An advanced vision of magnetocardiography as an unrivalled method for a more comprehensive non-invasive clinical electrophysiological assessment DOI Creative Commons
Riccardo Fenici,

M Picerni,

Peter Fenici

и другие.

American Heart Journal Plus Cardiology Research and Practice, Год журнала: 2025, Номер 52, С. 100514 - 100514

Опубликована: Фев. 23, 2025

Язык: Английский

The magnetocardiogram DOI Creative Commons
Bradley J. Roth

Biophysics Reviews, Год журнала: 2024, Номер 5(2)

Опубликована: Май 29, 2024

The magnetic field produced by the heart's electrical activity is called magnetocardiogram (MCG). first 20 years of MCG research established most concepts, instrumentation, and computational algorithms in field. Additional insights into fundamental mechanisms biomagnetism were gained studying isolated hearts or even pieces cardiac tissue. Much effort has gone calculating using computer models, including solving inverse problem deducing bioelectric sources from biomagnetic measurements. Recently, magnetocardiographic focused on clinical applications, driven part new technologies to measure weak fields.

Язык: Английский

Процитировано

5

AI-enabled diagnosis and localization of myocardial ischemia and coronary artery stenosis from magnetocardiographic recordings DOI Creative Commons
Rong Tao,

Shunlin Zhang,

Ruiyan Zhang

и другие.

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Фев. 19, 2025

Early diagnosis and localization of myocardial ischemia (MS) coronary artery stenosis (CAS) play a crucial role in the effective prevention management ischemic heart disease (IHD). Magnetocardiography (MCG) has emerged as promising approach for non-invasive, non-contact, high-sensitivity assessment cardiac dysfunction. This study presents multi-center, AI-enabled from MCG data. To this end, we collected large-scale dataset consisting 2,158 recordings eight clinical centers. We then proposed multiscale vision transformer-based network extracting spatio-temporal information multichannel recordings. Anatomical prior knowledge irrigated left ventricular regions was incorporated by carefully designed graph convolutional (GCN)-based feature fusion module. The achieved an accuracy 84.7%, sensitivity 83.8%, specificity 85.6% diagnosing IHD, average 78.4% five MS regions, 65.3% three arteries. Subsequent validation on independent 268 four centers demonstrated 82.3%, 81.3% 77.3% 65.6% can be used fast accurate tool, boosting integration examination into routine.

Язык: Английский

Процитировано

0

An advanced vision of magnetocardiography as an unrivalled method for a more comprehensive non-invasive clinical electrophysiological assessment DOI Creative Commons
Riccardo Fenici,

M Picerni,

Peter Fenici

и другие.

American Heart Journal Plus Cardiology Research and Practice, Год журнала: 2025, Номер 52, С. 100514 - 100514

Опубликована: Фев. 23, 2025

Язык: Английский

Процитировано

0