CN106923820B - Electrocardiosignal artifact identification method and electrocardiosignal artifact identification device - Google Patents
Electrocardiosignal artifact identification method and electrocardiosignal artifact identification device Download PDFInfo
- Publication number
- CN106923820B CN106923820B CN201710144783.4A CN201710144783A CN106923820B CN 106923820 B CN106923820 B CN 106923820B CN 201710144783 A CN201710144783 A CN 201710144783A CN 106923820 B CN106923820 B CN 106923820B
- Authority
- CN
- China
- Prior art keywords
- electrocardiosignal
- target
- template
- data segment
- points
- 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
- 238000000034 method Methods 0.000 title claims abstract description 46
- 230000000747 cardiac effect Effects 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 13
- 239000011159 matrix material Substances 0.000 claims description 9
- 230000003183 myoelectrical effect Effects 0.000 claims description 7
- 238000004800 variational method Methods 0.000 claims description 4
- 238000013459 approach Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 238000011022 operating instruction Methods 0.000 claims description 2
- 239000000126 substance Substances 0.000 claims description 2
- 238000000354 decomposition reaction Methods 0.000 claims 2
- 230000008569 process Effects 0.000 description 10
- 241000282414 Homo sapiens Species 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000001514 detection method Methods 0.000 description 4
- 208000000418 Premature Cardiac Complexes Diseases 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 239000003814 drug Substances 0.000 description 2
- 208000024172 Cardiovascular disease Diseases 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 238000000718 qrs complex Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Images
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
- A61B5/316—Modalities, i.e. specific diagnostic methods
-
- 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]
-
- 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Signal Processing (AREA)
- Cardiology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Psychiatry (AREA)
- Physiology (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The embodiment of the invention discloses an electrocardiosignal artifact identification method and an electrocardiosignal artifact identification device, which are used for identifying artifacts in acquired electrocardiosignals without any priori knowledge of the electrocardiosignals. The method provided by the embodiment of the invention comprises the following steps: reading original electrocardiosignals; determining a target electrocardiosignal according to the original electrocardiosignal, wherein the target electrocardiosignal is the electrocardiosignal without baseline drift, electromyographic interference and power frequency interference; determining all R points in the target electrocardiosignal according to the target electrocardiosignal; and identifying the artifact of the target electrocardiosignal according to all R points of the target electrocardiosignal.
Description
Technical Field
The invention relates to the field of medicine, in particular to an electrocardiosignal artifact identification method and an electrocardiosignal artifact identification device.
Background
The electrocardiographic signal is one of the biological signals which are researched and applied to medical clinic at the earliest time by human beings, is easier to detect than other biological signals, and has more intuitive regularity, so that the electrocardiographic analysis technology promotes the development of the medicine. Electrocardiographic examination is an important clinical method for diagnosing cardiovascular diseases.
In the process of detecting the electrocardiosignals of the human body, noise is mixed in the finally obtained electrocardiosignals. Some of these noises have a fixed law: such as baseline wander, electromyographic interference, power frequency interference, etc. And another kind of noise is not usually caused by the heart activity of the human body, such as the movement of the hand, the unsmooth contact surface between the hand and the electrode, and the like during the measurement process, and is called as artifact. It is often characterized as a mutation.
The artifact in the electrocardiosignal has great influence on the electrocardiosignal characteristic extraction and the subsequent characteristic analysis. The artifact is the portion of the electrocardiographic signal that is not a change in the electrocardiogram due to electrical activation of the heart. Most of the existing methods for removing the artifact in the electrocardiosignals aim at dynamic electrocardiograms. The dynamic electrocardiogram generally has the characteristic of long measuring time, which is convenient for detection to a certain extent. Secondly, most of the methods are based on approximately extracting non-artifact parts of the electrocardiosignals, then obtaining characteristic values of RR intervals, mean values, variances and the like of QRS complexes, and then detecting the signals one by one according to the values. And determining the electrocardiosignals which do not meet the conditions as false errors.
At present, artifact identification in the electrocardiosignals is mostly faced to dynamic electrocardiograms, and in addition, almost all artifact identification algorithms need certain priori knowledge, for example, the threshold value determining process needs to learn normal electrocardiosignals.
Disclosure of Invention
The embodiment of the invention provides an electrocardiosignal artifact identification method and an electrocardiosignal artifact identification device, which are used for identifying artifacts in collected electrocardiosignals.
The first aspect of the embodiments of the present invention provides a method for identifying artifacts of an electrocardiographic signal, which specifically includes:
reading original electrocardiosignals; determining a target electrocardiosignal according to the original electrocardiosignal, wherein the target electrocardiosignal is the electrocardiosignal without baseline drift, electromyographic interference and power frequency interference; determining all R points in the target electrocardiosignal according to the target electrocardiosignal; and identifying the artifact of the target electrocardiosignal according to all R points of the target electrocardiosignal.
A second aspect of the embodiments of the present invention provides an electrocardiographic signal artifact identification apparatus, including:
the reading module is used for reading an original electrocardiosignal;
the first determination module is used for determining a target electrocardiosignal according to the original electrocardiosignal, wherein the target electrocardiosignal is the electrocardiosignal without baseline drift, electromyographic interference and power frequency interference;
the second determining module is used for determining all R points in the target electrocardiosignal according to the target electrocardiosignal;
and the identification module is used for identifying the artifact of the target electrocardiosignal according to all the R points of the target electrocardiosignal.
A third aspect of the embodiments of the present invention provides an electrocardiographic signal artifact identification apparatus, including:
the device comprises a central processing unit, a memory, a storage medium, a power supply, a wireless network interface and an input/output interface;
the central processor, by invoking operating instructions stored on the memory or storage medium, is configured to perform operations as recited in any of claims 1-9.
According to the technical scheme, the embodiment of the invention has the following advantages: reading original electrocardiosignals; determining a target electrocardiosignal according to the original electrocardiosignal, wherein the target electrocardiosignal is the electrocardiosignal without baseline drift, electromyographic interference and power frequency interference; determining all R points in the target electrocardiosignals according to the target electrocardiosignals; and identifying the artifact of the target electrocardiosignal according to all R points of the target electrocardiosignal. Therefore, only baseline drift, several-point interference and power frequency interference of the original electrocardiosignals need to be removed, then all R points of the electrocardiosignals with the baseline drift, the electromyographic interference and the power frequency interference removed are calibrated, the artifact in the electrocardiosignals can be identified according to all the R points, and the artifact in the electrocardiosignals can be identified without certain priori knowledge.
Drawings
FIG. 1 is a schematic diagram of an embodiment of a method for recognizing artifact of an electrocardiograph signal according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of an embodiment of an apparatus for recognizing artifact of an electrocardiographic signal according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of another embodiment of an apparatus for recognizing artifact of cardiac signals according to an embodiment of the present invention;
fig. 4 is a schematic diagram of a hardware structure of the electrocardiographic signal artifact identification device in the embodiment of the present invention.
Detailed Description
The embodiment of the invention provides an electrocardiosignal artifact identification method and an electrocardiosignal artifact identification device, which are used for quickly identifying artifacts in electrocardiosignals without any priori knowledge.
The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that the embodiments described herein may be practiced otherwise than as specifically illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Referring to fig. 1, an embodiment of a method for recognizing an electrocardiographic signal artifact according to an embodiment of the present invention includes:
101. and reading the original electrocardiosignals.
In this embodiment, in the process of detecting the human electrocardiosignals, the original electrocardiosignals may be read first.
102. And removing baseline drift of the original electrocardiosignals by a secondary variational method to determine first electrocardiosignals.
In this embodiment, after reading the original electrocardiographic signal, the baseline drift in the original electrocardiographic signal may be removed by an entry-correction formula under a limited condition to determine the first electrocardiographic signal:
the limiting strips are as follows:
wherein the content of the first and second substances,
represents the estimated baseline wander signal and is,
representing the acquired signal, p is a non-negative parameter controlling the baseline drift to approach the true signal,the second variational matrix represents the second variational of the signal, z represents the electrocardiosignal after removing the baseline drift, namely the first electrocardiosignal, D represents the second variational matrix, and I represents the unit matrix of the pair size.
103. And removing myoelectric interference and power frequency interference of the first electrocardiosignal by a stationary wavelet transform method to determine the target electrocardiosignal.
In this embodiment, a stationary wavelet transform method may be adopted to remove the electromyographic interference and the power frequency interference, perform stationary wavelet transform on the first cardiac signal, select a preset threshold and an attenuation coefficient, and separate the electromyographic interference and the power frequency interference from the first cardiac signal, so as to remove the electromyographic interference and the power frequency interference.
The electromyographic interference and the power frequency interference in the first electrocardiosignal can be removed through the following formula to determine a target electrocardiosignal:
where α is a free factor with a value of 2.5. Gamma is a threshold value, and Y is the target electrocardiosignal;
calculated by the following formula:
wherein, Wi，jAnd N is the number of sampling points, u is the attenuation coefficient of each layer, and i is the number of layers of the decomposed original signal.
104. And determining all R points in the target electrocardiosignal according to the target electrocardiosignal.
In this embodiment, spline wavelet transform may be performed on the target electrocardiograph signal to determine a wavelet coefficient, a maximum minimum value pair in the wavelet coefficient is determined, and all R points in the target electrocardiograph signal are determined according to the maximum minimum value pair to process the wavelet coefficient to determine all R points in the target electrocardiograph signal. For example, 3 times of spline wavelet transformation can be performed on the target electrocardiosignal, wavelet coefficients Mj3 of the 3 rd layer are selected for analysis, a proper threshold value is selected to remove a relatively small extreme point, a maximum value and minimum value pair is found out from the rest data values, the positions of the original signals corresponding to the maximum value and the minimum value are found out, and the point with the maximum amplitude in the position range of the original signal X corresponding to the maximum value and the minimum value is the R point. After traversing, performing multi-detection point detection and deletion on the Mj3 layer, and when the distance between adjacent R points is too small, determining that the R points are detected more, namely determining the points which are not the R points as the R points, and deleting the R points with smaller amplitude; and when the detected distance between the adjacent R points is too large, the detection is considered to be detected, the presetting is adjusted, the R points are detected again, the threshold value is adjusted in the section of signal, and the R points are detected again according to the steps.
105. And determining the data segment of each R point according to the position reference of all R points in the target electrocardiosignals.
In this embodiment, after obtaining all R points in the target electrocardiographic signal, a respective data segment may be formed with the position of each R point as a reference, and may be implemented by programming:
x (Rpeak (i) -floor ((Rpeak (i) -Rpeak (i-1))/3): Rpeak (i) + floor ((Rpeak (i +1) -Rpeak (i))/2)), wherein Rpeak is an array of abscissa values identifying the R-wave point of the cardiac electrical signal.
106. And judging whether the data segment of each R point is input for the first time, if so, executing the step 107, and if not, executing the step 108.
In this embodiment, after the data segment of each R point is determined based on the position of each R point, a determination may be made when the data segment corresponding to each R point is input, and it is determined whether the data segment of each R point is input for the first time, if yes, step 107 is executed, and if no, step 108 is executed.
107. And taking the data segment corresponding to the R point input for the first time as a first template.
In this embodiment, when it is determined that the data segment corresponding to the R point that is input is the first input, the data segment corresponding to the R point that is input for the first time may be used as the first template.
108. And respectively judging whether the similarity between the data segment of each R point and each template in the template library is smaller than a preset threshold value according to a DTW algorithm, if so, executing a step 112, and if not, executing a step 109 to a step 111.
In this embodiment, when it is determined that the data segment corresponding to the input R point is not primarily input, whether the similarity between the data segment of each R point and each template in the template library is smaller than a preset threshold may be respectively determined according to the DTW algorithm, if yes, step 112 is performed, and if not, steps 109 to 111 are performed.
109. And judging whether the number of the templates in the template library is smaller than a preset value, if so, executing a step 110, and if not, executing a step 111.
In this embodiment, when the similarity between the data segment of each R point and each template in the template library is determined according to the DTW algorithm, and when it is determined that the similarity between the data segment of each R point and each template in the template library is not smaller than the preset threshold, at this time, it may be determined whether the number of templates in the template library is smaller than the preset value, if yes, step 110 is performed, and if no, step 111 is performed.
110. And establishing a new template according to the data segment corresponding to the template with the similarity not less than the preset threshold.
In this embodiment, when it is determined that the number of templates in the template library is smaller than the preset value, a new template may be established for a data segment corresponding to a template whose similarity in the data segment corresponding to each R point is not smaller than the preset threshold.
111. And deleting the template with the minimum similarity between the template in the template library and the data segment of each R point, and establishing a new template according to the data segment corresponding to the template with the similarity not less than a preset threshold value.
In this embodiment, when it is determined that the number of templates in the template library is not less than the preset value, the template with the smallest similarity between the template in the template library and the data segment of each R point may be deleted, and a new template may be established according to the data segment corresponding to the template with the similarity not less than the preset threshold value.
112. And marking the data segment corresponding to the template with the similarity smaller than the preset threshold as the same type as the template with the similarity smaller than the preset threshold.
In this embodiment, after the similarity between the data segment of each R point and each template in the template library is respectively determined according to the DTW algorithm, when it is determined that the similarity with the template in the template library is smaller than the preset threshold, the data segment corresponding to the template whose similarity is smaller than the preset threshold may be marked as the same class as the template whose similarity is smaller than the preset threshold.
It should be noted that the electrocardiographic signal artifact identification device may execute steps 106 to 112 in a loop until all the data segments corresponding to the R points are classified.
113. And counting the frequency of each category of the data segment marks corresponding to all R points in the target electrocardiosignal.
In this embodiment, after the data segments corresponding to all R points in the target electrocardiographic signal are classified, the frequency count of each category of the data segment markers corresponding to all R points in the target electrocardiographic signal may be used.
114. And judging whether the number of each category exceeds two categories, if so, executing step 115, and if not, executing step 116.
In this embodiment, after the frequency counts of each category of the data segment table corresponding to all R points in the target electrocardiographic signal are obtained, it can be determined whether the number of each category exceeds two categories, if yes, step 115 is executed, and if not, step 116 is executed.
115. And marking the category with the least frequency in each category and the category with the second least frequency in each category as the artifact of the target electrocardiosignal.
In this embodiment, when the number of each category exceeds two categories, the category with the lowest frequency number and the category with the second lowest frequency number in each category are marked as the artifact in the target electrocardiographic signal.
116. And determining that no artifact exists in the target electrocardiosignal.
In this embodiment, when the number of each category does not exceed two categories, it is determined that there is no artifact in the target electrocardiographic signal.
It should be noted that, because the magnitude of the similarity between the premature beat signal and the long and long electrocardio signal is between e-4 and e-5, and the magnitude of the similarity between the artifact and the normal electrocardio signal is above e-3, the larger the value calculated by DTW is, the larger the difference is, so that the premature beat signal and the artifact can be easily separated out, and the premature beat signal can be prevented from being mistaken as the artifact.
In summary, it can be seen that, when detecting the human electrocardiosignals, the original electrocardiosignals can be read first; determining a target electrocardiosignal according to the original electrocardiosignal, wherein the target electrocardiosignal is the electrocardiosignal without baseline drift, electromyographic interference and power frequency interference; determining all R points in the target electrocardiosignals according to the target electrocardiosignals; and identifying the artifact of the target electrocardiosignal according to all R points of the target electrocardiosignal. Therefore, only baseline drift, several-point interference and power frequency interference of the original electrocardiosignals need to be removed, then all R points of the electrocardiosignals with the baseline drift, the electromyographic interference and the power frequency interference removed are calibrated, the artifact in the electrocardiosignals can be identified according to all the R points, and the artifact in the electrocardiosignals can be identified without certain priori knowledge.
The embodiment of the present invention is described above from the perspective of a method for identifying an electrocardiographic signal artifact, and is described below from the perspective of an electrocardiographic signal artifact identification device.
Referring to fig. 2, an embodiment of an apparatus for recognizing an electrocardiographic signal artifact according to an embodiment of the present invention includes:
a reading module 201, configured to read an original electrocardiographic signal;
the first determining module 202 is configured to determine a target electrocardiosignal according to an original electrocardiosignal, where the target electrocardiosignal is an electrocardiosignal from which baseline drift, myoelectric interference and power frequency interference are removed;
the second determining module 203 is configured to determine all R points in the target electrocardiographic signal according to the target electrocardiographic signal;
the identifying module 204 is configured to identify artifacts of the target electrocardiograph signal according to all R points of the target electrocardiograph signal.
For ease of understanding, the following detailed description is made in conjunction with fig. 3.
Referring to fig. 3, the apparatus for recognizing an electrocardiographic signal artifact according to an embodiment of the present invention includes:
the reading module 301 is configured to read an original electrocardiographic signal;
the first determining module 302 is configured to determine a target electrocardiosignal according to an original electrocardiosignal, where the target electrocardiosignal is an electrocardiosignal from which baseline drift, myoelectric interference and power frequency interference are removed;
a second determining module 303, configured to determine all R points in the target electrocardiographic signal according to the target electrocardiographic signal;
and the identification module 304 is configured to identify the artifact of the target electrocardiosignal according to all R points of the target electrocardiosignal.
Wherein, the first determining module 302 may further include:
the first removing unit 3021 is configured to remove the baseline wander from the original electrocardiographic signal by a second variational method to determine a first electrocardiographic signal;
the second removing unit 3022 is configured to remove the electromyographic interference and the power frequency interference of the first cardiac electrical signal by the stationary wavelet transform method from the first cardiac electrical signal, so as to determine the target cardiac electrical signal.
The first removing unit 3021 is specifically configured to: under the limiting condition, removing the baseline drift in the original electrocardiosignals by the following formula to determine first electrocardiosignals:
the limiting strips are as follows:
wherein, therein
Represents the estimated baseline wander signal and is,
representing the acquired signal. ρ is a non-negative parameter that controls the baseline drift towards the true signal.
Representing a second variation of the signal; z represents heart after removal of baseline driftThe electrical signal is the first cardiac electrical signal, D represents a quadratic variation matrix, and I represents a unity matrix of pair size.
The second removing unit 3022 is specifically configured to:
removing myoelectric interference and power frequency interference of the first electrocardiosignal by the following formula to determine a target electrocardiosignal:
wherein, alpha is a free factor, the value of which is 2.5, gamma is a threshold value, and Y is the target electrocardiosignal;
calculated by the following formula:
wherein, Wi，jAnd N is the number of sampling points, u is the attenuation coefficient of each layer, and i is the number of layers of the decomposed original signal.
Wherein, the second determining module 303 may further include:
a first determining unit 3031, configured to perform spline wavelet transform on the target electrocardiographic signal to determine a wavelet coefficient;
and the second determining unit 3032 is configured to process the wavelet coefficients to determine all R points in the target electrocardiograph signal.
The second determining unit 3032 is specifically configured to:
determining a maximum value and minimum value pair in the wavelet coefficient;
and determining all R points in the target electrocardiosignal according to the maximum and minimum value pairs.
Wherein, the identifying module 304 may further include:
a third determining unit 3041, configured to determine a data segment of each R point according to all R point references in the target electrocardiograph signal;
a first judging unit 3042 for judging whether the data segment of each R point is input for the first time;
a second judging unit 3043, configured to, if the data segment at each R point is not input for the first time, respectively judge whether the similarity between the data segment at each R point and each template in the template library is smaller than a preset threshold according to the DTW algorithm;
a first marking unit 3044, configured to mark, when there is a template in the template library whose similarity with the template in the template library is smaller than a preset threshold in the data segment of each R point, the data segment corresponding to the template whose similarity is smaller than the preset threshold as the same class as the template whose similarity is smaller than the preset threshold;
a circulating unit 3045, configured to circularly execute the actions of the first determining unit, the second determining unit, and the marking unit until the marking of the data segments corresponding to all R points in the target electrocardiographic signal is classified;
a counting unit 3046, configured to count frequency of each category of the data segment markers corresponding to all R points in the target electrocardiographic signal;
a third judging unit 3047 for judging whether the number of each category exceeds two categories;
a second labeling unit 3048 configured to label, when the number of each category exceeds two, the category with the lowest frequency count in each category and the category with the second lowest frequency count in each category as an artifact of the target electrocardiographic signal;
a first processing unit 3049, configured to, when the data segment of each R point is primarily input, take the data segment corresponding to the R point that is primarily input as a first template;
a fourth judging unit 30410, configured to judge whether the number of templates in the template database is less than a preset value when there is no template whose similarity with the template in the template database is greater than a preset threshold in the data segment of each R point;
the second processing unit 30411, configured to, when the number of templates in the template library is smaller than a preset value, establish a new template according to a data segment corresponding to a template whose similarity is greater than a preset threshold;
the second processing unit 30411 is further configured to delete the template with the smallest similarity between the template in the template library and the data segment of each R point when the number of templates in the template library is not less than the preset value, and create a new template according to the data segment corresponding to the template with the similarity greater than the preset threshold value.
The interaction manner between each module and each unit in the electrocardiograph signal artifact identification apparatus in this embodiment is as described in the embodiment shown in fig. 1, and details are not described here again.
In summary, it can be seen that, when the received electrocardiographic signals need to perform artifact identification, the electrocardiographic signal artifact identification apparatus can read the original electrocardiographic signals through the reading module 301, determine the target electrocardiographic signals according to the original electrocardiographic signals through the first determining module 302, determine all R points in the target electrocardiographic signals according to the target electrocardiographic signals through the second determining module 303, and identify artifacts of the target electrocardiographic signals according to all R points in the target electrocardiographic signals through the identifying module 304. Therefore, when the artifact identification is needed, only the R point in the electrocardiosignal needs to be determined, and no prior knowledge is needed.
Referring to fig. 4, fig. 4 is a schematic structural diagram of an electrocardiograph signal artifact identification apparatus 400 according to an embodiment of the present invention, which may generate relatively large differences due to different configurations or performances, and may include one or more Central Processing Units (CPUs) 422 (e.g., one or more processors) and a memory 432, and one or more storage media 430 (e.g., one or more mass storage devices) storing an application 442 or data 444. Wherein the memory 432 and storage medium 430 may be transient or persistent storage. The program stored on the storage medium 430 may include one or more modules (not shown), each of which may include a series of instruction operations for the server. Still further, the central processor 422 may be configured to communicate with the storage medium 430 to execute a series of instruction operations in the storage medium 430 on the cardiac signal artifact identification device 400.
The cardiac signal artifact identification device 400 may also include one or more power supplies 426, one or more wired or wireless network interfaces 450, one or more input/output interfaces 458, and/or one or more operating systems 441, such as Windows Server, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.
The steps executed by the electrocardiographic signal artifact identification means in the above embodiment may be based on the structure of the electrocardiographic signal artifact identification means shown in fig. 4.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (15)
1. An electrocardiosignal artifact identification method is characterized by comprising the following steps:
reading original electrocardiosignals;
determining a target electrocardiosignal according to the original electrocardiosignal, wherein the target electrocardiosignal is the electrocardiosignal without baseline drift, electromyographic interference and power frequency interference;
determining all R points in the target electrocardiosignal according to the target electrocardiosignal;
identifying the artifact of the target electrocardiosignal according to all R points of the target electrocardiosignal;
the determining a target electrocardiosignal according to the original electrocardiosignal comprises:
removing baseline drift of the original electrocardiosignals by a secondary variational method to determine first electrocardiosignals;
removing myoelectric interference and power frequency interference of the first electrocardiosignal by a stationary wavelet transform method to determine the target electrocardiosignal;
the step of determining the first electrocardiosignal by removing the baseline drift of the original electrocardiosignal through a quadratic variation method comprises the following steps:
under the limiting condition, removing the baseline drift in the original electrocardiosignals by the following formula to determine first electrocardiosignals:
the limiting conditions are as follows:
wherein the content of the first and second substances,
represents the estimated baseline wander signal and is,
representing the acquired signal, p is a non-negative parameter controlling the baseline drift to approach the true signal,
representing the second variational of the signal, z representing the electrocardiosignal without the baseline drift, namely the first electrocardiosignal, D representing a second variational matrix, I representing a unit matrix with corresponding size, and gamma being a threshold value;
calculated by the following formula:
wherein, Wi，jFor decomposed wavelet coefficients, N is the sampleThe number of points u is the attenuation coefficient of each layer, and i is the number of layers obtained by decomposing the original electrocardiosignal X.
2. The method of claim 1, wherein the determining the target electrocardiosignal by removing electromyographic interference and power frequency interference of the first electrocardiosignal through a stationary wavelet transform method comprises:
removing myoelectric interference and power frequency interference of the first electrocardiosignal by the following formula to determine the target electrocardiosignal:
wherein, alpha is a free factor with a value of 2.5, and Y is the target electrocardiosignal.
3. The method of claim 1, wherein said determining all R points in the target cardiac electrical signal from the target cardiac electrical signal comprises:
performing spline wavelet transformation on the target electrocardiosignal to determine a wavelet coefficient;
and processing the wavelet coefficient to determine all R points in the target electrocardiosignal.
4. The method of claim 3, wherein said processing the wavelet coefficients to determine all R points in the target cardiac electrical signal comprises:
determining a maximum minimum value pair in the wavelet coefficients;
and determining all R points in the target electrocardiosignal according to the maximum and minimum value pairs.
5. The method of claim 1, wherein said identifying artifacts of the target cardiac electrical signal based on all R-points of the target cardiac electrical signal comprises:
step 1: determining a data segment of each R point by taking all R points in the target electrocardiosignal as a reference;
step 2: judging whether the data segment of each R point is input for the first time or not;
and step 3: if the data segment of each R point is not input for the first time, respectively judging whether the similarity between the data segment of each R point and each template in the template library is smaller than a preset threshold value according to a DTW algorithm;
and 4, step 4: if the similarity between the data segment of each R point and the template in the template library is smaller than a preset threshold, marking the data segment corresponding to the template with the similarity smaller than the preset threshold as the same class as the template with the similarity smaller than the preset threshold;
circularly executing the step 2 to the step 4 until the marking classification of the data segments corresponding to all R points in the target electrocardiosignal is finished;
counting the frequency of each category of the data segment marks corresponding to all R points in the target electrocardiosignal;
judging whether the number of each category exceeds two categories;
and if so, marking the category with the lowest frequency number in each category and the category with the second lowest frequency number in each category as the artifact of the target electrocardiosignal.
6. The method of claim 5, wherein when the data segment for each R point is a primary input, the method further comprises:
and taking the data segment corresponding to the R point input for the first time as a first template.
7. The method according to claim 5, wherein when the similarity between the data segment of each R point and the template of the template library is not greater than a preset threshold, the method further comprises:
judging whether the number of the templates in the template library is smaller than a preset value or not;
if so, establishing a new template according to the data segment corresponding to the template with the similarity larger than a preset threshold;
if not, deleting the template with the minimum similarity between the template in the template library and the data segment of each R point, and establishing a new template according to the data segment corresponding to the template with the similarity larger than a preset threshold value.
8. An apparatus for recognizing an artifact of an electrocardiographic signal, comprising:
the reading module is used for reading an original electrocardiosignal;
the first determination module is used for determining a target electrocardiosignal according to the original electrocardiosignal, wherein the target electrocardiosignal is the electrocardiosignal without baseline drift, electromyographic interference and power frequency interference;
the second determining module is used for determining all R points in the target electrocardiosignal according to the target electrocardiosignal;
the identification module is used for identifying the artifact of the target electrocardiosignal according to all R points of the target electrocardiosignal;
the first determining module includes:
the first removing unit is used for removing baseline drift of the original electrocardiosignals by a secondary variational method to determine first electrocardiosignals;
the second removing unit is used for removing electromyographic interference and power frequency interference of the first electrocardiosignal by the first electrocardiosignal through a stationary wavelet transform method to determine the target electrocardiosignal;
the first removing unit is specifically configured to:
under the limiting condition, removing the baseline drift in the original electrocardiosignals by the following formula to determine first electrocardiosignals:
the limiting conditions are as follows:
wherein, therein
Represents the estimated baseline wander signal and is,representing the acquired signal; rho is a non-negative parameter for controlling the baseline drift to approach the real signal;
representing a second variation of the signal; z represents the electrocardiosignal without the baseline drift, namely the first electrocardiosignal, D represents a quadratic variation matrix, I represents a unit matrix with corresponding size, and gamma is a threshold value;
calculated by the following formula:
wherein, Wi，jThe number of wavelet coefficients after decomposition is N, the number of sampling points, u, the attenuation coefficient of each layer, and i, the number of layers of the original electrocardiosignal X after decomposition.
9. The apparatus according to claim 8, wherein the second removing unit is specifically configured to:
removing myoelectric interference and power frequency interference of the first electrocardiosignal by the following formula to determine the target electrocardiosignal:
wherein, alpha is a free factor with a value of 2.5, and Y is the target electrocardiosignal.
10. The apparatus according to claim 8, wherein said second determining module comprises:
the first determining unit is used for performing spline wavelet transformation on the target electrocardiosignal to determine a wavelet coefficient;
and the second determining unit is used for processing the wavelet coefficients to determine all R points in the target electrocardiosignal.
11. The apparatus according to claim 10, wherein the second determining unit is specifically configured to:
determining a maximum minimum value pair in the wavelet coefficients;
and determining all R points in the target electrocardiosignal according to the maximum and minimum value pairs.
12. The apparatus according to claim 8, wherein the identification module comprises:
a third determining unit, configured to determine a data segment of each R point with reference to all R points in the target electrocardiographic signal;
the first judging unit is used for judging whether the data segment of each R point is input for the first time or not;
a second judging unit, configured to respectively judge, according to a DTW algorithm, whether the similarity between the data segment of each R point and each template in the template library is smaller than a preset threshold value if the data segment of each R point is not initially input;
a first marking unit, configured to mark, when a similarity between a data segment of each R point and a template in the template library is smaller than a preset threshold, a data segment corresponding to the template with the similarity smaller than the preset threshold as a same class as the template with the similarity smaller than the preset threshold;
a circulation unit, configured to circularly execute the actions of the first determination unit, the second determination unit, and the first marking unit until the marking of the data segments corresponding to all R points in the target electrocardiographic signal is classified;
the counting unit is used for counting the frequency of each category of the data segment marks corresponding to all R points in the target electrocardiosignal;
a third judging unit, configured to judge whether the number of each category exceeds two categories;
and a second marking unit, configured to mark, when the number of each category exceeds two categories, the category with the fewest frequency in each category and the category with the second fewest frequency in each category as the artifact of the target electrocardiograph signal.
13. The cardiac signal artifact identification device as recited in claim 12, wherein the identification module further comprises:
and the first processing unit is used for taking the data segment corresponding to the R point input for the first time as a first template when the data segment of each R point is input for the first time.
14. The cardiac signal artifact identification device as recited in claim 12, wherein the identification module further comprises:
a fourth judging unit, configured to judge whether the number of templates in the template library is smaller than a preset value when there is no template similarity greater than a preset threshold between the data segment of each R point and the template in the template library;
the second processing unit is used for establishing a new template according to the data segment corresponding to the template with the similarity larger than a preset threshold value when the number of the templates in the template library is smaller than a preset value;
the second processing unit is further configured to delete the template with the smallest similarity between the template in the template library and the data segment of each R point when the number of the templates in the template library is not less than a preset value, and establish a new template according to the data segment corresponding to the template with the similarity greater than a preset threshold value.
15. An apparatus for recognizing an artifact of an electrocardiographic signal, comprising:
the device comprises a central processing unit, a memory, a power supply, a wireless network interface and an input/output interface;
the central processor, by invoking operating instructions stored on the memory, is configured to perform the method of any of claims 1 to 7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710144783.4A CN106923820B (en) | 2017-03-10 | 2017-03-10 | Electrocardiosignal artifact identification method and electrocardiosignal artifact identification device |
| PCT/CN2017/079426 WO2018161391A1 (en) | 2017-03-10 | 2017-04-05 | Electrocardiogram signal artifact recognition method, and electrocardiogram signal artifact recognition device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710144783.4A CN106923820B (en) | 2017-03-10 | 2017-03-10 | Electrocardiosignal artifact identification method and electrocardiosignal artifact identification device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106923820A CN106923820A (en) | 2017-07-07 |
| CN106923820B true CN106923820B (en) | 2020-01-17 |
Family
ID=59431954
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710144783.4A Active CN106923820B (en) | 2017-03-10 | 2017-03-10 | Electrocardiosignal artifact identification method and electrocardiosignal artifact identification device |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN106923820B (en) |
| WO (1) | WO2018161391A1 (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109948396B (en) * | 2017-12-20 | 2021-07-23 | 深圳市理邦精密仪器股份有限公司 | Heart beat classification method, heart beat classification device and electronic equipment |
| CN110547786B (en) * | 2018-06-01 | 2020-05-05 | 山东省计算中心（国家超级计算济南中心） | Form recognition method of electrocardiogram waveform based on multi-scale wavelet transform |
| CN110731762B (en) * | 2019-09-18 | 2022-02-08 | 平安科技（深圳）有限公司 | Method, device, computer system and readable storage medium for preprocessing pulse wave based on similarity |
| CN111685759B (en) * | 2020-05-12 | 2022-09-09 | 河北大学 | P, T characteristic wave detection method of electrocardiosignals |
| CN113712525A (en) * | 2020-05-21 | 2021-11-30 | 深圳市理邦精密仪器股份有限公司 | Physiological parameter processing method and device and medical equipment |
| US20230017546A1 (en) * | 2021-07-19 | 2023-01-19 | GE Precision Healthcare LLC | Methods and systems for real-time cycle length determination in electrocardiogram signals |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8718753B2 (en) * | 2010-10-12 | 2014-05-06 | Ki H. Chon | Motion and noise artifact detection for ECG data |
| CN103705234B (en) * | 2013-12-05 | 2015-08-26 | 深圳先进技术研究院 | Demodulation method in ambulatory ecg signal data and device |
| CN103720468B (en) * | 2013-12-05 | 2015-07-29 | 深圳先进技术研究院 | Be applied to artifact identification method and the device of dynamic electrocardiogram (ECG) data |
| CN104545887B (en) * | 2014-12-24 | 2017-10-24 | 深圳先进技术研究院 | The recognition methods of artifact ecg wave form and device |
| CN105726015A (en) * | 2016-01-29 | 2016-07-06 | 武汉朗迪远程医疗科技有限公司 | Intelligent analysis and learning method for electrocardiogram data |
| CN105741305A (en) * | 2016-03-02 | 2016-07-06 | 深圳竹信科技有限公司 | Method and system for filtering electromyographical interference based on stationary wavelet transformation |
| CN105748066B (en) * | 2016-03-03 | 2018-03-16 | 深圳竹信科技有限公司 | A kind of extracting method and device of electro-cardiologic signal waveforms characteristic point |
-
2017
- 2017-03-10 CN CN201710144783.4A patent/CN106923820B/en active Active
- 2017-04-05 WO PCT/CN2017/079426 patent/WO2018161391A1/en active Application Filing
Also Published As
| Publication number | Publication date |
|---|---|
| WO2018161391A1 (en) | 2018-09-13 |
| CN106923820A (en) | 2017-07-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106923820B (en) | Electrocardiosignal artifact identification method and electrocardiosignal artifact identification device | |
| CN108186011B (en) | Atrial fibrillation detection method, atrial fibrillation detection device and readable storage medium | |
| CN109522916B (en) | Cascaded binary classifier for identifying rhythms in a single-lead Electrocardiogram (ECG) signal | |
| US20220142583A1 (en) | Methods and systems to quantify and remove asynchronous noise in biophysical signals | |
| US11051741B2 (en) | Non-invasive detection of coronary heart disease from short single-lead ECG | |
| CN110141218B (en) | Electrocardiosignal classification method, electrocardiosignal classification device, program product and storage medium | |
| WO2007130997A2 (en) | Method and device for filtering, segmenting, compressing and classifying oscillatory signals | |
| CN109948396B (en) | Heart beat classification method, heart beat classification device and electronic equipment | |
| WO2021253709A1 (en) | Electrocardiogram heartbeat classification method and apparatus, and electronic device and medium | |
| Gavrovska et al. | Automatic heart sound detection in pediatric patients without electrocardiogram reference via pseudo-affine Wigner–Ville distribution and Haar wavelet lifting | |
| CN112528783A (en) | Electrocardiogram heartbeat data clustering method and device, electronic equipment and medium | |
| US11344246B2 (en) | Long QT syndrome diagnosis and classification | |
| Ranjan et al. | A unified approach of ECG signal analysis | |
| CN107550484B (en) | Magnetocardiogram signal quality evaluation method and system | |
| Tu et al. | A novel method for automatic identification of motion artifact beats in ECG recordings | |
| EP3730049A1 (en) | Apparatus and method for analyzing electrocardiogram | |
| Zhu et al. | Feature extraction from a novel ECG model for arrhythmia diagnosis | |
| Keenan et al. | Detection of fetal arrhythmias in non-invasive fetal ECG recordings using data-driven entropy profiling | |
| US20230309899A1 (en) | Determination method and determination apparatus for beginning of t-wave, storage medium and computer program product | |
| JP5688309B2 (en) | Biological information analysis apparatus, biological information analysis method, and biological information analysis program | |
| Chen et al. | An automatic R-peak detection method based on hierarchical clustering | |
| CN113171102B (en) | ECG data classification method based on continuous deep learning | |
| CN111345815B (en) | Method, device, equipment and storage medium for detecting QRS wave in electrocardiosignal | |
| Dalvi et al. | Graph search based detection of periodic activations in complex periodic signals: Application in atrial fibrillation electrograms | |
| Pander et al. | Fuzzy-based algorithm for QRS detection |
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 |