Leveraging an ECG Beat Diffusion Model for Morphological Reconstruction from Indirect Signals

Electrocardiogram (ECG) signals provide essential information about the heart's condition and are widely used for diagnosing cardiovascular diseases. The morphology of a single heartbeat over the available leads is a primary biosignal for monitoring cardiac conditions. However, analyzing heartbeat morphology can be challenging due to noise and artifacts, missing leads, and a lack of annotated data. Generative models, such as denoising diffusion generative models (DDMs), have proven successful in generating complex data. We introduce BeatDiff, a lightweight DDM tailored for the morphology of multiple leads heartbeats. We then show that many important ECG downstream tasks can be formulated as conditional generation methods in a Bayesian inverse problem framework using BeatDiff as priors. We propose EM-BeatDiff, an Expectation-Maximization algorithm, to solve this conditional generation tasks without fine-tuning. We illustrate our results with several tasks, such as removal of ECG noise and artifacts (baseline wander, electrode motion), reconstruction of a 12-lead ECG from a single lead (useful for ECG reconstruction of smartwatch experiments), and unsupervised explainable anomaly detection. Experiments show that the combination of BeatDiff and EM-BeatDiff outperforms SOTA methods for the problems considered in this work.