Search

CN-122004884-A - Electrocardiosignal visualization method and related equipment

CN122004884ACN 122004884 ACN122004884 ACN 122004884ACN-122004884-A

Abstract

The application discloses an electrocardiosignal visualization method and related equipment, and relates to the field of electrocardiosignal analysis. The application obtains at least one body surface voltage characteristic vector at the target moment from an electrocardiogram, calls a configured potential estimation model, and processes each body surface voltage characteristic vector to obtain the heart surface electric excitation intensity distribution at each target moment. Rendering a heart three-dimensional model based on the heart surface electric excitation intensity distribution at each target moment to obtain a target heart three-dimensional model corresponding to each target moment. The application can display the target heart three-dimensional model in the state of cardiac electric excitation, is convenient for a user to intuitively observe the process from origin to conduction of cardiac electric excitation in the period of electrocardiograph detection, and judges abnormal electric excitation parts of the heart by combining with the diagnosis result of electrocardiograph.

Inventors

  • CHENG BINGHUI

Assignees

  • 蓬阳丰业(北京)医疗科技有限公司

Dates

Publication Date
20260512
Application Date
20260202

Claims (10)

  1. 1. An electrocardiographic signal visualization method, comprising: Acquiring at least one body surface voltage characteristic vector at a target moment from an electrocardiogram, wherein the body surface voltage characteristic vector is a set of voltage values of all waveforms in the electrocardiogram at the current moment; Invoking a configured potential prediction model, and processing each body surface voltage characteristic vector to obtain heart surface electric excitation intensity distribution at each target moment, wherein the heart surface electric excitation intensity distribution is a potential pre-estimated value of each network node on a pre-constructed heart three-dimensional model, and the potential prediction model is obtained by training according to body surface voltage characteristic vector sample data marked with the heart surface electric excitation intensity distribution; Rendering a heart three-dimensional model based on the heart surface electric excitation intensity distribution at each target moment to obtain a target heart three-dimensional model corresponding to each target moment.
  2. 2. The method of visualizing the cardiac signal as set forth in claim 1, wherein the process of rendering the three-dimensional model of the heart based on the cardiac surface electrical activation intensity distribution at each of the target moments to obtain a three-dimensional model of the target heart corresponding to each of the target moments comprises: according to the corresponding relation between the preset potential value interval and the RGB value, determining the RGB value corresponding to the potential predicted value of each network node; Rendering the heart three-dimensional model according to RGB values corresponding to the estimated potential values of all the network nodes corresponding to each target moment to obtain a target heart three-dimensional model corresponding to each target moment.
  3. 3. The method of visualizing an electrocardiograph signal according to claim 1, wherein the method further comprises: Under the condition that the number of the target moments is larger than 1, carrying out frequency domain analysis on potential pre-estimation values of each network node in all time periods of the target moments based on the heart surface electric excitation intensity distribution corresponding to all the target moments, so as to obtain excitation frequencies of each network node; rendering the pre-constructed heart three-dimensional model according to the activation frequency of each network node to obtain a three-dimensional model representing the heart surface activation frequency distribution.
  4. 4. The method of visualizing an electrocardiograph signal according to claim 1, wherein the method further comprises: determining a first cardiac electrical activity state of an electrocardiogram based on a target cardiac three-dimensional model corresponding to all moments in the electrocardiogram; And correcting the second heart electric activity state into the first heart electric activity state and using the electrocardiogram marked with the first heart electric activity state as sample data for updating an electrocardiogram identification model under the condition that the second heart electric activity state marked with the electrocardiogram corresponding to the electrocardiogram is different from the first heart electric activity state.
  5. 5. The method for visualizing an electrocardiograph signal according to claim 1, further comprising: And determining the target heart electric activity state of the electrocardiogram based on the target heart three-dimensional model corresponding to all the moments in the electrocardiogram, and outputting the target heart electric activity state.
  6. 6. The method of visualizing the cardiac signal in accordance with any one of claims 1-5, further comprising, prior to obtaining the body surface voltage feature vector for the at least one target time from the electrocardiogram: And responding to the selected operation of the user on at least one moment in the electrocardiogram, and taking each selected moment as a target moment.
  7. 7. The method for visualizing an cardiac signal as in any one of claims 1-5, further comprising: displaying a target heart three-dimensional model representing the heart electrical activation state at the target moment under the condition that the number of the target moments is 1; And under the condition that the number of the target moments is larger than 1, performing time sequence animation rendering on the target heart three-dimensional model corresponding to all the target moments to obtain and display three-dimensional dynamic demonstration animation representing the heart electric excitation state in the time period where all the target moments are located.
  8. 8. An electrocardiosignal visualization system is characterized by comprising a processor and a display terminal; The display terminal is used for displaying the electrocardiogram and the heart three-dimensional model, capturing the selected operation of a user on at least one moment in the electrocardiogram and transmitting the selected operation to the processor; The processor is used for responding to the selection operation, acquiring body surface voltage characteristic vectors at least at one time from an electrocardiogram, processing each body surface voltage characteristic vector according to the electrocardiosignal visualization method of any one of claims 1-7, obtaining a target heart three-dimensional model at each target time, and transmitting the target heart three-dimensional model to the display terminal.
  9. 9. An electronic device is characterized by comprising a memory and a processor; A memory for storing a program; A processor for executing a program for carrying out the steps of the method for visualizing cardiac signals as claimed in any one of claims 1 to 7.
  10. 10. A computer program product comprising a computer program which, when executed by a processor, implements the steps of the method of visualizing cardiac signals as claimed in any one of claims 1 to 7.

Description

Electrocardiosignal visualization method and related equipment Technical Field The application relates to the technical field of electrocardiosignal processing, in particular to an electrocardiosignal visualization method and related equipment. Background In the field of diagnosis of heart diseases, an electrocardiogram records the electric activity change of different parts of the heart in each cardiac cycle, and the electric activity change is presented in a waveform form, so that an important basis is provided for doctors to judge the health condition of the heart. However, conventional electrocardiographic analysis has certain limitations when faced with some complex cardiac disease diagnoses. For example, in atrial fibrillation diagnosis, normal heart activation has a specific conduction path and rhythm, and when atrial fibrillation occurs, rapid and irregular fibrillation occurs in each part of the atrium, but it is difficult to accurately determine the source part of atrial fibrillation from only a plurality of waveforms of an electrocardiogram. Disclosure of Invention In view of the foregoing, the present application has been made to provide an electrocardiographic signal visualization method and related apparatus for mapping an electrocardiogram to a three-dimensional model of a heart to accurately determine a source of an electrocardiographic abnormality. The specific scheme is as follows: In a first aspect, the present application provides an electrocardiographic signal visualization method, including: Acquiring at least one body surface voltage characteristic vector at a target moment from an electrocardiogram, wherein the body surface voltage characteristic vector is a set of voltage values of all waveforms in the electrocardiogram at the current moment; Invoking a configured potential prediction model, and processing each body surface voltage characteristic vector to obtain heart surface electric excitation intensity distribution at each target moment, wherein the heart surface electric excitation intensity distribution is a potential pre-estimated value of each network node on a pre-constructed heart three-dimensional model, and the potential prediction model is obtained by training according to body surface voltage characteristic vector sample data marked with the heart surface electric excitation intensity distribution; Rendering a heart three-dimensional model based on the heart surface electric excitation intensity distribution at each target moment to obtain a target heart three-dimensional model corresponding to each target moment. In another implementation manner of the first aspect of the embodiment of the present application, the process of rendering the three-dimensional heart model based on the electrical activation intensity distribution of the heart surface at each target time to obtain the three-dimensional heart model corresponding to each target time includes: according to the corresponding relation between the preset potential value interval and the RGB value, determining the RGB value corresponding to the potential predicted value of each network node; Rendering the heart three-dimensional model according to RGB values corresponding to the estimated potential values of all the network nodes corresponding to each target moment to obtain a target heart three-dimensional model corresponding to each target moment. In another implementation manner of the first aspect of the embodiment of the present application, in one possible design, the method further includes: Under the condition that the number of target moments is larger than 1, carrying out frequency domain analysis on potential pre-estimation values of each network node in all time periods of the target moments based on the heart surface electric excitation intensity distribution corresponding to all the target moments to obtain excitation frequencies of each network node; rendering the pre-constructed heart three-dimensional model according to the activation frequency of each network node to obtain a three-dimensional model representing the heart surface activation frequency distribution. In another implementation manner of the first aspect of the embodiment of the present application, in one possible design, the method further includes: determining a first cardiac electrical activity state of the electrocardiogram based on the target cardiac three-dimensional model corresponding to all moments in the electrocardiogram; and when the second heart electric activity state of the label corresponding to the electrocardiogram is different from the first heart electric activity state, correcting the second heart electric activity state into the first heart electric activity state, and taking the electrocardiogram labeled with the first heart electric activity state as sample data for updating an electrocardiogram identification model. In another implementation manner of the first aspect of the embodiment of the present applicat