Electrocardiogram (ECG) signal detection and positioning method based on weakly supervised learning

US12279875B2 · kind B2 · utility

Assignees

• QILU UNIVERSITY OF TECHNOLOGY (SHANDONG ACADEMY OF SCIENCES) · CN
• SHANDONG COMPUTER SCIENCE CENTER (NATIONAL SUPERCOMPUTER CENTER IN JINAN) · CN

Inventors

• Minglei SHU · Jinan, CN
• Pengyao XU · Jinan, CN
• Shuwang ZHOU · Jinan, CN
• Zhaoyang LIU · Jinan, CN
• Kaiwei Li · 红钢城街道, CN

Key dates

• Filing date: Dec 14, 2023
• Grant date: Apr 22, 2025
• Expiry date: Dec 14, 2043

Classification

• Technology area (CPC Y): Emerging Cross-Sectional Technologies
• CPC primary: Y02A90/10
• WIPO field: Medical technology
• WIPO sector: Instruments

Abstract

An electrocardiograph (ECG) signal detection and positioning method based on weakly supervised learning is provided. A deep learning model mainly includes a multi-scale feature extraction module, a self-attention encoding module, and a classification and positioning module. An extracted original ECG signal is denoised and segmented to obtain a fixed-length pure ECG signal segment. In the convolutionally-connected multi-scale feature extraction module, a channel local attention (CLA) layer is introduced, and a PReLU activation function is used to achieve a better local information extraction capability. The self-attention encoding module is introduced to establish an association between a local feature and a global feature. The classification and positioning module is introduced to output a general location of an abnormal signal. A fusion module enables the model to map a local predicted value onto a global predicted value, and model parameters are trained on a weakly annotated dataset.