CN117100276B - Cardiac function detection system, computer storage medium and terminal - Google Patents
Cardiac function detection system, computer storage medium and terminal Download PDFInfo
- Publication number
- CN117100276B CN117100276B CN202311375785.6A CN202311375785A CN117100276B CN 117100276 B CN117100276 B CN 117100276B CN 202311375785 A CN202311375785 A CN 202311375785A CN 117100276 B CN117100276 B CN 117100276B
- Authority
- CN
- China
- Prior art keywords
- wave
- field
- dimensional
- histogram
- value
- 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.)
- Active
Links
- 230000004217 heart function Effects 0.000 title claims abstract description 52
- 238000001514 detection method Methods 0.000 title claims abstract description 21
- 238000000034 method Methods 0.000 claims abstract description 38
- 238000000605 extraction Methods 0.000 claims abstract description 22
- 238000012216 screening Methods 0.000 claims abstract description 8
- 238000010586 diagram Methods 0.000 claims description 43
- 238000004891 communication Methods 0.000 claims description 23
- 230000005484 gravity Effects 0.000 claims description 16
- 230000001052 transient effect Effects 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 12
- 238000007781 pre-processing Methods 0.000 claims description 8
- 238000012163 sequencing technique Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 abstract description 7
- 230000035945 sensitivity Effects 0.000 abstract description 6
- 206010019280 Heart failures Diseases 0.000 description 6
- 239000000284 extract Substances 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 239000008280 blood Substances 0.000 description 3
- 210000004369 blood Anatomy 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000009467 reduction Effects 0.000 description 3
- 208000024891 symptom Diseases 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 208000027418 Wounds and injury Diseases 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 2
- 239000000090 biomarker Substances 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000000747 cardiac effect Effects 0.000 description 2
- 230000006378 damage Effects 0.000 description 2
- 238000000354 decomposition reaction Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 208000014674 injury Diseases 0.000 description 2
- 230000009545 invasion Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000001575 pathological effect Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 208000000059 Dyspnea Diseases 0.000 description 1
- 206010013975 Dyspnoeas Diseases 0.000 description 1
- 206010030113 Oedema Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000017531 blood circulation Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000000546 chi-square test Methods 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000002592 echocardiography Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 206010016256 fatigue Diseases 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000002427 irreversible effect Effects 0.000 description 1
- 230000003902 lesion Effects 0.000 description 1
- 208000031225 myocardial ischemia Diseases 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000004393 prognosis Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000009863 secondary prevention 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
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
- A61B5/346—Analysis of electrocardiograms
- A61B5/349—Detecting specific parameters of the electrocardiograph cycle
- A61B5/353—Detecting P-waves
-
- 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
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
- A61B5/346—Analysis of electrocardiograms
- A61B5/349—Detecting specific parameters of the electrocardiograph cycle
- A61B5/355—Detecting T-waves
-
- 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
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
- A61B5/346—Analysis of electrocardiograms
- A61B5/349—Detecting specific parameters of the electrocardiograph cycle
- A61B5/358—Detecting ST segments
-
- 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
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
- A61B5/346—Analysis of electrocardiograms
- A61B5/349—Detecting specific parameters of the electrocardiograph cycle
- A61B5/366—Detecting abnormal QRS complex, e.g. widening
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/30—Assessment of water resources
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Cardiology (AREA)
- Heart & Thoracic Surgery (AREA)
- Molecular Biology (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- Biophysics (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Image Analysis (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention discloses a heart function detection system, a computer storage medium and a terminal, and relates to the technical field of image processing. The heart function detection system comprises a data acquisition module: the method comprises the steps of acquiring a one-dimensional butterfly graph corresponding to a P wave, a QRS wave, a ST wave and a T wave band; and a two-dimensional drawing module: the method comprises the steps of respectively obtaining a two-dimensional isomagnetic map, a current density map, a gradient field, a rotation field and a divergence field corresponding to a P wave, a QRS wave, a ST wave and a T wave band; and the feature extraction module is used for: for extracting characteristic parameters related to cardiac function; and a feature screening module: the method comprises the steps of sorting, judging linear cross correlation and selecting quantity of extracted characteristic parameters to obtain a characteristic subset; and a judgment and comparison module: and judging whether the heart function of the tested person is normal according to the feature subset. The invention has high sensitivity and accuracy and can save manpower and time cost.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a heart function detection system, a computer storage medium and a terminal.
Background
Cardiac insufficiency is becoming an important cause of death in China and worldwide, and constitutes a major challenge for human health, with myocardial ischemia being the leading cause of heart pump failure. Cardiac insufficiency is the inability of the heart to pump blood effectively to meet the needs of the body, thus presenting clinical manifestations of fatigue, dyspnea, edema, etc. The heart failure has no obvious clinical symptoms in early stage, is easy to ignore, once symptoms appear, the heart failure progress is irreversible and the prognosis is extremely bad, and compared with the patients with symptoms, the early intervention of the patients has more obvious clinical value for promoting the heart to reconstruct. Echocardiography is currently the most effective examination means, but because of the long examination time and the need for direct contact with the skin of the patient, it is difficult to popularize the means as a conventional screening means in the secondary prevention of cardiac insufficiency.
At present, the detection of early cardiac insufficiency mainly comprises source data from a clinical risk factor model, an electrocardiogram parameter system and a biomarker, and parameters of the clinical risk factor and blood biomarker model are derived from medical information and a blood sample which are easy to obtain, but satisfactory sensitivity still cannot be achieved after optimization treatment and combination; in addition, the characteristics of the electrocardiogram source are easily influenced by the environment and the individual, and the problems of signal attenuation, waveform distortion and the like exist, so that the accuracy is poor. The above readily available parameters and data do not provide satisfactory sensitivity and accuracy.
Disclosure of Invention
The invention provides a heart function detection system, a computer storage medium and a terminal, which have high sensitivity and high accuracy and can save manpower and time cost.
In order to solve the technical problems, the invention provides the following technical scheme:
a cardiac function detection system, comprising:
and a data acquisition module: the method comprises the steps of obtaining initial data of a magnetocardiogram, preprocessing the initial data of the magnetocardiogram, and obtaining one-dimensional butterfly images corresponding to P wave, QRS wave, ST wave and T wave bands;
and a two-dimensional drawing module: the method comprises the steps of respectively acquiring a two-dimensional isomagnetic map, a current density map, a gradient field, a rotation field and a divergence field corresponding to a P wave, a QRS wave, an ST wave and a T wave band based on the acquired one-dimensional butterfly map and the positions of each magnetocardiogram channel;
and the feature extraction module is used for: the method is used for extracting characteristic parameters related to cardiac functions from a one-dimensional butterfly graph, a two-dimensional isomagnetic graph, a current density graph, a gradient field, a rotation field and a divergence field corresponding to P wave, QRS wave, ST wave and T wave bands;
and a feature screening module: the method comprises the steps of sorting, judging linear cross correlation and selecting quantity of extracted characteristic parameters to obtain a characteristic subset;
and a judgment and comparison module: judging whether the heart function of the tested person is normal according to the feature subset;
Wherein the characteristic parameters include: waveform type characteristic parameters, cross-correlation type characteristic parameters, LBP type characteristic parameters, image shape type characteristic, image pixel type characteristic, fine granularity dynamic characteristic, dynamic combination characteristic, transient combination characteristic, SVD type characteristic parameters and main field type characteristic parameters.
Further, the two-dimensional drawing module includes:
a first two-dimensional drawing module: the method comprises the steps of respectively drawing two-dimensional isomagnetic graphs corresponding to P wave, QRS wave, ST wave and T wave bands based on the obtained one-dimensional butterfly graph and the positions of each magnetocardiogram, and respectively calculating current density graphs corresponding to the P wave, the QRS wave, the ST wave and the T wave bands based on the two-dimensional isomagnetic graphs;
and a second two-dimensional drawing module: the gradient value and the rotation value of the vector signal at each position in the current density diagram corresponding to the P wave, the QRS wave, the ST wave and the T wave band are respectively calculated according to the gradient formula and the rotation formula, and the gradient field and the rotation field corresponding to the P wave, the QRS wave, the ST wave and the T wave band are respectively drawn according to the gradient value and the rotation value;
and a third two-dimensional drawing module: the method is used for calculating and obtaining the divergence value of the vector signal of each position in the gradient fields corresponding to the P wave, the QRS wave, the ST wave and the T wave band according to the divergence formula, and drawing and obtaining the divergence fields corresponding to the P wave, the QRS wave, the ST wave and the T wave band according to the divergence value.
Further, the feature extraction module includes:
a first feature extraction module: the method is used for extracting waveform characteristic parameters and cross-correlation characteristic parameters from one-dimensional butterfly graphs corresponding to P wave, QRS wave, ST wave and T wave bands;
and a second feature extraction module: the method is used for extracting image shape type characteristics, image pixel type characteristics, LBP type characteristic parameters, fine granularity dynamic characteristics, dynamic combination characteristics and transient combination characteristics from two-dimensional isomagnetic diagrams and current density diagrams corresponding to P wave, QRS wave, ST wave and T wave bands;
and a third feature extraction module: the SVD type characteristic parameters and the main field type characteristic parameters are extracted from the gradient fields, the rotation fields and the divergence fields corresponding to the P wave, the QRS wave, the ST wave and the T wave bands.
Further, the feature subset includes:
the m-th histogram of Y coordinates of the barycenter position of positive field in the two-dimensional isomagnetogram corresponding to the QRS wave 1 M-th histogram of Y-coordinate of barycenter position of positive field in two-dimensional isomagnetogram with bin value corresponding to T wave 2 The ratio between the bin values, the mth of the histogram of the direction of the positive and negative value main field gravity center connecting line in the two-dimensional isomagnetic diagram corresponding to the QRS wave 3 M-th histogram of direction of positive and negative value main field gravity center connecting line in two-dimensional isomagnetic diagram with bin value corresponding to T wave 4 The ratio between the bin values, the m-th histogram of the angle of the maximum single-connected graph minimum Feret diameter relative to the horizontal axis of the image in the two-dimensional isomagnetic graph corresponding to the QRS wave 5 M-th histogram of angle of maximum single-connected graph minimum Feret diameter relative to image horizontal axis in two-dimensional isomagnetic graph with bin value corresponding to T wave 6 The ratio between the individual bin values;
the ratio between the maximum value of the positive field Y coordinate of the T2 point and the maximum value of the positive field Y coordinate of the T1 point in the two-dimensional isomagnetic map corresponding to the T wave;
the m-th of the histogram of the barycenter X coordinate in the gradient field corresponding to the QRS wave 7 Mth of histogram of barycenter X coordinate in gradient field corresponding to each bin value and T wave 8 The ratio between the individual bin values;
the m-th histogram of the proportion of pixels in the convex hull of the maximum single connected graph in the gradient field corresponding to the QRS wave 9 M-th histogram of proportion of pixels in convex hull region of maximum single-connected graph in gradient field corresponding to each bin value and T wave 10 The ratio between the individual bin values;
the m-th of the histogram of the rotation value at the maximum current vector in the rotation field corresponding to the P wave 11 Individual bin values and T-wave pairsMth of histogram of rotation values at maximum current vector in the applied rotation field 12 The ratio between the individual bin values;
the m-th of the total vector angle formed by the positive main field in the gradient field corresponding to the P wave 13 The m-th of the total vector angle of the positive principal field in the gradient field whose percentile corresponds to the T-wave 14 The ratio between percentiles;
the ratio of the fourth difference of the angle between the x axis of the maximum single communication graph and the long axis of the ellipse in the two-dimensional isomagnetic graph corresponding to the ST wave to the fourth difference of the angle between the x axis of the maximum single communication graph and the long axis of the ellipse in the two-dimensional isomagnetic graph corresponding to the T wave;
the m-th of the histogram of the Y coordinate of the maximum position of the negative rotation field in the rotation field corresponding to the ST wave 15 M-th of histogram of negative rotation field maximum value position Y coordinate in rotation field with bin value corresponding to T wave 16 A bin value;
the mth of the angle between the x-axis of the maximum single communication graph and the major axis of the ellipse in the rotation field corresponding to the ST-segment wave 17 Mth of angle between x-axis of maximum single-connected graph and major axis of ellipse in rotation field with percentile corresponding to T wave 18 A personal percentile;
the m-th of the histogram of vector magnitude of the negative divergence field maximum value pointing to the positive divergence maximum value in the corresponding divergence field of the ST segment wave 19 M-th of vector-sized histogram with negative divergence field maximum pointing to positive divergence maximum in divergence field with each bin value corresponding to T wave 20 The ratio between the individual bin values;
the mth of the histogram of the maximum gradient vector direction in the gradient field corresponding to the ST wave 21 Mth of histogram of maximum gradient vector direction in gradient field with each bin value corresponding to T wave 22 The ratio between the individual bin values;
the m-th of the histogram of the angle between the X-axis of the maximum single-connected graph and the major axis of the ellipse in the current density graph corresponding to the point from the start point to the peak point of the P wave 23 A bin value;
and the Renyi entropy of the X coordinate of the gravity center position of the negative rotation field in the rotation field corresponding to the vertex from the P wave starting point.
A computer storage medium storing a computer program which, when executed by a processor, implements a cardiac function detection method comprising:
acquiring initial data of a magnetocardiogram, preprocessing the initial data of the magnetocardiogram, and acquiring one-dimensional butterfly images corresponding to P wave, QRS wave, ST wave and T wave bands;
based on the obtained one-dimensional butterfly graph and the positions of each magnetocardiogram channel, respectively obtaining a two-dimensional isomagnetogram, a current density graph, a gradient field, a rotation field and a divergence field corresponding to a P wave, a QRS wave, a ST wave and a T wave band;
extracting characteristic parameters related to cardiac functions from a one-dimensional butterfly diagram, a two-dimensional isomagnetic diagram, a current density diagram, a gradient field, a rotation field and a divergence field corresponding to a P wave, a QRS wave, a ST wave and a T wave band;
Sequencing, linear cross-correlation judgment and quantity selection are carried out on the extracted characteristic parameters, so that a characteristic subset is obtained;
judging whether the heart function of the tested person is normal or not according to the feature subset;
wherein the characteristic parameters include: waveform type characteristic parameters, cross-correlation type characteristic parameters, LBP type characteristic parameters, image shape type characteristic, image pixel type characteristic, fine granularity dynamic characteristic, dynamic combination characteristic, transient combination characteristic, SVD type characteristic parameters and main field type characteristic parameters.
Further, the steps of respectively acquiring the two-dimensional isomagnetic map, the current density map, the gradient field, the rotation field and the divergence field corresponding to the P wave, the QRS wave, the ST wave and the T wave band based on the acquired one-dimensional butterfly map and the positions of each magnetocardiogram channel include:
respectively drawing two-dimensional isomagnetic maps corresponding to P wave, QRS wave, ST wave and T wave bands based on the obtained one-dimensional butterfly map and the positions of each magnetocardiogram channel, and respectively calculating current density maps corresponding to the P wave, the QRS wave, the ST wave and the T wave bands based on the two-dimensional isomagnetic maps;
respectively calculating a gradient value and a rotation value of a vector signal at each position in a current density diagram corresponding to the P wave, the QRS wave, the ST wave and the T wave band according to the gradient formula and the rotation formula, and respectively drawing a gradient field and a rotation field corresponding to the P wave, the QRS wave, the ST wave and the T wave band according to the gradient value and the rotation value;
Calculating and obtaining the divergence value of the vector signal of each position in the gradient fields corresponding to the P wave, the QRS wave, the ST wave and the T wave band according to the divergence formula, and drawing and obtaining the divergence fields corresponding to the P wave, the QRS wave, the ST wave and the T wave band according to the divergence value.
Further, the step of extracting the characteristic parameters related to the cardiac function from the one-dimensional butterfly graph, the two-dimensional isomagnetic graph, the current density graph, the gradient field, the rotation field and the divergence field corresponding to the P wave, the QRS wave, the ST wave and the T wave band comprises the following steps:
extracting waveform characteristic parameters and cross-correlation characteristic parameters from one-dimensional butterfly graphs corresponding to P wave, QRS wave, ST wave and T wave bands; extracting image shape type features, image pixel type features, LBP type feature parameters, fine granularity dynamic features, dynamic combination features and transient combination features from the two-dimensional isomagnetic map and the current density map;
SVD type characteristic parameters and main field type characteristic parameters are extracted from gradient fields, rotation fields and divergence fields corresponding to P wave, QRS wave, ST wave band and T wave band.
Further, the feature subset includes:
the m-th histogram of Y coordinates of the barycenter position of positive field in the two-dimensional isomagnetogram corresponding to the QRS wave 1 M-th histogram of Y-coordinate of barycenter position of positive field in two-dimensional isomagnetogram with bin value corresponding to T wave 2 The ratio between the bin values, the mth of the histogram of the direction of the positive and negative value main field gravity center connecting line in the two-dimensional isomagnetic diagram corresponding to the QRS wave 3 M-th histogram of direction of positive and negative value main field gravity center connecting line in two-dimensional isomagnetic diagram with bin value corresponding to T wave 4 The ratio between the bin values, the m-th histogram of the angle of the maximum single-connected graph minimum Feret diameter relative to the horizontal axis of the image in the two-dimensional isomagnetic graph corresponding to the QRS wave 5 M-th histogram of angle of maximum single-connected graph minimum Feret diameter relative to image horizontal axis in two-dimensional isomagnetic graph with bin value corresponding to T wave 6 The ratio between the individual bin values;
the ratio between the maximum value of the positive field Y coordinate of the T2 point and the maximum value of the positive field Y coordinate of the T1 point in the two-dimensional isomagnetic map corresponding to the T wave;
the m-th of the histogram of the barycenter X coordinate in the gradient field corresponding to the QRS wave 7 Mth of histogram of barycenter X coordinate in gradient field corresponding to each bin value and T wave 8 The ratio between the individual bin values;
the m-th histogram of the proportion of pixels in the convex hull of the maximum single connected graph in the gradient field corresponding to the QRS wave 9 M-th histogram of proportion of pixels in convex hull region of maximum single-connected graph in gradient field corresponding to each bin value and T wave 10 The ratio between the individual bin values;
the m-th of the histogram of the rotation value at the maximum current vector in the rotation field corresponding to the P wave 11 Mth of histogram of rotation values at maximum current vector in rotation field with bin value corresponding to T wave 12 The ratio between the individual bin values;
the m-th of the total vector angle formed by the positive main field in the gradient field corresponding to the P wave 13 The m-th of the total vector angle of the positive principal field in the gradient field whose percentile corresponds to the T-wave 14 The ratio between percentiles;
the ratio of the fourth difference of the angle between the x axis of the maximum single communication graph and the long axis of the ellipse in the two-dimensional isomagnetic graph corresponding to the ST wave to the fourth difference of the angle between the x axis of the maximum single communication graph and the long axis of the ellipse in the two-dimensional isomagnetic graph corresponding to the T wave;
the m-th of the histogram of the Y coordinate of the maximum position of the negative rotation field in the rotation field corresponding to the ST wave 15 M-th of histogram of negative rotation field maximum value position Y coordinate in rotation field with bin value corresponding to T wave 16 A bin value;
the rotation field corresponding to the ST wave is between the x axis of the maximum single communication graph and the major axis of the ellipse M th angle 17 Mth of angle between x-axis of maximum single-connected graph and major axis of ellipse in rotation field with percentile corresponding to T wave 18 A personal percentile;
the m-th of the histogram of vector magnitude of the negative divergence field maximum value pointing to the positive divergence maximum value in the corresponding divergence field of the ST segment wave 19 M-th of vector-sized histogram with negative divergence field maximum pointing to positive divergence maximum in divergence field with each bin value corresponding to T wave 20 The ratio between the individual bin values;
the mth of the histogram of the maximum gradient vector direction in the gradient field corresponding to the ST wave 21 Mth of histogram of maximum gradient vector direction in gradient field with each bin value corresponding to T wave 22 The ratio between the individual bin values;
the m-th of the histogram of the angle between the X-axis of the maximum single-connected graph and the major axis of the ellipse in the current density graph corresponding to the point from the start point to the peak point of the P wave 23 A bin value;
and the Renyi entropy of the X coordinate of the gravity center position of the negative rotation field in the rotation field corresponding to the vertex from the P wave starting point.
A terminal comprising a processor and a memory, the memory being for storing a computer program, the processor being for executing the computer program stored by the memory to cause the terminal to execute the computer program on any one of the computer storage media described above.
Compared with the prior art, the heart function detection system, the computer storage medium and the terminal have the following beneficial effects:
1. the invention innovatively constructs gradient fields, rotation fields and divergence fields of a current density map from P waves, QRS waves, ST wave and T wave bands, extracts waveform characteristic parameters, cross-correlation characteristic parameters, LBP characteristic parameters, image shape characteristic, image pixel characteristic, fine granularity dynamic characteristic, dynamic combination characteristic, transient combination characteristic, SVD characteristic parameters, main field characteristic parameters and other characteristic parameters which are sensitive to heart reconstruction from more angles, explores the distribution rule of the characteristic parameters, provides more comprehensive characteristic information, can extract the characteristic parameters which are sensitive to heart reconstruction from more angles, assists in realizing the identification of patients in early cardiac function, and further improves the accuracy of early cardiac function detection results;
2. the invention can identify the characteristics related to the cardiac function comprehensively by constructing the gradient field, the rotation field and the divergence field of the current density map and adopting a new technical means to extract the characteristic parameters in multiple directions, and also constructs the cardiac function judging and comparing module, so that the invention can detect the electrocardiosignal change more directly and earlier, reflect the pathological state and identify the cardiac function efficacy sensitivity to 90%, thus being capable of being used for early screening of cardiac function and providing help for further examination and treatment of the next step.
3. The invention is superior to the prior one-dimensional or two-dimensional electrocardiogram and biological index parameters, avoids the complex source reconstruction process, has no invasion or injury to human body and has strong clinical feasibility; the operation is simple and convenient, and the labor and time cost is greatly saved.
Drawings
FIG. 1 is a schematic diagram of a cardiac function testing system according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of another embodiment of a cardiac function testing system according to the present invention;
FIG. 3 is a schematic diagram of another embodiment of the cardiac function detection system according to the present invention;
FIG. 4 is a flow chart of an embodiment of a computer storage medium of the present invention;
FIG. 5 is a flow chart of another embodiment of a computer storage medium of the present invention;
FIG. 6 is a flow chart of another embodiment of a computer storage medium of the present invention;
fig. 7 is a schematic structural view of an embodiment of the inventive terminal.
Detailed Description
In order to make the technical problems, technical solutions and advantages to be solved more apparent, the following detailed description will be given with reference to the accompanying drawings and specific embodiments.
In one aspect, the present invention provides a cardiac function detection system, as shown in FIGS. 1-3, comprising:
The data acquisition module 100: the method comprises the steps of obtaining initial data of a magnetocardiogram, preprocessing the initial data of the magnetocardiogram, and obtaining one-dimensional butterfly images corresponding to P wave, QRS wave, ST wave and T wave bands;
in an embodiment of the present invention, the data acquisition module 100 may acquire the original data of the magnetocardiogram of the multiple channels through the SERF 36-channel optical pump magnetometer magnetocardiogram.
In an embodiment of the present invention, preprocessing the original data of the magnetocardiogram in the data acquisition module 100 mainly includes filtering and noise reduction processing and band segmentation, and noise interference of the original data of the magnetocardiogram is removed through the filtering and noise reduction processing, so that accuracy of subsequent lesion degree and range detection is ensured; and then, carrying out band segmentation on the magnetocardiogram from which noise interference is removed, and obtaining one-dimensional butterfly patterns corresponding to P wave, QRS wave, ST wave and T wave bands.
In an embodiment of the present invention, the data acquisition module 100 may process the original magnetocardiogram data by using a filtering noise reduction and band splitting method known in the prior art, which is not described herein.
Two-dimensional drawing module 200: the method comprises the steps of respectively obtaining a two-dimensional isomagnetic map, a current density map, a gradient field, a rotation field and a divergence field corresponding to a P wave, a QRS wave, an ST wave and a T wave band based on the obtained one-dimensional butterfly map and the magnetic field intensity and the position recorded by each cardiac magnetic channel;
In an embodiment of the present invention, the two-dimensional drawing module 200 specifically includes:
the first two-dimensional drawing module 201: the method is used for respectively drawing two-dimensional isomagnetic maps corresponding to P wave, QRS wave, ST wave and T wave bands based on the obtained one-dimensional butterfly map and the magnetic field intensity and position recorded by each cardiac magnetic channel, and respectively calculating current density maps corresponding to the P wave, the QRS wave, the ST wave and the T wave bands based on the two-dimensional isomagnetic maps;
in an embodiment of the present invention, the first two-dimensional drawing module 201 may calculate the current densities of all points on the two-dimensional isomagnetic map according to a current density calculation formula, so as to obtain a current density map corresponding to the P-wave, QRS-wave, ST-wave and T-wave bands, where (x, y) represents the coordinate value of a certain point above the chest on the two-dimensional isomagnetic map.
The second two-dimensional drawing module 202: the gradient value and the rotation value of the vector signal at each position in the current density diagram corresponding to the P wave, the QRS wave, the ST wave and the T wave band are respectively calculated according to the gradient formula and the rotation formula, and the gradient field and the rotation field corresponding to the P wave, the QRS wave, the ST wave and the T wave band are respectively drawn according to the gradient value and the rotation value;
In an embodiment of the present invention, the gradient field drawing method corresponding to each band in the second two-dimensional drawing module 202 is as follows: the gradient value of each vector signal in the current density map is calculated using the gradient formula gradF (x, y) =f_x (x, y) i ̅ +f_y (x, y) j ̅, where F represents the current vector at a point (x, y) in the current density map, f_x (x, y) represents the partial derivative of function F with respect to x, f_y (x, y) represents the partial derivative of function F with respect to y, i ̅ is the unit vector of the x-axis, and j ̅ is the unit vector of the y-axis. The partial derivatives in its definition are calculated using finite differences. For the internal data points in the current density plot, the partial derivatives are calculated using the center difference. For data points along the edges of the current density plot, the partial derivatives are calculated using single-sided (forward) differential; and finally, drawing gradient fields corresponding to the P wave, the QRS wave, the ST wave and the T wave band according to the gradient values calculated by each vector signal.
The corresponding rotation field drawing method of each wave band is as follows: the rotation value of each vector signal in the current density map is calculated using the rotation formula curl (F) = dFy/dx-dFx/dy, where F represents the current vector at a point (x, y) in the current density map, dFy/dx represents the partial derivative of the y component in the current vector F with respect to the x-axis direction, and dFx/dy represents the 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 central differences for internal data points in the current density map, and calculating the partial derivatives using single-sided (forward) differences for data points along edges in the current density map; and finally, drawing the corresponding rotation fields of the P wave, the QRS wave, the ST wave and the T wave band according to the rotation value calculated by each vector signal position.
Third two-dimensional drawing module 203: the method is used for calculating and obtaining the divergence value of the vector signal of each position in the gradient fields corresponding to the P wave, the QRS wave, the ST wave and the T wave band according to the divergence formula, and drawing and obtaining the divergence fields corresponding to the P wave, the QRS wave, the ST wave and the T wave band according to the divergence value.
In an embodiment of the present invention, the method for drawing the divergence fields corresponding to each band in the third two-dimensional drawing module 203 is as follows: 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, 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 in the current density plot, the partial derivatives are calculated using the center difference. For data points along the edges in the current density plot, the partial derivatives are calculated using single-sided (forward) differential; and finally, drawing the corresponding divergence fields of the P wave, the QRS wave, the ST wave and the T wave band according to the calculated divergence value of each vector signal.
Feature extraction module 300: the method is used for extracting characteristic parameters related to cardiac functions from a one-dimensional butterfly graph, a two-dimensional isomagnetic graph, a current density graph, a gradient field, a rotation field and a divergence field corresponding to P wave, QRS wave, ST wave and T wave bands;
In an embodiment of the present invention, the feature extraction module 300 may obtain corresponding array data according to a one-dimensional butterfly diagram, a two-dimensional isomagnetic diagram, a current density diagram, a gradient field, a rotation field and a divergence field corresponding to the P wave, the QRS wave, the ST wave and the T wave bands, and extract feature parameters related to cardiac functions according to the array data.
In one embodiment of the present invention, the characteristic parameters related to cardiac function include: waveform type characteristic parameters, cross-correlation type characteristic parameters, LBP type characteristic parameters, image shape type characteristic, image pixel type characteristic, fine granularity dynamic characteristic, dynamic combination characteristic, transient combination characteristic, SVD type characteristic parameters and main field type characteristic parameters.
In an embodiment of the present invention, the feature extraction module 300 further includes:
the first feature extraction module 301: the method is used for extracting waveform characteristic parameters and cross-correlation characteristic parameters from one-dimensional butterfly graphs corresponding to P wave, QRS wave, ST wave and T wave bands, and specifically comprises the following steps:
the waveform characteristic parameter extraction method comprises the following steps: using dimensionless operators describing waveform shape changes as waveform class feature parameters, comprising: kurtosis factor, skewness factor, waveform factor, peak factor, pulse factor, margin factor, and fluctuation index;
The method for extracting the cross-correlation characteristic parameters comprises the following steps: when the SERF effect 36-channel optical pump magnetometer electrocardiograph is used, the Pearson linear correlation coefficient of the waveform between any two channels in the channels of the electrocardiograph is calculated, and the cross correlation characteristics among 630 different channels are calculated.
The second feature extraction module 302: the method is used for extracting image shape type characteristics, image pixel type characteristics, LBP type characteristic parameters, fine granularity dynamic characteristics, dynamic combination characteristics and transient combination characteristics from two-dimensional isomagnetic diagrams and current density diagrams corresponding to P wave, QRS wave, ST wave and T wave bands, and is specifically as follows:
the image shape class feature and image pixel class feature extraction method comprises the following steps: calculating main fields (namely, signal amplitude is larger than 0.8 x maximum amplitude) in a two-dimensional isomagnetic map and a current density map corresponding to a P wave, a QRS wave, a ST wave and a T wave band, converting the two-dimensional isomagnetic map and the current density map (color map) into a gray map and a binary map, respectively using the binary map to find a first large single communication area and a second large single communication area corresponding to the two-dimensional isomagnetic map (the two single communication areas respectively comprise main fields of two magnetic poles in the isomagnetic map) and a maximum communication area corresponding to the current density map, and finally respectively calculating image shape class characteristics and image pixel class characteristics of the two communication areas.
The local binary pattern (Local Binary Pattern, LBP) type characteristic parameter extraction method comprises the following steps: and converting the two-dimensional isomagnetic map and the current density map (color map) corresponding to the P wave, the QRS wave, the ST wave and the T wave into gray images. A pixel P (x, y) is selected as a center point, and a neighborhood radius around the point and the number of selected pixels in the neighborhood are determined (the selected field radius in this embodiment is 2, and the number of pixels is 8). Comparing the selected pixel value in the neighborhood with the gray value of the central pixel point, if the gray value of the pixel point in the neighborhood is larger than or equal to the gray value of the central pixel point, the binary value of the pixel point is 1, otherwise, the binary value of the pixel point is 0. The binary values are formed into a binary string, which is then converted into a 10-ary value. Repeating the steps, and calculating the LBP value of each pixel point in the image; finally, an LBP image is generated, wherein the value of each pixel point represents the LBP value of the pixel in the neighborhood of the pixel point.
The fine granularity dynamic feature refers to describing a feature dynamic change process by using rich statistical parameters, and the statistical parameters can be used as dynamic features. The statistical parameters include 7 major classes, namely a basic class, a concentrated quantity class, a differential quantity class, a dimensionless class, a histogram class, an entropy class and a higher order class.
The dynamic combination features are obtained by ratio processing of dynamic features of different wave bands extracted from two-dimensional isomagnetic diagrams/current density diagrams corresponding to the P wave, the QRS wave, the ST wave and the T wave bands. Specifically, the dynamic characteristic extracted from the two-dimensional isomagnetic map/current density map is selected to be a certain wave band calculation characteristic value.
The transient combination characteristic is obtained by ratio processing of transient characteristics at different moments extracted from two-dimensional isomagnetic diagrams/current density diagrams corresponding to the P wave, the QRS wave, the ST wave and the T wave band. Specifically, the transient characteristics extracted from the two-dimensional isomagnetic map/current density map corresponding to the P wave, QRS wave, ST wave and T wave band are selected to calculate the characteristic value at a certain moment.
The third feature extraction module 303: the SVD type characteristic parameters and main field type characteristic parameters are extracted from gradient fields, rotation fields and divergence fields corresponding to P wave, QRS wave, ST wave and T wave bands, and are specifically as follows:
the SVD type characteristic parameter extraction method comprises the following steps: acquiring array data according to a rotation field/a divergence field/a gradient field at a certain moment corresponding to a P wave, a QRS wave, an ST wave and a T wave band respectively; singular value decomposition is carried out on the array data, and normalization processing is carried out on the singular values after decomposition; and (3) selecting normalized 2,3,4 and 5 singular values as features, and calculating the average value, standard deviation and shannon entropy of the first 6 normalized singular values as features to obtain SVD feature parameters.
The main field characteristic parameter extraction method comprises the following steps: acquiring square matrix data according to a rotation field or a divergence field or a gradient field at a certain moment corresponding to the P wave, the QRS wave, the ST wave and the T wave band respectively; extracting the maximum value of positive amplitude signals with the signal more than 0.8 times and the minimum value of negative amplitude signals with the signal less than 0.8 times from square matrix data, wherein the data together form a main field; extracting the area, center of gravity and total vector related features of the main field, wherein the method comprises the following steps: the area of the positive primary field; the position of the center of gravity of the positive primary field; the total vector direction of the positive primary field; the total vector magnitude of the positive primary field components; the area of the primary field; the position of the center of gravity of the main field.
Feature screening module 400: the method comprises the steps of sorting, judging linear cross correlation and selecting quantity of extracted characteristic parameters to obtain a characteristic subset;
in an embodiment of the present invention, the feature screening module 400 may first sort the extracted feature parameters according to the class separability criteria using a feature selection algorithm (for example, chi-square test), and select the first N1 feature parameters, N1 being the number of training set observations; secondly, carrying out linear cross-correlation judgment on the N1 selected features, and reserving N2 feature parameters with cross-correlation coefficients smaller than 0.5; and finally, selecting the number of the characteristic parameters, drawing the change between the N3 cross-verified misclassification rates and the number of the characteristic parameters by using training set data, and selecting the point that the misclassification rate does not obviously drop along with the increase of the number of the characteristic parameters as the optimal point, wherein the number of the characteristic parameters corresponding to the point is the number of the finally selected characteristic parameters, and the characteristic parameters form a characteristic subset.
In an embodiment of the present invention, the evaluation ranking is performed according to the importance index of the feature parameters, and the parameter ranked in the first 1/10 of the total number of feature parameters is generally selected as the feature subset used for modeling.
In an embodiment of the present invention, when the number of feature parameters is 150, parameters with importance level ranked 1/10 are selected as feature subsets for modeling after preprocessing and evaluation according to the 150 feature parameters, and the 15 feature subsets include:
the ratio between the 4 th bin value of the histogram of the Y coordinate of the positive value field barycenter position in the two-dimensional isomagnetic diagram corresponding to the QRS wave and the 4 th bin value of the histogram of the Y coordinate of the positive value field barycenter position in the two-dimensional isomagnetic diagram corresponding to the T wave, the ratio between the 5 th bin value of the histogram of the direction of the positive and negative value main field barycenter connecting line in the two-dimensional isomagnetic diagram corresponding to the QRS wave and the 5 th bin value of the histogram of the direction of the positive and negative value main field barycenter connecting line in the two-dimensional isomagnetic diagram corresponding to the T wave, and the ratio between the 6 th bin value of the histogram of the angle of the maximum single communication graph minimum Feret diameter relative to the image horizontal axis in the histogram of the maximum single communication graph minimum Feret diameter relative to the image horizontal axis in the two-dimensional isomagnetic diagram corresponding to the T wave;
The ratio between the maximum value of the positive field Y coordinate of the T2 point and the maximum value of the positive field Y coordinate of the T1 point in the two-dimensional isomagnetic map corresponding to the T wave;
the ratio between the 9 th bin value of the histogram of the barycenter X coordinate in the gradient field corresponding to the QRS wave and the 9 th bin value of the histogram of the barycenter X coordinate in the gradient field corresponding to the T wave;
the ratio between the 7 th bin value of the histogram of the proportion occupied by the pixels in the convex hull of the maximum single-connected graph in the gradient field corresponding to the QRS wave and the 7 th bin value of the histogram of the proportion occupied by the pixels in the convex hull of the maximum single-connected graph in the gradient field corresponding to the T wave;
a ratio between an 8 th bin value of the histogram of rotation values at the maximum current vector in the rotation field corresponding to the P-wave and an 8 th bin value of the histogram of rotation values at the maximum current vector in the rotation field corresponding to the T-wave;
a ratio between the 90 th percentile of the total vector angle formed by the positive main field in the gradient field corresponding to the P wave and the 90 th percentile of the total vector angle formed by the positive main field in the gradient field corresponding to the T wave;
the ratio of the fourth difference of the angle between the x axis of the maximum single communication graph and the long axis of the ellipse in the two-dimensional isomagnetic graph corresponding to the ST wave to the fourth difference of the angle between the x axis of the maximum single communication graph and the long axis of the ellipse in the two-dimensional isomagnetic graph corresponding to the T wave;
The 9 th bin value of the histogram of the Y coordinate of the maximum value position of the negative rotation field in the rotation field corresponding to the ST wave and the 9 th bin value of the histogram of the Y coordinate of the maximum value position of the negative rotation field in the rotation field corresponding to the T wave;
the 3 rd percentile of the angle between the x-axis of the maximum single communication graph in the rotation field corresponding to the ST wave and the major axis of the ellipse is the 3 rd percentile of the angle between the x-axis of the maximum single communication graph in the rotation field corresponding to the T wave;
the ratio between the 3 rd bin value of the histogram of the vector magnitude of the negative divergence field maximum value pointing to the positive divergence maximum value in the divergence field corresponding to the ST wave and the 3 rd bin value of the histogram of the vector magnitude of the negative divergence field maximum value pointing to the positive divergence maximum value in the divergence field corresponding to the T wave;
a ratio between the 9 th bin value of the histogram of the maximum gradient vector direction in the gradient field corresponding to the ST wave and the 9 th bin value of the histogram of the maximum gradient vector direction in the gradient field corresponding to the T wave;
the 10 th bin value of the histogram of the angle between the X axis of the maximum single-connected graph and the major axis of the ellipse in the current density graph corresponding to the point from the start point to the top point of the P wave;
and the Renyi entropy of the X coordinate of the gravity center position of the negative rotation field in the rotation field corresponding to the P wave starting point to the vertex.
The judgment comparison module 500: for determining whether the heart function of the subject is normal based on the feature subset.
In an embodiment of the present invention, the machine learning method can be used in the determining and comparing module 500 to determine whether the coronary blood flow of the subject is normal, which is specifically as follows:
using known normoxic and known dysfunctional patients as the raw dataset, a machine learning model is trained using the feature subsets described above. Training a machine learning model, such as a support vector machine (Support Vector Machine with a linear kernel) based on a linear kernel, by using the extracted 15 feature subsets, outputting labels of normal class and abnormal class by the model, wherein 0 represents normal class, 1 represents abnormal class, and evaluating indexes such as accuracy, precision, recall, and AUC curve are used for evaluating the performance of the classification model.
When the feature subset of the tested person inputs the trained machine learning model, the heart function is considered abnormal when the output label class is 1, and the heart function of the tested person is considered normal when the output label class is 0.
In another aspect, the present invention also provides a computer storage medium, as shown in fig. 4-6, storing a computer program, where the computer program when executed by a processor implements a cardiac function detection method, the method including:
Step S1: acquiring initial data of a magnetocardiogram, preprocessing the initial data of the magnetocardiogram, and acquiring one-dimensional butterfly images corresponding to P wave, QRS wave, ST wave and T wave bands;
step S2: based on the obtained one-dimensional butterfly graph and the positions of each magnetocardiogram channel, respectively obtaining two-dimensional isomagnetograms, current density graphs, gradient fields, rotation fields and divergence fields corresponding to P wave, QRS wave, ST wave and T wave bands;
step S3: extracting characteristic parameters related to cardiac functions from a one-dimensional butterfly diagram, a two-dimensional isomagnetic diagram, a current density diagram, a gradient field, a rotation field and a divergence field corresponding to a P wave, a QRS wave, a ST wave and a T wave band; step S4: sequencing, linear cross-correlation judgment and quantity selection are carried out on the extracted characteristic parameters, so that a characteristic subset is obtained; step S5: and judging whether the heart function of the tested person is normal or not according to the feature subset.
Step S4: sequencing, linear cross-correlation judgment and quantity selection are carried out on the extracted characteristic parameters, so that a characteristic subset is obtained;
step S5: and judging whether the heart function of the tested person is normal or not according to the feature subset.
In an embodiment of the present invention, step S2 further includes:
step S21: respectively drawing two-dimensional isomagnetic maps corresponding to the P wave, the QRS wave, the ST wave and the T wave band based on the obtained one-dimensional butterfly map and the positions of each magnetocardiogram channel; respectively calculating current density maps corresponding to P wave, QRS wave, ST wave and T wave bands based on the two-dimensional isomagnetic map;
Step S22: and respectively calculating the gradient value and the rotation value of the vector signal at each position in the current density map corresponding to the P wave, the QRS wave, the ST wave and the T wave band according to the gradient formula and the rotation formula, and respectively drawing the gradient field and the rotation field corresponding to the P wave, the QRS wave, the ST wave and the T wave band according to the gradient value and the rotation value.
Step S23: calculating and obtaining the divergence value of the vector signal of each position in the gradient fields corresponding to the P wave, the QRS wave, the ST wave and the T wave band according to the divergence formula, and drawing and obtaining the divergence fields corresponding to the P wave, the QRS wave, the ST wave and the T wave band according to the divergence value.
In an embodiment of the present invention, step S3 further includes:
step S31: extracting waveform characteristic parameters and cross-correlation characteristic parameters from one-dimensional butterfly graphs corresponding to P wave, QRS wave, ST wave and T wave bands;
step S32: extracting image shape type features, image pixel type features, LBP type feature parameters, fine granularity dynamic features, dynamic combination features and transient combination features from a two-dimensional isomagnetic map and a current density map corresponding to a P wave, a QRS wave, a ST wave and a T wave band;
step S33: SVD type characteristic parameters and main field type characteristic parameters are extracted from gradient fields, rotation fields and divergence fields corresponding to P wave, QRS wave, ST wave band and T wave band.
Preferably, the computer storage medium may be a ROM, RAM, magnetic disk or optical disk, or other various media capable of storing program codes.
The present invention also provides a terminal, as shown in fig. 7, including a processor 700 and a memory 800, where the memory 700 is used to store a computer program, and the processor 800 is used to execute the computer program stored in the memory 700, so that the terminal performs any of the above cardiac function detection methods.
In summary, the invention innovatively constructs gradient fields, rotation fields and divergence fields of a current density map from P wave, QRS wave, ST wave and T wave bands, extracts waveform characteristic parameters, cross-correlation characteristic parameters, LBP characteristic parameters, image shape characteristic, image pixel characteristic, fine granularity dynamic characteristic, dynamic combination characteristic, transient combination characteristic, SVD characteristic parameters, main field characteristic parameters and other characteristic parameters which are sensitive to heart reconstruction from more angles, discovers the distribution rules of the characteristic parameters, provides more comprehensive characteristic information, can extract the characteristic parameters which are sensitive to heart reconstruction from more angles, assists in realizing the identification of patients in early cardiac function, and further improves the accuracy of early cardiac function detection results;
The invention can identify the characteristics related to the cardiac function comprehensively by constructing the gradient field, the rotation field and the divergence field of the current density map and adopting a new technical means to extract the characteristic parameters in multiple directions, and also constructs the cardiac function judging and comparing module, so that the invention can detect the electrocardiosignal change more directly and earlier, reflect the pathological state and identify the cardiac function efficacy sensitivity to 90%, thus being capable of being used for early screening of cardiac function and providing help for further examination and treatment of the next step.
The invention is superior to the prior one-dimensional or two-dimensional electrocardiogram and biological index parameters, avoids the complex source reconstruction process, has no invasion or injury to human body and has strong clinical feasibility; the operation is simple and convenient, and the labor and time cost is greatly saved.
While the foregoing is directed to the preferred embodiments of the present invention, it will be appreciated by those skilled in the art that various modifications and adaptations can be made without departing from the principles of the present invention, and such modifications and adaptations are intended to be comprehended within the scope of the present invention.
Claims (5)
1. A cardiac function detection system, comprising:
and a data acquisition module: the method comprises the steps of obtaining initial data of a magnetocardiogram, preprocessing the initial data of the magnetocardiogram, and obtaining one-dimensional butterfly images corresponding to P wave, QRS wave, ST wave and T wave bands;
And a two-dimensional drawing module: the method comprises the steps of respectively acquiring a two-dimensional isomagnetic map, a current density map, a gradient field, a rotation field and a divergence field corresponding to a P wave, a QRS wave, an ST wave and a T wave band based on the acquired one-dimensional butterfly map and the positions of each magnetocardiogram channel;
and the feature extraction module is used for: the method is used for extracting characteristic parameters related to cardiac functions from a one-dimensional butterfly graph, a two-dimensional isomagnetic graph, a current density graph, a gradient field, a rotation field and a divergence field corresponding to P wave, QRS wave, ST wave and T wave bands;
and a feature screening module: the method comprises the steps of sorting, judging linear cross correlation and selecting quantity of extracted characteristic parameters to obtain a characteristic subset;
and a judgment and comparison module: judging whether the heart function of the tested person is normal according to the feature subset;
wherein the characteristic parameters include: waveform type characteristic parameters, cross-correlation type characteristic parameters, LBP type characteristic parameters, image shape type characteristics, image pixel type characteristics, fine granularity dynamic characteristics, dynamic combination characteristics, transient combination characteristics, SVD type characteristic parameters and main field type characteristic parameters;
the two-dimensional drawing module comprises:
a first two-dimensional drawing module: the method comprises the steps of respectively drawing two-dimensional isomagnetic graphs corresponding to P wave, QRS wave, ST wave and T wave bands based on the obtained one-dimensional butterfly graph and the positions of each magnetocardiogram, and respectively calculating current density graphs corresponding to the P wave, the QRS wave, the ST wave and the T wave bands based on the two-dimensional isomagnetic graphs;
And a second two-dimensional drawing module: the gradient value and the rotation value of the vector signal at each position in the current density diagram corresponding to the P wave, the QRS wave, the ST wave and the T wave band are respectively calculated according to the gradient formula and the rotation formula, and the gradient field and the rotation field corresponding to the P wave, the QRS wave, the ST wave and the T wave band are respectively drawn according to the gradient value and the rotation value;
and a third two-dimensional drawing module: the method comprises the steps of calculating and obtaining the divergence value of vector signals at each position in gradient fields corresponding to P wave, QRS wave, ST wave and T wave bands according to a divergence formula, and drawing and obtaining the divergence fields corresponding to the P wave, the QRS wave, the ST wave and the T wave bands according to the divergence value;
the feature subset comprises:
the m-th histogram of Y coordinates of the barycenter position of positive field in the two-dimensional isomagnetogram corresponding to the QRS wave 1 M-th histogram of Y-coordinate of barycenter position of positive field in two-dimensional isomagnetogram with bin value corresponding to T wave 2 The ratio between the bin values, the mth of the histogram of the direction of the positive and negative value main field gravity center connecting line in the two-dimensional isomagnetic diagram corresponding to the QRS wave 3 M-th histogram of direction of positive and negative value main field gravity center connecting line in two-dimensional isomagnetic diagram with bin value corresponding to T wave 4 The ratio between the bin values, the m-th histogram of the angle of the maximum single-connected graph minimum Feret diameter relative to the horizontal axis of the image in the two-dimensional isomagnetic graph corresponding to the QRS wave 5 M-th histogram of angle of maximum single-connected graph minimum Feret diameter relative to image horizontal axis in two-dimensional isomagnetic graph with bin value corresponding to T wave 6 The ratio between the individual bin values;
the ratio between the maximum value of the positive field Y coordinate of the T2 point and the maximum value of the positive field Y coordinate of the T1 point in the two-dimensional isomagnetic map corresponding to the T wave;
the m-th of the histogram of the barycenter X coordinate in the gradient field corresponding to the QRS wave 7 Mth of histogram of barycenter X coordinate in gradient field corresponding to each bin value and T wave 8 The ratio between the individual bin values;
the m-th histogram of the proportion of pixels in the convex hull of the maximum single connected graph in the gradient field corresponding to the QRS wave 9 M-th histogram of proportion of pixels in convex hull region of maximum single-connected graph in gradient field corresponding to each bin value and T wave 10 The ratio between the individual bin values;
the m-th of the histogram of the rotation value at the maximum current vector in the rotation field corresponding to the P wave 11 Mth of histogram of rotation values at maximum current vector in rotation field with bin value corresponding to T wave 12 The ratio between the individual bin values;
the m-th of the total vector angle formed by the positive main field in the gradient field corresponding to the P wave 13 The m-th of the total vector angle of the positive principal field in the gradient field whose percentile corresponds to the T-wave 14 The ratio between percentiles;
the ratio of the fourth difference of the angle between the x axis of the maximum single communication graph and the long axis of the ellipse in the two-dimensional isomagnetic graph corresponding to the ST wave to the fourth difference of the angle between the x axis of the maximum single communication graph and the long axis of the ellipse in the two-dimensional isomagnetic graph corresponding to the T wave;
the m-th of the histogram of the Y coordinate of the maximum position of the negative rotation field in the rotation field corresponding to the ST wave 15 M-th of histogram of negative rotation field maximum value position Y coordinate in rotation field with bin value corresponding to T wave 16 A bin value;
the mth of the angle between the x-axis of the maximum single communication graph and the major axis of the ellipse in the rotation field corresponding to the ST-segment wave 17 Mth of angle between x-axis of maximum single-connected graph and major axis of ellipse in rotation field with percentile corresponding to T wave 18 A personal percentile;
the m-th of the histogram of vector magnitude of the negative divergence field maximum value pointing to the positive divergence maximum value in the corresponding divergence field of the ST segment wave 19 M-th of vector-sized histogram with negative divergence field maximum pointing to positive divergence maximum in divergence field with each bin value corresponding to T wave 20 The ratio between the individual bin values;
the mth of the histogram of the maximum gradient vector direction in the gradient field corresponding to the ST wave 21 Mth of histogram of maximum gradient vector direction in gradient field with each bin value corresponding to T wave 22 The ratio between the individual bin values;
the m-th of the histogram of the angle between the X-axis of the maximum single-connected graph and the major axis of the ellipse in the current density graph corresponding to the point from the start point to the peak point of the P wave 23 A bin value;
and the Renyi entropy of the X coordinate of the gravity center position of the negative rotation field in the rotation field corresponding to the vertex from the P wave starting point.
2. The cardiac function detection system of claim 1, wherein the feature extraction module comprises:
a first feature extraction module: the method is used for extracting waveform characteristic parameters and cross-correlation characteristic parameters from one-dimensional butterfly graphs corresponding to P wave, QRS wave, ST wave and T wave bands;
and a second feature extraction module: the method is used for extracting image shape type characteristics, image pixel type characteristics, LBP type characteristic parameters, fine granularity dynamic characteristics, dynamic combination characteristics and transient combination characteristics from two-dimensional isomagnetic diagrams and current density diagrams corresponding to P wave, QRS wave, ST wave and T wave bands;
and a third feature extraction module: the SVD type characteristic parameters and the main field type characteristic parameters are extracted from the gradient fields, the rotation fields and the divergence fields corresponding to the P wave, the QRS wave, the ST wave and the T wave bands.
3. A computer storage medium, wherein the computer readable storage medium stores a computer program, which when executed by a processor, implements a cardiac function detection method; the heart function detection method comprises the following steps:
acquiring initial data of a magnetocardiogram, preprocessing the initial data of the magnetocardiogram, and acquiring one-dimensional butterfly images corresponding to P wave, QRS wave, ST wave and T wave bands;
based on the obtained one-dimensional butterfly graph and the positions of each magnetocardiogram channel, respectively obtaining a two-dimensional isomagnetogram, a current density graph, a gradient field, a rotation field and a divergence field corresponding to a P wave, a QRS wave, a ST wave and a T wave band;
extracting characteristic parameters related to cardiac functions from a one-dimensional butterfly diagram, a two-dimensional isomagnetic diagram, a current density diagram, a gradient field, a rotation field and a divergence field corresponding to a P wave, a QRS wave, a ST wave and a T wave band;
sequencing, linear cross-correlation judgment and quantity selection are carried out on the extracted characteristic parameters, so that a characteristic subset is obtained;
judging whether the heart function of the tested person is normal or not according to the feature subset;
wherein the characteristic parameters include: waveform type characteristic parameters, cross-correlation type characteristic parameters, LBP type characteristic parameters, image shape type characteristics, image pixel type characteristics, fine granularity dynamic characteristics, dynamic combination characteristics, transient combination characteristics, SVD type characteristic parameters and main field type characteristic parameters;
The steps of respectively acquiring the two-dimensional isomagnetic map, the current density map, the gradient field, the rotation field and the divergence field corresponding to the P wave, the QRS wave, the ST wave and the T wave band based on the acquired one-dimensional butterfly map and the positions of each magnetocardiogram channel comprise:
respectively drawing two-dimensional isomagnetic maps corresponding to P wave, QRS wave, ST wave and T wave bands based on the obtained one-dimensional butterfly map and the positions of each magnetocardiogram channel, and respectively calculating current density maps corresponding to the P wave, the QRS wave, the ST wave and the T wave bands based on the two-dimensional isomagnetic maps;
respectively calculating a gradient value and a rotation value of a vector signal at each position in a current density diagram corresponding to the P wave, the QRS wave, the ST wave and the T wave band according to the gradient formula and the rotation formula, and respectively drawing a gradient field and a rotation field corresponding to the P wave, the QRS wave, the ST wave and the T wave band according to the gradient value and the rotation value;
calculating and obtaining the divergence value of the vector signal of each position in the gradient fields corresponding to the P wave, the QRS wave, the ST wave and the T wave band according to the divergence formula, and drawing and obtaining the divergence fields corresponding to the P wave, the QRS wave, the ST wave and the T wave band according to the divergence value;
the feature subset comprises:
The m-th histogram of Y coordinates of the barycenter position of positive field in the two-dimensional isomagnetogram corresponding to the QRS wave 1 M-th histogram of Y-coordinate of barycenter position of positive field in two-dimensional isomagnetogram with bin value corresponding to T wave 2 The ratio between the bin values, the mth of the histogram of the direction of the positive and negative value main field gravity center connecting line in the two-dimensional isomagnetic diagram corresponding to the QRS wave 3 M-th histogram of direction of positive and negative value main field gravity center connecting line in two-dimensional isomagnetic diagram with bin value corresponding to T wave 4 The ratio between the bin values, the m-th histogram of the angle of the maximum single-connected graph minimum Feret diameter relative to the horizontal axis of the image in the two-dimensional isomagnetic graph corresponding to the QRS wave 5 M-th histogram of angle of maximum single-connected graph minimum Feret diameter relative to image horizontal axis in two-dimensional isomagnetic graph with bin value corresponding to T wave 6 The ratio between the individual bin values;
the ratio between the maximum value of the positive field Y coordinate of the T2 point and the maximum value of the positive field Y coordinate of the T1 point in the two-dimensional isomagnetic map corresponding to the T wave;
the m-th of the histogram of the barycenter X coordinate in the gradient field corresponding to the QRS wave 7 Mth of histogram of barycenter X coordinate in gradient field corresponding to each bin value and T wave 8 The ratio between the individual bin values;
the m-th histogram of the proportion of pixels in the convex hull of the maximum single connected graph in the gradient field corresponding to the QRS wave 9 M-th histogram of proportion of pixels in convex hull region of maximum single-connected graph in gradient field corresponding to each bin value and T wave 10 The ratio between the individual bin values;
the m-th of the histogram of the rotation value at the maximum current vector in the rotation field corresponding to the P wave 11 Mth of histogram of rotation values at maximum current vector in rotation field with bin value corresponding to T wave 12 The ratio between the individual bin values;
the m-th of the total vector angle formed by the positive main field in the gradient field corresponding to the P wave 13 The m-th of the total vector angle of the positive principal field in the gradient field whose percentile corresponds to the T-wave 14 The ratio between percentiles;
the ratio of the fourth difference of the angle between the x axis of the maximum single communication graph and the long axis of the ellipse in the two-dimensional isomagnetic graph corresponding to the ST wave to the fourth difference of the angle between the x axis of the maximum single communication graph and the long axis of the ellipse in the two-dimensional isomagnetic graph corresponding to the T wave;
the m-th of the histogram of the Y coordinate of the maximum position of the negative rotation field in the rotation field corresponding to the ST wave 15 M-th of histogram of negative rotation field maximum value position Y coordinate in rotation field with bin value corresponding to T wave 16 A bin value;
the mth of the angle between the x-axis of the maximum single communication graph and the major axis of the ellipse in the rotation field corresponding to the ST-segment wave 17 Mth of angle between x-axis of maximum single-connected graph and major axis of ellipse in rotation field with percentile corresponding to T wave 18 A personal percentile;
the m-th of the histogram of vector magnitude of the negative divergence field maximum value pointing to the positive divergence maximum value in the corresponding divergence field of the ST segment wave 19 M-th of vector-sized histogram with negative divergence field maximum pointing to positive divergence maximum in divergence field with each bin value corresponding to T wave 20 The ratio between the individual bin values;
the mth of the histogram of the maximum gradient vector direction in the gradient field corresponding to the ST wave 21 Mth of histogram of maximum gradient vector direction in gradient field with each bin value corresponding to T wave 22 The ratio between the individual bin values;
the m-th of the histogram of the angle between the X-axis of the maximum single-connected graph and the major axis of the ellipse in the current density graph corresponding to the point from the start point to the peak point of the P wave 23 A bin value;
and the Renyi entropy of the X coordinate of the gravity center position of the negative rotation field in the rotation field corresponding to the vertex from the P wave starting point.
4. A computer storage medium according to claim 3, wherein the step of extracting characteristic parameters related to cardiac function from the one-dimensional butterfly map, the two-dimensional isomagnetic map, the current density map, the gradient field, the rotation field and the divergence field corresponding to the P-wave, the QRS wave, the ST-wave and the T-wave bands comprises:
Extracting waveform characteristic parameters and cross-correlation characteristic parameters from one-dimensional butterfly graphs corresponding to P wave, QRS wave, ST wave and T wave bands;
extracting image shape type features, image pixel type features, LBP type feature parameters, fine granularity dynamic features, dynamic combination features and transient combination features from a two-dimensional isomagnetic map and a current density map corresponding to a P wave, a QRS wave, a ST wave and a T wave band;
SVD type characteristic parameters and main field type characteristic parameters are extracted from gradient fields, rotation fields and divergence fields corresponding to P wave, QRS wave, ST wave band and T wave band.
5. A terminal comprising a processor and a memory, the memory for storing a computer program, the processor for executing the computer program stored in the memory to cause the terminal to execute the computer program in the computer storage medium of any one of claims 3-4.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311375785.6A CN117100276B (en) | 2023-10-23 | 2023-10-23 | Cardiac function detection system, computer storage medium and terminal |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311375785.6A CN117100276B (en) | 2023-10-23 | 2023-10-23 | Cardiac function detection system, computer storage medium and terminal |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117100276A CN117100276A (en) | 2023-11-24 |
CN117100276B true CN117100276B (en) | 2024-01-12 |
Family
ID=88797017
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311375785.6A Active CN117100276B (en) | 2023-10-23 | 2023-10-23 | Cardiac function detection system, computer storage medium and terminal |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117100276B (en) |
Citations (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
USRE32712E (en) * | 1979-08-20 | 1988-07-12 | General Electric Company | Moving gradient zeugmatography |
JP2000217798A (en) * | 1999-02-02 | 2000-08-08 | Hitachi Ltd | Biological magnetic field measuring instrument |
WO2001020477A2 (en) * | 1999-08-28 | 2001-03-22 | Squid Ag | Computer-based method for automatically processing data, especially magnetocardiographic data, of biomagnetic fields |
CN103190898A (en) * | 2013-04-23 | 2013-07-10 | 何怡刚 | Cardiac magnetic signal noise adaptive filtering and eliminating design method |
CN103810381A (en) * | 2014-01-26 | 2014-05-21 | 同济大学 | Coronary heart disease characteristic parameter extracting method based on multichannel magnetocardiogram |
JP2016101264A (en) * | 2014-11-27 | 2016-06-02 | 国立研究開発法人国立循環器病研究センター | Magnetocardiogram device |
CN106901717A (en) * | 2017-03-01 | 2017-06-30 | 中国科学院上海微系统与信息技术研究所 | Three-dimensional heart source localization method, system and server |
CN107361760A (en) * | 2017-07-12 | 2017-11-21 | 中国科学院上海微系统与信息技术研究所 | The magnetocardiograph of magnetocardiograph diagnostic system and the application system |
WO2018069287A1 (en) * | 2016-10-11 | 2018-04-19 | Biomagnetik Park Gmbh | Magnetocardiographic method and magnetocardiographic system |
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 |
CN108577825A (en) * | 2018-01-11 | 2018-09-28 | 中国科学院上海微系统与信息技术研究所 | A kind of myocardial ischemia lesion locations localization method and system, storage medium and terminal |
CN108697356A (en) * | 2016-02-18 | 2018-10-23 | 生物磁场有限公司 | Vector magnetocardiogram method and vector magnetocardiogram system |
WO2020120924A1 (en) * | 2018-12-12 | 2020-06-18 | Icerobotics Ltd | Apparatus and method(s) in biomagnetic measurements |
JP2020156870A (en) * | 2019-03-27 | 2020-10-01 | 旭化成エレクトロニクス株式会社 | Magnetocardiographic measurement apparatus |
CN112515679A (en) * | 2020-12-01 | 2021-03-19 | 北京昆迈医疗科技有限公司 | Unshielded magnetocardiogram device |
CN115337016A (en) * | 2022-08-01 | 2022-11-15 | 苏州卡迪默克医疗器械有限公司 | Method and device for evaluating myocardial ischemia based on current density vector diagram |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7485095B2 (en) * | 2000-05-30 | 2009-02-03 | Vladimir Shusterman | Measurement and analysis of trends in physiological and/or health data |
JP4027746B2 (en) * | 2002-08-07 | 2007-12-26 | 株式会社日立ハイテクノロジーズ | Biomagnetic field measurement device |
US9709653B2 (en) * | 2013-02-19 | 2017-07-18 | Toshiba Medical Systems Corporation | Mapping eddy current fields in MRI system |
US20190377035A1 (en) * | 2018-06-08 | 2019-12-12 | Asahi Kasei Microdevices Corporation | Magnetic field measurement apparatus, magnetic field measurement method, and storage medium with magnetic field measurement program stored thereon |
CN110074774B (en) * | 2019-04-28 | 2022-04-12 | 漫迪医疗仪器(上海)有限公司 | Analysis method, system, medium and terminal for heart ventricular septal abnormality based on magnetocardiogram |
-
2023
- 2023-10-23 CN CN202311375785.6A patent/CN117100276B/en active Active
Patent Citations (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
USRE32712E (en) * | 1979-08-20 | 1988-07-12 | General Electric Company | Moving gradient zeugmatography |
JP2000217798A (en) * | 1999-02-02 | 2000-08-08 | Hitachi Ltd | Biological magnetic field measuring instrument |
WO2001020477A2 (en) * | 1999-08-28 | 2001-03-22 | Squid Ag | Computer-based method for automatically processing data, especially magnetocardiographic data, of biomagnetic fields |
CN103190898A (en) * | 2013-04-23 | 2013-07-10 | 何怡刚 | Cardiac magnetic signal noise adaptive filtering and eliminating design method |
CN103810381A (en) * | 2014-01-26 | 2014-05-21 | 同济大学 | Coronary heart disease characteristic parameter extracting method based on multichannel magnetocardiogram |
JP2016101264A (en) * | 2014-11-27 | 2016-06-02 | 国立研究開発法人国立循環器病研究センター | Magnetocardiogram device |
CN108697356A (en) * | 2016-02-18 | 2018-10-23 | 生物磁场有限公司 | Vector magnetocardiogram method and vector magnetocardiogram system |
WO2018069287A1 (en) * | 2016-10-11 | 2018-04-19 | Biomagnetik Park Gmbh | Magnetocardiographic method and magnetocardiographic system |
CN106901717A (en) * | 2017-03-01 | 2017-06-30 | 中国科学院上海微系统与信息技术研究所 | Three-dimensional heart source localization method, system and server |
CN107361760A (en) * | 2017-07-12 | 2017-11-21 | 中国科学院上海微系统与信息技术研究所 | The magnetocardiograph of magnetocardiograph diagnostic system and the application system |
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 |
CN108577825A (en) * | 2018-01-11 | 2018-09-28 | 中国科学院上海微系统与信息技术研究所 | A kind of myocardial ischemia lesion locations localization 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 |
WO2020120924A1 (en) * | 2018-12-12 | 2020-06-18 | Icerobotics Ltd | Apparatus and method(s) in biomagnetic measurements |
JP2020156870A (en) * | 2019-03-27 | 2020-10-01 | 旭化成エレクトロニクス株式会社 | Magnetocardiographic measurement apparatus |
CN112515679A (en) * | 2020-12-01 | 2021-03-19 | 北京昆迈医疗科技有限公司 | Unshielded magnetocardiogram device |
CN115337016A (en) * | 2022-08-01 | 2022-11-15 | 苏州卡迪默克医疗器械有限公司 | Method and device for evaluating myocardial ischemia based on current density vector diagram |
Non-Patent Citations (4)
Title |
---|
冠状动脉粥样硬化性心脏病患者特征性的心磁图表现;权薇薇;陆国平;李英梅;沈越;袁;戚文航;;诊断学理论与实践(第06期);全文 * |
基于数据融合的ECT图像重建算法;马敏;王伯波;薛倩;;仪器仪表学报(第12期);全文 * |
心磁图在冠心病诊断中的临床应用;赵丹;陈元禄;刘芳;王建勇;赵春玲;陈庆华;;天津医科大学学报(第02期);全文 * |
新型无液氦心磁图仪操作流程与图像质量影响因素;屠琛琛;《心肺血管病杂志》;第42卷(第7期);758-761 * |
Also Published As
Publication number | Publication date |
---|---|
CN117100276A (en) | 2023-11-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110060774B (en) | Thyroid nodule identification method based on generative confrontation network | |
Wu et al. | A comparison of 1-D and 2-D deep convolutional neural networks in ECG classification | |
CN104523266B (en) | A kind of electrocardiosignal automatic classification method | |
Kaymak et al. | Deep learning for two-step classification of malignant pigmented skin lesions | |
Zhu et al. | Detection of the optic disc in images of the retina using the Hough transform | |
Liu et al. | A framework of wound segmentation based on deep convolutional networks | |
CN109645980A (en) | A kind of rhythm abnormality classification method based on depth migration study | |
CN104424386A (en) | Multi-parameter magnetic resonance image based prostate cancer computer auxiliary identification system | |
CN109925002A (en) | Artificial intelligence echocardiogram data collection system and its collecting method | |
CN113855038B (en) | Electrocardiosignal critical value prediction method and device based on multi-model integration | |
CN113080996B (en) | Electrocardiogram analysis method and device based on target detection | |
CN116304558B (en) | Epileptic brain magnetic map spike detection method and device | |
Dong et al. | Identifying carotid plaque composition in MRI with convolutional neural networks | |
Nayan et al. | A deep learning approach for brain tumor detection using magnetic resonance imaging | |
Xu et al. | Application of artificial intelligence technology in medical imaging | |
CN113069124A (en) | Electrocardio monitoring method based on CNN-ET model | |
CN117100276B (en) | Cardiac function detection system, computer storage medium and terminal | |
Zafar et al. | Deep learning based feature engineering to detect anterior and inferior myocardial infarction using uwb radar data | |
Sane et al. | Detection of myocardial infarction from 12 lead ECG images | |
CN114418999B (en) | Retinopathy detection system based on lesion attention pyramid convolution neural network | |
CN114224354B (en) | Arrhythmia classification method, arrhythmia classification device, and readable storage medium | |
CN115886833A (en) | Electrocardiosignal classification method and device, computer readable medium and electronic equipment | |
Erwin et al. | BVU-Net: A U-net modification by VGG-batch normalization for retinal blood vessel segmentation | |
CN113792740A (en) | Arteriovenous segmentation method, system, equipment and medium for fundus color photography | |
CN114612484A (en) | Retina OCT image segmentation method based on unsupervised learning |
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 |