Intracavity precise positioning method and related device based on electrocardiogram signal

Abstract

The embodiments of the present application relate to the technical fields of intracavity positioning and position detection, and provide an intracavity precise positioning method based on electrocardiogram signals and related devices, the method comprising: acquiring an initial in-vivo electrocardiogram signal of a user to be detected; filtering and fusing the initial in-vivo electrocardiogram signal to obtain a target in-vivo electrocardiogram signal; extracting P wave information from the target in-vivo electrocardiogram signal; using the P wave information to position the tip of a PICC to obtain target position information of the tip of the PICC in the cavity, thereby being able to filter and fuse the initial in-vivo electrocardiogram signal, and using the P wave information for precise positioning to obtain target position information, thereby improving the accuracy of determining the target position information.

Description

Technical Field

[0001] The present application relates to the technical field of intracavity positioning and position detection, and specifically to an intracavity precise positioning method based on electrocardiogram signals and related devices. Background Art

[0002] When a peripherally inserted central catheter (PICC) is used clinically for medium- and long-term intravenous infusion, such as clinical chemotherapy, parenteral nutrition, antibacterial therapy, etc., the tip of the PICC needs to be placed at the junction of the superior vena cava and the right atrium at 1 / 3 of the vena cava or CAJ (cavoatrial junction). Since the positioning process is performed in the body, it requires extremely high positioning accuracy.

[0003] In the existing scheme, when locating the PICC tip through the intracavitary electrocardiogram, the intracavitary electrocardiogram signal is usually directly classified and processed, and the tip is located according to the classification category. Since it directly uses the electrocardiogram signal for classification and processing, and locates according to the classification result, there may be errors caused by the electrocardiogram itself, which reduces the accuracy of classification and further reduces the accuracy of positioning. Summary of the invention

[0004] The embodiments of the present application provide a method and related device for precise intracavity positioning based on ECG signals, which can filter and fuse the initial in-vivo ECG signals, and use P-wave information for precise positioning to obtain target position information, thereby improving the accuracy of determining the target position information.

[0005] A first aspect of an embodiment of the present application provides a method for precise intracavity positioning based on electrocardiogram signals, the method comprising:

[0006] Obtaining an initial in vivo electrocardiogram signal of the user to be detected;

[0007] Performing filtering and fusion processing on the initial in-vivo ECG signal to obtain a target in-vivo ECG signal;

[0008] Extracting P wave information from the target body's electrocardiogram signal;

[0009] The P wave information is used to perform positioning processing on the PICC tip to obtain target position information of the PICC tip in the cavity.

[0010] In this example, the initial in vivo ECG signal of the user to be detected is obtained, the initial in vivo ECG signal is filtered and fused to obtain a target in vivo ECG signal, P wave information is extracted from the target in vivo ECG signal, and the PICC tip is positioned using the P wave information to obtain the target position information of the PICC tip in the cavity. Therefore, the initial in vivo ECG signal can be filtered and fused, and the P wave information can be used for precise positioning to obtain the target position information, thereby improving the accuracy of determining the target position information.

[0011] In a possible implementation, the filtering and fusing the initial in-vivo ECG signal to obtain the target in-vivo ECG signal includes:

[0012] Segmenting the initial in-vivo electrocardiogram signal to obtain k initial heart beat signals;

[0013] Performing filtering on the k initial heartbeat signals to obtain k reference heartbeat signals;

[0014] Performing R wave positioning processing on the k reference heartbeat signals to obtain k R wave position information, and performing S wave positioning processing on the k reference heartbeat signals to obtain k S wave position information;

[0015] The k reference heartbeat signals are fused according to the k R wave position information and the k S wave position information to obtain the target body's electrocardiogram signal.

[0016] In a possible implementation, the segmenting process of the initial in-vivo electrocardiogram signal to obtain k initial heartbeat signals includes:

[0017] Extracting k first positive voltage data points of the initial in vivo ECG signal, and extracting m first negative voltage data points of the initial in vivo ECG signal, the first positive voltage data point being a local maximum positive voltage point, and the first negative voltage data point being a local minimum negative voltage point;

[0018] Extracting k negative power data points from m first negative voltage data points according to the position information of the k first positive voltage data points to obtain k second negative voltage data points;

[0019] Using k first forward voltage data points to segment the initial in vivo electrocardiogram signal to obtain k first reference heart beat signals;

[0020] Using k second negative voltage data points to segment the initial in vivo electrocardiogram signal to obtain k second reference heart beat signals;

[0021] The k first reference heartbeat signals are fused with the corresponding second reference heartbeat signals to obtain k initial heartbeat signals.

[0022] In a possible implementation, fusing the k reference heartbeat signals according to the k R wave position information and the k S wave position information to obtain the target body electrocardiogram signal includes:

[0023] Aligning k reference heart beat signals according to the corresponding R wave peak positions to obtain a first aligned signal set;

[0024] fusing the reference heartbeat signal in the first alignment signal set to obtain a first intermediate in-vivo ECG signal;

[0025] Aligning k reference heartbeat signals according to corresponding S wave trough positions to obtain a second aligned signal set;

[0026] fusing the reference heartbeat signal in the second alignment signal set to obtain a second intermediate in-vivo ECG signal;

[0027] The first intermediate in-vivo ECG signal and the second intermediate in-vivo ECG signal are fused to obtain the target in-vivo ECG signal.

[0028] In a possible implementation, the using the P wave information to perform positioning processing on the PICC tip to obtain target position information of the PICC tip in the cavity includes:

[0029] Using the P wave information to extract the P wave profile, to obtain the P wave profile information;

[0030] Determine reference position information of the PICC tip in the cavity according to the P wave profile information;

[0031] Acquire status information of the user to be detected;

[0032] determining position correction information according to the state information;

[0033] The reference position information is corrected using the position correction information to obtain the target position information.

[0034] A second aspect of the embodiment of the present application provides an intracavity precise positioning device based on electrocardiogram signals, characterized in that the device comprises:

[0035] An acquisition unit, used for acquiring an initial in-vivo ECG signal of a user to be detected;

[0036] A processing unit, configured to perform filtering and fusion processing on the initial in-vivo ECG signal to obtain a target in-vivo ECG signal;

[0037] An extraction unit, used to extract P wave information from the target body's electrocardiogram signal;

[0038] The positioning unit is used to use the P wave information to perform positioning processing on the PICC tip to obtain the target position information of the PICC tip in the cavity.

[0039] In a possible implementation, the processing unit is specifically configured to:

[0040] Segmenting the initial in-vivo electrocardiogram signal to obtain k initial heart beat signals;

[0041] Performing filtering on the k initial heartbeat signals to obtain k reference heartbeat signals;

[0042] Performing R wave positioning processing on the k reference heartbeat signals to obtain k R wave position information, and performing S wave positioning processing on the k reference heartbeat signals to obtain k S wave position information;

[0043] The k reference heartbeat signals are fused according to the k R wave position information and the k S wave position information to obtain the target body's electrocardiogram signal.

[0044] In a possible implementation, in the aspect of segmenting the initial in-vivo electrocardiogram signal to obtain k initial heart beat signals, the processing unit is specifically used to:

[0045] Extracting k first positive voltage data points of the initial in vivo ECG signal, and extracting m first negative voltage data points of the initial in vivo ECG signal, the first positive voltage data point being a local maximum positive voltage point, and the first negative voltage data point being a local minimum negative voltage point;

[0046] Extracting k negative power data points from m first negative voltage data points according to the position information of the k first positive voltage data points to obtain k second negative voltage data points;

[0047] Using k first forward voltage data points to segment the initial in vivo electrocardiogram signal to obtain k first reference heart beat signals;

[0048] Using k second negative voltage data points to segment the initial in vivo electrocardiogram signal to obtain k second reference heart beat signals;

[0049] The k first reference heartbeat signals are fused with the corresponding second reference heartbeat signals to obtain k initial heartbeat signals.

[0050] In a possible implementation, in the aspect of fusing the k reference heartbeat signals according to the k R wave position information and the k S wave position information to obtain the target body electrocardiogram signal, the processing unit is specifically used to:

[0051] Aligning k reference heart beat signals according to the corresponding R wave peak positions to obtain a first aligned signal set;

[0052] fusing the reference heartbeat signal in the first alignment signal set to obtain a first intermediate in-vivo ECG signal;

[0053] Aligning k reference heartbeat signals according to corresponding S wave trough positions to obtain a second aligned signal set;

[0054] fusing the reference heartbeat signal in the second alignment signal set to obtain a second intermediate in-vivo ECG signal;

[0055] The first intermediate in-vivo ECG signal and the second intermediate in-vivo ECG signal are fused to obtain the target in-vivo ECG signal.

[0056] In a possible implementation, the positioning unit is specifically configured to:

[0057] Using the P wave information to extract the P wave profile, to obtain the P wave profile information;

[0058] Determine reference position information of the PICC tip in the cavity according to the P wave profile information;

[0059] Acquire status information of the user to be detected;

[0060] determining position correction information according to the state information;

[0061] The reference position information is corrected using the position correction information to obtain the target position information.

[0062] A third aspect of an embodiment of the present application provides a terminal, comprising a processor, an input device, an output device and a memory, wherein the processor, input device, output device and memory are interconnected, wherein the memory is used to store a computer program, the computer program comprises program instructions, and the processor is configured to call the program instructions to execute the step instructions in the first aspect of the embodiment of the present application.

[0063] The fourth aspect of the embodiments of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps described in the first aspect of the embodiments of the present application.

[0064] A fifth aspect of the embodiments of the present application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps described in the first aspect of the embodiments of the present application. The computer program product may be a software installation package.

[0065] The implementation of the embodiments of the present application has the following beneficial effects:

[0066] The target in vivo ECG signal is obtained by acquiring the initial in vivo ECG signal of the user to be detected, filtering and fusing the initial in vivo ECG signal, extracting P wave information from the target in vivo ECG signal, and positioning the PICC tip using the P wave information to obtain the target position information of the PICC tip in the cavity. Therefore, the initial in vivo ECG signal can be filtered and fused, and the P wave information can be used for precise positioning to obtain the target position information, thereby improving the accuracy of determining the target position information. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0068] Figure 1 A schematic flow chart of a method for precise intracavitary positioning based on electrocardiogram signals is provided for an embodiment of the present application;

[0069] Figure 2 A schematic diagram of a first transition heartbeat signal is provided for an embodiment of the present application;

[0070] Figure 3 A schematic diagram of the structure of a terminal provided in an embodiment of the present application;

[0071] Figure 4 A structural schematic diagram of an intracavity precise positioning device based on electrocardiogram signals is provided for an embodiment of the present application. DETAILED DESCRIPTION

[0072] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0073] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0074] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments.

[0075] In order to better understand the intracavitary precise positioning method based on ECG signals provided in the embodiment of the present application, the method for positioning the PICC tip in the existing scheme is briefly introduced below. In the existing scheme, the intracavitary ECG signal data of the PICC catheter is usually obtained, and the intracavitary ECG signal data is used to classify the heart beats, and the heart classification results are obtained. The results are used to locate the PICC tip. When it is specifically implemented, only some common segmentation methods are used for processing, and the change characteristics of the P wave when locating the PICC tip are not fully combined and analyzed, which reduces the accuracy of the positioning.

[0076] In order to solve the above-mentioned technical problems, an embodiment of the present application provides a method for precise intracavity positioning based on ECG signals, which can filter and fuse the initial in-vivo ECG signals to obtain a target in-vivo ECG signal that is more closely matched to the detection, and use the P wave information extracted from the target in-vivo ECG signal for precise positioning to obtain the target position information, thereby improving the accuracy of determining the target position information.

[0077] See also Figure 1 , Figure 1 The present invention provides a flow chart of a method for accurate intracavitary positioning based on electrocardiogram signals. Figure 1 As shown, the method includes:

[0078] 101. Obtain an initial in-vivo electrocardiogram signal of a user to be detected.

[0079] When the medical staff begins to perform PICC catheterization on the user to be tested, the corresponding intracavitary electrocardiogram signal and body surface electrocardiogram signal are collected by the signal acquisition device to obtain the initial in vivo electrocardiogram signal. The signal acquisition device can be an ultrasonic instrument or other equipment capable of collecting electrocardiogram signals, which is not specifically limited here.

[0080] When performing PICC catheterization, due to the special location of the catheter and the advancement of the catheter, it will have a certain impact on the P wave in the ECG signal, that is, the P wave will change with the position of the catheter tip. In the process of position change, a negative voltage will be generated, that is, the peak of the P wave will be in the negative direction. Therefore, the existing conventional methods are used to obtain and detect the P wave, which usually only considers the characteristics of the positive P wave, resulting in poor adaptation during feature processing, thereby reducing the accuracy of subsequent processing.

[0081] 102. Perform filtering and fusion processing on the initial in-vivo ECG signal to obtain a target in-vivo ECG signal.

[0082] Among them, the initial in-vivo ECG signal can be segmented to obtain multiple initial heartbeat signals, and then the initial heartbeat signal is filtered to obtain multiple reference heartbeat signals, and finally the multiple reference heartbeat signals are fused using the R wave position information and the S wave position information in the heartbeat signal to obtain the target in-vivo ECG signal. Therefore, the fusion processing can be combined with the S wave position information, and the fusion processing can be fully considered with the negative characteristics, so as to improve the accuracy of the obtained target in-vivo ECG signal.

[0083] 103. Extract P wave information from the target body's electrocardiogram signal.

[0084] The starting point and the ending point of the P wave can be extracted from the target body's ECG signal, so that the starting point and the ending point can be determined as the P wave information. Specifically, the starting point and the ending point of the P wave can be determined based on the position point coordinates of the peak of the R wave in the target body's ECG signal, and the related offset. For example, after extracting the position point coordinates of the peak of the R wave, and then the position information of the Q wave on the left side of the peak of the R wave, the starting point and the ending point of the waveform on the left side of the Q wave are extracted from the target body's ECG signal, and determined as the P wave information.

[0085] 104. Use the P wave information to perform positioning processing on the PICC tip to obtain target position information of the PICC tip in the cavity.

[0086] Specifically, as the PICC tip advances in position, it will have a certain impact on the P wave in the ECG signal, that is, the P wave will change as the position of the catheter tip changes. In the process of position change, a negative voltage will be generated, that is, the peak of the P wave will be in the negative direction, and after reaching the predetermined position, the peak value of the wave will be fixed or fluctuate within a certain small range, so that the target position information of the PICC tip in the cavity can be determined based on the waveform of the P wave.

[0087] For example, the starting point and the ending point of the P wave can be used to extract the waveform between the starting point and the ending point from the target body's ECG signal, thereby obtaining the P wave contour information. The reference position information can be determined based on the P wave contour information, and then the reference position information is corrected in combination with the state information of the user to be detected to obtain the target position information. Therefore, since the user's heart rate, heartbeat, etc. will fluctuate to a certain extent, the reference position information can be corrected in combination with the current state of the user to be detected, such as the fluctuation of the heart rate, heart rate, etc., to obtain the target position information, which can make the target position information more realistic and improve the accuracy of the target position information.

[0088] In this example, the initial in vivo ECG signal of the user to be detected is obtained, the initial in vivo ECG signal is filtered and fused to obtain a target in vivo ECG signal, P wave information is extracted from the target in vivo ECG signal, and the PICC tip is positioned using the P wave information to obtain the target position information of the PICC tip in the cavity. Therefore, the initial in vivo ECG signal can be filtered and fused, and the P wave information can be used for precise positioning to obtain the target position information, thereby improving the accuracy of determining the target position information.

[0089] In one possible implementation, the initial in-vivo ECG signal is a signal of multiple heartbeats collected, but the PICC tip needs to be paused and moved during position assessment to obtain an accurate position. At this time, the PICC tip does not move, and the collected ECG signal will be in a relatively stable state. However, the presence of some interference signals cannot be avoided. If only one P wave is selected from multiple heartbeats for positioning processing, some positioning errors may be caused, reducing the accuracy of positioning. In order to solve the above-mentioned problem of insufficient stability, multiple heartbeat signals can be fused to stabilize signal characteristics and improve stability during subsequent positioning processing. Specifically, a method for filtering and fusing the initial in-vivo ECG signal to obtain a target in-vivo ECG signal includes:

[0090] A1, segmenting the initial in-vivo ECG signal to obtain k initial heart beat signals;

[0091] A2, filtering the k initial heartbeat signals to obtain k reference heartbeat signals;

[0092] A3, performing R wave positioning processing on the k reference heartbeat signals to obtain k R wave position information, and performing S wave positioning processing on the k reference heartbeat signals to obtain k S wave position information;

[0093] A4. Perform fusion processing on the k reference heartbeat signals according to the k R wave position information and the k S wave position information to obtain the target body's electrocardiogram signal.

[0094] The initial in vivo ECG signal can be segmented using positive voltage data points and negative voltage data points, so that k initial heartbeat signals can be obtained. A heartbeat signal can be an ECG signal with the crest of the R wave as the starting point and the crest of an adjacent R wave as the end point.

[0095] A general filtering method may be used to filter the k initial heartbeat signals to obtain k reference heartbeat signals.

[0096] The general R-wave and S-wave positioning methods can be used for positioning processing to obtain R-wave position information and S-wave position information.

[0097] It can be that k reference heartbeat signals are aligned and fused using R wave position information to obtain a first intermediate in-vivo ECG signal, and k reference heartbeat signals are aligned and fused using S wave position information to obtain a second intermediate in-vivo ECG signal, and finally the first intermediate in-vivo ECG signal and the second intermediate in-vivo ECG signal are fused to obtain a target in-vivo ECG signal. Therefore, alignment and fusion can be performed once using the positive R wave position information, and alignment and fusion can be performed once using the reverse S wave position information, and finally the two intermediate signals are fused to obtain a target in-vivo ECG signal, so that the positive and negative features can be combined for fusion. Since the P wave may have a negative peak, the fusion process can be better performed to improve the accuracy of the fused target in-vivo ECG signal.

[0098] In a possible implementation, in the existing solution, when segmenting the ECG signal, the segmentation is usually performed only through the positive R wave. A method for segmenting the initial in vivo ECG signal to obtain k initial heart beat signals includes:

[0099] B1, extracting k first positive voltage data points of the initial in vivo ECG signal, and extracting m first negative voltage data points of the initial in vivo ECG signal, the first positive voltage data point being a local maximum positive voltage point, and the first negative voltage data point being a local minimum negative voltage point;

[0100] B2. extracting k negative power data points from the m first negative voltage data points according to the position information of the k first positive voltage data points to obtain k second negative voltage data points;

[0101] B3, using k first forward voltage data points to segment the initial in vivo electrocardiogram signal to obtain k first reference heart beat signals;

[0102] B4, using k second negative voltage data points to segment the initial in vivo electrocardiogram signal to obtain k second reference heart beat signals;

[0103] B5. Fusing the k first reference heartbeat signals with the corresponding second reference heartbeat signals to obtain k initial heartbeat signals.

[0104] Among them, the first forward voltage data point can specifically be a local maximum forward voltage point that exceeds a first preset threshold value. The first preset threshold value is set by empirical value or historical data. The first preset threshold value is used to screen out the peak point of the R wave to obtain the first forward voltage data point.

[0105] Due to the movement of the position at the tip of the PICC, a negative waveform will appear in the P wave of the ECG signal. Therefore, it is necessary to extract and process the negative waveform to improve accuracy. The m first negative voltage data points obtained at this time may include the peak point of the negative waveform of the P wave, so it is necessary to remove such waveform points to obtain the trough point of the S wave to obtain the first negative voltage data point. The negative voltage value of the negative voltage data point at this time should be less than the second preset threshold value to distinguish the Q wave from the S wave. Since the S wave is far away from the P wave, there may be no overlap with the P wave. Therefore, the trough point corresponding to the S wave is used as the second negative voltage data point, which can avoid interference during processing and improve accuracy. Of course, it is also possible to extract k second negative voltage data points from the m first negative voltage data points based on the positional relationship between the Q wave, the S wave and the R wave. The k second negative voltage data points are the trough values ​​of the S wave.

[0106] Specifically, after screening out k first positive voltage data points and k second negative voltage data points, the k first positive voltage data points can be used to segment and calibrate the initial in vivo ECG signal to obtain a calibration array. Specifically, it can be assumed that the coordinates of the first first positive voltage data point are A1 (Ax1, Ay1), the coordinates of the second first positive voltage data point are A2 (Ax2, Ay2), and the coordinates of the i-th first positive voltage data point are Ai (Axi, Ayi). Therefore, when calibrating, the ECG signal between A1 (Ax1, Ay1) and A2 (Ax2, Ay2) can be used as a first transition heartbeat signal, which can be as follows. Figure 2 As shown, Figure 2 A schematic diagram of a first transition heartbeat signal is shown.

[0107] After calibrating k transition heartbeat signals, it is necessary to filter and reconstruct the k transition heartbeat signals to obtain k first reference heartbeat signals. Specifically, the array of each heartbeat signal can be recorded as R group, specifically: RR (A1A2, A2A3, ..., An-1An), where A1A2 is the R wave peak position point of the first transition heartbeat signal, and An-1An is the R wave peak position point of the nth transition heartbeat signal. Since the initial split is performed according to the peak value of the R wave, the first transition heartbeat signal at this time has two peak values. For example, the first first transition heartbeat signal has two peak position points A1 and A2.

[0108] The segmentation can be performed from the right R wave endpoint (A2) of the first reference heartbeat signal. Specifically, since the P wave signal in the heartbeat signal is needed as the subsequent PICC tip for positioning, the original features of the P wave signal need to be retained to the greatest extent. At this time, A2 is used as the center, 0.75 times the distance between A1A2 is used as the left part, and 0.25 times the distance between A2A3 is used as the right part for segmentation to obtain the first segmented signal. By performing segmentation in this way, k segmented signals can be obtained. Therefore, the original features of the P wave signal can be retained to the greatest extent in the segmented signals obtained by segmentation. In order to make the final signal complete and maintain the same length, the left and right sides of the segmented signal can be complemented separately. Here, 0 can be used for complementation to keep the scale of each segmented signal the same for subsequent processing.

[0109] A first matrix M is constructed, which is a trajectory matrix.

[0110] ,

[0111] Among them, Q1 is the position corresponding to A2, P is the reference length, specifically P is the product of 0.5 times the average interval length between the peaks and the correction factor, and the correction factor is a reference length correction factor set according to the state of the user to be detected during the detection to improve the adaptability. Each row in the first matrix corresponds to a segmentation signal. After constructing the first matrix M, singular value decomposition is performed to obtain the eigenvalues ​​and eigenvectors of the matrix, and finally the signal is reconstructed, the maximum singular value is selected as the signal value, and then the signal is reconstructed using a general singular value construction method to obtain a complete signal, and then the complete signal is split with k first forward voltage data points as periodic points to obtain k first reference heartbeat signals. Therefore, the above method can be used to reconstruct and split the signal to obtain k first reference heartbeat signals, which can filter out the noise in the initial in vivo ECG signal, improve the signal quality, and provide more accurate data support for subsequent fusion.

[0112] Similarly, the coordinates of the i-th second negative voltage data point can be marked as Bi (Bxi, Byi), and the above method of splitting the initial in vivo ECG signal according to the k first positive voltage data points can be used to obtain k second reference heart beat signals. Since the P wave signal is farther away from the S wave, in order to better retain the characteristics of the P wave signal during segmentation, the multiple on the left side can be 0.85 and the multiple on the right side can be 0.15. This can achieve the maximum retention of the original characteristics.

[0113] When the first reference heartbeat signal and the corresponding second reference heartbeat signal are fused, there will be a certain small fluctuation in the distance between the peak points of the R wave and the distance between the trough points of the S wave, and after the reconstruction and splitting, the reference base points are different, which will cause a certain deviation in the data between the split first reference heartbeat signal and the corresponding second reference heartbeat signal. In this case, the correlation characteristics between the R wave peak and the S wave trough can be combined to perform accurate segmentation, and the interference signal can also be filtered out to improve the accuracy. Specifically, the mean of the signal values ​​at the same time in the first reference heartbeat signal and the corresponding second reference heartbeat signal can be determined as the signal value of the corresponding initial heartbeat signal. The specifications of the initial heartbeat signal are the same as those of the first reference heartbeat signal. Since there is a certain non-overlapping part between the first first reference heartbeat signal and the corresponding first second reference heartbeat signal, the corresponding signal in the initial heartbeat signal at this time can directly adopt the value in the first initial heartbeat signal.

[0114] In one possible implementation, since the ECG signal will fluctuate to a certain extent, after the PICC tip moves to a certain position, it will be in a stationary state for the next movement. At this time, the fluctuation of the ECG signal may affect the accuracy of subsequent positioning. In order to solve the above problem, the features of multiple heartbeat signals can be fused in the present embodiment, and subsequent positioning processing can be performed based on the fused features, which can reduce the reduction in accuracy caused by fluctuations and improve the accuracy of subsequent positioning. Specifically: according to k R wave position information and k S wave position information, the k reference heartbeat signals are fused and processed to obtain the method of the ECG signal in the target body, including:

[0115] C1. Align k reference heart beat signals according to the corresponding R wave peak positions to obtain a first aligned signal set;

[0116] C2. Fusing the reference heartbeat signal in the first alignment signal set to obtain a first intermediate in-vivo ECG signal;

[0117] C3, aligning the k reference heartbeat signals according to the corresponding S wave trough positions to obtain a second aligned signal set;

[0118] C4, fusing the reference heartbeat signal in the second alignment signal set to obtain a second intermediate in-vivo ECG signal;

[0119] C5. Fusing the first intermediate in-vivo ECG signal and the second intermediate in-vivo ECG signal to obtain the target in-vivo ECG signal.

[0120] Among them, when processing it according to the peak position of the R wave, since the signal lengths between the reference heart beat signals will be different, the maximum length of the reference heart beat signal is used as the reference length, and the reference heart beat signal below this length is complemented, and the complementation at this time can be filled with 0.

[0121] Of course, in order to further improve the accuracy of fusion, when performing length alignment, the reference heartbeat signals can be clustered to obtain the central reference heartbeat signal of the cluster center, and the length of the reference heartbeat signal is determined as the reference length, and the length deviation value between other reference heartbeat signals and the central reference heartbeat signal is extracted. Preliminary filtering is performed based on the length deviation value, and the reference heartbeat signals with length deviation values ​​higher than the preset threshold are removed. A preliminary reference heartbeat signal set is obtained, and then the signals in the preliminary reference heartbeat signal set are subjected to length geometric interpolation processing to obtain heartbeat signals with consistent length after processing.

[0122] The heartbeat signals with the same length are fused to obtain a first intermediate in-vivo ECG signal. Specifically, the fusion may be performed by using a mean fusion method to obtain the first intermediate in-vivo ECG signal.

[0123] The method for processing k reference heartbeat signals according to the trough position of the S wave and subsequently fusing them to obtain the second intermediate in-vivo ECG signal can adopt the method for obtaining the first intermediate in-vivo ECG signal, which will not be repeated here. Due to the different centers, the specific data for scaling and interpolation processing will be different, so the trough position of the S wave and the peak position of the R wave are used. This is because when the PICC tip moves, the P wave will also have a negative signal, so the negative feature can be highlighted in the fused signal to improve accuracy.

[0124] Specifically, when the first intermediate in-vivo ECG signal and the second intermediate in-vivo ECG signal are fused to obtain the target in-vivo ECG signal, a weighted fusion method can be used for fusion processing, and the fusion processing is performed with the ratio of the second intermediate in-vivo ECG signal being higher than the ratio of the first intermediate in-vivo ECG signal. The specific ratio can be set by empirical values ​​or historical data, so that negative features can be more prominent in the fused signal to improve accuracy.

[0125] In one possible implementation, when using P-wave information to locate the tip of the PICC, the existing solution usually compares the P-wave information with the data stored in the database to obtain the corresponding position. However, due to individual differences between different users to be detected during positioning, direct positioning using the above method will result in certain deviations, resulting in reduced accuracy. In order to solve the above problem, the present application provides a method for locating the tip of the PICC using the P-wave information to obtain the target position information of the tip of the PICC in the cavity. The method can correct the position information in combination with the status information of the user to be detected to obtain the final target position information, so as to improve the accuracy of the target position information acquisition. The details are as follows:

[0126] D1. Extracting a P wave profile using the P wave information to obtain the P wave profile information;

[0127] D2. determining the reference position information of the PICC tip in the cavity according to the P wave profile information;

[0128] D3, obtaining the status information of the user to be detected;

[0129] D4. determining position correction information according to the state information;

[0130] D5. Use the position correction information to correct the reference position information to obtain the target position information.

[0131] The method for determining the reference position information of the PICC tip in the cavity using the P wave contour information can be: performing positioning processing based on the P wave contour information using a pre-trained positioning model to obtain the reference position information. The positioning model is trained by extracting user-authorized data that can be used for model training.

[0132] The status information of the user to be detected may include the heart rate fluctuation information of the user to be detected. The position correction information may be determined based on the heart rate fluctuation information. Since the heart rate fluctuation of the user to be detected may affect the contour of the P wave, etc., the position correction information may be determined based on the heart rate fluctuation information. Different heart rate fluctuation information corresponds to different position correction information.

[0133] Finally, the reference position information is corrected using the position correction information to obtain the target position information, which can improve the accuracy of obtaining the target position information.

[0134] For the above embodiments, please refer to Figure 3 , Figure 3 A schematic diagram of the structure of a terminal provided in an embodiment of the present application, such as Figure 3 As shown, it includes a processor, an input device, an output device and a memory, which are connected to each other, wherein the memory is used to store a computer program, the computer program includes program instructions, the processor is configured to call the program instructions, and the program includes instructions for executing the following steps;

[0135] Obtaining an initial in vivo electrocardiogram signal of the user to be detected;

[0136] Performing filtering and fusion processing on the initial in-vivo ECG signal to obtain a target in-vivo ECG signal;

[0137] Extracting P wave information from the target body's electrocardiogram signal;

[0138] The P wave information is used to perform positioning processing on the PICC tip to obtain target position information of the PICC tip in the cavity.

[0139] The above mainly introduces the scheme of the embodiment of the present application from the perspective of the execution process on the method side. It is understandable that in order to realize the above functions, the terminal includes a hardware structure and / or software module corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments provided herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0140] The embodiment of the present application can divide the terminal into functional units according to the above method example. For example, each functional unit can be divided according to each function, or two or more functions can be integrated into one processing unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. It should be noted that the division of units in the embodiment of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0141] In line with the above, see Figure 4 , Figure 4The present application provides a schematic diagram of a structure of an intracavity precise positioning device based on electrocardiogram signals. Figure 4 As shown, the device comprises:

[0142] An acquisition unit 301 is used to acquire an initial in-vivo ECG signal of a user to be detected;

[0143] The processing unit 302 is used to perform filtering and fusion processing on the initial in-vivo ECG signal to obtain a target in-vivo ECG signal;

[0144] An extraction unit 303 is used to extract P wave information from the target body's ECG signal;

[0145] The positioning unit 304 is used to use the P wave information to perform positioning processing on the PICC tip to obtain the target position information of the PICC tip in the cavity.

[0146] In a possible implementation, the processing unit 302 is specifically configured to:

[0147] Segmenting the initial in-vivo electrocardiogram signal to obtain k initial heart beat signals;

[0148] Performing filtering on the k initial heartbeat signals to obtain k reference heartbeat signals;

[0149] Performing R wave positioning processing on the k reference heartbeat signals to obtain k R wave position information, and performing S wave positioning processing on the k reference heartbeat signals to obtain k S wave position information;

[0150] The k reference heartbeat signals are fused according to the k R wave position information and the k S wave position information to obtain the target body's electrocardiogram signal.

[0151] In a possible implementation, in the aspect of segmenting the initial in-vivo electrocardiogram signal to obtain k initial heart beat signals, the processing unit 302 is specifically configured to:

[0152] Extracting k first positive voltage data points of the initial in vivo ECG signal, and extracting m first negative voltage data points of the initial in vivo ECG signal, the first positive voltage data point being a local maximum positive voltage point, and the first negative voltage data point being a local minimum negative voltage point;

[0153] Extracting k negative power data points from m first negative voltage data points according to the position information of the k first positive voltage data points to obtain k second negative voltage data points;

[0154] Using k first forward voltage data points to segment the initial in vivo electrocardiogram signal to obtain k first reference heart beat signals;

[0155] Using k second negative voltage data points to segment the initial in vivo electrocardiogram signal to obtain k second reference heart beat signals;

[0156] The k first reference heartbeat signals are fused with the corresponding second reference heartbeat signals to obtain k initial heartbeat signals.

[0157] In a possible implementation, in the aspect of fusing the k reference heartbeat signals according to the k R wave position information and the k S wave position information to obtain the target body electrocardiogram signal, the processing unit 302 is specifically used to:

[0158] Aligning k reference heart beat signals according to the corresponding R wave peak positions to obtain a first aligned signal set;

[0159] fusing the reference heartbeat signal in the first alignment signal set to obtain a first intermediate in-vivo ECG signal;

[0160] Aligning k reference heartbeat signals according to corresponding S wave trough positions to obtain a second aligned signal set;

[0161] fusing the reference heartbeat signal in the second alignment signal set to obtain a second intermediate in-vivo ECG signal;

[0162] The first intermediate in-vivo ECG signal and the second intermediate in-vivo ECG signal are fused to obtain the target in-vivo ECG signal.

[0163] In a possible implementation, the positioning unit 304 is specifically configured to:

[0164] Using the P wave information to extract the P wave profile, to obtain the P wave profile information;

[0165] Determine reference position information of the PICC tip in the cavity according to the P wave profile information;

[0166] Acquire status information of the user to be detected;

[0167] determining position correction information according to the state information;

[0168] The reference position information is corrected using the position correction information to obtain the target position information.

[0169] An embodiment of the present application also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program enables a computer to execute part or all of the steps of any one of the methods for precise intracavity positioning based on electrocardiogram signals as recorded in the above method embodiments.

[0170] An embodiment of the present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program enables a computer to execute part or all of the steps of any one of the methods for precise intracavity positioning based on electrocardiogram signals as recorded in the above method embodiments.

[0171] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0172] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0173] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the device or unit can be electrical or other forms.

[0174] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0175] In addition, the functional units in the various embodiments of the application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated units may be implemented in the form of hardware or in the form of software program modules.

[0176] If the integrated unit is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, disk or optical disk, etc., and other media that can store program codes.

[0177] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, which can include: a flash drive, a read-only memory, a random access memory, a magnetic disk or an optical disk, etc.

[0178] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A precise intracavity positioning device based on electrocardiogram signals, characterized in that: The device comprises: An acquisition unit, used for acquiring an initial in-vivo ECG signal of a user to be detected; A processing unit, configured to perform filtering and fusion processing on the initial in-vivo ECG signal to obtain a target in-vivo ECG signal; An extraction unit, used to extract P wave information from the target body's electrocardiogram signal; A positioning unit, used to perform positioning processing on the PICC tip using the P wave information to obtain target position information of the PICC tip in the cavity; The processing unit is specifically used for: Segmenting the initial in-vivo electrocardiogram signal to obtain k initial heart beat signals; Performing filtering on the k initial heartbeat signals to obtain k reference heartbeat signals; Performing R wave positioning processing on the k reference heartbeat signals to obtain k R wave position information, and performing S wave positioning processing on the k reference heartbeat signals to obtain k S wave position information; fusing the k reference heartbeat signals according to the k R wave position information and the k S wave position information to obtain the target body electrocardiogram signal; In the aspect of segmenting the initial in-vivo electrocardiogram signal to obtain k initial heartbeat signals, the processing unit is specifically used for: Extracting k first positive voltage data points of the initial in vivo ECG signal, and extracting m first negative voltage data points of the initial in vivo ECG signal, the first positive voltage data point being a local maximum positive voltage point, and the first negative voltage data point being a local minimum negative voltage point; Extracting k negative power data points from m first negative voltage data points according to the position information of the k first positive voltage data points to obtain k second negative voltage data points; Using k first forward voltage data points to segment the initial in vivo electrocardiogram signal to obtain k first reference heart beat signals; Using k second negative voltage data points to segment the initial in vivo electrocardiogram signal to obtain k second reference heart beat signals; The k first reference heartbeat signals are fused with the corresponding second reference heartbeat signals to obtain k initial heartbeat signals.

2. The intracavity precise positioning device based on electrocardiogram signals according to claim 1, characterized in that: In the aspect of fusing the k reference heartbeat signals according to the k R wave position information and the k S wave position information to obtain the target body electrocardiogram signal, the processing unit is specifically used for: Aligning k reference heart beat signals according to the corresponding R wave peak positions to obtain a first aligned signal set; fusing the reference heartbeat signal in the first alignment signal set to obtain a first intermediate in-vivo ECG signal; Aligning k reference heartbeat signals according to corresponding S wave trough positions to obtain a second aligned signal set; fusing the reference heartbeat signal in the second alignment signal set to obtain a second intermediate in-vivo ECG signal; The first intermediate in-vivo ECG signal and the second intermediate in-vivo ECG signal are fused to obtain the target in-vivo ECG signal.

3. The intracavity precise positioning device based on electrocardiogram signals according to claim 2, characterized in that: The positioning unit is specifically used for: Using the P wave information to extract the P wave profile, to obtain the P wave profile information; Determine reference position information of the PICC tip in the cavity according to the P wave profile information; Acquire status information of the user to be detected; determining position correction information according to the state information; The reference position information is corrected using the position correction information to obtain the target position information.

Images