CN117084684A - Characteristic parameter extraction method and system based on electrocardio current density map extension field - Google Patents
Characteristic parameter extraction method and system based on electrocardio current density map extension field Download PDFInfo
- Publication number
- CN117084684A CN117084684A CN202311353583.1A CN202311353583A CN117084684A CN 117084684 A CN117084684 A CN 117084684A CN 202311353583 A CN202311353583 A CN 202311353583A CN 117084684 A CN117084684 A CN 117084684A
- Authority
- CN
- China
- Prior art keywords
- field
- current density
- gradient
- divergence
- density map
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000605 extraction Methods 0.000 title claims abstract description 18
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 35
- 238000000034 method Methods 0.000 claims abstract description 25
- 238000010586 diagram Methods 0.000 claims description 13
- 230000008859 change Effects 0.000 claims description 11
- 238000010276 construction Methods 0.000 claims description 7
- 230000000694 effects Effects 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 5
- 230000003287 optical effect Effects 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 238000001514 detection method Methods 0.000 abstract description 9
- 201000010099 disease Diseases 0.000 abstract description 5
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 abstract description 5
- 239000013598 vector Substances 0.000 description 16
- 230000008901 benefit Effects 0.000 description 7
- 238000003745 diagnosis Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 230000035945 sensitivity Effects 0.000 description 4
- 208000019622 heart disease Diseases 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000005057 refrigeration Methods 0.000 description 2
- 208000024172 Cardiovascular disease Diseases 0.000 description 1
- 241000238366 Cephalopoda Species 0.000 description 1
- 201000000057 Coronary Stenosis Diseases 0.000 description 1
- 206010011089 Coronary artery stenosis Diseases 0.000 description 1
- 230000000747 cardiac effect Effects 0.000 description 1
- 238000002001 electrophysiology Methods 0.000 description 1
- 230000007831 electrophysiology Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 230000002107 myocardial effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/242—Detecting biomagnetic fields, e.g. magnetic fields produced by bioelectric currents
- A61B5/243—Detecting biomagnetic fields, e.g. magnetic fields produced by bioelectric currents specially adapted for magnetocardiographic [MCG] signals
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- Public Health (AREA)
- Animal Behavior & Ethology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Veterinary Medicine (AREA)
- Artificial Intelligence (AREA)
- Theoretical Computer Science (AREA)
- Pathology (AREA)
- Physiology (AREA)
- Signal Processing (AREA)
- Psychiatry (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Cardiology (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention belongs to the technical field of signal processing, and provides a characteristic parameter extraction method and a characteristic parameter extraction system based on an expanded field of a magneto-cardiogram, wherein a two-dimensional isomagnetic map is constructed by combining magnetic field intensity and channel positions acquired by each channel based on a magneto-cardiogram data set, and a current density map is obtained by calculation based on the two-dimensional isomagnetic map; constructing a rotation field, a gradient field and a divergence field based on the current density map; singular value decomposition is carried out in a rotation field, a gradient field and a divergence field to obtain SVD characteristic parameters. Compared with the prior art, the method and the system of the invention are more efficient, fully excavate gradient, rotation and divergence information contained in the current density map, have clear physical meaning of parameters and have important contribution to extracting the characteristic parameters in the disease auxiliary detection model.
Description
Technical Field
The invention belongs to the technical field of signal processing, and particularly relates to a characteristic parameter extraction method and system based on an expanded field of a magneto-cardiogram current density map.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
The Magnetocardiogram (MCG) is a functional diagnosis technology for detecting the change of a spatial magnetic field caused by the volume current generated by the ion activity in myocardial cells, and the MCG is not interfered by human tissues, so that the magnetocardiogram signals and the change rules thereof can be clearly displayed, and more accurate auxiliary detection is provided for heart diseases.
The sensitivity and specificity of magnetocardiography for cardiovascular disease diagnosis depends on the effective utilization of the data. Characteristic parameters extracted from conventional magnetocardiography are currently used for data of magnetocardiography, such as: time change and amplitude change information are extracted from a one-dimensional butterfly graph, position and direction information of the positive electrode and the negative electrode are extracted from a two-dimensional isomagnetic graph, and information such as the size, the position and the angle of a maximum current vector and a total current vector are extracted from a current density graph. At present, two types of characteristics (maximum current vector and total current vector) are mainly extracted from a current density diagram, the mining of vector information in the current density diagram is single, the efficacy of identifying diseases is limited, and missed diagnosis and misdiagnosis are easy to occur.
Disclosure of Invention
In order to solve at least one technical problem in the background art, the invention provides a characteristic parameter extraction method and a characteristic parameter extraction system based on an expanded field of a magneto-cardiogram flow density map, which can fully embody rich information reflected by the magneto-cardiogram through extracting signals of a rotation field, a gradient field and a divergence field on the basis of the magneto-cardiogram flow density map, and has clear physical meaning of indexes.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
the first aspect of the invention provides a characteristic parameter extraction method based on an expanded field of a magneto-cardiogram current density map, which comprises the following steps:
acquiring a magnetocardiogram data set;
based on the magnetocardiogram data set, combining the magnetic field intensity and the channel position obtained by each channel to construct a two-dimensional isomagnetogram, and calculating based on the two-dimensional isomagnetogram to obtain a current density chart;
constructing a rotation field, a gradient field and a divergence field based on the current density map;
singular value decomposition is carried out in a rotation field, a divergence field and a gradient field to obtain SVD characteristic parameters.
Further, the magnetocardiogram dataset is acquired by a multichannel optical pump magnetometer based on spin-free relaxation effects.
Further, after acquiring the magnetocardiogram data set, preprocessing the magnetocardiogram data set to obtain magnetocardiogram data sets of a plurality of wave bands, including:
the original magnetocardiogram signals are filtered and noise reduced through a high-pass filter, a low-pass filter and a power frequency wave trap, R wave positioning is carried out on the magnetocardiogram after noise reduction, a magnetocardiogram beat is obtained according to the R wave position, and a one-dimensional butterfly image is obtained after superposition and average; and (3) carrying out band segmentation on the one-dimensional butterfly graph to obtain a P wave, QRS wave, ST segment and T wave band magnetocardiogram data set.
Further, the constructing a curl field, a gradient field, and a divergence field based on the current density map includes:
calculating partial derivatives in definition by using finite difference according to a rotation formula and a gradient formula, calculating a rotation value and a gradient value of current amplitude change of each position in a current density diagram, and drawing a corresponding rotation field and a gradient field; and calculating the partial derivative in the definition of the gradient field by using finite difference according to a divergence formula on the basis of the gradient field, and calculating a divergence value to draw the divergence field.
Further, the method for calculating the partial derivative in the corresponding formula by using the finite difference comprises the following steps: for the internal data points, the partial derivatives are calculated using the center differential, and for the data points along the edges, the partial derivatives are calculated using the single-sided differential.
Further, the singular value decomposition is performed in the rotation field, the divergence field and the gradient field to obtain the SVD characteristic parameters, which includes:
acquiring square matrix data according to a rotation field, a gradient field and a divergence field at a certain moment, performing singular value decomposition on the square matrix data, performing normalization processing on the decomposed singular values, and selecting normalized 2,3,4 and 5 singular values as features; and selecting the first N normalized features to calculate the average value, standard deviation and shannon entropy of the features.
Further, the SVD class feature parameters include: the method comprises the steps of (1) 2 nd of N normalized singular values after the field SVD decomposition, 3 rd of N normalized singular values after the field SVD decomposition, 4 th of N normalized singular values after the field SVD decomposition, 5 th of N normalized singular values after the field SVD decomposition, an average value of N normalized singular values after the field SVD decomposition, a standard deviation of N normalized singular values after the field SVD decomposition and Shannon entropy of N singular values after the field SVD decomposition.
The second aspect of the present invention provides a feature parameter extraction system based on an expanded field of a magneto-cardiogram current density map, comprising:
a data acquisition module for acquiring a magnetocardiogram dataset;
the current density map calculation module is used for constructing a two-dimensional isomagnetic map based on the magnetocardiogram data set and combining the magnetic field intensity and the channel position acquired by each channel, and calculating to obtain a current density map based on the two-dimensional isomagnetic map;
an extended field construction module for constructing a curl field, a gradient field, and a divergence field based on the current density map;
and the characteristic parameter extraction module is used for carrying out singular value decomposition in a rotation field, a divergence field and a gradient field to obtain SVD characteristic parameters.
Further, in the extended field construction module, the constructing a curl field, a gradient field, and a divergence field based on the current density map includes:
calculating partial derivatives in definition by using finite difference according to a rotation formula and a gradient formula, calculating a rotation value and a gradient value of current amplitude change of each position in a current density diagram, and drawing a corresponding rotation field and a gradient field; and calculating the partial derivative in the definition of the gradient field by using finite difference according to a divergence formula on the basis of the gradient field, and calculating a divergence value to draw the divergence field.
Further, the method for calculating the partial derivative in the corresponding formula by using the finite difference comprises the following steps: for the internal data points, the partial derivatives are calculated using the center differential, and for the data points along the edges, the partial derivatives are calculated using the single-sided differential.
Compared with the prior art, the invention has the beneficial effects that:
1. according to the invention, a rotation field, a gradient field and a divergence field are expanded according to the magnetocardiogram two-dimensional current density map, the three expansion fields show the rotation value, the divergence value and the gradient value change information of current vectors at each position in the current density map, and the abundant electrophysiological information of the heart contained in the magnetocardiogram is fully embodied.
2. According to the invention, SVD characteristic parameters are extracted according to the expanded fields of the magnetocardiogram two-dimensional current density map, so that the extraction of important cardiac electrophysiology information contained in the three expanded fields is realized, the physical meaning of the extracted characteristic parameters is clear, the anti-interference capability is strong, the authenticity of magnetocardiogram data can be reflected, and the method has important contribution to an auxiliary heart disease detection model.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention.
FIG. 1 is a flow chart of a method for extracting characteristic parameters based on an expanded field of a magneto-cardiogram current density map according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a feature parameter extraction structure based on an expanded field of a magnetic core current density map according to an embodiment of the present invention.
Detailed Description
The invention will be further described with reference to the drawings and examples.
It should be noted that the following detailed description is illustrative and is intended to provide further explanation of the invention. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the present invention. As used herein, the singular is also intended to include the plural unless the context clearly indicates otherwise, and furthermore, it is to be understood that the terms "comprises" and/or "comprising" when used in this specification are taken to specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof.
Interpretation of the terms
Magnetocardiogram: the magnetocardiogram is used as a noninvasive, non-radiative and non-contact functional diagnosis technology, and can clearly show the magnetocardiogram signals and the change rules thereof by utilizing the characteristic of magnetic transparency of human bodies, thus having certain advantages for coronary artery stenosis detection.
The magneto-cardiogram instrument of the optical pump magnetometer (optically pumped magnetometer, OPM) used by the invention is a novel weak magnetic sensing technology developed based on Spin-Exchange Relaxation-Free (SERF) theory, and has the advantages of high sensitivity, no need of refrigeration, stable signal, no need of special magnetic shielding room and the like. Is superior to the SQUID magnetometer used in the past.
Preprocessing a magnetocardiogram data set acquired by a multichannel magnetocardiogram based on SERF effect, and segmenting wave bands to acquire P wave, QRS wave, ST wave and T wave band magnetocardiogram data sets; based on the preprocessed magnetocardiogram data set, constructing a two-dimensional isomagnetogram by combining the magnetic field intensity and the channel position acquired by each channel, and calculating a current density map; calculating the rotation value and the gradient value of the vector signal of each position in the current density diagram to construct a rotation field and a gradient field, and calculating the divergence value of each position in the gradient field to construct a divergence field; and further performing Singular Value Decomposition (SVD) in a rotation field, a divergence field and a gradient field to obtain SVD characteristic parameters.
Compared with the prior art, the method and the system of the invention are more efficient, fully excavate gradient, rotation and divergence information contained in the current density map, have clear physical meaning of parameters and strong anti-interference capability, can better embody the authenticity of the magnetocardiogram data, and have important contribution to extracting the characteristic parameters in the disease auxiliary detection model.
Example 1
As shown in fig. 1, the embodiment provides a characteristic parameter extraction method based on an expanded field of a magnetic core current density map, which includes the following steps:
s101: acquiring a magnetocardiogram data set;
in this embodiment, the magnetocardiogram dataset is obtained by a multichannel optical pump magnetometer magnetocardiogram based on the SERF effect.
The advantage is that the ultra-high sensitivity extremely weak magnetic detection technology based on the SERF effect has the advantages of small volume, light weight, high sensitivity, no need of refrigeration, wearable performance and the like, and the detection process can be completed in a short time, so that the method has the advantages of no wound, no noise and no patient contact, and is beneficial to filling the blank field of heart disease diagnosis.
Preprocessing the magnetocardiogram data set to obtain magnetocardiogram data sets of a plurality of wave bands;
the preprocessing of the magnetocardiogram data set specifically comprises the following steps: the original magnetocardiogram signals are filtered and noise reduced through a high-pass filter, a low-pass filter and a power frequency wave trap, R wave positioning is carried out on the magnetocardiogram after noise reduction, a magnetocardiogram beat is obtained according to the R wave position, and a one-dimensional butterfly image is obtained after superposition and average; and (3) carrying out band segmentation on the one-dimensional butterfly graph to obtain a P wave, QRS wave, ST segment and T wave band magnetocardiogram data set.
S102: based on the preprocessed magnetocardiogram data set, combining the magnetic field intensity and the channel position acquired by each channel, constructing a two-dimensional isomagnetogram, and calculating based on the two-dimensional isomagnetogram to obtain a current density diagram.
Specifically, according to the magnetic field intensity and the channel position obtained by each channel, a two-dimensional isomagnetic diagram is drawn, and a current density formula is adopted:calculating the current density of all points in the two-dimensional isomagnetic mapJWhereinEThe magnetic field strength at a certain point (x, y) is indicated.
S103: constructing a rotation field, a gradient field and a divergence field based on the current density map;
specifically, according to the rotation formula curl (F) = dFy/dx-dFx/dy, where F represents a current vector at a point (x, y) in the current density map, dFy/dx represents a partial derivative of the y component in the current vector F with respect to the x-axis direction, and dFx/dy represents a partial derivative of the x component in the current vector F with respect to the y-axis direction. Calculating the partial derivatives in its definition using finite differences, calculating the partial derivatives using center differences for internal data points, and calculating the partial derivatives using single-sided (forward) differences for data points along the edges; finally, the rotation field is plotted according to the rotation value calculated at each position.
According to the gradient formulaWherein F represents the current vector of a point (x, y) in the current density map,/->Representing a functionF partial derivative of x->Representing the partial derivative of the function F with respect to y, < >>Is the unit vector of the x-axis,>is the unit vector of the y-axis. The partial derivatives in its definition are calculated using finite differences. For the internal data points, the partial derivatives are calculated using the center difference. For data points along the edges, the partial derivatives are calculated using single-sided (forward) differential; finally, the gradient field is plotted from the gradient values calculated for each location.
According to the divergence formula div (f) = dfx/dx+ dfy/dy, where f represents the gradient vector at a point (x, y) in the two-dimensional gradient field, dfx/dx represents the partial derivative of the x-axis vector of f with respect to x and dfy/dy represents the partial derivative of the y-axis vector of f with respect to y. The partial derivatives in its definition are calculated using finite differences. For the internal data points, the partial derivatives are calculated using the center difference. For data points along the edges, the partial derivatives are calculated using single-sided (forward) differential; finally, the divergence field is plotted from the calculated divergence value for each location.
S104: singular value decomposition is carried out in a rotation field, a divergence field and a gradient field to obtain SVD characteristic parameters.
In this embodiment, the method for obtaining the SVD class feature parameter includes: acquiring square matrix data according to a rotation field/gradient field/divergence field at a certain moment, performing singular value decomposition on the array data, performing normalization processing on the decomposed singular values, and selecting normalized 2,3,4 and 5 singular values as features; and selecting the average value, standard deviation and shannon entropy of the first N normalized feature calculators as features.
The method specifically comprises the following steps:
the method comprises the steps of (1) 2 nd of N normalized singular values after the field SVD decomposition, 3 rd of N normalized singular values after the field SVD decomposition, 4 th of N normalized singular values after the field SVD decomposition, 5 th of N normalized singular values after the field SVD decomposition, an average value of N normalized singular values after the field SVD decomposition, a standard deviation of N normalized singular values after the field SVD decomposition and Shannon entropy of N singular values after the field SVD decomposition.
In this embodiment, N has a value of 6.
The scheme has the advantages that gradient, rotation and divergence information contained in the current density diagram is fully mined, the physical significance of parameters is clear, the signal after singular value decomposition has strong anti-interference capability, the authenticity of magnetocardiogram data can be reflected, and the method has important contribution to extracting characteristic parameters in an auxiliary disease detection model.
Example two
As shown in fig. 2, the present embodiment provides a characteristic parameter extraction system based on an expanded field of a magnetic core current density map, including:
a data acquisition module for acquiring a magnetocardiogram dataset;
the current density map calculation module is used for constructing a two-dimensional isomagnetic map based on the magnetocardiogram data set and combining the magnetic field intensity and the channel position acquired by each channel, and calculating to obtain a current density map based on the two-dimensional isomagnetic map;
an extended field construction module for constructing a curl field, a gradient field, and a divergence field based on the current density map;
and the characteristic parameter extraction module is used for carrying out singular value decomposition in a rotation field, a divergence field and a gradient field to obtain SVD characteristic parameters.
Further, in the extended field construction module, the constructing a curl field, a gradient field, and a divergence field based on the current density map includes:
calculating partial derivatives in definition by using finite difference according to a rotation formula and a gradient formula, calculating a rotation value and a gradient value of current amplitude change of each position in a current density diagram, and drawing a corresponding rotation field and a gradient field; and calculating the partial derivative in the definition of the gradient field by using finite difference according to a divergence formula on the basis of the gradient field, and calculating a divergence value to draw the divergence field.
Further, the method for calculating the partial derivative in the corresponding formula by using the finite difference comprises the following steps: for the internal data points, the partial derivatives are calculated using the center differential, and for the data points along the edges, the partial derivatives are calculated using the single-sided differential.
The method has the advantages that gradient, rotation and divergence information contained in the current density diagram is fully mined, the physical meaning of parameters is clear, and the method has important contribution to extracting characteristic parameters in an auxiliary disease detection model.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. The characteristic parameter extraction method based on the expanded field of the magneto-cardiogram current density map is characterized by comprising the following steps of:
acquiring a magnetocardiogram data set;
based on the magnetocardiogram data set, combining the magnetic field intensity and the channel position obtained by each channel to construct a two-dimensional isomagnetogram, and calculating based on the two-dimensional isomagnetogram to obtain a current density chart;
constructing a rotation field, a gradient field and a divergence field based on the current density map;
singular value decomposition is carried out in a rotation field, a divergence field and a gradient field to obtain SVD characteristic parameters.
2. The method for extracting characteristic parameters based on an expanded field of a magneto-cardiogram according to claim 1, wherein the magneto-cardiogram data set is acquired by a multi-channel optical pump magnetometer magneto-cardiogram based on a SERF effect.
3. The method for extracting the characteristic parameters of the extended field based on the magneto-cardiogram density map according to claim 1, wherein after obtaining the magneto-cardiogram data set, preprocessing the magneto-cardiogram data set to obtain a plurality of wave band magneto-cardiogram data sets, comprising:
the original magnetocardiogram signals are filtered and noise reduced through a high-pass filter, a low-pass filter and a power frequency wave trap, R wave positioning is carried out on the magnetocardiogram after noise reduction, a magnetocardiogram beat is obtained according to the R wave position, and a one-dimensional butterfly image is obtained after superposition and average; and (3) carrying out band segmentation on the one-dimensional butterfly graph to obtain a P wave, QRS wave, ST segment and T wave band magnetocardiogram data set.
4. The method for extracting characteristic parameters of an extended field based on a magneto-cardiogram current density map as set forth in claim 1, wherein the constructing a curl field, a gradient field, and a divergence field based on a current density map includes:
calculating partial derivatives in definition by using finite difference according to a rotation formula and a gradient formula, calculating a rotation value and a gradient value of current amplitude change of each position in a current density diagram, and drawing a corresponding rotation field and a gradient field; and calculating the partial derivative in the definition of the gradient field by using finite difference according to a divergence formula on the basis of the gradient field, and calculating a divergence value to draw the divergence field.
5. The method for extracting feature parameters of an extended field based on a magnetic cardiogram current density map according to claim 4, wherein the method for calculating partial derivatives in the corresponding formula using finite difference calculation is as follows: for the internal data points, the partial derivatives are calculated using the center differential, and for the data points along the edges, the partial derivatives are calculated using the single-sided differential.
6. The method for extracting the characteristic parameters based on the expanded field of the magneto-cardiogram density map as claimed in claim 1, wherein the singular value decomposition is performed in the rotation field, the divergence field and the gradient field to obtain the SVD characteristic parameters, comprising:
acquiring square matrix data according to a rotation field, a gradient field and a divergence field at a certain moment, performing singular value decomposition on the square matrix data, performing normalization processing on the decomposed singular values, and selecting normalized 2,3,4 and 5 singular values as features; and selecting the first N normalized features to calculate the average value, standard deviation and shannon entropy of the features.
7. The method for extracting feature parameters of an extended field based on a magnetic cardiogram current density map according to claim 1, wherein the SVD-type feature parameters include: the method comprises the steps of (1) 2 nd of N normalized singular values after the field SVD decomposition, 3 rd of N normalized singular values after the field SVD decomposition, 4 th of N normalized singular values after the field SVD decomposition, 5 th of N normalized singular values after the field SVD decomposition, an average value of N normalized singular values after the field SVD decomposition, a standard deviation of N normalized singular values after the field SVD decomposition and Shannon entropy of N singular values after the field SVD decomposition.
8. Characteristic parameter extraction system based on heart magnetic current density map extension field, characterized by comprising:
a data acquisition module for acquiring a magnetocardiogram dataset;
the current density map calculation module is used for constructing a two-dimensional isomagnetic map based on the magnetocardiogram data set and combining the magnetic field intensity and the channel position acquired by each channel, and calculating to obtain a current density map based on the two-dimensional isomagnetic map;
an extended field construction module for constructing a curl field, a gradient field, and a divergence field based on the current density map;
and the characteristic parameter extraction module is used for carrying out singular value decomposition in a rotation field, a divergence field and a gradient field to obtain SVD characteristic parameters.
9. The system for extracting characteristic parameters of an extended field based on a magneto-cardiogram current density map according to claim 8, wherein in the extended field construction module, the constructing a curl field, a gradient field, and a divergence field based on a current density map comprises:
calculating partial derivatives in definition by using finite difference according to a rotation formula and a gradient formula, calculating a rotation value and a gradient value of current amplitude change of each position in a current density diagram, and drawing a corresponding rotation field and a gradient field; and calculating the partial derivative in the definition of the gradient field by using finite difference according to a divergence formula on the basis of the gradient field, and calculating a divergence value to draw the divergence field.
10. The system for extracting characteristic parameters of an extended field based on a magnetic core current density map according to claim 9, wherein in the extended field construction module, the method for calculating the partial derivative in the corresponding formula by using finite difference is as follows: for the internal data points, the partial derivatives are calculated using the center differential, and for the data points along the edges, the partial derivatives are calculated using the single-sided differential.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311353583.1A CN117084684B (en) | 2023-10-19 | 2023-10-19 | Characteristic parameter extraction method and system based on electrocardio current density map extension field |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311353583.1A CN117084684B (en) | 2023-10-19 | 2023-10-19 | Characteristic parameter extraction method and system based on electrocardio current density map extension field |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117084684A true CN117084684A (en) | 2023-11-21 |
| CN117084684B CN117084684B (en) | 2024-02-02 |
Family
ID=88783712
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311353583.1A Active CN117084684B (en) | 2023-10-19 | 2023-10-19 | Characteristic parameter extraction method and system based on electrocardio current density map extension field |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117084684B (en) |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2001020477A2 (en) * | 1999-08-28 | 2001-03-22 | Squid Ag | Computer-based method for automatically processing data, especially magnetocardiographic data, of biomagnetic fields |
| JP2006075403A (en) * | 2004-09-10 | 2006-03-23 | Japan Science & Technology Agency | Cardiac magnetic field diagnostic apparatus and method of actuating the same |
| US20110018540A1 (en) * | 2008-03-28 | 2011-01-27 | Hitachi Medical Corportion | Method of calculating coil pattern, and gradient magnetic field coil. |
| JP2013232128A (en) * | 2012-05-01 | 2013-11-14 | Link Research Kk | Electromagnetic field analysis, wave optical calculation program, and apparatus using electromagnetic field analysis and wave optical calculation program |
| CN105139423A (en) * | 2015-08-18 | 2015-12-09 | 上海交通大学 | Motion feature extraction method and system based on curl and divergence |
| US20170281086A1 (en) * | 2016-04-01 | 2017-10-05 | Thomas Alan Donaldson | Sensors to determine neuronal activity of an organism to facilitate a human-machine interface |
| CN108245152A (en) * | 2018-01-11 | 2018-07-06 | 中国科学院上海微系统与信息技术研究所 | A kind of myocardial ischemia characteristic parameter extraction method and system, storage medium and terminal |
| CN108281184A (en) * | 2018-02-01 | 2018-07-13 | 中国科学院上海微系统与信息技术研究所 | Myocardial ischemia based on machine learning examines method, storage medium and electronic equipment in advance |
| CN110074774A (en) * | 2019-04-28 | 2019-08-02 | 漫迪医疗仪器（上海）有限公司 | Analysis method, system, medium and the terminal of cardiac septum exception based on magnetocardiogram |
| CN111783344A (en) * | 2020-07-07 | 2020-10-16 | 天津大学 | Method for simulation analysis of cable defects based on magnetic field distribution characteristics |
| CN112801853A (en) * | 2021-02-09 | 2021-05-14 | 中国人民解放军国防科技大学 | Parallel acceleration method for extracting hyperspectral image features based on NAPC (non-uniform resource locator) |
| US20220034983A1 (en) * | 2020-07-29 | 2022-02-03 | Synaptive Medical Inc. | System and method to improve performance of asymmetrical gradient coils by allowing a uniform offset field |
| CN114170201A (en) * | 2021-12-08 | 2022-03-11 | 山东大学 | Non-contact respiration rate detection method and system based on edge optical flow information |
| CN115758730A (en) * | 2022-11-18 | 2023-03-07 | 国网山东省电力公司威海供电公司 | Aging detection method and device for self-melting type cable intermediate joint |
-
2023
- 2023-10-19 CN CN202311353583.1A patent/CN117084684B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2001020477A2 (en) * | 1999-08-28 | 2001-03-22 | Squid Ag | Computer-based method for automatically processing data, especially magnetocardiographic data, of biomagnetic fields |
| JP2006075403A (en) * | 2004-09-10 | 2006-03-23 | Japan Science & Technology Agency | Cardiac magnetic field diagnostic apparatus and method of actuating the same |
| US20110018540A1 (en) * | 2008-03-28 | 2011-01-27 | Hitachi Medical Corportion | Method of calculating coil pattern, and gradient magnetic field coil. |
| JP2013232128A (en) * | 2012-05-01 | 2013-11-14 | Link Research Kk | Electromagnetic field analysis, wave optical calculation program, and apparatus using electromagnetic field analysis and wave optical calculation program |
| CN105139423A (en) * | 2015-08-18 | 2015-12-09 | 上海交通大学 | Motion feature extraction method and system based on curl and divergence |
| US20170281086A1 (en) * | 2016-04-01 | 2017-10-05 | Thomas Alan Donaldson | Sensors to determine neuronal activity of an organism to facilitate a human-machine interface |
| CN108245152A (en) * | 2018-01-11 | 2018-07-06 | 中国科学院上海微系统与信息技术研究所 | A kind of myocardial ischemia characteristic parameter extraction method and system, storage medium and terminal |
| CN108281184A (en) * | 2018-02-01 | 2018-07-13 | 中国科学院上海微系统与信息技术研究所 | Myocardial ischemia based on machine learning examines method, storage medium and electronic equipment in advance |
| CN110074774A (en) * | 2019-04-28 | 2019-08-02 | 漫迪医疗仪器（上海）有限公司 | Analysis method, system, medium and the terminal of cardiac septum exception based on magnetocardiogram |
| CN111783344A (en) * | 2020-07-07 | 2020-10-16 | 天津大学 | Method for simulation analysis of cable defects based on magnetic field distribution characteristics |
| US20220034983A1 (en) * | 2020-07-29 | 2022-02-03 | Synaptive Medical Inc. | System and method to improve performance of asymmetrical gradient coils by allowing a uniform offset field |
| CN112801853A (en) * | 2021-02-09 | 2021-05-14 | 中国人民解放军国防科技大学 | Parallel acceleration method for extracting hyperspectral image features based on NAPC (non-uniform resource locator) |
| CN114170201A (en) * | 2021-12-08 | 2022-03-11 | 山东大学 | Non-contact respiration rate detection method and system based on edge optical flow information |
| CN115758730A (en) * | 2022-11-18 | 2023-03-07 | 国网山东省电力公司威海供电公司 | Aging detection method and device for self-melting type cable intermediate joint |
Non-Patent Citations (2)
| Title |
|---|
| 张光: "基于磁梯度张量SVD的磁性目标识别方法", 兵工自动化, vol. 41, no. 5, pages 20 - 24 * |
| 赵永鹏: "基于机器学习的心磁信号研究", 中国优秀硕士学位论文全文数据库（电子期刊）, pages 062 - 4 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117084684B (en) | 2024-02-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108245152B (en) | Myocardial ischemia characteristic parameter extraction method and system, storage medium and terminal | |
| CN102973253B (en) | Method and system for monitoring human physiological indexes by using visual information | |
| CN110353665A (en) | ECG signal signature waveform detection method is singly led based on improved one-dimensional U-net | |
| CN110074774B (en) | Analysis method, system, medium and terminal for heart ventricular septal abnormality based on magnetocardiogram | |
| CN109919948A (en) | Nasopharyngeal Carcinoma Lesions parted pattern training method and dividing method based on deep learning | |
| CN112754431A (en) | Respiration and heartbeat monitoring system based on millimeter wave radar and lightweight neural network | |
| CN108577825B (en) | Myocardial ischemia lesion position positioning method and system, storage medium and terminal | |
| CN113951900B (en) | Motor imagery intention recognition method based on multi-mode signals | |
| CN111481192A (en) | Electrocardiosignal R wave detection method based on improved U-Net | |
| CN109833031A (en) | It is a kind of that the sleep mode automatically method by stages of more physiological signals is utilized based on LSTM | |
| CN113239755A (en) | Medical hyperspectral image classification method based on space-spectrum fusion deep learning | |
| CN101919704A (en) | Heart sound signal positioning and segmenting method | |
| CN117814805B (en) | Intelligent processing method for data of clinical care equipment | |
| Torti et al. | Custom FPGA processing for real-time fetal ECG extraction and identification | |
| CN117084684B (en) | Characteristic parameter extraction method and system based on electrocardio current density map extension field | |
| Xu et al. | Application of artificial intelligence technology in medical imaging | |
| CN114065825A (en) | Brain magnetic MEG source positioning method based on structural similarity | |
| CN115624322B (en) | Non-contact physiological signal detection method and system based on efficient space-time modeling | |
| Kishore et al. | An innovative machine learning approach for classifying ECG signals in healthcare devices | |
| US20230404414A1 (en) | AI-enhanced Wearable Photo-Electro-Tonoarteriography (PETAG) Method And Apparatus | |
| CN112562031B (en) | Nuclear magnetic resonance image clustering method based on sample distance reconstruction | |
| CN116098633A (en) | Minimally invasive intervention brain-computer interface ideation brain control system for consciousness disturbance | |
| Yang et al. | Electrocardiogram classification of lead convolutional neural network based on fuzzy algorithm | |
| Yang et al. | A lightweight fully convolutional network for cardiac MRI segmentation | |
| Nayak et al. | A precise ECG QRS complex detector using a WOA optimized fractional-order digital differentiator |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |