Enhancing AI-Based ECG Delineation with Deep Learning Denoising Techniques
For veterinary cardiology, this provides a preprocessing method to enhance ECG delineation accuracy, though it is an incremental application of existing denoising techniques to a new domain.
The paper addresses the challenge of noise in canine ECG analysis by proposing an autoencoder-based denoising model that improves signal quality for downstream delineation, demonstrating robustness across varying noise conditions.
Evaluating canine electrocardiograms (ECGs) is challenging due to noise that can obscure clinically relevant cardiac electrical activity. Common sources of interference include respiration, muscle activity, poor lead contact, and external electrical artifacts. Classical signal denoising techniques, such as filtering and wavelet-based methods, struggle to suppress diverse noise patterns while preserving morphological features critical for accurate ECG delineation. We propose an autoencoder-based neural network model and training strategy for ECG denoising as a preprocessing step for canine ECG analysis. The model is trained to reconstruct clean cardiac signals from noisy inputs, enabling effective noise reduction without degrading diagnostically important waveforms. Our approach demonstrates strong performance across both noisy and clean ECG recordings, indicating robustness to varying signal conditions and suitability for downstream delineation tasks.