CN-116236208-B - Multi-lead electrocardio electrode patch positioning method based on human body surface characteristics

CN116236208BCN 116236208 BCN116236208 BCN 116236208BCN-116236208-B

Abstract

The invention provides a multi-lead electrocardio electrode patch positioning method based on human body surface characteristics, which belongs to the technical field of medical equipment and comprises the steps of inputting video data of an electrocardio electrode patch worn by a user into a pre-trained target positioning model to obtain human body upper body surface characteristics and electrocardio electrode patch characteristic state information, calculating and obtaining characteristic operation association results of the human body upper body surface characteristics and the electrocardio electrode patch characteristic state information to generate electrocardio electrode patch wearing state information, and determining an electrocardio electrode patch positioning instruction result by the electrocardio electrode patch wearing state information. According to the invention, the terminal with the video function is used for collecting the body surface characteristics and the electrode patch position information of the user when wearing the electrocardio electrode patch in real time, feeding back information such as whether the user wears the electrocardio electrode patch correctly or not or an error correction method and the like to the user, assisting the user to wear the electrocardio electrode patch correctly, and effectively reducing or avoiding errors of electrocardio signal measurement caused by the fact that the user wears the electrocardio electrode patch by mistake.

Inventors

ZHAO JIANHUI
DENG WENJUN
YUAN ZHIYONG

Assignees

武汉大学

Dates

Publication Date: 20260508
Application Date: 20230227

Claims (9)

1. A method for positioning a multi-lead electrocardio electrode patch, which is characterized by comprising the following steps: Acquiring video data of an electrocardio electrode patch worn by a user, and inputting the video data of the electrocardio electrode patch worn by the user into a pre-trained target positioning model to obtain body surface characteristics of the upper body of a human body and electrocardio electrode patch characteristic state information; calculating and obtaining characteristic operation association results of the body surface characteristics of the upper body of the human body and the electrocardio electrode patch characteristic state information; generating electrocardio electrode patch wearing state information according to the characteristic operation association result, and determining an electrocardio electrode patch positioning guide result according to the electrocardio electrode patch wearing state information; The method for acquiring the video data of the electrocardio electrode patch worn by the user, inputting the video data of the electrocardio electrode patch worn by the user into a pre-trained target positioning model to obtain the body surface characteristics of the upper body of the human body and the electrocardio electrode patch characteristic state information comprises the following steps: Initializing an N-dimensional vector comprising a plurality of characteristic state information, wherein N is the total number of the body surface characteristics of the upper body of the human body plus the electrocardio electrode patches, and the plurality of characteristic state information comprises a target type, a target score value, a target center point abscissa, a target center point ordinate, a target detection frame height and a target detection frame width; If the target type is determined to be a human nipple, performing non-ascending sorting on components corresponding to the human nipple in the plurality of characteristic state information, and taking the first two components as human nipple detection results; if the target type is determined to be the boundary line of the upper body of the human body, non-ascending order is carried out on the components corresponding to the boundary line of the upper body of the human body in the plurality of characteristic state information, and then the first two components are taken as human body boundary detection results; if the target type is determined to be an electrode patch, performing non-ascending order on components corresponding to the electrode patch in the plurality of characteristic state information, and taking a plurality of components as electrode patch detection results; And constructing a two-dimensional matrix according to the human nipple detection result, the human demarcation line detection result and the electrode patch detection result, wherein the two-dimensional matrix comprises a human right nipple component, a human left nipple component, a human right borderline component, a human left borderline component, a right upper limb electrode patch component, a left upper limb electrode patch component, a first chest electrode patch component, a second chest electrode patch component, a third chest electrode patch component, a fourth chest electrode patch component, a fifth chest electrode patch component, a sixth chest electrode patch component, a right lower limb electrode patch component and a left lower limb electrode patch component.
2. The multi-lead ecg electrode patch positioning method of claim 1, wherein the calculating to obtain the feature operation correlation result of the human upper body surface feature and the ecg electrode patch feature status information comprises: If it is determined that the abscissa of the first chest electrode patch component, the second chest electrode patch component, the third chest electrode patch component, the fourth chest electrode patch component, the fifth chest electrode patch component, and the sixth chest electrode patch component are sequentially incremented, a subsequent calculation step is performed, and otherwise, a first feature operation association result is returned.
3. The multi-lead ecg electrode patch positioning method of claim 2, wherein the calculating obtains a feature operation correlation result of the human upper body surface feature and the ecg electrode patch feature status information, further comprising: Obtaining a first ratio of the absolute value of the first chest electrode patch component ordinate minus the second chest electrode patch component ordinate to the absolute value of the first chest electrode patch component abscissa minus the second chest electrode patch component abscissa, and a second ratio of the absolute value of the human body right nipple component ordinate minus the human body left nipple component ordinate to the absolute value of the human body right nipple component abscissa minus the human body left nipple component abscissa; If the absolute value of the difference between the first ratio and the second ratio is smaller than or equal to a first preset error value, executing a subsequent calculation step, otherwise, returning a second characteristic operation association result; Obtaining a first product obtained by subtracting the human left nipple component abscissa from the first chest electrode patch component abscissa and subtracting the human right nipple component ordinate from the human left nipple component ordinate, and a second product obtained by subtracting the human right nipple component abscissa from the human left nipple component abscissa from the first chest electrode patch component ordinate and subtracting the human left nipple component ordinate from the human left nipple component ordinate; if the difference between the first product and the second product is smaller than or equal to the first preset error value, executing the subsequent calculation step, otherwise, returning a third characteristic operation association result; if the Euclidean distance between the first chest electrode patch component and the human right nipple component is less than or equal to the second preset error value, and the Euclidean distance between the second chest electrode patch component and the human left nipple component is less than or equal to the second preset error value, executing the subsequent calculation step, otherwise, returning to the fourth characteristic operation association result.
4. The multi-lead ecg electrode patch positioning method of claim 3, wherein the calculating obtains a feature operation correlation result of the human upper body surface feature and the ecg electrode patch feature status information, further comprising: Obtaining a third product obtained by multiplying the difference of the fourth chest electrode patch component abscissa minus the human left nipple component abscissa by the difference of the human left nipple component abscissa minus the human right nipple component abscissa, and a fourth product obtained by multiplying the difference of the fourth chest electrode patch component ordinate minus the human left nipple component ordinate by the difference of the human left nipple component ordinate minus the human right nipple component ordinate; If the difference between the third product and the fourth product is smaller than or equal to a first preset error value, executing a subsequent calculation step, otherwise, returning a fifth characteristic operation association result; If the Euclidean distance between the patch component of the fourth chest electrode and the left nipple component of the human body is less than or equal to the second preset error value, executing the subsequent calculation step, otherwise, returning to the sixth characteristic operation association result.
5. The multi-lead ecg electrode patch positioning method of claim 4, wherein the calculating obtains a feature operation correlation result of the human upper body surface feature and the ecg electrode patch feature status information, further comprising: Acquiring a first linear distance from a third front electrode patch center point to a connecting line of a second front electrode patch center point and a fourth front electrode patch center point, a second linear distance from the third front electrode patch center point to the second front electrode patch center point, and a third linear distance from the third front electrode patch center point to the fourth front electrode patch center point; If the difference between the first linear distance and the second preset error value is less than or equal to 0, executing the subsequent calculation step, otherwise, returning to a seventh characteristic operation association result; And if the absolute value of the difference between the second linear distance and the third linear distance is smaller than or equal to the second preset error value, executing the subsequent calculation step, otherwise, returning to the eighth characteristic operation association result.
6. The multi-lead ecg electrode patch positioning method of claim 5, wherein the calculating obtains a feature operation correlation result of the human upper body surface feature and the ecg electrode patch feature status information, further comprising: Obtaining a fifth product obtained by subtracting the human left boundary component abscissa from the sixth chest electrode patch component abscissa, multiplying the difference of the human left nipple component abscissa and the human right nipple component abscissa from the sixth chest electrode patch component ordinate and multiplying the difference of the human left boundary component ordinate from the sixth chest electrode patch component ordinate and the human right nipple component ordinate from the human left nipple component ordinate; If the difference between the fifth product and the sixth product is smaller than or equal to a first preset error value, executing a subsequent calculation step, otherwise, returning a ninth characteristic operation association result; Obtaining a seventh product obtained by subtracting the fourth chest electrode patch component abscissa from the sixth chest electrode patch component abscissa and subtracting the human right nipple component ordinate from the human left nipple component ordinate, and an eighth product obtained by subtracting the human right nipple component abscissa from the human left nipple component abscissa from the sixth chest electrode patch component ordinate and subtracting the fourth chest electrode patch component ordinate from the sixth chest electrode patch component ordinate; And if the difference between the seventh product and the eighth product is less than or equal to the first preset error value, executing the subsequent calculation step, otherwise, returning a tenth characteristic operation association result.
7. The multi-lead ecg electrode patch positioning method of claim 6, wherein the calculating obtains a feature operation correlation result of the human upper body surface feature and the ecg electrode patch feature status information, further comprising: Obtaining a ninth product obtained by subtracting the fourth chest electrode patch component abscissa from the fifth chest electrode patch component abscissa, multiplying the difference of the human left nipple component ordinate and the human right nipple component abscissa from the fifth chest electrode patch component ordinate and a tenth product obtained by subtracting the fourth chest electrode patch component ordinate from the fifth chest electrode patch component ordinate and multiplying the difference of the human left nipple component abscissa and the human right nipple component abscissa from the human left nipple component abscissa; And if the difference between the ninth product and the tenth product is smaller than the first preset error value, executing the subsequent calculation step, otherwise, returning to the eleventh characteristic operation association result.
8. The method of any one of claims 3 to 5, wherein the second predetermined error value is obtained by multiplying a predetermined ratio by an average frame length of a sum of target frame lengths and target frame widths of 10 electrode patches in a two-dimensional matrix.
9. The multi-lead ecg electrode patch positioning method of claim 1, wherein the generating ecg electrode patch wearing state information from the characteristic operation association result, determining an ecg electrode patch positioning guidance result from the ecg electrode patch wearing state information, comprises: if the characteristic operation association result is determined to be wearing error information, feeding back a wearing error electrode patch number and an electrode patch adjusting method to a user by adopting voice or characters; If the characteristic operation association result is determined to be the wearing correct information, the wearing success prompt information is fed back to the user by voice or characters.

Description

Multi-lead electrocardio electrode patch positioning method based on human body surface characteristics Technical Field The invention relates to the technical field of medical equipment, in particular to a multi-lead electrocardio electrode patch positioning method based on human body surface characteristics. Background In cardiovascular disease diagnosis, an electrocardiogram is one of important indexes, and is usually obtained by wearing a special electrocardiogram detection instrument on a patient, and most commonly, a multi-lead electrocardio electrode patch is worn to obtain an electrocardiogram of the patient, so that whether a person to be examined suffers from heart diseases or not is known through observation of the electrocardiogram. With the increasing popularity of services such as remote inquiry and home health monitoring, more and more users acquire their own electrocardiographic data at any time in a home self-test mode, and most of users are not trained in wearing special electrode patches, so that great errors of the acquired electrocardiograph are possibly caused by inaccurate wearing of the electrode patches to a great extent, and the accuracy of analysis and cardiac diagnosis of electrocardiograph signals by doctors or instruments is affected. Accordingly, there is a need to provide an effective way to assist the user in locating the ecg electrode patches and to assist the user in wearing the ecg electrode patches correctly. Disclosure of Invention The invention provides a multi-lead electrocardio electrode patch positioning method based on human body surface characteristics, which is used for solving the defect that a method for guiding a user to wear an electrocardio electrode patch correctly is lacking in the prior art. The invention provides a multi-lead electrocardio electrode patch positioning method based on human body surface characteristics, which comprises the following steps: Acquiring video data of an electrocardio electrode patch worn by a user, and inputting the video data of the electrocardio electrode patch worn by the user into a pre-trained target positioning model to obtain body surface characteristics of the upper body of a human body and electrocardio electrode patch characteristic state information; calculating and obtaining characteristic operation association results of the body surface characteristics of the upper body of the human body and the electrocardio electrode patch characteristic state information; And generating electrocardio electrode patch wearing state information according to the characteristic operation association result, and determining an electrocardio electrode patch positioning guidance result according to the electrocardio electrode patch wearing state information. According to the multi-lead electrocardio electrode patch positioning method based on human body surface characteristics, which is provided by the invention, the video data of the electrocardio electrode patch worn by a user is collected, the video data of the electrocardio electrode patch worn by the user is input into a pre-trained target positioning model, and the human body upper body surface characteristics and electrocardio electrode patch characteristic state information are obtained, and the method comprises the following steps: Initializing an N-dimensional vector comprising a plurality of characteristic state information, wherein N is the total number of the body surface characteristics of the upper body of the human body plus the electrocardio electrode patches, and the plurality of characteristic state information comprises a target type, a target score value, a target center point abscissa, a target center point ordinate, a target detection frame height and a target detection frame width; If the target type is determined to be a human nipple, performing non-ascending sorting on components corresponding to the human nipple in the plurality of characteristic state information, and taking the first two components as human nipple detection results; if the target type is determined to be the boundary line of the upper body of the human body, non-ascending order is carried out on the components corresponding to the boundary line of the upper body of the human body in the plurality of characteristic state information, and then the first two components are taken as human body boundary detection results; if the target type is determined to be an electrode patch, performing non-ascending order on components corresponding to the electrode patch in the plurality of characteristic state information, and taking a plurality of components as electrode patch detection results; And constructing a two-dimensional matrix according to the human nipple detection result, the human demarcation line detection result and the electrode patch detection result, wherein the two-dimensional matrix comprises a human right nipple component, a human left nipple component, a human right borderline compo