Intracardiac abnormal excitation point positioning model construction method based on CNN and LSTM

Abstract

The invention discloses an intracardiac abnormal activation point positioning model construction method based on CNN and LSTM, and the model can achieve the good positioning of the specific position of a VT abnormal activation point under the condition that the 12-lead body surface potential data of a patient is obtained, and obtains the three-dimensional coordinates of the position. According tothe invention, the idea of deep learning is introduced into ventricular tachycardia abnormal excitation point positioning; in the training stage, the collected QRS data is used as input; the three-dimensional coordinates of the QRS data corresponding to the mapping points are taken as labels to train a CNN-LSTM network, feature extraction is performed on the input data by using Conv1D, feature fusion is performed on a time domain by using LSTM, regression prediction is performed on the three-dimensional coordinates by using a full connection layer, and finally the CNN-LSTM network is constructed. According to the network model, the position prediction of the VT abnormal activation point is realized from the perspective of data driving, and the time-consuming and labor-consuming problems ofcatheter ablation in clinic are effectively solved.

Description

technical field [0001] The invention belongs to the technical field of cardiac electrophysiological analysis, and in particular relates to a method for constructing a localization model of an intracardiac abnormal activation point based on CNN and LSTM. Background technique [0002] Machine learning is the product of the development of artificial intelligence. To make a machine intelligent, it must be endowed with the ability to learn. For machines, real life is a huge data set full of various data. What machine learning needs to do The goal is to reveal the true meaning behind the data and be able to make accurate predictions. The mainstream machine learning methods mainly rely on statistics, use massive data to extract valuable information for learning, and establish a model for judgment and prediction. Recently, with the improvement of computer performance, the deep learning method represented by the neural network can use the gradient descent method to iteratively updat...

AI Technical Summary

Problems solved by technology

[0005] Although the current clinical diagnosis of ventricular tachycardia is mainly based on the 12-lead electrocardiogram, such a method can only make a preliminary diagnosis of VT and determine whether it is suffering from ventricular tachycardia and other diseases, and cannot provide information such as the occurrence of tachycardia. More detailed information such as the specific location of

On the other hand, in the clinical treatment of VT, we need catheter ablation to treat the lesion at a fixed point; at present, surgeons need to use invasive means to directly measure the electrophysiological activity of the target location of the heart, and to detect abnormalities in VT. However, the invasive pacing mapping method is not efficient, time-consuming and laborious, and has certain risks

Images