A cardiac radiofrequency ablation steady-state monitoring method and system

Abstract

The present invention discloses a cardiac radiofrequency ablation steady-state monitoring method and system, which relates to the field of ablation monitoring technology. The method includes: obtaining an ablation catheter, a sensor array interactively connected to the ablation catheter, extracting monitoring data of the sensor array in a preset monitoring window, obtaining a temperature-impedance monitoring data sequence and a current monitoring data sequence; obtaining a temperature-impedance monitoring data feature set; obtaining a temperature-impedance monitoring data deviation coefficient; obtaining a current monitoring stability coefficient; according to the size of the temperature-impedance monitoring data deviation coefficient and the current monitoring stability coefficient, feedback updating the preset monitoring window, obtaining an updated monitoring window, and performing cardiac radiofrequency ablation steady-state monitoring based on the updated monitoring window. The present invention solves the technical problems in the prior art that the cardiac radiofrequency ablation steady-state monitoring has a low fit with the actual situation and a delayed response, and achieves the technical effect of improving the reliability of steady-state monitoring.

Description

Technical Field

[0001] The present invention relates to the technical field of ablation monitoring, and in particular to a cardiac radiofrequency ablation steady-state monitoring method and system. Background Art

[0002] Cardiac radiofrequency ablation is a technology widely used to treat arrhythmias, especially common cardiac electrophysiological diseases such as atrial fibrillation and premature atrial contractions. Radiofrequency ablation transmits radiofrequency energy to the area of ​​cardiac lesions through a catheter to achieve the purpose of ablating abnormal cardiac tissue. At present, fixed monitoring windows are mostly used for data collection, and the monitoring window cannot be adaptively adjusted according to the dynamic changes of the ablation process, resulting in the inability to effectively capture sudden changes during the ablation process.

[0003] The existing technology has technical problems such as low fit between steady-state monitoring of cardiac radiofrequency ablation and actual conditions and delayed response. Summary of the invention

[0004] The present application provides a cardiac radiofrequency ablation steady-state monitoring method and system, which are used to solve the technical problems in the prior art that the cardiac radiofrequency ablation steady-state monitoring has a low degree of fit with the actual situation and a delayed response.

[0005] In view of the above problems, the present application provides a method and system for steady-state monitoring of cardiac radiofrequency ablation.

[0006] In a first aspect of the present application, a method for steady-state monitoring of cardiac radiofrequency ablation is provided, the method comprising: Acquire an ablation catheter, interact with a sensor array connected to the ablation catheter, extract monitoring data of the sensor array within a preset monitoring window, and obtain a temperature-impedance monitoring data sequence and a current monitoring data sequence, wherein the ablation catheter is used for performing cardiac radiofrequency ablation; Based on the receptive field random generator, multiple data random generation is performed to obtain a receptive field set, and a data feature analyzer set is constructed based on the receptive field set, and the data feature analyzer set is used to extract data from the temperature-impedance monitoring data sequence respectively to obtain a temperature-impedance monitoring data feature set; Using preset temperature-impedance monitoring data standard features, feature deviation identification is performed on the temperature-impedance monitoring data feature set to obtain a temperature-impedance monitoring data deviation coefficient; Traversing the current monitoring data sequence to perform current monitoring stability identification and obtain a current monitoring stability coefficient; According to the temperature-impedance monitoring data deviation coefficient and the current monitoring stability coefficient, the preset monitoring window is feedback updated to obtain an updated monitoring window, and cardiac radiofrequency ablation steady-state monitoring is performed based on the updated monitoring window.

[0007] A second aspect of the present application provides a cardiac radiofrequency ablation steady-state monitoring system, the system comprising: A data sequence acquisition module, used to acquire an ablation catheter, interact with a sensor array connected to the ablation catheter, extract monitoring data of the sensor array within a preset monitoring window, and obtain a temperature-impedance monitoring data sequence and a current monitoring data sequence, wherein the ablation catheter is used for performing cardiac radiofrequency ablation; A monitoring data feature set acquisition module is used to perform multiple random data generation based on a receptive field random generator to obtain a receptive field set, and to construct a data feature analyzer set based on the receptive field set, and to use the data feature analyzer set to extract data from the temperature-impedance monitoring data sequence to obtain a temperature-impedance monitoring data feature set; A data deviation coefficient obtaining module is used to use preset temperature-impedance monitoring data standard features to perform feature deviation identification on the temperature-impedance monitoring data feature set to obtain the temperature-impedance monitoring data deviation coefficient; A current monitoring stability coefficient obtaining module, used for traversing the current monitoring data sequence to perform current monitoring stability identification and obtain a current monitoring stability coefficient; The steady-state monitoring module is used to feedback update the preset monitoring window according to the size of the temperature-impedance monitoring data deviation coefficient and the current monitoring stability coefficient, obtain an updated monitoring window, and perform steady-state monitoring of cardiac radiofrequency ablation based on the updated monitoring window.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages: The present application obtains the ablation catheter, interacts with the sensor array connected to the ablation catheter, extracts the monitoring data of the sensor array in the preset monitoring window, obtains the temperature-impedance monitoring data sequence and the current monitoring data sequence, wherein the ablation catheter is used for cardiac radiofrequency ablation, then performs multiple data random generation based on the receptive field random generator, obtains the receptive field set, and constructs a data feature analyzer set based on the receptive field set, uses the data feature analyzer set to extract data from the temperature-impedance monitoring data sequence, obtains the temperature-impedance monitoring data feature set, and then uses the preset temperature-impedance monitoring data standard feature to perform feature deviation identification on the temperature-impedance monitoring data feature set, obtains the temperature-impedance monitoring data deviation coefficient, and then traverses the current monitoring data sequence to identify the current monitoring stability, obtains the current monitoring stability coefficient, and according to the size of the temperature-impedance monitoring data deviation coefficient and the current monitoring stability coefficient, the preset monitoring window is fed back and updated to obtain the updated monitoring window, and the steady-state monitoring of cardiac radiofrequency ablation is performed based on the updated monitoring window. The technical effect of improving the reliability of steady-state monitoring is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0010] Figure 1 A schematic flow chart of a cardiac radiofrequency ablation steady-state monitoring method provided in an embodiment of the present application; Figure 2 A schematic diagram of the structure of a cardiac radiofrequency ablation steady-state monitoring system provided in an embodiment of the present application.

[0011] Explanation of the reference numerals: data sequence acquisition module 11 , monitoring data feature set acquisition module 12 , data deviation coefficient acquisition module 13 , current monitoring stability coefficient acquisition module 14 , steady-state monitoring module 15 . DETAILED DESCRIPTION

[0012] The present application provides a cardiac radiofrequency ablation steady-state monitoring method and system, which are used to solve the technical problems in the prior art that the cardiac radiofrequency ablation steady-state monitoring has a low degree of fit with the actual situation and a delayed response.

[0013] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings 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.

[0014] It should be noted that the terms "including" and "having" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or inherent to these processes, methods, products or devices.

[0015] Embodiment 1 like Figure 1 As shown, the present application provides a method for steady-state monitoring of cardiac radiofrequency ablation, wherein the method comprises: Step S100: obtaining an ablation catheter, interacting with a sensor array connected to the ablation catheter, extracting monitoring data of the sensor array within a preset monitoring window, and obtaining a temperature-impedance monitoring data sequence and a current monitoring data sequence, wherein the ablation catheter is used for performing cardiac radiofrequency ablation; In one possible embodiment, the ablation catheter is a medical device used for cardiac radiofrequency ablation treatment. It usually has a slender and soft structure, and transmits radiofrequency energy to the area of ​​cardiac lesions through the catheter tip to perform tissue ablation treatment. The catheter is generally equipped with multiple sensors for real-time monitoring of parameters such as temperature, impedance, and current during the ablation process to ensure the accuracy and safety of the treatment. The sensor array refers to multiple sensors connected to the ablation catheter, which are used to monitor different physiological signals in the heart in real time. Common sensors include temperature sensors, impedance sensors, current sensors, etc. Through these sensors, the ablation process can be carefully monitored to provide comprehensive data on the state of cardiac tissue.

[0016] The preset monitoring window refers to a specific time period or data collection interval for collecting sensor data. During the ablation process, by selecting an appropriate monitoring window, data of key parameters such as temperature, impedance and current can be collected in real time as needed, and analyzed later. The temperature-impedance monitoring data sequence refers to the continuous data of temperature and impedance collected by the sensor array within the preset monitoring window. These data sequences help evaluate the contact between the ablation catheter and the heart tissue and the thermal effect of the ablation process. The current monitoring data sequence refers to the time series data recording the ablation catheter current. By monitoring the changes in current, we can further understand the contact stability between the catheter tip and the heart tissue, as well as the transfer efficiency of radio frequency energy.

[0017] The ablation catheter is connected and interacted with the relevant sensor array so that various monitoring data can be transmitted in real time. These sensors will continuously obtain temperature, impedance and current data during ablation treatment. Then, within the preset monitoring window, the sensor array is extracted to obtain data after continuous monitoring of multiple key parameters, and the temperature-impedance monitoring data sequence and the current monitoring data sequence are obtained. These data will be used for further analysis to evaluate the steady-state and dynamic changes during the ablation process. The technical effect of providing reliable data support for subsequent analysis has been achieved.

[0018] Step S200: performing multiple random data generation based on a receptive field random generator to obtain a receptive field set, and constructing a data feature analyzer set based on the receptive field set, and using the data feature analyzer set to extract data from the temperature-impedance monitoring data sequence to obtain a temperature-impedance monitoring data feature set; Furthermore, step S200 of the embodiment of the present application further includes: Construct a receptive field random generator, wherein the receptive field random generator includes a receptive field random generation function, and the receptive field random generation function is: ; in, is the receptive field, , It follows a standard normal distribution. , is the Gamma function, .

[0019] Further, multiple data random generation is performed based on the receptive field random generator to obtain a receptive field set, and a data feature analyzer set is constructed based on the receptive field set, and the data feature analyzer set is used to extract data from the temperature-impedance monitoring data sequence to obtain a temperature-impedance monitoring data feature set. Step S200 of the embodiment of the present application also includes: Performing multiple random data generation based on the receptive field random generator to obtain an initial receptive field set; Combining the initial receptive fields in pairs, and performing similarity recognition on the combination results to obtain a similarity recognition result set; The initial receptive field set is distinguished and authenticated according to the similarity recognition result set, and if the authentication is passed, the initial receptive field set is used as the receptive field set.

[0020] Furthermore, step S200 of the embodiment of the present application further includes: Obtain Q sample temperature-impedance monitoring data sequences and corresponding Q sample temperature-impedance monitoring data features, where Q is an integer greater than or equal to 1; Randomly extracting a first receptive field from the receptive field set, and performing data segmentation on the Q sample temperature-impedance monitoring data sequences based on the size of the first receptive field to obtain a set of Q sample temperature-impedance monitoring data subsequences; Determine the number of nodes in the input layer based on the size of the first receptive field and the amount of indicator data of the temperature-impedance monitoring data, and configure the first input layer according to the number of nodes in the input layer; Using the Q sample temperature-impedance monitoring data subsequence sets and the Q sample temperature-impedance monitoring data features, a convolutional neural network including a first input layer, a fully connected layer, and an output layer is trained, and network parameters are updated according to the output during the training until the training converges, thereby obtaining a trained first data feature analyzer; The data feature analyzers are constructed in combination with the receptive field set, the Q sample temperature-impedance monitoring data sequences, and the Q sample temperature-impedance monitoring data features to obtain the data feature analyzer set.

[0021] In an embodiment of the present application, the receptive field random generator is a tool that generates different data ranges (or windows) based on a specific algorithm. It is used to generate multiple random data sets (receptive fields). Through these randomly generated receptive fields, data analysis can be performed at different scales to capture subtle changes in the ablation process. The data feature analyzer set is a set of functional models that perform data feature analysis based on the data extraction scale of the receptive field set, and is used to extract representative or judgment-meaningful features (such as mean, variance, peak, etc.) from the temperature-impedance monitoring data sequence. These features can help to analyze and identify the steady state of the ablation process later. The temperature-impedance monitoring data feature set reflects the changes in temperature and impedance during the ablation process within a preset monitoring window.

[0022] Preferably, the receptive field random generator is constructed using the receptive field random generation function, based on random parameters, such as those that obey a standard normal distribution. and obedience Distribution To generate receptive fields of different sizes, based on the The size of is used as a control variable to determine the randomness and variation of the receptive field. The receptive field random generator is used to perform multiple random generation to obtain the initial receptive field set. Each generated initial receptive field is used to capture dynamic features of different scales during the ablation process.

[0023] Then, the initial receptive fields are combined in pairs, and similarity recognition is performed on the combined results to obtain a similarity recognition result set. The similarity recognition result set reflects the degree of similarity between the initial receptive fields. The lower the similarity between the initial receptive fields, the higher the analysis quality. Therefore, the initial receptive field set is distinguished and authenticated based on the similarity recognition result set.

[0024] Optionally, the number of the similarity recognition result sets exceeding a preset similarity threshold (the maximum similarity preset by a person skilled in the art) is counted. If it is greater than or equal to the preset number, the authentication is passed. If the authentication is passed, the initial receptive field set is used as the receptive field set. If it is less than the preset number, the authentication does not need to be passed, and the receptive field is regenerated using the receptive field random generator. The technical effect of paving the way for multi-scale data analysis is achieved.

[0025] In one possible embodiment, Q sample temperature-impedance monitoring data sequences and corresponding Q sample temperature-impedance monitoring data features are obtained. A first receptive field is randomly extracted from the receptive field set, and the Q sample temperature-impedance monitoring data sequences are segmented based on the size of the first receptive field to obtain a set of Q sample temperature-impedance monitoring data subsequences. For example, when the size of the first receptive field is 5, the Q sample temperature-impedance monitoring data sequences are segmented into 5 data as a subsequence to obtain the set of Q sample temperature-impedance monitoring data subsequences.

[0026] The number of nodes in the input layer is determined according to the size of the first receptive field and the amount of indicator data of the temperature-impedance monitoring data. For example, when the size of the first receptive field is 5, the amount of indicator data of the temperature-impedance monitoring data is 2, and the indicators are temperature and impedance respectively. Therefore, the number of nodes in the input layer is 2×5=10. Configure the first input layer according to the number of nodes in the input layer. The first input layer is the first level of the neural network, which is used to receive a set of temperature-impedance monitoring data subsequences as input. In this step, the number of nodes in the input layer will be configured according to the results of the previous calculation to ensure that the input layer can correctly process the data subsequence.

[0027] The fully connected layer is used to extract high-level abstract features from the data. This layer is used to fuse the features extracted by convolution. The output layer is used to output the temperature-impedance monitoring data features. Using the Q sample temperature-impedance monitoring data subsequence sets and the Q sample temperature-impedance monitoring data features, a convolutional neural network including a first input layer, a fully connected layer, and an output layer is trained to learn the one-to-one correspondence between the temperature-impedance monitoring data features and the sample temperature-impedance monitoring data subsequence sets, and the network parameters are updated according to the output during training until the training converges, thereby obtaining a first data feature analyzer that has been trained.

[0028] Based on the same acquisition principle as that of the first data feature analyzer, the data feature analyzer is constructed in combination with the receptive field set, the Q sample temperature-impedance monitoring data sequences and the Q sample temperature-impedance monitoring data features, respectively, to obtain the data feature analyzer set. With the help of different receptive fields, a multi-scale analysis is performed from the temperature-impedance monitoring data sequence to extract important features, achieving the goal of providing basic data support for subsequent monitoring and steady-state analysis.

[0029] Step S300: using preset temperature-impedance monitoring data standard features, performing feature deviation identification on the temperature-impedance monitoring data feature set to obtain a temperature-impedance monitoring data deviation coefficient; Further, by using the preset temperature-impedance monitoring data standard features, the temperature-impedance monitoring data feature set is subjected to feature deviation identification to obtain the temperature-impedance monitoring data deviation coefficient. Step S300 of the embodiment of the present application further includes: Traversing and identifying the degree of feature deviation between the temperature-impedance monitoring data feature set and the preset temperature-impedance monitoring data standard feature, and obtaining a temperature-impedance monitoring data feature deviation degree set; Performing mean calculation on the characteristic deviation set of the temperature-impedance monitoring data to determine the characteristic deviation mean of the temperature-impedance monitoring data, with the characteristic deviation mean of the temperature-impedance monitoring data being the deviation center; The deviation center is updated and iterated based on a preset neighborhood radius until a preset iteration stop condition is met, and the temperature-impedance monitoring data characteristic deviation corresponding to the deviation center of the last iteration update is used as the temperature-impedance monitoring data characteristic deviation coefficient.

[0030] Furthermore, step S300 of the embodiment of the present application further includes: According to a preset neighborhood radius, a neighborhood is constructed for the deviation center to obtain a deviation mean neighborhood; Iteratively updating the deviation center based on the preset neighborhood radius to obtain an iterative deviation center, and constructing a deviation iterative neighborhood; Determine whether the difference in the number of neighborhood deviations between the deviation iteration neighborhood and the deviation mean neighborhood is less than or equal to a preset difference; if not, update the deviation iteration neighborhood to the deviation center, and continue to update and iterate until the preset iteration stop condition is met to obtain the temperature-impedance monitoring data characteristic deviation coefficient, wherein the preset iteration stop condition is that the number of iterations is greater than or equal to the preset number of iterations and / or the difference in the number of neighborhood deviations between two adjacent iterations is less than or equal to the preset difference.

[0031] In a possible embodiment, the preset temperature-impedance monitoring data standard feature is a characteristic condition of data when the ablation process is in a steady state, which is preset by a person skilled in the art. The temperature-impedance monitoring data deviation coefficient reflects the general degree of deviation of the temperature-impedance monitoring data feature set as a whole relative to the preset temperature-impedance monitoring data standard feature. By obtaining the temperature-impedance monitoring data deviation coefficient, the technical effect of providing reliable data for analyzing the steady state of the ablation process is achieved.

[0032] In one embodiment, based on the preset temperature-impedance monitoring data standard features, combined with the cosine similarity calculation formula, the similarity of the preset temperature-impedance monitoring data standard features and the temperature-impedance monitoring data feature set is calculated respectively, and the value of 1 minus the calculation result is used as the temperature-impedance monitoring data feature deviation, thereby obtaining the temperature-impedance monitoring data feature deviation set. By calculating the feature deviation, it is possible to effectively determine whether a significant change or instability has occurred in the ablation process.

[0033] Then, the mean value of the characteristic deviation degree set of the temperature-impedance monitoring data is calculated to determine the general characteristic deviation degree under the condition of considering the edge value and the accidental value, and the mean value of the characteristic deviation degree of the temperature-impedance monitoring data is obtained. Then, taking the mean value of the characteristic deviation degree of the temperature-impedance monitoring data as the deviation center, the update iteration is performed according to the preset neighborhood radius to determine the characteristic deviation degree of the temperature-impedance monitoring data that best represents the characteristic deviation degree set of the temperature-impedance monitoring data, and use it as the characteristic deviation coefficient of the temperature-impedance monitoring data.

[0034] Preferably, the deviation center is taken as the center of the circle and the preset neighborhood radius is taken as the neighborhood radius to construct a neighborhood to obtain a deviation from the mean neighborhood. Then, the deviation center is updated and iterated based on the preset neighborhood radius, that is, the deviation center is moved in any direction according to the preset neighborhood radius to obtain an iterative deviation center.

[0035] Based on the same construction principle as that for obtaining the deviation from the mean neighborhood, a deviation from the iteration neighborhood is obtained. Then, the number of neighborhood deviations in the deviation from the mean neighborhood and the deviation from the iteration neighborhood is counted respectively. The more the number of neighborhood deviations in each neighborhood, the more representative the corresponding deviation center is. It is determined whether the difference in the number of neighborhood deviations between the deviation from the iteration neighborhood and the deviation from the mean neighborhood is less than or equal to the preset difference. If not, it indicates that the iterative deviation center is more representative than the original deviation center. At this time, the deviation from the iteration neighborhood is updated to the deviation center, and the update iteration is continued until the preset iteration stop condition is met to obtain the characteristic deviation coefficient of the temperature-impedance monitoring data, wherein the preset iteration stop condition is that the number of iterations is greater than or equal to the preset number of iterations and / or the difference in the number of neighborhood deviations between two adjacent iterations is less than or equal to the preset difference.

[0036] If yes, it indicates that the original deviation from the center is more representative, and at this time, the mean deviation of the temperature-impedance monitoring data characteristics is used as the temperature-impedance monitoring data characteristic deviation coefficient. This achieves the technical effect of accurately identifying and quantifying the changing trend of the monitoring data during dynamic monitoring of the ablation process, providing an important basis for the adjustment and optimization of the ablation process.

[0037] Step S400: traversing the current monitoring data sequence to identify the current monitoring stability and obtain a current monitoring stability coefficient; Step S500: According to the temperature-impedance monitoring data deviation coefficient and the current monitoring stability coefficient, the preset monitoring window is feedback updated to obtain an updated monitoring window, and cardiac radiofrequency ablation steady-state monitoring is performed based on the updated monitoring window.

[0038] Furthermore, step S500 of the embodiment of the present application further includes: Performing weighted calculation on the temperature-impedance monitoring data deviation coefficient and the current monitoring stability coefficient to determine a window feedback adjustment coefficient; The preset monitoring window is feedback updated based on the window feedback adjustment coefficient to obtain the updated monitoring window.

[0039] In one possible embodiment, the fluctuation variance of the current monitoring data sequence is calculated, and the difference between the calculated result and 1 is used as the current monitoring stability coefficient. The current monitoring stability coefficient reflects the stability of the current monitoring data. The larger the coefficient, the higher the stability. In other words, the current monitoring stability coefficient is a measure of the stability of the current monitoring data, reflecting the stability of the current signal during the ablation process. Usually, the current signal should remain relatively stable under normal circumstances. If the current monitoring stability coefficient deviates from the normal range, it may indicate that the energy transmission during the ablation process is uneven or abnormal.

[0040] In one embodiment, the temperature-impedance monitoring data deviation coefficient and the current monitoring stability coefficient are weighted according to the weights pre-set by a person skilled in the art to obtain the window feedback adjustment coefficient, thereby comprehensively considering the impact of multiple factors on the monitoring window feedback adjustment to ensure the accuracy and effectiveness of the monitoring process. The monitoring window feedback adjustment coefficient determines how to adjust the range and sampling frequency of the monitoring window to ensure that key changes in the ablation process can be reflected in a timely manner. The adjusted monitoring window will be more adaptable to dynamic changes in the ablation process.

[0041] Preferably, multiple sample window feedback adjustment coefficients, multiple sample preset monitoring windows, and corresponding multiple sample update monitoring windows are obtained as training data, and supervised training is performed on the framework built based on the convolutional neural network. During the training, the two-to-one mapping relationship between the window feedback adjustment coefficient and the preset monitoring window and the update monitoring window is learned until the training converges, and a trained feedback update network is obtained. The feedback update network is used to perform feedback update on the preset monitoring window to obtain the updated monitoring window. The preset monitoring window is optimized according to the current state of the ablation process, and the capture and response to key changes are more rapid and accurate.

[0042] In summary, the embodiments of the present application have at least the following technical effects: This application introduces a receptive field random generator to perform multi-scale analysis on temperature-impedance monitoring data, which can evaluate the dynamic changes in the ablation process in real time, and then identify abnormal temperature and impedance deviations, and conduct a comprehensive analysis of the temperature-impedance monitoring data deviation coefficient and the current monitoring stability coefficient, which can effectively identify the potential degree of abnormality in the ablation process and adjust the monitoring window in time. The technical effect of comprehensively analyzing the steady-state characteristics of the ablation process and improving the reliability of steady-state monitoring of cardiac radiofrequency ablation has been achieved.

[0043] Embodiment 2 is based on the same inventive concept as the cardiac radiofrequency ablation steady-state monitoring method in the above embodiment. Figure 2 As shown, the present application provides a cardiac radiofrequency ablation steady-state monitoring system, and the system and method embodiments in the present application are based on the same inventive concept. The system includes: The data sequence acquisition module 11 is used to acquire an ablation catheter, interact with a sensor array connected to the ablation catheter, extract monitoring data of the sensor array within a preset monitoring window, and obtain a temperature-impedance monitoring data sequence and a current monitoring data sequence, wherein the ablation catheter is used for performing cardiac radiofrequency ablation; The monitoring data feature set acquisition module 12 is used to perform multiple random data generation based on the receptive field random generator to obtain a receptive field set, and to construct a data feature analyzer set based on the receptive field set, and to use the data feature analyzer set to extract data from the temperature-impedance monitoring data sequence respectively to obtain a temperature-impedance monitoring data feature set; The data deviation coefficient obtaining module 13 is used to use the preset temperature-impedance monitoring data standard features to perform feature deviation identification on the temperature-impedance monitoring data feature set to obtain the temperature-impedance monitoring data deviation coefficient; A current monitoring stability coefficient obtaining module 14 is used to traverse the current monitoring data sequence to perform current monitoring stability identification and obtain a current monitoring stability coefficient; The steady-state monitoring module 15 is used to feedback update the preset monitoring window according to the temperature-impedance monitoring data deviation coefficient and the current monitoring stability coefficient, obtain an updated monitoring window, and perform cardiac radiofrequency ablation steady-state monitoring based on the updated monitoring window.

[0044] Further, the method is used to perform the following steps: Construct a receptive field random generator, wherein the receptive field random generator includes a receptive field random generation function, and the receptive field random generation function is: ; in, is the receptive field, , It follows a standard normal distribution. , is the Gamma function, .

[0045] Further, the method is used to perform the following steps: Performing multiple random data generation based on the receptive field random generator to obtain an initial receptive field set; Combining the initial receptive fields in pairs, and performing similarity recognition on the combination results to obtain a similarity recognition result set; The initial receptive field set is distinguished and authenticated according to the similarity recognition result set, and if the authentication is passed, the initial receptive field set is used as the receptive field set.

[0046] Further, the method is used to perform the following steps: Obtain Q sample temperature-impedance monitoring data sequences and corresponding Q sample temperature-impedance monitoring data features, where Q is an integer greater than or equal to 1; Randomly extracting a first receptive field from the receptive field set, and performing data segmentation on the Q sample temperature-impedance monitoring data sequences based on the size of the first receptive field to obtain a set of Q sample temperature-impedance monitoring data subsequences; Determine the number of nodes in the input layer based on the size of the first receptive field and the amount of indicator data of the temperature-impedance monitoring data, and configure the first input layer according to the number of nodes in the input layer; Using the Q sample temperature-impedance monitoring data subsequence sets and the Q sample temperature-impedance monitoring data features, a convolutional neural network including a first input layer, a fully connected layer, and an output layer is trained, and network parameters are updated according to the output during the training until the training converges, thereby obtaining a trained first data feature analyzer; The data feature analyzers are constructed in combination with the receptive field set, the Q sample temperature-impedance monitoring data sequences, and the Q sample temperature-impedance monitoring data features to obtain the data feature analyzer set.

[0047] Further, the method is used to perform the following steps: Traversing and identifying the degree of feature deviation between the temperature-impedance monitoring data feature set and the preset temperature-impedance monitoring data standard feature, and obtaining a temperature-impedance monitoring data feature deviation degree set; Performing mean calculation on the characteristic deviation set of the temperature-impedance monitoring data to determine the characteristic deviation mean of the temperature-impedance monitoring data, with the characteristic deviation mean of the temperature-impedance monitoring data being the deviation center; The deviation center is updated and iterated based on a preset neighborhood radius until a preset iteration stop condition is met, and the temperature-impedance monitoring data characteristic deviation corresponding to the deviation center of the last iteration update is used as the temperature-impedance monitoring data characteristic deviation coefficient.

[0048] Further, the method is used to perform the following steps: According to a preset neighborhood radius, a neighborhood is constructed for the deviation center to obtain a deviation mean neighborhood; Iteratively updating the deviation center based on the preset neighborhood radius to obtain an iterative deviation center, and constructing a deviation iterative neighborhood; Determine whether the difference in the number of neighborhood deviations between the deviation iteration neighborhood and the deviation mean neighborhood is less than or equal to a preset difference; if not, update the deviation iteration neighborhood to the deviation center, and continue to update and iterate until the preset iteration stop condition is met to obtain the temperature-impedance monitoring data characteristic deviation coefficient, wherein the preset iteration stop condition is that the number of iterations is greater than or equal to the preset number of iterations and / or the difference in the number of neighborhood deviations between two adjacent iterations is less than or equal to the preset difference.

[0049] Further, the method is used to perform the following steps: Performing weighted calculation on the temperature-impedance monitoring data deviation coefficient and the current monitoring stability coefficient to determine a window feedback adjustment coefficient; The preset monitoring window is feedback updated based on the window feedback adjustment coefficient to obtain the updated monitoring window.

[0050] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0051] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0052] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A method for steady-state monitoring of cardiac radiofrequency ablation, characterized in that: The method comprises: Acquire an ablation catheter, interact with a sensor array connected to the ablation catheter, extract monitoring data of the sensor array within a preset monitoring window, and obtain a temperature-impedance monitoring data sequence and a current monitoring data sequence, wherein the ablation catheter is used for performing cardiac radiofrequency ablation; Based on the receptive field random generator, multiple data random generation is performed to obtain a receptive field set, and a data feature analyzer set is constructed based on the receptive field set, and the data feature analyzer set is used to extract data from the temperature-impedance monitoring data sequence respectively to obtain a temperature-impedance monitoring data feature set; Using preset temperature-impedance monitoring data standard features, feature deviation identification is performed on the temperature-impedance monitoring data feature set to obtain a temperature-impedance monitoring data deviation coefficient; Traversing the current monitoring data sequence to perform current monitoring stability identification and obtain a current monitoring stability coefficient; According to the temperature-impedance monitoring data deviation coefficient and the current monitoring stability coefficient, the preset monitoring window is feedback updated to obtain an updated monitoring window, and cardiac radiofrequency ablation steady-state monitoring is performed based on the updated monitoring window.

2. A cardiac radiofrequency ablation steady-state monitoring method as claimed in claim 1, characterized in that: include: Construct a receptive field random generator, wherein the receptive field random generator includes a receptive field random generation function, and the receptive field random generation function is: ； in, is the receptive field, , It follows a standard normal distribution. , is the Gamma function, .

3. A cardiac radiofrequency ablation steady-state monitoring method as claimed in claim 1, characterized in that: Based on the receptive field random generator, multiple data random generation is performed to obtain a receptive field set, and a data feature analyzer set is constructed based on the receptive field set. The data feature analyzer set is used to extract data from the temperature-impedance monitoring data sequence respectively to obtain a temperature-impedance monitoring data feature set, including: Performing multiple random data generation based on the receptive field random generator to obtain an initial receptive field set; Combining the initial receptive fields in pairs, and performing similarity recognition on the combination results to obtain a similarity recognition result set; The initial receptive field set is distinguished and authenticated according to the similarity recognition result set, and if the authentication is passed, the initial receptive field set is used as the receptive field set.

4. A cardiac radiofrequency ablation steady-state monitoring method as claimed in claim 3, characterized in that: include: Obtain Q sample temperature-impedance monitoring data sequences and corresponding Q sample temperature-impedance monitoring data features, where Q is an integer greater than or equal to 1; Randomly extracting a first receptive field from the receptive field set, and performing data segmentation on the Q sample temperature-impedance monitoring data sequences based on the size of the first receptive field to obtain a set of Q sample temperature-impedance monitoring data subsequences; Determine the number of nodes in the input layer based on the size of the first receptive field and the amount of indicator data of the temperature-impedance monitoring data, and configure the first input layer according to the number of nodes in the input layer; Using the Q sample temperature-impedance monitoring data subsequence sets and the Q sample temperature-impedance monitoring data features, a convolutional neural network including a first input layer, a fully connected layer, and an output layer is trained, and network parameters are updated according to the output during the training until the training converges, thereby obtaining a trained first data feature analyzer; The data feature analyzers are constructed in combination with the receptive field set, the Q sample temperature-impedance monitoring data sequences, and the Q sample temperature-impedance monitoring data features to obtain the data feature analyzer set.

5. A cardiac radiofrequency ablation steady-state monitoring method as claimed in claim 1, characterized in that: Using the preset temperature-impedance monitoring data standard features, the temperature-impedance monitoring data feature set is subjected to feature deviation identification to obtain the temperature-impedance monitoring data deviation coefficient, including: Traversing and identifying the degree of feature deviation between the temperature-impedance monitoring data feature set and the preset temperature-impedance monitoring data standard feature, and obtaining a temperature-impedance monitoring data feature deviation degree set; Performing mean calculation on the characteristic deviation set of the temperature-impedance monitoring data to determine the characteristic deviation mean of the temperature-impedance monitoring data, with the characteristic deviation mean of the temperature-impedance monitoring data being the deviation center; The deviation center is updated and iterated based on a preset neighborhood radius until a preset iteration stop condition is met, and the temperature-impedance monitoring data characteristic deviation corresponding to the deviation center of the last iteration update is used as the temperature-impedance monitoring data characteristic deviation coefficient.

6. A cardiac radiofrequency ablation steady-state monitoring method as claimed in claim 5, characterized in that: include: According to a preset neighborhood radius, a neighborhood is constructed for the deviation center to obtain a deviation mean neighborhood; Iteratively updating the deviation center based on the preset neighborhood radius to obtain an iterative deviation center, and constructing a deviation iterative neighborhood; Determine whether the difference in the number of neighborhood deviations between the deviation iteration neighborhood and the deviation mean neighborhood is less than or equal to a preset difference; if not, update the deviation iteration neighborhood to the deviation center, and continue to update and iterate until the preset iteration stop condition is met to obtain the temperature-impedance monitoring data characteristic deviation coefficient, wherein the preset iteration stop condition is that the number of iterations is greater than or equal to the preset number of iterations and / or the difference in the number of neighborhood deviations between two adjacent iterations is less than or equal to the preset difference.

7. A cardiac radiofrequency ablation steady-state monitoring method as claimed in claim 1, characterized in that: include: Performing weighted calculation on the temperature-impedance monitoring data deviation coefficient and the current monitoring stability coefficient to determine a window feedback adjustment coefficient; The preset monitoring window is feedback updated based on the window feedback adjustment coefficient to obtain the updated monitoring window.

8. A cardiac radiofrequency ablation steady-state monitoring system, characterized in that: The system is used to implement a cardiac radiofrequency ablation steady-state monitoring method according to any one of claims 1 to 7, and the system comprises: A data sequence acquisition module, used to acquire an ablation catheter, interact with a sensor array connected to the ablation catheter, extract monitoring data of the sensor array within a preset monitoring window, and obtain a temperature-impedance monitoring data sequence and a current monitoring data sequence, wherein the ablation catheter is used for performing cardiac radiofrequency ablation; A monitoring data feature set acquisition module is used to perform multiple random data generation based on a receptive field random generator to obtain a receptive field set, and to construct a data feature analyzer set based on the receptive field set, and to use the data feature analyzer set to extract data from the temperature-impedance monitoring data sequence to obtain a temperature-impedance monitoring data feature set; A data deviation coefficient obtaining module is used to use preset temperature-impedance monitoring data standard features to perform feature deviation identification on the temperature-impedance monitoring data feature set to obtain the temperature-impedance monitoring data deviation coefficient; A current monitoring stability coefficient obtaining module, used for traversing the current monitoring data sequence to perform current monitoring stability identification and obtain a current monitoring stability coefficient; The steady-state monitoring module is used to feedback update the preset monitoring window according to the size of the temperature-impedance monitoring data deviation coefficient and the current monitoring stability coefficient, obtain an updated monitoring window, and perform steady-state monitoring of cardiac radiofrequency ablation based on the updated monitoring window.

Images