CN113974636B - Image target detection-based 12-lead electrocardio electrode plate wearing auxiliary inspection method - Google Patents
Image target detection-based 12-lead electrocardio electrode plate wearing auxiliary inspection method Download PDFInfo
- Publication number
- CN113974636B CN113974636B CN202111366145.XA CN202111366145A CN113974636B CN 113974636 B CN113974636 B CN 113974636B CN 202111366145 A CN202111366145 A CN 202111366145A CN 113974636 B CN113974636 B CN 113974636B
- Authority
- CN
- China
- Prior art keywords
- electrode
- result
- target detection
- error
- image
- 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
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
- A61B5/25—Bioelectric electrodes therefor
- A61B5/279—Bioelectric electrodes therefor specially adapted for particular uses
- A61B5/28—Bioelectric electrodes therefor specially adapted for particular uses for electrocardiography [ECG]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0002—Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network
- A61B5/0004—Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network characterised by the type of physiological signal transmitted
- A61B5/0006—ECG or EEG signals
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/25—Bioelectric electrodes therefor
- A61B5/251—Means for maintaining electrode contact with the body
- A61B5/256—Wearable electrodes, e.g. having straps or bands
-
- 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
- A61B5/25—Bioelectric electrodes therefor
- A61B5/279—Bioelectric electrodes therefor specially adapted for particular uses
- A61B5/28—Bioelectric electrodes therefor specially adapted for particular uses for electrocardiography [ECG]
- A61B5/282—Holders for multiple electrodes
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Animal Behavior & Ethology (AREA)
- Veterinary Medicine (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Artificial Intelligence (AREA)
- Physiology (AREA)
- Cardiology (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Psychiatry (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention discloses a 12-lead electrocardio electrode plate wearing auxiliary inspection method based on image target detection, which comprises the steps of firstly detecting 10 electrode plates in an image by utilizing a target detection network model; then, according to the coordinate relation of the electrode plates, determining the number of each electrode plate in the image; then, carrying out auxiliary inspection on electrode plate wearing by analyzing whether the position relation of each electrode plate in the image meets the specification; and finally, the auxiliary inspection result is worn by the feedback electrode plate in a picture-text combination mode. The invention can be applied to mobile phone App, web page end and other edge ends. Under the condition that remote diagnosis and treatment are not medical, after the electrode plates of the 12-lead electrocardio acquisition device are worn by a user, the image of the wearing condition of the electrode plates can be shot by using a mobile phone or a computer camera, and the wearing condition of the electrode plates can be checked in an auxiliary way by using the method, so that the electrocardio electrode plates can be worn more accurately, and the quality of electrocardio signals acquired in remote diagnosis and treatment is improved.
Description
Technical Field
The invention belongs to the technical field of medical equipment, relates to a 12-lead electrocardio-electrode pad wearing auxiliary inspection method, and in particular relates to a 12-lead electrocardio-electrode pad wearing auxiliary inspection method based on image target detection.
Background
Cardiovascular disease is one of the main causes of death in humans, and cardiovascular health is increasingly gaining attention. Along with the development of network technology, applications such as remote cardiac diagnosis, electrocardiographic monitoring and the like begin to appear. Many of these applications are based on electrocardiographic signal acquisition. With these applications, the user needs to collect the electrocardiograph signal by using the electrocardiograph collection device, and transmit the collected electrocardiograph signal to a remote diagnosis end (remote doctor, intelligent analysis system, etc.) for analysis and diagnosis through a network.
When a user carries out remote diagnosis and treatment at home, the electrocardiosignals are acquired, the electrocardio electrode plates are required to be worn, most of users do not have related training, and the users wear the electrode plates by themselves under the condition that the remote diagnosis and treatment is not medical, so that some deviation can be caused. If the position of the electrode plate is not correct, the quality of the collected electrocardiosignals can be affected, so that the accuracy of electrocardiosignal analysis and diagnosis is affected.
The existing 12-lead electrocardiograph acquisition device requires medical staff to wear electrode plates for patients on site, and under the condition that remote diagnosis and treatment are not medical, a user can only wear electrode patches by himself through a specification, so that some deviations are easy to occur.
Therefore, how to provide an effective and convenient method for home use to assist the user in wearing the electrocardiographic electrode sheet is one of the problems to be solved in the art.
Disclosure of Invention
In order to solve the technical problems, the invention provides a 12-lead electrocardio electrode pad wearing auxiliary checking method based on image target detection, which can carry out auxiliary checking on the electrode pad wearing condition of a 12-lead electrocardio acquisition device and help a user to wear the electrode pad correctly.
The technical scheme adopted by the invention is as follows: a12-lead electrocardio electrode plate wearing auxiliary inspection method based on image target detection comprises the following steps:
step 1: detecting 10 electrode plates in an image by using a target detection network model;
initializing a result of a result array, and storing the detection result in the result array; the result array is an array containing N elements, and N is the number of electrode plates detected in the image by the target detection network model; any result i represents one electrode slice condition detected by the target detection network model, and comprises a score value, a center point x coordinate, a center point y coordinate, a detection frame width and a detection frame height, which are respectively marked as result i, score, result i, x, result i, y, result i, width and result i, height; i is more than or equal to 0 and less than N; ordering the elements in the result array according to the result [ i ]. Score non-ascending order; taking the first 10 elements after sequencing of the result array as a final electrode slice detection result;
step 2: determining the number of each electrode according to the ordering relation between the x coordinate of the center point and the y coordinate of the center point of each electrode slice in the result array, initializing a dictionary data structure, and storing the number and the elements in the corresponding result array as key value pairs in the dictionary;
step 3: according to the position information of each numbered electrode slice in the image in the subject, analyzing whether the relative position relation of the electrode slices meets the wearing requirement of the electrocardio electrode slices in the medical science, and returning an analysis result.
Compared with the prior art, the invention has the beneficial effects that:
(1) The 12-lead electrocardio electrode plate wearing auxiliary inspection method based on image target detection can solve the problem that deviation is easy to occur because a user only can wear the electrode plate by himself through a specification under the condition that remote diagnosis and treatment are not medical care at present.
(2) The 12-lead electrocardio-electrode plate wearing auxiliary inspection method is carried out based on images, so that special hardware equipment is not needed, and the 12-lead electrocardio-electrode plate wearing auxiliary inspection method is convenient to use at home. The invention can be applied to mobile phone App, web page end and other side ends, a user does not need to purchase special equipment, can use a mobile phone or a computer camera to shoot images of the wearing condition of the electrode plate, and can use the method of the invention to carry out auxiliary inspection on the wearing condition of the electrode plate.
Drawings
Fig. 1 is a schematic flow chart of an embodiment of the present invention.
FIG. 2 is a schematic diagram of the result of detecting electrode plates in an image using a target detection model according to an embodiment of the present invention.
Fig. 3 is a schematic diagram of a result of determining a number of each electrode plate according to a coordinate ordering relationship of each electrode plate in an image in an embodiment of the present invention.
Fig. 4 is a schematic diagram of a result of an auxiliary inspection for feeding back electrode pad wear in a graphic combination manner in an embodiment of the present invention.
Detailed Description
In order to facilitate the understanding and practice of the invention, those of ordinary skill in the art will now make further details with reference to the drawings and examples, it being understood that the examples described herein are for the purpose of illustration and explanation only and are not intended to limit the invention thereto.
Remote diagnosis and treatment applications such as remote diagnosis of the heart and electrocardiographic monitoring are all based on electrocardiographic signals, and the applications require a user to acquire electrocardiographic signals by using an electrocardiographic acquisition device. When a user acquires electrocardiosignals by himself, the electrode plates are required to be worn at the correct positions, and then the electrocardiosignals with higher quality can be obtained. Most users are not trained in the related process, so that some deviation is easy to occur when wearing the electrode plates. If deviation occurs, the quality of the collected electrocardiosignals is affected, so that the accuracy of electrocardiosignal analysis and diagnosis is affected. The correct wearing of the electrocardio electrode plates requires that the relative position relation of each electrode plate meets the wearing specification. The basic idea of the 12-lead electrocardiographic electrode patch wearing auxiliary inspection method based on image target detection provided by the invention is that: detecting all electrode slices in the electrode slice wearing image of the user by using the YOLO target detection network model, and analyzing whether the relative position relation of each numbered electrode slice meets the wearing specification of the electrocardio electrode slice after determining the number of each electrode slice in the image, thereby realizing auxiliary inspection of the electrocardio electrode slice wearing.
Referring to fig. 1, the method for assisting in wearing and checking the 12-lead electrocardiographic electrode sheet based on image target detection provided by the invention comprises the following steps:
step 1: and constructing and using a YOLO target detection network model to detect 10 electrode slices in the image.
Firstly, constructing an electrode plate target detection data set, then constructing a YOLO target detection network model for detecting the electrode plate, and training by using the data set to obtain a trained YOLO target detection network model;
the specific implementation comprises the following substeps:
step 1.1: shooting images of a sufficient number of electrode plates in different scenes, and marking each electrode plate in all the images to obtain a target detection data set of the electrode plates;
step 1.2: constructing a YOLO target detection network model for electrode slice detection, and training by using the data set obtained in the step 1.1; during training, the number of categories in the YOLO target detection network model is set to be 1, and the ratio of the length and the width of the anchor in the YOLO target detection network model is set to be 1:1, a step of; and obtaining a trained YOLO target detection network model.
In the embodiment, the electrode plates in the given image are detected by using the trained YOLO target detection network model, so that a detection result can be obtained. result is an array containing N elements, N being the number of electrode pads detected in the image by the YOLO target detection network model. Any result [ i ] (i < N) represents one electrode slice condition detected by the YOLO target detection network model, and comprises a score value, a center point x coordinate, a center point y coordinate, a detection frame width and a detection frame height which are respectively marked as result [ i ]. Score, result [ i ]. X, result [ i ]. Y, result [ i ]. Width and result [ i ]. Height. The acquisition of 12-lead electrocardiosignals requires wearing 10 electrode plates, so that 10 electrode plates are actually arranged in an image. The YOLO target detection network model may be capable of misidentifying certain areas in the image as targets, and the target scores of the misidentification are usually low, so that the elements in result are sorted according to non-ascending order of result [ i ]. Score (0 is less than or equal to i < N), and the first 10 sorted elements are taken as the final electrode slice detection result. An example of the electrode sheet detection result is schematically shown in fig. 2, and solid dots in fig. 2 are positions of each detected electrode sheet in the image.
Step 2: and determining the number of each electrode according to the ordering relation between the x coordinate of the center point and the y coordinate of the center point of each electrode plate in the result array. Firstly initializing a dictionary data structure, wherein the key of the dictionary is an electrode number, and the value of the key is an element in a corresponding result array, and the element is used for storing the result of determining the electrode plate number. And (2) sorting the elements in the result array obtained in the step (1) according to non-descending order of result [ i ]. Y (0 is less than or equal to i < 10). Finally, the following comparison and operation are sequentially carried out:
(1) Comparing the sizes of result 0, x and result 1, x, and marking the smaller electrode as RA electrode and storing it in the subject, and marking the larger electrode as LA electrode and storing it in the subject;
(2) Comparing the sizes of result 2, x and result 3, x, and recording the smaller electrode as V1 electrode and the larger electrode as V2 electrode and the larger electrode in the subject;
(3) Recording result 4 as V3 electrode and storing it in the subject;
(4) Comparing the sizes of result 5, result 6, x and result 7, x, the smaller one is marked as V4 electrode and stored in the subject, the middle one is marked as V5 electrode and stored in the subject, the larger one is marked as V6 electrode and stored in the subject;
(5) Comparing the sizes of result 8. X and result 9. X, the smaller one is marked as "RL" electrode and stored in the subject, and the larger one is marked as "LL" electrode and stored in the subject.
An exemplary illustration of determining electrode sheet numbering results is shown in fig. 3.
Step 3: according to the position information of each numbered electrode slice in the image in the subject, analyzing whether the relative position relation of the electrode slices meets the wearing requirement of the electrocardio electrode slices in the medical science, and returning an analysis result code.
The embodiment sequentially judges the relative position information of the electrode slices as follows:
(1) And judging whether the abscissa of the center points of the V1 to V6 electrode plates increases in sequence. If yes, continuing to execute subsequent judgment; otherwise, the analysis result code analysiresultcode= "error V1 to V6" is returned. The judgment process of whether the abscissa of the center points of the V1 to V6 electrode plates increases gradually is as follows:
wherein the subject [ V i ]X represents the number V in the image i Is the abscissa of the center point of the electrode plate.
(2) And judging whether the ordinate of the center point of the V1 electrode plate and the ordinate of the center point of the V2 electrode plate are equal within the error allowable range. If yes, continuing to execute subsequent judgment; otherwise, the analysis result code analysis result code= "error v1_v2" is returned. The judging process of whether the ordinate of the center point of the V1 electrode plate and the ordinate of the center point of the V2 electrode plate are equal within the error allowable range comprises the following steps:
|dict[V1].y-dict[V2].y|≤α;
wherein, the direct [ V1]. Y and the direct [ V2]. Y respectively represent the ordinate of the center point of the electrode sheet with the serial numbers of V1 and V2 in the image, and alpha is the maximum allowable error value.
(3) And judging whether the maximum value and the minimum value of the ordinate of the center point of the V4, V5 and V6 electrode plates are equal within the error allowable range. If yes, continuing to execute subsequent judgment; otherwise, the analysis result code analysis resultcode= "error v4_v5_v6" is returned. The judging process of whether the maximum value and the minimum value of the ordinate of the center point of the V4, V5 and V6 electrode plates are equal within the error allowable range is as follows:
max(dict[V4].y,dict[V5].y,dict[V6].y)-
min(dict[V4].y,dict[V5].y,dict[V6].y)≤α;
wherein max and min are function symbols, respectively represent maximum and minimum values among a plurality of values, and the differences V4, Y, V5, Y represent the ordinate of the center point of the electrode sheet with the numbers V4, V5 and V6 in the image, and alpha is the maximum allowable error value.
(4) Calculating distance from the center point of the V3 electrode plate to the straight line where the center points of the V2 and V4 electrode plates are located (V3,V2V4) And determine distance (V3,V2V4) Whether or not the error is within the allowable range is 0. If yes, continuing to execute subsequent judgment; otherwise, the analysis result code analysis resultcode= "error v2_v3_v4_type1" is returned. distance (distance) (V3,V2V4) The judging process of whether the error is 0 within the error allowable range is as follows:
distance (V3,V2V4) -α≤0;
where α is the maximum allowable error value.
(5) Calculating distance between center points of V2 and V3 electrode plates (V2,V3) V3 and V4 electrodesDistance between center points of the sheets (V3,V4) And determine distance (V2,V3) And distance (V3,V4) Whether or not the errors are equal within the allowable range. If yes, returning an analysis result code of analysis result code= "correct"; otherwise, the analysis result code analysis resultcode= "error v2_v3_v4_type2" is returned. distance (distance) (V2,V3) And distance (V3,V4) The judging process of whether the two are equal within the allowable error range is as follows:
|distance (V2,V3) -distance (V3,V4) |≤α;
where α is the maximum allowable error.
The allowable error α in this embodiment is one half of the average frame length of 10 electrode sheet targets in the image obtained in step 1. The calculation process of alpha is as follows:
and (2) the width and the height of the ith electrode slice target detection frame obtained in the step (1) are respectively obtained by result [ i ]. Width and result [ i ]. Height.
According to the analysis result code obtained in the step 3, the electrode plate number and the prompt information related to the analysis result code are obtained from the following table, and the result of the auxiliary examination for wearing the electrocardio electrode plate is fed back in a mode of combining images and texts. An example schematic diagram of the auxiliary inspection result of the feedback electrode sheet wearing in a graphic combination mode is shown in fig. 4.
In fig. 4, the electrode sheet with the problem is framed and corresponding prompt information is given.
The method of the invention can be applied to mobile phone App, web page end and other edge ends. Under the condition that remote diagnosis and treatment are not medical, after the electrode plates of the 12-lead electrocardio acquisition device are worn by a user, the image of the wearing condition of the electrode plates can be shot by using a mobile phone or a computer camera, and the wearing condition of the electrode plates can be checked in an auxiliary way by using the method, so that the electrocardio electrode plates can be worn more accurately, and the quality of electrocardio signals acquired in remote diagnosis and treatment is improved.
It should be understood that the foregoing description of the preferred embodiments is not intended to limit the scope of the invention, but rather to limit the scope of the claims, and that those skilled in the art can make substitutions or modifications without departing from the scope of the invention as set forth in the appended claims.
Claims (4)
1. The 12-lead electrocardio electrode plate wearing auxiliary inspection method based on image target detection is characterized by comprising the following steps of:
step 1: detecting 10 electrode plates in an image by using a target detection network model;
initializing a result of a result array, and storing the detection result in the result array; the result array is an array containing N elements, and N is the number of electrode plates detected in the image by the target detection network model; any result i represents one electrode slice condition detected by the target detection network model, and comprises a score value, a center point x coordinate, a center point y coordinate, a detection frame width and a detection frame height, which are respectively marked as result i, score, result i, x, result i, y, result i, width and result i, height; i is more than or equal to 0 and less than N; ordering the elements in the result array according to the result [ i ]. Score non-ascending order; taking the first 10 elements after sequencing of the result array as a final electrode slice detection result;
step 2: determining the number of each electrode according to the ordering relation between the x coordinate of the center point and the y coordinate of the center point of each electrode slice in the result array, initializing a dictionary data structure, and storing the number and the elements in the corresponding result array as key value pairs in the dictionary;
the specific implementation process of the step 2 comprises the following substeps:
step 2.1: sorting the elements in the result array obtained in the step 1 according to a non-descending order of result [ j ]. Y, wherein j is more than or equal to 0 and less than 10;
step 2.2: initializing a dictionary data structure subject; the keys of the section are electrode numbers and the values are elements in a corresponding result array;
step 2.3: comparing the sizes of result 0, x and result 1, x; the smaller one is marked as an RA electrode and stored in the subject, and the larger one is marked as an LA electrode and stored in the subject;
step 2.4: comparing the sizes of result 2, x and result 3, x; the smaller electrode is marked as a V1 electrode and is stored in the subject, and the larger electrode is marked as a V2 electrode and is stored in the subject;
step 2.5: recording result 4 as V3 electrode and storing it in the subject;
step 2.6: comparing the sizes of result 5, result 6, x and result 7; the smaller one is marked as a V4 electrode and stored in the subject, the middle one is marked as a V5 electrode and stored in the subject, and the larger one is marked as a V6 electrode and stored in the subject;
step 2.7: comparing the sizes of result 8, x and result 9, x, the smaller one is marked as RL electrode and stored in the subject, the larger one is marked as LL electrode and stored in the subject;
step 3: analyzing whether the relative position relation of each numbered electrode slice in the part meets the wearing requirement of the electrocardio electrode slice in medicine according to the position information of each numbered electrode slice in the image, and returning an analysis result;
the specific implementation process of the step 3 comprises the following substeps:
step 3.1: judging whether the abscissa of the center points of the V1 to V6 electrode plates increases gradually; if yes, executing the step 3.2; otherwise, returning an analysis result code analysis result code= "error V1-V6";
the judgment process of whether the abscissa of the center points of the V1 to V6 electrode plates increases gradually is as follows:
dict[V i ].x<dict[V i+1 ].x,
wherein the subject [ V i ]X represents the number V in the image i The abscissa of the electrode sheet center point;
step 3.2: judging whether the ordinate of the center point of the V1 electrode plate is equal to the ordinate of the center point of the V2 electrode plate within the error allowable range; if yes, executing the step 3.3; otherwise, returning an analysis result code = "error v1_v2";
the judging process of whether the ordinate of the center point of the V1 electrode plate and the ordinate of the center point of the V2 electrode plate are equal within the error allowable range comprises the following steps:
|dict[V1].y-dict[V2].y|≤α;
wherein, the direct [ V1]. Y and the direct [ V2]. Y respectively represent the ordinate of the center point of the electrode sheet with the serial numbers of V1 and V2 in the image, and alpha is the maximum allowable error value;
step 3.3: judging whether maximum values and minimum values of the longitudinal coordinates of the center points of the V4, V5 and V6 electrode plates are equal within an error allowable range; if yes, executing the step 3.4; otherwise, returning an analysis result code= "error v4_v5_v6";
the judging process of whether the maximum value and the minimum value of the ordinate of the center point of the V4, V5 and V6 electrode plates are equal within the error allowable range is as follows:
max(dict[V4].y,dict[V5].y,dict[V6].y)-min(dict[V4].y,dict[V5].y,dict[V6].y)≤α;
wherein max and min are function symbols, respectively represent maximum and minimum values among a plurality of values returned, and the fact [ V4]. Y, the fact [ V5]. Y, the fact [ V6]. Y, respectively represent the ordinate of the center point of the electrode sheet with the numbers of V4, V5 and V6 in the image, and alpha is the maximum allowable error value;
step 3.4: calculating distance from the center point of the V3 electrode plate to the straight line where the center points of the V2 and V4 electrode plates are located (V3,V2V4) And determine distance (V3,V2V4) Whether 0 is within the error allowance range; if yes, executing the step 3.5; otherwise, returning an analysis result code analysis result code= "error v2_v3_v4_type1";
distance (V3,V2V4) the judging process of whether the error is 0 within the error allowable range is as follows:
distance (V3,V2V4) -α≤0;
wherein α is the maximum allowable error value;
step 3.5: calculating distance between center points of V2 and V3 electrode plates (V2,V3) Distance between the center points of the V3 and V4 electrode plates (V3,V4) And determine distance (V2,V3) And distance (V3,V4) Whether the error is equal within the allowable error range; if yes, returning an analysis result code of analysis result code= "correct"; otherwise, returning an analysis result code analysis result code= "error v2_v3_v4_type2";
distance (V2,V3) and distance (V3,V4) The judgment as to whether the two are equal within the allowable error range is as follows:
|distance (V2,V3) -distance (V3,V4) |≤α;
alpha is the maximum allowable error.
2. The image object detection-based 12-lead electrocardiographic electrode patch wearing auxiliary inspection method according to claim 1, characterized by: in the step 1, firstly, an electrode plate target detection data set is constructed, then a YOLO target detection network model for detecting the electrode plate is constructed, and training is carried out by using the data set to obtain a trained YOLO target detection network model;
the specific implementation comprises the following substeps:
step 1.1: shooting images of a plurality of electrode plates in different scenes, and marking each electrode plate in all the images to obtain a target detection data set of the electrode plates;
step 1.2: constructing a YOLO target detection network model for electrode slice detection, and training by using the data set obtained in the step 1.1; during training, setting the number of categories in the YOLO target detection network model as 1, and setting the ratio of length to width of the anchor in the YOLO target detection network model as 1:1; and obtaining a trained YOLO target detection network model.
3. The image object detection-based 12-lead electrocardiographic electrode patch wearing auxiliary inspection method according to claim 1, characterized by: the maximum allowable error alpha is one half of the average frame length of 10 electrode slice targets in the image obtained in the step 1;
and (2) the width and the height of the ith electrode slice target detection frame obtained in the step (1) are respectively obtained by result [ i ]. Width and result [ i ]. Height.
4. A 12-lead electrocardiographic electrode patch wearing auxiliary inspection method based on image target detection according to any one of claims 1-3, characterized in that: feeding back the result of the wearing auxiliary inspection of the electrocardio electrode plate in a picture-text combination mode according to the analysis result obtained in the step 3; if the problem exists, the prompt information of the problem and the number of the related electrode plate are returned; marking electrode plates with problems in wearing by using boxes in the images, and giving corresponding prompt information; if the problem does not exist, a correct wearing prompt is returned.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111366145.XA CN113974636B (en) | 2021-11-18 | 2021-11-18 | Image target detection-based 12-lead electrocardio electrode plate wearing auxiliary inspection method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111366145.XA CN113974636B (en) | 2021-11-18 | 2021-11-18 | Image target detection-based 12-lead electrocardio electrode plate wearing auxiliary inspection method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113974636A CN113974636A (en) | 2022-01-28 |
CN113974636B true CN113974636B (en) | 2023-07-18 |
Family
ID=79749218
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111366145.XA Active CN113974636B (en) | 2021-11-18 | 2021-11-18 | Image target detection-based 12-lead electrocardio electrode plate wearing auxiliary inspection method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113974636B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113208601A (en) * | 2020-01-17 | 2021-08-06 | 深圳理邦智慧健康发展有限公司 | Self-service electrocardiogram acquisition method, terminal, system and readable storage medium |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN205268157U (en) * | 2015-12-11 | 2016-06-01 | 包骏 | Non -contact heart electric sensor and wearable multichannel electrocardio sampling underwear thereof |
CN105852845A (en) * | 2016-03-26 | 2016-08-17 | 深圳市前海安测信息技术有限公司 | Wearable 12-lead remote electrocardiograph monitoring device as well as application system and method thereof |
CN105877742A (en) * | 2016-05-18 | 2016-08-24 | 四川长虹电器股份有限公司 | Misplacement detection method for lead-I electrode of electrocardiosignal |
CN105943020A (en) * | 2016-05-03 | 2016-09-21 | 东北大学 | Cardiac electric axis 6-lead wrong connection detection system and method |
CN106859632A (en) * | 2015-12-11 | 2017-06-20 | 包骏 | A kind of contactless electrocardiogram equipment of wearable real time multi-channel and its cardioelectric monitor method |
CN109009080A (en) * | 2018-08-29 | 2018-12-18 | 北京大众益康科技有限公司 | Electrocardioscanner and cardioelectric monitor system |
CN109674463A (en) * | 2017-10-19 | 2019-04-26 | 上海西门子医疗器械有限公司 | Judge the method and apparatus of cardiac diagnosis lead misconnection |
CN110638440A (en) * | 2019-08-29 | 2020-01-03 | 上海询康数字科技有限公司 | Self-service electrocardio detecting system |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11623102B2 (en) * | 2018-07-31 | 2023-04-11 | Medtronic, Inc. | Wearable defibrillation apparatus configured to apply a machine learning algorithm |
-
2021
- 2021-11-18 CN CN202111366145.XA patent/CN113974636B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN205268157U (en) * | 2015-12-11 | 2016-06-01 | 包骏 | Non -contact heart electric sensor and wearable multichannel electrocardio sampling underwear thereof |
CN106859632A (en) * | 2015-12-11 | 2017-06-20 | 包骏 | A kind of contactless electrocardiogram equipment of wearable real time multi-channel and its cardioelectric monitor method |
CN105852845A (en) * | 2016-03-26 | 2016-08-17 | 深圳市前海安测信息技术有限公司 | Wearable 12-lead remote electrocardiograph monitoring device as well as application system and method thereof |
CN105943020A (en) * | 2016-05-03 | 2016-09-21 | 东北大学 | Cardiac electric axis 6-lead wrong connection detection system and method |
CN105877742A (en) * | 2016-05-18 | 2016-08-24 | 四川长虹电器股份有限公司 | Misplacement detection method for lead-I electrode of electrocardiosignal |
CN109674463A (en) * | 2017-10-19 | 2019-04-26 | 上海西门子医疗器械有限公司 | Judge the method and apparatus of cardiac diagnosis lead misconnection |
CN109009080A (en) * | 2018-08-29 | 2018-12-18 | 北京大众益康科技有限公司 | Electrocardioscanner and cardioelectric monitor system |
CN110638440A (en) * | 2019-08-29 | 2020-01-03 | 上海询康数字科技有限公司 | Self-service electrocardio detecting system |
Non-Patent Citations (1)
Title |
---|
The effects of electrode misplacement on clinicians’ interpretation of the standard 12-lead electrocardiogram;R.R.Bond,D.D.Finlay;European Journal of Internal Medicine;第610-615页 * |
Also Published As
Publication number | Publication date |
---|---|
CN113974636A (en) | 2022-01-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US8323190B2 (en) | Comprehensive neuromuscular profiler | |
US20120143064A1 (en) | Muscle function evaluating system | |
CN106618481A (en) | Traditional Chinese medicine intelligent diagnosis expert system | |
US20180182091A1 (en) | Method and system for imaging and analysis of anatomical features | |
CN113647939B (en) | Artificial intelligence rehabilitation evaluation and training system for spinal degenerative diseases | |
CN109480780A (en) | A kind of cerebral apoplexy early warning system and method | |
CN103908244A (en) | ECG lead wrong connection judging method and device | |
CN113974636B (en) | Image target detection-based 12-lead electrocardio electrode plate wearing auxiliary inspection method | |
CN115376694B (en) | Multi-mode self-adaptive assessment system and method for limb dysfunction | |
CN116246778B (en) | Intelligent diagnosis platform for lung function detection | |
US20200375491A1 (en) | Heartbeat analyzing method and heartbeat analyzing method | |
CN111419283B (en) | Ultrasonic analysis system for evaluating disease severity of patient with new coronaries | |
CN112057043A (en) | Traditional Chinese medicine pulse data processing method, equipment and storage medium | |
CN106510654A (en) | Positioning method and system of pulse condition analyzer | |
CN116012568A (en) | System for acquiring cardiac rhythm information through photographing electrocardiogram | |
US8016777B1 (en) | Hand-held probe for prostate cancer screening | |
CN112957018A (en) | Heart state detection method and device based on artificial intelligence | |
CN116236208A (en) | Multi-lead electrocardio electrode patch positioning method based on human body surface characteristics | |
CN116631558B (en) | Construction method of medical detection project based on Internet | |
US20230355204A1 (en) | Wearable ultrasound patch for monitoring subjects in motion using machine learning and wireless electronics | |
CN109615656A (en) | A kind of backbone localization method based on pattern search | |
US11786202B2 (en) | Method, system, and medium for analyzing image sequence of periodic physiological activity | |
CN109480822A (en) | A kind of electrocardiographic diagnosis function detecting method and its processing method | |
TWI756793B (en) | A channel information processing system | |
CN112037164B (en) | Body part identification method and device in medical image |
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 |