Atrial Fibrillation
Atrial fibrillation (AF), an irregular heartbeat, is a prevalent cardiac arrhythmia posing significant health risks. Current research focuses on improving AF detection and risk stratification using diverse methods, including deep learning models (e.g., convolutional neural networks, recurrent neural networks, Siamese networks) applied to electrocardiograms (ECGs), photoplethysmography (PPG) signals, and medical images (e.g., LGE-MRI). These advancements aim to enhance diagnostic accuracy, enable continuous monitoring via wearable devices, and personalize treatment strategies, ultimately improving patient outcomes and reducing the burden of this serious condition. Improved image analysis techniques, such as advanced segmentation methods, are also contributing to a better understanding of atrial anatomy and its role in AF.
Papers
SiamAF: Learning Shared Information from ECG and PPG Signals for Robust Atrial Fibrillation Detection
Zhicheng Guo, Cheng Ding, Duc H. Do, Amit Shah, Randall J. Lee, Xiao Hu, Cynthia Rudin
Two-Stage Deep Learning Framework for Quality Assessment of Left Atrial Late Gadolinium Enhanced MRI Images
K M Arefeen Sultan, Benjamin Orkild, Alan Morris, Eugene Kholmovski, Erik Bieging, Eugene Kwan, Ravi Ranjan, Ed DiBella, Shireen Elhabian