Canine Electrocardiogram
Canine electrocardiogram (ECG) analysis focuses on developing automated methods for interpreting ECG signals from dogs, aiming to improve diagnostic accuracy and efficiency in veterinary cardiology. Current research heavily utilizes deep learning models, including convolutional neural networks and various self-supervised learning approaches, to classify arrhythmias, predict mortality risk, and even estimate other physiological parameters like blood pressure using multimodal data (ECG and other biosignals). These advancements hold significant promise for enhancing veterinary care by providing faster, more accessible, and potentially more accurate diagnoses, particularly in areas with limited access to veterinary specialists.
Papers
TSRNet: Simple Framework for Real-time ECG Anomaly Detection with Multimodal Time and Spectrogram Restoration Network
Nhat-Tan Bui, Dinh-Hieu Hoang, Thinh Phan, Minh-Triet Tran, Brijesh Patel, Donald Adjeroh, Ngan Le
Probabilistic learning of the Purkinje network from the electrocardiogram
Felipe Álvarez-Barrientos, Mariana Salinas-Camus, Simone Pezzuto, Francisco Sahli Costabal