Noise reduction of intracardiac electrocardiograms using autoencoders, and utilization and refinement of intracardiac and surface electrocardiograms using deep learning training loss functions.

The use of a denoising autoencoder and deep learning training loss functions refines ECGs to reduce noise and artifacts, improving cardiac mapping and treatment accuracy by highlighting clinically important zones, thus addressing the limitations of current ECG-based cardiac disease identification.

JP7841680B2Active Publication Date: 2026-04-07BIOSENSE WEBSTER (ISRAEL) LTD
3 Cites 0 Cited by

Patent Information

Application Number
JP2021094238
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Priority Date
2021-06-02
Filing Date
2021-06-04
Publication Date
2026-04-07
Estimated Expiration
2041-06-04

AI Technical Summary

Technical Problem

Current methods for treating cardiac diseases using electrocardiograms (ECGs) are hindered by noise and artifacts in electrical signals, which can obscure the identification of clinically important zones or events, such as potential origins of cardiac disease.

Method used

A system utilizing a denoising autoencoder and deep learning training loss functions to refine intracardiac and surface electrocardiograms, applying filters and energy thresholds to enhance signal clarity and highlight clinically significant areas, thereby improving the accuracy of cardiac mapping and treatment.

Benefits of technology

The system significantly reduces noise in ECGs, enabling precise identification of cardiac disease origins and facilitating more accurate cardiac procedures by generating improved ECGs and intracardiac ECGs, enhancing the reliability of cardiac treatment.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

To provide a system and a method for reducing noise of intracardiac electrocardiograms using an autoencoder and for utilizing and refining intracardiac and body surface electrocardiograms using one or more deep learning training loss functions.SOLUTION: A system and a method include a memory storing a processor-executable code for a denoised autoencoder, and one or more processors coupled to the memory. The processors execute the processor-executable code to receive raw signal data comprising signal noise, encode, by the denoised autoencoder, the raw signal data by performing a denoising autoencoder operation to produce a latent representation, and decode, by the denoised autoencoder, the latent representation to produce clean signal data reconstructed without the signal noise.SELECTED DRAWING: Figure 1
Need to check novelty before this filing date? Find Prior Art