, and the processor 602 executes the programs after receiving execution instructions.

[0121] Processor 602 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 processor 602 or by instructions in software form. The processor 602 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), an On-Premises 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 can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor.

[0122] The medical device and the cardiac beat overlay analysis 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.

[0123] This application also provides a computer-readable storage medium corresponding to the heartbeat overlay analysis method provided in the foregoing embodiments. Please refer to [reference needed]. Figure 12 As shown, the computer-readable storage medium 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 heartbeat overlay analysis method provided in any of the foregoing embodiments.

[0124] 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.

[0125] The computer-readable storage medium provided in the above embodiments of this application and the heartbeat overlay analysis 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.

[0126] Other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of the invention are indicated by the following claims.

[0127] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0128] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for analyzing heartbeat overlay diagrams, characterized in that, The method includes: Obtain a heartbeat overlay plot from the electrocardiogram scatter plot; A heartbeat template is obtained based on the aforementioned heartbeat overlay image; Based on the degree of difference between the heartbeat template and each heartbeat in the heartbeat overlay image, the heartbeats in the heartbeat overlay image are classified to obtain multiple classifications; Heartbeats belonging to the same category in the overlay image are moved to the corresponding window for display, with one window corresponding to one category; The step of obtaining the heartbeat template based on the heartbeat overlay image includes: Determine the target region in the heartbeat overlay image, where the target region is the area with high heartbeat overlap; Along the direction of heartbeat amplitude, the median line between two relative boundaries on the target region is selected as the heartbeat template.

2. The method according to claim 1, characterized in that, The classification of heartbeats in the overlay image based on the degree of difference between the heartbeat template and each heartbeat in the overlay image includes: Determine the degree of difference of each heartbeat in the heartbeat overlay image relative to the heartbeat template; Heartbeats with the same degree of difference are grouped into one category.

3. The method according to claim 2, characterized in that, Determining the degree of difference of each heartbeat in the heartbeat overlay image relative to the heartbeat template includes: For each heartbeat in the heartbeat overlay image, determine the similarity between the heartbeat and the heartbeat template; The degree of difference between the heartbeat and the heartbeat template is determined based on the similarity.

4. The method according to claim 3, characterized in that, Determining the similarity between the heartbeat and the heartbeat template includes: Determine the Pearson coefficient between the time series data of the heartbeat and the time series data of the heartbeat template; The Pearson coefficient is determined as the similarity.

5. The method according to claim 3, characterized in that, Determining the difference level of the heartbeat relative to the heartbeat template based on the similarity includes: The similarity is compared with a preset range; The level corresponding to the range to which the similarity belongs is determined as the difference level of the heartbeat relative to the heartbeat template; The higher the similarity, the lower the corresponding level of difference.

6. The method according to claim 1, characterized in that, The step of obtaining the heartbeat overlay map based on the electrocardiogram scatter plot includes: The electrocardiogram scatter plot is divided into regions; For each segmented region, a heart rate overlay map of that region is generated based on the scatter data contained within that region.

7. The method according to claim 1, characterized in that, After obtaining the heartbeat overlay map from the electrocardiogram scatter plot, the method further includes: Obtain the initial heartbeat category for each heartbeat in the heartbeat overlay image; For each heartbeat, a deep learning algorithm is used to predict the heartbeat category based on the time series data of the heartbeat, and the predicted heartbeat category is compared with the initial heartbeat category of the heartbeat; If there is a discrepancy, a label is added to the heartbeat, and the predicted heartbeat category is determined as the true heartbeat category. If they match, the initial heartbeat category is determined as the true heartbeat category of the heartbeat.

8. The method according to claim 7, characterized in that, The method further includes: The output displays the waveforms and actual heartbeat categories of each heartbeat in the heartbeat overlay image; The background color of the heartbeat waveform with added markers is different from that of the heartbeat waveform without added markers.

9. The method according to claim 1, characterized in that, The method further includes: A deep learning algorithm was used to classify arrhythmias based on the electrocardiogram scatter plot to obtain the arrhythmia category. The arrhythmia categories are used as preliminary analysis results and output for display.

10. An analytical device for cardiac beat overlay diagrams, characterized in that, The device includes: The overlay plot acquisition module is used to acquire a cardiac overlay plot based on the electrocardiogram scatter plot; The template acquisition module is used to obtain a heartbeat template based on the heartbeat overlay image; The classification module is used to classify the heartbeats in the heartbeat overlay image based on the degree of difference between the heartbeat template and each heartbeat in the heartbeat overlay image, thereby obtaining multiple classifications. The window display module is used to move heartbeats belonging to the same category in the heartbeat overlay image to the corresponding window for display, with one window corresponding to one category; The template acquisition module is specifically used to determine the target region in the heartbeat overlay image, the target region being a region with high heartbeat overlap; along the heartbeat amplitude direction, the median line between two relative boundaries on the target region is selected as the heartbeat template.

11. A medical device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the method as described in any one of claims 1-9.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by a processor, it implements the steps of the method as described in any one of claims 1-9.

Images