Non-local neural network myocardial transmembrane potential reconstruction method based on iterative shrinkage threshold algorithm

Abstract

The invention discloses a non-local neural network myocardial transmembrane potential reconstruction method based on an iterative shrinkage threshold algorithm. Through the fusion of a neural networkand a conventional optimization algorithm, and according to the non-local self-similarity of a transmembrane potential in space-time distribution, the invention designs a non-local feature extractionmodule; and an iterative shrinkage threshold algorithm optimization framework provides reliable theoretical explanation and convergence guarantee for the algorithm, the fusion of the neural network increases the flexibility and generalization performance of the method, and the addition of the non-local feature extraction module improves the performance of the network. Through the finally obtainedspace-time distribution of the myocardial transmembrane potential, the position and boundary of an infarction area during myocardial infarction, a pace-making point during ectopic pace-making and other areas with abnormal electrical activity can be accurately observed through three-dimensional display or waveform display, and the method has important reference significance in clinical diagnosis and treatment.

Description

technical field [0001] The invention belongs to the technical field of cardiac electrophysiological inversion, and in particular relates to a non-local neural network myocardial transmembrane potential reconstruction method based on an iterative contraction threshold algorithm. Background technique [0002] Heart disease is one of the biggest killers of human health. Cardiac arrhythmia may be life-threatening, and it is a disease with high morbidity and mortality worldwide. The prevention, diagnosis and treatment of heart disease have been a hot spot for scientists for a long time. The mechanical movement of the heart, such as the well-known heartbeat, is triggered by the propagation of electrical signals in the cardiomyocytes. Abnormalities in the propagation of electrical signals often lead to serious heart diseases, such as tachycardia, premature ventricular contractions, etc., and then It causes heart failure and is life-threatening, and some diseases caused by non-abnor...

AI Technical Summary

Problems solved by technology

[0004] Electrocardiogram imaging is a classic inverse problem that integrates regularization, optimization methods, and signal processing. Its ill-posedness mainly comes from the following aspects: (1) The dimensions of the known quantities do not match the dimensions of the unknown quantities. In order to achieve a certain Positioning accuracy, the number of unknown points representing the heart is usually far greater than the number of surface leads; (2) According to the equivalent double-layer principle of the Helmholtz electromagnetic field, there are infinitely many heart surface solutions mapped to the same surface electric field; (3) The high spatial frequency components are seriously attenuated in the process of mapping to the body surface, so they need to be amplified to reconstruct the corresponding source on the heart, so a slight disturbance on the body surface will have a great impact on the solution

Images