CN106580307A - Quality judgement method and quality judgement system for electrocardiogram - Google Patents
Quality judgement method and quality judgement system for electrocardiogram Download PDFInfo
- Publication number
- CN106580307A CN106580307A CN201510657536.5A CN201510657536A CN106580307A CN 106580307 A CN106580307 A CN 106580307A CN 201510657536 A CN201510657536 A CN 201510657536A CN 106580307 A CN106580307 A CN 106580307A
- Authority
- CN
- China
- Prior art keywords
- lead
- quality
- electrocardiogram
- signal
- preassigned
- 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.)
- Pending
Links
Abstract
The invention provides a quality judgment method for electrocardiogram. The method comprises the following steps: receiving a 12-lead signal forming electrocardiogram; judging whether the electrocardiogram is valid or not according to the 12-lead signal; and judging the quality of the electrocardiogram according to the 12-lead signal if the electrocardiogram is valid. The invention further provides a quality judgment system for electrocardiogram. When the quality judgement system and quality judgement method for electrocardiogram are applied to electrocardiogram equipment, the electrocardiogram equipment has a lead signal collection function and a lead signal quality judgment function. Furthermore, according to the quality judgement system and quality judgement method, the electrocardiogram of which the quality does not achieve a preset standard is graded, so that important information of the electrocardiogram of which the quality does not achieve the preset standard can be better maintained.
Description
Technical field
The invention belongs to electrocardiogram judgment technology field, specifically, is related to a kind of Electrocardiographic Quality estimation method and Quality estimation system.
Background technology
The lead signals for constituting electrocardiogram (Electrocardiogram, abbreviation ECG) are a kind of faint bio signals, wherein, lead signals can be subject to the electromagnetic interference of body and instrument during collection and produce noise.For doctor, the worst electrocardiogram of quality can be ignored, and then re-start collection;And second-rate can substantially be used for diagnosing the illness.However, for computer, Electrocardiographic quality affects larger for the diagnosis of disease.Therefore, needed to make the quality of lead signals judge before pretreatment, feature extraction and medical diagnosis on disease is carried out to electrocardiogram.
Existing ecg equipment only possesses lead signals acquisition function and does not possess lead signals quality assessment function, and the quality (i.e. whether the quality of lead signals reaches preassigned) of the lead signals of its collection is passed judgment on completely by the clinical experience of doctor.And, in the gatherer process of lead signals, the quality of lead signals is highly susceptible to anthropic factor and the impact of environmental factorss, therefore for ropy lead signals can only be resurveyed, so, the effectiveness and practicality of the lead signals acquisition system of ecg equipment are not only reduced, and reduces the reliability of the lead signals of collection.
The content of the invention
Above-mentioned of the prior art in order to solve the problems, such as, it is an object of the invention to provide a kind of Electrocardiographic Quality estimation method, it includes:Receive and constitute Electrocardiographic 12 lead signal;Judge whether electrocardiogram is effective according to 12 lead signal;If electrocardiogram effectively, according to 12 lead signal Electrocardiographic quality is judged.
Further, if electrocardiogram is invalid, receive again and constitute Electrocardiographic 12 lead signal.
Further, the Quality estimation method also includes:If Electrocardiographic quality is not up to preassigned, the electrocardiogram for then preassigned being not up to quality according to 12 lead signal carries out grade classification, and the quality being not up in the electrocardiogram of preassigned according to 12 lead signal acquisition quality is not up to the lead signals of preassigned;The quality being not up to quality according to the grade after classification in the electrocardiogram of preassigned is not up to the lead signals of preassigned and carries out different process.
Further, the Quality estimation method also includes:If Electrocardiographic quality reaches preassigned, the Quality estimation method terminates.
Further, judge that the whether effective concrete grammar of electrocardiogram includes according to 12 lead signal:Whether the sampling time for judging each lead signals is not less than a time threshold;If the sampling time of each lead signals is not less than the time threshold, judge whether the sampled point signal that there is no continuous predetermined quantity is zero in each lead signals;If the sampled point signal that there is no continuous predetermined quantity in each lead signals is zero, judge whether that right-hand man's lead is reversed according to 12 lead signal;If not existing, right-hand man's lead is reversed, electrocardiogram is effective.
Further, if at least sampling time of a lead signals is less than the time threshold, if and/or the sampled point signal that there is continuous predetermined quantity in an at least lead signals is zero, if and/or to there is right-hand man's lead reversed, then electrocardiogram is invalid, and receives the Electrocardiographic 12 lead signal of composition again.
Further, judge whether that the reversed concrete grammar of right-hand man's lead includes according to 12 lead signal:Judge whether the first standard limb lead signal and the first augmented limb lead signal in 12 lead signal all have P ripples;If there is P ripples in the first standard limb lead signal and the first augmented limb lead signal, then judge whether the P ripples in the first standard limb lead signal are inverted according to the angle between the maximum and baseline of P ripples, and P ripples in the first augmented limb lead signal whether non-inverted is judged according to the angle between the maximum and baseline of P ripples, wherein, the baseline is the line of P ripples starting point and terminating point;If P ripples in the first standard limb lead signal are inverted, and the P ripple non-inverted in the first augmented limb lead signal, then whether the form for judging the QRS wave of the first chest lead signals to the 6th chest lead signals in 12 lead signal is rS types;If at least one is not rS types in the QRS wave of first chest lead signals to the 6th chest lead signals, there is right-hand man's lead reversed;If the P ripples in the P ripples non-inverted and/or the first augmented limb lead signal in the first standard limb lead signal are inverted and/or first chest lead signals are all rS types to the QRS wave that the 6th chest lead is believed, there is no right-hand man's lead reversed.
Further, if there is no P ripples in the first standard limb lead signal and/or the first augmented limb lead signal, Electrocardiographic quality is judged according to 12 lead signal.
Further, the electrocardiogram that preassigned is not up to quality according to 12 lead signal carries out grade classification, and the concrete grammar of the quality being not up in the electrocardiogram of preassigned according to the 12 lead signal acquisition quality lead signals that are not up to preassigned includes:Calculate the signal to noise ratio of each lead signals;Mean square deviation and meansigma methodss are determined according to the signal to noise ratio of 12 lead signal;Electrocardiographic grade is determined according to the mean square deviation, and the signal to noise ratio according to each lead signals and the meansigma methodss obtain the lead signals that quality is not up to preassigned;Wherein, the grade at least includes:The first estate, the second grade and the tertiary gradient.
Further, the quality being not up to quality in the electrocardiogram of preassigned according to the grade after classification is not up to the lead signals of preassigned and carries out the concrete grammar of different process and includes:If the Electrocardiographic grade that quality is not up to preassigned is confirmed as the first estate, the quality being not up to quality using low-pass filtering method in the electrocardiogram of preassigned is not up to the lead signals of preassigned and carries out noise remove;If the Electrocardiographic grade that quality is not up to preassigned is confirmed as the second grade, the quality being not up to quality using wavelet thresholding methods in the electrocardiogram of preassigned is not up to the lead signals of preassigned and carries out noise remove;If the Electrocardiographic grade that quality is not up to preassigned is confirmed as the tertiary gradient, receives again and constitute Electrocardiographic 12 lead signal.
Another object of the present invention also resides in a kind of Electrocardiographic Quality estimation system of offer, and it includes:Receiver module, is configured to receive the Electrocardiographic 12 lead signal of composition;There is invalid judge module, be configured to judge whether electrocardiogram is effective according to 12 lead signal;Quality estimation module, be configured to it is described have invalid judge module to be judged as that electrocardiogram is effective when, Electrocardiographic quality is judged according to 12 lead signal;Grade diversity module, it is configured to be judged as that Electrocardiographic quality is not up to predetermined standard time in the Quality estimation module, the quality that the electrocardiogram for being not up to quality preassigned according to 12 lead signal carries out grade classification and is not up in the electrocardiogram of preassigned according to 12 lead signal acquisition quality is not up to the lead signals of preassigned;Processing module, is configured to be not up to the grade after the electrocardiogram of preassigned is graded according to quality, and the quality being not up to quality in the electrocardiogram of preassigned is not up to the lead signals of preassigned and processes.
Beneficial effects of the present invention:When the Electrocardiographic Quality estimation system and Quality estimation method of the present invention are applied to ecg equipment, ecg equipment can be made not only to possess lead signals acquisition function and to be also equipped with lead signals quality assessment function.Further, Quality estimation system of the invention and Quality estimation method have carried out grade staged care due to the electrocardiogram that preassigned is not up to quality so that quality is not up to the Electrocardiographic important information of preassigned can preferably be retained.
Description of the drawings
By combining the following description that accompanying drawing is carried out, above and other aspect of embodiments of the invention, feature and advantage will become clearer from, in accompanying drawing:
Fig. 1 is the flow chart of the Electrocardiographic Quality estimation method of first embodiment of the invention;
Fig. 2 is that first embodiment of the invention judges the whether effective flow chart of electrocardiogram;
Fig. 3 is the flow chart reversed with the presence or absence of right-hand man's lead of first embodiment of the invention;
Fig. 4 is the flow chart of Electrocardiographic Quality estimation method according to the second embodiment of the present invention;
Fig. 5 be according to the second embodiment of the present invention judge the whether effective flow chart of electrocardiogram;
Fig. 6 is the flow chart reversed with the presence or absence of right-hand man's lead according to the second embodiment of the present invention;
Fig. 7 is the module map of Electrocardiographic Quality estimation system according to the third embodiment of the invention.
Specific embodiment
Hereinafter, with reference to the accompanying drawings to describing embodiments of the invention in detail.However, it is possible in many different forms implementing the present invention, and the present invention should not be construed as limited to the specific embodiment that illustrates here.On the contrary, there is provided these embodiments are in order to explain the principle and its practical application of the present invention, so that others skilled in the art are it will be appreciated that various embodiments of the present invention and the various modifications for being suitable for specific intended application.
<First embodiment>
Fig. 1 is the flow chart of the Electrocardiographic Quality estimation method of first embodiment of the invention.
With reference to Fig. 1, in step sl, receive and constitute Electrocardiographic 12 lead signal.
In the present embodiment, this 12 lead signals include:First standard limb lead signal (i.e. standard I lead signals), second standard limb lead signal (i.e. standard II lead signals), 3rd standard limb lead signal (i.e. standard III lead signals), first augmented limb lead signal (aVR lead signals), second augmented limb lead signal (aVL lead signals), 3rd augmented limb lead signal (aVF lead signals), first chest lead signals (V1 lead signals), second chest lead signals (V2 lead signals), 3rd chest lead signals (V3 lead signals), 4th chest lead signals (V4 lead signals), 5th chest lead signals (V5 lead signals), 6th chest lead signals (V6 lead signals).
Additionally, in the present embodiment, constituting Electrocardiographic 12 lead signal can gather from Chinese cardiovascular disease data base (Chinese Cardiovascular Disease Database, abbreviation CCDD), but the present invention is not restricted to this.
In step s 2, judge whether the electrocardiogram that this 12 lead signal is constituted is effective according to the 12 lead signal for receiving.
In the present embodiment, if electrocardiogram is invalid, return to step S1;If electrocardiogram effectively, carries out step S3.
Fig. 2 is that first embodiment of the invention judges the whether effective flow chart of electrocardiogram.With reference to Fig. 2, further, in step s 2, judge that the whether effective concrete grammar of electrocardiogram includes according to 12 lead signal:
Step S21:Whether the sampling time for judging each lead signals is all not less than a time threshold (wherein, the time threshold can be for example 9 seconds).
If at least sampling time of a lead signals is less than the time threshold, electrocardiogram is invalid, and return to step S1.If the sampling time of each lead signals is not less than the time threshold, step S22 is carried out.
Step S22:Judge that the sampled point signal (here, can be for example 200 sampled point signals) that whether there is no continuous predetermined quantity in each lead signals is zero.
If the sampled point signal that there is continuous predetermined quantity in an at least lead signals is zero, electrocardiogram is invalid, and return to step S1.
If the sampled point signal that there is no continuous predetermined quantity in each lead signals is zero, step S23 is carried out.
Step S23:Judge whether that right-hand man's lead is reversed according to 12 lead signal.
If existing, right-hand man's lead is reversed, electrocardiogram is invalid, and return to step S1.
If it is reversed to there is no right-hand man's lead, electrocardiogram effectively, and carries out step S3.
Fig. 3 is the flow chart reversed with the presence or absence of right-hand man's lead of first embodiment of the invention.With reference to Fig. 3, further, in step S23, judge whether that the reversed concrete grammar of right-hand man's lead includes:
Step S231:Judge whether all there is P ripples in the first standard limb lead signal and the first augmented limb lead signal in this 12 lead signal.
Wherein, if at least one there is no P ripples in the first standard limb lead signal and the first augmented limb lead signal, step S3 is carried out.
If there is P ripples in the first standard limb lead signal and the first augmented limb lead signal, step S232 is carried out.
Step S232:Judge whether the P ripples in the first standard limb lead signal are inverted according to the angle between the maximum and baseline of P ripples, and P ripples in the first augmented limb lead signal whether non-inverted is judged according to the angle between the maximum and baseline of P ripples, wherein, the baseline is the line of P ripples starting point and terminating point.
Here, if the P ripples on the first standard limb lead signal with 1/3rd are inverted, the P ripples in the first standard limb lead signal are inverted.Similarly, if the P ripples on the first augmented limb lead signal with 1/3rd are inverted, the P ripples in the first augmented limb lead signal are inverted.
If the P ripples in the first standard limb lead signal are inverted, and the P ripple non-inverted in the first augmented limb lead signal, then step S233 is carried out.
If the P ripples in the P ripples non-inverted and/or the first augmented limb lead signal in the first standard limb lead signal are inverted, step S3 is carried out.
Step S233:Whether the form for judging the QRS wave of the first chest lead signals to the 6th chest lead signals in this 12 lead signals is rS types.
If at least one is not rS types in the QRS wave of the first chest lead signals to the 6th chest lead signals, right-hand man's lead is reversed, and electrocardiogram is invalid, and return to step S1.
If being rS types in the QRS wave of the first chest lead signals to the 6th chest lead signals, it is reversed to there is no right-hand man's lead, and carries out step S3.
With continued reference to Fig. 1, in step s3, Electrocardiographic quality is judged according to 12 lead signal.
Further, in step s3, judge that the concrete grammar of Electrocardiographic quality includes according to 12 lead signal:First, to be used as training some original electrocardiographicdigital figures lead signals (wherein, the lead signals of original electrocardiographicdigital figure described here are used as training, the 12 lead signal of the above-mentioned reception not implied that) skipN point is skipped, the data of middle continuous N1 point are taken as input data.Additionally, in the lead signals of some original electrocardiographicdigital figures, only retaining the data of the lead signals of the original electrocardiographicdigital figure of eight types, the lead signals of the original electrocardiographicdigital figure of this eight type are II, III, V1, V2, V3, V4, V5, V6 lead signals.(5 points having more herein are respectively finally to be organized into a 560*1905:The recording mechanism of twelve-lead electrocardiogram, 1, the number of the lead that tissue data are adopted, the sampling number N1 of each lead, (0 is normal to classification, i.e., quality reaches preassigned;1 is abnormal, i.e., quality is not up to preassigned)) training matrix, wherein positive and negative sample proportion is 1:1.In the present embodiment, feq takes 200, skipN and takes 25, N1 and takes 1900, but the present invention is not restricted to this.
Then, using " Jin Linpeng, the Dong Jun of prior art.Towards the Deep Learning algorithm of Clinical ElectrocardiographicAnalysis Analysis.Chinese science:Information science, the 3rd phase of volume 45 in 2015:Lead convolutional neural networks (Lead Convolutional Neural Network, abbreviation LCNN) method in 398-416 " is trained to the training matrix organized, so as to obtain a weight (can also be referred to as model).
Afterwards, the 12 lead data for receiving are put in model according to the matrix that the processing method of training data is organized into 1*1905 and are tested.If test output result is 0, then it represents that the electrocardio plot quality is preferable;If test output result is 1, then it represents that the electrocardio plot quality is not up to preassigned.
In sum, when the Electrocardiographic Quality estimation method of first embodiment of the invention is applied to ecg equipment, ecg equipment can be made not only to possess lead signals acquisition function and is also equipped with lead signals quality assessment function.
<Second embodiment>
Fig. 4 is the flow chart of Electrocardiographic Quality estimation method according to the second embodiment of the present invention.
With reference to Fig. 4, in step sl, receive and constitute Electrocardiographic 12 lead signal.
In the present embodiment, this 12 lead signals include:First standard limb lead signal (i.e. standard I lead signals), second standard limb lead signal (i.e. standard II lead signals), 3rd standard limb lead signal (i.e. standard III lead signals), first augmented limb lead signal (aVR lead signals), second augmented limb lead signal (aVL lead signals), 3rd augmented limb lead signal (aVF lead signals), first chest lead signals (V1 lead signals), second chest lead signals (V2 lead signals), 3rd chest lead signals (V3 lead signals), 4th chest lead signals (V4 lead signals), 5th chest lead signals (V5 lead signals), 6th chest lead signals (V6 lead signals).
Additionally, in the present embodiment, constituting Electrocardiographic 12 lead signal can gather from Chinese cardiovascular disease data base (Chinese Cardiovascular Disease Database, abbreviation CCDD), but the present invention is not restricted to this.
In step s 2, judge whether the electrocardiogram that this 12 lead signal is constituted is effective according to the 12 lead signal for receiving.Here, if electrocardiogram is invalid, return to step S1;If electrocardiogram effectively, carries out step S3 to step S6.
Fig. 5 be according to the second embodiment of the present invention judge the whether effective flow chart of electrocardiogram.With reference to Fig. 5, further, in step s 2, judge that the whether effective concrete grammar of electrocardiogram includes according to 12 lead signal:
Step S21:Whether the sampling time for judging each lead signals is all not less than a time threshold (wherein, the time threshold can be for example 9 seconds).
If at least sampling time of a lead signals is less than the time threshold, electrocardiogram is invalid, and return to step S1.If the sampling time of each lead signals is not less than the time threshold, step S22 is carried out.
Step S22:Judge that the sampled point signal (here, can be for example 200 sampled point signals) that whether there is no continuous predetermined quantity in each lead signals is zero.
If the sampled point signal that there is continuous predetermined quantity in an at least lead signals is zero, electrocardiogram is invalid, and return to step S1.
If the sampled point signal that there is no continuous predetermined quantity in each lead signals is zero, step S23 is carried out.
Step S23:Judge whether that right-hand man's lead is reversed according to 12 lead signal.
If existing, right-hand man's lead is reversed, electrocardiogram is invalid, and return to step S1.
If it is reversed to there is no right-hand man's lead, electrocardiogram effectively, and carries out step S3.
Fig. 6 is the flow chart reversed with the presence or absence of right-hand man's lead according to the second embodiment of the present invention.With reference to Fig. 6, further, in step S23, judge whether that the reversed concrete grammar of right-hand man's lead includes:
Step S231:Judge whether all there is P ripples in the first standard limb lead signal and the first augmented limb lead signal in this 12 lead signal.
Wherein, if at least one there is no P ripples in the first standard limb lead signal and the first augmented limb lead signal, step S3 is carried out.
If there is P ripples in the first standard limb lead signal and the first augmented limb lead signal, step S232 is carried out.
Step S232:Judge whether the P ripples in the first standard limb lead signal are inverted according to the angle between the maximum and baseline of P ripples, and P ripples in the first augmented limb lead signal whether non-inverted is judged according to the angle between the maximum and baseline of P ripples, wherein, the baseline is the line of P ripples starting point and terminating point.
Here, if the P ripples on the first standard limb lead signal with 1/3rd are inverted, the P ripples in the first standard limb lead signal are inverted.Similarly, if the P ripples on the first augmented limb lead signal with 1/3rd are inverted, the P ripples in the first augmented limb lead signal are inverted.
If the P ripples in the first standard limb lead signal are inverted, and the P ripple non-inverted in the first augmented limb lead signal, then step S233 is carried out.
If the P ripples in the P ripples non-inverted and/or the first augmented limb lead signal in the first standard limb lead signal are inverted, step S3 is carried out.
Step S233:Whether the form for judging the QRS wave of the first chest lead signals to the 6th chest lead signals in this 12 lead signals is rS types.
If at least one is not rS types in the QRS wave of the first chest lead signals to the 6th chest lead signals, right-hand man's lead is reversed, and electrocardiogram is invalid, and return to step S1.
If being rS types in the QRS wave of the first chest lead signals to the 6th chest lead signals, it is reversed to there is no right-hand man's lead, and carries out step S3.
With continued reference to Fig. 4, in step s3, Electrocardiographic quality is judged according to 12 lead signal.
Further, in step s3, judge that the concrete grammar of Electrocardiographic quality includes according to 12 lead signal:
First, to be used as training some original electrocardiographicdigital figures lead signals (wherein, the lead signals of original electrocardiographicdigital figure described here are used as training, the 12 lead signal of the above-mentioned reception not implied that) skipN point is skipped, the data of middle continuous N1 point are taken as input data.Additionally, in the lead signals of some original electrocardiographicdigital figures, only retaining the data of the lead signals of the original electrocardiographicdigital figure of eight types, the lead signals of the original electrocardiographicdigital figure of this eight type are II, III, V1, V2, V3, V4, V5, V6 lead signals.(5 points having more herein are respectively finally to be organized into a 560*1905:The recording mechanism of twelve-lead electrocardiogram, 1, the number of the lead that tissue data are adopted, the sampling number N1 of each lead, (0 is normal to classification, i.e., quality reaches preassigned;1 is abnormal, i.e., quality is not up to preassigned)) training matrix, wherein positive and negative sample proportion is 1:1.In the present embodiment, feq takes 200, skipN and takes 100, N1 and takes 1900, but the present invention is not restricted to this.
Then, using " Jin Linpeng, the Dong Jun of prior art.Towards the Deep Learning algorithm of Clinical ElectrocardiographicAnalysis Analysis.Chinese science:Information science, the 3rd phase of volume 45 in 2015:Lead convolutional neural networks (Lead Convolutional Neural Network, abbreviation LCNN) method in 398-416 " is trained to the training matrix organized, so as to obtain a weight (can also be referred to as model).
Afterwards, the 12 lead data for receiving are put in model according to the matrix that the processing method of training data is organized into 1*1905 and are tested.If test output result is 0, then it represents that the electrocardio plot quality is preferable;If test output result is 1, then it represents that the electrocardio plot quality is not up to preassigned.
With continued reference to Fig. 4, after step S3 has been carried out, if Electrocardiographic quality reaches preassigned, step S6 is directly carried out;If Electrocardiographic quality is not up to preassigned, step S4 is carried out to step S6.
In step s 4, the electrocardiogram for preassigned being not up to quality according to 12 lead signal carries out grade classification, and the quality being not up in the electrocardiogram of preassigned according to 12 lead signal acquisition quality is not up to the lead signals of preassigned.
Specifically, the electrocardiogram for preassigned being not up to quality according to 12 lead signal carries out grade classification, and the concrete grammar of the quality being not up in the electrocardiogram of preassigned according to the 12 lead signal acquisition quality lead signals that are not up to preassigned includes:
First, the signal to noise ratio snr of each lead signals is calculated.
Specifically, as an example, by each lead signals y (n), (wherein, n is one of 12 lead signal, that is n=1,2,3, ..., the baseline in addition to characteristic point 12) is all zeroed, and obtains clean lead signals x (n).The signal to noise ratio of each lead signals is obtained using lead signals x (n)
Wherein, N is sampled point.
Then, mean square deviation MSE and meansigma methodss E are determined according to the signal to noise ratio snr of 12 lead signal.
Specifically, as an example, meansigma methodss
Mean square deviation
Wherein, the signal ratio of the n-th lead signals of SNR (n) expressions, n=1,2,3 ... ..., 12.
Then, Electrocardiographic grade is determined according to mean square deviation MSE, and the signal to noise ratio snr (n) according to each lead signals and meansigma methodss E obtain the lead signals that quality is not up to preassigned.
Specifically, as an example, when MSE/5 is less than 1, the quality is not up to the electrocardiogram of preassigned and is judged as the first estate;When MSE/5 is more than or equal to 1 and during less than or equal to 2, the quality is not up to the electrocardiogram of preassigned and is judged as the second grade;When MSE/5 is more than 2, the quality is not up to the electrocardiogram of preassigned and is judged as the tertiary gradient.
In the present embodiment, constitute in Electrocardiographic 12 lead signal that at least a lead signals quality is not up to preassigned, so the electrocardio plot quality is not up to preassigned, that is, constitute quality be not up in the Electrocardiographic 12 lead signal of preassigned be not each lead signals quality it is all poor.Further, if the signal to noise ratio snr (n) of the n-th lead signals is less than 1 with the ratio (SNR (n)/E) of meansigma methodss E, the quality of the n-th lead signals is not up to preassigned;If the signal to noise ratio snr (n) of the n-th lead signals is not less than 1 with the ratio (SNR (n)/E) of meansigma methodss E, the quality of the n-th lead signals reaches preassigned.
With continued reference to Fig. 4, in step s 5, the quality being not up to quality according to the grade after classification in the electrocardiogram of preassigned is not up to the lead signals of preassigned and carries out different process.
In the present embodiment, the quality being not up to quality in the electrocardiogram of preassigned according to the grade after classification is not up to the lead signals of preassigned and carries out the concrete grammar of different process and includes:If the electrocardiogram that quality is not up to preassigned is confirmed as the first estate, the quality being not up to quality using low-pass filtering method in the electrocardiogram of preassigned is not up to the lead signals of preassigned and carries out noise remove;If quality is not up to the electrocardiogram of preassigned is confirmed as the second grade, the quality being not up to quality using wavelet thresholding methods in the electrocardiogram of preassigned is not up to the lead signals of preassigned and carries out noise remove;If quality is not up to the electrocardiogram of preassigned is confirmed as the tertiary gradient, return to step S1.
Step S6:Electrocardiographic Quality estimation method according to the second embodiment of the present invention terminates, and the electrocardiogram or the quality Jing after the process of step S5 for reaching preassigned according to quality is not up to the electrocardiogram of preassigned and carries out feature extraction and the classification of diseases in later stage.
In sum, when Electrocardiographic Quality estimation method according to the second embodiment of the present invention is applied to ecg equipment, ecg equipment can be made not only to possess lead signals acquisition function and is also equipped with lead signals quality assessment function.Further, because the electrocardiogram that preassigned is not up to quality has carried out grade staged care so that quality is not up to the Electrocardiographic important information of preassigned can preferably be retained.
<3rd embodiment>
Fig. 7 is the module map of Electrocardiographic Quality estimation system according to the third embodiment of the invention.
With reference to Fig. 7, Electrocardiographic Quality estimation system according to the third embodiment of the invention includes:Receiver module 10, there are invalid judge module 20, Quality estimation module 30, grade diversity module 40, processing module 50.
Receiver module 10 is configured to receive and constitutes Electrocardiographic 12 lead signal.The description that the signal kinds that this 12 lead signals are specifically included refer in above-mentioned steps S1.
There is invalid judge module 20 to be configured to judge whether electrocardiogram is effective according to 12 lead signal.In the present embodiment, invalid judge module 20 is further configured to judge whether electrocardiogram is effective using the method for above-mentioned steps S2.
If there is invalid judge module 20 to be judged as electrocardiogram effectively, Quality estimation module 30 is configured to judge Electrocardiographic quality according to 12 lead signal.In the present embodiment, Quality estimation module 30 is further configured to judge Electrocardiographic quality using the method for above-mentioned step S3.
If Quality estimation module 30 is judged as that Electrocardiographic quality is not up to preassigned, then grade diversity module 40 carries out grade classification according to the electrocardiogram that 12 lead signal is not up to preassigned to quality, and grade diversity module 40 is not up to the lead signals of preassigned according to the quality that 12 lead signal acquisition quality is not up in the electrocardiogram of preassigned.In the present embodiment, the electrocardiogram that grade diversity module 40 is further configured to be not up to quality preassigned using the method for above-mentioned step S4 carries out grade classification, and grade diversity module 40 is further configured to obtain the lead signals that the quality that quality is not up in the electrocardiogram of preassigned is not up to preassigned using the method for above-mentioned step S4
Processing module 40 is configured to be not up to the grade after the electrocardiogram of preassigned is graded according to quality, and the quality being not up to quality in the electrocardiogram of preassigned is not up to the lead signals of preassigned and processes.In the present embodiment, the quality that processing module 40 is further configured to be not up to quality in the electrocardiogram of preassigned using the method for above-mentioned step S5 is not up to the lead signals of preassigned and processes.
The application be with reference to according to the method and apparatus (system) of the embodiment of the present application come what is described.It should be understood that can by computer program instructions combining information sensing apparatus flowchart and/or each flow process and/or square frame and flow chart in block diagram and/or the flow process in block diagram and/or square frame combination.These computer program instructions can be provided to the processor of general purpose computer, special-purpose computer, Embedded Processor or other programmable data processing devices to produce a machine so that coordinate information induction equipment to produce the device of the function of specifying in one flow process of flow chart or one square frame of multiple flow processs and/or block diagram or multiple square frames for realization by the instruction of the computing device of computer or other programmable data processing devices.
These computer program instructions may be alternatively stored in can be guided in the computer-readable memory that computer or other programmable data processing devices work in a specific way, so that the instruction being stored in the computer-readable memory produces the manufacture for including command device, the command device realizes the function of specifying in one flow process of flow chart or one square frame of multiple flow processs and/or block diagram or multiple square frames.
These computer program instructions also can be loaded in computer or other programmable data processing devices, so that series of operation steps is performed on computer or other programmable devices to produce computer implemented process, the step of offer for realizing the function of specifying in one flow process of flow chart or one square frame of multiple flow processs and/or block diagram or multiple square frames so as to the instruction performed on computer or other programmable devices.
In a typical configuration, computing device includes one or more processors (CPU), input/output interface, network interface and internal memory.
Internal memory potentially includes the volatile memory in computer-readable medium, the such as form such as random access memory (RAM) and/or Nonvolatile memory, read only memory (ROM) or flash memory (flash RAM).Internal memory is the example of computer-readable medium.
Computer-readable medium includes that permanent and non-permanent, removable and non-removable media can realize information Store by any method or technique.Information can be computer-readable instruction, data structure, the module of program or other data.The example of the storage medium of computer includes, but it is not limited to phase transition internal memory (PRAM), static RAM (SRAM), dynamic random access memory (DRAM), other kinds of random access memory (RAM), read only memory (ROM), Electrically Erasable Read Only Memory (EEPROM), fast flash memory bank or other memory techniques, read-only optical disc read only memory (CD-ROM), digital versatile disc (DVD) or other optical storages, magnetic cassette tape, tape magnetic rigid disk is stored or other magnetic storage apparatus or any other non-transmission medium, can be used to store the information that can be accessed by a computing device.Define according to herein, computer-readable medium does not include temporary computer readable media (transitory media), the such as data signal and carrier wave of modulation.
It can further be stated that, term " including ", "comprising" or its any other variant are intended to including for nonexcludability, so that a series of process, method, commodity or equipment including key elements not only includes those key elements, but also including other key elements being not expressly set out, or also include the key element intrinsic for this process, method, commodity or equipment.In the absence of more restrictions, the key element for being limited by sentence "including a ...", it is not excluded that also there is other identical element in the process including the key element, method, commodity or equipment.
Although illustrating and describing the present invention with reference to specific embodiment, it should be appreciated by those skilled in the art that:In the case of without departing from the spirit and scope of the present invention limited by claim and its equivalent, can the here various change that carries out in form and details.
Claims (10)
1. a kind of Electrocardiographic Quality estimation method, it is characterised in that include:
Receive and constitute Electrocardiographic 12 lead signal;
Judge whether electrocardiogram is effective according to 12 lead signal;
If electrocardiogram effectively, according to 12 lead signal Electrocardiographic quality is judged.
2. Quality estimation method according to claim 1, it is characterised in that if electrocardiogram is invalid,
Again receive and constitute Electrocardiographic 12 lead signal.
3. Quality estimation method according to claim 1 and 2, it is characterised in that also include:
It is not up to predetermined to quality according to 12 lead signal if Electrocardiographic quality is not up to preassigned
The electrocardiogram of standard carries out grade classification, and is not up to preassigned according to 12 lead signal acquisition quality
Quality in electrocardiogram is not up to the lead signals of preassigned;
The not up to pre- calibration of quality quality being not up to according to the grade after classification in the electrocardiogram of preassigned
Accurate lead signals carry out different process.
4. Quality estimation method according to claim 1, it is characterised in that according to 12 lead signal
Judge that the whether effective concrete grammar of electrocardiogram includes:
Whether the sampling time for judging each lead signals is not less than a time threshold;
If the sampling time of each lead signals is not less than the time threshold, each lead signals are judged
In whether the sampled point signal that there is no continuous predetermined quantity is zero;
If the sampled point signal that there is no continuous predetermined quantity in each lead signals is zero, according to ten
Two lead signals judge whether that right-hand man's lead is reversed;
If not existing, right-hand man's lead is reversed, electrocardiogram is effective.
5. Quality estimation method according to claim 4, it is characterised in that
If at least sampling time of a lead signals is less than in the time threshold, and/or an at least lead signals
The sampled point signal that there is continuous predetermined quantity is zero, and/or to there is right-hand man's lead reversed, then electrocardiogram
It is invalid, and the Electrocardiographic 12 lead signal of composition is received again.
6. the Quality estimation method according to claim 4 or 5, it is characterised in that according to 12 lead
Signal judges whether that the reversed concrete grammar of right-hand man's lead includes:
Judge that the first standard limb lead signal and the first augmented limb lead signal in 12 lead signal are
It is no all to there is P ripples;
If there is P ripples in the first standard limb lead signal and the first augmented limb lead signal,
Then judge that the P ripples in the first standard limb lead signal are according to the angle between the maximum and baseline of P ripples
No inversion, and judged in the first augmented limb lead signal according to the angle between the maximum and baseline of P ripples
P ripples whether non-inverted, wherein, the baseline is the line of P ripples starting point and terminating point;
If the P ripples in the first standard limb lead signal are inverted, and first augmented limb lead is believed
P ripple non-inverted in number, then judge that the first chest lead signals in 12 lead signal are believed to the 6th chest lead
Number the form of QRS wave whether be rS types;
If at least one is not rS in the QRS wave of first chest lead signals to the 6th chest lead signals
, then there is right-hand man's lead reversed in type;
If the P ripples non-inverted and/or first augmented limb lead in the first standard limb lead signal
The QRS wave of the inversion of P ripples and/or first chest lead signals to the 6th chest lead signals in signal is all
It is rS types, then there is no right-hand man's lead reversed.
7. Quality estimation method according to claim 6, it is characterised in that if the first standard limb
There is no P ripples in body lead signals and/or the first augmented limb lead signal, then believed according to 12 lead
Number judge Electrocardiographic quality.
8. Quality estimation method according to claim 3, it is characterised in that according to 12 lead signal
The electrocardiogram of preassigned is not up to quality carries out grade classification, and according to 12 lead signal acquisition quality
Quality not up in the electrocardiogram of preassigned is not up to the concrete grammar bag of the lead signals of preassigned
Include:
Calculate the signal to noise ratio of each lead signals;
Mean square deviation and meansigma methodss are determined according to the signal to noise ratio of 12 lead signal;
Electrocardiographic grade is determined according to the mean square deviation, and the signal to noise ratio according to each lead signals and described
Meansigma methodss obtain the lead signals that quality is not up to preassigned;
Wherein, the grade at least includes:The first estate, the second grade and the tertiary gradient.
9. Quality estimation method according to claim 8, it is characterised in that according to the grade after classification
The quality being not up to quality in the electrocardiogram of preassigned is not up to the lead signals of preassigned and carries out difference
The concrete grammar of process include:
If the Electrocardiographic grade that quality is not up to preassigned is confirmed as the first estate, using low pass filtered
The quality that wave method is not up in the electrocardiogram of preassigned to quality is not up to the lead signals of preassigned and enters
Row noise remove;
If the Electrocardiographic grade that quality is not up to preassigned is confirmed as the second grade, using small echo threshold
The quality that value method is not up in the electrocardiogram of preassigned to quality is not up to the lead signals of preassigned and enters
Row noise remove;
If the Electrocardiographic grade that quality is not up to preassigned is confirmed as the tertiary gradient, structure is received again
Into Electrocardiographic 12 lead signal.
10. a kind of Electrocardiographic Quality estimation system, it is characterised in that include:
Receiver module, is configured to receive the Electrocardiographic 12 lead signal of composition;
There is invalid judge module, be configured to judge whether electrocardiogram is effective according to 12 lead signal;
Quality estimation module, be configured to it is described have invalid judge module to judge that electrocardiogram is effective when, according to
12 lead signal judges Electrocardiographic quality;
Grade diversity module, is configured to judge that Electrocardiographic quality is not up to pre- in the Quality estimation module
Calibration is punctual, the electrocardiogram that preassigned is not up to quality according to 12 lead signal carry out grade classification and
Preassigned is not up to according to the quality that 12 lead signal acquisition quality is not up in the electrocardiogram of preassigned
Lead signals;
Processing module, is configured to be not up to the grade after the electrocardiogram of preassigned is graded according to quality,
The quality being not up to quality in the electrocardiogram of preassigned is not up at the lead signals of preassigned
Reason.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510657536.5A CN106580307A (en) | 2015-10-13 | 2015-10-13 | Quality judgement method and quality judgement system for electrocardiogram |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510657536.5A CN106580307A (en) | 2015-10-13 | 2015-10-13 | Quality judgement method and quality judgement system for electrocardiogram |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106580307A true CN106580307A (en) | 2017-04-26 |
Family
ID=58551904
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510657536.5A Pending CN106580307A (en) | 2015-10-13 | 2015-10-13 | Quality judgement method and quality judgement system for electrocardiogram |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106580307A (en) |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107194200A (en) * | 2017-07-14 | 2017-09-22 | 深圳市德力凯医疗设备股份有限公司 | A kind of selections method, storage medium and the ultrasonic device of ultrasonic system data |
CN107296627A (en) * | 2017-07-14 | 2017-10-27 | 深圳市德力凯医疗设备股份有限公司 | Output intent, storage medium and the ultrasonic device of cerebral-vessel imaging index |
CN107582045A (en) * | 2017-09-06 | 2018-01-16 | 成都心吉康科技有限公司 | Electrocardiogram acquisition method, wearable device and its control method |
CN108158578A (en) * | 2017-12-14 | 2018-06-15 | 北京顺源开华科技有限公司 | Noise segments recognition methods, ECG signal processing method and processing device |
CN108523877A (en) * | 2018-03-23 | 2018-09-14 | 南京中医药大学 | A kind of electrocardiosignal quality discrimination method and its ecg analysis method |
CN108836311A (en) * | 2018-07-13 | 2018-11-20 | 希蓝科技(北京)有限公司 | A kind of whole process can monitor interactive remote cardiac diagnosis method and system |
CN109602415A (en) * | 2018-11-12 | 2019-04-12 | 安徽心之声医疗科技有限公司 | Electrocardio equipment lead based on machine learning is inverted recognition methods |
CN109645981A (en) * | 2018-12-18 | 2019-04-19 | 联想(北京)有限公司 | Data processing method and data processing equipment |
CN109820522A (en) * | 2019-01-22 | 2019-05-31 | 苏州乐轩科技有限公司 | Mood arrangement for detecting, system and method |
CN109948396A (en) * | 2017-12-20 | 2019-06-28 | 深圳市理邦精密仪器股份有限公司 | A kind of beat classification method, beat classification device and electronic equipment |
TWI693063B (en) * | 2019-03-14 | 2020-05-11 | 美商宇心生醫股份有限公司 | Electrocardiogram quick labeling method |
CN111803060A (en) * | 2020-07-14 | 2020-10-23 | 武汉中旗生物医疗电子有限公司 | Electrocardio artifact signal removing method and device |
CN114190951A (en) * | 2021-12-31 | 2022-03-18 | 上海联影医疗科技股份有限公司 | ECG signal processing method, system, device and medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100022903A1 (en) * | 2008-07-28 | 2010-01-28 | Sitzman David A | System and method for signal quality indication and false alarm reduction in ecg monitoring systems |
CN103735259A (en) * | 2013-12-27 | 2014-04-23 | 深圳市理邦精密仪器股份有限公司 | Electrocardio signal quality determination indication method and system |
CN103908244A (en) * | 2014-04-03 | 2014-07-09 | 深圳市理邦精密仪器股份有限公司 | ECG lead wrong connection judging method and device |
CN204260739U (en) * | 2014-09-09 | 2015-04-15 | 广东工业大学 | Electrocardiographic quality of data real-time control system |
CN104783783A (en) * | 2015-04-23 | 2015-07-22 | 康泰医学系统(秦皇岛)股份有限公司 | Method for handheld electrocardio detector to automatically start electrocardiogram recording |
-
2015
- 2015-10-13 CN CN201510657536.5A patent/CN106580307A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100022903A1 (en) * | 2008-07-28 | 2010-01-28 | Sitzman David A | System and method for signal quality indication and false alarm reduction in ecg monitoring systems |
CN101637384A (en) * | 2008-07-28 | 2010-02-03 | 通用电气公司 | System and method for signal quality indication and false alarm reduction in ECG monitoring systems |
CN103735259A (en) * | 2013-12-27 | 2014-04-23 | 深圳市理邦精密仪器股份有限公司 | Electrocardio signal quality determination indication method and system |
CN103908244A (en) * | 2014-04-03 | 2014-07-09 | 深圳市理邦精密仪器股份有限公司 | ECG lead wrong connection judging method and device |
CN204260739U (en) * | 2014-09-09 | 2015-04-15 | 广东工业大学 | Electrocardiographic quality of data real-time control system |
CN104783783A (en) * | 2015-04-23 | 2015-07-22 | 康泰医学系统(秦皇岛)股份有限公司 | Method for handheld electrocardio detector to automatically start electrocardiogram recording |
Non-Patent Citations (1)
Title |
---|
李桥等: "基于信号质量评估和卡尔曼滤波的心率估计算法", 《中国医学物理学杂志》 * |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107296627A (en) * | 2017-07-14 | 2017-10-27 | 深圳市德力凯医疗设备股份有限公司 | Output intent, storage medium and the ultrasonic device of cerebral-vessel imaging index |
CN107194200A (en) * | 2017-07-14 | 2017-09-22 | 深圳市德力凯医疗设备股份有限公司 | A kind of selections method, storage medium and the ultrasonic device of ultrasonic system data |
CN107582045A (en) * | 2017-09-06 | 2018-01-16 | 成都心吉康科技有限公司 | Electrocardiogram acquisition method, wearable device and its control method |
CN108158578A (en) * | 2017-12-14 | 2018-06-15 | 北京顺源开华科技有限公司 | Noise segments recognition methods, ECG signal processing method and processing device |
CN109948396A (en) * | 2017-12-20 | 2019-06-28 | 深圳市理邦精密仪器股份有限公司 | A kind of beat classification method, beat classification device and electronic equipment |
CN108523877A (en) * | 2018-03-23 | 2018-09-14 | 南京中医药大学 | A kind of electrocardiosignal quality discrimination method and its ecg analysis method |
CN108836311A (en) * | 2018-07-13 | 2018-11-20 | 希蓝科技(北京)有限公司 | A kind of whole process can monitor interactive remote cardiac diagnosis method and system |
CN109602415B (en) * | 2018-11-12 | 2022-02-18 | 安徽心之声医疗科技有限公司 | Electrocardio equipment lead inversion identification method based on machine learning |
CN109602415A (en) * | 2018-11-12 | 2019-04-12 | 安徽心之声医疗科技有限公司 | Electrocardio equipment lead based on machine learning is inverted recognition methods |
CN109645981A (en) * | 2018-12-18 | 2019-04-19 | 联想(北京)有限公司 | Data processing method and data processing equipment |
CN109820522A (en) * | 2019-01-22 | 2019-05-31 | 苏州乐轩科技有限公司 | Mood arrangement for detecting, system and method |
TWI693063B (en) * | 2019-03-14 | 2020-05-11 | 美商宇心生醫股份有限公司 | Electrocardiogram quick labeling method |
CN111803060A (en) * | 2020-07-14 | 2020-10-23 | 武汉中旗生物医疗电子有限公司 | Electrocardio artifact signal removing method and device |
CN111803060B (en) * | 2020-07-14 | 2022-12-06 | 武汉中旗生物医疗电子有限公司 | Electrocardio artifact signal removing method and device |
CN114190951A (en) * | 2021-12-31 | 2022-03-18 | 上海联影医疗科技股份有限公司 | ECG signal processing method, system, device and medium |
CN114190951B (en) * | 2021-12-31 | 2023-11-03 | 上海联影医疗科技股份有限公司 | ECG signal processing method, system, device and medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106580307A (en) | Quality judgement method and quality judgement system for electrocardiogram | |
CN110393519B (en) | Electrocardiosignal analysis method and device, storage medium and processor | |
CN110840402B (en) | Atrial fibrillation signal identification method and system based on machine learning | |
CN107837082A (en) | Electrocardiogram automatic analysis method and device based on artificial intelligence self study | |
US20200155024A1 (en) | Detection of electrocardiographic signal | |
US20200178825A1 (en) | System and method for identifying cardiac arrhythmias with deep neural networks | |
EP3692904A1 (en) | Method and device for self-learning dynamic electrocardiography analysis employing artificial intelligence | |
US11617528B2 (en) | Systems and methods for reduced lead electrocardiogram diagnosis using deep neural networks and rule-based systems | |
CN102779234B (en) | A kind of cardiogram classification processing method and device | |
Lee et al. | QRS detection method based on fully convolutional networks for capacitive electrocardiogram | |
CN103006211B (en) | Map mapping device based on brain electrical activity network analysis | |
CN108511055B (en) | Ventricular premature beat recognition system and method based on classifier fusion and diagnosis rules | |
CN110226920B (en) | Electrocardiosignal identification method and device, computer equipment and storage medium | |
CN112329609A (en) | Feature fusion transfer learning arrhythmia classification system based on 2D heart beat | |
CN111345816B (en) | Multi-lead QRS complex detection method, device, equipment and storage medium | |
Kumar et al. | Efficient QRS complex detection algorithm based on Fast Fourier Transform | |
CN107391900A (en) | Atrial fibrillation detection method, disaggregated model training method and terminal device | |
EP3803709A1 (en) | Detecting abnormalities in ecg signals | |
CN107958214A (en) | Parallel parsing device, method and the mobile terminal of ECG signal | |
CN111839506A (en) | Mental load detection method and device | |
CN103190901A (en) | R wave detection algorithm based on extremum field mean mode decomposition and improved Hilbert enveloping | |
Xu et al. | An ECG denoising method based on the generative adversarial residual network | |
CN110327033A (en) | A kind of screening method of the myocardial infarction electrocardiogram based on deep neural network | |
CN117357080A (en) | Near infrared spectrum signal denoising method and device, terminal equipment and storage medium | |
CN116636856A (en) | Electrocardiogram classification method, system, electronic equipment and storage medium |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170426 |
|
RJ01 | Rejection of invention patent application after publication |