Analysis method and system of magnetocardiogram, storage medium and electronic equipment

Abstract

The invention provides a magnetocardiogram analysis method and system, a storage medium and electronic equipment. The method comprises the steps that a magnetocardiogram data set of a magnetocardiogram to be analyzed is acquired; drawing a time wave group diagram and a space wave group diagram for each magnetocardiogram signal in the magnetocardiogram data set; based on the time wave group diagram and the space wave group diagram of the magnetocardiogram signal, the waveform type of the magnetocardiogram signal in each wave band is judged; based on the waveform type of each magnetocardiogram signal in each wave band in the magnetocardiogram data set, calculating waveform distribution parameters of each magnetocardiogram signal in each wave band; based on the waveform distribution parameters of each magnetocardiogram signal in each wave band, the matching degree of each magnetocardiogram signal and a target magnetocardiogram is judged, and an analysis result of each magnetocardiogram signal in the magnetocardiogram data set is obtained. According to the method, the electrical activity characteristics of the heart behind different waveform distributions are effectively described, and the time and space distribution rules of the magnetocardiogram signals are effectively represented.

Description

Technical Field

[0001] The present invention belongs to the technical field of data processing, and in particular relates to a magnetocardiogram analysis method, system, storage medium and electronic equipment. Background Art

[0002] Magnetocardiography is a non-invasive detection method that collects and analyzes changes in the surrounding magnetic field caused by cardiac excitement. It captures the weak magnetic field signals generated by cardiac electrical activity through magnetic sensors such as superconducting quantum interferometers, and can provide richer spatial and temporal resolution information than traditional electrocardiograms. It has unique advantages in detecting myocardial ischemia, arrhythmias and fetal heart abnormalities.

[0003] Current research on magnetocardiography (MCG) mainly focuses on some single waveform features, such as R-wave amplitude, T-wave integral, waveform factor, fluctuation index, etc., and uses machine learning or deep learning algorithms to model, analyze and predict waveform features. However, the analysis and prediction of these single waveform features limits the ability to compare and analyze MG with cardiac electrophysiological activity. Summary of the Invention

[0004] The present invention provides a magnetocardiogram analysis method, system, storage medium and electronic equipment, which are used to solve the problem in the prior art of how to improve the comparative analysis capability of the magnetocardiogram and cardiac electrophysiological activity.

[0005] In a first aspect, the present invention provides a magnetocardiogram analysis method, comprising: obtaining a magnetocardiogram dataset of a magnetocardiogram to be analyzed; drawing a time wave group diagram and a space wave group diagram for each magnetocardiogram signal in the magnetocardiogram dataset; judging the waveform type of the magnetocardiogram signal in each band based on the time wave group diagram and the space wave group diagram of the magnetocardiogram signal; calculating the waveform distribution parameters of each magnetocardiogram signal in each band based on the waveform type of each magnetocardiogram signal in each band in the magnetocardiogram dataset; judging the degree of match between each magnetocardiogram signal and a target magnetocardiogram waveform diagram based on the waveform distribution parameters of each magnetocardiogram signal in each band, and obtaining an analysis result for each magnetocardiogram signal in the magnetocardiogram dataset.

[0006] In an implementation of the first aspect, based on the time wave group diagram and the space wave group diagram of the magnetocardiographic signal, determining the waveform type of the magnetocardiographic signal in each band includes: determining the waveform type of the T wave band of the magnetocardiographic signal, including: connecting the tail after the T wave and the head before the P wave in the time wave group diagram to obtain the TP wave band of the corresponding magnetocardiographic signal; subtracting the signal average value of the corresponding TP wave band from each single signal wave in the space wave group diagram to obtain the per-channel signal after TP baseline fine-tuning; extracting the maximum positive wave and the maximum negative wave from the per-channel signal after TP baseline fine-tuning; when the maximum positive wave meets the first condition, it is a reliable positive wave, and when The maximum negative wave is a reliable negative wave when it meets the second condition; the waveform type of the T wave band of each channel is determined according to the number and order of reliable positive waves and reliable negative waves in each channel signal after fine-tuning the TP baseline; wherein, the waveform types of the T wave band include upright, low and flat, positive and negative, negative and positive, and inverted; the waveform type corresponding to a single reliable positive wave is upright, the waveform type corresponding to no reliable positive wave and a reliable negative wave is low and flat, the waveform type corresponding to the first reliable positive wave and the second reliable negative wave is positive and negative, the waveform type corresponding to the first reliable negative wave and the second reliable positive wave is negative and positive, and the waveform type corresponding to a single reliable negative wave is inverted.

[0007] In an implementation of the first aspect, based on the time wave group diagram and the space wave group diagram of the cardiomagnetic signal, determining the waveform type of the cardiomagnetic signal in each band includes: determining the waveform type of the QRS band of the cardiomagnetic signal, including: connecting the tail after the T wave and the head before the P wave in the time wave group diagram to obtain the TP band of the corresponding cardiomagnetic signal; subtracting the signal average value of the corresponding TP band from each single signal wave in the space wave group diagram to obtain the signal of each channel after the TP baseline is fine-tuned; obtaining the QRS band and QRS of each channel signal after the TP baseline is fine-tuned. Bands of preset lengths before and after the band are taken as candidate bands, all peaks and troughs in the candidate bands are counted as candidate points, and the ratio of each candidate point to the maximum amplitude of the QRS band is calculated; the candidate point with a ratio value greater than the preset value is taken as an alternative wave; the candidate wave is threshold filtered to obtain a reliable wave; the waveform type of the QRS band is determined according to the number and positive and negative directions of the reliable waves; wherein the waveform types of the QRS band include R, RR, qR, QR, Qr, Rs, RS, rS, Q, QQ, QRS and QRSs.

[0008] In an implementation of the first aspect, filtering the alternative waves to obtain reliable waves includes: sorting the alternative waves from large to small according to the proportional values; directly adding the alternative wave with the largest proportional value as the reliable wave; judging in order from large to small according to the proportional values ​​whether the corresponding sorted alternative waves are added as reliable waves, including: when the corresponding sorted alternative wave is greater than the corresponding preset sorting threshold, adding the corresponding sorted alternative wave as the reliable wave, otherwise not adding it; when two adjacent corresponding sorted alternative waves are in the same direction and the proportional values ​​are both less than the noise threshold, judging whether the corresponding sorted alternative waves are added as reliable waves. If the two adjacent correspondingly sorted alternative waves are noise, they will not be added, and the subsequent sorted alternative waves on the same side will not be added; when the two adjacent correspondingly sorted non-noise alternative waves are in the same direction and the ratio value is less than the threshold value, the two adjacent correspondingly sorted non-noise alternative waves are determined to be notches and merged into one wave and then added as a reliable wave; each time the current alternative wave is determined to be added as a reliable wave, if there is an alternative wave between the current alternative wave and the existing reliable wave, all alternative waves between the current alternative wave and the existing reliable wave are automatically added as reliable waves, excluding noise.

[0009] In an implementation of the first aspect, determining the waveform type of the magnetocardiographic signal in each band based on the time wave group diagram and the space wave group diagram of the magnetocardiographic signal includes: determining the waveform type of the ST band of the magnetocardiographic signal, including: connecting the tail after the T wave and the head before the P wave in the time wave group diagram to obtain the TP band of the corresponding magnetocardiographic signal; subtracting the signal average value of the corresponding TP band from each single signal wave in the space wave group diagram to obtain a per-channel signal after fine-tuning the TP baseline; calculating the positive-to-negative amplitude ratio of the ST band based on the per-channel signal after fine-tuning the TP baseline; if the positive-to-negative amplitude ratio is greater than or equal to a first threshold and less than or equal to a second threshold, it is within a normal range, and the waveform type of the corresponding ST band is non-elevation or depression; if the positive-to-negative amplitude ratio is less than the first threshold, the waveform type of the corresponding ST band is depression; if the positive-to-negative amplitude ratio is greater than the second threshold, the waveform type of the corresponding ST band is elevation.

[0010] In an implementation of the first aspect, based on the waveform type of each magnetocardiographic signal in each band in a magnetocardiographic data set, calculating the waveform distribution parameter of each magnetocardiographic signal in each band includes: counting the distribution ratio of the waveform type in each band of the magnetocardiographic signal corresponding to each acquisition channel in the magnetocardiographic data set; and merging the corresponding distribution ratio information of acquisition channels with a higher distribution ratio and the same waveform type as the distribution parameter of the corresponding waveform type of each magnetocardiographic signal, i.e., the waveform distribution parameter.

[0011] In an implementation of the first aspect, based on the waveform distribution parameters of each magnetocardiographic signal in each band, determining the matching degree of each magnetocardiographic signal with the target magnetocardiographic waveform diagram includes: calculating the waveform matching degree of each magnetocardiographic signal with the target magnetocardiographic waveform diagram in different bands based on the distribution parameters of different waveform types of each magnetocardiographic signal in each band and the corresponding distribution weight coefficient; and calculating the comprehensive matching degree based on the waveform matching degree of each magnetocardiographic signal with the target magnetocardiographic waveform diagram in different bands and the corresponding waveform weight coefficient.

[0012] In a second aspect, the present invention provides a magnetocardiogram analysis system, comprising: a magnetocardiogram data acquisition module, which acquires a magnetocardiogram data set of a magnetocardiogram to be analyzed; a waveform drawing module, which draws a time wave group diagram and a space wave group diagram for each magnetocardiogram signal in the magnetocardiogram data set; a waveform type determination module, which determines the waveform type of the magnetocardiogram signal in each band based on the time wave group diagram and the space wave group diagram of the magnetocardiogram signal; a waveform distribution calculation module, which calculates the waveform distribution parameters of each magnetocardiogram signal in each band based on the waveform type of each magnetocardiogram signal in each band in the magnetocardiogram data set; and a matching analysis module, which determines the degree of matching between each magnetocardiogram signal and a target magnetocardiogram waveform diagram based on the waveform distribution parameters of each magnetocardiogram signal in each band, and obtains an analysis result of each magnetocardiogram signal in the magnetocardiogram data set.

[0013] In a third aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-mentioned magnetocardiogram analysis methods.

[0014] In a fourth aspect, the present invention provides an electronic device comprising: a processor and a memory; wherein the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the electronic device performs any of the above-mentioned magnetocardiogram analysis methods.

[0015] As described above, the magnetocardiogram analysis method, system, storage medium, and electronic device of the present invention have the following beneficial effects:

[0016] This application classifies waveforms of different bands according to their waveform characteristics, extracts the distribution patterns of each channel of different waveform types in different bands, and quantifies these distribution patterns into different distribution parameters, effectively depicting the characteristics of cardiac electrical activity behind different waveform distributions. It is an effective representation of the temporal and spatial distribution patterns of cardiac magnetic signals, and has strong medical interpretability and important clinical research value. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 Shown is a schematic diagram of the steps of the magnetocardiogram analysis method according to one embodiment of the present invention;

[0018] Figure 2A FIG2 is a schematic diagram showing step S103 of the magnetocardiogram analysis method according to an embodiment of the present invention;

[0019] Figure 2B FIG2 is a schematic diagram showing step S103 of the magnetocardiogram analysis method according to another embodiment of the present invention;

[0020] Figure 2C Schematic diagram showing step S215 of the magnetocardiogram analysis method according to one embodiment of the present invention;

[0021] Figure 2D FIG2 is a schematic diagram showing step S103 of the magnetocardiogram analysis method according to another embodiment of the present invention;

[0022] Figure 3A The figure shows a time wave group diagram of the magnetocardiogram signal in step S102 of the magnetocardiogram analysis method according to one embodiment of the present invention;

[0023] Figure 3B FIG2 is a diagram showing a spatial wave group of a magnetocardiogram signal in step S102 of the magnetocardiogram analysis method according to an embodiment of the present invention;

[0024] Figure 4 A schematic diagram showing the QRS wave types in an embodiment of the magnetocardiogram analysis method of the present invention;

[0025] Figure 5 A schematic diagram showing the distribution of T wave types in an embodiment of the magnetocardiogram analysis method of the present invention;

[0026] Figure 6 A spatial wave group diagram showing the inversion distribution parameters of the T-wave type in an embodiment of the magnetocardiogram analysis method of the present invention;

[0027] Figure 7 A schematic diagram showing the distribution of QRS wave types in an embodiment of the magnetocardiogram analysis method of the present invention;

[0028] Figure 8 A spatial wave group diagram showing the negative distribution parameters of the QRS wave type in an embodiment of the magnetocardiogram analysis method of the present invention;

[0029] Figure 9 A schematic diagram showing the distribution of ST wave types in an embodiment of the magnetocardiogram analysis method of the present invention;

[0030] Figure 10 Shown is a schematic structural diagram of a magnetocardiogram analysis system according to one embodiment of the present invention;

[0031] Figure 11 FIG. 1 is a schematic structural diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0032] The following describes the embodiments of the present invention through specific examples. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments. The details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other unless they conflict.

[0033] It should be noted that the illustrations provided in the following embodiments are merely schematic illustrations of the basic concept of the present invention. Therefore, the illustrations only show components related to the present invention and are not drawn according to the number, shape, and size of components in actual implementation. In actual implementation, the type, quantity, and proportion of each component may be changed arbitrarily, and the component layout may also be more complex.

[0034] A magnetocardiogram (MCO) is a wave group diagram that superimposes signal data from different channels in the temporal or spatial dimensions during MCO acquisition. Throughout the entire cycle of cardiac electrical activity, it exhibits distinct band characteristics and spatial and temporal distribution patterns, such as the positive wave in the lower half of the QRS band and the inverted wave in the lower left corner of the T band. The lack of unified classification rules and research methods for specific bands limits the ability to compare and analyze MCOO with cardiac electrophysiological activity.

[0035] In order to more intuitively and systematically describe the type characteristics and distribution patterns of each band of the magnetic cardiogram waveform, this application determines the waveform category and calculates the waveform distribution characteristics of the QRS band, ST band and T band according to the waveform characteristics. It can show the cardiac electrophysiological changes behind different bands, which is of great significance to cardiac function assessment and cardiac event research.

[0036] The technical solutions in the embodiments of the present invention will be described in detail below with reference to the accompanying drawings in the embodiments of the present invention.

[0037] See also Figure 1 The magnetocardiogram analysis method provided by the embodiment of the present invention includes the following steps S101 to S105.

[0038] Step S101: obtaining a magnetocardiogram dataset to be analyzed.

[0039] Step S102 : plotting a time wave group diagram and a space wave group diagram for each magnetocardiogram signal in the magnetocardiogram dataset.

[0040] Specifically, a magnetocardiogram dataset is a collection of magnetocardiogram data, each of which is multi-channel signal data, meaning that magnetocardiogram data is a magnetocardiogram signal. Taking a 36-channel magnetocardiograph as an example, each piece of magnetocardiogram data is a single-cycle signal data from 36 channels, i.e., 36*N, where 36 is the number of channels and N is the heartbeat period of the magnetocardiogram data, such as 1000ms. Each millisecond of the 36-channel signal data is a 6*6 dot matrix, representing the magnetic field distribution value of the frontal plane (a plane parallel to the chest when lying down) at that moment. This can be further interpolated into a 100*100 dot matrix (drawn into an isomagnetic map).

[0041] Step S103 : determining the waveform type of the magnetocardiographic signal in each band based on the temporal wave group diagram and the spatial wave group diagram of the magnetocardiographic signal.

[0042] Step S104 : calculating the waveform distribution parameters of each magnetocardiogram signal in each band based on the waveform type of each magnetocardiogram signal in each band in the magnetocardiogram dataset.

[0043] Step S105 , based on the waveform distribution parameters of each magnetocardiogram signal in each band, determining the matching degree of each magnetocardiogram signal with the target magnetocardiogram waveform, and obtaining an analysis result of each magnetocardiogram signal in the magnetocardiogram dataset.

[0044] In one embodiment of the present application, the magnetocardiogram dataset acquired based on the multi-channel magnetocardiograph is a C*N magnetocardiogram dataset, where the C*N magnetocardiogram dataset is the original magnetocardiogram signal of the entire cycle detected by the magnetocardiograph, the number of acquisition channels of the magnetocardiograph is C, and the cycle length of the acquired original magnetocardiogram signal is N milliseconds. Based on the C*N magnetocardiogram dataset, a time wave group diagram of each magnetocardiogram signal is drawn (e.g., Figure 3A ) and spatial wave group diagrams (as shown in Figure 3B Based on the time wave group diagram and the spatial wave group diagram, the waveform type of each acquisition channel in different bands (such as the QRS band, ST band, and T band) is determined. Different bands have different changing patterns in the magnetocardiographic waveform diagram. Based on these characteristics, different waveform types can be calculated for each channel in different bands.

[0045] It should be noted that the magnetocardiogram is a wave group diagram in which the signal data of different channels are superimposed in the time or space dimension during the acquisition of magnetocardiogram. In the entire cycle of cardiac electrical activity, there are obvious band characteristics, as well as spatial and temporal distribution patterns, such as the positive wave in the lower half of the QRS band and the inverted wave in the lower left corner of the T band. At present, the research on the magnetocardiogram mainly focuses on some single waveform features, such as R wave amplitude, T wave integral, waveform factor, fluctuation index, etc. The waveform features are modeled, analyzed and predicted by machine learning or deep learning algorithms. There is a lack of unified classification rules and distribution law research methods for specific bands, which limits the comparison and analysis ability of the magnetocardiogram and cardiac electrophysiological activity. In order to more intuitively and systematically describe the type characteristics and distribution law of each band of the magnetocardiogram waveform, this application proposes the analysis method of the magnetocardiogram, which determines the waveform category and calculates the waveform distribution characteristics of the QRS band, ST band and T band according to the waveform characteristics, and can show the cardiac electrophysiological change law behind different bands, which is of great significance to cardiac function assessment and cardiac event research.

[0046] In one embodiment of the present application, step S103 determines the waveform type of the magnetocardiographic signal in each band based on the time wave group diagram and the space wave group diagram of the magnetocardiographic signal. One implementation process includes determining the waveform type of the T wave band of the magnetocardiographic signal.

[0047] like Figure 2A As shown, an implementation process of determining the waveform type of the T-band of the magnetocardiographic signal includes steps S201 to S204.

[0048] S201, connecting the tail of the T wave and the head of the P wave in the time wave group diagram to obtain the TP band of the corresponding magnetocardiographic signal;

[0049] S202, subtracting the signal average value of the corresponding TP band from each single signal wave in the spatial wave group diagram to obtain the signal of each channel after TP baseline fine-tuning;

[0050] S203, extracting the maximum positive wave and the maximum negative wave from each channel signal after the TP baseline is fine-tuned; when the maximum positive wave meets a first condition, it is a reliable positive wave; when the maximum negative wave meets a second condition, it is a reliable negative wave;

[0051] S204, determining the waveform type of the T wave band of each channel based on the number and sequence of reliable positive waves and reliable negative waves in each channel signal after fine-tuning the TP baseline; wherein the waveform types of the T wave band include upright, flat, positive-negative, negative-positive, and inverted; the waveform type corresponding to a single reliable positive wave is upright, the waveform type corresponding to no reliable positive wave and a reliable negative wave is flat, the waveform type corresponding to a first reliable positive wave and a second reliable negative wave is positive-negative, the waveform type corresponding to a first reliable negative wave and a second reliable positive wave is negative-positive, and the waveform type corresponding to a single reliable negative wave is inverted.

[0052] Exemplarily, a specific implementation process of determining the waveform type of the T wave band of the magnetocardiographic signal includes:

[0053] 1) TP baseline fine-tuning: Subtract the average signal value of the corresponding TP band from each individual signal wave in the spatial wave group diagram to obtain the per-channel signal after TP baseline fine-tuning to reduce the impact of noise. The TP band is composed of the tail of the T wave and the head of the P wave, connected in a tail-to-head manner.

[0054] 2) Calculate reliable waves: Calculate the maximum amplitude M for all channels using the signal from each channel after fine-tuning the TP baseline. For a single channel, take the maximum positive wave fp and the maximum negative wave -fn in the T band. A reliable positive wave is considered a reliable wave if the maximum positive wave satisfies the first condition fp / M > r1. Similarly, a reliable negative wave is considered a reliable wave if the maximum negative wave satisfies the second condition -fn / M > r2, where r1 / r2 is the preset threshold. Reliable T waves for all channels can be obtained using the same calculation method.

[0055] 3) Determination of T wave type: T wave types include upright, flat, positive-negative, negative-positive, and inverted, which can be represented by T / F / +- / -+ / I, respectively. Based on the number and type of reliable T waves, a single positive wave is upright, no reliable wave is flat, positive followed by negative and negative followed by positive are respectively represented by positive-negative / negative-positive, and a single negative wave is inverted.

[0056] In one embodiment of the present application, step S103 may further include determining the waveform type of the QRS wave band of the magnetocardiogram based on the time wave group diagram and the space wave group diagram of the magnetocardiogram.

[0057] like Figure 2B As shown, an implementation process of determining the waveform type of the QRS wave band of the magnetocardiographic signal includes steps S211 to S216.

[0058] S211, connecting the tail of the T wave and the head of the P wave in the time wave group diagram to obtain the TP band corresponding to the magnetocardiographic signal;

[0059] S212, subtracting the signal average value of the corresponding TP band from each single signal wave in the spatial wave group diagram to obtain the signal of each channel after TP baseline fine-tuning;

[0060] S213, obtaining the QRS band of each channel signal after TP baseline fine-tuning and the bands of preset lengths before and after the QRS band as candidate bands, counting all peaks and troughs in the candidate bands as candidate points, and calculating the ratio of each candidate point to the maximum amplitude of the QRS band;

[0061] S214, taking the candidate point whose ratio value is greater than a preset value as a candidate wave;

[0062] S215, performing threshold filtering on the candidate waves to obtain reliable waves;

[0063] S216, determining the waveform type of the QRS wave band according to the number and positive and negative directions of reliable waves; wherein the waveform types of the QRS wave band include R, RR, qR, QR, Qr, Rs, RS, rS, Q, QQ, QRS and QRSs.

[0064] In one embodiment of the present application, Figure 2C As shown, step S215 performs threshold filtering on the candidate wave to obtain a reliable wave, and an implementation process includes:

[0065] S2151, sorting the candidate waves in descending order according to their proportional values;

[0066] S2152, directly add the candidate wave with the largest ratio value as the reliable wave;

[0067] S2153, judging in descending order by the proportion values ​​whether the corresponding sorted candidate waves are added as reliable waves, including:

[0068] S2153a, when the candidate wave of the corresponding sort is greater than the corresponding preset sort threshold, the candidate wave of the corresponding sort is added as a reliable wave, otherwise it is not added;

[0069] S2153b, when two adjacent correspondingly sorted candidate waves have the same direction and their ratio values ​​are both less than the noise threshold, the two adjacent correspondingly sorted candidate waves are determined to be noise and are not added, and the subsequent sorted candidate waves on the same side are not added;

[0070] S2153c: When two adjacent correspondingly ordered non-noise candidate waves have the same direction and a ratio value smaller than a threshold value, the two adjacent correspondingly ordered non-noise candidate waves are determined to be notches, merged into one wave, and then added as a reliable wave.

[0071] Furthermore, each time the current candidate wave is determined to be added as a reliable wave, if there are candidate waves between the current candidate wave and the existing reliable wave, all candidate waves between the current candidate wave and the existing reliable wave are automatically added as reliable waves, excluding noise.

[0072] Exemplarily, an exemplary specific implementation process of determining the waveform type of the QRS wave band of the magnetocardiographic signal includes:

[0073] 1) TP baseline fine-tuning: Subtract the average signal value of the corresponding TP band from each individual signal wave in the spatial wave group diagram to obtain the per-channel signal after TP baseline fine-tuning to reduce the impact of noise. The TP band is composed of the tail of the T wave and the head of the P wave, connected in a tail-to-head manner.

[0074] 2) Candidate point set: After fine-tuning the TP baseline, the QRS band and the band before and after +t0ms are extracted from each channel signal as candidate bands. All peaks and troughs of the candidate bands are counted as candidate points, and the ratio of the candidate points to the maximum QRS amplitude is calculated. t0 is the preset threshold.

[0075] 3) Alternative wave set: The candidate points with a ratio value greater than v1 are selected as the alternative waves, and then the alternative waves are sorted from large to small. The alternative wave with the largest ratio value is directly added as the reliable wave.

[0076] 4) Select waves in sequence: in descending order of proportion values, if the proportion value of the second alternative wave is greater than v2, it is added as a reliable wave; if the proportion value of the third alternative wave is greater than v3, it is added as a reliable wave, and so on, until the judgment of the last alternative wave is completed.

[0077] 5) Noise Determination: When the ratio values ​​of two adjacent candidate waves in the same direction are both less than vn, they are considered noise and are not added. Furthermore, subsequent candidate waves in the same direction (i.e., on the same side, left, or right) are not added as reliable waves. v1, v2, v3, ..., vn correspond to different ratio limits.

[0078] Considering a single signal wave, two candidate waves with the same direction indicate the same positive / negative direction (waveforms pointing up / down). When two candidate waves with the same direction are adjacent and have small amplitudes, they are considered high-frequency noise waves. In this case, with the largest wave (possibly positive / negative) as the origin, the two noise waves may be to the left / right. Subsequent candidate waves further to the left / right are not added, describing "subsequent candidate waves with the same direction are no longer added as reliable waves." The same direction means being to the left / right of the origin.

[0079] 6) Intermediate Waves: Each time a candidate wave is added as a reliable wave, all candidate waves between it and the existing wave are automatically added, excluding noise. If the ratio of two adjacent non-noise, same-direction candidate waves is close and less than h1, the two adjacent non-noise, same-direction candidate waves are considered notches and need to be merged into one candidate wave. h1 is the threshold value.

[0080] 7) Determine the QRS wave type: There are 12 QRS wave types, which can be recorded as 'R', 'RR', 'qR', 'QR', 'Qr', 'Rs', 'RS', 'rS', 'Q', 'QQ', 'QRS', and 'QRSs'. All reliable waves added in the above manner are determined to be of one of the 12 types based on the number of reliable waves and the positive and negative directions.

[0081] like Figure 4 As shown in the figure, it shows 12 types of QRS waves, among which lowercase letters represent smaller non-notched waves, and any waves greater than or equal to 3 reliable waves are recorded as QRSs.

[0082] R wave: a positive reliable wave;

[0083] RR waves: two positive reliable waves;

[0084] qR: There is a small negative wave first, followed by a clear positive wave;

[0085] QR: There is a clear negative wave first, followed by a clear positive wave;

[0086] Qr: There is a clear negative wave first, followed by a small positive wave;

[0087] Rs: There is a clear positive wave first, followed by a small negative wave;

[0088] RS: There is a clear positive wave followed by a clear negative wave;

[0089] rS: There is a small positive wave first, followed by a clear negative wave;

[0090] Q: A reliable wave in the negative direction;

[0091] QQ: two negative reliable waves;

[0092] QRS: three reliable waves;

[0093] QRSs: Multiple reliable waves (more than three waves).

[0094] In this embodiment, the 12 QRS wave types are named and designed according to the characteristics of the magnetic heart signal, which are related to but not exactly the same as the electrocardiogram definition.

[0095] In one embodiment of the present application, an implementation process of determining the waveform type of the magnetocardiogram signal in each frequency band based on the time wave group diagram and the spatial wave group diagram of the magnetocardiogram signal may further include determining the waveform type of the ST band of the magnetocardiogram signal.

[0096] As Figure 2D shown, an implementation process of determining the waveform type of the ST band of the magnetocardiogram signal includes steps S221 to S226.

[0097] S221, connect the tail after the T wave and the head before the P wave in the time wave group diagram head to tail to obtain the TP band corresponding to the magnetocardiogram signal;

[0098] S222, subtract the signal average value of the corresponding TP band from each single signal wave in the spatial wave group diagram to obtain the signal of each channel after TP baseline fine-tuning;

[0099] S223, calculate the positive and negative amplitude ratio of the ST band based on the signal of each channel after the TP baseline fine-tuning;

[0100] S224, if the positive and negative amplitude ratio is greater than or equal to the first threshold and less than or equal to the second threshold, it belongs to the normal range, and the waveform type of the corresponding ST band is not elevated or depressed;

[0101] S225, if the positive and negative amplitude ratio is less than the first threshold, the waveform type of the corresponding ST band is depressed;

[0102] S226, if the positive and negative amplitude ratio is greater than the second threshold, the waveform type of the corresponding ST band is elevated.

[0103] Exemplarily, an exemplary implementation process of determining the waveform type of the ST band of the magnetocardiogram signal includes:

[0104] 1) TP baseline fine-tuning: Subtract the signal average value of the corresponding TP band from each single signal wave in the spatial wave group diagram to obtain the signal of each channel after TP baseline fine-tuning to reduce the influence of noise. Among them, the TP band is the band formed by connecting the tail after the T wave and the head before the P wave in a head-to-tail manner.

[0105] 2) Calculate the positive and negative amplitude ratio fr of the ST band with the signal of each channel after TP baseline fine-tuning. When u1 <= fr <= u2, it is within the normal range, not elevated or depressed; when fr < u1, it is recorded as depressed, and when fr > u2, it is recorded as elevated, where u1 and u2 are preset determination thresholds.

[0106] In one embodiment of the present application, step S104 calculates the waveform distribution parameter of each magnetocardiogram signal in each band based on the waveform type of each magnetocardiogram signal in each band in the magnetocardiogram dataset. One implementation process includes: counting the distribution ratio of the waveform type of each band of the magnetocardiogram signal corresponding to each acquisition channel in the magnetocardiogram dataset; and merging the corresponding distribution ratio information of acquisition channels with higher distribution ratios and the same waveform type as the distribution parameter of the corresponding waveform type of each magnetocardiogram signal, i.e., the waveform distribution parameter.

[0107] In this embodiment, based on the waveform types of the QRS band, ST band and T band of each channel, the distribution parameters of multiple waveform types are calculated; for different bands, the distribution of waveform types has different rules. According to the information statistics of different waveform types under the 0 / 1 label on the 1000-case data set of this application, multiple distribution parameters of different bands can be calculated (taking 36 channels as an example, other multiple channels are similar).

[0108] For example, the calculation of the distribution parameters of different waveform types of the T band includes: counting the distribution ratios of different T wave types in the data set of label data 1, and merging the channel information of the same type with a higher distribution ratio as the distribution parameter, as shown in FIG Figure 5 As shown, it shows a higher proportion of T wave types and channels.

[0109] Upright distribution parameter T1: The distribution ratios of the four prominent channels [A3, A4, B3, B4] with upright T waves under different waveform types are summed to obtain the upright distribution parameter value of one embodiment (for example, the distribution ratios of the four channels under five waveform types are [96, 65, 86, 53, 35], [100, 73, 67, 78, 40], [75, 56, 65, 44, 38], and [88, 77, 60, 54, 40], expressed as percentages. The T wave types of the four channels are upright / flat / upright / upright. The values ​​are taken in order and summed to obtain the upright distribution parameter of (96 + 73 + 75 + 88) / 100 = 3.32).

[0110] Inversion distribution parameter T2: Similarly, the distribution ratios of the 9 significant channels with inverted T waves [D3, D4, E3, E4, E5, F2, F3, F4, F5] under different waveform types are summed to obtain the inversion distribution parameter value of an embodiment, such as Figure 6 As shown, it shows a spatial wave group diagram of an embodiment, and the inversion distribution parameter is 27.7.

[0111] For example, calculating the distribution parameters of different types of QRS wave bands includes: counting the distribution ratios of different QRS wave types in the data set, and merging the channel information of the same type with a higher distribution ratio as the distribution parameter, such as Figure 7As shown, it shows a higher proportion of QRS complex types and channels.

[0112] Negative distribution parameter QRS1: Similar to the above T wave distribution parameter, the 12 significant channels of the negative QRS wave [A1, A2, A3, A4, A5, A6, B1, B2, B3, B4, B5, B6] are summed up under different types of distribution ratios to obtain the negative distribution parameter of an embodiment, such as Figure 8 As shown, it shows a spatial wave group diagram of an embodiment, and the inversion distribution parameter is 52.5.

[0113] Forward distribution parameter QRS2: The forward distribution parameter of an embodiment is obtained by summing the distribution proportions of the 14 significant channels [D2, D3, D4, D5, E2, E3, E4, E5, F1, F2, F3, F4, F5, F6] of the QRS wave in different types.

[0114] Qr distribution parameter QRS3: The distribution ratios of the five significant channels [A1, A2, A3, B1, B2] of the QRS wave Qr type under different types are summed to obtain the Qr distribution parameter of an embodiment.

[0115] rS distribution parameter QRS4: The distribution ratios of the six significant channels [A4, A5, A6, B3, B4, B5] of the QRS wave rS type are summed under different types to obtain the rS distribution parameter of an embodiment.

[0116] Exemplarily, a specific implementation process of calculating different types of distribution parameters of the ST band includes:

[0117] 1) Area determination: The same ST type in at least n1 adjacent channels is considered a reliable wave (elevation or depression). The orientation of the main abnormal area of ​​36 channels is derived based on the weights and divided into five types: top / bottom / left / right / center. The sides are divided into 2 rows and the center is divided into 4*4=16 channels.

[0118] 2) ST distribution parameter ST1: Count the distribution ratios of different ST wave types in the data set for 1 label data, and define 16 distribution ratio values ​​under 5 orientations and 4 types (normal / elevated / depressed / elevated and depressed) (no orientation information in normal) as ST distribution parameters, such as Figure 9 As shown, it shows a spatial wave group diagram of an embodiment, ST segment elevation and depression, the orientation is intermediate, and the ST distribution parameter is 3.5.

[0119] Because the QRS band, ST band and T band are more sensitive to abnormal changes in cardiac function, they have shown high sensitivity and specificity in comparative experiments on different cardiac events and have broad application prospects. Therefore, the embodiments of this application select the waveform distribution parameters of the QRS band, ST band and T band for illustration, but the protection scope of this application is not limited to the three sensitive bands of QRS band, ST band and T band listed in this embodiment, and any other bands are applicable to the scheme described in this application.

[0120] In one embodiment of the present application, step S105 determines the matching degree of each magnetocardiographic signal with the target magnetocardiographic waveform diagram based on the waveform distribution parameters of each magnetocardiographic signal in each band. One implementation process includes: calculating the waveform matching degree of each magnetocardiographic signal with the target magnetocardiographic waveform diagram in different bands based on the distribution parameters of different waveform types of each magnetocardiographic signal in each band and the corresponding distribution weight coefficient; and calculating the comprehensive matching degree based on the waveform matching degree of each magnetocardiographic signal with the target magnetocardiographic waveform diagram in different bands and the corresponding waveform weight coefficient.

[0121] Exemplarily, based on multiple waveform distribution parameters, the matching degree between the magnetocardiographic waveform image and the reference magnetocardiographic waveform image set is determined; the matching degree is calculated under any number of combinations of the three bands:

[0122] mc=L1*(a1*T1+a2*T2)+L2*(b1*QRS1+b2*QRS2+b3*QRS3+b4*QRS4)+L3*ST1;

[0123] Where mc is the matching degree, L1, L2, L3, a1, a2, b1, b2, b3, and b4 are empirical coefficients, T1 is the upright distribution parameter value, T2 is the inverted distribution parameter value, QRS1 is the negative distribution parameter value, QRS2 is the positive distribution parameter value, QRS3 is the Qr distribution parameter value, QRS4 is the rS distribution parameter value, and ST1 is the ST distribution parameter value.

[0124] The matching degree calculation method described in this application can also be used for determination using a single band or a combination of any bands. It should be noted that different coefficients should be set for the matching degree formula under specific data sets and different band combinations.

[0125] This application classifies waveforms of different bands according to their waveform characteristics. The channel distributions of different waveform types in different bands have different rules. This application quantifies these distribution rules into different distribution parameters, which can effectively characterize the characteristics of cardiac electrical activity behind different waveform distributions. It is an effective representation of the temporal and spatial distribution rules of cardiac magnetic signals, and has strong medical interpretability and important clinical research value.

[0126] For example, a dataset and parameter settings are as follows: a dataset of 1000 cases (i.e., a magnetocardiogram dataset) is constructed and divided into two groups, each with a 0 / 1 label. Assume that all 1000 cases have 36 channels, with a data dimension of 36*Ni, where Ni is the single-cycle length of the magnetocardiogram signal of channel i, in milliseconds, and i is a positive integer greater than or equal to 1 and less than or equal to 36; the magnetocardiogram data of the QRS band, ST band, and T band are respectively intercepted, with a data dimension of 36*Mj, where Mj is the length of each band; using the magnetocardiogram analysis method described in this application, the waveform type of each of the 36 channels is calculated, so that each case has a QRS waveform type, a T wave waveform type, and an ST waveform type for 36 channels.

[0127] For a longitudinal comparison, consider T wave waveform types (i.e., the waveform type of the T band). For example, consider channel A3. Counting 1000 data points for five T wave types on channel A3. Assuming 100 of these 1000 T wave types are upright, and 96 of these belong to label 1, the proportion of upright T wave abnormalities on that single channel is 96%. Similarly, counting the proportions of each of the five T waveform types yields [96, 65, 86, 53, 35], representing the distribution of abnormal T wave proportions on channel A3. Similarly, across 36 channels, there are 36 distributions of abnormal T wave proportions (36*5), 36 distributions of abnormal QRS complex proportions (36*12), and 5 distributions of abnormal ST wave proportions (5*4).

[0128] ST waveform types are defined as 4 types with 5 positions (normal / elevated / depressed / elevated and depressed), rather than 36 channels (upper / lower / left / right / center). Because the "normal" type does not have position information, there are a total of 5*3+1=16 specific waveform types. Each ST waveform type in the 1000 data sets has a proportion labeled 1. The abnormal proportions of each waveform type are calculated to obtain an array of 16 numbers.

[0129] Based on the distribution characteristics of the 1000 data sets in terms of QRS waveform type, ST waveform type, and T wave waveform type, the "distribution parameters" were calculated separately. For example, two distribution parameters were calculated for abnormal concentrated areas of upright and inverted T wave distribution (i.e., the channel and type with the larger value in the 36 arrays).

[0130] Taking the upright distribution parameter as an example, where four channels are concentrated, the upright distribution parameter is calculated according to the following method for one embodiment: First, the waveform type of the T wave for the 36 channels of this sample is calculated. The waveform type for these four channels is assumed to be upright / flat / upright / upright. As described above, the distribution ratio values ​​are obtained and the parameter is calculated, resulting in (96 + 73 + 75 + 88) / 100 = 3.32. The theoretical value range of the upright distribution parameter is 0-4, as it is the sum of the ratio values ​​of the four channels divided by 100. Similarly, the inverted distribution parameter uses nine channels and has a theoretical value range of 0-9.

[0131] The calculation process of the distribution parameters of the QRS wave is similar to that of the T wave.

[0132] The ST wave is calculated by dividing the single type value by 10, with a theoretical value between 0 and 10. For example, in one embodiment, the ST wave waveform type is intermediate elevation and depression, which corresponds to 35 in the abnormal proportion distribution array (16 numbers) (the proportion of label 1 is 35%), and the corresponding ST distribution parameter is 35 / 10 = 3.5. Because the value range of each distribution parameter in each band is different, based on the values ​​of each distribution parameter in 1000 data sets, a certain proportional coefficient can be preset through methods such as logistic regression to achieve the best discrimination between the 0 / 1 labels in the comprehensive matching score.

[0133] In the embodiment of the present application, whether it is the constructed 1000 cases of data or the new external data, the QRS waveform type, T wave waveform type and ST waveform type of the 36 channels can be calculated in sequence according to the method described in the present application; then, the channels selected according to different distribution parameters and their respective abnormal proportion distribution arrays are substituted into the calculation of 7 distribution parameters; finally, the matching degree calculation formula is substituted into the matching degree calculation formula to obtain the matching degree score, which is the degree of matching with label 1 in the 1000 cases of data, that is, the degree of abnormality, which is more biased towards 1 (the larger the more abnormal) under a certain threshold.

[0134] In this application, the preset coefficients of the matching degree calculation formula can be different. The preset coefficients depend on the constructed data set. The matching degree can also be calculated using a single band or any combination of bands. The matching degree thresholds under different methods are also different, that is, when it is greater than a certain value, it is more biased towards 1.

[0135] The analysis method of the waveform types and their corresponding waveform distribution parameters described in this application is the core design of this application. It determines the waveform type, calculates the distribution parameters, obtains the waveform matching degree of different bands, and obtains the analysis results of the magnetocardiogram to be analyzed based on the comprehensive matching degree with the target magnetocardiogram.

[0136] The three bands (QRS band, ST band and T band) in this application have clear clinical background and physical significance, and other bands / intervals with reasonable significance can be implemented using the method described in this application.

[0137] This application extracts a series of distribution parameters for different distribution phenomena in different bands. The distribution laws in other scenarios are also applicable. For example, in a certain data set, there are bidirectional distribution laws of T waves in certain channels, and the bidirectional distribution parameters of T waves can also be calculated similarly.

[0138] An embodiment of the present application further provides a magnetocardiogram analysis system, which can implement the magnetocardiogram analysis method described in the present application. However, the implementation device of the magnetocardiogram analysis method described in the present application includes but is not limited to the structure of the magnetocardiogram analysis system listed in this embodiment. All structural variations and replacements of the prior art made according to the principles of the present application are included in the scope of protection of the present application.

[0139] See also Figure 10 This embodiment provides a magnetocardiogram analysis system 100, which includes: a magnetocardiogram data acquisition module 110, a waveform drawing module 120, a waveform type determination module 130, a waveform distribution calculation module 140 and a matching analysis module 150.

[0140] The magnetocardiogram data acquisition module 110 acquires a magnetocardiogram dataset of a magnetocardiogram to be analyzed.

[0141] The waveform drawing module 120 draws a time wave group diagram and a space wave group diagram for each magnetocardiogram signal in the magnetocardiogram dataset.

[0142] The waveform type determination module 130 determines the waveform type of the magnetocardiographic signal in each band based on the temporal wave group diagram and the spatial wave group diagram of the magnetocardiographic signal.

[0143] The waveform distribution calculation module 140 calculates the waveform distribution parameters of each magnetocardiogram signal in each band based on the waveform type of each magnetocardiogram signal in each band in the magnetocardiogram dataset.

[0144] The matching analysis module 150 determines the matching degree between each magnetocardiogram signal and the target magnetocardiogram waveform based on the waveform distribution parameters of each magnetocardiogram signal in each band, and obtains the analysis result of each magnetocardiogram signal in the magnetocardiogram dataset.

[0145] Since the specific implementation of this embodiment corresponds to the aforementioned method embodiment, the same details will not be repeated here, and those skilled in the art should also understand that Figure 10 The division of the various modules in the embodiment is merely a division of logical functions. In actual implementation, all or part of the modules can be integrated into one or more physical entities, and all of these modules can be implemented in the form of software called by processing elements, or all of them can be implemented in the form of hardware. Some modules can also be implemented in the form of software called by processing elements, and some modules can be implemented in the form of hardware.

[0146] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices or methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of modules / units is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules or units can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules or units, which can be electrical, mechanical or other forms.

[0147] Modules / units described as separate components may or may not be physically separate, and components displayed as modules / units may or may not be physical modules, that is, they may be located in one place or distributed across multiple network elements. Some or all of the modules / units may be selected based on actual needs to achieve the objectives of the embodiments of the present invention. For example, the functional modules / units in various embodiments of the present invention may be integrated into a single processing module, each module / unit may exist physically separately, or two or more modules / units may be integrated into a single module / unit.

[0148] Those skilled in the art should further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the composition and steps of each example according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0149] The embodiment of the present invention also provides a computer-readable storage medium. A person skilled in the art will understand that all or part of the steps in the method for implementing the above embodiment can be completed by instructing a processor through a program, and the program can be stored in a computer-readable storage medium, and the storage medium is a non-transitory medium, such as a random access memory, a read-only memory, a flash memory, a hard disk, a solid-state drive, a magnetic tape, a floppy disk, an optical disc, and any combination thereof. The above storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that includes one or more available media. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a digital video disc (DVD)), or a semiconductor medium (for example, a solid-state drive (SSD)), etc.

[0150] An embodiment of the present invention further provides an electronic device. The electronic device includes a processor and a memory. The memory is used to store computer programs.

[0151] The memory includes various media that can store program codes, such as ROM, RAM, magnetic disk, USB flash drive, memory card or optical disk.

[0152] The processor is connected to the memory and is used to execute the computer program stored in the memory, so that the electronic device performs the above-mentioned magnetocardiogram analysis method.

[0153] Preferably, the processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0154] like Figure 11As shown, the electronic device of the present invention is in the form of a general-purpose computing device. Components of the electronic device may include, but are not limited to: one or more processors or processing units 111, memory 112, and a bus 113 connecting different system components (including memory 112 and processing unit 111).

[0155] Bus 113 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures. Examples of these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0156] Electronic devices typically include a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device, including volatile and non-volatile media, removable and non-removable media.

[0157] The memory 112 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 1121 and / or cache memory 1122. The electronic device may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 723 may be used to read and write non-removable, non-volatile magnetic media ( Figure 11 Not shown, often called a "hard drive"). Although Figure 11 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 113 via one or more data medium interfaces. Memory 112 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of various embodiments of the present invention.

[0158] A program / utility 1124 having a set (at least one) of program modules 11241 may be stored, for example, in memory 112. Such program modules 11241 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may include an implementation of a network environment. The program modules 11241 generally implement the functions and / or methods of the embodiments described herein.

[0159] The electronic device may also communicate with one or more external devices (e.g., keyboards, pointing devices, displays, etc.), one or more devices that enable a user to interact with the electronic device, and / or any device that enables the electronic device to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed via input / output (I / O) interface 74. Furthermore, the electronic device may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via network adapter 75. Figure 7 As shown, the network adapter 75 communicates with other modules of the electronic device via the bus 73. It should be understood that, although not shown in the figures, other hardware and / or software modules may be used in conjunction with the electronic device, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0160] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the present invention. Anyone skilled in the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by one of ordinary skill in the art without departing from the spirit and technical principles disclosed herein are intended to be covered by the claims of the present invention.

Claims

1. A method for analyzing a magnetocardiogram, characterized in that: include: Obtain a magnetocardiogram dataset to be analyzed; plotting a time wave group diagram and a space wave group diagram for each magnetocardiogram signal in the magnetocardiogram data set; Based on the time wave group diagram and space wave group diagram of the magnetocardiographic signal, the waveform type of the magnetocardiographic signal in each band is determined; Based on the waveform type of each magnetocardiogram signal in each band in the magnetocardiogram dataset, the waveform distribution parameters of each magnetocardiogram signal in each band are calculated; Based on the waveform distribution parameters of each magnetocardiogram signal in each band, the matching degree of each magnetocardiogram signal with the target magnetocardiogram waveform is determined to obtain the analysis result of each magnetocardiogram signal in the magnetocardiogram dataset.

2. The magnetocardiogram analysis method according to claim 1, characterized in that: Based on the time wave group diagram and space wave group diagram of the magnetocardiographic signal, the waveform type of the magnetocardiographic signal in each band is determined as follows: Determine the waveform type of the T band of the magnetic cardiogram signal, including: Connect the tail of the T wave and the head of the P wave in the time wave group diagram to obtain the TP band corresponding to the magnetic heart signal; Subtract the average signal value of the corresponding TP band from each single signal wave in the spatial wave group diagram to obtain the signal of each channel after TP baseline fine-tuning; Extracting the maximum positive wave and the maximum negative wave from each channel signal after the TP baseline is fine-tuned; when the maximum positive wave meets the first condition, it is a reliable positive wave; when the maximum negative wave meets the second condition, it is a reliable negative wave; The waveform type of the T wave band of each channel is determined based on the number and sequence of reliable positive waves and reliable negative waves in each channel signal after the TP baseline is fine-tuned; wherein, the waveform types of the T wave band include upright, flat, positive-negative, negative-positive, and inverted; the waveform type corresponding to a single reliable positive wave is upright, the waveform type corresponding to no reliable positive wave and a reliable negative wave is flat, the waveform type corresponding to a reliable positive wave first and a reliable negative wave later is positive-negative, the waveform type corresponding to a reliable negative wave first and a reliable positive wave later is negative-positive, and the waveform type corresponding to a single reliable negative wave is inverted.

3. The magnetocardiogram analysis method according to claim 1, characterized in that: Based on the time wave group diagram and space wave group diagram of the magnetocardiographic signal, the waveform type of the magnetocardiographic signal in each band is determined as follows: Determine the waveform type of the QRS wave band of the magnetic cardiogram signal, including: Connect the tail of the T wave and the head of the P wave in the time wave group diagram to obtain the TP band corresponding to the magnetic heart signal; Subtract the average signal value of the corresponding TP band from each single signal wave in the spatial wave group diagram to obtain the signal of each channel after TP baseline fine-tuning; The QRS band of each channel signal after TP baseline fine-tuning and the bands of preset lengths before and after the QRS band are obtained as candidate bands. All peaks and troughs in the candidate bands are counted as candidate points, and the ratio of each candidate point to the maximum amplitude of the QRS band is calculated. The candidate points whose proportion values ​​are greater than the preset value are taken as candidate waves; performing threshold filtering on the candidate waves to obtain reliable waves; The waveform type of the QRS wave band is determined according to the number and positive and negative directions of reliable waves; wherein the waveform types of the QRS wave band include R, RR, qR, QR, Qr, Rs, RS, rS, Q, QQ, QRS and QRSs.

4. The magnetocardiogram analysis method according to claim 3, characterized in that: Filtering the candidate waves to obtain reliable waves includes: sorting the candidate waves in descending order according to their proportional values; The candidate wave with the largest ratio value is directly added as a reliable wave; According to the proportion value from large to small, the corresponding sorted candidate waves are judged in order to determine whether to add them as reliable waves, including: When the candidate wave of the corresponding sort is greater than the corresponding preset sort threshold, the candidate wave of the corresponding sort is added as a reliable wave, otherwise it is not added; When two adjacent correspondingly sorted candidate waves have the same direction and their ratio values ​​are both less than the noise threshold, the two adjacent correspondingly sorted candidate waves are determined to be noise and are not added, and the subsequent sorted candidate waves on the same side are not added; When two adjacent correspondingly sorted non-noise candidate waves have the same direction and a ratio value less than a threshold value, the two adjacent correspondingly sorted non-noise candidate waves are determined to be notches, merged into one wave, and then added as a reliable wave; Each time the current candidate wave is determined to be added as a reliable wave, if there are alternative waves between the current candidate wave and the existing reliable waves, all alternative waves between the current candidate wave and the existing reliable wave will be automatically added as reliable waves, excluding noise.

5. The magnetocardiogram analysis method according to claim 1, characterized in that: Based on the time wave group diagram and space wave group diagram of the magnetocardiographic signal, the waveform type of the magnetocardiographic signal in each band is determined as follows: Determine the waveform type of the ST wave segment of the magnetic heart signal, including: Connect the tail of the T wave and the head of the P wave in the time wave group diagram to obtain the TP band corresponding to the magnetic heart signal; Subtract the average signal value of the corresponding TP band from each single signal wave in the spatial wave group diagram to obtain the signal of each channel after TP baseline fine-tuning; Calculating the positive and negative amplitude ratio of the ST band based on the signal of each channel after the TP baseline is fine-tuned; If the positive-to-negative amplitude ratio is greater than or equal to the first threshold and less than or equal to the second threshold, it is within the normal range, and the waveform type of the corresponding ST wave segment is neither elevated nor depressed; If the positive-to-negative amplitude ratio is less than a first threshold, the waveform type of the corresponding ST wave segment is depression; If the positive-to-negative amplitude ratio is greater than a second threshold, the waveform type of the corresponding ST wave segment is elevation.

6. The magnetocardiogram analysis method according to claim 1, characterized in that: Based on the waveform type of each MCG signal in each band in the MCG dataset, the waveform distribution parameters of each MCG signal in each band are calculated, including: Counting the distribution ratio of the waveform type of each band of the magnetocardiogram signal corresponding to each acquisition channel in the magnetocardiogram dataset; The corresponding distribution ratio information of the acquisition channels with higher distribution ratios and the same waveform type is merged as the distribution parameter of the corresponding waveform type of each magnetocardiographic signal, that is, the waveform distribution parameter.

7. The magnetocardiogram analysis method according to claim 1, characterized in that: Based on the waveform distribution parameters of each MCG signal in each band, the matching degree between each MCG signal and the target MCG waveform is determined as follows: The waveform matching degree between each magnetocardiogram signal and the target magnetocardiogram waveform in different bands is calculated based on the distribution parameters of each magnetocardiogram signal in different waveform types in each band and the corresponding distribution weight coefficient; The comprehensive matching degree is calculated based on the waveform matching degree of each magnetocardiographic signal and the target magnetocardiographic waveform in different bands and the corresponding waveform weight coefficient.

8. A magnetocardiogram analysis system, characterized in that: include: A magnetocardiogram data acquisition module is used to acquire a magnetocardiogram dataset to be analyzed; a waveform drawing module for drawing a time wave group diagram and a space wave group diagram for each magnetocardiogram signal in the magnetocardiogram data set; The waveform type determination module determines the waveform type of the magnetocardiographic signal in each band based on the time wave group diagram and space wave group diagram of the magnetocardiographic signal; The waveform distribution calculation module calculates the waveform distribution parameters of each magnetocardiogram signal in each band based on the waveform type of each magnetocardiogram signal in each band in the magnetocardiogram dataset; The matching analysis module determines the matching degree of each magnetocardiogram signal with the target magnetocardiogram waveform based on the waveform distribution parameters of each magnetocardiogram signal in each band, and obtains the analysis result of each magnetocardiogram signal in the magnetocardiogram dataset.

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

10. An electronic device, characterized in that: The electronic device includes: a processor and a memory; wherein the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the electronic device performs the magnetocardiogram analysis method according to any one of claims 1 to 7.

Images