AI-Powered Noninvasive Electrocardiographic Imaging Using the Priori-to-Attention Network (P2AN) for Wearable Health Monitoring DOI Creative Commons

Shijie He,

Hanrui Dong,

Xianbin Zhang

и другие.

Sensors, Год журнала: 2025, Номер 25(6), С. 1810 - 1810

Опубликована: Март 14, 2025

The rapid development of smart wearable devices has significantly advanced noninvasive, continuous health monitoring, enabling real-time collection vital biosignals. Electrocardiographic imaging (ECGI), a noninvasive technique that reconstructs transmembrane potential (TMP) from body surface potential, emerged as promising method for reflecting cardiac electrical activity. However, the ECG inverse problem’s inherent instability hindered its practical application. To address this, we introduce novel Priori-to-Attention Network (P2AN) enhances stability ECGI solutions. By leveraging one-dimensional nature signals and body’s propagation properties, P2AN uses small-scale convolutions attention computation, integrating priori physiological knowledge via cross-attention mechanisms. This approach eliminates need clinical TMP measurements improves solution accuracy through normalization constraints. We evaluate method’s effectiveness in diagnosing myocardial ischemia ventricular hypertrophy, demonstrating significant improvements reconstruction lesion localization. Moreover, exhibits high robustness noisy environments, making it highly suitable integration with electrocardiographic clothing. improving spatiotemporal noise resilience, offers cardiovascular monitoring using AI-powered devices.

Язык: Английский

AI-Powered Noninvasive Electrocardiographic Imaging Using the Priori-to-Attention Network (P2AN) for Wearable Health Monitoring DOI Creative Commons

Shijie He,

Hanrui Dong,

Xianbin Zhang

и другие.

Sensors, Год журнала: 2025, Номер 25(6), С. 1810 - 1810

Опубликована: Март 14, 2025

The rapid development of smart wearable devices has significantly advanced noninvasive, continuous health monitoring, enabling real-time collection vital biosignals. Electrocardiographic imaging (ECGI), a noninvasive technique that reconstructs transmembrane potential (TMP) from body surface potential, emerged as promising method for reflecting cardiac electrical activity. However, the ECG inverse problem’s inherent instability hindered its practical application. To address this, we introduce novel Priori-to-Attention Network (P2AN) enhances stability ECGI solutions. By leveraging one-dimensional nature signals and body’s propagation properties, P2AN uses small-scale convolutions attention computation, integrating priori physiological knowledge via cross-attention mechanisms. This approach eliminates need clinical TMP measurements improves solution accuracy through normalization constraints. We evaluate method’s effectiveness in diagnosing myocardial ischemia ventricular hypertrophy, demonstrating significant improvements reconstruction lesion localization. Moreover, exhibits high robustness noisy environments, making it highly suitable integration with electrocardiographic clothing. improving spatiotemporal noise resilience, offers cardiovascular monitoring using AI-powered devices.

Язык: Английский

Процитировано

0